diff --git a/coverage/d_145eef247bfb46b6___init___py.html b/coverage/d_145eef247bfb46b6___init___py.html
index 235e3a10..1791f236 100644
--- a/coverage/d_145eef247bfb46b6___init___py.html
+++ b/coverage/d_145eef247bfb46b6___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -89,7 +89,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_337e94e8243e179c_residualffn_models_py.html b/coverage/d_337e94e8243e179c_residualffn_models_py.html
index 1ffd31df..dc635628 100644
--- a/coverage/d_337e94e8243e179c_residualffn_models_py.html
+++ b/coverage/d_337e94e8243e179c_residualffn_models_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_337e94e8243e179c_residualffn_modules_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -140,7 +140,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_337e94e8243e179c_residualffn_modules_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_337e94e8243e179c_residualffn_modules_py.html b/coverage/d_337e94e8243e179c_residualffn_modules_py.html
index 076c7451..cf0f2c6a 100644
--- a/coverage/d_337e94e8243e179c_residualffn_modules_py.html
+++ b/coverage/d_337e94e8243e179c_residualffn_modules_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_modules_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -274,7 +274,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_modules_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3c6d3a4d2db9b72b___init___py.html b/coverage/d_3c6d3a4d2db9b72b___init___py.html
index a3349cc6..62757285 100644
--- a/coverage/d_3c6d3a4d2db9b72b___init___py.html
+++ b/coverage/d_3c6d3a4d2db9b72b___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_8e16ca04a866d040_lstnet_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -93,7 +93,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_8e16ca04a866d040_lstnet_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6___init___py.html b/coverage/d_3ccb7b6033502eb6___init___py.html
index eea2bc43..ff827707 100644
--- a/coverage/d_3ccb7b6033502eb6___init___py.html
+++ b/coverage/d_3ccb7b6033502eb6___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_aggregation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -106,7 +106,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_aggregation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_aggregation_py.html b/coverage/d_3ccb7b6033502eb6_aggregation_py.html
index 512afadd..84ba4306 100644
--- a/coverage/d_3ccb7b6033502eb6_aggregation_py.html
+++ b/coverage/d_3ccb7b6033502eb6_aggregation_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_cache_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -196,7 +196,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_cache_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_cache_azure_py.html b/coverage/d_3ccb7b6033502eb6_cache_azure_py.html
index ef190ec6..f8711d8d 100644
--- a/coverage/d_3ccb7b6033502eb6_cache_azure_py.html
+++ b/coverage/d_3ccb7b6033502eb6_cache_azure_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_cache_mysql_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -795,7 +795,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_cache_mysql_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_cache_mysql_py.html b/coverage/d_3ccb7b6033502eb6_cache_mysql_py.html
index d15df58f..23522183 100644
--- a/coverage/d_3ccb7b6033502eb6_cache_mysql_py.html
+++ b/coverage/d_3ccb7b6033502eb6_cache_mysql_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_datastruct_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -177,7 +177,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_datastruct_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_cache_py.html b/coverage/d_3ccb7b6033502eb6_cache_py.html
index 7ae85a14..f384f2fd 100644
--- a/coverage/d_3ccb7b6033502eb6_cache_py.html
+++ b/coverage/d_3ccb7b6033502eb6_cache_py.html
@@ -54,9 +54,9 @@ <h1>
             </div>
         </aside>
         <h2>
-            <span class="text">433 statements &nbsp;</span>
+            <span class="text">434 statements &nbsp;</span>
             <button type="button" class="run button_toggle_run" value="run" data-shortcut="r" title="Toggle lines run">112<span class="text"> run</span></button>
-            <button type="button" class="mis show_mis button_toggle_mis" value="mis" data-shortcut="m" title="Toggle lines missing">321<span class="text"> missing</span></button>
+            <button type="button" class="mis show_mis button_toggle_mis" value="mis" data-shortcut="m" title="Toggle lines missing">322<span class="text"> missing</span></button>
             <button type="button" class="exc show_exc button_toggle_exc" value="exc" data-shortcut="x" title="Toggle lines excluded">0<span class="text"> excluded</span></button>
         </h2>
         <p class="text">
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_cache_azure_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -793,81 +793,83 @@ <h2>
     <p class="pln"><span class="n"><a id="t711" href="#t711">711</a></span><span class="t"><span class="str">    :param load: whether to load a previously persisted result; if False, do not load an old result but store the newly computed result</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t712" href="#t712">712</a></span><span class="t"><span class="str">    :param version: if not None, previously persisted data will only be returned if it was stored with the same version</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t713" href="#t713">713</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t714" href="#t714">714</a></span><span class="t">    <span class="key">if</span> <span class="nam">filename_prefix</span> <span class="key">is</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t715" href="#t715">715</a></span><span class="t">        <span class="nam">filename_prefix</span> <span class="op">=</span> <span class="str">""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t716" href="#t716">716</a></span><span class="t">    <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t717" href="#t717">717</a></span><span class="t">        <span class="nam">filename_prefix</span> <span class="op">+=</span> <span class="str">"-"</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t718" href="#t718">718</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t719" href="#t719">719</a></span><span class="t">    <span class="key">def</span> <span class="nam">decorator</span><span class="op">(</span><span class="nam">fn</span><span class="op">:</span> <span class="nam">Callable</span><span class="op">,</span> <span class="op">*</span><span class="nam">_args</span><span class="op">,</span> <span class="op">**</span><span class="nam">_kwargs</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t714" href="#t714">714</a></span><span class="t">    <span class="nam">os</span><span class="op">.</span><span class="nam">makedirs</span><span class="op">(</span><span class="nam">cache_base_path</span><span class="op">,</span> <span class="nam">exist_ok</span><span class="op">=</span><span class="key">True</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t715" href="#t715">715</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t716" href="#t716">716</a></span><span class="t">    <span class="key">if</span> <span class="nam">filename_prefix</span> <span class="key">is</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t717" href="#t717">717</a></span><span class="t">        <span class="nam">filename_prefix</span> <span class="op">=</span> <span class="str">""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t718" href="#t718">718</a></span><span class="t">    <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t719" href="#t719">719</a></span><span class="t">        <span class="nam">filename_prefix</span> <span class="op">+=</span> <span class="str">"-"</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t720" href="#t720">720</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t721" href="#t721">721</a></span><span class="t">        <span class="op">@</span><span class="nam">wraps</span><span class="op">(</span><span class="nam">fn</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t722" href="#t722">722</a></span><span class="t">        <span class="key">def</span> <span class="nam">wrapped</span><span class="op">(</span><span class="op">*</span><span class="nam">args</span><span class="op">,</span> <span class="op">**</span><span class="nam">kwargs</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t723" href="#t723">723</a></span><span class="t">            <span class="nam">hash_code_str</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t724" href="#t724">724</a></span><span class="t">            <span class="nam">have_args</span> <span class="op">=</span> <span class="nam">len</span><span class="op">(</span><span class="nam">args</span><span class="op">)</span> <span class="op">></span> <span class="num">0</span> <span class="key">or</span> <span class="nam">len</span><span class="op">(</span><span class="nam">kwargs</span><span class="op">)</span> <span class="op">></span> <span class="num">0</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t725" href="#t725">725</a></span><span class="t">            <span class="key">if</span> <span class="nam">have_args</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t726" href="#t726">726</a></span><span class="t">                <span class="nam">hash_code_str</span> <span class="op">=</span> <span class="nam">pickle_hash</span><span class="op">(</span><span class="op">(</span><span class="nam">args</span><span class="op">,</span> <span class="nam">kwargs</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t727" href="#t727">727</a></span><span class="t">            <span class="key">if</span> <span class="nam">filename</span> <span class="key">is</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t728" href="#t728">728</a></span><span class="t">                <span class="nam">pickle_filename</span> <span class="op">=</span> <span class="nam">filename_prefix</span> <span class="op">+</span> <span class="nam">fn</span><span class="op">.</span><span class="nam">__qualname__</span><span class="op">.</span><span class="nam">replace</span><span class="op">(</span><span class="str">".&lt;locals>."</span><span class="op">,</span> <span class="str">"."</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t729" href="#t729">729</a></span><span class="t">                <span class="key">if</span> <span class="nam">hash_code_str</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t730" href="#t730">730</a></span><span class="t">                    <span class="nam">pickle_filename</span> <span class="op">+=</span> <span class="str">"-"</span> <span class="op">+</span> <span class="nam">hash_code_str</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t731" href="#t731">731</a></span><span class="t">                <span class="nam">pickle_filename</span> <span class="op">+=</span> <span class="str">".cache.pickle"</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t732" href="#t732">732</a></span><span class="t">            <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t733" href="#t733">733</a></span><span class="t">                <span class="key">if</span> <span class="nam">hash_code_str</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t734" href="#t734">734</a></span><span class="t">                    <span class="key">if</span> <span class="str">"%s"</span> <span class="key">not</span> <span class="key">in</span> <span class="nam">filename</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t735" href="#t735">735</a></span><span class="t">                        <span class="key">raise</span> <span class="nam">Exception</span><span class="op">(</span><span class="str">"Function called with arguments but full cache filename contains no placeholder (%s) "</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t736" href="#t736">736</a></span><span class="t">                                        <span class="str">"for argument hash"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t737" href="#t737">737</a></span><span class="t">                    <span class="nam">pickle_filename</span> <span class="op">=</span> <span class="nam">filename</span> <span class="op">%</span> <span class="nam">hash_code_str</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t738" href="#t738">738</a></span><span class="t">                <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t739" href="#t739">739</a></span><span class="t">                    <span class="key">if</span> <span class="str">"%s"</span> <span class="key">in</span> <span class="nam">filename</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t740" href="#t740">740</a></span><span class="t">                        <span class="key">raise</span> <span class="nam">Exception</span><span class="op">(</span><span class="str">"Function without arguments but full cache filename with placeholder (%s) was specified"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t741" href="#t741">741</a></span><span class="t">                    <span class="nam">pickle_filename</span> <span class="op">=</span> <span class="nam">filename</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t742" href="#t742">742</a></span><span class="t">            <span class="nam">pickle_path</span> <span class="op">=</span> <span class="nam">os</span><span class="op">.</span><span class="nam">path</span><span class="op">.</span><span class="nam">join</span><span class="op">(</span><span class="nam">cache_base_path</span><span class="op">,</span> <span class="nam">pickle_filename</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t743" href="#t743">743</a></span><span class="t">            <span class="key">return</span> <span class="nam">cached</span><span class="op">(</span><span class="key">lambda</span><span class="op">:</span> <span class="nam">fn</span><span class="op">(</span><span class="op">*</span><span class="nam">args</span><span class="op">,</span> <span class="op">**</span><span class="nam">kwargs</span><span class="op">)</span><span class="op">,</span> <span class="nam">pickle_path</span><span class="op">,</span> <span class="nam">function_name</span><span class="op">=</span><span class="nam">fn</span><span class="op">.</span><span class="nam">__name__</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="nam">backend</span><span class="op">,</span> <span class="nam">load</span><span class="op">=</span><span class="nam">load</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t744" href="#t744">744</a></span><span class="t">                <span class="nam">version</span><span class="op">=</span><span class="nam">version</span><span class="op">,</span> <span class="nam">protocol</span><span class="op">=</span><span class="nam">protocol</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t745" href="#t745">745</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t746" href="#t746">746</a></span><span class="t">        <span class="key">return</span> <span class="nam">wrapped</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t721" href="#t721">721</a></span><span class="t">    <span class="key">def</span> <span class="nam">decorator</span><span class="op">(</span><span class="nam">fn</span><span class="op">:</span> <span class="nam">Callable</span><span class="op">,</span> <span class="op">*</span><span class="nam">_args</span><span class="op">,</span> <span class="op">**</span><span class="nam">_kwargs</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t722" href="#t722">722</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t723" href="#t723">723</a></span><span class="t">        <span class="op">@</span><span class="nam">wraps</span><span class="op">(</span><span class="nam">fn</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t724" href="#t724">724</a></span><span class="t">        <span class="key">def</span> <span class="nam">wrapped</span><span class="op">(</span><span class="op">*</span><span class="nam">args</span><span class="op">,</span> <span class="op">**</span><span class="nam">kwargs</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t725" href="#t725">725</a></span><span class="t">            <span class="nam">hash_code_str</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t726" href="#t726">726</a></span><span class="t">            <span class="nam">have_args</span> <span class="op">=</span> <span class="nam">len</span><span class="op">(</span><span class="nam">args</span><span class="op">)</span> <span class="op">></span> <span class="num">0</span> <span class="key">or</span> <span class="nam">len</span><span class="op">(</span><span class="nam">kwargs</span><span class="op">)</span> <span class="op">></span> <span class="num">0</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t727" href="#t727">727</a></span><span class="t">            <span class="key">if</span> <span class="nam">have_args</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t728" href="#t728">728</a></span><span class="t">                <span class="nam">hash_code_str</span> <span class="op">=</span> <span class="nam">pickle_hash</span><span class="op">(</span><span class="op">(</span><span class="nam">args</span><span class="op">,</span> <span class="nam">kwargs</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t729" href="#t729">729</a></span><span class="t">            <span class="key">if</span> <span class="nam">filename</span> <span class="key">is</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t730" href="#t730">730</a></span><span class="t">                <span class="nam">pickle_filename</span> <span class="op">=</span> <span class="nam">filename_prefix</span> <span class="op">+</span> <span class="nam">fn</span><span class="op">.</span><span class="nam">__qualname__</span><span class="op">.</span><span class="nam">replace</span><span class="op">(</span><span class="str">".&lt;locals>."</span><span class="op">,</span> <span class="str">"."</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t731" href="#t731">731</a></span><span class="t">                <span class="key">if</span> <span class="nam">hash_code_str</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t732" href="#t732">732</a></span><span class="t">                    <span class="nam">pickle_filename</span> <span class="op">+=</span> <span class="str">"-"</span> <span class="op">+</span> <span class="nam">hash_code_str</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t733" href="#t733">733</a></span><span class="t">                <span class="nam">pickle_filename</span> <span class="op">+=</span> <span class="str">".cache.pickle"</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t734" href="#t734">734</a></span><span class="t">            <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t735" href="#t735">735</a></span><span class="t">                <span class="key">if</span> <span class="nam">hash_code_str</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t736" href="#t736">736</a></span><span class="t">                    <span class="key">if</span> <span class="str">"%s"</span> <span class="key">not</span> <span class="key">in</span> <span class="nam">filename</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t737" href="#t737">737</a></span><span class="t">                        <span class="key">raise</span> <span class="nam">Exception</span><span class="op">(</span><span class="str">"Function called with arguments but full cache filename contains no placeholder (%s) "</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t738" href="#t738">738</a></span><span class="t">                                        <span class="str">"for argument hash"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t739" href="#t739">739</a></span><span class="t">                    <span class="nam">pickle_filename</span> <span class="op">=</span> <span class="nam">filename</span> <span class="op">%</span> <span class="nam">hash_code_str</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t740" href="#t740">740</a></span><span class="t">                <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t741" href="#t741">741</a></span><span class="t">                    <span class="key">if</span> <span class="str">"%s"</span> <span class="key">in</span> <span class="nam">filename</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t742" href="#t742">742</a></span><span class="t">                        <span class="key">raise</span> <span class="nam">Exception</span><span class="op">(</span><span class="str">"Function without arguments but full cache filename with placeholder (%s) was specified"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t743" href="#t743">743</a></span><span class="t">                    <span class="nam">pickle_filename</span> <span class="op">=</span> <span class="nam">filename</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t744" href="#t744">744</a></span><span class="t">            <span class="nam">pickle_path</span> <span class="op">=</span> <span class="nam">os</span><span class="op">.</span><span class="nam">path</span><span class="op">.</span><span class="nam">join</span><span class="op">(</span><span class="nam">cache_base_path</span><span class="op">,</span> <span class="nam">pickle_filename</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t745" href="#t745">745</a></span><span class="t">            <span class="key">return</span> <span class="nam">cached</span><span class="op">(</span><span class="key">lambda</span><span class="op">:</span> <span class="nam">fn</span><span class="op">(</span><span class="op">*</span><span class="nam">args</span><span class="op">,</span> <span class="op">**</span><span class="nam">kwargs</span><span class="op">)</span><span class="op">,</span> <span class="nam">pickle_path</span><span class="op">,</span> <span class="nam">function_name</span><span class="op">=</span><span class="nam">fn</span><span class="op">.</span><span class="nam">__name__</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="nam">backend</span><span class="op">,</span> <span class="nam">load</span><span class="op">=</span><span class="nam">load</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t746" href="#t746">746</a></span><span class="t">                <span class="nam">version</span><span class="op">=</span><span class="nam">version</span><span class="op">,</span> <span class="nam">protocol</span><span class="op">=</span><span class="nam">protocol</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t747" href="#t747">747</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t748" href="#t748">748</a></span><span class="t">    <span class="key">return</span> <span class="nam">decorator</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t748" href="#t748">748</a></span><span class="t">        <span class="key">return</span> <span class="nam">wrapped</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t749" href="#t749">749</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t750" href="#t750">750</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t751" href="#t751">751</a></span><span class="t"><span class="nam">PickleCached</span> <span class="op">=</span> <span class="nam">pickle_cached</span>  <span class="com"># for backward compatibility</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t750" href="#t750">750</a></span><span class="t">    <span class="key">return</span> <span class="nam">decorator</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t751" href="#t751">751</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t752" href="#t752">752</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t753" href="#t753">753</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t754" href="#t754">754</a></span><span class="t"><span class="key">class</span> <span class="nam">LoadSaveInterface</span><span class="op">(</span><span class="nam">ABC</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t755" href="#t755">755</a></span><span class="t">    <span class="op">@</span><span class="nam">abstractmethod</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t756" href="#t756">756</a></span><span class="t">    <span class="key">def</span> <span class="nam">save</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">str</span><span class="op">)</span> <span class="op">-></span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t757" href="#t757">757</a></span><span class="t">        <span class="key">pass</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t758" href="#t758">758</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t759" href="#t759">759</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t760" href="#t760">760</a></span><span class="t">    <span class="op">@</span><span class="nam">abstractmethod</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t761" href="#t761">761</a></span><span class="t">    <span class="key">def</span> <span class="nam">load</span><span class="op">(</span><span class="nam">cls</span><span class="op">:</span> <span class="nam">T</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">str</span><span class="op">)</span> <span class="op">-></span> <span class="nam">T</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t762" href="#t762">762</a></span><span class="t">        <span class="key">pass</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t763" href="#t763">763</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t764" href="#t764">764</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t765" href="#t765">765</a></span><span class="t"><span class="key">class</span> <span class="nam">PickleLoadSaveMixin</span><span class="op">(</span><span class="nam">LoadSaveInterface</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t766" href="#t766">766</a></span><span class="t">    <span class="key">def</span> <span class="nam">save</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">Union</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Path</span><span class="op">]</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="str">"pickle"</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t767" href="#t767">767</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t768" href="#t768">768</a></span><span class="t"><span class="str">        Saves the instance as pickle</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t769" href="#t769">769</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t770" href="#t770">770</a></span><span class="t"><span class="str">        :param path:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t771" href="#t771">771</a></span><span class="t"><span class="str">        :param backend: pickle or joblib</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t772" href="#t772">772</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t773" href="#t773">773</a></span><span class="t">        <span class="nam">dump_pickle</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">path</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="nam">backend</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t774" href="#t774">774</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t775" href="#t775">775</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t776" href="#t776">776</a></span><span class="t">    <span class="key">def</span> <span class="nam">load</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">Union</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Path</span><span class="op">]</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="str">"pickle"</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t777" href="#t777">777</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t778" href="#t778">778</a></span><span class="t"><span class="str">        Loads a class instance from pickle</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t779" href="#t779">779</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t780" href="#t780">780</a></span><span class="t"><span class="str">        :param path:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t781" href="#t781">781</a></span><span class="t"><span class="str">        :param backend: pickle or joblib</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t782" href="#t782">782</a></span><span class="t"><span class="str">        :return: instance of the present class</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t783" href="#t783">783</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t784" href="#t784">784</a></span><span class="t">        <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"Loading instance of {cls} from {path}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t785" href="#t785">785</a></span><span class="t">        <span class="nam">result</span> <span class="op">=</span> <span class="nam">load_pickle</span><span class="op">(</span><span class="nam">path</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="nam">backend</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t786" href="#t786">786</a></span><span class="t">        <span class="key">if</span> <span class="key">not</span> <span class="nam">isinstance</span><span class="op">(</span><span class="nam">result</span><span class="op">,</span> <span class="nam">cls</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t787" href="#t787">787</a></span><span class="t">            <span class="key">raise</span> <span class="nam">Exception</span><span class="op">(</span><span class="str">f"Excepted instance of {cls}, instead got: {result.__class__.__name__}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t788" href="#t788">788</a></span><span class="t">        <span class="key">return</span> <span class="nam">result</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t753" href="#t753">753</a></span><span class="t"><span class="nam">PickleCached</span> <span class="op">=</span> <span class="nam">pickle_cached</span>  <span class="com"># for backward compatibility</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t754" href="#t754">754</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t755" href="#t755">755</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t756" href="#t756">756</a></span><span class="t"><span class="key">class</span> <span class="nam">LoadSaveInterface</span><span class="op">(</span><span class="nam">ABC</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t757" href="#t757">757</a></span><span class="t">    <span class="op">@</span><span class="nam">abstractmethod</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t758" href="#t758">758</a></span><span class="t">    <span class="key">def</span> <span class="nam">save</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">str</span><span class="op">)</span> <span class="op">-></span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t759" href="#t759">759</a></span><span class="t">        <span class="key">pass</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t760" href="#t760">760</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t761" href="#t761">761</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t762" href="#t762">762</a></span><span class="t">    <span class="op">@</span><span class="nam">abstractmethod</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t763" href="#t763">763</a></span><span class="t">    <span class="key">def</span> <span class="nam">load</span><span class="op">(</span><span class="nam">cls</span><span class="op">:</span> <span class="nam">T</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">str</span><span class="op">)</span> <span class="op">-></span> <span class="nam">T</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t764" href="#t764">764</a></span><span class="t">        <span class="key">pass</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t765" href="#t765">765</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t766" href="#t766">766</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t767" href="#t767">767</a></span><span class="t"><span class="key">class</span> <span class="nam">PickleLoadSaveMixin</span><span class="op">(</span><span class="nam">LoadSaveInterface</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t768" href="#t768">768</a></span><span class="t">    <span class="key">def</span> <span class="nam">save</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">Union</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Path</span><span class="op">]</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="str">"pickle"</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t769" href="#t769">769</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t770" href="#t770">770</a></span><span class="t"><span class="str">        Saves the instance as pickle</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t771" href="#t771">771</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t772" href="#t772">772</a></span><span class="t"><span class="str">        :param path:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t773" href="#t773">773</a></span><span class="t"><span class="str">        :param backend: pickle, cloudpickle, or joblib</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t774" href="#t774">774</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t775" href="#t775">775</a></span><span class="t">        <span class="nam">dump_pickle</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">path</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="nam">backend</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t776" href="#t776">776</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t777" href="#t777">777</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t778" href="#t778">778</a></span><span class="t">    <span class="key">def</span> <span class="nam">load</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">Union</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Path</span><span class="op">]</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="str">"pickle"</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t779" href="#t779">779</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t780" href="#t780">780</a></span><span class="t"><span class="str">        Loads a class instance from pickle</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t781" href="#t781">781</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t782" href="#t782">782</a></span><span class="t"><span class="str">        :param path:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t783" href="#t783">783</a></span><span class="t"><span class="str">        :param backend: pickle, cloudpickle, or joblib</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t784" href="#t784">784</a></span><span class="t"><span class="str">        :return: instance of the present class</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t785" href="#t785">785</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t786" href="#t786">786</a></span><span class="t">        <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"Loading instance of {cls} from {path}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t787" href="#t787">787</a></span><span class="t">        <span class="nam">result</span> <span class="op">=</span> <span class="nam">load_pickle</span><span class="op">(</span><span class="nam">path</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="nam">backend</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t788" href="#t788">788</a></span><span class="t">        <span class="key">if</span> <span class="key">not</span> <span class="nam">isinstance</span><span class="op">(</span><span class="nam">result</span><span class="op">,</span> <span class="nam">cls</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t789" href="#t789">789</a></span><span class="t">            <span class="key">raise</span> <span class="nam">Exception</span><span class="op">(</span><span class="str">f"Excepted instance of {cls}, instead got: {result.__class__.__name__}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t790" href="#t790">790</a></span><span class="t">        <span class="key">return</span> <span class="nam">result</span>&nbsp;</span><span class="r"></span></p>
 </main>
 <footer>
     <div class="content">
@@ -877,7 +879,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_cache_azure_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_datastruct_py.html b/coverage/d_3ccb7b6033502eb6_datastruct_py.html
index 4c5caf3d..929120fa 100644
--- a/coverage/d_3ccb7b6033502eb6_datastruct_py.html
+++ b/coverage/d_3ccb7b6033502eb6_datastruct_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_deprecation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -509,7 +509,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_deprecation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_deprecation_py.html b/coverage/d_3ccb7b6033502eb6_deprecation_py.html
index 73680567..714b5a2a 100644
--- a/coverage/d_3ccb7b6033502eb6_deprecation_py.html
+++ b/coverage/d_3ccb7b6033502eb6_deprecation_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_dtype_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -115,7 +115,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_dtype_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_dtype_py.html b/coverage/d_3ccb7b6033502eb6_dtype_py.html
index 81d4033c..89126c59 100644
--- a/coverage/d_3ccb7b6033502eb6_dtype_py.html
+++ b/coverage/d_3ccb7b6033502eb6_dtype_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_hash_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -121,7 +121,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_hash_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_hash_py.html b/coverage/d_3ccb7b6033502eb6_hash_py.html
index 803644e4..31f79e40 100644
--- a/coverage/d_3ccb7b6033502eb6_hash_py.html
+++ b/coverage/d_3ccb7b6033502eb6_hash_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_helper_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -124,7 +124,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_helper_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_helper_py.html b/coverage/d_3ccb7b6033502eb6_helper_py.html
index c5e65b8e..6b67a7d2 100644
--- a/coverage/d_3ccb7b6033502eb6_helper_py.html
+++ b/coverage/d_3ccb7b6033502eb6_helper_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_io_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -175,7 +175,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_io_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_io_py.html b/coverage/d_3ccb7b6033502eb6_io_py.html
index ba3b5583..1e7c2e47 100644
--- a/coverage/d_3ccb7b6033502eb6_io_py.html
+++ b/coverage/d_3ccb7b6033502eb6_io_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_jscode_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -274,7 +274,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_jscode_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_jscode_py.html b/coverage/d_3ccb7b6033502eb6_jscode_py.html
index f5b24f5e..b84dd05e 100644
--- a/coverage/d_3ccb7b6033502eb6_jscode_py.html
+++ b/coverage/d_3ccb7b6033502eb6_jscode_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_logging_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -241,7 +241,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_logging_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_logging_py.html b/coverage/d_3ccb7b6033502eb6_logging_py.html
index 9d1a2a62..89c4b6ad 100644
--- a/coverage/d_3ccb7b6033502eb6_logging_py.html
+++ b/coverage/d_3ccb7b6033502eb6_logging_py.html
@@ -54,9 +54,9 @@ <h1>
             </div>
         </aside>
         <h2>
-            <span class="text">152 statements &nbsp;</span>
+            <span class="text">154 statements &nbsp;</span>
             <button type="button" class="run button_toggle_run" value="run" data-shortcut="r" title="Toggle lines run">61<span class="text"> run</span></button>
-            <button type="button" class="mis show_mis button_toggle_mis" value="mis" data-shortcut="m" title="Toggle lines missing">91<span class="text"> missing</span></button>
+            <button type="button" class="mis show_mis button_toggle_mis" value="mis" data-shortcut="m" title="Toggle lines missing">93<span class="text"> missing</span></button>
             <button type="button" class="exc show_exc button_toggle_exc" value="exc" data-shortcut="x" title="Toggle lines excluded">0<span class="text"> excluded</span></button>
         </h2>
         <p class="text">
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_math_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -100,7 +100,7 @@ <h2>
     <p class="run"><span class="n"><a id="t18" href="#t18">18</a></span><span class="t"><span class="nam">_logFormat</span> <span class="op">=</span> <span class="nam">LOG_DEFAULT_FORMAT</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t19" href="#t19">19</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t20" href="#t20">20</a></span><span class="t"><span class="com"># User-configured callback which is called after logging is configured via function `configure`</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t21" href="#t21">21</a></span><span class="t"><span class="nam">_configureCallback</span><span class="op">:</span> <span class="nam">Optional</span><span class="op">[</span><span class="nam">Callable</span><span class="op">[</span><span class="op">[</span><span class="op">]</span><span class="op">,</span> <span class="key">None</span><span class="op">]</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t21" href="#t21">21</a></span><span class="t"><span class="nam">_configureCallbacks</span><span class="op">:</span> <span class="nam">List</span><span class="op">[</span><span class="nam">Callable</span><span class="op">[</span><span class="op">[</span><span class="op">]</span><span class="op">,</span> <span class="key">None</span><span class="op">]</span><span class="op">]</span> <span class="op">=</span> <span class="op">[</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t22" href="#t22">22</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t23" href="#t23">23</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="run"><span class="n"><a id="t24" href="#t24">24</a></span><span class="t"><span class="key">def</span> <span class="nam">remove_log_handlers</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
@@ -120,300 +120,302 @@ <h2>
     <p class="mis show_mis"><span class="n"><a id="t38" href="#t38">38</a></span><span class="t">    <span class="key">return</span> <span class="nam">handler</span> <span class="key">in</span> <span class="nam">getLogger</span><span class="op">(</span><span class="op">)</span><span class="op">.</span><span class="nam">handlers</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t39" href="#t39">39</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t40" href="#t40">40</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t41" href="#t41">41</a></span><span class="t"><span class="key">def</span> <span class="nam">set_configure_callback</span><span class="op">(</span><span class="nam">callback</span><span class="op">:</span> <span class="nam">Callable</span><span class="op">[</span><span class="op">[</span><span class="op">]</span><span class="op">,</span> <span class="key">None</span><span class="op">]</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t41" href="#t41">41</a></span><span class="t"><span class="key">def</span> <span class="nam">set_configure_callback</span><span class="op">(</span><span class="nam">callback</span><span class="op">:</span> <span class="nam">Callable</span><span class="op">[</span><span class="op">[</span><span class="op">]</span><span class="op">,</span> <span class="key">None</span><span class="op">]</span><span class="op">,</span> <span class="nam">append</span><span class="op">:</span> <span class="nam">bool</span> <span class="op">=</span> <span class="key">True</span><span class="op">)</span> <span class="op">-></span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t42" href="#t42">42</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t43" href="#t43">43</a></span><span class="t"><span class="str">    Configures a function to be called when logging is configured, e.g. through :func:`configure, :func:`run_main` or</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t44" href="#t44">44</a></span><span class="t"><span class="str">    :func:`run_cli`.</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t45" href="#t45">45</a></span><span class="t"><span class="str">    A typical use for the callback is to configure the logging behaviour of packages, setting appropriate log levels.</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t46" href="#t46">46</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t47" href="#t47">47</a></span><span class="t"><span class="str">    :param callback: the function to cal</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t48" href="#t48">48</a></span><span class="t"><span class="str">    :return:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t47" href="#t47">47</a></span><span class="t"><span class="str">    :param callback: the function to call</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t48" href="#t48">48</a></span><span class="t"><span class="str">    :param append: whether to append to the list of callbacks; if False, any existing callbacks will be removed</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t49" href="#t49">49</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t50" href="#t50">50</a></span><span class="t">    <span class="key">global</span> <span class="nam">_configureCallback</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t51" href="#t51">51</a></span><span class="t">    <span class="nam">_configureCallback</span> <span class="op">=</span> <span class="nam">callback</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t52" href="#t52">52</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t53" href="#t53">53</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t54" href="#t54">54</a></span><span class="t"><span class="com"># noinspection PyShadowingBuiltins</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t55" href="#t55">55</a></span><span class="t"><span class="key">def</span> <span class="nam">configure</span><span class="op">(</span><span class="nam">format</span><span class="op">=</span><span class="nam">LOG_DEFAULT_FORMAT</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">lg</span><span class="op">.</span><span class="nam">DEBUG</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t56" href="#t56">56</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t57" href="#t57">57</a></span><span class="t"><span class="str">    Configures logging to stdout with the given format and log level,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t58" href="#t58">58</a></span><span class="t"><span class="str">    also configuring the default log levels of some overly verbose libraries as well as some pandas output options.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t59" href="#t59">59</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t60" href="#t60">60</a></span><span class="t"><span class="str">    :param format: the log format</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t61" href="#t61">61</a></span><span class="t"><span class="str">    :param level: the minimum log level</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t62" href="#t62">62</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t63" href="#t63">63</a></span><span class="t">    <span class="key">global</span> <span class="nam">_logFormat</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t64" href="#t64">64</a></span><span class="t">    <span class="nam">_logFormat</span> <span class="op">=</span> <span class="nam">format</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t65" href="#t65">65</a></span><span class="t">    <span class="nam">remove_log_handlers</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t66" href="#t66">66</a></span><span class="t">    <span class="nam">basicConfig</span><span class="op">(</span><span class="nam">level</span><span class="op">=</span><span class="nam">level</span><span class="op">,</span> <span class="nam">format</span><span class="op">=</span><span class="nam">format</span><span class="op">,</span> <span class="nam">stream</span><span class="op">=</span><span class="nam">sys</span><span class="op">.</span><span class="nam">stdout</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t67" href="#t67">67</a></span><span class="t">    <span class="nam">getLogger</span><span class="op">(</span><span class="str">"matplotlib"</span><span class="op">)</span><span class="op">.</span><span class="nam">setLevel</span><span class="op">(</span><span class="nam">lg</span><span class="op">.</span><span class="nam">INFO</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t68" href="#t68">68</a></span><span class="t">    <span class="nam">getLogger</span><span class="op">(</span><span class="str">"urllib3"</span><span class="op">)</span><span class="op">.</span><span class="nam">setLevel</span><span class="op">(</span><span class="nam">lg</span><span class="op">.</span><span class="nam">INFO</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t69" href="#t69">69</a></span><span class="t">    <span class="nam">getLogger</span><span class="op">(</span><span class="str">"msal"</span><span class="op">)</span><span class="op">.</span><span class="nam">setLevel</span><span class="op">(</span><span class="nam">lg</span><span class="op">.</span><span class="nam">INFO</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t70" href="#t70">70</a></span><span class="t">    <span class="nam">pd</span><span class="op">.</span><span class="nam">set_option</span><span class="op">(</span><span class="str">'display.max_colwidth'</span><span class="op">,</span> <span class="num">255</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t71" href="#t71">71</a></span><span class="t">    <span class="key">if</span> <span class="nam">_configureCallback</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t72" href="#t72">72</a></span><span class="t">        <span class="nam">_configureCallback</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t73" href="#t73">73</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t74" href="#t74">74</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t75" href="#t75">75</a></span><span class="t"><span class="com"># noinspection PyShadowingBuiltins</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t76" href="#t76">76</a></span><span class="t"><span class="key">def</span> <span class="nam">run_main</span><span class="op">(</span><span class="nam">main_fn</span><span class="op">:</span> <span class="nam">Callable</span><span class="op">[</span><span class="op">[</span><span class="op">]</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span><span class="op">,</span> <span class="nam">format</span><span class="op">=</span><span class="nam">LOG_DEFAULT_FORMAT</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">lg</span><span class="op">.</span><span class="nam">DEBUG</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t77" href="#t77">77</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t78" href="#t78">78</a></span><span class="t"><span class="str">    Configures logging with the given parameters, ensuring that any exceptions that occur during</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t79" href="#t79">79</a></span><span class="t"><span class="str">    the execution of the given function are logged.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t80" href="#t80">80</a></span><span class="t"><span class="str">    Logs two additional messages, one before the execution of the function, and one upon its completion.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t81" href="#t81">81</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t82" href="#t82">82</a></span><span class="t"><span class="str">    :param main_fn: the function to be executed</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t83" href="#t83">83</a></span><span class="t"><span class="str">    :param format: the log message format</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t84" href="#t84">84</a></span><span class="t"><span class="str">    :param level: the minimum log level</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t85" href="#t85">85</a></span><span class="t"><span class="str">    :return: the result of `main_fn`</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t86" href="#t86">86</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t87" href="#t87">87</a></span><span class="t">    <span class="nam">configure</span><span class="op">(</span><span class="nam">format</span><span class="op">=</span><span class="nam">format</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">level</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t88" href="#t88">88</a></span><span class="t">    <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">"Starting"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t89" href="#t89">89</a></span><span class="t">    <span class="key">try</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t90" href="#t90">90</a></span><span class="t">        <span class="nam">result</span> <span class="op">=</span> <span class="nam">main_fn</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t91" href="#t91">91</a></span><span class="t">        <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">"Done"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t92" href="#t92">92</a></span><span class="t">        <span class="key">return</span> <span class="nam">result</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t93" href="#t93">93</a></span><span class="t">    <span class="key">except</span> <span class="nam">Exception</span> <span class="key">as</span> <span class="nam">e</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t94" href="#t94">94</a></span><span class="t">        <span class="nam">log</span><span class="op">.</span><span class="nam">error</span><span class="op">(</span><span class="str">"Exception during script execution"</span><span class="op">,</span> <span class="nam">exc_info</span><span class="op">=</span><span class="nam">e</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t95" href="#t95">95</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t96" href="#t96">96</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t97" href="#t97">97</a></span><span class="t"><span class="key">def</span> <span class="nam">run_cli</span><span class="op">(</span><span class="nam">main_fn</span><span class="op">:</span> <span class="nam">Callable</span><span class="op">[</span><span class="op">[</span><span class="op">]</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span><span class="op">,</span> <span class="nam">format</span><span class="op">=</span><span class="nam">LOG_DEFAULT_FORMAT</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">lg</span><span class="op">.</span><span class="nam">DEBUG</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t98" href="#t98">98</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t99" href="#t99">99</a></span><span class="t"><span class="str">    Configures logging with the given parameters and runs the given main function as a</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t100" href="#t100">100</a></span><span class="t"><span class="str">    CLI using `jsonargparse` (which is configured to also parse attribute docstrings, such</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t101" href="#t101">101</a></span><span class="t"><span class="str">    that dataclasses can be used as function arguments).</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t102" href="#t102">102</a></span><span class="t"><span class="str">    Using this function requires that `jsonargparse` and `docstring_parser` be available.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t103" href="#t103">103</a></span><span class="t"><span class="str">    Like `run_main`, two additional log messages will be logged (at the beginning and end</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t104" href="#t104">104</a></span><span class="t"><span class="str">    of the execution), and it is ensured that all exceptions will be logged.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t105" href="#t105">105</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t106" href="#t106">106</a></span><span class="t"><span class="str">    :param main_fn: the function to be executed</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t107" href="#t107">107</a></span><span class="t"><span class="str">    :param format: the log message format</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t108" href="#t108">108</a></span><span class="t"><span class="str">    :param level: the minimum log level</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t109" href="#t109">109</a></span><span class="t"><span class="str">    :return: the result of `main_fn`</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t110" href="#t110">110</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t111" href="#t111">111</a></span><span class="t">    <span class="key">from</span> <span class="nam">jsonargparse</span> <span class="key">import</span> <span class="nam">set_docstring_parse_options</span><span class="op">,</span> <span class="nam">CLI</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t112" href="#t112">112</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t113" href="#t113">113</a></span><span class="t">    <span class="nam">set_docstring_parse_options</span><span class="op">(</span><span class="nam">attribute_docstrings</span><span class="op">=</span><span class="key">True</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t114" href="#t114">114</a></span><span class="t">    <span class="key">return</span> <span class="nam">run_main</span><span class="op">(</span><span class="key">lambda</span><span class="op">:</span> <span class="nam">CLI</span><span class="op">(</span><span class="nam">main_fn</span><span class="op">)</span><span class="op">,</span> <span class="nam">format</span><span class="op">=</span><span class="nam">format</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">level</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t115" href="#t115">115</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t116" href="#t116">116</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t117" href="#t117">117</a></span><span class="t"><span class="key">def</span> <span class="nam">datetime_tag</span><span class="op">(</span><span class="op">)</span> <span class="op">-></span> <span class="nam">str</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t118" href="#t118">118</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t119" href="#t119">119</a></span><span class="t"><span class="str">    :return: a string tag for use in log file names which contains the current date and time (compact but readable)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t120" href="#t120">120</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t121" href="#t121">121</a></span><span class="t">    <span class="key">return</span> <span class="nam">datetime</span><span class="op">.</span><span class="nam">now</span><span class="op">(</span><span class="op">)</span><span class="op">.</span><span class="nam">strftime</span><span class="op">(</span><span class="str">'%Y%m%d-%H%M%S'</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t122" href="#t122">122</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t123" href="#t123">123</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t124" href="#t124">124</a></span><span class="t"><span class="nam">_fileLoggerPaths</span><span class="op">:</span> <span class="nam">List</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="op">[</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t125" href="#t125">125</a></span><span class="t"><span class="nam">_isAtExitReportFileLoggerRegistered</span> <span class="op">=</span> <span class="key">False</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t126" href="#t126">126</a></span><span class="t"><span class="nam">_memoryLogStream</span><span class="op">:</span> <span class="nam">Optional</span><span class="op">[</span><span class="nam">StringIO</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t127" href="#t127">127</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t128" href="#t128">128</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t129" href="#t129">129</a></span><span class="t"><span class="key">def</span> <span class="nam">_at_exit_report_file_logger</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t130" href="#t130">130</a></span><span class="t">    <span class="key">for</span> <span class="nam">path</span> <span class="key">in</span> <span class="nam">_fileLoggerPaths</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t131" href="#t131">131</a></span><span class="t">        <span class="nam">print</span><span class="op">(</span><span class="str">f"A log file was saved to {path}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t132" href="#t132">132</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t133" href="#t133">133</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t134" href="#t134">134</a></span><span class="t"><span class="key">def</span> <span class="nam">add_file_logger</span><span class="op">(</span><span class="nam">path</span><span class="op">,</span> <span class="nam">register_atexit</span><span class="op">=</span><span class="key">True</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t135" href="#t135">135</a></span><span class="t">    <span class="key">global</span> <span class="nam">_isAtExitReportFileLoggerRegistered</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t136" href="#t136">136</a></span><span class="t">    <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"Logging to {path} ..."</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t137" href="#t137">137</a></span><span class="t">    <span class="nam">handler</span> <span class="op">=</span> <span class="nam">FileHandler</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t138" href="#t138">138</a></span><span class="t">    <span class="nam">handler</span><span class="op">.</span><span class="nam">setFormatter</span><span class="op">(</span><span class="nam">Formatter</span><span class="op">(</span><span class="nam">_logFormat</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t139" href="#t139">139</a></span><span class="t">    <span class="nam">Logger</span><span class="op">.</span><span class="nam">root</span><span class="op">.</span><span class="nam">addHandler</span><span class="op">(</span><span class="nam">handler</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t140" href="#t140">140</a></span><span class="t">    <span class="nam">_fileLoggerPaths</span><span class="op">.</span><span class="nam">append</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t141" href="#t141">141</a></span><span class="t">    <span class="key">if</span> <span class="key">not</span> <span class="nam">_isAtExitReportFileLoggerRegistered</span> <span class="key">and</span> <span class="nam">register_atexit</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t142" href="#t142">142</a></span><span class="t">        <span class="nam">atexit</span><span class="op">.</span><span class="nam">register</span><span class="op">(</span><span class="nam">_at_exit_report_file_logger</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t143" href="#t143">143</a></span><span class="t">        <span class="nam">_isAtExitReportFileLoggerRegistered</span> <span class="op">=</span> <span class="key">True</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t144" href="#t144">144</a></span><span class="t">    <span class="key">return</span> <span class="nam">handler</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t145" href="#t145">145</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t146" href="#t146">146</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t147" href="#t147">147</a></span><span class="t"><span class="key">def</span> <span class="nam">add_memory_logger</span><span class="op">(</span><span class="op">)</span> <span class="op">-></span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t148" href="#t148">148</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t149" href="#t149">149</a></span><span class="t"><span class="str">    Enables in-memory logging (if it is not already enabled), i.e. all log statements are written to a memory buffer and can later be</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t150" href="#t150">150</a></span><span class="t"><span class="str">    read via function `get_memory_log()`</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t151" href="#t151">151</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t152" href="#t152">152</a></span><span class="t">    <span class="key">global</span> <span class="nam">_memoryLogStream</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t153" href="#t153">153</a></span><span class="t">    <span class="key">if</span> <span class="nam">_memoryLogStream</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t154" href="#t154">154</a></span><span class="t">        <span class="key">return</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t155" href="#t155">155</a></span><span class="t">    <span class="nam">_memoryLogStream</span> <span class="op">=</span> <span class="nam">StringIO</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t156" href="#t156">156</a></span><span class="t">    <span class="nam">handler</span> <span class="op">=</span> <span class="nam">StreamHandler</span><span class="op">(</span><span class="nam">_memoryLogStream</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t157" href="#t157">157</a></span><span class="t">    <span class="nam">handler</span><span class="op">.</span><span class="nam">setFormatter</span><span class="op">(</span><span class="nam">Formatter</span><span class="op">(</span><span class="nam">_logFormat</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t158" href="#t158">158</a></span><span class="t">    <span class="nam">Logger</span><span class="op">.</span><span class="nam">root</span><span class="op">.</span><span class="nam">addHandler</span><span class="op">(</span><span class="nam">handler</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t159" href="#t159">159</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t160" href="#t160">160</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t161" href="#t161">161</a></span><span class="t"><span class="key">def</span> <span class="nam">get_memory_log</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t162" href="#t162">162</a></span><span class="t">    <span class="key">return</span> <span class="nam">_memoryLogStream</span><span class="op">.</span><span class="nam">getvalue</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t163" href="#t163">163</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t164" href="#t164">164</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t165" href="#t165">165</a></span><span class="t"><span class="key">class</span> <span class="nam">StopWatch</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t166" href="#t166">166</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t167" href="#t167">167</a></span><span class="t"><span class="str">    Represents a stop watch for timing an execution. Constructing an instance starts the stopwatch.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t168" href="#t168">168</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t169" href="#t169">169</a></span><span class="t">    <span class="key">def</span> <span class="nam">__init__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">start</span><span class="op">=</span><span class="key">True</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t170" href="#t170">170</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">start_time</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t171" href="#t171">171</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_elapsed_secs</span> <span class="op">=</span> <span class="num">0.0</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t172" href="#t172">172</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span> <span class="op">=</span> <span class="nam">start</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t173" href="#t173">173</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t174" href="#t174">174</a></span><span class="t">    <span class="key">def</span> <span class="nam">reset</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">start</span><span class="op">=</span><span class="key">True</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t175" href="#t175">175</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t176" href="#t176">176</a></span><span class="t"><span class="str">        Resets the stopwatch, setting the elapsed time to zero.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t177" href="#t177">177</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t178" href="#t178">178</a></span><span class="t"><span class="str">        :param start: whether to start the stopwatch immediately</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t179" href="#t179">179</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t180" href="#t180">180</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">start_time</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t181" href="#t181">181</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_elapsed_secs</span> <span class="op">=</span> <span class="num">0.0</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t182" href="#t182">182</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span> <span class="op">=</span> <span class="nam">start</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t183" href="#t183">183</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t184" href="#t184">184</a></span><span class="t">    <span class="key">def</span> <span class="nam">restart</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t185" href="#t185">185</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t186" href="#t186">186</a></span><span class="t"><span class="str">        Resets the stopwatch (setting the elapsed time to zero) and restarts it immediately</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t187" href="#t187">187</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t188" href="#t188">188</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">reset</span><span class="op">(</span><span class="nam">start</span><span class="op">=</span><span class="key">True</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t189" href="#t189">189</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t190" href="#t190">190</a></span><span class="t">    <span class="key">def</span> <span class="nam">_get_elapsed_time_since_last_start</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t191" href="#t191">191</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t192" href="#t192">192</a></span><span class="t">            <span class="key">return</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span> <span class="op">-</span> <span class="nam">self</span><span class="op">.</span><span class="nam">start_time</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t193" href="#t193">193</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t194" href="#t194">194</a></span><span class="t">            <span class="key">return</span> <span class="num">0</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t195" href="#t195">195</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t196" href="#t196">196</a></span><span class="t">    <span class="key">def</span> <span class="nam">pause</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t197" href="#t197">197</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t198" href="#t198">198</a></span><span class="t"><span class="str">        Pauses the stopwatch. It can be resumed via method 'resume'.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t199" href="#t199">199</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t200" href="#t200">200</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_elapsed_secs</span> <span class="op">+=</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_get_elapsed_time_since_last_start</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t201" href="#t201">201</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span> <span class="op">=</span> <span class="key">False</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t202" href="#t202">202</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t203" href="#t203">203</a></span><span class="t">    <span class="key">def</span> <span class="nam">resume</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t204" href="#t204">204</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t205" href="#t205">205</a></span><span class="t"><span class="str">        Resumes the stopwatch (assuming that it is currently paused). If the stopwatch is not paused,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t206" href="#t206">206</a></span><span class="t"><span class="str">        the method has no effect (and a warning is logged).</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t207" href="#t207">207</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t208" href="#t208">208</a></span><span class="t">        <span class="key">if</span> <span class="key">not</span> <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t209" href="#t209">209</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">start_time</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t210" href="#t210">210</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span> <span class="op">=</span> <span class="key">True</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t211" href="#t211">211</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t212" href="#t212">212</a></span><span class="t">            <span class="nam">log</span><span class="op">.</span><span class="nam">warning</span><span class="op">(</span><span class="str">"Stopwatch is already running (resume has not effect)"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t213" href="#t213">213</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t214" href="#t214">214</a></span><span class="t">    <span class="key">def</span> <span class="nam">get_elapsed_time_secs</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span> <span class="op">-></span> <span class="nam">float</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t215" href="#t215">215</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t216" href="#t216">216</a></span><span class="t"><span class="str">        Gets the total elapsed time, in seconds, on this stopwatch.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t217" href="#t217">217</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t218" href="#t218">218</a></span><span class="t"><span class="str">        :return: the elapsed time in seconds</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t219" href="#t219">219</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t220" href="#t220">220</a></span><span class="t">        <span class="key">return</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_elapsed_secs</span> <span class="op">+</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_get_elapsed_time_since_last_start</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t221" href="#t221">221</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t222" href="#t222">222</a></span><span class="t">    <span class="key">def</span> <span class="nam">get_elapsed_timedelta</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span> <span class="op">-></span> <span class="nam">pd</span><span class="op">.</span><span class="nam">Timedelta</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t223" href="#t223">223</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t224" href="#t224">224</a></span><span class="t"><span class="str">        :return: the elapsed time as a pandas.Timedelta object</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t225" href="#t225">225</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t226" href="#t226">226</a></span><span class="t">        <span class="key">return</span> <span class="nam">pd</span><span class="op">.</span><span class="nam">Timedelta</span><span class="op">(</span><span class="nam">self</span><span class="op">.</span><span class="nam">get_elapsed_time_secs</span><span class="op">(</span><span class="op">)</span><span class="op">,</span> <span class="nam">unit</span><span class="op">=</span><span class="str">"s"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t227" href="#t227">227</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t228" href="#t228">228</a></span><span class="t">    <span class="key">def</span> <span class="nam">get_elapsed_time_string</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span> <span class="op">-></span> <span class="nam">str</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t229" href="#t229">229</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t230" href="#t230">230</a></span><span class="t"><span class="str">        :return: a string representation of the elapsed time</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t231" href="#t231">231</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t232" href="#t232">232</a></span><span class="t">        <span class="nam">secs</span> <span class="op">=</span> <span class="nam">self</span><span class="op">.</span><span class="nam">get_elapsed_time_secs</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t233" href="#t233">233</a></span><span class="t">        <span class="key">if</span> <span class="nam">secs</span> <span class="op">&lt;</span> <span class="num">60</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t234" href="#t234">234</a></span><span class="t">            <span class="key">return</span> <span class="str">f"{secs:.3f} seconds"</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t235" href="#t235">235</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t236" href="#t236">236</a></span><span class="t">            <span class="key">return</span> <span class="nam">str</span><span class="op">(</span><span class="nam">pd</span><span class="op">.</span><span class="nam">Timedelta</span><span class="op">(</span><span class="nam">secs</span><span class="op">,</span> <span class="nam">unit</span><span class="op">=</span><span class="str">"s"</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t237" href="#t237">237</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t238" href="#t238">238</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t239" href="#t239">239</a></span><span class="t"><span class="key">class</span> <span class="nam">StopWatchManager</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t240" href="#t240">240</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t241" href="#t241">241</a></span><span class="t"><span class="str">    A singleton which manages a pool of named stopwatches, such that executions to be timed by referring to a name only -</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t242" href="#t242">242</a></span><span class="t"><span class="str">    without the need for a limited scope.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t243" href="#t243">243</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t244" href="#t244">244</a></span><span class="t">    <span class="nam">_instance</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t245" href="#t245">245</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t246" href="#t246">246</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t247" href="#t247">247</a></span><span class="t">    <span class="key">def</span> <span class="nam">get_instance</span><span class="op">(</span><span class="nam">cls</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t248" href="#t248">248</a></span><span class="t">        <span class="key">if</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">_instance</span> <span class="key">is</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t249" href="#t249">249</a></span><span class="t">            <span class="nam">cls</span><span class="op">.</span><span class="nam">_instance</span> <span class="op">=</span> <span class="nam">StopWatchManager</span><span class="op">(</span><span class="num">42</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t250" href="#t250">250</a></span><span class="t">        <span class="key">return</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">_instance</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t251" href="#t251">251</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t252" href="#t252">252</a></span><span class="t">    <span class="key">def</span> <span class="nam">__init__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">secret</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t253" href="#t253">253</a></span><span class="t">        <span class="key">if</span> <span class="nam">secret</span> <span class="op">!=</span> <span class="num">42</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t254" href="#t254">254</a></span><span class="t">            <span class="key">raise</span> <span class="nam">Exception</span><span class="op">(</span><span class="str">"Use only the singleton instance via getInstance"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t255" href="#t255">255</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span> <span class="op">=</span> <span class="op">{</span><span class="op">}</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t256" href="#t256">256</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t257" href="#t257">257</a></span><span class="t">    <span class="key">def</span> <span class="nam">start</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">name</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t258" href="#t258">258</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span><span class="op">[</span><span class="nam">name</span><span class="op">]</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t259" href="#t259">259</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t260" href="#t260">260</a></span><span class="t">    <span class="key">def</span> <span class="nam">stop</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">name</span><span class="op">)</span> <span class="op">-></span> <span class="nam">float</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t261" href="#t261">261</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t262" href="#t262">262</a></span><span class="t"><span class="str">        :param name: the name of the stopwatch</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t263" href="#t263">263</a></span><span class="t"><span class="str">        :return: the time that has passed in seconds</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t264" href="#t264">264</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t265" href="#t265">265</a></span><span class="t">        <span class="nam">time_passed_secs</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span> <span class="op">-</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span><span class="op">[</span><span class="nam">name</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t266" href="#t266">266</a></span><span class="t">        <span class="key">del</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span><span class="op">[</span><span class="nam">name</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t267" href="#t267">267</a></span><span class="t">        <span class="key">return</span> <span class="nam">time_passed_secs</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t268" href="#t268">268</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t269" href="#t269">269</a></span><span class="t">    <span class="key">def</span> <span class="nam">is_running</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">name</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t270" href="#t270">270</a></span><span class="t">        <span class="key">return</span> <span class="nam">name</span> <span class="key">in</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t271" href="#t271">271</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t272" href="#t272">272</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t273" href="#t273">273</a></span><span class="t"><span class="key">class</span> <span class="nam">LogTime</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t274" href="#t274">274</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t275" href="#t275">275</a></span><span class="t"><span class="str">    An execution time logger which can be conveniently applied using a with-statement - in order to log the executing time of the respective</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t276" href="#t276">276</a></span><span class="t"><span class="str">    with-block.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t277" href="#t277">277</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t278" href="#t278">278</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t279" href="#t279">279</a></span><span class="t">    <span class="key">def</span> <span class="nam">__init__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">name</span><span class="op">,</span> <span class="nam">enabled</span><span class="op">=</span><span class="key">True</span><span class="op">,</span> <span class="nam">logger</span><span class="op">:</span> <span class="nam">Logger</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t280" href="#t280">280</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t281" href="#t281">281</a></span><span class="t"><span class="str">        :param name: the name of the event whose time is to be logged upon completion as "&lt;name> completed in &lt;time>"</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t282" href="#t282">282</a></span><span class="t"><span class="str">        :param enabled: whether the logging is actually enabled; can be set to False to disable logging without necessitating</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t283" href="#t283">283</a></span><span class="t"><span class="str">            changes to client code</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t284" href="#t284">284</a></span><span class="t"><span class="str">        :param logger: the logger to use; if None, use the logger of LogTime's module</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t285" href="#t285">285</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t286" href="#t286">286</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">name</span> <span class="op">=</span> <span class="nam">name</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t287" href="#t287">287</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span> <span class="op">=</span> <span class="nam">enabled</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t288" href="#t288">288</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">stopwatch</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t289" href="#t289">289</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">logger</span> <span class="op">=</span> <span class="nam">logger</span> <span class="key">if</span> <span class="nam">logger</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span> <span class="key">else</span> <span class="nam">log</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t290" href="#t290">290</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t291" href="#t291">291</a></span><span class="t">    <span class="key">def</span> <span class="nam">start</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t292" href="#t292">292</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t293" href="#t293">293</a></span><span class="t"><span class="str">        Starts the stopwatch</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t294" href="#t294">294</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t295" href="#t295">295</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">stopwatch</span> <span class="op">=</span> <span class="nam">StopWatch</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t296" href="#t296">296</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t297" href="#t297">297</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">logger</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"{self.name} starting ..."</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t298" href="#t298">298</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t299" href="#t299">299</a></span><span class="t">    <span class="key">def</span> <span class="nam">stop</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t300" href="#t300">300</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t301" href="#t301">301</a></span><span class="t"><span class="str">        Stops the stopwatch and logs the time taken (if enabled)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t302" href="#t302">302</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t303" href="#t303">303</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">stopwatch</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span> <span class="key">and</span> <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t304" href="#t304">304</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">logger</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"{self.name} completed in {self.stopwatch.get_elapsed_time_string()}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t305" href="#t305">305</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t306" href="#t306">306</a></span><span class="t">    <span class="key">def</span> <span class="nam">__exit__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">exc_type</span><span class="op">,</span> <span class="nam">exc_value</span><span class="op">,</span> <span class="nam">traceback</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t307" href="#t307">307</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">stop</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t308" href="#t308">308</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t309" href="#t309">309</a></span><span class="t">    <span class="key">def</span> <span class="nam">__enter__</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t310" href="#t310">310</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">start</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t311" href="#t311">311</a></span><span class="t">        <span class="key">return</span> <span class="nam">self</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t312" href="#t312">312</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t313" href="#t313">313</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t314" href="#t314">314</a></span><span class="t"><span class="key">class</span> <span class="nam">FileLoggerContext</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t315" href="#t315">315</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t316" href="#t316">316</a></span><span class="t"><span class="str">    A context handler to be used in conjunction with Python's `with` statement which enables file-based logging.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t317" href="#t317">317</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t318" href="#t318">318</a></span><span class="t">    <span class="key">def</span> <span class="nam">__init__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">str</span><span class="op">,</span> <span class="nam">enabled</span><span class="op">=</span><span class="key">True</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t319" href="#t319">319</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t320" href="#t320">320</a></span><span class="t"><span class="str">        :param path: the path to the log file</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t321" href="#t321">321</a></span><span class="t"><span class="str">        :param enabled: whether to actually perform any logging.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t322" href="#t322">322</a></span><span class="t"><span class="str">            This switch allows the with statement to be applied regardless of whether logging shall be enabled.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t323" href="#t323">323</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t324" href="#t324">324</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span> <span class="op">=</span> <span class="nam">enabled</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t325" href="#t325">325</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">path</span> <span class="op">=</span> <span class="nam">path</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t326" href="#t326">326</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_log_handler</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t327" href="#t327">327</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t328" href="#t328">328</a></span><span class="t">    <span class="key">def</span> <span class="nam">__enter__</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t329" href="#t329">329</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t330" href="#t330">330</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">_log_handler</span> <span class="op">=</span> <span class="nam">add_file_logger</span><span class="op">(</span><span class="nam">self</span><span class="op">.</span><span class="nam">path</span><span class="op">,</span> <span class="nam">register_atexit</span><span class="op">=</span><span class="key">False</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t331" href="#t331">331</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t332" href="#t332">332</a></span><span class="t">    <span class="key">def</span> <span class="nam">__exit__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">exc_type</span><span class="op">,</span> <span class="nam">exc_value</span><span class="op">,</span> <span class="nam">traceback</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t333" href="#t333">333</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_log_handler</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t334" href="#t334">334</a></span><span class="t">            <span class="nam">remove_log_handler</span><span class="op">(</span><span class="nam">self</span><span class="op">.</span><span class="nam">_log_handler</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t50" href="#t50">50</a></span><span class="t">    <span class="key">global</span> <span class="nam">_configureCallbacks</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t51" href="#t51">51</a></span><span class="t">    <span class="key">if</span> <span class="key">not</span> <span class="nam">append</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t52" href="#t52">52</a></span><span class="t">        <span class="nam">_configureCallbacks</span> <span class="op">=</span> <span class="op">[</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t53" href="#t53">53</a></span><span class="t">    <span class="nam">_configureCallbacks</span><span class="op">.</span><span class="nam">append</span><span class="op">(</span><span class="nam">callback</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t54" href="#t54">54</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t55" href="#t55">55</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t56" href="#t56">56</a></span><span class="t"><span class="com"># noinspection PyShadowingBuiltins</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t57" href="#t57">57</a></span><span class="t"><span class="key">def</span> <span class="nam">configure</span><span class="op">(</span><span class="nam">format</span><span class="op">=</span><span class="nam">LOG_DEFAULT_FORMAT</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">lg</span><span class="op">.</span><span class="nam">DEBUG</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t58" href="#t58">58</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t59" href="#t59">59</a></span><span class="t"><span class="str">    Configures logging to stdout with the given format and log level,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t60" href="#t60">60</a></span><span class="t"><span class="str">    also configuring the default log levels of some overly verbose libraries as well as some pandas output options.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t61" href="#t61">61</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t62" href="#t62">62</a></span><span class="t"><span class="str">    :param format: the log format</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t63" href="#t63">63</a></span><span class="t"><span class="str">    :param level: the minimum log level</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t64" href="#t64">64</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t65" href="#t65">65</a></span><span class="t">    <span class="key">global</span> <span class="nam">_logFormat</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t66" href="#t66">66</a></span><span class="t">    <span class="nam">_logFormat</span> <span class="op">=</span> <span class="nam">format</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t67" href="#t67">67</a></span><span class="t">    <span class="nam">remove_log_handlers</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t68" href="#t68">68</a></span><span class="t">    <span class="nam">basicConfig</span><span class="op">(</span><span class="nam">level</span><span class="op">=</span><span class="nam">level</span><span class="op">,</span> <span class="nam">format</span><span class="op">=</span><span class="nam">format</span><span class="op">,</span> <span class="nam">stream</span><span class="op">=</span><span class="nam">sys</span><span class="op">.</span><span class="nam">stdout</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t69" href="#t69">69</a></span><span class="t">    <span class="nam">getLogger</span><span class="op">(</span><span class="str">"matplotlib"</span><span class="op">)</span><span class="op">.</span><span class="nam">setLevel</span><span class="op">(</span><span class="nam">lg</span><span class="op">.</span><span class="nam">INFO</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t70" href="#t70">70</a></span><span class="t">    <span class="nam">getLogger</span><span class="op">(</span><span class="str">"urllib3"</span><span class="op">)</span><span class="op">.</span><span class="nam">setLevel</span><span class="op">(</span><span class="nam">lg</span><span class="op">.</span><span class="nam">INFO</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t71" href="#t71">71</a></span><span class="t">    <span class="nam">getLogger</span><span class="op">(</span><span class="str">"msal"</span><span class="op">)</span><span class="op">.</span><span class="nam">setLevel</span><span class="op">(</span><span class="nam">lg</span><span class="op">.</span><span class="nam">INFO</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t72" href="#t72">72</a></span><span class="t">    <span class="nam">pd</span><span class="op">.</span><span class="nam">set_option</span><span class="op">(</span><span class="str">'display.max_colwidth'</span><span class="op">,</span> <span class="num">255</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t73" href="#t73">73</a></span><span class="t">    <span class="key">for</span> <span class="nam">callback</span> <span class="key">in</span> <span class="nam">_configureCallbacks</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t74" href="#t74">74</a></span><span class="t">        <span class="nam">callback</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t75" href="#t75">75</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t76" href="#t76">76</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t77" href="#t77">77</a></span><span class="t"><span class="com"># noinspection PyShadowingBuiltins</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t78" href="#t78">78</a></span><span class="t"><span class="key">def</span> <span class="nam">run_main</span><span class="op">(</span><span class="nam">main_fn</span><span class="op">:</span> <span class="nam">Callable</span><span class="op">[</span><span class="op">[</span><span class="op">]</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span><span class="op">,</span> <span class="nam">format</span><span class="op">=</span><span class="nam">LOG_DEFAULT_FORMAT</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">lg</span><span class="op">.</span><span class="nam">DEBUG</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t79" href="#t79">79</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t80" href="#t80">80</a></span><span class="t"><span class="str">    Configures logging with the given parameters, ensuring that any exceptions that occur during</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t81" href="#t81">81</a></span><span class="t"><span class="str">    the execution of the given function are logged.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t82" href="#t82">82</a></span><span class="t"><span class="str">    Logs two additional messages, one before the execution of the function, and one upon its completion.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t83" href="#t83">83</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t84" href="#t84">84</a></span><span class="t"><span class="str">    :param main_fn: the function to be executed</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t85" href="#t85">85</a></span><span class="t"><span class="str">    :param format: the log message format</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t86" href="#t86">86</a></span><span class="t"><span class="str">    :param level: the minimum log level</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t87" href="#t87">87</a></span><span class="t"><span class="str">    :return: the result of `main_fn`</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t88" href="#t88">88</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t89" href="#t89">89</a></span><span class="t">    <span class="nam">configure</span><span class="op">(</span><span class="nam">format</span><span class="op">=</span><span class="nam">format</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">level</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t90" href="#t90">90</a></span><span class="t">    <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">"Starting"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t91" href="#t91">91</a></span><span class="t">    <span class="key">try</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t92" href="#t92">92</a></span><span class="t">        <span class="nam">result</span> <span class="op">=</span> <span class="nam">main_fn</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t93" href="#t93">93</a></span><span class="t">        <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">"Done"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t94" href="#t94">94</a></span><span class="t">        <span class="key">return</span> <span class="nam">result</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t95" href="#t95">95</a></span><span class="t">    <span class="key">except</span> <span class="nam">Exception</span> <span class="key">as</span> <span class="nam">e</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t96" href="#t96">96</a></span><span class="t">        <span class="nam">log</span><span class="op">.</span><span class="nam">error</span><span class="op">(</span><span class="str">"Exception during script execution"</span><span class="op">,</span> <span class="nam">exc_info</span><span class="op">=</span><span class="nam">e</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t97" href="#t97">97</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t98" href="#t98">98</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t99" href="#t99">99</a></span><span class="t"><span class="key">def</span> <span class="nam">run_cli</span><span class="op">(</span><span class="nam">main_fn</span><span class="op">:</span> <span class="nam">Callable</span><span class="op">[</span><span class="op">[</span><span class="op">]</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span><span class="op">,</span> <span class="nam">format</span><span class="op">=</span><span class="nam">LOG_DEFAULT_FORMAT</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">lg</span><span class="op">.</span><span class="nam">DEBUG</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t100" href="#t100">100</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t101" href="#t101">101</a></span><span class="t"><span class="str">    Configures logging with the given parameters and runs the given main function as a</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t102" href="#t102">102</a></span><span class="t"><span class="str">    CLI using `jsonargparse` (which is configured to also parse attribute docstrings, such</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t103" href="#t103">103</a></span><span class="t"><span class="str">    that dataclasses can be used as function arguments).</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t104" href="#t104">104</a></span><span class="t"><span class="str">    Using this function requires that `jsonargparse` and `docstring_parser` be available.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t105" href="#t105">105</a></span><span class="t"><span class="str">    Like `run_main`, two additional log messages will be logged (at the beginning and end</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t106" href="#t106">106</a></span><span class="t"><span class="str">    of the execution), and it is ensured that all exceptions will be logged.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t107" href="#t107">107</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t108" href="#t108">108</a></span><span class="t"><span class="str">    :param main_fn: the function to be executed</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t109" href="#t109">109</a></span><span class="t"><span class="str">    :param format: the log message format</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t110" href="#t110">110</a></span><span class="t"><span class="str">    :param level: the minimum log level</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t111" href="#t111">111</a></span><span class="t"><span class="str">    :return: the result of `main_fn`</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t112" href="#t112">112</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t113" href="#t113">113</a></span><span class="t">    <span class="key">from</span> <span class="nam">jsonargparse</span> <span class="key">import</span> <span class="nam">set_docstring_parse_options</span><span class="op">,</span> <span class="nam">CLI</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t114" href="#t114">114</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t115" href="#t115">115</a></span><span class="t">    <span class="nam">set_docstring_parse_options</span><span class="op">(</span><span class="nam">attribute_docstrings</span><span class="op">=</span><span class="key">True</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t116" href="#t116">116</a></span><span class="t">    <span class="key">return</span> <span class="nam">run_main</span><span class="op">(</span><span class="key">lambda</span><span class="op">:</span> <span class="nam">CLI</span><span class="op">(</span><span class="nam">main_fn</span><span class="op">)</span><span class="op">,</span> <span class="nam">format</span><span class="op">=</span><span class="nam">format</span><span class="op">,</span> <span class="nam">level</span><span class="op">=</span><span class="nam">level</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t117" href="#t117">117</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t118" href="#t118">118</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t119" href="#t119">119</a></span><span class="t"><span class="key">def</span> <span class="nam">datetime_tag</span><span class="op">(</span><span class="op">)</span> <span class="op">-></span> <span class="nam">str</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t120" href="#t120">120</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t121" href="#t121">121</a></span><span class="t"><span class="str">    :return: a string tag for use in log file names which contains the current date and time (compact but readable)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t122" href="#t122">122</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t123" href="#t123">123</a></span><span class="t">    <span class="key">return</span> <span class="nam">datetime</span><span class="op">.</span><span class="nam">now</span><span class="op">(</span><span class="op">)</span><span class="op">.</span><span class="nam">strftime</span><span class="op">(</span><span class="str">'%Y%m%d-%H%M%S'</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t124" href="#t124">124</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t125" href="#t125">125</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t126" href="#t126">126</a></span><span class="t"><span class="nam">_fileLoggerPaths</span><span class="op">:</span> <span class="nam">List</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="op">[</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t127" href="#t127">127</a></span><span class="t"><span class="nam">_isAtExitReportFileLoggerRegistered</span> <span class="op">=</span> <span class="key">False</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t128" href="#t128">128</a></span><span class="t"><span class="nam">_memoryLogStream</span><span class="op">:</span> <span class="nam">Optional</span><span class="op">[</span><span class="nam">StringIO</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t129" href="#t129">129</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t130" href="#t130">130</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t131" href="#t131">131</a></span><span class="t"><span class="key">def</span> <span class="nam">_at_exit_report_file_logger</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t132" href="#t132">132</a></span><span class="t">    <span class="key">for</span> <span class="nam">path</span> <span class="key">in</span> <span class="nam">_fileLoggerPaths</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t133" href="#t133">133</a></span><span class="t">        <span class="nam">print</span><span class="op">(</span><span class="str">f"A log file was saved to {path}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t134" href="#t134">134</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t135" href="#t135">135</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t136" href="#t136">136</a></span><span class="t"><span class="key">def</span> <span class="nam">add_file_logger</span><span class="op">(</span><span class="nam">path</span><span class="op">,</span> <span class="nam">register_atexit</span><span class="op">=</span><span class="key">True</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t137" href="#t137">137</a></span><span class="t">    <span class="key">global</span> <span class="nam">_isAtExitReportFileLoggerRegistered</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t138" href="#t138">138</a></span><span class="t">    <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"Logging to {path} ..."</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t139" href="#t139">139</a></span><span class="t">    <span class="nam">handler</span> <span class="op">=</span> <span class="nam">FileHandler</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t140" href="#t140">140</a></span><span class="t">    <span class="nam">handler</span><span class="op">.</span><span class="nam">setFormatter</span><span class="op">(</span><span class="nam">Formatter</span><span class="op">(</span><span class="nam">_logFormat</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t141" href="#t141">141</a></span><span class="t">    <span class="nam">Logger</span><span class="op">.</span><span class="nam">root</span><span class="op">.</span><span class="nam">addHandler</span><span class="op">(</span><span class="nam">handler</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t142" href="#t142">142</a></span><span class="t">    <span class="nam">_fileLoggerPaths</span><span class="op">.</span><span class="nam">append</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t143" href="#t143">143</a></span><span class="t">    <span class="key">if</span> <span class="key">not</span> <span class="nam">_isAtExitReportFileLoggerRegistered</span> <span class="key">and</span> <span class="nam">register_atexit</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t144" href="#t144">144</a></span><span class="t">        <span class="nam">atexit</span><span class="op">.</span><span class="nam">register</span><span class="op">(</span><span class="nam">_at_exit_report_file_logger</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t145" href="#t145">145</a></span><span class="t">        <span class="nam">_isAtExitReportFileLoggerRegistered</span> <span class="op">=</span> <span class="key">True</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t146" href="#t146">146</a></span><span class="t">    <span class="key">return</span> <span class="nam">handler</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t147" href="#t147">147</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t148" href="#t148">148</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t149" href="#t149">149</a></span><span class="t"><span class="key">def</span> <span class="nam">add_memory_logger</span><span class="op">(</span><span class="op">)</span> <span class="op">-></span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t150" href="#t150">150</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t151" href="#t151">151</a></span><span class="t"><span class="str">    Enables in-memory logging (if it is not already enabled), i.e. all log statements are written to a memory buffer and can later be</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t152" href="#t152">152</a></span><span class="t"><span class="str">    read via function `get_memory_log()`</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t153" href="#t153">153</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t154" href="#t154">154</a></span><span class="t">    <span class="key">global</span> <span class="nam">_memoryLogStream</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t155" href="#t155">155</a></span><span class="t">    <span class="key">if</span> <span class="nam">_memoryLogStream</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t156" href="#t156">156</a></span><span class="t">        <span class="key">return</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t157" href="#t157">157</a></span><span class="t">    <span class="nam">_memoryLogStream</span> <span class="op">=</span> <span class="nam">StringIO</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t158" href="#t158">158</a></span><span class="t">    <span class="nam">handler</span> <span class="op">=</span> <span class="nam">StreamHandler</span><span class="op">(</span><span class="nam">_memoryLogStream</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t159" href="#t159">159</a></span><span class="t">    <span class="nam">handler</span><span class="op">.</span><span class="nam">setFormatter</span><span class="op">(</span><span class="nam">Formatter</span><span class="op">(</span><span class="nam">_logFormat</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t160" href="#t160">160</a></span><span class="t">    <span class="nam">Logger</span><span class="op">.</span><span class="nam">root</span><span class="op">.</span><span class="nam">addHandler</span><span class="op">(</span><span class="nam">handler</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t161" href="#t161">161</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t162" href="#t162">162</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t163" href="#t163">163</a></span><span class="t"><span class="key">def</span> <span class="nam">get_memory_log</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t164" href="#t164">164</a></span><span class="t">    <span class="key">return</span> <span class="nam">_memoryLogStream</span><span class="op">.</span><span class="nam">getvalue</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t165" href="#t165">165</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t166" href="#t166">166</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t167" href="#t167">167</a></span><span class="t"><span class="key">class</span> <span class="nam">StopWatch</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t168" href="#t168">168</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t169" href="#t169">169</a></span><span class="t"><span class="str">    Represents a stop watch for timing an execution. Constructing an instance starts the stopwatch.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t170" href="#t170">170</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t171" href="#t171">171</a></span><span class="t">    <span class="key">def</span> <span class="nam">__init__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">start</span><span class="op">=</span><span class="key">True</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t172" href="#t172">172</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">start_time</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t173" href="#t173">173</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_elapsed_secs</span> <span class="op">=</span> <span class="num">0.0</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t174" href="#t174">174</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span> <span class="op">=</span> <span class="nam">start</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t175" href="#t175">175</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t176" href="#t176">176</a></span><span class="t">    <span class="key">def</span> <span class="nam">reset</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">start</span><span class="op">=</span><span class="key">True</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t177" href="#t177">177</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t178" href="#t178">178</a></span><span class="t"><span class="str">        Resets the stopwatch, setting the elapsed time to zero.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t179" href="#t179">179</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t180" href="#t180">180</a></span><span class="t"><span class="str">        :param start: whether to start the stopwatch immediately</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t181" href="#t181">181</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t182" href="#t182">182</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">start_time</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t183" href="#t183">183</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_elapsed_secs</span> <span class="op">=</span> <span class="num">0.0</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t184" href="#t184">184</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span> <span class="op">=</span> <span class="nam">start</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t185" href="#t185">185</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t186" href="#t186">186</a></span><span class="t">    <span class="key">def</span> <span class="nam">restart</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t187" href="#t187">187</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t188" href="#t188">188</a></span><span class="t"><span class="str">        Resets the stopwatch (setting the elapsed time to zero) and restarts it immediately</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t189" href="#t189">189</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t190" href="#t190">190</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">reset</span><span class="op">(</span><span class="nam">start</span><span class="op">=</span><span class="key">True</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t191" href="#t191">191</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t192" href="#t192">192</a></span><span class="t">    <span class="key">def</span> <span class="nam">_get_elapsed_time_since_last_start</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t193" href="#t193">193</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t194" href="#t194">194</a></span><span class="t">            <span class="key">return</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span> <span class="op">-</span> <span class="nam">self</span><span class="op">.</span><span class="nam">start_time</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t195" href="#t195">195</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t196" href="#t196">196</a></span><span class="t">            <span class="key">return</span> <span class="num">0</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t197" href="#t197">197</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t198" href="#t198">198</a></span><span class="t">    <span class="key">def</span> <span class="nam">pause</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t199" href="#t199">199</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t200" href="#t200">200</a></span><span class="t"><span class="str">        Pauses the stopwatch. It can be resumed via method 'resume'.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t201" href="#t201">201</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t202" href="#t202">202</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_elapsed_secs</span> <span class="op">+=</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_get_elapsed_time_since_last_start</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t203" href="#t203">203</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span> <span class="op">=</span> <span class="key">False</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t204" href="#t204">204</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t205" href="#t205">205</a></span><span class="t">    <span class="key">def</span> <span class="nam">resume</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t206" href="#t206">206</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t207" href="#t207">207</a></span><span class="t"><span class="str">        Resumes the stopwatch (assuming that it is currently paused). If the stopwatch is not paused,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t208" href="#t208">208</a></span><span class="t"><span class="str">        the method has no effect (and a warning is logged).</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t209" href="#t209">209</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t210" href="#t210">210</a></span><span class="t">        <span class="key">if</span> <span class="key">not</span> <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t211" href="#t211">211</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">start_time</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t212" href="#t212">212</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">is_running</span> <span class="op">=</span> <span class="key">True</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t213" href="#t213">213</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t214" href="#t214">214</a></span><span class="t">            <span class="nam">log</span><span class="op">.</span><span class="nam">warning</span><span class="op">(</span><span class="str">"Stopwatch is already running (resume has not effect)"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t215" href="#t215">215</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t216" href="#t216">216</a></span><span class="t">    <span class="key">def</span> <span class="nam">get_elapsed_time_secs</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span> <span class="op">-></span> <span class="nam">float</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t217" href="#t217">217</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t218" href="#t218">218</a></span><span class="t"><span class="str">        Gets the total elapsed time, in seconds, on this stopwatch.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t219" href="#t219">219</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t220" href="#t220">220</a></span><span class="t"><span class="str">        :return: the elapsed time in seconds</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t221" href="#t221">221</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t222" href="#t222">222</a></span><span class="t">        <span class="key">return</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_elapsed_secs</span> <span class="op">+</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_get_elapsed_time_since_last_start</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t223" href="#t223">223</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t224" href="#t224">224</a></span><span class="t">    <span class="key">def</span> <span class="nam">get_elapsed_timedelta</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span> <span class="op">-></span> <span class="nam">pd</span><span class="op">.</span><span class="nam">Timedelta</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t225" href="#t225">225</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t226" href="#t226">226</a></span><span class="t"><span class="str">        :return: the elapsed time as a pandas.Timedelta object</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t227" href="#t227">227</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t228" href="#t228">228</a></span><span class="t">        <span class="key">return</span> <span class="nam">pd</span><span class="op">.</span><span class="nam">Timedelta</span><span class="op">(</span><span class="nam">self</span><span class="op">.</span><span class="nam">get_elapsed_time_secs</span><span class="op">(</span><span class="op">)</span><span class="op">,</span> <span class="nam">unit</span><span class="op">=</span><span class="str">"s"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t229" href="#t229">229</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t230" href="#t230">230</a></span><span class="t">    <span class="key">def</span> <span class="nam">get_elapsed_time_string</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span> <span class="op">-></span> <span class="nam">str</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t231" href="#t231">231</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t232" href="#t232">232</a></span><span class="t"><span class="str">        :return: a string representation of the elapsed time</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t233" href="#t233">233</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t234" href="#t234">234</a></span><span class="t">        <span class="nam">secs</span> <span class="op">=</span> <span class="nam">self</span><span class="op">.</span><span class="nam">get_elapsed_time_secs</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t235" href="#t235">235</a></span><span class="t">        <span class="key">if</span> <span class="nam">secs</span> <span class="op">&lt;</span> <span class="num">60</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t236" href="#t236">236</a></span><span class="t">            <span class="key">return</span> <span class="str">f"{secs:.3f} seconds"</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t237" href="#t237">237</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t238" href="#t238">238</a></span><span class="t">            <span class="key">return</span> <span class="nam">str</span><span class="op">(</span><span class="nam">pd</span><span class="op">.</span><span class="nam">Timedelta</span><span class="op">(</span><span class="nam">secs</span><span class="op">,</span> <span class="nam">unit</span><span class="op">=</span><span class="str">"s"</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t239" href="#t239">239</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t240" href="#t240">240</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t241" href="#t241">241</a></span><span class="t"><span class="key">class</span> <span class="nam">StopWatchManager</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t242" href="#t242">242</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t243" href="#t243">243</a></span><span class="t"><span class="str">    A singleton which manages a pool of named stopwatches, such that executions to be timed by referring to a name only -</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t244" href="#t244">244</a></span><span class="t"><span class="str">    without the need for a limited scope.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t245" href="#t245">245</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t246" href="#t246">246</a></span><span class="t">    <span class="nam">_instance</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t247" href="#t247">247</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t248" href="#t248">248</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t249" href="#t249">249</a></span><span class="t">    <span class="key">def</span> <span class="nam">get_instance</span><span class="op">(</span><span class="nam">cls</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t250" href="#t250">250</a></span><span class="t">        <span class="key">if</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">_instance</span> <span class="key">is</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t251" href="#t251">251</a></span><span class="t">            <span class="nam">cls</span><span class="op">.</span><span class="nam">_instance</span> <span class="op">=</span> <span class="nam">StopWatchManager</span><span class="op">(</span><span class="num">42</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t252" href="#t252">252</a></span><span class="t">        <span class="key">return</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">_instance</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t253" href="#t253">253</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t254" href="#t254">254</a></span><span class="t">    <span class="key">def</span> <span class="nam">__init__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">secret</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t255" href="#t255">255</a></span><span class="t">        <span class="key">if</span> <span class="nam">secret</span> <span class="op">!=</span> <span class="num">42</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t256" href="#t256">256</a></span><span class="t">            <span class="key">raise</span> <span class="nam">Exception</span><span class="op">(</span><span class="str">"Use only the singleton instance via getInstance"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t257" href="#t257">257</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span> <span class="op">=</span> <span class="op">{</span><span class="op">}</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t258" href="#t258">258</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t259" href="#t259">259</a></span><span class="t">    <span class="key">def</span> <span class="nam">start</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">name</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t260" href="#t260">260</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span><span class="op">[</span><span class="nam">name</span><span class="op">]</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t261" href="#t261">261</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t262" href="#t262">262</a></span><span class="t">    <span class="key">def</span> <span class="nam">stop</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">name</span><span class="op">)</span> <span class="op">-></span> <span class="nam">float</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t263" href="#t263">263</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t264" href="#t264">264</a></span><span class="t"><span class="str">        :param name: the name of the stopwatch</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t265" href="#t265">265</a></span><span class="t"><span class="str">        :return: the time that has passed in seconds</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t266" href="#t266">266</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t267" href="#t267">267</a></span><span class="t">        <span class="nam">time_passed_secs</span> <span class="op">=</span> <span class="nam">time</span><span class="op">.</span><span class="nam">time</span><span class="op">(</span><span class="op">)</span> <span class="op">-</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span><span class="op">[</span><span class="nam">name</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t268" href="#t268">268</a></span><span class="t">        <span class="key">del</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span><span class="op">[</span><span class="nam">name</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t269" href="#t269">269</a></span><span class="t">        <span class="key">return</span> <span class="nam">time_passed_secs</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t270" href="#t270">270</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t271" href="#t271">271</a></span><span class="t">    <span class="key">def</span> <span class="nam">is_running</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">name</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t272" href="#t272">272</a></span><span class="t">        <span class="key">return</span> <span class="nam">name</span> <span class="key">in</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_stopWatches</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t273" href="#t273">273</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t274" href="#t274">274</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t275" href="#t275">275</a></span><span class="t"><span class="key">class</span> <span class="nam">LogTime</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t276" href="#t276">276</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t277" href="#t277">277</a></span><span class="t"><span class="str">    An execution time logger which can be conveniently applied using a with-statement - in order to log the executing time of the respective</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t278" href="#t278">278</a></span><span class="t"><span class="str">    with-block.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t279" href="#t279">279</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t280" href="#t280">280</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t281" href="#t281">281</a></span><span class="t">    <span class="key">def</span> <span class="nam">__init__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">name</span><span class="op">,</span> <span class="nam">enabled</span><span class="op">=</span><span class="key">True</span><span class="op">,</span> <span class="nam">logger</span><span class="op">:</span> <span class="nam">Logger</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t282" href="#t282">282</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t283" href="#t283">283</a></span><span class="t"><span class="str">        :param name: the name of the event whose time is to be logged upon completion as "&lt;name> completed in &lt;time>"</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t284" href="#t284">284</a></span><span class="t"><span class="str">        :param enabled: whether the logging is actually enabled; can be set to False to disable logging without necessitating</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t285" href="#t285">285</a></span><span class="t"><span class="str">            changes to client code</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t286" href="#t286">286</a></span><span class="t"><span class="str">        :param logger: the logger to use; if None, use the logger of LogTime's module</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t287" href="#t287">287</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t288" href="#t288">288</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">name</span> <span class="op">=</span> <span class="nam">name</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t289" href="#t289">289</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span> <span class="op">=</span> <span class="nam">enabled</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t290" href="#t290">290</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">stopwatch</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t291" href="#t291">291</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">logger</span> <span class="op">=</span> <span class="nam">logger</span> <span class="key">if</span> <span class="nam">logger</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span> <span class="key">else</span> <span class="nam">log</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t292" href="#t292">292</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t293" href="#t293">293</a></span><span class="t">    <span class="key">def</span> <span class="nam">start</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t294" href="#t294">294</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t295" href="#t295">295</a></span><span class="t"><span class="str">        Starts the stopwatch</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t296" href="#t296">296</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t297" href="#t297">297</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">stopwatch</span> <span class="op">=</span> <span class="nam">StopWatch</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t298" href="#t298">298</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t299" href="#t299">299</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">logger</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"{self.name} starting ..."</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t300" href="#t300">300</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t301" href="#t301">301</a></span><span class="t">    <span class="key">def</span> <span class="nam">stop</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t302" href="#t302">302</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t303" href="#t303">303</a></span><span class="t"><span class="str">        Stops the stopwatch and logs the time taken (if enabled)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t304" href="#t304">304</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t305" href="#t305">305</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">stopwatch</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span> <span class="key">and</span> <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t306" href="#t306">306</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">logger</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"{self.name} completed in {self.stopwatch.get_elapsed_time_string()}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t307" href="#t307">307</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t308" href="#t308">308</a></span><span class="t">    <span class="key">def</span> <span class="nam">__exit__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">exc_type</span><span class="op">,</span> <span class="nam">exc_value</span><span class="op">,</span> <span class="nam">traceback</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t309" href="#t309">309</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">stop</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t310" href="#t310">310</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t311" href="#t311">311</a></span><span class="t">    <span class="key">def</span> <span class="nam">__enter__</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t312" href="#t312">312</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">start</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t313" href="#t313">313</a></span><span class="t">        <span class="key">return</span> <span class="nam">self</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t314" href="#t314">314</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t315" href="#t315">315</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t316" href="#t316">316</a></span><span class="t"><span class="key">class</span> <span class="nam">FileLoggerContext</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t317" href="#t317">317</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t318" href="#t318">318</a></span><span class="t"><span class="str">    A context handler to be used in conjunction with Python's `with` statement which enables file-based logging.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t319" href="#t319">319</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t320" href="#t320">320</a></span><span class="t">    <span class="key">def</span> <span class="nam">__init__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">path</span><span class="op">:</span> <span class="nam">str</span><span class="op">,</span> <span class="nam">enabled</span><span class="op">=</span><span class="key">True</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t321" href="#t321">321</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t322" href="#t322">322</a></span><span class="t"><span class="str">        :param path: the path to the log file</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t323" href="#t323">323</a></span><span class="t"><span class="str">        :param enabled: whether to actually perform any logging.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t324" href="#t324">324</a></span><span class="t"><span class="str">            This switch allows the with statement to be applied regardless of whether logging shall be enabled.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t325" href="#t325">325</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t326" href="#t326">326</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span> <span class="op">=</span> <span class="nam">enabled</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t327" href="#t327">327</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">path</span> <span class="op">=</span> <span class="nam">path</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t328" href="#t328">328</a></span><span class="t">        <span class="nam">self</span><span class="op">.</span><span class="nam">_log_handler</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t329" href="#t329">329</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t330" href="#t330">330</a></span><span class="t">    <span class="key">def</span> <span class="nam">__enter__</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t331" href="#t331">331</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">enabled</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t332" href="#t332">332</a></span><span class="t">            <span class="nam">self</span><span class="op">.</span><span class="nam">_log_handler</span> <span class="op">=</span> <span class="nam">add_file_logger</span><span class="op">(</span><span class="nam">self</span><span class="op">.</span><span class="nam">path</span><span class="op">,</span> <span class="nam">register_atexit</span><span class="op">=</span><span class="key">False</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t333" href="#t333">333</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t334" href="#t334">334</a></span><span class="t">    <span class="key">def</span> <span class="nam">__exit__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">exc_type</span><span class="op">,</span> <span class="nam">exc_value</span><span class="op">,</span> <span class="nam">traceback</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t335" href="#t335">335</a></span><span class="t">        <span class="key">if</span> <span class="nam">self</span><span class="op">.</span><span class="nam">_log_handler</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t336" href="#t336">336</a></span><span class="t">            <span class="nam">remove_log_handler</span><span class="op">(</span><span class="nam">self</span><span class="op">.</span><span class="nam">_log_handler</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
 </main>
 <footer>
     <div class="content">
@@ -423,7 +425,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_math_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_math_py.html b/coverage/d_3ccb7b6033502eb6_math_py.html
index ab92269c..4f0de2b8 100644
--- a/coverage/d_3ccb7b6033502eb6_math_py.html
+++ b/coverage/d_3ccb7b6033502eb6_math_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_multiprocessing_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -132,7 +132,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_multiprocessing_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_multiprocessing_py.html b/coverage/d_3ccb7b6033502eb6_multiprocessing_py.html
index 2d238d5d..d8a84075 100644
--- a/coverage/d_3ccb7b6033502eb6_multiprocessing_py.html
+++ b/coverage/d_3ccb7b6033502eb6_multiprocessing_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_pandas_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -138,7 +138,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_pandas_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_pandas_py.html b/coverage/d_3ccb7b6033502eb6_pandas_py.html
index 3b5f5165..2eddaa24 100644
--- a/coverage/d_3ccb7b6033502eb6_pandas_py.html
+++ b/coverage/d_3ccb7b6033502eb6_pandas_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_pickle_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -231,7 +231,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_pickle_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_pickle_py.html b/coverage/d_3ccb7b6033502eb6_pickle_py.html
index 3e834fc9..da1fa787 100644
--- a/coverage/d_3ccb7b6033502eb6_pickle_py.html
+++ b/coverage/d_3ccb7b6033502eb6_pickle_py.html
@@ -2,7 +2,7 @@
 <html>
 <head>
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
-    <title>Coverage for src/sensai/util/pickle.py: 34%</title>
+    <title>Coverage for src/sensai/util/pickle.py: 33%</title>
     <link rel="icon" sizes="32x32" href="favicon_32.png">
     <link rel="stylesheet" href="style.css" type="text/css">
     <script type="text/javascript" src="coverage_html.js" defer></script>
@@ -12,7 +12,7 @@
     <div class="content">
         <h1>
             <span class="text">Coverage for </span><b>src/sensai/util/pickle.py</b>:
-            <span class="pc_cov">34%</span>
+            <span class="pc_cov">33%</span>
         </h1>
         <aside id="help_panel_wrapper">
             <input id="help_panel_state" type="checkbox">
@@ -54,9 +54,9 @@ <h1>
             </div>
         </aside>
         <h2>
-            <span class="text">133 statements &nbsp;</span>
-            <button type="button" class="run button_toggle_run" value="run" data-shortcut="r" title="Toggle lines run">45<span class="text"> run</span></button>
-            <button type="button" class="mis show_mis button_toggle_mis" value="mis" data-shortcut="m" title="Toggle lines missing">88<span class="text"> missing</span></button>
+            <span class="text">141 statements &nbsp;</span>
+            <button type="button" class="run button_toggle_run" value="run" data-shortcut="r" title="Toggle lines run">47<span class="text"> run</span></button>
+            <button type="button" class="mis show_mis button_toggle_mis" value="mis" data-shortcut="m" title="Toggle lines missing">94<span class="text"> missing</span></button>
             <button type="button" class="exc show_exc button_toggle_exc" value="exc" data-shortcut="x" title="Toggle lines excluded">0<span class="text"> excluded</span></button>
         </h2>
         <p class="text">
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_plot_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -84,11 +84,11 @@ <h2>
     <p class="run"><span class="n"><a id="t2" href="#t2">2</a></span><span class="t"><span class="key">import</span> <span class="nam">os</span>&nbsp;</span><span class="r"></span></p>
     <p class="run"><span class="n"><a id="t3" href="#t3">3</a></span><span class="t"><span class="key">import</span> <span class="nam">pickle</span>&nbsp;</span><span class="r"></span></p>
     <p class="run"><span class="n"><a id="t4" href="#t4">4</a></span><span class="t"><span class="key">from</span> <span class="nam">pathlib</span> <span class="key">import</span> <span class="nam">Path</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t5" href="#t5">5</a></span><span class="t"><span class="key">from</span> <span class="nam">typing</span> <span class="key">import</span> <span class="nam">List</span><span class="op">,</span> <span class="nam">Dict</span><span class="op">,</span> <span class="nam">Any</span><span class="op">,</span> <span class="nam">Iterable</span><span class="op">,</span> <span class="nam">Union</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t5" href="#t5">5</a></span><span class="t"><span class="key">from</span> <span class="nam">typing</span> <span class="key">import</span> <span class="nam">Any</span><span class="op">,</span> <span class="nam">Callable</span><span class="op">,</span> <span class="nam">Dict</span><span class="op">,</span> <span class="nam">Iterable</span><span class="op">,</span> <span class="nam">List</span><span class="op">,</span> <span class="nam">Union</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t6" href="#t6">6</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="run"><span class="n"><a id="t7" href="#t7">7</a></span><span class="t"><span class="key">import</span> <span class="nam">joblib</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t8" href="#t8">8</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t9" href="#t9">9</a></span><span class="t"><span class="key">from</span> <span class="op">.</span><span class="nam">io</span> <span class="key">import</span> <span class="nam">is_s3_path</span><span class="op">,</span> <span class="nam">S3Object</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t9" href="#t9">9</a></span><span class="t"><span class="key">from</span> <span class="op">.</span><span class="nam">io</span> <span class="key">import</span> <span class="nam">S3Object</span><span class="op">,</span> <span class="nam">is_s3_path</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t10" href="#t10">10</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="run"><span class="n"><a id="t11" href="#t11">11</a></span><span class="t"><span class="nam">log</span> <span class="op">=</span> <span class="nam">logging</span><span class="op">.</span><span class="nam">getLogger</span><span class="op">(</span><span class="nam">__name__</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t12" href="#t12">12</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
@@ -98,218 +98,235 @@ <h2>
     <p class="mis show_mis"><span class="n"><a id="t16" href="#t16">16</a></span><span class="t">        <span class="nam">path</span> <span class="op">=</span> <span class="nam">str</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t17" href="#t17">17</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="run"><span class="n"><a id="t18" href="#t18">18</a></span><span class="t">    <span class="key">def</span> <span class="nam">read_file</span><span class="op">(</span><span class="nam">f</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t19" href="#t19">19</a></span><span class="t">        <span class="key">if</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"pickle"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t19" href="#t19">19</a></span><span class="t">        <span class="key">def</span> <span class="nam">_load_with_error_log</span><span class="op">(</span><span class="nam">loader</span><span class="op">:</span> <span class="nam">Callable</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="run"><span class="n"><a id="t20" href="#t20">20</a></span><span class="t">            <span class="key">try</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t21" href="#t21">21</a></span><span class="t">                <span class="key">return</span> <span class="nam">pickle</span><span class="op">.</span><span class="nam">load</span><span class="op">(</span><span class="nam">f</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t22" href="#t22">22</a></span><span class="t">            <span class="key">except</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t21" href="#t21">21</a></span><span class="t">                <span class="key">return</span> <span class="nam">loader</span><span class="op">(</span><span class="nam">f</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t22" href="#t22">22</a></span><span class="t">            <span class="key">except</span> <span class="nam">Exception</span> <span class="key">as</span> <span class="nam">e</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="mis show_mis"><span class="n"><a id="t23" href="#t23">23</a></span><span class="t">                <span class="nam">log</span><span class="op">.</span><span class="nam">error</span><span class="op">(</span><span class="str">f"Error loading {path}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t24" href="#t24">24</a></span><span class="t">                <span class="key">raise</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t25" href="#t25">25</a></span><span class="t">        <span class="key">elif</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"joblib"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t26" href="#t26">26</a></span><span class="t">            <span class="key">return</span> <span class="nam">joblib</span><span class="op">.</span><span class="nam">load</span><span class="op">(</span><span class="nam">f</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t27" href="#t27">27</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t28" href="#t28">28</a></span><span class="t">            <span class="key">raise</span> <span class="nam">ValueError</span><span class="op">(</span><span class="str">f"Unknown backend '{backend}'"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t29" href="#t29">29</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t30" href="#t30">30</a></span><span class="t">    <span class="key">if</span> <span class="nam">is_s3_path</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t31" href="#t31">31</a></span><span class="t">        <span class="key">return</span> <span class="nam">read_file</span><span class="op">(</span><span class="nam">S3Object</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span><span class="op">.</span><span class="nam">open_file</span><span class="op">(</span><span class="str">"rb"</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t32" href="#t32">32</a></span><span class="t">    <span class="key">with</span> <span class="nam">open</span><span class="op">(</span><span class="nam">path</span><span class="op">,</span> <span class="str">"rb"</span><span class="op">)</span> <span class="key">as</span> <span class="nam">f</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t33" href="#t33">33</a></span><span class="t">        <span class="key">return</span> <span class="nam">read_file</span><span class="op">(</span><span class="nam">f</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t34" href="#t34">34</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t24" href="#t24">24</a></span><span class="t">                <span class="key">raise</span> <span class="nam">e</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t25" href="#t25">25</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t26" href="#t26">26</a></span><span class="t">        <span class="key">if</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"pickle"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t27" href="#t27">27</a></span><span class="t">            <span class="key">return</span> <span class="nam">_load_with_error_log</span><span class="op">(</span><span class="nam">pickle</span><span class="op">.</span><span class="nam">load</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t28" href="#t28">28</a></span><span class="t">        <span class="key">elif</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"cloudpickle"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t29" href="#t29">29</a></span><span class="t">            <span class="key">import</span> <span class="nam">cloudpickle</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t30" href="#t30">30</a></span><span class="t">            <span class="key">return</span> <span class="nam">_load_with_error_log</span><span class="op">(</span><span class="nam">cloudpickle</span><span class="op">.</span><span class="nam">load</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t31" href="#t31">31</a></span><span class="t">        <span class="key">elif</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"joblib"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t32" href="#t32">32</a></span><span class="t">            <span class="key">return</span> <span class="nam">joblib</span><span class="op">.</span><span class="nam">load</span><span class="op">(</span><span class="nam">f</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t33" href="#t33">33</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t34" href="#t34">34</a></span><span class="t">            <span class="key">raise</span> <span class="nam">ValueError</span><span class="op">(</span><span class="str">f"Unknown backend '{backend}'. Supported backends are 'pickle', 'joblib' and 'cloudpickle'"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t35" href="#t35">35</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t36" href="#t36">36</a></span><span class="t"><span class="key">def</span> <span class="nam">dump_pickle</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="nam">pickle_path</span><span class="op">:</span> <span class="nam">Union</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Path</span><span class="op">]</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="str">"pickle"</span><span class="op">,</span> <span class="nam">protocol</span><span class="op">=</span><span class="nam">pickle</span><span class="op">.</span><span class="nam">HIGHEST_PROTOCOL</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t37" href="#t37">37</a></span><span class="t">    <span class="key">if</span> <span class="nam">isinstance</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">,</span> <span class="nam">Path</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t38" href="#t38">38</a></span><span class="t">        <span class="nam">pickle_path</span> <span class="op">=</span> <span class="nam">str</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t39" href="#t39">39</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t40" href="#t40">40</a></span><span class="t">    <span class="key">def</span> <span class="nam">open_file</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t41" href="#t41">41</a></span><span class="t">        <span class="key">if</span> <span class="nam">is_s3_path</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t42" href="#t42">42</a></span><span class="t">            <span class="key">return</span> <span class="nam">S3Object</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">)</span><span class="op">.</span><span class="nam">open_file</span><span class="op">(</span><span class="str">"wb"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t43" href="#t43">43</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t44" href="#t44">44</a></span><span class="t">            <span class="key">return</span> <span class="nam">open</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">,</span> <span class="str">"wb"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t36" href="#t36">36</a></span><span class="t">    <span class="key">if</span> <span class="nam">is_s3_path</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t37" href="#t37">37</a></span><span class="t">        <span class="key">return</span> <span class="nam">read_file</span><span class="op">(</span><span class="nam">S3Object</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span><span class="op">.</span><span class="nam">open_file</span><span class="op">(</span><span class="str">"rb"</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t38" href="#t38">38</a></span><span class="t">    <span class="key">with</span> <span class="nam">open</span><span class="op">(</span><span class="nam">path</span><span class="op">,</span> <span class="str">"rb"</span><span class="op">)</span> <span class="key">as</span> <span class="nam">f</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t39" href="#t39">39</a></span><span class="t">        <span class="key">return</span> <span class="nam">read_file</span><span class="op">(</span><span class="nam">f</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t40" href="#t40">40</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t41" href="#t41">41</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t42" href="#t42">42</a></span><span class="t"><span class="key">def</span> <span class="nam">dump_pickle</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="nam">pickle_path</span><span class="op">:</span> <span class="nam">Union</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Path</span><span class="op">]</span><span class="op">,</span> <span class="nam">backend</span><span class="op">=</span><span class="str">"pickle"</span><span class="op">,</span> <span class="nam">protocol</span><span class="op">=</span><span class="nam">pickle</span><span class="op">.</span><span class="nam">HIGHEST_PROTOCOL</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t43" href="#t43">43</a></span><span class="t">    <span class="key">if</span> <span class="nam">isinstance</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">,</span> <span class="nam">Path</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t44" href="#t44">44</a></span><span class="t">        <span class="nam">pickle_path</span> <span class="op">=</span> <span class="nam">str</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t45" href="#t45">45</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t46" href="#t46">46</a></span><span class="t">    <span class="nam">dir_name</span> <span class="op">=</span> <span class="nam">os</span><span class="op">.</span><span class="nam">path</span><span class="op">.</span><span class="nam">dirname</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t47" href="#t47">47</a></span><span class="t">    <span class="key">if</span> <span class="nam">dir_name</span> <span class="op">!=</span> <span class="str">""</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t48" href="#t48">48</a></span><span class="t">        <span class="nam">os</span><span class="op">.</span><span class="nam">makedirs</span><span class="op">(</span><span class="nam">dir_name</span><span class="op">,</span> <span class="nam">exist_ok</span><span class="op">=</span><span class="key">True</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t49" href="#t49">49</a></span><span class="t">    <span class="key">with</span> <span class="nam">open_file</span><span class="op">(</span><span class="op">)</span> <span class="key">as</span> <span class="nam">f</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t50" href="#t50">50</a></span><span class="t">        <span class="key">if</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"pickle"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t51" href="#t51">51</a></span><span class="t">            <span class="key">try</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t52" href="#t52">52</a></span><span class="t">                <span class="nam">pickle</span><span class="op">.</span><span class="nam">dump</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="nam">f</span><span class="op">,</span> <span class="nam">protocol</span><span class="op">=</span><span class="nam">protocol</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t53" href="#t53">53</a></span><span class="t">            <span class="key">except</span> <span class="nam">AttributeError</span> <span class="key">as</span> <span class="nam">e</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t54" href="#t54">54</a></span><span class="t">                <span class="nam">failing_paths</span> <span class="op">=</span> <span class="nam">PickleFailureDebugger</span><span class="op">.</span><span class="nam">debug_failure</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t55" href="#t55">55</a></span><span class="t">                <span class="key">raise</span> <span class="nam">AttributeError</span><span class="op">(</span><span class="str">f"Cannot pickle paths {failing_paths} of {obj}: {str(e)}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t56" href="#t56">56</a></span><span class="t">        <span class="key">elif</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"joblib"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t57" href="#t57">57</a></span><span class="t">            <span class="nam">joblib</span><span class="op">.</span><span class="nam">dump</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="nam">f</span><span class="op">,</span> <span class="nam">protocol</span><span class="op">=</span><span class="nam">protocol</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t58" href="#t58">58</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t59" href="#t59">59</a></span><span class="t">            <span class="key">raise</span> <span class="nam">ValueError</span><span class="op">(</span><span class="str">f"Unknown backend '{backend}'"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t60" href="#t60">60</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t61" href="#t61">61</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t62" href="#t62">62</a></span><span class="t"><span class="key">class</span> <span class="nam">PickleFailureDebugger</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t63" href="#t63">63</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t64" href="#t64">64</a></span><span class="t"><span class="str">    A collection of methods for testing whether objects can be pickled and logging useful infos in case they cannot</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t65" href="#t65">65</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t66" href="#t66">66</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t67" href="#t67">67</a></span><span class="t">    <span class="nam">enabled</span> <span class="op">=</span> <span class="key">False</span>  <span class="com"># global flag controlling the behaviour of logFailureIfEnabled</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t68" href="#t68">68</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t69" href="#t69">69</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t70" href="#t70">70</a></span><span class="t">    <span class="key">def</span> <span class="nam">_debug_failure</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">,</span> <span class="nam">path</span><span class="op">,</span> <span class="nam">failures</span><span class="op">,</span> <span class="nam">handled_object_ids</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t71" href="#t71">71</a></span><span class="t">        <span class="key">if</span> <span class="nam">id</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span> <span class="key">in</span> <span class="nam">handled_object_ids</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t72" href="#t72">72</a></span><span class="t">            <span class="key">return</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t73" href="#t73">73</a></span><span class="t">        <span class="nam">handled_object_ids</span><span class="op">.</span><span class="nam">add</span><span class="op">(</span><span class="nam">id</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t74" href="#t74">74</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t75" href="#t75">75</a></span><span class="t">        <span class="key">try</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t76" href="#t76">76</a></span><span class="t">            <span class="nam">pickle</span><span class="op">.</span><span class="nam">dumps</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t77" href="#t77">77</a></span><span class="t">        <span class="key">except</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t78" href="#t78">78</a></span><span class="t">            <span class="com"># determine dictionary of children to investigate (if any)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t79" href="#t79">79</a></span><span class="t">            <span class="key">if</span> <span class="nam">hasattr</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="str">'__dict__'</span><span class="op">)</span><span class="op">:</span>  <span class="com"># Because of strange behaviour of getstate, here try-except is used instead of if-else</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t80" href="#t80">80</a></span><span class="t">                <span class="key">try</span><span class="op">:</span>  <span class="com"># Because of strange behaviour of getattr(_, '__getstate__'), we here use try-except</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t81" href="#t81">81</a></span><span class="t">                    <span class="nam">d</span> <span class="op">=</span> <span class="nam">obj</span><span class="op">.</span><span class="nam">__getstate__</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t82" href="#t82">82</a></span><span class="t">                    <span class="key">if</span> <span class="nam">type</span><span class="op">(</span><span class="nam">d</span><span class="op">)</span> <span class="op">!=</span> <span class="nam">dict</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t83" href="#t83">83</a></span><span class="t">                        <span class="nam">d</span> <span class="op">=</span> <span class="op">{</span><span class="str">"state"</span><span class="op">:</span> <span class="nam">d</span><span class="op">}</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t84" href="#t84">84</a></span><span class="t">                <span class="key">except</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t85" href="#t85">85</a></span><span class="t">                    <span class="nam">d</span> <span class="op">=</span> <span class="nam">obj</span><span class="op">.</span><span class="nam">__dict__</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t86" href="#t86">86</a></span><span class="t">            <span class="key">elif</span> <span class="nam">type</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span> <span class="op">==</span> <span class="nam">dict</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t87" href="#t87">87</a></span><span class="t">                <span class="nam">d</span> <span class="op">=</span> <span class="nam">obj</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t88" href="#t88">88</a></span><span class="t">            <span class="key">elif</span> <span class="nam">type</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span> <span class="key">in</span> <span class="op">(</span><span class="nam">list</span><span class="op">,</span> <span class="nam">tuple</span><span class="op">,</span> <span class="nam">set</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t89" href="#t89">89</a></span><span class="t">                <span class="nam">d</span> <span class="op">=</span> <span class="nam">dict</span><span class="op">(</span><span class="nam">enumerate</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t90" href="#t90">90</a></span><span class="t">            <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t91" href="#t91">91</a></span><span class="t">                <span class="nam">d</span> <span class="op">=</span> <span class="op">{</span><span class="op">}</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t92" href="#t92">92</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t93" href="#t93">93</a></span><span class="t">            <span class="com"># recursively test children</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t94" href="#t94">94</a></span><span class="t">            <span class="nam">have_failed_child</span> <span class="op">=</span> <span class="key">False</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t95" href="#t95">95</a></span><span class="t">            <span class="key">for</span> <span class="nam">key</span><span class="op">,</span> <span class="nam">child</span> <span class="key">in</span> <span class="nam">d</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t96" href="#t96">96</a></span><span class="t">                <span class="nam">child_path</span> <span class="op">=</span> <span class="nam">list</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span> <span class="op">+</span> <span class="op">[</span><span class="str">f"{key}[{child.__class__.__name__}]"</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t97" href="#t97">97</a></span><span class="t">                <span class="nam">have_failed_child</span> <span class="op">=</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">_debug_failure</span><span class="op">(</span><span class="nam">child</span><span class="op">,</span> <span class="nam">child_path</span><span class="op">,</span> <span class="nam">failures</span><span class="op">,</span> <span class="nam">handled_object_ids</span><span class="op">)</span> <span class="key">or</span> <span class="nam">have_failed_child</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t98" href="#t98">98</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t99" href="#t99">99</a></span><span class="t">            <span class="key">if</span> <span class="key">not</span> <span class="nam">have_failed_child</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t100" href="#t100">100</a></span><span class="t">                <span class="nam">failures</span><span class="op">.</span><span class="nam">append</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t101" href="#t101">101</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t102" href="#t102">102</a></span><span class="t">            <span class="key">return</span> <span class="key">True</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t103" href="#t103">103</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t104" href="#t104">104</a></span><span class="t">            <span class="key">return</span> <span class="key">False</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t105" href="#t105">105</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t106" href="#t106">106</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t107" href="#t107">107</a></span><span class="t">    <span class="key">def</span> <span class="nam">debug_failure</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">)</span> <span class="op">-></span> <span class="nam">List</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t108" href="#t108">108</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t109" href="#t109">109</a></span><span class="t"><span class="str">        Recursively tries to pickle the given object and returns a list of failed paths</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t110" href="#t110">110</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t111" href="#t111">111</a></span><span class="t"><span class="str">        :param obj: the object for which to recursively test pickling</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t112" href="#t112">112</a></span><span class="t"><span class="str">        :return: a list of object paths that failed to pickle</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t113" href="#t113">113</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t114" href="#t114">114</a></span><span class="t">        <span class="nam">handled_object_ids</span> <span class="op">=</span> <span class="nam">set</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t115" href="#t115">115</a></span><span class="t">        <span class="nam">failures</span> <span class="op">=</span> <span class="op">[</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t116" href="#t116">116</a></span><span class="t">        <span class="nam">cls</span><span class="op">.</span><span class="nam">_debug_failure</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="op">[</span><span class="nam">obj</span><span class="op">.</span><span class="nam">__class__</span><span class="op">.</span><span class="nam">__name__</span><span class="op">]</span><span class="op">,</span> <span class="nam">failures</span><span class="op">,</span> <span class="nam">handled_object_ids</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t117" href="#t117">117</a></span><span class="t">        <span class="key">return</span> <span class="op">[</span><span class="str">"."</span><span class="op">.</span><span class="nam">join</span><span class="op">(</span><span class="nam">l</span><span class="op">)</span> <span class="key">for</span> <span class="nam">l</span> <span class="key">in</span> <span class="nam">failures</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t46" href="#t46">46</a></span><span class="t">    <span class="key">def</span> <span class="nam">open_file</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t47" href="#t47">47</a></span><span class="t">        <span class="key">if</span> <span class="nam">is_s3_path</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t48" href="#t48">48</a></span><span class="t">            <span class="key">return</span> <span class="nam">S3Object</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">)</span><span class="op">.</span><span class="nam">open_file</span><span class="op">(</span><span class="str">"wb"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t49" href="#t49">49</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t50" href="#t50">50</a></span><span class="t">            <span class="key">return</span> <span class="nam">open</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">,</span> <span class="str">"wb"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t51" href="#t51">51</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t52" href="#t52">52</a></span><span class="t">    <span class="nam">dir_name</span> <span class="op">=</span> <span class="nam">os</span><span class="op">.</span><span class="nam">path</span><span class="op">.</span><span class="nam">dirname</span><span class="op">(</span><span class="nam">pickle_path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t53" href="#t53">53</a></span><span class="t">    <span class="key">if</span> <span class="nam">dir_name</span> <span class="op">!=</span> <span class="str">""</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t54" href="#t54">54</a></span><span class="t">        <span class="nam">os</span><span class="op">.</span><span class="nam">makedirs</span><span class="op">(</span><span class="nam">dir_name</span><span class="op">,</span> <span class="nam">exist_ok</span><span class="op">=</span><span class="key">True</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t55" href="#t55">55</a></span><span class="t">    <span class="key">with</span> <span class="nam">open_file</span><span class="op">(</span><span class="op">)</span> <span class="key">as</span> <span class="nam">f</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t56" href="#t56">56</a></span><span class="t">        <span class="key">if</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"pickle"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t57" href="#t57">57</a></span><span class="t">            <span class="key">try</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t58" href="#t58">58</a></span><span class="t">                <span class="nam">pickle</span><span class="op">.</span><span class="nam">dump</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="nam">f</span><span class="op">,</span> <span class="nam">protocol</span><span class="op">=</span><span class="nam">protocol</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t59" href="#t59">59</a></span><span class="t">            <span class="key">except</span> <span class="nam">AttributeError</span> <span class="key">as</span> <span class="nam">e</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t60" href="#t60">60</a></span><span class="t">                <span class="nam">failing_paths</span> <span class="op">=</span> <span class="nam">PickleFailureDebugger</span><span class="op">.</span><span class="nam">debug_failure</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t61" href="#t61">61</a></span><span class="t">                <span class="key">raise</span> <span class="nam">AttributeError</span><span class="op">(</span><span class="str">f"Cannot pickle paths {failing_paths} of {obj}: {str(e)}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t62" href="#t62">62</a></span><span class="t">        <span class="key">elif</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"joblib"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t63" href="#t63">63</a></span><span class="t">            <span class="nam">joblib</span><span class="op">.</span><span class="nam">dump</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="nam">f</span><span class="op">,</span> <span class="nam">protocol</span><span class="op">=</span><span class="nam">protocol</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t64" href="#t64">64</a></span><span class="t">        <span class="key">elif</span> <span class="nam">backend</span> <span class="op">==</span> <span class="str">"cloudpickle"</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t65" href="#t65">65</a></span><span class="t">            <span class="key">import</span> <span class="nam">cloudpickle</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t66" href="#t66">66</a></span><span class="t">            <span class="nam">cloudpickle</span><span class="op">.</span><span class="nam">dump</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="nam">f</span><span class="op">,</span> <span class="nam">protocol</span><span class="op">=</span><span class="nam">protocol</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t67" href="#t67">67</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t68" href="#t68">68</a></span><span class="t">            <span class="key">raise</span> <span class="nam">ValueError</span><span class="op">(</span><span class="str">f"Unknown backend '{backend}'. Supported backends are 'pickle', 'joblib' and 'cloudpickle'"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t69" href="#t69">69</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t70" href="#t70">70</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t71" href="#t71">71</a></span><span class="t"><span class="key">class</span> <span class="nam">PickleFailureDebugger</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t72" href="#t72">72</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t73" href="#t73">73</a></span><span class="t"><span class="str">    A collection of methods for testing whether objects can be pickled and logging useful infos in case they cannot</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t74" href="#t74">74</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t75" href="#t75">75</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t76" href="#t76">76</a></span><span class="t">    <span class="nam">enabled</span> <span class="op">=</span> <span class="key">False</span>  <span class="com"># global flag controlling the behaviour of logFailureIfEnabled</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t77" href="#t77">77</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t78" href="#t78">78</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t79" href="#t79">79</a></span><span class="t">    <span class="key">def</span> <span class="nam">_debug_failure</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">,</span> <span class="nam">path</span><span class="op">,</span> <span class="nam">failures</span><span class="op">,</span> <span class="nam">handled_object_ids</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t80" href="#t80">80</a></span><span class="t">        <span class="key">if</span> <span class="nam">id</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span> <span class="key">in</span> <span class="nam">handled_object_ids</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t81" href="#t81">81</a></span><span class="t">            <span class="key">return</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t82" href="#t82">82</a></span><span class="t">        <span class="nam">handled_object_ids</span><span class="op">.</span><span class="nam">add</span><span class="op">(</span><span class="nam">id</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t83" href="#t83">83</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t84" href="#t84">84</a></span><span class="t">        <span class="key">try</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t85" href="#t85">85</a></span><span class="t">            <span class="nam">pickle</span><span class="op">.</span><span class="nam">dumps</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t86" href="#t86">86</a></span><span class="t">        <span class="key">except</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t87" href="#t87">87</a></span><span class="t">            <span class="com"># determine dictionary of children to investigate (if any)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t88" href="#t88">88</a></span><span class="t">            <span class="key">if</span> <span class="nam">hasattr</span><span class="op">(</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t89" href="#t89">89</a></span><span class="t">                <span class="nam">obj</span><span class="op">,</span> <span class="str">'__dict__'</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t90" href="#t90">90</a></span><span class="t">            <span class="op">)</span><span class="op">:</span>  <span class="com"># Because of strange behaviour of getstate, here try-except is used instead of if-else</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t91" href="#t91">91</a></span><span class="t">                <span class="key">try</span><span class="op">:</span>  <span class="com"># Because of strange behaviour of getattr(_, '__getstate__'), we here use try-except</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t92" href="#t92">92</a></span><span class="t">                    <span class="nam">d</span> <span class="op">=</span> <span class="nam">obj</span><span class="op">.</span><span class="nam">__getstate__</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t93" href="#t93">93</a></span><span class="t">                    <span class="key">if</span> <span class="nam">type</span><span class="op">(</span><span class="nam">d</span><span class="op">)</span> <span class="op">!=</span> <span class="nam">dict</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t94" href="#t94">94</a></span><span class="t">                        <span class="nam">d</span> <span class="op">=</span> <span class="op">{</span><span class="str">"state"</span><span class="op">:</span> <span class="nam">d</span><span class="op">}</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t95" href="#t95">95</a></span><span class="t">                <span class="key">except</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t96" href="#t96">96</a></span><span class="t">                    <span class="nam">d</span> <span class="op">=</span> <span class="nam">obj</span><span class="op">.</span><span class="nam">__dict__</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t97" href="#t97">97</a></span><span class="t">            <span class="key">elif</span> <span class="nam">type</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span> <span class="op">==</span> <span class="nam">dict</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t98" href="#t98">98</a></span><span class="t">                <span class="nam">d</span> <span class="op">=</span> <span class="nam">obj</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t99" href="#t99">99</a></span><span class="t">            <span class="key">elif</span> <span class="nam">type</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span> <span class="key">in</span> <span class="op">(</span><span class="nam">list</span><span class="op">,</span> <span class="nam">tuple</span><span class="op">,</span> <span class="nam">set</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t100" href="#t100">100</a></span><span class="t">                <span class="nam">d</span> <span class="op">=</span> <span class="nam">dict</span><span class="op">(</span><span class="nam">enumerate</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t101" href="#t101">101</a></span><span class="t">            <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t102" href="#t102">102</a></span><span class="t">                <span class="nam">d</span> <span class="op">=</span> <span class="op">{</span><span class="op">}</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t103" href="#t103">103</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t104" href="#t104">104</a></span><span class="t">            <span class="com"># recursively test children</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t105" href="#t105">105</a></span><span class="t">            <span class="nam">have_failed_child</span> <span class="op">=</span> <span class="key">False</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t106" href="#t106">106</a></span><span class="t">            <span class="key">for</span> <span class="nam">key</span><span class="op">,</span> <span class="nam">child</span> <span class="key">in</span> <span class="nam">d</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t107" href="#t107">107</a></span><span class="t">                <span class="nam">child_path</span> <span class="op">=</span> <span class="nam">list</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span> <span class="op">+</span> <span class="op">[</span><span class="str">f"{key}[{child.__class__.__name__}]"</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t108" href="#t108">108</a></span><span class="t">                <span class="nam">have_failed_child</span> <span class="op">=</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">_debug_failure</span><span class="op">(</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t109" href="#t109">109</a></span><span class="t">                    <span class="nam">child</span><span class="op">,</span> <span class="nam">child_path</span><span class="op">,</span> <span class="nam">failures</span><span class="op">,</span> <span class="nam">handled_object_ids</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t110" href="#t110">110</a></span><span class="t">                <span class="op">)</span> <span class="key">or</span> <span class="nam">have_failed_child</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t111" href="#t111">111</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t112" href="#t112">112</a></span><span class="t">            <span class="key">if</span> <span class="key">not</span> <span class="nam">have_failed_child</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t113" href="#t113">113</a></span><span class="t">                <span class="nam">failures</span><span class="op">.</span><span class="nam">append</span><span class="op">(</span><span class="nam">path</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t114" href="#t114">114</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t115" href="#t115">115</a></span><span class="t">            <span class="key">return</span> <span class="key">True</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t116" href="#t116">116</a></span><span class="t">        <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t117" href="#t117">117</a></span><span class="t">            <span class="key">return</span> <span class="key">False</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t118" href="#t118">118</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="run"><span class="n"><a id="t119" href="#t119">119</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t120" href="#t120">120</a></span><span class="t">    <span class="key">def</span> <span class="nam">log_failure_if_enabled</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">,</span> <span class="nam">context_info</span><span class="op">:</span> <span class="nam">str</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t120" href="#t120">120</a></span><span class="t">    <span class="key">def</span> <span class="nam">debug_failure</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">)</span> <span class="op">-></span> <span class="nam">List</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t121" href="#t121">121</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t122" href="#t122">122</a></span><span class="t"><span class="str">        If the class flag 'enabled' is set to true, the pickling of the given object is</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t123" href="#t123">123</a></span><span class="t"><span class="str">        recursively tested and the results are logged at error level if there are problems and</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t124" href="#t124">124</a></span><span class="t"><span class="str">        info level otherwise.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t125" href="#t125">125</a></span><span class="t"><span class="str">        If the flag is disabled, no action is taken.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t126" href="#t126">126</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t127" href="#t127">127</a></span><span class="t"><span class="str">        :param obj: the object for which to recursively test pickling</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t128" href="#t128">128</a></span><span class="t"><span class="str">        :param context_info: optional additional string to be included in the log message</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t129" href="#t129">129</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t130" href="#t130">130</a></span><span class="t">        <span class="key">if</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">enabled</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t131" href="#t131">131</a></span><span class="t">            <span class="nam">failures</span> <span class="op">=</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">debug_failure</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t132" href="#t132">132</a></span><span class="t">            <span class="nam">prefix</span> <span class="op">=</span> <span class="str">f"Picklability analysis for {obj}"</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t133" href="#t133">133</a></span><span class="t">            <span class="key">if</span> <span class="nam">context_info</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t134" href="#t134">134</a></span><span class="t">                <span class="nam">prefix</span> <span class="op">+=</span> <span class="str">" (context: %s)"</span> <span class="op">%</span> <span class="nam">context_info</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t135" href="#t135">135</a></span><span class="t">            <span class="key">if</span> <span class="nam">len</span><span class="op">(</span><span class="nam">failures</span><span class="op">)</span> <span class="op">></span> <span class="num">0</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t136" href="#t136">136</a></span><span class="t">                <span class="nam">log</span><span class="op">.</span><span class="nam">error</span><span class="op">(</span><span class="str">f"{prefix}: pickling would result in failures due to: {failures}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t137" href="#t137">137</a></span><span class="t">            <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t138" href="#t138">138</a></span><span class="t">                <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"{prefix}: is picklable"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t122" href="#t122">122</a></span><span class="t"><span class="str">        Recursively tries to pickle the given object and returns a list of failed paths</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t123" href="#t123">123</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t124" href="#t124">124</a></span><span class="t"><span class="str">        :param obj: the object for which to recursively test pickling</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t125" href="#t125">125</a></span><span class="t"><span class="str">        :return: a list of object paths that failed to pickle</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t126" href="#t126">126</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t127" href="#t127">127</a></span><span class="t">        <span class="nam">handled_object_ids</span> <span class="op">=</span> <span class="nam">set</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t128" href="#t128">128</a></span><span class="t">        <span class="nam">failures</span> <span class="op">=</span> <span class="op">[</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t129" href="#t129">129</a></span><span class="t">        <span class="nam">cls</span><span class="op">.</span><span class="nam">_debug_failure</span><span class="op">(</span><span class="nam">obj</span><span class="op">,</span> <span class="op">[</span><span class="nam">obj</span><span class="op">.</span><span class="nam">__class__</span><span class="op">.</span><span class="nam">__name__</span><span class="op">]</span><span class="op">,</span> <span class="nam">failures</span><span class="op">,</span> <span class="nam">handled_object_ids</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t130" href="#t130">130</a></span><span class="t">        <span class="key">return</span> <span class="op">[</span><span class="str">"."</span><span class="op">.</span><span class="nam">join</span><span class="op">(</span><span class="nam">l</span><span class="op">)</span> <span class="key">for</span> <span class="nam">l</span> <span class="key">in</span> <span class="nam">failures</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t131" href="#t131">131</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t132" href="#t132">132</a></span><span class="t">    <span class="op">@</span><span class="nam">classmethod</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t133" href="#t133">133</a></span><span class="t">    <span class="key">def</span> <span class="nam">log_failure_if_enabled</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">,</span> <span class="nam">context_info</span><span class="op">:</span> <span class="nam">str</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t134" href="#t134">134</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t135" href="#t135">135</a></span><span class="t"><span class="str">        If the class flag 'enabled' is set to true, the pickling of the given object is</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t136" href="#t136">136</a></span><span class="t"><span class="str">        recursively tested and the results are logged at error level if there are problems and</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t137" href="#t137">137</a></span><span class="t"><span class="str">        info level otherwise.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t138" href="#t138">138</a></span><span class="t"><span class="str">        If the flag is disabled, no action is taken.</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t139" href="#t139">139</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t140" href="#t140">140</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t141" href="#t141">141</a></span><span class="t"><span class="key">def</span> <span class="nam">setstate</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t142" href="#t142">142</a></span><span class="t">        <span class="nam">obj</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t143" href="#t143">143</a></span><span class="t">        <span class="nam">state</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t144" href="#t144">144</a></span><span class="t">        <span class="nam">renamed_properties</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t145" href="#t145">145</a></span><span class="t">        <span class="nam">new_optional_properties</span><span class="op">:</span> <span class="nam">List</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t146" href="#t146">146</a></span><span class="t">        <span class="nam">new_default_properties</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t147" href="#t147">147</a></span><span class="t">        <span class="nam">removed_properties</span><span class="op">:</span> <span class="nam">List</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span> <span class="op">-></span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t148" href="#t148">148</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t149" href="#t149">149</a></span><span class="t"><span class="str">    Helper function for safe implementations of __setstate__ in classes, which appropriately handles the cases where</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t150" href="#t150">150</a></span><span class="t"><span class="str">    a parent class already implements __setstate__ and where it does not. Call this function whenever you would actually</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t151" href="#t151">151</a></span><span class="t"><span class="str">    like to call the super-class' implementation.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t152" href="#t152">152</a></span><span class="t"><span class="str">    Unfortunately, __setstate__ is not implemented in object, rendering super().__setstate__(state) invalid in the general case.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t140" href="#t140">140</a></span><span class="t"><span class="str">        :param obj: the object for which to recursively test pickling</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t141" href="#t141">141</a></span><span class="t"><span class="str">        :param context_info: optional additional string to be included in the log message</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t142" href="#t142">142</a></span><span class="t"><span class="str">        """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t143" href="#t143">143</a></span><span class="t">        <span class="key">if</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">enabled</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t144" href="#t144">144</a></span><span class="t">            <span class="nam">failures</span> <span class="op">=</span> <span class="nam">cls</span><span class="op">.</span><span class="nam">debug_failure</span><span class="op">(</span><span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t145" href="#t145">145</a></span><span class="t">            <span class="nam">prefix</span> <span class="op">=</span> <span class="str">f"Picklability analysis for {obj}"</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t146" href="#t146">146</a></span><span class="t">            <span class="key">if</span> <span class="nam">context_info</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t147" href="#t147">147</a></span><span class="t">                <span class="nam">prefix</span> <span class="op">+=</span> <span class="str">" (context: %s)"</span> <span class="op">%</span> <span class="nam">context_info</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t148" href="#t148">148</a></span><span class="t">            <span class="key">if</span> <span class="nam">len</span><span class="op">(</span><span class="nam">failures</span><span class="op">)</span> <span class="op">></span> <span class="num">0</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t149" href="#t149">149</a></span><span class="t">                <span class="nam">log</span><span class="op">.</span><span class="nam">error</span><span class="op">(</span><span class="str">f"{prefix}: pickling would result in failures due to: {failures}"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t150" href="#t150">150</a></span><span class="t">            <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t151" href="#t151">151</a></span><span class="t">                <span class="nam">log</span><span class="op">.</span><span class="nam">info</span><span class="op">(</span><span class="str">f"{prefix}: is picklable"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t152" href="#t152">152</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t153" href="#t153">153</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t154" href="#t154">154</a></span><span class="t"><span class="str">    :param cls: the class in which you are implementing __setstate__</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t155" href="#t155">155</a></span><span class="t"><span class="str">    :param obj: the instance of cls</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t156" href="#t156">156</a></span><span class="t"><span class="str">    :param state: the state dictionary</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t157" href="#t157">157</a></span><span class="t"><span class="str">    :param renamed_properties: a mapping from old property names to new property names</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t158" href="#t158">158</a></span><span class="t"><span class="str">    :param new_optional_properties: a list of names of new property names, which, if not present, shall be initialised with None</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t159" href="#t159">159</a></span><span class="t"><span class="str">    :param new_default_properties: a dictionary mapping property names to their default values, which shall be added if they are not present</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t160" href="#t160">160</a></span><span class="t"><span class="str">    :param removed_properties: a list of names of properties that are no longer being used</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t161" href="#t161">161</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t162" href="#t162">162</a></span><span class="t">    <span class="com"># handle new/changed properties</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t163" href="#t163">163</a></span><span class="t">    <span class="key">if</span> <span class="nam">renamed_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t164" href="#t164">164</a></span><span class="t">        <span class="key">for</span> <span class="nam">mOld</span><span class="op">,</span> <span class="nam">mNew</span> <span class="key">in</span> <span class="nam">renamed_properties</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t165" href="#t165">165</a></span><span class="t">            <span class="key">if</span> <span class="nam">mOld</span> <span class="key">in</span> <span class="nam">state</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t166" href="#t166">166</a></span><span class="t">                <span class="nam">state</span><span class="op">[</span><span class="nam">mNew</span><span class="op">]</span> <span class="op">=</span> <span class="nam">state</span><span class="op">[</span><span class="nam">mOld</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t167" href="#t167">167</a></span><span class="t">                <span class="key">del</span> <span class="nam">state</span><span class="op">[</span><span class="nam">mOld</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t168" href="#t168">168</a></span><span class="t">    <span class="key">if</span> <span class="nam">new_optional_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t169" href="#t169">169</a></span><span class="t">        <span class="key">for</span> <span class="nam">mNew</span> <span class="key">in</span> <span class="nam">new_optional_properties</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t170" href="#t170">170</a></span><span class="t">            <span class="key">if</span> <span class="nam">mNew</span> <span class="key">not</span> <span class="key">in</span> <span class="nam">state</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t171" href="#t171">171</a></span><span class="t">                <span class="nam">state</span><span class="op">[</span><span class="nam">mNew</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t172" href="#t172">172</a></span><span class="t">    <span class="key">if</span> <span class="nam">new_default_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t173" href="#t173">173</a></span><span class="t">        <span class="key">for</span> <span class="nam">mNew</span><span class="op">,</span> <span class="nam">mValue</span> <span class="key">in</span> <span class="nam">new_default_properties</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t174" href="#t174">174</a></span><span class="t">            <span class="key">if</span> <span class="nam">mNew</span> <span class="key">not</span> <span class="key">in</span> <span class="nam">state</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t175" href="#t175">175</a></span><span class="t">                <span class="nam">state</span><span class="op">[</span><span class="nam">mNew</span><span class="op">]</span> <span class="op">=</span> <span class="nam">mValue</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t176" href="#t176">176</a></span><span class="t">    <span class="key">if</span> <span class="nam">removed_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t177" href="#t177">177</a></span><span class="t">        <span class="key">for</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">removed_properties</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t178" href="#t178">178</a></span><span class="t">            <span class="key">if</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">state</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t179" href="#t179">179</a></span><span class="t">                <span class="key">del</span> <span class="nam">state</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t180" href="#t180">180</a></span><span class="t">    <span class="com"># call super implementation, if any</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t181" href="#t181">181</a></span><span class="t">    <span class="nam">s</span> <span class="op">=</span> <span class="nam">super</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t182" href="#t182">182</a></span><span class="t">    <span class="key">if</span> <span class="nam">hasattr</span><span class="op">(</span><span class="nam">s</span><span class="op">,</span> <span class="str">'__setstate__'</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t183" href="#t183">183</a></span><span class="t">        <span class="nam">s</span><span class="op">.</span><span class="nam">__setstate__</span><span class="op">(</span><span class="nam">state</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t184" href="#t184">184</a></span><span class="t">    <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t185" href="#t185">185</a></span><span class="t">        <span class="nam">obj</span><span class="op">.</span><span class="nam">__dict__</span> <span class="op">=</span> <span class="nam">state</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t186" href="#t186">186</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t187" href="#t187">187</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t188" href="#t188">188</a></span><span class="t"><span class="key">def</span> <span class="nam">getstate</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t189" href="#t189">189</a></span><span class="t">        <span class="nam">obj</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t190" href="#t190">190</a></span><span class="t">        <span class="nam">transient_properties</span><span class="op">:</span> <span class="nam">Iterable</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t191" href="#t191">191</a></span><span class="t">        <span class="nam">excluded_properties</span><span class="op">:</span> <span class="nam">Iterable</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t192" href="#t192">192</a></span><span class="t">        <span class="nam">override_properties</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t193" href="#t193">193</a></span><span class="t">        <span class="nam">excluded_default_properties</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span> <span class="op">-></span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t194" href="#t194">194</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t195" href="#t195">195</a></span><span class="t"><span class="str">    Helper function for safe implementations of __getstate__ in classes, which appropriately handles the cases where</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t196" href="#t196">196</a></span><span class="t"><span class="str">    a parent class already implements __getstate__ and where it does not. Call this function whenever you would actually</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t197" href="#t197">197</a></span><span class="t"><span class="str">    like to call the super-class' implementation.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t198" href="#t198">198</a></span><span class="t"><span class="str">    Unfortunately, __getstate__ is not implemented in object, rendering super().__getstate__() invalid in the general case.</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t199" href="#t199">199</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t200" href="#t200">200</a></span><span class="t"><span class="str">    :param cls: the class in which you are implementing __getstate__</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t201" href="#t201">201</a></span><span class="t"><span class="str">    :param obj: the instance of cls</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t202" href="#t202">202</a></span><span class="t"><span class="str">    :param transient_properties: transient properties which be set to None in serialisations</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t203" href="#t203">203</a></span><span class="t"><span class="str">    :param excluded_properties: properties which shall be completely removed from serialisations</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t204" href="#t204">204</a></span><span class="t"><span class="str">    :param override_properties: a mapping from property names to values specifying (new or existing) properties which are to be set;</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t205" href="#t205">205</a></span><span class="t"><span class="str">        use this to set a fixed value for an existing property or to add a completely new property</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t206" href="#t206">206</a></span><span class="t"><span class="str">    :param excluded_default_properties: properties which shall be completely removed from serialisations, if they are set</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t207" href="#t207">207</a></span><span class="t"><span class="str">        to the given default value</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t208" href="#t208">208</a></span><span class="t"><span class="str">    :return: the state dictionary, which may be modified by the receiver</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t209" href="#t209">209</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t210" href="#t210">210</a></span><span class="t">    <span class="nam">s</span> <span class="op">=</span> <span class="nam">super</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t211" href="#t211">211</a></span><span class="t">    <span class="key">if</span> <span class="nam">hasattr</span><span class="op">(</span><span class="nam">s</span><span class="op">,</span> <span class="str">'__getstate__'</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t212" href="#t212">212</a></span><span class="t">        <span class="nam">d</span> <span class="op">=</span> <span class="nam">s</span><span class="op">.</span><span class="nam">__getstate__</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t213" href="#t213">213</a></span><span class="t">    <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t214" href="#t214">214</a></span><span class="t">        <span class="nam">d</span> <span class="op">=</span> <span class="nam">obj</span><span class="op">.</span><span class="nam">__dict__</span><span class="op">.</span><span class="nam">copy</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t215" href="#t215">215</a></span><span class="t">    <span class="key">if</span> <span class="nam">transient_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t216" href="#t216">216</a></span><span class="t">        <span class="key">for</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">transient_properties</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t217" href="#t217">217</a></span><span class="t">            <span class="key">if</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">d</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t218" href="#t218">218</a></span><span class="t">                <span class="nam">d</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t219" href="#t219">219</a></span><span class="t">    <span class="key">if</span> <span class="nam">excluded_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t220" href="#t220">220</a></span><span class="t">        <span class="key">for</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">excluded_properties</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t221" href="#t221">221</a></span><span class="t">            <span class="key">if</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">d</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t222" href="#t222">222</a></span><span class="t">                <span class="key">del</span> <span class="nam">d</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t223" href="#t223">223</a></span><span class="t">    <span class="key">if</span> <span class="nam">override_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t224" href="#t224">224</a></span><span class="t">        <span class="key">for</span> <span class="nam">k</span><span class="op">,</span> <span class="nam">v</span> <span class="key">in</span> <span class="nam">override_properties</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t225" href="#t225">225</a></span><span class="t">            <span class="nam">d</span><span class="op">[</span><span class="nam">k</span><span class="op">]</span> <span class="op">=</span> <span class="nam">v</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t226" href="#t226">226</a></span><span class="t">    <span class="key">if</span> <span class="nam">excluded_default_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t227" href="#t227">227</a></span><span class="t">        <span class="key">for</span> <span class="nam">p</span><span class="op">,</span> <span class="nam">v</span> <span class="key">in</span> <span class="nam">excluded_default_properties</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t228" href="#t228">228</a></span><span class="t">            <span class="key">if</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">d</span> <span class="key">and</span> <span class="nam">d</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span> <span class="op">==</span> <span class="nam">v</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t229" href="#t229">229</a></span><span class="t">                <span class="key">del</span> <span class="nam">d</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
-    <p class="mis show_mis"><span class="n"><a id="t230" href="#t230">230</a></span><span class="t">    <span class="key">return</span> <span class="nam">d</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t154" href="#t154">154</a></span><span class="t"><span class="key">def</span> <span class="nam">setstate</span><span class="op">(</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t155" href="#t155">155</a></span><span class="t">    <span class="nam">cls</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t156" href="#t156">156</a></span><span class="t">    <span class="nam">obj</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t157" href="#t157">157</a></span><span class="t">    <span class="nam">state</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t158" href="#t158">158</a></span><span class="t">    <span class="nam">renamed_properties</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t159" href="#t159">159</a></span><span class="t">    <span class="nam">new_optional_properties</span><span class="op">:</span> <span class="nam">List</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t160" href="#t160">160</a></span><span class="t">    <span class="nam">new_default_properties</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t161" href="#t161">161</a></span><span class="t">    <span class="nam">removed_properties</span><span class="op">:</span> <span class="nam">List</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t162" href="#t162">162</a></span><span class="t"><span class="op">)</span> <span class="op">-></span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t163" href="#t163">163</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t164" href="#t164">164</a></span><span class="t"><span class="str">    Helper function for safe implementations of __setstate__ in classes, which appropriately handles the cases where</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t165" href="#t165">165</a></span><span class="t"><span class="str">    a parent class already implements __setstate__ and where it does not. Call this function whenever you would actually</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t166" href="#t166">166</a></span><span class="t"><span class="str">    like to call the super-class' implementation.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t167" href="#t167">167</a></span><span class="t"><span class="str">    Unfortunately, __setstate__ is not implemented in object, rendering super().__setstate__(state) invalid in the general case.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t168" href="#t168">168</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t169" href="#t169">169</a></span><span class="t"><span class="str">    :param cls: the class in which you are implementing __setstate__</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t170" href="#t170">170</a></span><span class="t"><span class="str">    :param obj: the instance of cls</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t171" href="#t171">171</a></span><span class="t"><span class="str">    :param state: the state dictionary</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t172" href="#t172">172</a></span><span class="t"><span class="str">    :param renamed_properties: a mapping from old property names to new property names</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t173" href="#t173">173</a></span><span class="t"><span class="str">    :param new_optional_properties: a list of names of new property names, which, if not present, shall be initialised with None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t174" href="#t174">174</a></span><span class="t"><span class="str">    :param new_default_properties: a dictionary mapping property names to their default values, which shall be added if they are not present</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t175" href="#t175">175</a></span><span class="t"><span class="str">    :param removed_properties: a list of names of properties that are no longer being used</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t176" href="#t176">176</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t177" href="#t177">177</a></span><span class="t">    <span class="com"># handle new/changed properties</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t178" href="#t178">178</a></span><span class="t">    <span class="key">if</span> <span class="nam">renamed_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t179" href="#t179">179</a></span><span class="t">        <span class="key">for</span> <span class="nam">mOld</span><span class="op">,</span> <span class="nam">mNew</span> <span class="key">in</span> <span class="nam">renamed_properties</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t180" href="#t180">180</a></span><span class="t">            <span class="key">if</span> <span class="nam">mOld</span> <span class="key">in</span> <span class="nam">state</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t181" href="#t181">181</a></span><span class="t">                <span class="nam">state</span><span class="op">[</span><span class="nam">mNew</span><span class="op">]</span> <span class="op">=</span> <span class="nam">state</span><span class="op">[</span><span class="nam">mOld</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t182" href="#t182">182</a></span><span class="t">                <span class="key">del</span> <span class="nam">state</span><span class="op">[</span><span class="nam">mOld</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t183" href="#t183">183</a></span><span class="t">    <span class="key">if</span> <span class="nam">new_optional_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t184" href="#t184">184</a></span><span class="t">        <span class="key">for</span> <span class="nam">mNew</span> <span class="key">in</span> <span class="nam">new_optional_properties</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t185" href="#t185">185</a></span><span class="t">            <span class="key">if</span> <span class="nam">mNew</span> <span class="key">not</span> <span class="key">in</span> <span class="nam">state</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t186" href="#t186">186</a></span><span class="t">                <span class="nam">state</span><span class="op">[</span><span class="nam">mNew</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t187" href="#t187">187</a></span><span class="t">    <span class="key">if</span> <span class="nam">new_default_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t188" href="#t188">188</a></span><span class="t">        <span class="key">for</span> <span class="nam">mNew</span><span class="op">,</span> <span class="nam">mValue</span> <span class="key">in</span> <span class="nam">new_default_properties</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t189" href="#t189">189</a></span><span class="t">            <span class="key">if</span> <span class="nam">mNew</span> <span class="key">not</span> <span class="key">in</span> <span class="nam">state</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t190" href="#t190">190</a></span><span class="t">                <span class="nam">state</span><span class="op">[</span><span class="nam">mNew</span><span class="op">]</span> <span class="op">=</span> <span class="nam">mValue</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t191" href="#t191">191</a></span><span class="t">    <span class="key">if</span> <span class="nam">removed_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t192" href="#t192">192</a></span><span class="t">        <span class="key">for</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">removed_properties</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t193" href="#t193">193</a></span><span class="t">            <span class="key">if</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">state</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t194" href="#t194">194</a></span><span class="t">                <span class="key">del</span> <span class="nam">state</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t195" href="#t195">195</a></span><span class="t">    <span class="com"># call super implementation, if any</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t196" href="#t196">196</a></span><span class="t">    <span class="nam">s</span> <span class="op">=</span> <span class="nam">super</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t197" href="#t197">197</a></span><span class="t">    <span class="key">if</span> <span class="nam">hasattr</span><span class="op">(</span><span class="nam">s</span><span class="op">,</span> <span class="str">'__setstate__'</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t198" href="#t198">198</a></span><span class="t">        <span class="nam">s</span><span class="op">.</span><span class="nam">__setstate__</span><span class="op">(</span><span class="nam">state</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t199" href="#t199">199</a></span><span class="t">    <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t200" href="#t200">200</a></span><span class="t">        <span class="nam">obj</span><span class="op">.</span><span class="nam">__dict__</span> <span class="op">=</span> <span class="nam">state</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t201" href="#t201">201</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t202" href="#t202">202</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t203" href="#t203">203</a></span><span class="t"><span class="key">def</span> <span class="nam">getstate</span><span class="op">(</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t204" href="#t204">204</a></span><span class="t">    <span class="nam">cls</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t205" href="#t205">205</a></span><span class="t">    <span class="nam">obj</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t206" href="#t206">206</a></span><span class="t">    <span class="nam">transient_properties</span><span class="op">:</span> <span class="nam">Iterable</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t207" href="#t207">207</a></span><span class="t">    <span class="nam">excluded_properties</span><span class="op">:</span> <span class="nam">Iterable</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t208" href="#t208">208</a></span><span class="t">    <span class="nam">override_properties</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t209" href="#t209">209</a></span><span class="t">    <span class="nam">excluded_default_properties</span><span class="op">:</span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t210" href="#t210">210</a></span><span class="t"><span class="op">)</span> <span class="op">-></span> <span class="nam">Dict</span><span class="op">[</span><span class="nam">str</span><span class="op">,</span> <span class="nam">Any</span><span class="op">]</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t211" href="#t211">211</a></span><span class="t">    <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t212" href="#t212">212</a></span><span class="t"><span class="str">    Helper function for safe implementations of __getstate__ in classes, which appropriately handles the cases where</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t213" href="#t213">213</a></span><span class="t"><span class="str">    a parent class already implements __getstate__ and where it does not. Call this function whenever you would actually</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t214" href="#t214">214</a></span><span class="t"><span class="str">    like to call the super-class' implementation.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t215" href="#t215">215</a></span><span class="t"><span class="str">    Unfortunately, __getstate__ is not implemented in object, rendering super().__getstate__() invalid in the general case.</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t216" href="#t216">216</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t217" href="#t217">217</a></span><span class="t"><span class="str">    :param cls: the class in which you are implementing __getstate__</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t218" href="#t218">218</a></span><span class="t"><span class="str">    :param obj: the instance of cls</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t219" href="#t219">219</a></span><span class="t"><span class="str">    :param transient_properties: transient properties which be set to None in serialisations</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t220" href="#t220">220</a></span><span class="t"><span class="str">    :param excluded_properties: properties which shall be completely removed from serialisations</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t221" href="#t221">221</a></span><span class="t"><span class="str">    :param override_properties: a mapping from property names to values specifying (new or existing) properties which are to be set;</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t222" href="#t222">222</a></span><span class="t"><span class="str">        use this to set a fixed value for an existing property or to add a completely new property</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t223" href="#t223">223</a></span><span class="t"><span class="str">    :param excluded_default_properties: properties which shall be completely removed from serialisations, if they are set</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t224" href="#t224">224</a></span><span class="t"><span class="str">        to the given default value</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t225" href="#t225">225</a></span><span class="t"><span class="str">    :return: the state dictionary, which may be modified by the receiver</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t226" href="#t226">226</a></span><span class="t"><span class="str">    """</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t227" href="#t227">227</a></span><span class="t">    <span class="nam">s</span> <span class="op">=</span> <span class="nam">super</span><span class="op">(</span><span class="nam">cls</span><span class="op">,</span> <span class="nam">obj</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t228" href="#t228">228</a></span><span class="t">    <span class="key">if</span> <span class="nam">hasattr</span><span class="op">(</span><span class="nam">s</span><span class="op">,</span> <span class="str">'__getstate__'</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t229" href="#t229">229</a></span><span class="t">        <span class="nam">d</span> <span class="op">=</span> <span class="nam">s</span><span class="op">.</span><span class="nam">__getstate__</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t230" href="#t230">230</a></span><span class="t">    <span class="key">else</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t231" href="#t231">231</a></span><span class="t">        <span class="nam">d</span> <span class="op">=</span> <span class="nam">obj</span><span class="op">.</span><span class="nam">__dict__</span><span class="op">.</span><span class="nam">copy</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t232" href="#t232">232</a></span><span class="t">    <span class="key">if</span> <span class="nam">transient_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t233" href="#t233">233</a></span><span class="t">        <span class="key">for</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">transient_properties</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t234" href="#t234">234</a></span><span class="t">            <span class="key">if</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">d</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t235" href="#t235">235</a></span><span class="t">                <span class="nam">d</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t236" href="#t236">236</a></span><span class="t">    <span class="key">if</span> <span class="nam">excluded_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t237" href="#t237">237</a></span><span class="t">        <span class="key">for</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">excluded_properties</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t238" href="#t238">238</a></span><span class="t">            <span class="key">if</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">d</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t239" href="#t239">239</a></span><span class="t">                <span class="key">del</span> <span class="nam">d</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t240" href="#t240">240</a></span><span class="t">    <span class="key">if</span> <span class="nam">override_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t241" href="#t241">241</a></span><span class="t">        <span class="key">for</span> <span class="nam">k</span><span class="op">,</span> <span class="nam">v</span> <span class="key">in</span> <span class="nam">override_properties</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t242" href="#t242">242</a></span><span class="t">            <span class="nam">d</span><span class="op">[</span><span class="nam">k</span><span class="op">]</span> <span class="op">=</span> <span class="nam">v</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t243" href="#t243">243</a></span><span class="t">    <span class="key">if</span> <span class="nam">excluded_default_properties</span> <span class="key">is</span> <span class="key">not</span> <span class="key">None</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t244" href="#t244">244</a></span><span class="t">        <span class="key">for</span> <span class="nam">p</span><span class="op">,</span> <span class="nam">v</span> <span class="key">in</span> <span class="nam">excluded_default_properties</span><span class="op">.</span><span class="nam">items</span><span class="op">(</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t245" href="#t245">245</a></span><span class="t">            <span class="key">if</span> <span class="nam">p</span> <span class="key">in</span> <span class="nam">d</span> <span class="key">and</span> <span class="nam">d</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span> <span class="op">==</span> <span class="nam">v</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t246" href="#t246">246</a></span><span class="t">                <span class="key">del</span> <span class="nam">d</span><span class="op">[</span><span class="nam">p</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
+    <p class="mis show_mis"><span class="n"><a id="t247" href="#t247">247</a></span><span class="t">    <span class="key">return</span> <span class="nam">d</span>&nbsp;</span><span class="r"></span></p>
 </main>
 <footer>
     <div class="content">
@@ -319,7 +336,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_plot_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_plot_py.html b/coverage/d_3ccb7b6033502eb6_plot_py.html
index bcdc5888..4dfa5e07 100644
--- a/coverage/d_3ccb7b6033502eb6_plot_py.html
+++ b/coverage/d_3ccb7b6033502eb6_plot_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_profiling_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -435,7 +435,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_profiling_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_profiling_py.html b/coverage/d_3ccb7b6033502eb6_profiling_py.html
index f978b7c5..f0ecf034 100644
--- a/coverage/d_3ccb7b6033502eb6_profiling_py.html
+++ b/coverage/d_3ccb7b6033502eb6_profiling_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_sequences_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -150,7 +150,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_sequences_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_sequences_py.html b/coverage/d_3ccb7b6033502eb6_sequences_py.html
index 6ea0f77d..3a9280c0 100644
--- a/coverage/d_3ccb7b6033502eb6_sequences_py.html
+++ b/coverage/d_3ccb7b6033502eb6_sequences_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_string_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -287,7 +287,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_string_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_string_py.html b/coverage/d_3ccb7b6033502eb6_string_py.html
index 7238edb2..d23c90dc 100644
--- a/coverage/d_3ccb7b6033502eb6_string_py.html
+++ b/coverage/d_3ccb7b6033502eb6_string_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_test_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -605,7 +605,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_test_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_test_py.html b/coverage/d_3ccb7b6033502eb6_test_py.html
index 02e6dd52..f25015a5 100644
--- a/coverage/d_3ccb7b6033502eb6_test_py.html
+++ b/coverage/d_3ccb7b6033502eb6_test_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_time_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -144,7 +144,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_time_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_time_py.html b/coverage/d_3ccb7b6033502eb6_time_py.html
index 6eb492d0..d8bc8905 100644
--- a/coverage/d_3ccb7b6033502eb6_time_py.html
+++ b/coverage/d_3ccb7b6033502eb6_time_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_typing_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -142,7 +142,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_typing_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_typing_py.html b/coverage/d_3ccb7b6033502eb6_typing_py.html
index 157c4140..b45d1191 100644
--- a/coverage/d_3ccb7b6033502eb6_typing_py.html
+++ b/coverage/d_3ccb7b6033502eb6_typing_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_version_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -97,7 +97,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6_version_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ccb7b6033502eb6_version_py.html b/coverage/d_3ccb7b6033502eb6_version_py.html
index 66686f40..aeb9a216 100644
--- a/coverage/d_3ccb7b6033502eb6_version_py.html
+++ b/coverage/d_3ccb7b6033502eb6_version_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_vector_model_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -116,7 +116,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_vector_model_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ffb4ead6faaaac2___init___py.html b/coverage/d_3ffb4ead6faaaac2___init___py.html
index 5fc39a2b..dee87088 100644
--- a/coverage/d_3ffb4ead6faaaac2___init___py.html
+++ b/coverage/d_3ffb4ead6faaaac2___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ffb4ead6faaaac2_pl_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -90,7 +90,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ffb4ead6faaaac2_pl_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_3ffb4ead6faaaac2_pl_models_py.html b/coverage/d_3ffb4ead6faaaac2_pl_models_py.html
index 0a1d0252..a5dc9c4c 100644
--- a/coverage/d_3ffb4ead6faaaac2_pl_models_py.html
+++ b/coverage/d_3ffb4ead6faaaac2_pl_models_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c677a990458909b3___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -187,7 +187,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c677a990458909b3___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_4a7aa1929d28f620___init___py.html b/coverage/d_4a7aa1929d28f620___init___py.html
index 1945f421..977c61e9 100644
--- a/coverage/d_4a7aa1929d28f620___init___py.html
+++ b/coverage/d_4a7aa1929d28f620___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620_eval_stats_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -92,7 +92,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620_eval_stats_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_4a7aa1929d28f620_eval_stats_base_py.html b/coverage/d_4a7aa1929d28f620_eval_stats_base_py.html
index e3b26e14..4d01e8d8 100644
--- a/coverage/d_4a7aa1929d28f620_eval_stats_base_py.html
+++ b/coverage/d_4a7aa1929d28f620_eval_stats_base_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620_eval_stats_classification_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -427,7 +427,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620_eval_stats_classification_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_4a7aa1929d28f620_eval_stats_classification_py.html b/coverage/d_4a7aa1929d28f620_eval_stats_classification_py.html
index 3fe0d4cf..fb3e3742 100644
--- a/coverage/d_4a7aa1929d28f620_eval_stats_classification_py.html
+++ b/coverage/d_4a7aa1929d28f620_eval_stats_classification_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620_eval_stats_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -512,12 +512,12 @@ <h2>
     <p class="run"><span class="n"><a id="t430" href="#t430">430</a></span><span class="t">    <span class="key">def</span> <span class="nam">get_misclassified_indices</span><span class="op">(</span><span class="nam">self</span><span class="op">)</span> <span class="op">-></span> <span class="nam">List</span><span class="op">[</span><span class="nam">int</span><span class="op">]</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="mis show_mis"><span class="n"><a id="t431" href="#t431">431</a></span><span class="t">        <span class="key">return</span> <span class="op">[</span><span class="nam">i</span> <span class="key">for</span> <span class="nam">i</span><span class="op">,</span> <span class="op">(</span><span class="nam">predClass</span><span class="op">,</span> <span class="nam">trueClass</span><span class="op">)</span> <span class="key">in</span> <span class="nam">enumerate</span><span class="op">(</span><span class="nam">zip</span><span class="op">(</span><span class="nam">self</span><span class="op">.</span><span class="nam">y_predicted</span><span class="op">,</span> <span class="nam">self</span><span class="op">.</span><span class="nam">y_true</span><span class="op">)</span><span class="op">)</span> <span class="key">if</span> <span class="nam">predClass</span> <span class="op">!=</span> <span class="nam">trueClass</span><span class="op">]</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t432" href="#t432">432</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t433" href="#t433">433</a></span><span class="t">    <span class="key">def</span> <span class="nam">plot_confusion_matrix</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">normalize</span><span class="op">=</span><span class="key">True</span><span class="op">,</span> <span class="nam">title_add</span><span class="op">:</span> <span class="nam">str</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t433" href="#t433">433</a></span><span class="t">    <span class="key">def</span> <span class="nam">plot_confusion_matrix</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">normalize</span><span class="op">=</span><span class="key">True</span><span class="op">,</span> <span class="nam">title_add</span><span class="op">:</span> <span class="nam">str</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span> <span class="op">-></span> <span class="nam">plt</span><span class="op">.</span><span class="nam">Figure</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t434" href="#t434">434</a></span><span class="t">        <span class="com"># based on https://scikit-learn.org/0.20/auto_examples/model_selection/plot_confusion_matrix.html</span>&nbsp;</span><span class="r"></span></p>
     <p class="mis show_mis"><span class="n"><a id="t435" href="#t435">435</a></span><span class="t">        <span class="nam">cm</span> <span class="op">=</span> <span class="nam">self</span><span class="op">.</span><span class="nam">get_confusion_matrix</span><span class="op">(</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
     <p class="mis show_mis"><span class="n"><a id="t436" href="#t436">436</a></span><span class="t">        <span class="key">return</span> <span class="nam">cm</span><span class="op">.</span><span class="nam">plot</span><span class="op">(</span><span class="nam">normalize</span><span class="op">=</span><span class="nam">normalize</span><span class="op">,</span> <span class="nam">title_add</span><span class="op">=</span><span class="nam">title_add</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t437" href="#t437">437</a></span><span class="t">&nbsp;</span><span class="r"></span></p>
-    <p class="run"><span class="n"><a id="t438" href="#t438">438</a></span><span class="t">    <span class="key">def</span> <span class="nam">plot_precision_recall_curve</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">title_add</span><span class="op">:</span> <span class="nam">str</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="run"><span class="n"><a id="t438" href="#t438">438</a></span><span class="t">    <span class="key">def</span> <span class="nam">plot_precision_recall_curve</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">title_add</span><span class="op">:</span> <span class="nam">str</span> <span class="op">=</span> <span class="key">None</span><span class="op">)</span> <span class="op">-></span> <span class="nam">plt</span><span class="op">.</span><span class="nam">Figure</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="mis show_mis"><span class="n"><a id="t439" href="#t439">439</a></span><span class="t">        <span class="key">from</span> <span class="nam">sklearn</span><span class="op">.</span><span class="nam">metrics</span> <span class="key">import</span> <span class="nam">PrecisionRecallDisplay</span>  <span class="com"># only supported by newer versions of sklearn</span>&nbsp;</span><span class="r"></span></p>
     <p class="mis show_mis"><span class="n"><a id="t440" href="#t440">440</a></span><span class="t">        <span class="key">if</span> <span class="key">not</span> <span class="nam">self</span><span class="op">.</span><span class="nam">is_probabilities_available</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="mis show_mis"><span class="n"><a id="t441" href="#t441">441</a></span><span class="t">            <span class="key">raise</span> <span class="nam">Exception</span><span class="op">(</span><span class="str">"Precision-recall curve requires probabilities"</span><span class="op">)</span>&nbsp;</span><span class="r"></span></p>
@@ -719,7 +719,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620_eval_stats_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_4a7aa1929d28f620_eval_stats_clustering_py.html b/coverage/d_4a7aa1929d28f620_eval_stats_clustering_py.html
index 5fac6d08..6ec7093d 100644
--- a/coverage/d_4a7aa1929d28f620_eval_stats_clustering_py.html
+++ b/coverage/d_4a7aa1929d28f620_eval_stats_clustering_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620_eval_stats_regression_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -308,7 +308,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620_eval_stats_regression_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_4a7aa1929d28f620_eval_stats_regression_py.html b/coverage/d_4a7aa1929d28f620_eval_stats_regression_py.html
index 176874d8..4e394f58 100644
--- a/coverage/d_4a7aa1929d28f620_eval_stats_regression_py.html
+++ b/coverage/d_4a7aa1929d28f620_eval_stats_regression_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_eval_util_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -403,7 +403,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_eval_util_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_535e1cc7b06ed03f___init___py.html b/coverage/d_535e1cc7b06ed03f___init___py.html
index b8ba2a21..b3b259b0 100644
--- a/coverage/d_535e1cc7b06ed03f___init___py.html
+++ b/coverage/d_535e1cc7b06ed03f___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -94,7 +94,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_535e1cc7b06ed03f_torch_base_py.html b/coverage/d_535e1cc7b06ed03f_torch_base_py.html
index d3e9f6a3..08303915 100644
--- a/coverage/d_535e1cc7b06ed03f_torch_base_py.html
+++ b/coverage/d_535e1cc7b06ed03f_torch_base_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_data_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -969,7 +969,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_data_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_535e1cc7b06ed03f_torch_data_py.html b/coverage/d_535e1cc7b06ed03f_torch_data_py.html
index e7aa0e3f..0e9fe365 100644
--- a/coverage/d_535e1cc7b06ed03f_torch_data_py.html
+++ b/coverage/d_535e1cc7b06ed03f_torch_data_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_enums_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -733,7 +733,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_enums_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_535e1cc7b06ed03f_torch_enums_py.html b/coverage/d_535e1cc7b06ed03f_torch_enums_py.html
index fc88efe0..8af3f9a7 100644
--- a/coverage/d_535e1cc7b06ed03f_torch_enums_py.html
+++ b/coverage/d_535e1cc7b06ed03f_torch_enums_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_eval_util_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -171,7 +171,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_eval_util_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_535e1cc7b06ed03f_torch_eval_util_py.html b/coverage/d_535e1cc7b06ed03f_torch_eval_util_py.html
index d03d411e..fde6f97f 100644
--- a/coverage/d_535e1cc7b06ed03f_torch_eval_util_py.html
+++ b/coverage/d_535e1cc7b06ed03f_torch_eval_util_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3c6d3a4d2db9b72b___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -116,7 +116,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3c6d3a4d2db9b72b___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_535e1cc7b06ed03f_torch_modules_py.html b/coverage/d_535e1cc7b06ed03f_torch_modules_py.html
index b89425f8..19da9a22 100644
--- a/coverage/d_535e1cc7b06ed03f_torch_modules_py.html
+++ b/coverage/d_535e1cc7b06ed03f_torch_modules_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_opt_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -97,7 +97,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torch_opt_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_535e1cc7b06ed03f_torch_opt_py.html b/coverage/d_535e1cc7b06ed03f_torch_opt_py.html
index afb16541..1838e8bc 100644
--- a/coverage/d_535e1cc7b06ed03f_torch_opt_py.html
+++ b/coverage/d_535e1cc7b06ed03f_torch_opt_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torchtext_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -1023,7 +1023,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f_torchtext_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_535e1cc7b06ed03f_torchtext_py.html b/coverage/d_535e1cc7b06ed03f_torchtext_py.html
index d179ac2b..17fb6a48 100644
--- a/coverage/d_535e1cc7b06ed03f_torchtext_py.html
+++ b/coverage/d_535e1cc7b06ed03f_torchtext_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -169,7 +169,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_643c821173b729ee___init___py.html b/coverage/d_643c821173b729ee___init___py.html
index b6b67965..0db6989b 100644
--- a/coverage/d_643c821173b729ee___init___py.html
+++ b/coverage/d_643c821173b729ee___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_643c821173b729ee_ensemble_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -90,7 +90,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_643c821173b729ee_ensemble_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_643c821173b729ee_ensemble_base_py.html b/coverage/d_643c821173b729ee_ensemble_base_py.html
index cdd033eb..5115cb90 100644
--- a/coverage/d_643c821173b729ee_ensemble_base_py.html
+++ b/coverage/d_643c821173b729ee_ensemble_base_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_643c821173b729ee_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -161,7 +161,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_643c821173b729ee_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_643c821173b729ee_models_py.html b/coverage/d_643c821173b729ee_models_py.html
index 18f44c57..68ce11de 100644
--- a/coverage/d_643c821173b729ee_models_py.html
+++ b/coverage/d_643c821173b729ee_models_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -120,7 +120,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_7eceb030faf4fa5b___init___py.html b/coverage/d_7eceb030faf4fa5b___init___py.html
index f4082ecc..434461a4 100644
--- a/coverage/d_7eceb030faf4fa5b___init___py.html
+++ b/coverage/d_7eceb030faf4fa5b___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b__globalmaptiles_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -89,7 +89,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b__globalmaptiles_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_7eceb030faf4fa5b__globalmaptiles_py.html b/coverage/d_7eceb030faf4fa5b__globalmaptiles_py.html
index c41023f7..8da55e3d 100644
--- a/coverage/d_7eceb030faf4fa5b__globalmaptiles_py.html
+++ b/coverage/d_7eceb030faf4fa5b__globalmaptiles_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b_geo_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -448,7 +448,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b_geo_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_7eceb030faf4fa5b_geo_clustering_py.html b/coverage/d_7eceb030faf4fa5b_geo_clustering_py.html
index c32bf876..7bfc6038 100644
--- a/coverage/d_7eceb030faf4fa5b_geo_clustering_py.html
+++ b/coverage/d_7eceb030faf4fa5b_geo_clustering_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b_geo_coords_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -335,7 +335,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b_geo_coords_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_7eceb030faf4fa5b_geo_coords_py.html b/coverage/d_7eceb030faf4fa5b_geo_coords_py.html
index eb4dadb8..b28ea33b 100644
--- a/coverage/d_7eceb030faf4fa5b_geo_coords_py.html
+++ b/coverage/d_7eceb030faf4fa5b_geo_coords_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -281,7 +281,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_7eceb030faf4fa5b_local_coords_py.html b/coverage/d_7eceb030faf4fa5b_local_coords_py.html
index f8dd7f1c..e398e299 100644
--- a/coverage/d_7eceb030faf4fa5b_local_coords_py.html
+++ b/coverage/d_7eceb030faf4fa5b_local_coords_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b_map_tiles_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -271,7 +271,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b_map_tiles_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_7eceb030faf4fa5b_map_tiles_py.html b/coverage/d_7eceb030faf4fa5b_map_tiles_py.html
index 71e15295..c2d3bac9 100644
--- a/coverage/d_7eceb030faf4fa5b_map_tiles_py.html
+++ b/coverage/d_7eceb030faf4fa5b_map_tiles_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_hyperopt_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -145,7 +145,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_hyperopt_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_8e16ca04a866d040_lstnet_models_py.html b/coverage/d_8e16ca04a866d040_lstnet_models_py.html
index 5aa1346b..ed858daf 100644
--- a/coverage/d_8e16ca04a866d040_lstnet_models_py.html
+++ b/coverage/d_8e16ca04a866d040_lstnet_models_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_8e16ca04a866d040_lstnet_modules_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -265,7 +265,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_8e16ca04a866d040_lstnet_modules_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_8e16ca04a866d040_lstnet_modules_py.html b/coverage/d_8e16ca04a866d040_lstnet_modules_py.html
index 6a10610b..9465b2b2 100644
--- a/coverage/d_8e16ca04a866d040_lstnet_modules_py.html
+++ b/coverage/d_8e16ca04a866d040_lstnet_modules_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d049e11bc7279f8f_mlp_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -318,7 +318,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d049e11bc7279f8f_mlp_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_968cc2eb7979e5c9___init___py.html b/coverage/d_968cc2eb7979e5c9___init___py.html
index 6b0df219..a175f9cc 100644
--- a/coverage/d_968cc2eb7979e5c9___init___py.html
+++ b/coverage/d_968cc2eb7979e5c9___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9_azure_tracking_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -90,7 +90,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9_azure_tracking_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_968cc2eb7979e5c9_azure_tracking_py.html b/coverage/d_968cc2eb7979e5c9_azure_tracking_py.html
index 36065a75..793941ae 100644
--- a/coverage/d_968cc2eb7979e5c9_azure_tracking_py.html
+++ b/coverage/d_968cc2eb7979e5c9_azure_tracking_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9_clearml_tracking_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -141,7 +141,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9_clearml_tracking_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_968cc2eb7979e5c9_clearml_tracking_py.html b/coverage/d_968cc2eb7979e5c9_clearml_tracking_py.html
index 69291944..31436b31 100644
--- a/coverage/d_968cc2eb7979e5c9_clearml_tracking_py.html
+++ b/coverage/d_968cc2eb7979e5c9_clearml_tracking_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9_mlflow_tracking_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -156,7 +156,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9_mlflow_tracking_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_968cc2eb7979e5c9_mlflow_tracking_py.html b/coverage/d_968cc2eb7979e5c9_mlflow_tracking_py.html
index eab2f8da..5c5c51f9 100644
--- a/coverage/d_968cc2eb7979e5c9_mlflow_tracking_py.html
+++ b/coverage/d_968cc2eb7979e5c9_mlflow_tracking_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9_tracking_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -174,7 +174,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_968cc2eb7979e5c9_tracking_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_968cc2eb7979e5c9_tracking_base_py.html b/coverage/d_968cc2eb7979e5c9_tracking_base_py.html
index 7ac6c3f1..09dba99b 100644
--- a/coverage/d_968cc2eb7979e5c9_tracking_base_py.html
+++ b/coverage/d_968cc2eb7979e5c9_tracking_base_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -294,7 +294,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ccb7b6033502eb6___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_96cde01957db023b___init___py.html b/coverage/d_96cde01957db023b___init___py.html
index 4482859b..8d19d657 100644
--- a/coverage/d_96cde01957db023b___init___py.html
+++ b/coverage/d_96cde01957db023b___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_coordinate_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -90,7 +90,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_coordinate_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_96cde01957db023b_coordinate_clustering_ground_truth_py.html b/coverage/d_96cde01957db023b_coordinate_clustering_ground_truth_py.html
index 9da089fa..7ce25da6 100644
--- a/coverage/d_96cde01957db023b_coordinate_clustering_ground_truth_py.html
+++ b/coverage/d_96cde01957db023b_coordinate_clustering_ground_truth_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_coordinates_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -197,7 +197,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_coordinates_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_96cde01957db023b_coordinate_clustering_py.html b/coverage/d_96cde01957db023b_coordinate_clustering_py.html
index facdf17b..923416e7 100644
--- a/coverage/d_96cde01957db023b_coordinate_clustering_py.html
+++ b/coverage/d_96cde01957db023b_coordinate_clustering_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_coordinate_clustering_ground_truth_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -253,7 +253,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_coordinate_clustering_ground_truth_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_96cde01957db023b_coordinates_py.html b/coverage/d_96cde01957db023b_coordinates_py.html
index 3ca6fedb..1d4e3505 100644
--- a/coverage/d_96cde01957db023b_coordinates_py.html
+++ b/coverage/d_96cde01957db023b_coordinates_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_geometry_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -131,7 +131,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_geometry_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_96cde01957db023b_geometry_py.html b/coverage/d_96cde01957db023b_geometry_py.html
index 608b6630..cac506fd 100644
--- a/coverage/d_96cde01957db023b_geometry_py.html
+++ b/coverage/d_96cde01957db023b_geometry_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_graph_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -158,7 +158,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_96cde01957db023b_graph_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_96cde01957db023b_graph_py.html b/coverage/d_96cde01957db023b_graph_py.html
index ce69984e..663c3f96 100644
--- a/coverage/d_96cde01957db023b_graph_py.html
+++ b/coverage/d_96cde01957db023b_graph_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b_local_coords_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -180,7 +180,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b_local_coords_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_ad23503bef421ba7___init___py.html b/coverage/d_ad23503bef421ba7___init___py.html
index 4b8156f9..71cfa259 100644
--- a/coverage/d_ad23503bef421ba7___init___py.html
+++ b/coverage/d_ad23503bef421ba7___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_crossval_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -105,7 +105,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_crossval_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_ad23503bef421ba7_crossval_py.html b/coverage/d_ad23503bef421ba7_crossval_py.html
index 6aa1f8d4..a5da852e 100644
--- a/coverage/d_ad23503bef421ba7_crossval_py.html
+++ b/coverage/d_ad23503bef421ba7_crossval_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -346,7 +346,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_4a7aa1929d28f620___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_ad23503bef421ba7_eval_util_py.html b/coverage/d_ad23503bef421ba7_eval_util_py.html
index aa421bb7..6a57c329 100644
--- a/coverage/d_ad23503bef421ba7_eval_util_py.html
+++ b/coverage/d_ad23503bef421ba7_eval_util_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_evaluator_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -1063,7 +1063,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_evaluator_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_ad23503bef421ba7_evaluator_clustering_py.html b/coverage/d_ad23503bef421ba7_evaluator_clustering_py.html
index e4d23ca5..c998ba97 100644
--- a/coverage/d_ad23503bef421ba7_evaluator_clustering_py.html
+++ b/coverage/d_ad23503bef421ba7_evaluator_clustering_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_metric_computation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -168,7 +168,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_metric_computation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_ad23503bef421ba7_evaluator_py.html b/coverage/d_ad23503bef421ba7_evaluator_py.html
index 52915ffd..c0ef1cb2 100644
--- a/coverage/d_ad23503bef421ba7_evaluator_py.html
+++ b/coverage/d_ad23503bef421ba7_evaluator_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_evaluator_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -448,7 +448,7 @@ <h2>
     <p class="run"><span class="n"><a id="t366" href="#t366">366</a></span><span class="t"><span class="key">class</span> <span class="nam">ClassificationEvaluatorParams</span><span class="op">(</span><span class="nam">EvaluatorParams</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="run"><span class="n"><a id="t367" href="#t367">367</a></span><span class="t">    <span class="key">def</span> <span class="nam">__init__</span><span class="op">(</span><span class="nam">self</span><span class="op">,</span> <span class="nam">data_splitter</span><span class="op">:</span> <span class="nam">DataSplitter</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span> <span class="nam">fractional_split_test_fraction</span><span class="op">:</span> <span class="nam">float</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span> <span class="nam">fractional_split_random_seed</span><span class="op">=</span><span class="num">42</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t368" href="#t368">368</a></span><span class="t">            <span class="nam">fractional_split_shuffle</span><span class="op">=</span><span class="key">True</span><span class="op">,</span> <span class="nam">additional_metrics</span><span class="op">:</span> <span class="nam">Sequence</span><span class="op">[</span><span class="nam">ClassificationMetric</span><span class="op">]</span> <span class="op">=</span> <span class="key">None</span><span class="op">,</span>&nbsp;</span><span class="r"></span></p>
-    <p class="pln"><span class="n"><a id="t369" href="#t369">369</a></span><span class="t">            <span class="nam">compute_probabilities</span><span class="op">:</span> <span class="nam">bool</span> <span class="op">=</span> <span class="key">False</span><span class="op">,</span> <span class="nam">binary_positive_label</span><span class="op">=</span><span class="nam">GUESS</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
+    <p class="pln"><span class="n"><a id="t369" href="#t369">369</a></span><span class="t">            <span class="nam">compute_probabilities</span><span class="op">:</span> <span class="nam">bool</span> <span class="op">=</span> <span class="key">False</span><span class="op">,</span> <span class="nam">binary_positive_label</span><span class="op">:</span> <span class="nam">Optional</span><span class="op">[</span><span class="nam">str</span><span class="op">]</span> <span class="op">=</span> <span class="nam">GUESS</span><span class="op">)</span><span class="op">:</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t370" href="#t370">370</a></span><span class="t">        <span class="str">"""</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t371" href="#t371">371</a></span><span class="t"><span class="str">        :param data_splitter: [if test data must be obtained via split] a splitter to use in order to obtain; if None, must specify</span>&nbsp;</span><span class="r"></span></p>
     <p class="pln"><span class="n"><a id="t372" href="#t372">372</a></span><span class="t"><span class="str">            fractionalSplitTestFraction for fractional split (default)</span>&nbsp;</span><span class="r"></span></p>
@@ -601,7 +601,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_ad23503bef421ba7_evaluator_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_ad23503bef421ba7_metric_computation_py.html b/coverage/d_ad23503bef421ba7_metric_computation_py.html
index d89a84d2..611d6774 100644
--- a/coverage/d_ad23503bef421ba7_metric_computation_py.html
+++ b/coverage/d_ad23503bef421ba7_metric_computation_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_feature_importance_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -139,7 +139,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_feature_importance_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_b228d188fec94922___init___py.html b/coverage/d_b228d188fec94922___init___py.html
index c3b86059..85f24153 100644
--- a/coverage/d_b228d188fec94922___init___py.html
+++ b/coverage/d_b228d188fec94922___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_b228d188fec94922_clustering_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -92,7 +92,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_b228d188fec94922_clustering_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_b228d188fec94922_clustering_base_py.html b/coverage/d_b228d188fec94922_clustering_base_py.html
index ab94e177..59dc287f 100644
--- a/coverage/d_b228d188fec94922_clustering_base_py.html
+++ b/coverage/d_b228d188fec94922_clustering_base_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_b228d188fec94922_greedy_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -263,7 +263,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_b228d188fec94922_greedy_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_b228d188fec94922_greedy_clustering_py.html b/coverage/d_b228d188fec94922_greedy_clustering_py.html
index 123ca61d..f060f45f 100644
--- a/coverage/d_b228d188fec94922_greedy_clustering_py.html
+++ b/coverage/d_b228d188fec94922_greedy_clustering_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_b228d188fec94922_sklearn_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -304,7 +304,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_b228d188fec94922_sklearn_clustering_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_b228d188fec94922_sklearn_clustering_py.html b/coverage/d_b228d188fec94922_sklearn_clustering_py.html
index c9afa817..c0984cbe 100644
--- a/coverage/d_b228d188fec94922_sklearn_clustering_py.html
+++ b/coverage/d_b228d188fec94922_sklearn_clustering_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_columngen_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -125,7 +125,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_columngen_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874___init___py.html b/coverage/d_c26d41993906f874___init___py.html
index 7692a64e..d5a6585c 100644
--- a/coverage/d_c26d41993906f874___init___py.html
+++ b/coverage/d_c26d41993906f874___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_catboost_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -116,7 +116,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_catboost_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_catboost_py.html b/coverage/d_c26d41993906f874_catboost_py.html
index 50f26b15..11f98b87 100644
--- a/coverage/d_c26d41993906f874_catboost_py.html
+++ b/coverage/d_c26d41993906f874_catboost_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_b228d188fec94922___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -170,7 +170,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_b228d188fec94922___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_columngen_py.html b/coverage/d_c26d41993906f874_columngen_py.html
index 4958870b..9cd4357b 100644
--- a/coverage/d_c26d41993906f874_columngen_py.html
+++ b/coverage/d_c26d41993906f874_columngen_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_data_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -252,7 +252,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_data_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_data_py.html b/coverage/d_c26d41993906f874_data_py.html
index 234cd383..a4424b25 100644
--- a/coverage/d_c26d41993906f874_data_py.html
+++ b/coverage/d_c26d41993906f874_data_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c717810afab4adb0___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -356,7 +356,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c717810afab4adb0___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_distance_metric_py.html b/coverage/d_c26d41993906f874_distance_metric_py.html
index b83937b3..9c31cd4b 100644
--- a/coverage/d_c26d41993906f874_distance_metric_py.html
+++ b/coverage/d_c26d41993906f874_distance_metric_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_643c821173b729ee___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -336,7 +336,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_643c821173b729ee___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_feature_importance_py.html b/coverage/d_c26d41993906f874_feature_importance_py.html
index dd79298e..1d64b2f0 100644
--- a/coverage/d_c26d41993906f874_feature_importance_py.html
+++ b/coverage/d_c26d41993906f874_feature_importance_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_f655864e46f781b3___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -325,7 +325,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_f655864e46f781b3___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_hyperopt_py.html b/coverage/d_c26d41993906f874_hyperopt_py.html
index e764bf29..3661f7e9 100644
--- a/coverage/d_c26d41993906f874_hyperopt_py.html
+++ b/coverage/d_c26d41993906f874_hyperopt_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_lightgbm_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -630,7 +630,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_lightgbm_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_lightgbm_py.html b/coverage/d_c26d41993906f874_lightgbm_py.html
index e422b028..83b206fa 100644
--- a/coverage/d_c26d41993906f874_lightgbm_py.html
+++ b/coverage/d_c26d41993906f874_lightgbm_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_local_search_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -203,7 +203,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_local_search_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_local_search_py.html b/coverage/d_c26d41993906f874_local_search_py.html
index 0163562b..012810b1 100644
--- a/coverage/d_c26d41993906f874_local_search_py.html
+++ b/coverage/d_c26d41993906f874_local_search_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_minizinc_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -820,7 +820,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_minizinc_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_minizinc_py.html b/coverage/d_c26d41993906f874_minizinc_py.html
index 91456c0f..43eed2e2 100644
--- a/coverage/d_c26d41993906f874_minizinc_py.html
+++ b/coverage/d_c26d41993906f874_minizinc_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_multi_model_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -260,7 +260,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_multi_model_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_multi_model_py.html b/coverage/d_c26d41993906f874_multi_model_py.html
index 6bc89f27..91609a82 100644
--- a/coverage/d_c26d41993906f874_multi_model_py.html
+++ b/coverage/d_c26d41993906f874_multi_model_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_naive_bayes_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -115,7 +115,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_naive_bayes_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_naive_bayes_py.html b/coverage/d_c26d41993906f874_naive_bayes_py.html
index 8a0761f0..dc22a29c 100644
--- a/coverage/d_c26d41993906f874_naive_bayes_py.html
+++ b/coverage/d_c26d41993906f874_naive_bayes_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_nearest_neighbors_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -157,7 +157,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_nearest_neighbors_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_nearest_neighbors_py.html b/coverage/d_c26d41993906f874_nearest_neighbors_py.html
index 1705e656..c8a15939 100644
--- a/coverage/d_c26d41993906f874_nearest_neighbors_py.html
+++ b/coverage/d_c26d41993906f874_nearest_neighbors_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_normalisation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -471,7 +471,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_normalisation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_normalisation_py.html b/coverage/d_c26d41993906f874_normalisation_py.html
index 12e3a75b..96aa9141 100644
--- a/coverage/d_c26d41993906f874_normalisation_py.html
+++ b/coverage/d_c26d41993906f874_normalisation_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ffb4ead6faaaac2___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -158,7 +158,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_3ffb4ead6faaaac2___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_sklearn_quantile_py.html b/coverage/d_c26d41993906f874_sklearn_quantile_py.html
index 2b77bd33..ac261d97 100644
--- a/coverage/d_c26d41993906f874_sklearn_quantile_py.html
+++ b/coverage/d_c26d41993906f874_sklearn_quantile_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_tensor_model_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -205,7 +205,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_tensor_model_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_tensor_model_py.html b/coverage/d_c26d41993906f874_tensor_model_py.html
index b25ce6d8..52b0294a 100644
--- a/coverage/d_c26d41993906f874_tensor_model_py.html
+++ b/coverage/d_c26d41993906f874_tensor_model_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d8dcec525de9b95d___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -483,7 +483,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d8dcec525de9b95d___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_vector_model_py.html b/coverage/d_c26d41993906f874_vector_model_py.html
index bf6b65be..0083b5d3 100644
--- a/coverage/d_c26d41993906f874_vector_model_py.html
+++ b/coverage/d_c26d41993906f874_vector_model_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_vectoriser_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -861,7 +861,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_vectoriser_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_vectoriser_py.html b/coverage/d_c26d41993906f874_vectoriser_py.html
index 0c8e8dd2..a1b8638b 100644
--- a/coverage/d_c26d41993906f874_vectoriser_py.html
+++ b/coverage/d_c26d41993906f874_vectoriser_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_xgboost_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -489,7 +489,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_xgboost_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c26d41993906f874_xgboost_py.html b/coverage/d_c26d41993906f874_xgboost_py.html
index a2b0ae73..2baad9d1 100644
--- a/coverage/d_c26d41993906f874_xgboost_py.html
+++ b/coverage/d_c26d41993906f874_xgboost_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="index.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -157,7 +157,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="index.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c677a990458909b3___init___py.html b/coverage/d_c677a990458909b3___init___py.html
index de2fd373..ecb5b91d 100644
--- a/coverage/d_c677a990458909b3___init___py.html
+++ b/coverage/d_c677a990458909b3___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c677a990458909b3_sklearn_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -91,7 +91,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c677a990458909b3_sklearn_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c677a990458909b3_sklearn_base_py.html b/coverage/d_c677a990458909b3_sklearn_base_py.html
index f42f36dd..d3f4106e 100644
--- a/coverage/d_c677a990458909b3_sklearn_base_py.html
+++ b/coverage/d_c677a990458909b3_sklearn_base_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c677a990458909b3_sklearn_classification_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -461,7 +461,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c677a990458909b3_sklearn_classification_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c677a990458909b3_sklearn_classification_py.html b/coverage/d_c677a990458909b3_sklearn_classification_py.html
index 55f3c0ad..ac85609c 100644
--- a/coverage/d_c677a990458909b3_sklearn_classification_py.html
+++ b/coverage/d_c677a990458909b3_sklearn_classification_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c677a990458909b3_sklearn_regression_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -167,7 +167,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c677a990458909b3_sklearn_regression_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c677a990458909b3_sklearn_regression_py.html b/coverage/d_c677a990458909b3_sklearn_regression_py.html
index 84a278c8..c27a0d53 100644
--- a/coverage/d_c677a990458909b3_sklearn_regression_py.html
+++ b/coverage/d_c677a990458909b3_sklearn_regression_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_sklearn_quantile_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -231,7 +231,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_sklearn_quantile_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c717810afab4adb0___init___py.html b/coverage/d_c717810afab4adb0___init___py.html
index 7872a2e6..7308e4c1 100644
--- a/coverage/d_c717810afab4adb0___init___py.html
+++ b/coverage/d_c717810afab4adb0___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c717810afab4adb0_dft_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -92,7 +92,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c717810afab4adb0_dft_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c717810afab4adb0_dft_py.html b/coverage/d_c717810afab4adb0_dft_py.html
index 3f82df25..2e857a18 100644
--- a/coverage/d_c717810afab4adb0_dft_py.html
+++ b/coverage/d_c717810afab4adb0_dft_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c717810afab4adb0_sklearn_transformer_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -1107,7 +1107,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c717810afab4adb0_sklearn_transformer_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c717810afab4adb0_sklearn_transformer_py.html b/coverage/d_c717810afab4adb0_sklearn_transformer_py.html
index 07bd5d65..e9f905b1 100644
--- a/coverage/d_c717810afab4adb0_sklearn_transformer_py.html
+++ b/coverage/d_c717810afab4adb0_sklearn_transformer_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c717810afab4adb0_value_transformation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -182,7 +182,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c717810afab4adb0_value_transformation_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_c717810afab4adb0_value_transformation_py.html b/coverage/d_c717810afab4adb0_value_transformation_py.html
index b6c05c67..182baedd 100644
--- a/coverage/d_c717810afab4adb0_value_transformation_py.html
+++ b/coverage/d_c717810afab4adb0_value_transformation_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_distance_metric_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -123,7 +123,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_c26d41993906f874_distance_metric_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_d049e11bc7279f8f_mlp_models_py.html b/coverage/d_d049e11bc7279f8f_mlp_models_py.html
index 1692a778..d0e00434 100644
--- a/coverage/d_d049e11bc7279f8f_mlp_models_py.html
+++ b/coverage/d_d049e11bc7279f8f_mlp_models_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d049e11bc7279f8f_mlp_modules_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -200,7 +200,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d049e11bc7279f8f_mlp_modules_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_d049e11bc7279f8f_mlp_modules_py.html b/coverage/d_d049e11bc7279f8f_mlp_modules_py.html
index 21dc515d..938b5cf2 100644
--- a/coverage/d_d049e11bc7279f8f_mlp_modules_py.html
+++ b/coverage/d_d049e11bc7279f8f_mlp_modules_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_337e94e8243e179c_residualffn_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -136,7 +136,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_337e94e8243e179c_residualffn_models_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_d8dcec525de9b95d___init___py.html b/coverage/d_d8dcec525de9b95d___init___py.html
index d422ec0d..bb2eb49e 100644
--- a/coverage/d_d8dcec525de9b95d___init___py.html
+++ b/coverage/d_d8dcec525de9b95d___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d8dcec525de9b95d_tf_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -91,7 +91,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d8dcec525de9b95d_tf_base_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_d8dcec525de9b95d_tf_base_py.html b/coverage/d_d8dcec525de9b95d_tf_base_py.html
index cbf4a36f..6fec591f 100644
--- a/coverage/d_d8dcec525de9b95d_tf_base_py.html
+++ b/coverage/d_d8dcec525de9b95d_tf_base_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d8dcec525de9b95d_tf_mlp_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -215,7 +215,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_d8dcec525de9b95d_tf_mlp_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_d8dcec525de9b95d_tf_mlp_py.html b/coverage/d_d8dcec525de9b95d_tf_mlp_py.html
index 07187548..12adc1be 100644
--- a/coverage/d_d8dcec525de9b95d_tf_mlp_py.html
+++ b/coverage/d_d8dcec525de9b95d_tf_mlp_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -117,7 +117,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_535e1cc7b06ed03f___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_f655864e46f781b3___init___py.html b/coverage/d_f655864e46f781b3___init___py.html
index 5951da0a..d2838349 100644
--- a/coverage/d_f655864e46f781b3___init___py.html
+++ b/coverage/d_f655864e46f781b3___init___py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_f655864e46f781b3_feature_generator_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -91,7 +91,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_f655864e46f781b3_feature_generator_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_f655864e46f781b3_feature_generator_py.html b/coverage/d_f655864e46f781b3_feature_generator_py.html
index 41592eb8..02933342 100644
--- a/coverage/d_f655864e46f781b3_feature_generator_py.html
+++ b/coverage/d_f655864e46f781b3_feature_generator_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_f655864e46f781b3_feature_generator_registry_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -1002,7 +1002,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_f655864e46f781b3_feature_generator_registry_py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/d_f655864e46f781b3_feature_generator_registry_py.html b/coverage/d_f655864e46f781b3_feature_generator_registry_py.html
index 144f6488..d0f5ab1e 100644
--- a/coverage/d_f655864e46f781b3_feature_generator_registry_py.html
+++ b/coverage/d_f655864e46f781b3_feature_generator_registry_py.html
@@ -65,7 +65,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
         <aside class="hidden">
             <button type="button" class="button_next_chunk" data-shortcut="j"/>
@@ -284,7 +284,7 @@ <h2>
             <a id="nextFileLink" class="nav" href="d_7eceb030faf4fa5b___init___py.html">&#xbb; next</a>
             &nbsp; &nbsp; &nbsp;
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </footer>
diff --git a/coverage/index.html b/coverage/index.html
index db39d11d..ee74859f 100644
--- a/coverage/index.html
+++ b/coverage/index.html
@@ -45,7 +45,7 @@ <h1>Coverage report:
         </form>
         <p class="text">
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
 </header>
@@ -658,10 +658,10 @@ <h1>Coverage report:
             </tr>
             <tr class="file">
                 <td class="name left"><a href="d_3ccb7b6033502eb6_cache_py.html">src/sensai/util/cache.py</a></td>
-                <td>433</td>
-                <td>321</td>
+                <td>434</td>
+                <td>322</td>
                 <td>0</td>
-                <td class="right" data-ratio="112 433">26%</td>
+                <td class="right" data-ratio="112 434">26%</td>
             </tr>
             <tr class="file">
                 <td class="name left"><a href="d_3ccb7b6033502eb6_cache_azure_py.html">src/sensai/util/cache_azure.py</a></td>
@@ -728,10 +728,10 @@ <h1>Coverage report:
             </tr>
             <tr class="file">
                 <td class="name left"><a href="d_3ccb7b6033502eb6_logging_py.html">src/sensai/util/logging.py</a></td>
-                <td>152</td>
-                <td>91</td>
+                <td>154</td>
+                <td>93</td>
                 <td>0</td>
-                <td class="right" data-ratio="61 152">40%</td>
+                <td class="right" data-ratio="61 154">40%</td>
             </tr>
             <tr class="file">
                 <td class="name left"><a href="d_3ccb7b6033502eb6_math_py.html">src/sensai/util/math.py</a></td>
@@ -756,10 +756,10 @@ <h1>Coverage report:
             </tr>
             <tr class="file">
                 <td class="name left"><a href="d_3ccb7b6033502eb6_pickle_py.html">src/sensai/util/pickle.py</a></td>
-                <td>133</td>
-                <td>88</td>
+                <td>141</td>
+                <td>94</td>
                 <td>0</td>
-                <td class="right" data-ratio="45 133">34%</td>
+                <td class="right" data-ratio="47 141">33%</td>
             </tr>
             <tr class="file">
                 <td class="name left"><a href="d_3ccb7b6033502eb6_plot_py.html">src/sensai/util/plot.py</a></td>
@@ -842,10 +842,10 @@ <h1>Coverage report:
         <tfoot>
             <tr class="total">
                 <td class="name left">Total</td>
-                <td>11815</td>
-                <td>6841</td>
+                <td>11826</td>
+                <td>6850</td>
                 <td>0</td>
-                <td class="right" data-ratio="4974 11815">42%</td>
+                <td class="right" data-ratio="4976 11826">42%</td>
             </tr>
         </tfoot>
     </table>
@@ -857,7 +857,7 @@ <h1>Coverage report:
     <div class="content">
         <p>
             <a class="nav" href="https://coverage.readthedocs.io/en/7.2.7">coverage.py v7.2.7</a>,
-            created at 2024-03-02 11:39 +0000
+            created at 2024-03-18 20:05 +0000
         </p>
     </div>
     <aside class="hidden">
diff --git a/coverage/status.json b/coverage/status.json
index 9eef3511..4169809e 100644
--- a/coverage/status.json
+++ b/coverage/status.json
@@ -1 +1 @@
-{"format":2,"version":"7.2.7","globals":"dabdb271e48834cae039a7ec25509a82","files":{"d_145eef247bfb46b6___init___py":{"hash":"8f96e0487d400bed7b4c91e861310773","index":{"nums":[0,1,0,0,0,0,0,0],"html_filename":"d_145eef247bfb46b6___init___py.html","relative_filename":"src/__init__.py"}},"d_c26d41993906f874___init___py":{"hash":"bd39a80a9747bfb2f2077097828c2977","index":{"nums":[0,1,17,0,0,0,0,0],"html_filename":"d_c26d41993906f874___init___py.html","relative_filename":"src/sensai/__init__.py"}},"d_c26d41993906f874_catboost_py":{"hash":"ccd189561346ce8447ea1996d991c05a","index":{"nums":[0,1,44,0,44,0,0,0],"html_filename":"d_c26d41993906f874_catboost_py.html","relative_filename":"src/sensai/catboost.py"}},"d_b228d188fec94922___init___py":{"hash":"6c19a47140bc80459f82b3a224e4fddc","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_b228d188fec94922___init___py.html","relative_filename":"src/sensai/clustering/__init__.py"}},"d_b228d188fec94922_clustering_base_py":{"hash":"3095c974cf1876f19339df8e0935c10e","index":{"nums":[0,1,108,0,72,0,0,0],"html_filename":"d_b228d188fec94922_clustering_base_py.html","relative_filename":"src/sensai/clustering/clustering_base.py"}},"d_b228d188fec94922_greedy_clustering_py":{"hash":"a6673c11433388fd26b81ed4c4103feb","index":{"nums":[0,1,111,0,78,0,0,0],"html_filename":"d_b228d188fec94922_greedy_clustering_py.html","relative_filename":"src/sensai/clustering/greedy_clustering.py"}},"d_b228d188fec94922_sklearn_clustering_py":{"hash":"67f02b1b130a2146d2294e790bb02051","index":{"nums":[0,1,15,0,5,0,0,0],"html_filename":"d_b228d188fec94922_sklearn_clustering_py.html","relative_filename":"src/sensai/clustering/sklearn_clustering.py"}},"d_c26d41993906f874_columngen_py":{"hash":"3f892cd4721a86db6ef72db8d540511f","index":{"nums":[0,1,78,0,52,0,0,0],"html_filename":"d_c26d41993906f874_columngen_py.html","relative_filename":"src/sensai/columngen.py"}},"d_c26d41993906f874_data_py":{"hash":"b7db740e756cb8a528e6d9a06ff901e7","index":{"nums":[0,1,169,0,73,0,0,0],"html_filename":"d_c26d41993906f874_data_py.html","relative_filename":"src/sensai/data.py"}},"d_c717810afab4adb0___init___py":{"hash":"f1c40568e708ca4fbea4fc701c04fd8d","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_c717810afab4adb0___init___py.html","relative_filename":"src/sensai/data_transformation/__init__.py"}},"d_c717810afab4adb0_dft_py":{"hash":"50a64d3815d1c94abeec896a11e14f00","index":{"nums":[0,1,564,0,223,0,0,0],"html_filename":"d_c717810afab4adb0_dft_py.html","relative_filename":"src/sensai/data_transformation/dft.py"}},"d_c717810afab4adb0_sklearn_transformer_py":{"hash":"acd189dcdd409fb4e5e047b10ee4cf06","index":{"nums":[0,1,49,0,18,0,0,0],"html_filename":"d_c717810afab4adb0_sklearn_transformer_py.html","relative_filename":"src/sensai/data_transformation/sklearn_transformer.py"}},"d_c717810afab4adb0_value_transformation_py":{"hash":"037055b6cebb41c383a36397049c7b22","index":{"nums":[0,1,19,0,13,0,0,0],"html_filename":"d_c717810afab4adb0_value_transformation_py.html","relative_filename":"src/sensai/data_transformation/value_transformation.py"}},"d_c26d41993906f874_distance_metric_py":{"hash":"c8ee04f0817d0051c5e3396ba0f44b8d","index":{"nums":[0,1,169,0,109,0,0,0],"html_filename":"d_c26d41993906f874_distance_metric_py.html","relative_filename":"src/sensai/distance_metric.py"}},"d_643c821173b729ee___init___py":{"hash":"9bc9c4643ef860bce7b46393c63ad492","index":{"nums":[0,1,1,0,0,0,0,0],"html_filename":"d_643c821173b729ee___init___py.html","relative_filename":"src/sensai/ensemble/__init__.py"}},"d_643c821173b729ee_ensemble_base_py":{"hash":"133547dc30c894ea14cbf4d350d4641b","index":{"nums":[0,1,52,0,33,0,0,0],"html_filename":"d_643c821173b729ee_ensemble_base_py.html","relative_filename":"src/sensai/ensemble/ensemble_base.py"}},"d_643c821173b729ee_models_py":{"hash":"9bf3be55f9b16a1a24540a88cebea064","index":{"nums":[0,1,24,0,16,0,0,0],"html_filename":"d_643c821173b729ee_models_py.html","relative_filename":"src/sensai/ensemble/models.py"}},"d_ad23503bef421ba7___init___py":{"hash":"46e85f9fc396e34f6319cef0e87cc525","index":{"nums":[0,1,6,0,0,0,0,0],"html_filename":"d_ad23503bef421ba7___init___py.html","relative_filename":"src/sensai/evaluation/__init__.py"}},"d_ad23503bef421ba7_crossval_py":{"hash":"ee7ac67553eb2d1d708dbd64146e1831","index":{"nums":[0,1,155,0,94,0,0,0],"html_filename":"d_ad23503bef421ba7_crossval_py.html","relative_filename":"src/sensai/evaluation/crossval.py"}},"d_4a7aa1929d28f620___init___py":{"hash":"0cdddf5fc4e9f3e80a57c4840079c91b","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_4a7aa1929d28f620___init___py.html","relative_filename":"src/sensai/evaluation/eval_stats/__init__.py"}},"d_4a7aa1929d28f620_eval_stats_base_py":{"hash":"9d5481d2d00deabe6bfaf4cb953472c1","index":{"nums":[0,1,196,0,95,0,0,0],"html_filename":"d_4a7aa1929d28f620_eval_stats_base_py.html","relative_filename":"src/sensai/evaluation/eval_stats/eval_stats_base.py"}},"d_4a7aa1929d28f620_eval_stats_classification_py":{"hash":"88f50ca9a9ae919938212a8ee9255911","index":{"nums":[0,1,403,0,249,0,0,0],"html_filename":"d_4a7aa1929d28f620_eval_stats_classification_py.html","relative_filename":"src/sensai/evaluation/eval_stats/eval_stats_classification.py"}},"d_4a7aa1929d28f620_eval_stats_clustering_py":{"hash":"5ce16ece9402dcd00bab0549c1a98f6d","index":{"nums":[0,1,130,0,57,0,0,0],"html_filename":"d_4a7aa1929d28f620_eval_stats_clustering_py.html","relative_filename":"src/sensai/evaluation/eval_stats/eval_stats_clustering.py"}},"d_4a7aa1929d28f620_eval_stats_regression_py":{"hash":"53c2ba3b3b53f40f691fc06c23df9a80","index":{"nums":[0,1,182,0,77,0,0,0],"html_filename":"d_4a7aa1929d28f620_eval_stats_regression_py.html","relative_filename":"src/sensai/evaluation/eval_stats/eval_stats_regression.py"}},"d_ad23503bef421ba7_eval_util_py":{"hash":"8ab4e25544b237594da5e9dd4a100747","index":{"nums":[0,1,530,0,422,0,0,0],"html_filename":"d_ad23503bef421ba7_eval_util_py.html","relative_filename":"src/sensai/evaluation/eval_util.py"}},"d_ad23503bef421ba7_evaluator_py":{"hash":"206acbbda199c31b1012bf4a0ef94294","index":{"nums":[0,1,233,0,80,0,0,0],"html_filename":"d_ad23503bef421ba7_evaluator_py.html","relative_filename":"src/sensai/evaluation/evaluator.py"}},"d_ad23503bef421ba7_evaluator_clustering_py":{"hash":"c6cbd8a3775b3a7b8ca239e92b9cf4cd","index":{"nums":[0,1,36,0,36,0,0,0],"html_filename":"d_ad23503bef421ba7_evaluator_clustering_py.html","relative_filename":"src/sensai/evaluation/evaluator_clustering.py"}},"d_ad23503bef421ba7_metric_computation_py":{"hash":"073883e05676a7ec9ac075a840da0435","index":{"nums":[0,1,36,0,36,0,0,0],"html_filename":"d_ad23503bef421ba7_metric_computation_py.html","relative_filename":"src/sensai/evaluation/metric_computation.py"}},"d_c26d41993906f874_feature_importance_py":{"hash":"8d506e617c42aa95aadf4a9f244baa4e","index":{"nums":[0,1,137,0,93,0,0,0],"html_filename":"d_c26d41993906f874_feature_importance_py.html","relative_filename":"src/sensai/feature_importance.py"}},"d_f655864e46f781b3___init___py":{"hash":"87d5119dfb281ebc394c3b7698e92b49","index":{"nums":[0,1,2,0,0,0,0,0],"html_filename":"d_f655864e46f781b3___init___py.html","relative_filename":"src/sensai/featuregen/__init__.py"}},"d_f655864e46f781b3_feature_generator_py":{"hash":"77962ff60060a6b636943add2d31c945","index":{"nums":[0,1,415,0,161,0,0,0],"html_filename":"d_f655864e46f781b3_feature_generator_py.html","relative_filename":"src/sensai/featuregen/feature_generator.py"}},"d_f655864e46f781b3_feature_generator_registry_py":{"hash":"8911d89176794fc5a8aad629c35fd017","index":{"nums":[0,1,67,0,9,0,0,0],"html_filename":"d_f655864e46f781b3_feature_generator_registry_py.html","relative_filename":"src/sensai/featuregen/feature_generator_registry.py"}},"d_7eceb030faf4fa5b___init___py":{"hash":"3c77fc9ef7f887ac2508d4109cf92472","index":{"nums":[0,1,0,0,0,0,0,0],"html_filename":"d_7eceb030faf4fa5b___init___py.html","relative_filename":"src/sensai/geoanalytics/__init__.py"}},"d_7eceb030faf4fa5b__globalmaptiles_py":{"hash":"8752e08e07e31073ccbd55f17755197f","index":{"nums":[0,1,86,0,86,0,0,0],"html_filename":"d_7eceb030faf4fa5b__globalmaptiles_py.html","relative_filename":"src/sensai/geoanalytics/_globalmaptiles.py"}},"d_7eceb030faf4fa5b_geo_clustering_py":{"hash":"002d32f476e5bc513ae33bde9d128e84","index":{"nums":[0,1,163,0,163,0,0,0],"html_filename":"d_7eceb030faf4fa5b_geo_clustering_py.html","relative_filename":"src/sensai/geoanalytics/geo_clustering.py"}},"d_7eceb030faf4fa5b_geo_coords_py":{"hash":"3f7bd1bf2d19cb740ebfd4061525f9a5","index":{"nums":[0,1,110,0,110,0,0,0],"html_filename":"d_7eceb030faf4fa5b_geo_coords_py.html","relative_filename":"src/sensai/geoanalytics/geo_coords.py"}},"d_96cde01957db023b___init___py":{"hash":"018c7be3afe40b98e6fcca3ebb03d841","index":{"nums":[0,1,1,0,0,0,0,0],"html_filename":"d_96cde01957db023b___init___py.html","relative_filename":"src/sensai/geoanalytics/geopandas/__init__.py"}},"d_96cde01957db023b_coordinate_clustering_py":{"hash":"be3098cf7051dcd868ae49e8e27827e1","index":{"nums":[0,1,69,0,38,0,0,0],"html_filename":"d_96cde01957db023b_coordinate_clustering_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/coordinate_clustering.py"}},"d_96cde01957db023b_coordinate_clustering_ground_truth_py":{"hash":"01402d7764147296395b22d7b7b0b6c9","index":{"nums":[0,1,58,0,45,0,0,0],"html_filename":"d_96cde01957db023b_coordinate_clustering_ground_truth_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/coordinate_clustering_ground_truth.py"}},"d_96cde01957db023b_coordinates_py":{"hash":"3d7132b37809dead8d5c1cdee31bb24c","index":{"nums":[0,1,28,0,15,0,0,0],"html_filename":"d_96cde01957db023b_coordinates_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/coordinates.py"}},"d_96cde01957db023b_geometry_py":{"hash":"375bdde18140f978aefdf2650f392ce9","index":{"nums":[0,1,36,0,25,0,0,0],"html_filename":"d_96cde01957db023b_geometry_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/geometry.py"}},"d_96cde01957db023b_graph_py":{"hash":"bc3136a48287f9d1f4bdaf6aa12f4bb3","index":{"nums":[0,1,46,0,26,0,0,0],"html_filename":"d_96cde01957db023b_graph_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/graph.py"}},"d_7eceb030faf4fa5b_local_coords_py":{"hash":"fb1ed67b326f4c8b29f8e92d0778e26f","index":{"nums":[0,1,102,0,102,0,0,0],"html_filename":"d_7eceb030faf4fa5b_local_coords_py.html","relative_filename":"src/sensai/geoanalytics/local_coords.py"}},"d_7eceb030faf4fa5b_map_tiles_py":{"hash":"19ec0067a81ef54d223596fe43475402","index":{"nums":[0,1,41,0,41,0,0,0],"html_filename":"d_7eceb030faf4fa5b_map_tiles_py.html","relative_filename":"src/sensai/geoanalytics/map_tiles.py"}},"d_c26d41993906f874_hyperopt_py":{"hash":"93df38cbc9bc8def02e231500027d83e","index":{"nums":[0,1,294,0,227,0,0,0],"html_filename":"d_c26d41993906f874_hyperopt_py.html","relative_filename":"src/sensai/hyperopt.py"}},"d_c26d41993906f874_lightgbm_py":{"hash":"3cace60410b786887d42058c1ef287ae","index":{"nums":[0,1,47,0,47,0,0,0],"html_filename":"d_c26d41993906f874_lightgbm_py.html","relative_filename":"src/sensai/lightgbm.py"}},"d_c26d41993906f874_local_search_py":{"hash":"153c62859e754a06bf51967822e90f18","index":{"nums":[0,1,380,0,280,0,0,0],"html_filename":"d_c26d41993906f874_local_search_py.html","relative_filename":"src/sensai/local_search.py"}},"d_c26d41993906f874_minizinc_py":{"hash":"1d3ab2683075b80f7175fa3a46f5b907","index":{"nums":[0,1,102,0,102,0,0,0],"html_filename":"d_c26d41993906f874_minizinc_py.html","relative_filename":"src/sensai/minizinc.py"}},"d_c26d41993906f874_multi_model_py":{"hash":"fdfec5f54692d0c2ecaea88117848ddc","index":{"nums":[0,1,17,0,17,0,0,0],"html_filename":"d_c26d41993906f874_multi_model_py.html","relative_filename":"src/sensai/multi_model.py"}},"d_c26d41993906f874_naive_bayes_py":{"hash":"7b92fea42ba57b5682f486deac862f72","index":{"nums":[0,1,53,0,42,0,0,0],"html_filename":"d_c26d41993906f874_naive_bayes_py.html","relative_filename":"src/sensai/naive_bayes.py"}},"d_c26d41993906f874_nearest_neighbors_py":{"hash":"77bcf0f29e85a4650d75b13ba5a531c0","index":{"nums":[0,1,247,0,176,0,0,0],"html_filename":"d_c26d41993906f874_nearest_neighbors_py.html","relative_filename":"src/sensai/nearest_neighbors.py"}},"d_c26d41993906f874_normalisation_py":{"hash":"f74ca6140a8734ed05fad11423d2cc66","index":{"nums":[0,1,54,0,15,0,0,0],"html_filename":"d_c26d41993906f874_normalisation_py.html","relative_filename":"src/sensai/normalisation.py"}},"d_3ffb4ead6faaaac2___init___py":{"hash":"b12601160078f8ae3291f6cbf01bd73c","index":{"nums":[0,1,1,0,1,0,0,0],"html_filename":"d_3ffb4ead6faaaac2___init___py.html","relative_filename":"src/sensai/pytorch_lightning/__init__.py"}},"d_3ffb4ead6faaaac2_pl_models_py":{"hash":"0e313b618f0c2abfba4cbf4ef470edd2","index":{"nums":[0,1,61,0,61,0,0,0],"html_filename":"d_3ffb4ead6faaaac2_pl_models_py.html","relative_filename":"src/sensai/pytorch_lightning/pl_models.py"}},"d_c677a990458909b3___init___py":{"hash":"c73b838897c6a085bd7a7cb1aebcbc92","index":{"nums":[0,1,2,0,0,0,0,0],"html_filename":"d_c677a990458909b3___init___py.html","relative_filename":"src/sensai/sklearn/__init__.py"}},"d_c677a990458909b3_sklearn_base_py":{"hash":"e685b07f4599f0fee2ac544534257bc7","index":{"nums":[0,1,218,0,61,0,0,0],"html_filename":"d_c677a990458909b3_sklearn_base_py.html","relative_filename":"src/sensai/sklearn/sklearn_base.py"}},"d_c677a990458909b3_sklearn_classification_py":{"hash":"249a0a9677f9e10cc4f9490f46be1755","index":{"nums":[0,1,35,0,7,0,0,0],"html_filename":"d_c677a990458909b3_sklearn_classification_py.html","relative_filename":"src/sensai/sklearn/sklearn_classification.py"}},"d_c677a990458909b3_sklearn_regression_py":{"hash":"1d7489c666982ac214419f320ce479da","index":{"nums":[0,1,55,0,11,0,0,0],"html_filename":"d_c677a990458909b3_sklearn_regression_py.html","relative_filename":"src/sensai/sklearn/sklearn_regression.py"}},"d_c26d41993906f874_sklearn_quantile_py":{"hash":"b4e77ecab2b1c95a7efb72120ecf144e","index":{"nums":[0,1,69,0,69,0,0,0],"html_filename":"d_c26d41993906f874_sklearn_quantile_py.html","relative_filename":"src/sensai/sklearn_quantile.py"}},"d_c26d41993906f874_tensor_model_py":{"hash":"82965bf5b15df75c4dd02976a684bbd5","index":{"nums":[0,1,175,0,118,0,0,0],"html_filename":"d_c26d41993906f874_tensor_model_py.html","relative_filename":"src/sensai/tensor_model.py"}},"d_d8dcec525de9b95d___init___py":{"hash":"45fd4d8260090d75c3ebaee41206f659","index":{"nums":[0,1,2,0,0,0,0,0],"html_filename":"d_d8dcec525de9b95d___init___py.html","relative_filename":"src/sensai/tensorflow/__init__.py"}},"d_d8dcec525de9b95d_tf_base_py":{"hash":"f4c30d462b3564afaf06e31c42affac9","index":{"nums":[0,1,75,0,53,0,0,0],"html_filename":"d_d8dcec525de9b95d_tf_base_py.html","relative_filename":"src/sensai/tensorflow/tf_base.py"}},"d_d8dcec525de9b95d_tf_mlp_py":{"hash":"08bba42a93bedbdfb5438d28c0f563ff","index":{"nums":[0,1,19,0,12,0,0,0],"html_filename":"d_d8dcec525de9b95d_tf_mlp_py.html","relative_filename":"src/sensai/tensorflow/tf_mlp.py"}},"d_535e1cc7b06ed03f___init___py":{"hash":"4db34afeafe4cd06c8e8c35c132e3058","index":{"nums":[0,1,5,0,0,0,0,0],"html_filename":"d_535e1cc7b06ed03f___init___py.html","relative_filename":"src/sensai/torch/__init__.py"}},"d_535e1cc7b06ed03f_torch_base_py":{"hash":"42ffd3f2d916df16ecc6e85efc1262c1","index":{"nums":[0,1,451,0,134,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_base_py.html","relative_filename":"src/sensai/torch/torch_base.py"}},"d_535e1cc7b06ed03f_torch_data_py":{"hash":"db8690850cf71e4c47f0efb576715191","index":{"nums":[0,1,384,0,128,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_data_py.html","relative_filename":"src/sensai/torch/torch_data.py"}},"d_535e1cc7b06ed03f_torch_enums_py":{"hash":"b10d33f9b0afcf4f0be72d1dcfa1e61e","index":{"nums":[0,1,57,0,17,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_enums_py.html","relative_filename":"src/sensai/torch/torch_enums.py"}},"d_535e1cc7b06ed03f_torch_eval_util_py":{"hash":"b4bdd3845a58cb2a6a34515e8abccc6c","index":{"nums":[0,1,18,0,18,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_eval_util_py.html","relative_filename":"src/sensai/torch/torch_eval_util.py"}},"d_3c6d3a4d2db9b72b___init___py":{"hash":"b2d2d89feb121bd1cb0072bdae029f94","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_3c6d3a4d2db9b72b___init___py.html","relative_filename":"src/sensai/torch/torch_models/__init__.py"}},"d_8e16ca04a866d040_lstnet_models_py":{"hash":"6f2f36300c266335dc854c800858585a","index":{"nums":[0,1,102,0,73,0,0,0],"html_filename":"d_8e16ca04a866d040_lstnet_models_py.html","relative_filename":"src/sensai/torch/torch_models/lstnet/lstnet_models.py"}},"d_8e16ca04a866d040_lstnet_modules_py":{"hash":"7e94a6e8dcb299b3f37808f6a5e9a49d","index":{"nums":[0,1,106,0,85,0,0,0],"html_filename":"d_8e16ca04a866d040_lstnet_modules_py.html","relative_filename":"src/sensai/torch/torch_models/lstnet/lstnet_modules.py"}},"d_d049e11bc7279f8f_mlp_models_py":{"hash":"5a53019c95fd12c0d1076733c8f6feb8","index":{"nums":[0,1,42,0,0,0,0,0],"html_filename":"d_d049e11bc7279f8f_mlp_models_py.html","relative_filename":"src/sensai/torch/torch_models/mlp/mlp_models.py"}},"d_d049e11bc7279f8f_mlp_modules_py":{"hash":"ff8fa423a6257d54119c3e489202f894","index":{"nums":[0,1,34,0,3,0,0,0],"html_filename":"d_d049e11bc7279f8f_mlp_modules_py.html","relative_filename":"src/sensai/torch/torch_models/mlp/mlp_modules.py"}},"d_337e94e8243e179c_residualffn_models_py":{"hash":"c02ebcbc45b18cb0d1efdb3439520503","index":{"nums":[0,1,27,0,0,0,0,0],"html_filename":"d_337e94e8243e179c_residualffn_models_py.html","relative_filename":"src/sensai/torch/torch_models/residualffn/residualffn_models.py"}},"d_337e94e8243e179c_residualffn_modules_py":{"hash":"2822234a5a5d6e53797dbe30a3470bb8","index":{"nums":[0,1,83,0,15,0,0,0],"html_filename":"d_337e94e8243e179c_residualffn_modules_py.html","relative_filename":"src/sensai/torch/torch_models/residualffn/residualffn_modules.py"}},"d_535e1cc7b06ed03f_torch_modules_py":{"hash":"d87fbcdf95f1d80b59b3bc526877ee9d","index":{"nums":[0,1,6,0,0,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_modules_py.html","relative_filename":"src/sensai/torch/torch_modules.py"}},"d_535e1cc7b06ed03f_torch_opt_py":{"hash":"76637fc7fed8875a8a4a6b41e216e8ac","index":{"nums":[0,1,568,0,114,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_opt_py.html","relative_filename":"src/sensai/torch/torch_opt.py"}},"d_535e1cc7b06ed03f_torchtext_py":{"hash":"50666147dcc6611e16d1d9238d30c9b8","index":{"nums":[0,1,51,0,51,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torchtext_py.html","relative_filename":"src/sensai/torch/torchtext.py"}},"d_968cc2eb7979e5c9___init___py":{"hash":"e6066900ef9e271efd149ed3648e67c5","index":{"nums":[0,1,1,0,0,0,0,0],"html_filename":"d_968cc2eb7979e5c9___init___py.html","relative_filename":"src/sensai/tracking/__init__.py"}},"d_968cc2eb7979e5c9_azure_tracking_py":{"hash":"c5699bdd7ac6a1deaa5f35da5b16701c","index":{"nums":[0,1,29,0,29,0,0,0],"html_filename":"d_968cc2eb7979e5c9_azure_tracking_py.html","relative_filename":"src/sensai/tracking/azure_tracking.py"}},"d_968cc2eb7979e5c9_clearml_tracking_py":{"hash":"85005c730151cd51bfb352f32ed16f18","index":{"nums":[0,1,36,0,36,0,0,0],"html_filename":"d_968cc2eb7979e5c9_clearml_tracking_py.html","relative_filename":"src/sensai/tracking/clearml_tracking.py"}},"d_968cc2eb7979e5c9_mlflow_tracking_py":{"hash":"08da7c372331207cfb33078235d4a330","index":{"nums":[0,1,57,0,57,0,0,0],"html_filename":"d_968cc2eb7979e5c9_mlflow_tracking_py.html","relative_filename":"src/sensai/tracking/mlflow_tracking.py"}},"d_968cc2eb7979e5c9_tracking_base_py":{"hash":"80521a41f5dfe58157146c5ca0ed515b","index":{"nums":[0,1,106,0,38,0,0,0],"html_filename":"d_968cc2eb7979e5c9_tracking_base_py.html","relative_filename":"src/sensai/tracking/tracking_base.py"}},"d_3ccb7b6033502eb6___init___py":{"hash":"5825e443191eb73caf035f8b032dede8","index":{"nums":[0,1,11,0,0,0,0,0],"html_filename":"d_3ccb7b6033502eb6___init___py.html","relative_filename":"src/sensai/util/__init__.py"}},"d_3ccb7b6033502eb6_aggregation_py":{"hash":"a1d97ecc698a6bf09cbbe95e8a0381db","index":{"nums":[0,1,47,0,27,0,0,0],"html_filename":"d_3ccb7b6033502eb6_aggregation_py.html","relative_filename":"src/sensai/util/aggregation.py"}},"d_3ccb7b6033502eb6_cache_py":{"hash":"9e0e7c2a2aab3700c1709caae84fc7a5","index":{"nums":[0,1,433,0,321,0,0,0],"html_filename":"d_3ccb7b6033502eb6_cache_py.html","relative_filename":"src/sensai/util/cache.py"}},"d_3ccb7b6033502eb6_cache_azure_py":{"hash":"570b27180932ca88851dc7309b4a6ce6","index":{"nums":[0,1,388,0,388,0,0,0],"html_filename":"d_3ccb7b6033502eb6_cache_azure_py.html","relative_filename":"src/sensai/util/cache_azure.py"}},"d_3ccb7b6033502eb6_cache_mysql_py":{"hash":"a5cc2df1cd10df022da547a0f4474690","index":{"nums":[0,1,70,0,53,0,0,0],"html_filename":"d_3ccb7b6033502eb6_cache_mysql_py.html","relative_filename":"src/sensai/util/cache_mysql.py"}},"d_3ccb7b6033502eb6_datastruct_py":{"hash":"bf2327abb6eed2b4045d8583171be683","index":{"nums":[0,1,214,0,45,0,0,0],"html_filename":"d_3ccb7b6033502eb6_datastruct_py.html","relative_filename":"src/sensai/util/datastruct.py"}},"d_3ccb7b6033502eb6_deprecation_py":{"hash":"92ed5e591d4c88ec41354a9958978571","index":{"nums":[0,1,15,0,2,0,0,0],"html_filename":"d_3ccb7b6033502eb6_deprecation_py.html","relative_filename":"src/sensai/util/deprecation.py"}},"d_3ccb7b6033502eb6_dtype_py":{"hash":"60447f9fb590036805d6412acdc9f799","index":{"nums":[0,1,20,0,7,0,0,0],"html_filename":"d_3ccb7b6033502eb6_dtype_py.html","relative_filename":"src/sensai/util/dtype.py"}},"d_3ccb7b6033502eb6_hash_py":{"hash":"9dc97e9780e375b5206be273c3aeffa4","index":{"nums":[0,1,15,0,10,0,0,0],"html_filename":"d_3ccb7b6033502eb6_hash_py.html","relative_filename":"src/sensai/util/hash.py"}},"d_3ccb7b6033502eb6_helper_py":{"hash":"019585dde0e219d7a9c3cd2187676d09","index":{"nums":[0,1,28,0,5,0,0,0],"html_filename":"d_3ccb7b6033502eb6_helper_py.html","relative_filename":"src/sensai/util/helper.py"}},"d_3ccb7b6033502eb6_io_py":{"hash":"2aba041cb5a9e70749024ee6028b874f","index":{"nums":[0,1,120,0,84,0,0,0],"html_filename":"d_3ccb7b6033502eb6_io_py.html","relative_filename":"src/sensai/util/io.py"}},"d_3ccb7b6033502eb6_jscode_py":{"hash":"b54aeca0a4a255286e4ec960a053e326","index":{"nums":[0,1,95,0,95,0,0,0],"html_filename":"d_3ccb7b6033502eb6_jscode_py.html","relative_filename":"src/sensai/util/jscode.py"}},"d_3ccb7b6033502eb6_logging_py":{"hash":"8cde00fdd7be2ef7d5551763567396ca","index":{"nums":[0,1,152,0,91,0,0,0],"html_filename":"d_3ccb7b6033502eb6_logging_py.html","relative_filename":"src/sensai/util/logging.py"}},"d_3ccb7b6033502eb6_math_py":{"hash":"2c847fa20aaff8ef9c42d5f75f9c0fc8","index":{"nums":[0,1,25,0,25,0,0,0],"html_filename":"d_3ccb7b6033502eb6_math_py.html","relative_filename":"src/sensai/util/math.py"}},"d_3ccb7b6033502eb6_multiprocessing_py":{"hash":"ff3b46d45275f9ef1a5400ffd3384de2","index":{"nums":[0,1,36,0,20,0,0,0],"html_filename":"d_3ccb7b6033502eb6_multiprocessing_py.html","relative_filename":"src/sensai/util/multiprocessing.py"}},"d_3ccb7b6033502eb6_pandas_py":{"hash":"3821d1e522f9bc6b0f3efabaebaf755f","index":{"nums":[0,1,49,0,21,0,0,0],"html_filename":"d_3ccb7b6033502eb6_pandas_py.html","relative_filename":"src/sensai/util/pandas.py"}},"d_3ccb7b6033502eb6_pickle_py":{"hash":"444eeb27562f56d32ac3b646720241b6","index":{"nums":[0,1,133,0,88,0,0,0],"html_filename":"d_3ccb7b6033502eb6_pickle_py.html","relative_filename":"src/sensai/util/pickle.py"}},"d_3ccb7b6033502eb6_plot_py":{"hash":"ac6b9228cebcb1d7f762c27963cfe999","index":{"nums":[0,1,189,0,145,0,0,0],"html_filename":"d_3ccb7b6033502eb6_plot_py.html","relative_filename":"src/sensai/util/plot.py"}},"d_3ccb7b6033502eb6_profiling_py":{"hash":"702757669eee11b1eba000179a86b1c5","index":{"nums":[0,1,32,0,23,0,0,0],"html_filename":"d_3ccb7b6033502eb6_profiling_py.html","relative_filename":"src/sensai/util/profiling.py"}},"d_3ccb7b6033502eb6_sequences_py":{"hash":"b00cd2426f8f2e6482af7c627a89390a","index":{"nums":[0,1,92,0,32,0,0,0],"html_filename":"d_3ccb7b6033502eb6_sequences_py.html","relative_filename":"src/sensai/util/sequences.py"}},"d_3ccb7b6033502eb6_string_py":{"hash":"fcc85ec2f14d2b30e89bcb9d87cca4b2","index":{"nums":[0,1,215,0,86,0,0,0],"html_filename":"d_3ccb7b6033502eb6_string_py.html","relative_filename":"src/sensai/util/string.py"}},"d_3ccb7b6033502eb6_test_py":{"hash":"6cc882f369fbc8392da76e9c41278f8e","index":{"nums":[0,1,28,0,28,0,0,0],"html_filename":"d_3ccb7b6033502eb6_test_py.html","relative_filename":"src/sensai/util/test.py"}},"d_3ccb7b6033502eb6_time_py":{"hash":"a836d509a3da93561c506b77a0e4c085","index":{"nums":[0,1,30,0,30,0,0,0],"html_filename":"d_3ccb7b6033502eb6_time_py.html","relative_filename":"src/sensai/util/time.py"}},"d_3ccb7b6033502eb6_typing_py":{"hash":"1052441f05519e193ffac73a7b2e6675","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_3ccb7b6033502eb6_typing_py.html","relative_filename":"src/sensai/util/typing.py"}},"d_3ccb7b6033502eb6_version_py":{"hash":"7b40d4848ae51caeee1d28aa222ff46a","index":{"nums":[0,1,11,0,8,0,0,0],"html_filename":"d_3ccb7b6033502eb6_version_py.html","relative_filename":"src/sensai/util/version.py"}},"d_c26d41993906f874_vector_model_py":{"hash":"4890494a5cf0076f8c858f4b8e01de01","index":{"nums":[0,1,366,0,85,0,0,0],"html_filename":"d_c26d41993906f874_vector_model_py.html","relative_filename":"src/sensai/vector_model.py"}},"d_c26d41993906f874_vectoriser_py":{"hash":"cd382e3b35c1109e6dc44b2fcb9ddbc8","index":{"nums":[0,1,202,0,202,0,0,0],"html_filename":"d_c26d41993906f874_vectoriser_py.html","relative_filename":"src/sensai/vectoriser.py"}},"d_c26d41993906f874_xgboost_py":{"hash":"55a533f1dceff678e4b91807b14bb4d4","index":{"nums":[0,1,27,0,27,0,0,0],"html_filename":"d_c26d41993906f874_xgboost_py.html","relative_filename":"src/sensai/xgboost.py"}}}}
\ No newline at end of file
+{"format":2,"version":"7.2.7","globals":"dabdb271e48834cae039a7ec25509a82","files":{"d_145eef247bfb46b6___init___py":{"hash":"8f96e0487d400bed7b4c91e861310773","index":{"nums":[0,1,0,0,0,0,0,0],"html_filename":"d_145eef247bfb46b6___init___py.html","relative_filename":"src/__init__.py"}},"d_c26d41993906f874___init___py":{"hash":"bd39a80a9747bfb2f2077097828c2977","index":{"nums":[0,1,17,0,0,0,0,0],"html_filename":"d_c26d41993906f874___init___py.html","relative_filename":"src/sensai/__init__.py"}},"d_c26d41993906f874_catboost_py":{"hash":"ccd189561346ce8447ea1996d991c05a","index":{"nums":[0,1,44,0,44,0,0,0],"html_filename":"d_c26d41993906f874_catboost_py.html","relative_filename":"src/sensai/catboost.py"}},"d_b228d188fec94922___init___py":{"hash":"6c19a47140bc80459f82b3a224e4fddc","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_b228d188fec94922___init___py.html","relative_filename":"src/sensai/clustering/__init__.py"}},"d_b228d188fec94922_clustering_base_py":{"hash":"3095c974cf1876f19339df8e0935c10e","index":{"nums":[0,1,108,0,72,0,0,0],"html_filename":"d_b228d188fec94922_clustering_base_py.html","relative_filename":"src/sensai/clustering/clustering_base.py"}},"d_b228d188fec94922_greedy_clustering_py":{"hash":"a6673c11433388fd26b81ed4c4103feb","index":{"nums":[0,1,111,0,78,0,0,0],"html_filename":"d_b228d188fec94922_greedy_clustering_py.html","relative_filename":"src/sensai/clustering/greedy_clustering.py"}},"d_b228d188fec94922_sklearn_clustering_py":{"hash":"67f02b1b130a2146d2294e790bb02051","index":{"nums":[0,1,15,0,5,0,0,0],"html_filename":"d_b228d188fec94922_sklearn_clustering_py.html","relative_filename":"src/sensai/clustering/sklearn_clustering.py"}},"d_c26d41993906f874_columngen_py":{"hash":"3f892cd4721a86db6ef72db8d540511f","index":{"nums":[0,1,78,0,52,0,0,0],"html_filename":"d_c26d41993906f874_columngen_py.html","relative_filename":"src/sensai/columngen.py"}},"d_c26d41993906f874_data_py":{"hash":"b7db740e756cb8a528e6d9a06ff901e7","index":{"nums":[0,1,169,0,73,0,0,0],"html_filename":"d_c26d41993906f874_data_py.html","relative_filename":"src/sensai/data.py"}},"d_c717810afab4adb0___init___py":{"hash":"f1c40568e708ca4fbea4fc701c04fd8d","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_c717810afab4adb0___init___py.html","relative_filename":"src/sensai/data_transformation/__init__.py"}},"d_c717810afab4adb0_dft_py":{"hash":"50a64d3815d1c94abeec896a11e14f00","index":{"nums":[0,1,564,0,223,0,0,0],"html_filename":"d_c717810afab4adb0_dft_py.html","relative_filename":"src/sensai/data_transformation/dft.py"}},"d_c717810afab4adb0_sklearn_transformer_py":{"hash":"acd189dcdd409fb4e5e047b10ee4cf06","index":{"nums":[0,1,49,0,18,0,0,0],"html_filename":"d_c717810afab4adb0_sklearn_transformer_py.html","relative_filename":"src/sensai/data_transformation/sklearn_transformer.py"}},"d_c717810afab4adb0_value_transformation_py":{"hash":"037055b6cebb41c383a36397049c7b22","index":{"nums":[0,1,19,0,13,0,0,0],"html_filename":"d_c717810afab4adb0_value_transformation_py.html","relative_filename":"src/sensai/data_transformation/value_transformation.py"}},"d_c26d41993906f874_distance_metric_py":{"hash":"c8ee04f0817d0051c5e3396ba0f44b8d","index":{"nums":[0,1,169,0,109,0,0,0],"html_filename":"d_c26d41993906f874_distance_metric_py.html","relative_filename":"src/sensai/distance_metric.py"}},"d_643c821173b729ee___init___py":{"hash":"9bc9c4643ef860bce7b46393c63ad492","index":{"nums":[0,1,1,0,0,0,0,0],"html_filename":"d_643c821173b729ee___init___py.html","relative_filename":"src/sensai/ensemble/__init__.py"}},"d_643c821173b729ee_ensemble_base_py":{"hash":"133547dc30c894ea14cbf4d350d4641b","index":{"nums":[0,1,52,0,33,0,0,0],"html_filename":"d_643c821173b729ee_ensemble_base_py.html","relative_filename":"src/sensai/ensemble/ensemble_base.py"}},"d_643c821173b729ee_models_py":{"hash":"9bf3be55f9b16a1a24540a88cebea064","index":{"nums":[0,1,24,0,16,0,0,0],"html_filename":"d_643c821173b729ee_models_py.html","relative_filename":"src/sensai/ensemble/models.py"}},"d_ad23503bef421ba7___init___py":{"hash":"46e85f9fc396e34f6319cef0e87cc525","index":{"nums":[0,1,6,0,0,0,0,0],"html_filename":"d_ad23503bef421ba7___init___py.html","relative_filename":"src/sensai/evaluation/__init__.py"}},"d_ad23503bef421ba7_crossval_py":{"hash":"ee7ac67553eb2d1d708dbd64146e1831","index":{"nums":[0,1,155,0,94,0,0,0],"html_filename":"d_ad23503bef421ba7_crossval_py.html","relative_filename":"src/sensai/evaluation/crossval.py"}},"d_4a7aa1929d28f620___init___py":{"hash":"0cdddf5fc4e9f3e80a57c4840079c91b","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_4a7aa1929d28f620___init___py.html","relative_filename":"src/sensai/evaluation/eval_stats/__init__.py"}},"d_4a7aa1929d28f620_eval_stats_base_py":{"hash":"9d5481d2d00deabe6bfaf4cb953472c1","index":{"nums":[0,1,196,0,95,0,0,0],"html_filename":"d_4a7aa1929d28f620_eval_stats_base_py.html","relative_filename":"src/sensai/evaluation/eval_stats/eval_stats_base.py"}},"d_4a7aa1929d28f620_eval_stats_classification_py":{"hash":"a1e4e7094c48615eea38fab95aba0fcb","index":{"nums":[0,1,403,0,249,0,0,0],"html_filename":"d_4a7aa1929d28f620_eval_stats_classification_py.html","relative_filename":"src/sensai/evaluation/eval_stats/eval_stats_classification.py"}},"d_4a7aa1929d28f620_eval_stats_clustering_py":{"hash":"5ce16ece9402dcd00bab0549c1a98f6d","index":{"nums":[0,1,130,0,57,0,0,0],"html_filename":"d_4a7aa1929d28f620_eval_stats_clustering_py.html","relative_filename":"src/sensai/evaluation/eval_stats/eval_stats_clustering.py"}},"d_4a7aa1929d28f620_eval_stats_regression_py":{"hash":"53c2ba3b3b53f40f691fc06c23df9a80","index":{"nums":[0,1,182,0,77,0,0,0],"html_filename":"d_4a7aa1929d28f620_eval_stats_regression_py.html","relative_filename":"src/sensai/evaluation/eval_stats/eval_stats_regression.py"}},"d_ad23503bef421ba7_eval_util_py":{"hash":"8ab4e25544b237594da5e9dd4a100747","index":{"nums":[0,1,530,0,422,0,0,0],"html_filename":"d_ad23503bef421ba7_eval_util_py.html","relative_filename":"src/sensai/evaluation/eval_util.py"}},"d_ad23503bef421ba7_evaluator_py":{"hash":"9b39c08909c8b4587db80431026067ec","index":{"nums":[0,1,233,0,80,0,0,0],"html_filename":"d_ad23503bef421ba7_evaluator_py.html","relative_filename":"src/sensai/evaluation/evaluator.py"}},"d_ad23503bef421ba7_evaluator_clustering_py":{"hash":"c6cbd8a3775b3a7b8ca239e92b9cf4cd","index":{"nums":[0,1,36,0,36,0,0,0],"html_filename":"d_ad23503bef421ba7_evaluator_clustering_py.html","relative_filename":"src/sensai/evaluation/evaluator_clustering.py"}},"d_ad23503bef421ba7_metric_computation_py":{"hash":"073883e05676a7ec9ac075a840da0435","index":{"nums":[0,1,36,0,36,0,0,0],"html_filename":"d_ad23503bef421ba7_metric_computation_py.html","relative_filename":"src/sensai/evaluation/metric_computation.py"}},"d_c26d41993906f874_feature_importance_py":{"hash":"8d506e617c42aa95aadf4a9f244baa4e","index":{"nums":[0,1,137,0,93,0,0,0],"html_filename":"d_c26d41993906f874_feature_importance_py.html","relative_filename":"src/sensai/feature_importance.py"}},"d_f655864e46f781b3___init___py":{"hash":"87d5119dfb281ebc394c3b7698e92b49","index":{"nums":[0,1,2,0,0,0,0,0],"html_filename":"d_f655864e46f781b3___init___py.html","relative_filename":"src/sensai/featuregen/__init__.py"}},"d_f655864e46f781b3_feature_generator_py":{"hash":"77962ff60060a6b636943add2d31c945","index":{"nums":[0,1,415,0,161,0,0,0],"html_filename":"d_f655864e46f781b3_feature_generator_py.html","relative_filename":"src/sensai/featuregen/feature_generator.py"}},"d_f655864e46f781b3_feature_generator_registry_py":{"hash":"8911d89176794fc5a8aad629c35fd017","index":{"nums":[0,1,67,0,9,0,0,0],"html_filename":"d_f655864e46f781b3_feature_generator_registry_py.html","relative_filename":"src/sensai/featuregen/feature_generator_registry.py"}},"d_7eceb030faf4fa5b___init___py":{"hash":"3c77fc9ef7f887ac2508d4109cf92472","index":{"nums":[0,1,0,0,0,0,0,0],"html_filename":"d_7eceb030faf4fa5b___init___py.html","relative_filename":"src/sensai/geoanalytics/__init__.py"}},"d_7eceb030faf4fa5b__globalmaptiles_py":{"hash":"8752e08e07e31073ccbd55f17755197f","index":{"nums":[0,1,86,0,86,0,0,0],"html_filename":"d_7eceb030faf4fa5b__globalmaptiles_py.html","relative_filename":"src/sensai/geoanalytics/_globalmaptiles.py"}},"d_7eceb030faf4fa5b_geo_clustering_py":{"hash":"002d32f476e5bc513ae33bde9d128e84","index":{"nums":[0,1,163,0,163,0,0,0],"html_filename":"d_7eceb030faf4fa5b_geo_clustering_py.html","relative_filename":"src/sensai/geoanalytics/geo_clustering.py"}},"d_7eceb030faf4fa5b_geo_coords_py":{"hash":"3f7bd1bf2d19cb740ebfd4061525f9a5","index":{"nums":[0,1,110,0,110,0,0,0],"html_filename":"d_7eceb030faf4fa5b_geo_coords_py.html","relative_filename":"src/sensai/geoanalytics/geo_coords.py"}},"d_96cde01957db023b___init___py":{"hash":"018c7be3afe40b98e6fcca3ebb03d841","index":{"nums":[0,1,1,0,0,0,0,0],"html_filename":"d_96cde01957db023b___init___py.html","relative_filename":"src/sensai/geoanalytics/geopandas/__init__.py"}},"d_96cde01957db023b_coordinate_clustering_py":{"hash":"be3098cf7051dcd868ae49e8e27827e1","index":{"nums":[0,1,69,0,38,0,0,0],"html_filename":"d_96cde01957db023b_coordinate_clustering_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/coordinate_clustering.py"}},"d_96cde01957db023b_coordinate_clustering_ground_truth_py":{"hash":"01402d7764147296395b22d7b7b0b6c9","index":{"nums":[0,1,58,0,45,0,0,0],"html_filename":"d_96cde01957db023b_coordinate_clustering_ground_truth_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/coordinate_clustering_ground_truth.py"}},"d_96cde01957db023b_coordinates_py":{"hash":"3d7132b37809dead8d5c1cdee31bb24c","index":{"nums":[0,1,28,0,15,0,0,0],"html_filename":"d_96cde01957db023b_coordinates_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/coordinates.py"}},"d_96cde01957db023b_geometry_py":{"hash":"375bdde18140f978aefdf2650f392ce9","index":{"nums":[0,1,36,0,25,0,0,0],"html_filename":"d_96cde01957db023b_geometry_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/geometry.py"}},"d_96cde01957db023b_graph_py":{"hash":"bc3136a48287f9d1f4bdaf6aa12f4bb3","index":{"nums":[0,1,46,0,26,0,0,0],"html_filename":"d_96cde01957db023b_graph_py.html","relative_filename":"src/sensai/geoanalytics/geopandas/graph.py"}},"d_7eceb030faf4fa5b_local_coords_py":{"hash":"fb1ed67b326f4c8b29f8e92d0778e26f","index":{"nums":[0,1,102,0,102,0,0,0],"html_filename":"d_7eceb030faf4fa5b_local_coords_py.html","relative_filename":"src/sensai/geoanalytics/local_coords.py"}},"d_7eceb030faf4fa5b_map_tiles_py":{"hash":"19ec0067a81ef54d223596fe43475402","index":{"nums":[0,1,41,0,41,0,0,0],"html_filename":"d_7eceb030faf4fa5b_map_tiles_py.html","relative_filename":"src/sensai/geoanalytics/map_tiles.py"}},"d_c26d41993906f874_hyperopt_py":{"hash":"93df38cbc9bc8def02e231500027d83e","index":{"nums":[0,1,294,0,227,0,0,0],"html_filename":"d_c26d41993906f874_hyperopt_py.html","relative_filename":"src/sensai/hyperopt.py"}},"d_c26d41993906f874_lightgbm_py":{"hash":"3cace60410b786887d42058c1ef287ae","index":{"nums":[0,1,47,0,47,0,0,0],"html_filename":"d_c26d41993906f874_lightgbm_py.html","relative_filename":"src/sensai/lightgbm.py"}},"d_c26d41993906f874_local_search_py":{"hash":"153c62859e754a06bf51967822e90f18","index":{"nums":[0,1,380,0,280,0,0,0],"html_filename":"d_c26d41993906f874_local_search_py.html","relative_filename":"src/sensai/local_search.py"}},"d_c26d41993906f874_minizinc_py":{"hash":"1d3ab2683075b80f7175fa3a46f5b907","index":{"nums":[0,1,102,0,102,0,0,0],"html_filename":"d_c26d41993906f874_minizinc_py.html","relative_filename":"src/sensai/minizinc.py"}},"d_c26d41993906f874_multi_model_py":{"hash":"fdfec5f54692d0c2ecaea88117848ddc","index":{"nums":[0,1,17,0,17,0,0,0],"html_filename":"d_c26d41993906f874_multi_model_py.html","relative_filename":"src/sensai/multi_model.py"}},"d_c26d41993906f874_naive_bayes_py":{"hash":"7b92fea42ba57b5682f486deac862f72","index":{"nums":[0,1,53,0,42,0,0,0],"html_filename":"d_c26d41993906f874_naive_bayes_py.html","relative_filename":"src/sensai/naive_bayes.py"}},"d_c26d41993906f874_nearest_neighbors_py":{"hash":"77bcf0f29e85a4650d75b13ba5a531c0","index":{"nums":[0,1,247,0,176,0,0,0],"html_filename":"d_c26d41993906f874_nearest_neighbors_py.html","relative_filename":"src/sensai/nearest_neighbors.py"}},"d_c26d41993906f874_normalisation_py":{"hash":"f74ca6140a8734ed05fad11423d2cc66","index":{"nums":[0,1,54,0,15,0,0,0],"html_filename":"d_c26d41993906f874_normalisation_py.html","relative_filename":"src/sensai/normalisation.py"}},"d_3ffb4ead6faaaac2___init___py":{"hash":"b12601160078f8ae3291f6cbf01bd73c","index":{"nums":[0,1,1,0,1,0,0,0],"html_filename":"d_3ffb4ead6faaaac2___init___py.html","relative_filename":"src/sensai/pytorch_lightning/__init__.py"}},"d_3ffb4ead6faaaac2_pl_models_py":{"hash":"0e313b618f0c2abfba4cbf4ef470edd2","index":{"nums":[0,1,61,0,61,0,0,0],"html_filename":"d_3ffb4ead6faaaac2_pl_models_py.html","relative_filename":"src/sensai/pytorch_lightning/pl_models.py"}},"d_c677a990458909b3___init___py":{"hash":"c73b838897c6a085bd7a7cb1aebcbc92","index":{"nums":[0,1,2,0,0,0,0,0],"html_filename":"d_c677a990458909b3___init___py.html","relative_filename":"src/sensai/sklearn/__init__.py"}},"d_c677a990458909b3_sklearn_base_py":{"hash":"e685b07f4599f0fee2ac544534257bc7","index":{"nums":[0,1,218,0,61,0,0,0],"html_filename":"d_c677a990458909b3_sklearn_base_py.html","relative_filename":"src/sensai/sklearn/sklearn_base.py"}},"d_c677a990458909b3_sklearn_classification_py":{"hash":"249a0a9677f9e10cc4f9490f46be1755","index":{"nums":[0,1,35,0,7,0,0,0],"html_filename":"d_c677a990458909b3_sklearn_classification_py.html","relative_filename":"src/sensai/sklearn/sklearn_classification.py"}},"d_c677a990458909b3_sklearn_regression_py":{"hash":"1d7489c666982ac214419f320ce479da","index":{"nums":[0,1,55,0,11,0,0,0],"html_filename":"d_c677a990458909b3_sklearn_regression_py.html","relative_filename":"src/sensai/sklearn/sklearn_regression.py"}},"d_c26d41993906f874_sklearn_quantile_py":{"hash":"b4e77ecab2b1c95a7efb72120ecf144e","index":{"nums":[0,1,69,0,69,0,0,0],"html_filename":"d_c26d41993906f874_sklearn_quantile_py.html","relative_filename":"src/sensai/sklearn_quantile.py"}},"d_c26d41993906f874_tensor_model_py":{"hash":"82965bf5b15df75c4dd02976a684bbd5","index":{"nums":[0,1,175,0,118,0,0,0],"html_filename":"d_c26d41993906f874_tensor_model_py.html","relative_filename":"src/sensai/tensor_model.py"}},"d_d8dcec525de9b95d___init___py":{"hash":"45fd4d8260090d75c3ebaee41206f659","index":{"nums":[0,1,2,0,0,0,0,0],"html_filename":"d_d8dcec525de9b95d___init___py.html","relative_filename":"src/sensai/tensorflow/__init__.py"}},"d_d8dcec525de9b95d_tf_base_py":{"hash":"f4c30d462b3564afaf06e31c42affac9","index":{"nums":[0,1,75,0,53,0,0,0],"html_filename":"d_d8dcec525de9b95d_tf_base_py.html","relative_filename":"src/sensai/tensorflow/tf_base.py"}},"d_d8dcec525de9b95d_tf_mlp_py":{"hash":"08bba42a93bedbdfb5438d28c0f563ff","index":{"nums":[0,1,19,0,12,0,0,0],"html_filename":"d_d8dcec525de9b95d_tf_mlp_py.html","relative_filename":"src/sensai/tensorflow/tf_mlp.py"}},"d_535e1cc7b06ed03f___init___py":{"hash":"4db34afeafe4cd06c8e8c35c132e3058","index":{"nums":[0,1,5,0,0,0,0,0],"html_filename":"d_535e1cc7b06ed03f___init___py.html","relative_filename":"src/sensai/torch/__init__.py"}},"d_535e1cc7b06ed03f_torch_base_py":{"hash":"42ffd3f2d916df16ecc6e85efc1262c1","index":{"nums":[0,1,451,0,134,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_base_py.html","relative_filename":"src/sensai/torch/torch_base.py"}},"d_535e1cc7b06ed03f_torch_data_py":{"hash":"db8690850cf71e4c47f0efb576715191","index":{"nums":[0,1,384,0,128,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_data_py.html","relative_filename":"src/sensai/torch/torch_data.py"}},"d_535e1cc7b06ed03f_torch_enums_py":{"hash":"b10d33f9b0afcf4f0be72d1dcfa1e61e","index":{"nums":[0,1,57,0,17,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_enums_py.html","relative_filename":"src/sensai/torch/torch_enums.py"}},"d_535e1cc7b06ed03f_torch_eval_util_py":{"hash":"b4bdd3845a58cb2a6a34515e8abccc6c","index":{"nums":[0,1,18,0,18,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_eval_util_py.html","relative_filename":"src/sensai/torch/torch_eval_util.py"}},"d_3c6d3a4d2db9b72b___init___py":{"hash":"b2d2d89feb121bd1cb0072bdae029f94","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_3c6d3a4d2db9b72b___init___py.html","relative_filename":"src/sensai/torch/torch_models/__init__.py"}},"d_8e16ca04a866d040_lstnet_models_py":{"hash":"6f2f36300c266335dc854c800858585a","index":{"nums":[0,1,102,0,73,0,0,0],"html_filename":"d_8e16ca04a866d040_lstnet_models_py.html","relative_filename":"src/sensai/torch/torch_models/lstnet/lstnet_models.py"}},"d_8e16ca04a866d040_lstnet_modules_py":{"hash":"7e94a6e8dcb299b3f37808f6a5e9a49d","index":{"nums":[0,1,106,0,85,0,0,0],"html_filename":"d_8e16ca04a866d040_lstnet_modules_py.html","relative_filename":"src/sensai/torch/torch_models/lstnet/lstnet_modules.py"}},"d_d049e11bc7279f8f_mlp_models_py":{"hash":"5a53019c95fd12c0d1076733c8f6feb8","index":{"nums":[0,1,42,0,0,0,0,0],"html_filename":"d_d049e11bc7279f8f_mlp_models_py.html","relative_filename":"src/sensai/torch/torch_models/mlp/mlp_models.py"}},"d_d049e11bc7279f8f_mlp_modules_py":{"hash":"ff8fa423a6257d54119c3e489202f894","index":{"nums":[0,1,34,0,3,0,0,0],"html_filename":"d_d049e11bc7279f8f_mlp_modules_py.html","relative_filename":"src/sensai/torch/torch_models/mlp/mlp_modules.py"}},"d_337e94e8243e179c_residualffn_models_py":{"hash":"c02ebcbc45b18cb0d1efdb3439520503","index":{"nums":[0,1,27,0,0,0,0,0],"html_filename":"d_337e94e8243e179c_residualffn_models_py.html","relative_filename":"src/sensai/torch/torch_models/residualffn/residualffn_models.py"}},"d_337e94e8243e179c_residualffn_modules_py":{"hash":"2822234a5a5d6e53797dbe30a3470bb8","index":{"nums":[0,1,83,0,15,0,0,0],"html_filename":"d_337e94e8243e179c_residualffn_modules_py.html","relative_filename":"src/sensai/torch/torch_models/residualffn/residualffn_modules.py"}},"d_535e1cc7b06ed03f_torch_modules_py":{"hash":"d87fbcdf95f1d80b59b3bc526877ee9d","index":{"nums":[0,1,6,0,0,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_modules_py.html","relative_filename":"src/sensai/torch/torch_modules.py"}},"d_535e1cc7b06ed03f_torch_opt_py":{"hash":"76637fc7fed8875a8a4a6b41e216e8ac","index":{"nums":[0,1,568,0,114,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torch_opt_py.html","relative_filename":"src/sensai/torch/torch_opt.py"}},"d_535e1cc7b06ed03f_torchtext_py":{"hash":"50666147dcc6611e16d1d9238d30c9b8","index":{"nums":[0,1,51,0,51,0,0,0],"html_filename":"d_535e1cc7b06ed03f_torchtext_py.html","relative_filename":"src/sensai/torch/torchtext.py"}},"d_968cc2eb7979e5c9___init___py":{"hash":"e6066900ef9e271efd149ed3648e67c5","index":{"nums":[0,1,1,0,0,0,0,0],"html_filename":"d_968cc2eb7979e5c9___init___py.html","relative_filename":"src/sensai/tracking/__init__.py"}},"d_968cc2eb7979e5c9_azure_tracking_py":{"hash":"c5699bdd7ac6a1deaa5f35da5b16701c","index":{"nums":[0,1,29,0,29,0,0,0],"html_filename":"d_968cc2eb7979e5c9_azure_tracking_py.html","relative_filename":"src/sensai/tracking/azure_tracking.py"}},"d_968cc2eb7979e5c9_clearml_tracking_py":{"hash":"85005c730151cd51bfb352f32ed16f18","index":{"nums":[0,1,36,0,36,0,0,0],"html_filename":"d_968cc2eb7979e5c9_clearml_tracking_py.html","relative_filename":"src/sensai/tracking/clearml_tracking.py"}},"d_968cc2eb7979e5c9_mlflow_tracking_py":{"hash":"08da7c372331207cfb33078235d4a330","index":{"nums":[0,1,57,0,57,0,0,0],"html_filename":"d_968cc2eb7979e5c9_mlflow_tracking_py.html","relative_filename":"src/sensai/tracking/mlflow_tracking.py"}},"d_968cc2eb7979e5c9_tracking_base_py":{"hash":"80521a41f5dfe58157146c5ca0ed515b","index":{"nums":[0,1,106,0,38,0,0,0],"html_filename":"d_968cc2eb7979e5c9_tracking_base_py.html","relative_filename":"src/sensai/tracking/tracking_base.py"}},"d_3ccb7b6033502eb6___init___py":{"hash":"5825e443191eb73caf035f8b032dede8","index":{"nums":[0,1,11,0,0,0,0,0],"html_filename":"d_3ccb7b6033502eb6___init___py.html","relative_filename":"src/sensai/util/__init__.py"}},"d_3ccb7b6033502eb6_aggregation_py":{"hash":"a1d97ecc698a6bf09cbbe95e8a0381db","index":{"nums":[0,1,47,0,27,0,0,0],"html_filename":"d_3ccb7b6033502eb6_aggregation_py.html","relative_filename":"src/sensai/util/aggregation.py"}},"d_3ccb7b6033502eb6_cache_py":{"hash":"292eb283bad77a661fd9b5080b307e71","index":{"nums":[0,1,434,0,322,0,0,0],"html_filename":"d_3ccb7b6033502eb6_cache_py.html","relative_filename":"src/sensai/util/cache.py"}},"d_3ccb7b6033502eb6_cache_azure_py":{"hash":"570b27180932ca88851dc7309b4a6ce6","index":{"nums":[0,1,388,0,388,0,0,0],"html_filename":"d_3ccb7b6033502eb6_cache_azure_py.html","relative_filename":"src/sensai/util/cache_azure.py"}},"d_3ccb7b6033502eb6_cache_mysql_py":{"hash":"a5cc2df1cd10df022da547a0f4474690","index":{"nums":[0,1,70,0,53,0,0,0],"html_filename":"d_3ccb7b6033502eb6_cache_mysql_py.html","relative_filename":"src/sensai/util/cache_mysql.py"}},"d_3ccb7b6033502eb6_datastruct_py":{"hash":"bf2327abb6eed2b4045d8583171be683","index":{"nums":[0,1,214,0,45,0,0,0],"html_filename":"d_3ccb7b6033502eb6_datastruct_py.html","relative_filename":"src/sensai/util/datastruct.py"}},"d_3ccb7b6033502eb6_deprecation_py":{"hash":"92ed5e591d4c88ec41354a9958978571","index":{"nums":[0,1,15,0,2,0,0,0],"html_filename":"d_3ccb7b6033502eb6_deprecation_py.html","relative_filename":"src/sensai/util/deprecation.py"}},"d_3ccb7b6033502eb6_dtype_py":{"hash":"60447f9fb590036805d6412acdc9f799","index":{"nums":[0,1,20,0,7,0,0,0],"html_filename":"d_3ccb7b6033502eb6_dtype_py.html","relative_filename":"src/sensai/util/dtype.py"}},"d_3ccb7b6033502eb6_hash_py":{"hash":"9dc97e9780e375b5206be273c3aeffa4","index":{"nums":[0,1,15,0,10,0,0,0],"html_filename":"d_3ccb7b6033502eb6_hash_py.html","relative_filename":"src/sensai/util/hash.py"}},"d_3ccb7b6033502eb6_helper_py":{"hash":"019585dde0e219d7a9c3cd2187676d09","index":{"nums":[0,1,28,0,5,0,0,0],"html_filename":"d_3ccb7b6033502eb6_helper_py.html","relative_filename":"src/sensai/util/helper.py"}},"d_3ccb7b6033502eb6_io_py":{"hash":"2aba041cb5a9e70749024ee6028b874f","index":{"nums":[0,1,120,0,84,0,0,0],"html_filename":"d_3ccb7b6033502eb6_io_py.html","relative_filename":"src/sensai/util/io.py"}},"d_3ccb7b6033502eb6_jscode_py":{"hash":"b54aeca0a4a255286e4ec960a053e326","index":{"nums":[0,1,95,0,95,0,0,0],"html_filename":"d_3ccb7b6033502eb6_jscode_py.html","relative_filename":"src/sensai/util/jscode.py"}},"d_3ccb7b6033502eb6_logging_py":{"hash":"f4b685f7db1b27a309acc4f28653f32a","index":{"nums":[0,1,154,0,93,0,0,0],"html_filename":"d_3ccb7b6033502eb6_logging_py.html","relative_filename":"src/sensai/util/logging.py"}},"d_3ccb7b6033502eb6_math_py":{"hash":"2c847fa20aaff8ef9c42d5f75f9c0fc8","index":{"nums":[0,1,25,0,25,0,0,0],"html_filename":"d_3ccb7b6033502eb6_math_py.html","relative_filename":"src/sensai/util/math.py"}},"d_3ccb7b6033502eb6_multiprocessing_py":{"hash":"ff3b46d45275f9ef1a5400ffd3384de2","index":{"nums":[0,1,36,0,20,0,0,0],"html_filename":"d_3ccb7b6033502eb6_multiprocessing_py.html","relative_filename":"src/sensai/util/multiprocessing.py"}},"d_3ccb7b6033502eb6_pandas_py":{"hash":"3821d1e522f9bc6b0f3efabaebaf755f","index":{"nums":[0,1,49,0,21,0,0,0],"html_filename":"d_3ccb7b6033502eb6_pandas_py.html","relative_filename":"src/sensai/util/pandas.py"}},"d_3ccb7b6033502eb6_pickle_py":{"hash":"f1ba770739ef1ba0968d226d2d1b239e","index":{"nums":[0,1,141,0,94,0,0,0],"html_filename":"d_3ccb7b6033502eb6_pickle_py.html","relative_filename":"src/sensai/util/pickle.py"}},"d_3ccb7b6033502eb6_plot_py":{"hash":"ac6b9228cebcb1d7f762c27963cfe999","index":{"nums":[0,1,189,0,145,0,0,0],"html_filename":"d_3ccb7b6033502eb6_plot_py.html","relative_filename":"src/sensai/util/plot.py"}},"d_3ccb7b6033502eb6_profiling_py":{"hash":"702757669eee11b1eba000179a86b1c5","index":{"nums":[0,1,32,0,23,0,0,0],"html_filename":"d_3ccb7b6033502eb6_profiling_py.html","relative_filename":"src/sensai/util/profiling.py"}},"d_3ccb7b6033502eb6_sequences_py":{"hash":"b00cd2426f8f2e6482af7c627a89390a","index":{"nums":[0,1,92,0,32,0,0,0],"html_filename":"d_3ccb7b6033502eb6_sequences_py.html","relative_filename":"src/sensai/util/sequences.py"}},"d_3ccb7b6033502eb6_string_py":{"hash":"fcc85ec2f14d2b30e89bcb9d87cca4b2","index":{"nums":[0,1,215,0,86,0,0,0],"html_filename":"d_3ccb7b6033502eb6_string_py.html","relative_filename":"src/sensai/util/string.py"}},"d_3ccb7b6033502eb6_test_py":{"hash":"6cc882f369fbc8392da76e9c41278f8e","index":{"nums":[0,1,28,0,28,0,0,0],"html_filename":"d_3ccb7b6033502eb6_test_py.html","relative_filename":"src/sensai/util/test.py"}},"d_3ccb7b6033502eb6_time_py":{"hash":"a836d509a3da93561c506b77a0e4c085","index":{"nums":[0,1,30,0,30,0,0,0],"html_filename":"d_3ccb7b6033502eb6_time_py.html","relative_filename":"src/sensai/util/time.py"}},"d_3ccb7b6033502eb6_typing_py":{"hash":"1052441f05519e193ffac73a7b2e6675","index":{"nums":[0,1,3,0,0,0,0,0],"html_filename":"d_3ccb7b6033502eb6_typing_py.html","relative_filename":"src/sensai/util/typing.py"}},"d_3ccb7b6033502eb6_version_py":{"hash":"7b40d4848ae51caeee1d28aa222ff46a","index":{"nums":[0,1,11,0,8,0,0,0],"html_filename":"d_3ccb7b6033502eb6_version_py.html","relative_filename":"src/sensai/util/version.py"}},"d_c26d41993906f874_vector_model_py":{"hash":"4890494a5cf0076f8c858f4b8e01de01","index":{"nums":[0,1,366,0,85,0,0,0],"html_filename":"d_c26d41993906f874_vector_model_py.html","relative_filename":"src/sensai/vector_model.py"}},"d_c26d41993906f874_vectoriser_py":{"hash":"cd382e3b35c1109e6dc44b2fcb9ddbc8","index":{"nums":[0,1,202,0,202,0,0,0],"html_filename":"d_c26d41993906f874_vectoriser_py.html","relative_filename":"src/sensai/vectoriser.py"}},"d_c26d41993906f874_xgboost_py":{"hash":"55a533f1dceff678e4b91807b14bb4d4","index":{"nums":[0,1,27,0,27,0,0,0],"html_filename":"d_c26d41993906f874_xgboost_py.html","relative_filename":"src/sensai/xgboost.py"}}}}
\ No newline at end of file
diff --git a/docs/_sources/intro.ipynb.txt b/docs/_sources/intro.ipynb.txt
index f2fd0acb..eee8c2cf 100644
--- a/docs/_sources/intro.ipynb.txt
+++ b/docs/_sources/intro.ipynb.txt
@@ -13,10 +13,10 @@
    "metadata": {
     "collapsed": false,
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:29.202323Z",
-     "iopub.status.busy": "2024-03-02T11:32:29.202040Z",
-     "iopub.status.idle": "2024-03-02T11:32:29.302641Z",
-     "shell.execute_reply": "2024-03-02T11:32:29.301838Z"
+     "iopub.execute_input": "2024-03-18T19:58:47.591757Z",
+     "iopub.status.busy": "2024-03-18T19:58:47.591217Z",
+     "iopub.status.idle": "2024-03-18T19:58:47.755497Z",
+     "shell.execute_reply": "2024-03-18T19:58:47.754564Z"
     }
    },
    "outputs": [],
@@ -30,10 +30,10 @@
    "execution_count": 2,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:29.305761Z",
-     "iopub.status.busy": "2024-03-02T11:32:29.305197Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.569512Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.568731Z"
+     "iopub.execute_input": "2024-03-18T19:58:47.759064Z",
+     "iopub.status.busy": "2024-03-18T19:58:47.758749Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.155632Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.154677Z"
     }
    },
    "outputs": [],
@@ -61,10 +61,10 @@
    "execution_count": 3,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.574117Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.573415Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.591659Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.590860Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.160372Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.159563Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.179386Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.178559Z"
     }
    },
    "outputs": [],
@@ -105,10 +105,10 @@
    "execution_count": 4,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.596005Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.595546Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.632778Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.632040Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.184621Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.183980Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.223197Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.222301Z"
     }
    },
    "outputs": [],
@@ -133,10 +133,10 @@
    "execution_count": 5,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.636376Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.635927Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.665605Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.664746Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.227121Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.226648Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.259900Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.258788Z"
     }
    },
    "outputs": [
@@ -170,84 +170,84 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>102</th>\n",
-       "      <td>7.1</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>5.9</td>\n",
-       "      <td>2.1</td>\n",
-       "      <td>virginica</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>52</th>\n",
-       "      <td>6.9</td>\n",
-       "      <td>3.1</td>\n",
-       "      <td>4.9</td>\n",
+       "      <th>78</th>\n",
+       "      <td>6.0</td>\n",
+       "      <td>2.9</td>\n",
+       "      <td>4.5</td>\n",
        "      <td>1.5</td>\n",
        "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>4.8</td>\n",
+       "      <th>31</th>\n",
+       "      <td>5.4</td>\n",
        "      <td>3.4</td>\n",
-       "      <td>1.6</td>\n",
-       "      <td>0.2</td>\n",
+       "      <td>1.5</td>\n",
+       "      <td>0.4</td>\n",
        "      <td>setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>30</th>\n",
-       "      <td>4.8</td>\n",
-       "      <td>3.1</td>\n",
-       "      <td>1.6</td>\n",
-       "      <td>0.2</td>\n",
+       "      <th>17</th>\n",
+       "      <td>5.1</td>\n",
+       "      <td>3.5</td>\n",
+       "      <td>1.4</td>\n",
+       "      <td>0.3</td>\n",
        "      <td>setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>142</th>\n",
-       "      <td>5.8</td>\n",
-       "      <td>2.7</td>\n",
-       "      <td>5.1</td>\n",
-       "      <td>1.9</td>\n",
+       "      <th>107</th>\n",
+       "      <td>7.3</td>\n",
+       "      <td>2.9</td>\n",
+       "      <td>6.3</td>\n",
+       "      <td>1.8</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>4.4</td>\n",
+       "      <th>77</th>\n",
+       "      <td>6.7</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>1.7</td>\n",
+       "      <td>versicolor</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>97</th>\n",
+       "      <td>6.2</td>\n",
        "      <td>2.9</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>0.2</td>\n",
-       "      <td>setosa</td>\n",
+       "      <td>4.3</td>\n",
+       "      <td>1.3</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>138</th>\n",
-       "      <td>6.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>4.8</td>\n",
+       "      <th>108</th>\n",
+       "      <td>6.7</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>5.8</td>\n",
        "      <td>1.8</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>17</th>\n",
-       "      <td>5.1</td>\n",
-       "      <td>3.5</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>0.3</td>\n",
-       "      <td>setosa</td>\n",
+       "      <th>54</th>\n",
+       "      <td>6.5</td>\n",
+       "      <td>2.8</td>\n",
+       "      <td>4.6</td>\n",
+       "      <td>1.5</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>24</th>\n",
-       "      <td>4.8</td>\n",
-       "      <td>3.4</td>\n",
-       "      <td>1.9</td>\n",
-       "      <td>0.2</td>\n",
-       "      <td>setosa</td>\n",
+       "      <th>69</th>\n",
+       "      <td>5.6</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>3.9</td>\n",
+       "      <td>1.1</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>137</th>\n",
-       "      <td>6.4</td>\n",
-       "      <td>3.1</td>\n",
-       "      <td>5.5</td>\n",
-       "      <td>1.8</td>\n",
-       "      <td>virginica</td>\n",
+       "      <th>32</th>\n",
+       "      <td>5.2</td>\n",
+       "      <td>4.1</td>\n",
+       "      <td>1.5</td>\n",
+       "      <td>0.1</td>\n",
+       "      <td>setosa</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -255,28 +255,28 @@
       ],
       "text/plain": [
        "     sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
-       "102                7.1               3.0                5.9               2.1   \n",
-       "52                 6.9               3.1                4.9               1.5   \n",
-       "11                 4.8               3.4                1.6               0.2   \n",
-       "30                 4.8               3.1                1.6               0.2   \n",
-       "142                5.8               2.7                5.1               1.9   \n",
-       "8                  4.4               2.9                1.4               0.2   \n",
-       "138                6.0               3.0                4.8               1.8   \n",
+       "78                 6.0               2.9                4.5               1.5   \n",
+       "31                 5.4               3.4                1.5               0.4   \n",
        "17                 5.1               3.5                1.4               0.3   \n",
-       "24                 4.8               3.4                1.9               0.2   \n",
-       "137                6.4               3.1                5.5               1.8   \n",
+       "107                7.3               2.9                6.3               1.8   \n",
+       "77                 6.7               3.0                5.0               1.7   \n",
+       "97                 6.2               2.9                4.3               1.3   \n",
+       "108                6.7               2.5                5.8               1.8   \n",
+       "54                 6.5               2.8                4.6               1.5   \n",
+       "69                 5.6               2.5                3.9               1.1   \n",
+       "32                 5.2               4.1                1.5               0.1   \n",
        "\n",
        "          class  \n",
-       "102   virginica  \n",
-       "52   versicolor  \n",
-       "11       setosa  \n",
-       "30       setosa  \n",
-       "142   virginica  \n",
-       "8        setosa  \n",
-       "138   virginica  \n",
+       "78   versicolor  \n",
+       "31       setosa  \n",
        "17       setosa  \n",
-       "24       setosa  \n",
-       "137   virginica  "
+       "107   virginica  \n",
+       "77   versicolor  \n",
+       "97   versicolor  \n",
+       "108   virginica  \n",
+       "54   versicolor  \n",
+       "69   versicolor  \n",
+       "32       setosa  "
       ]
      },
      "execution_count": 5,
@@ -303,10 +303,10 @@
    "execution_count": 6,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.699948Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.699443Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.717824Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.716999Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.292750Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.292192Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.311120Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.310273Z"
     }
    },
    "outputs": [],
@@ -333,10 +333,10 @@
    "execution_count": 7,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.721297Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.720863Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.740272Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.739582Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.314792Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.314547Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.342288Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.341518Z"
     }
    },
    "outputs": [],
@@ -361,10 +361,10 @@
    "execution_count": 8,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.743659Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.743214Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.762191Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.761411Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.346071Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.345574Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.363865Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.363056Z"
     }
    },
    "outputs": [],
@@ -387,10 +387,10 @@
    "execution_count": 9,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.765575Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.765127Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.894169Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.893382Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.367675Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.367132Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.480199Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.479514Z"
     }
    },
    "outputs": [
@@ -398,27 +398,27 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:30,788 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:49,384 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:30,791 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:49,385 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:30,887 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:49,474 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "SkLearnRandomForestVectorClassificationModel[id=140271289194000, featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]"
+       "SkLearnRandomForestVectorClassificationModel[id=140682438463888, featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]"
       ]
      },
      "execution_count": 9,
@@ -443,10 +443,10 @@
    "execution_count": 10,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.897583Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.897140Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.922714Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.921913Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.483740Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.483181Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.520928Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.520106Z"
     }
    },
    "outputs": [
@@ -530,10 +530,10 @@
    "execution_count": 11,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.926220Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.925951Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.955821Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.954947Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.524709Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.524166Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.553367Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.552504Z"
     }
    },
    "outputs": [
@@ -564,27 +564,27 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>149</th>\n",
+       "      <th>102</th>\n",
        "      <td>virginica</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>71</th>\n",
+       "      <th>92</th>\n",
        "      <td>versicolor</td>\n",
        "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>103</th>\n",
+       "      <th>140</th>\n",
        "      <td>virginica</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>48</th>\n",
-       "      <td>setosa</td>\n",
-       "      <td>setosa</td>\n",
+       "      <th>57</th>\n",
+       "      <td>versicolor</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>129</th>\n",
+       "      <th>107</th>\n",
        "      <td>virginica</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
@@ -594,24 +594,24 @@
        "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>setosa</td>\n",
-       "      <td>setosa</td>\n",
+       "      <th>87</th>\n",
+       "      <td>versicolor</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>144</th>\n",
+       "      <th>130</th>\n",
        "      <td>virginica</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>58</th>\n",
-       "      <td>versicolor</td>\n",
-       "      <td>versicolor</td>\n",
+       "      <th>103</th>\n",
+       "      <td>virginica</td>\n",
+       "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>57</th>\n",
-       "      <td>versicolor</td>\n",
-       "      <td>versicolor</td>\n",
+       "      <th>1</th>\n",
+       "      <td>setosa</td>\n",
+       "      <td>setosa</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -619,16 +619,16 @@
       ],
       "text/plain": [
        "    predictedClass       class\n",
-       "149      virginica   virginica\n",
-       "71      versicolor  versicolor\n",
-       "103      virginica   virginica\n",
-       "48          setosa      setosa\n",
-       "129      virginica   virginica\n",
+       "102      virginica   virginica\n",
+       "92      versicolor  versicolor\n",
+       "140      virginica   virginica\n",
+       "57      versicolor  versicolor\n",
+       "107      virginica   virginica\n",
        "99      versicolor  versicolor\n",
-       "1           setosa      setosa\n",
-       "144      virginica   virginica\n",
-       "58      versicolor  versicolor\n",
-       "57      versicolor  versicolor"
+       "87      versicolor  versicolor\n",
+       "130      virginica   virginica\n",
+       "103      virginica   virginica\n",
+       "1           setosa      setosa"
       ]
      },
      "execution_count": 11,
@@ -663,10 +663,10 @@
    "execution_count": 12,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.959982Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.959756Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.981880Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.981147Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.556908Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.556663Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.576879Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.576067Z"
     }
    },
    "outputs": [],
@@ -687,10 +687,10 @@
    "execution_count": 13,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.985989Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.985538Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.102927Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.102180Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.581252Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.580832Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.702437Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.701496Z"
     }
    },
    "outputs": [
@@ -698,21 +698,21 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,000 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:49,598 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,002 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:49,599 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,089 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:49,690 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     }
    ],
@@ -734,17 +734,17 @@
    "execution_count": 14,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.106667Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.106198Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.126111Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.125368Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.706077Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.705789Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.732649Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.731763Z"
     }
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "ClassificationEvalStats[id=140271317975952, accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, N=30]"
+       "ClassificationEvalStats[id=140682469084368, accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, N=30]"
       ]
      },
      "execution_count": 14,
@@ -769,10 +769,10 @@
    "execution_count": 15,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.129853Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.129624Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.156934Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.156214Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.736791Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.736290Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.757957Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.757103Z"
     }
    },
    "outputs": [
@@ -807,10 +807,10 @@
    "execution_count": 16,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.160457Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.160058Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.178499Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.177767Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.761838Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.761268Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.788807Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.788063Z"
     }
    },
    "outputs": [
@@ -841,10 +841,10 @@
    "execution_count": 17,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.181390Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.181179Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.478429Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.477578Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.792785Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.792112Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.094266Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.093305Z"
     }
    },
    "outputs": [
@@ -879,10 +879,10 @@
    "execution_count": 18,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.482734Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.482098Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.501169Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.500404Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.097667Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.097181Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.116236Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.115495Z"
     }
    },
    "outputs": [],
@@ -917,10 +917,10 @@
    "execution_count": 19,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.504258Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.504047Z",
-     "iopub.status.idle": "2024-03-02T11:32:32.128637Z",
-     "shell.execute_reply": "2024-03-02T11:32:32.127861Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.120228Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.119608Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.818388Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.817478Z"
     }
    },
    "outputs": [
@@ -928,41 +928,41 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,521 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7f93741cc710>\n"
+      "INFO  2024-03-18 19:58:50,136 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ff32e9eba50>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,521 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:50,137 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,523 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:50,139 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,609 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:50,227 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,622 sensai.evaluation.eval_util:gather_results - Evaluation results for class: ClassificationEvalStats[accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, top2Accuracy=1.0, N=30]\n"
+      "INFO  2024-03-18 19:58:50,238 sensai.evaluation.eval_util:gather_results - Evaluation results for class: ClassificationEvalStats[accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, top2Accuracy=1.0, N=30]\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "<sensai.evaluation.evaluator.VectorClassificationModelEvaluationData at 0x7f93745d58d0>"
+       "<sensai.evaluation.evaluator.VectorClassificationModelEvaluationData at 0x7ff32e5ae650>"
       ]
      },
      "execution_count": 19,
@@ -1013,10 +1013,10 @@
    "execution_count": 20,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:32.132454Z",
-     "iopub.status.busy": "2024-03-02T11:32:32.131890Z",
-     "iopub.status.idle": "2024-03-02T11:32:32.156103Z",
-     "shell.execute_reply": "2024-03-02T11:32:32.155464Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.822602Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.822092Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.841847Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.841028Z"
     }
    },
    "outputs": [
@@ -1051,10 +1051,10 @@
    "execution_count": 21,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:32.159782Z",
-     "iopub.status.busy": "2024-03-02T11:32:32.159120Z",
-     "iopub.status.idle": "2024-03-02T11:32:32.175801Z",
-     "shell.execute_reply": "2024-03-02T11:32:32.175151Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.845149Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.844913Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.868806Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.867951Z"
     }
    },
    "outputs": [],
@@ -1088,10 +1088,10 @@
    "execution_count": 22,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:32.179977Z",
-     "iopub.status.busy": "2024-03-02T11:32:32.179739Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.549477Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.548747Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.874032Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.873530Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.286907Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.286155Z"
     }
    },
    "outputs": [
@@ -1099,357 +1099,357 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,202 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
+      "INFO  2024-03-18 19:58:50,898 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,202 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:50,898 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,204 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:50,900 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,291 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:50,990 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,304 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]\n"
+      "INFO  2024-03-18 19:58:51,000 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,305 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
+      "INFO  2024-03-18 19:58:51,001 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,305 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,002 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,306 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,003 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,394 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,092 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,403 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]\n"
+      "INFO  2024-03-18 19:58:51,104 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,404 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
+      "INFO  2024-03-18 19:58:51,105 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,404 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,106 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,406 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,107 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,493 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,196 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,502 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]\n"
+      "INFO  2024-03-18 19:58:51,208 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,502 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
+      "INFO  2024-03-18 19:58:51,208 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,503 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,210 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,505 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,211 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,592 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,300 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,602 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]\n"
+      "INFO  2024-03-18 19:58:51,309 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,602 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
+      "INFO  2024-03-18 19:58:51,310 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,603 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,311 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,604 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,312 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,692 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,401 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,703 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]\n"
+      "INFO  2024-03-18 19:58:51,413 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,704 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
+      "INFO  2024-03-18 19:58:51,414 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,705 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,414 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,706 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,416 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,794 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,505 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,804 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]\n"
+      "INFO  2024-03-18 19:58:51,517 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,805 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
+      "INFO  2024-03-18 19:58:51,518 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,805 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,518 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,808 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,520 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,895 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,609 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,906 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]\n"
+      "INFO  2024-03-18 19:58:51,621 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,907 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
+      "INFO  2024-03-18 19:58:51,622 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,907 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,623 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,909 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,624 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,006 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,727 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,015 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]\n"
+      "INFO  2024-03-18 19:58:51,742 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,016 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
+      "INFO  2024-03-18 19:58:51,743 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,018 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,743 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,019 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,744 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,127 sensai.vector_model:fit - Fitting completed in 0.11 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,843 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,139 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]\n"
+      "INFO  2024-03-18 19:58:51,854 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,140 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
+      "INFO  2024-03-18 19:58:51,855 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,140 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,856 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,141 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,858 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,238 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,956 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,262 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]\n"
+      "INFO  2024-03-18 19:58:51,972 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,278 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
+      "INFO  2024-03-18 19:58:51,990 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
       "       mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]\n",
       "class            0.96       0.053333                0.963571               0.050077                     0.89878                    0.10223\n"
      ]
@@ -1457,7 +1457,7 @@
     {
      "data": {
       "text/plain": [
-       "<sensai.evaluation.crossval.VectorClassificationModelCrossValidationData at 0x7f9373dc8bd0>"
+       "<sensai.evaluation.crossval.VectorClassificationModelCrossValidationData at 0x7ff32e4864d0>"
       ]
      },
      "execution_count": 22,
@@ -1502,10 +1502,10 @@
    "execution_count": 23,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.553247Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.553019Z",
-     "iopub.status.idle": "2024-03-02T11:32:35.334416Z",
-     "shell.execute_reply": "2024-03-02T11:32:35.333663Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.290259Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.290038Z",
+     "iopub.status.idle": "2024-03-18T19:58:54.169288Z",
+     "shell.execute_reply": "2024-03-18T19:58:54.168436Z"
     }
    },
    "outputs": [
@@ -1513,364 +1513,364 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,572 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named 'RandomForest' ...\n"
+      "INFO  2024-03-18 19:58:52,308 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named 'RandomForest' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,648 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
+      "INFO  2024-03-18 19:58:52,318 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,648 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,392 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,650 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,394 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,737 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,483 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,749 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]\n"
+      "INFO  2024-03-18 19:58:52,493 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,750 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
+      "INFO  2024-03-18 19:58:52,494 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,750 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,494 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,752 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,496 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,840 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,584 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,851 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]\n"
+      "INFO  2024-03-18 19:58:52,594 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,851 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
+      "INFO  2024-03-18 19:58:52,595 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,852 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,596 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,854 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,597 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,954 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,699 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,963 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]\n"
+      "INFO  2024-03-18 19:58:52,713 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,964 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
+      "INFO  2024-03-18 19:58:52,714 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,965 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,715 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,966 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,717 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,069 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,814 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,080 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]\n"
+      "INFO  2024-03-18 19:58:52,827 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,082 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
+      "INFO  2024-03-18 19:58:52,828 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,083 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,829 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,085 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,831 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,177 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,934 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,187 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]\n"
+      "INFO  2024-03-18 19:58:52,949 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,188 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
+      "INFO  2024-03-18 19:58:52,949 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,188 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,950 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,190 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,952 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,280 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,075 sensai.vector_model:fit - Fitting completed in 0.12 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,292 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]\n"
+      "INFO  2024-03-18 19:58:53,085 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,292 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
+      "INFO  2024-03-18 19:58:53,086 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,293 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,087 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,295 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:53,088 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,382 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,177 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,394 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]\n"
+      "INFO  2024-03-18 19:58:53,189 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,396 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
+      "INFO  2024-03-18 19:58:53,189 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,396 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,190 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,397 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:53,192 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,489 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,280 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,499 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]\n"
+      "INFO  2024-03-18 19:58:53,290 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,499 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
+      "INFO  2024-03-18 19:58:53,291 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,500 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,292 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,501 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:53,293 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,590 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,383 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,600 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]\n"
+      "INFO  2024-03-18 19:58:53,395 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,601 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
+      "INFO  2024-03-18 19:58:53,397 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,601 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,397 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,603 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:53,399 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,690 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,487 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,700 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]\n"
+      "INFO  2024-03-18 19:58:53,498 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,710 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
+      "INFO  2024-03-18 19:58:53,510 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
       "       mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]\n",
       "class            0.96       0.053333                0.963571               0.050077                     0.89878                    0.10223\n"
      ]
@@ -1879,364 +1879,364 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,797 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named 'DecisionTree' ...\n"
+      "INFO  2024-03-18 19:58:53,586 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named 'DecisionTree' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,798 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
+      "INFO  2024-03-18 19:58:53,587 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,799 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,588 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,801 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,590 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,804 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,593 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,811 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
+      "INFO  2024-03-18 19:58:53,601 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,811 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
+      "INFO  2024-03-18 19:58:53,602 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,812 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,603 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,813 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,604 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,816 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,607 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,824 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
+      "INFO  2024-03-18 19:58:53,615 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,824 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
+      "INFO  2024-03-18 19:58:53,616 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,825 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,617 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,826 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,618 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,828 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,621 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,835 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
+      "INFO  2024-03-18 19:58:53,628 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,836 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
+      "INFO  2024-03-18 19:58:53,629 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,837 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,630 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,838 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,632 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,840 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,635 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,847 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]\n"
+      "INFO  2024-03-18 19:58:53,642 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,847 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
+      "INFO  2024-03-18 19:58:53,646 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,848 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,647 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,849 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,649 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,853 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,652 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,859 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9548416039104165, N=15]\n"
+      "INFO  2024-03-18 19:58:53,660 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9548416039104165, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,860 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
+      "INFO  2024-03-18 19:58:53,661 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,861 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,662 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,862 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,663 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,864 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,667 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,871 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.39810717055349726, N=15]\n"
+      "INFO  2024-03-18 19:58:53,675 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.39810717055349726, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,872 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
+      "INFO  2024-03-18 19:58:53,676 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,872 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,677 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,873 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,678 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,875 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,682 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,882 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.39810717055349726, N=15]\n"
+      "INFO  2024-03-18 19:58:53,689 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.39810717055349726, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,883 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
+      "INFO  2024-03-18 19:58:53,689 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,883 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,690 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,884 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,692 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,887 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,695 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,893 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9444444444444445, geoMeanTrueClassProb=0.9548416039104165, N=15]\n"
+      "INFO  2024-03-18 19:58:53,701 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9444444444444445, geoMeanTrueClassProb=0.9548416039104165, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,894 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
+      "INFO  2024-03-18 19:58:53,702 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,895 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,703 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,896 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,705 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,898 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,708 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,905 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]\n"
+      "INFO  2024-03-18 19:58:53,714 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,905 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
+      "INFO  2024-03-18 19:58:53,715 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,906 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,716 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,907 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,717 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,909 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,720 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,916 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.6309573444801932, N=15]\n"
+      "INFO  2024-03-18 19:58:53,727 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.6309573444801932, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,926 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
+      "INFO  2024-03-18 19:58:53,740 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
       "       mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]\n",
       "class            0.94       0.046667                0.944683                0.04441                    0.756512                   0.238693\n"
      ]
@@ -2245,7 +2245,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:35,001 sensai.evaluation.eval_util:compare_models - Model comparison results, aggregated across folds:\n",
+      "INFO  2024-03-18 19:58:53,833 sensai.evaluation.eval_util:compare_models - Model comparison results, aggregated across folds:\n",
       "              mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]\n",
       "model_name                                                                                                                                       \n",
       "RandomForest            0.96       0.053333                0.963571               0.050077                    0.898780                   0.102230\n",
@@ -2292,10 +2292,10 @@
    "execution_count": 24,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:35.338287Z",
-     "iopub.status.busy": "2024-03-02T11:32:35.337714Z",
-     "iopub.status.idle": "2024-03-02T11:32:35.533235Z",
-     "shell.execute_reply": "2024-03-02T11:32:35.532492Z"
+     "iopub.execute_input": "2024-03-18T19:58:54.173182Z",
+     "iopub.status.busy": "2024-03-18T19:58:54.172636Z",
+     "iopub.status.idle": "2024-03-18T19:58:54.382964Z",
+     "shell.execute_reply": "2024-03-18T19:58:54.382079Z"
     }
    },
    "outputs": [
@@ -2410,10 +2410,10 @@
    "execution_count": 25,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:35.537194Z",
-     "iopub.status.busy": "2024-03-02T11:32:35.536586Z",
-     "iopub.status.idle": "2024-03-02T11:32:35.555897Z",
-     "shell.execute_reply": "2024-03-02T11:32:35.555207Z"
+     "iopub.execute_input": "2024-03-18T19:58:54.386785Z",
+     "iopub.status.busy": "2024-03-18T19:58:54.386162Z",
+     "iopub.status.idle": "2024-03-18T19:58:54.408153Z",
+     "shell.execute_reply": "2024-03-18T19:58:54.407270Z"
     }
    },
    "outputs": [
@@ -2442,10 +2442,10 @@
    "execution_count": 26,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:35.558794Z",
-     "iopub.status.busy": "2024-03-02T11:32:35.558369Z",
-     "iopub.status.idle": "2024-03-02T11:32:35.582171Z",
-     "shell.execute_reply": "2024-03-02T11:32:35.581547Z"
+     "iopub.execute_input": "2024-03-18T19:58:54.412258Z",
+     "iopub.status.busy": "2024-03-18T19:58:54.411546Z",
+     "iopub.status.idle": "2024-03-18T19:58:54.432172Z",
+     "shell.execute_reply": "2024-03-18T19:58:54.431317Z"
     }
    },
    "outputs": [
diff --git a/docs/_sources/neural_networks.ipynb.txt b/docs/_sources/neural_networks.ipynb.txt
index 7e7603fe..1ca033ce 100644
--- a/docs/_sources/neural_networks.ipynb.txt
+++ b/docs/_sources/neural_networks.ipynb.txt
@@ -18,10 +18,10 @@
    "execution_count": 1,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:29.202455Z",
-     "iopub.status.busy": "2024-03-02T11:32:29.202180Z",
-     "iopub.status.idle": "2024-03-02T11:32:29.302609Z",
-     "shell.execute_reply": "2024-03-02T11:32:29.301772Z"
+     "iopub.execute_input": "2024-03-18T19:58:47.591719Z",
+     "iopub.status.busy": "2024-03-18T19:58:47.591290Z",
+     "iopub.status.idle": "2024-03-18T19:58:47.755497Z",
+     "shell.execute_reply": "2024-03-18T19:58:47.754564Z"
     }
    },
    "outputs": [],
@@ -35,10 +35,10 @@
    "execution_count": 2,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:29.305744Z",
-     "iopub.status.busy": "2024-03-02T11:32:29.305318Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.601176Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.600456Z"
+     "iopub.execute_input": "2024-03-18T19:58:47.759221Z",
+     "iopub.status.busy": "2024-03-18T19:58:47.758724Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.116589Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.115706Z"
     }
    },
    "outputs": [],
@@ -71,10 +71,10 @@
    "execution_count": 3,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.604770Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.604289Z",
-     "iopub.status.idle": "2024-03-02T11:32:32.981472Z",
-     "shell.execute_reply": "2024-03-02T11:32:32.980746Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.120322Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.119982Z",
+     "iopub.status.idle": "2024-03-18T19:58:51.702376Z",
+     "shell.execute_reply": "2024-03-18T19:58:51.701359Z"
     }
    },
    "outputs": [],
@@ -94,10 +94,10 @@
    "execution_count": 4,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:32.985269Z",
-     "iopub.status.busy": "2024-03-02T11:32:32.984654Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.024673Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.023845Z"
+     "iopub.execute_input": "2024-03-18T19:58:51.706408Z",
+     "iopub.status.busy": "2024-03-18T19:58:51.705770Z",
+     "iopub.status.idle": "2024-03-18T19:58:51.753970Z",
+     "shell.execute_reply": "2024-03-18T19:58:51.753016Z"
     }
    },
    "outputs": [
@@ -310,10 +310,10 @@
    "execution_count": 5,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.057096Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.056490Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.129598Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.128640Z"
+     "iopub.execute_input": "2024-03-18T19:58:51.790144Z",
+     "iopub.status.busy": "2024-03-18T19:58:51.789387Z",
+     "iopub.status.idle": "2024-03-18T19:58:51.860708Z",
+     "shell.execute_reply": "2024-03-18T19:58:51.859814Z"
     }
    },
    "outputs": [],
@@ -333,10 +333,10 @@
    "execution_count": 6,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.134426Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.133799Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.527595Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.526817Z"
+     "iopub.execute_input": "2024-03-18T19:58:51.864775Z",
+     "iopub.status.busy": "2024-03-18T19:58:51.864561Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.295615Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.294806Z"
     }
    },
    "outputs": [
@@ -382,10 +382,10 @@
    "execution_count": 7,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.531056Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.530584Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.554854Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.554059Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.299537Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.299037Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.318771Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.317981Z"
     }
    },
    "outputs": [],
@@ -406,10 +406,10 @@
    "execution_count": 8,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.558381Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.558176Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.851513Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.850665Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.322757Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.322147Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.629621Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.628872Z"
     }
    },
    "outputs": [],
@@ -439,10 +439,10 @@
    "execution_count": 9,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.855930Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.855208Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.874334Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.873633Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.634411Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.633959Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.653307Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.652530Z"
     }
    },
    "outputs": [],
@@ -465,10 +465,10 @@
    "execution_count": 10,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.877572Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.877003Z",
-     "iopub.status.idle": "2024-03-02T11:32:59.578534Z",
-     "shell.execute_reply": "2024-03-02T11:32:59.577861Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.657100Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.656454Z",
+     "iopub.status.idle": "2024-03-18T19:59:18.464651Z",
+     "shell.execute_reply": "2024-03-18T19:59:18.463925Z"
     }
    },
    "outputs": [
@@ -476,322 +476,322 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,899 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named 'RandomForest' ...\n"
+      "INFO  2024-03-18 19:58:52,678 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named 'RandomForest' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:34,125 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7effac5a8e50> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
+      "DEBUG 2024-03-18 19:58:52,937 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7ddfded82c90> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,126 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, modelConstructor=RandomForestClassifier(random_state=42, min_samples_leaf=1, n_estimators=10)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effac5a8790>\n"
+      "INFO  2024-03-18 19:58:52,939 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, modelConstructor=RandomForestClassifier(random_state=42, min_samples_leaf=1, n_estimators=10)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfded82b50>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,127 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,940 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:34,151 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
+      "DEBUG 2024-03-18 19:58:52,985 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,152 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,986 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:36,908 sensai.vector_model:fit - Fitting completed in 2.78 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:55,860 sensai.vector_model:fit - Fitting completed in 2.92 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:36,983 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]\n"
+      "INFO  2024-03-18 19:58:55,944 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,306 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named 'MLP' ...\n"
+      "INFO  2024-03-18 19:58:56,221 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named 'MLP' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,307 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7eff4cd88880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=None, inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effac5a8790>\n"
+      "INFO  2024-03-18 19:58:56,223 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7ddf80988880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=None, inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfded82b50>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,308 sensai.vector_model:fit - Fitting MultiLayerPerceptronVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:56,224 sensai.vector_model:fit - Fitting MultiLayerPerceptronVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:37,316 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
+      "DEBUG 2024-03-18 19:58:56,230 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,482 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7eff4cd88880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7effab8fccb0>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]] with cuda=False\n"
+      "INFO  2024-03-18 19:58:56,368 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7ddf80988880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7ddfde8fa170>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]] with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,484 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
+      "INFO  2024-03-18 19:58:56,370 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,657 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
+      "INFO  2024-03-18 19:58:56,547 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,658 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
+      "INFO  2024-03-18 19:58:56,549 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,660 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7eff4cd88880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7effab8fccb0>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None]\n"
+      "INFO  2024-03-18 19:58:56,551 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7ddf80988880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7ddfde8fa170>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,660 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 40480\n"
+      "INFO  2024-03-18 19:58:56,551 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 40480\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,661 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]]\n"
+      "INFO  2024-03-18 19:58:56,552 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,669 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
+      "INFO  2024-03-18 19:58:56,561 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,670 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
+      "INFO  2024-03-18 19:58:56,562 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:38,818 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  1.15s | train loss 1.4059 | validation NLL 0.7300 | best NLL 0.730044 from this epoch\n"
+      "INFO  2024-03-18 19:58:57,735 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  1.17s | train loss 1.4059 | validation NLL 0.7300 | best NLL 0.730044 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:39,950 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  1.12s | train loss 0.5021 | validation NLL 0.3806 | best NLL 0.380582 from this epoch\n"
+      "INFO  2024-03-18 19:58:58,930 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  1.19s | train loss 0.5021 | validation NLL 0.3806 | best NLL 0.380582 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:41,111 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  1.15s | train loss 0.3138 | validation NLL 0.2847 | best NLL 0.284687 from this epoch\n"
+      "INFO  2024-03-18 19:58:59,967 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  1.03s | train loss 0.3138 | validation NLL 0.2847 | best NLL 0.284687 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:42,270 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  1.15s | train loss 0.2409 | validation NLL 0.2393 | best NLL 0.239259 from this epoch\n"
+      "INFO  2024-03-18 19:59:01,003 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  1.03s | train loss 0.2409 | validation NLL 0.2393 | best NLL 0.239259 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:43,440 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  1.16s | train loss 0.1981 | validation NLL 0.2081 | best NLL 0.208118 from this epoch\n"
+      "INFO  2024-03-18 19:59:02,039 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  1.03s | train loss 0.1981 | validation NLL 0.2081 | best NLL 0.208118 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:44,441 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  0.99s | train loss 0.1676 | validation NLL 0.1872 | best NLL 0.187202 from this epoch\n"
+      "INFO  2024-03-18 19:59:03,075 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  1.03s | train loss 0.1676 | validation NLL 0.1872 | best NLL 0.187202 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:45,450 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  1.00s | train loss 0.1450 | validation NLL 0.1697 | best NLL 0.169709 from this epoch\n"
+      "INFO  2024-03-18 19:59:04,110 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  1.03s | train loss 0.1450 | validation NLL 0.1697 | best NLL 0.169709 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:46,585 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  1.13s | train loss 0.1274 | validation NLL 0.1593 | best NLL 0.159322 from this epoch\n"
+      "INFO  2024-03-18 19:59:05,149 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  1.03s | train loss 0.1274 | validation NLL 0.1593 | best NLL 0.159322 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:47,590 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  1.00s | train loss 0.1131 | validation NLL 0.1509 | best NLL 0.150902 from this epoch\n"
+      "INFO  2024-03-18 19:59:06,184 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  1.03s | train loss 0.1131 | validation NLL 0.1509 | best NLL 0.150902 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:48,604 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  10/1000 completed in  1.01s | train loss 0.1013 | validation NLL 0.1440 | best NLL 0.144011 from this epoch\n"
+      "INFO  2024-03-18 19:59:07,215 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  10/1000 completed in  1.02s | train loss 0.1013 | validation NLL 0.1440 | best NLL 0.144011 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:49,727 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  11/1000 completed in  1.11s | train loss 0.0906 | validation NLL 0.1381 | best NLL 0.138148 from this epoch\n"
+      "INFO  2024-03-18 19:59:08,244 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  11/1000 completed in  1.02s | train loss 0.0906 | validation NLL 0.1381 | best NLL 0.138148 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:50,848 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  12/1000 completed in  1.11s | train loss 0.0816 | validation NLL 0.1334 | best NLL 0.133373 from this epoch\n"
+      "INFO  2024-03-18 19:59:09,276 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  12/1000 completed in  1.02s | train loss 0.0816 | validation NLL 0.1334 | best NLL 0.133373 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:51,970 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  13/1000 completed in  1.12s | train loss 0.0739 | validation NLL 0.1315 | best NLL 0.131459 from this epoch\n"
+      "INFO  2024-03-18 19:59:10,451 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  13/1000 completed in  1.17s | train loss 0.0739 | validation NLL 0.1315 | best NLL 0.131459 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:53,009 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  14/1000 completed in  1.03s | train loss 0.0667 | validation NLL 0.1281 | best NLL 0.128110 from this epoch\n"
+      "INFO  2024-03-18 19:59:11,623 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  14/1000 completed in  1.16s | train loss 0.0667 | validation NLL 0.1281 | best NLL 0.128110 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:54,140 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  15/1000 completed in  1.12s | train loss 0.0610 | validation NLL 0.1271 | best NLL 0.127124 from this epoch\n"
+      "INFO  2024-03-18 19:59:12,817 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  15/1000 completed in  1.19s | train loss 0.0610 | validation NLL 0.1271 | best NLL 0.127124 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:55,255 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  16/1000 completed in  1.11s | train loss 0.0553 | validation NLL 0.1222 | best NLL 0.122218 from this epoch\n"
+      "INFO  2024-03-18 19:59:13,995 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  16/1000 completed in  1.17s | train loss 0.0553 | validation NLL 0.1222 | best NLL 0.122218 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:56,375 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  17/1000 completed in  1.11s | train loss 0.0504 | validation NLL 0.1258 | best NLL 0.122218 from epoch 16\n"
+      "INFO  2024-03-18 19:59:15,149 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  17/1000 completed in  1.15s | train loss 0.0504 | validation NLL 0.1258 | best NLL 0.122218 from epoch 16\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,485 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  18/1000 completed in  1.11s | train loss 0.0461 | validation NLL 0.1233 | best NLL 0.122218 from epoch 16\n"
+      "INFO  2024-03-18 19:59:16,309 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  18/1000 completed in  1.16s | train loss 0.0461 | validation NLL 0.1233 | best NLL 0.122218 from epoch 16\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,486 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 2 epochs without validation metric improvement\n"
+      "INFO  2024-03-18 19:59:16,310 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 2 epochs without validation metric improvement\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,487 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
+      "INFO  2024-03-18 19:59:16,311 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,487 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 16 with NLL 0.12221813999116421 on validation set\n"
+      "INFO  2024-03-18 19:59:16,311 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 16 with NLL 0.12221813999116421 on validation set\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,495 sensai.vector_model:fit - Fitting completed in 20.19 seconds: MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7eff4cd88880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7eff4cd88880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7effab8fccb0>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP]\n"
+      "INFO  2024-03-18 19:59:16,320 sensai.vector_model:fit - Fitting completed in 20.10 seconds: MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7ddf80988880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7ddf80988880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7ddfde8fa170>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:57,496 sensai.torch.torch_data:__init__ - Applying <sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7effae07b150> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 19:59:16,321 sensai.torch.torch_data:__init__ - Applying <sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7ddfdcd5c850> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,623 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]\n"
+      "INFO  2024-03-18 19:59:16,450 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,900 sensai.evaluation.eval_util:compare_models - Model comparison results:\n",
+      "INFO  2024-03-18 19:59:16,732 sensai.evaluation.eval_util:compare_models - Model comparison results:\n",
       "              accuracy  balancedAccuracy\n",
       "model_name                              \n",
       "RandomForest  0.946667          0.945917\n",
@@ -801,7 +801,7 @@
     {
      "data": {
       "text/plain": [
-       "<sensai.evaluation.eval_util.ModelComparisonData at 0x7effaa5af390>"
+       "<sensai.evaluation.eval_util.ModelComparisonData at 0x7ddfdbbdac10>"
       ]
      },
      "execution_count": 10,
@@ -883,10 +883,10 @@
    "execution_count": 11,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:59.582054Z",
-     "iopub.status.busy": "2024-03-02T11:32:59.581518Z",
-     "iopub.status.idle": "2024-03-02T11:32:59.604642Z",
-     "shell.execute_reply": "2024-03-02T11:32:59.604134Z"
+     "iopub.execute_input": "2024-03-18T19:59:18.467916Z",
+     "iopub.status.busy": "2024-03-18T19:59:18.467709Z",
+     "iopub.status.idle": "2024-03-18T19:59:18.490220Z",
+     "shell.execute_reply": "2024-03-18T19:59:18.489601Z"
     }
    },
    "outputs": [],
@@ -933,10 +933,10 @@
    "execution_count": 12,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:59.607499Z",
-     "iopub.status.busy": "2024-03-02T11:32:59.607073Z",
-     "iopub.status.idle": "2024-03-02T11:32:59.624847Z",
-     "shell.execute_reply": "2024-03-02T11:32:59.624334Z"
+     "iopub.execute_input": "2024-03-18T19:59:18.493489Z",
+     "iopub.status.busy": "2024-03-18T19:59:18.492990Z",
+     "iopub.status.idle": "2024-03-18T19:59:18.513108Z",
+     "shell.execute_reply": "2024-03-18T19:59:18.512354Z"
     }
    },
    "outputs": [],
@@ -961,10 +961,10 @@
    "execution_count": 13,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:59.627639Z",
-     "iopub.status.busy": "2024-03-02T11:32:59.627108Z",
-     "iopub.status.idle": "2024-03-02T11:32:59.649461Z",
-     "shell.execute_reply": "2024-03-02T11:32:59.648947Z"
+     "iopub.execute_input": "2024-03-18T19:59:18.516683Z",
+     "iopub.status.busy": "2024-03-18T19:59:18.516103Z",
+     "iopub.status.idle": "2024-03-18T19:59:18.539346Z",
+     "shell.execute_reply": "2024-03-18T19:59:18.538810Z"
     }
    },
    "outputs": [],
@@ -996,10 +996,10 @@
    "execution_count": 14,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:59.652180Z",
-     "iopub.status.busy": "2024-03-02T11:32:59.651796Z",
-     "iopub.status.idle": "2024-03-02T11:34:33.190349Z",
-     "shell.execute_reply": "2024-03-02T11:34:33.189673Z"
+     "iopub.execute_input": "2024-03-18T19:59:18.542079Z",
+     "iopub.status.busy": "2024-03-18T19:59:18.541845Z",
+     "iopub.status.idle": "2024-03-18T20:00:52.906075Z",
+     "shell.execute_reply": "2024-03-18T20:00:52.905360Z"
     }
    },
    "outputs": [
@@ -1007,203 +1007,203 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:59,879 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7effac5a8e50> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
+      "DEBUG 2024-03-18 19:59:18,801 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7ddfded82c90> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,880 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7effa8da9850>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effa91a2c50>\n"
+      "INFO  2024-03-18 19:59:18,802 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7ddfdbf90690>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdb7cc350>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,881 sensai.vector_model:fit - Fitting TorchVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:59:18,803 sensai.vector_model:fit - Fitting TorchVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:59,910 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
+      "DEBUG 2024-03-18 19:59:18,825 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,911 sensai.torch.torch_base:_fit_classifier - Fitting <__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10> ...\n"
+      "INFO  2024-03-18 19:59:18,826 sensai.torch.torch_base:_fit_classifier - Fitting <__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0> ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,970 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False\n"
+      "INFO  2024-03-18 19:59:18,886 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,971 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
+      "INFO  2024-03-18 19:59:18,887 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,405 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
+      "INFO  2024-03-18 19:59:21,321 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,407 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
+      "INFO  2024-03-18 19:59:21,322 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,408 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None]\n"
+      "INFO  2024-03-18 19:59:21,323 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,408 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862\n"
+      "INFO  2024-03-18 19:59:21,323 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,409 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]\n"
+      "INFO  2024-03-18 19:59:21,324 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,420 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
+      "INFO  2024-03-18 19:59:21,335 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,421 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
+      "INFO  2024-03-18 19:59:21,336 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:12,225 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.80s | train loss 0.8318 | validation NLL 0.1962 | best NLL 0.196246 from this epoch\n"
+      "INFO  2024-03-18 19:59:31,168 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.83s | train loss 0.8318 | validation NLL 0.1962 | best NLL 0.196246 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:21,992 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.76s | train loss 0.1365 | validation NLL 0.1341 | best NLL 0.134100 from this epoch\n"
+      "INFO  2024-03-18 19:59:41,005 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.83s | train loss 0.1365 | validation NLL 0.1341 | best NLL 0.134100 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:31,736 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.73s | train loss 0.0724 | validation NLL 0.1154 | best NLL 0.115383 from this epoch\n"
+      "INFO  2024-03-18 19:59:50,892 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.88s | train loss 0.0724 | validation NLL 0.1154 | best NLL 0.115383 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:41,472 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.72s | train loss 0.0524 | validation NLL 0.1286 | best NLL 0.115383 from epoch 3\n"
+      "INFO  2024-03-18 20:00:00,774 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.87s | train loss 0.0524 | validation NLL 0.1286 | best NLL 0.115383 from epoch 3\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:51,268 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.80s | train loss 0.0418 | validation NLL 0.1073 | best NLL 0.107293 from this epoch\n"
+      "INFO  2024-03-18 20:00:10,651 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.88s | train loss 0.0418 | validation NLL 0.1073 | best NLL 0.107293 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:01,017 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.74s | train loss 0.0345 | validation NLL 0.0818 | best NLL 0.081762 from this epoch\n"
+      "INFO  2024-03-18 20:00:20,471 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.81s | train loss 0.0345 | validation NLL 0.0818 | best NLL 0.081762 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:10,726 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.70s | train loss 0.0293 | validation NLL 0.0953 | best NLL 0.081762 from epoch 6\n"
+      "INFO  2024-03-18 20:00:30,288 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.81s | train loss 0.0293 | validation NLL 0.0953 | best NLL 0.081762 from epoch 6\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:20,455 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.73s | train loss 0.0245 | validation NLL 0.1157 | best NLL 0.081762 from epoch 6\n"
+      "INFO  2024-03-18 20:00:40,140 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.85s | train loss 0.0245 | validation NLL 0.1157 | best NLL 0.081762 from epoch 6\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,224 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  9.77s | train loss 0.0209 | validation NLL 0.0996 | best NLL 0.081762 from epoch 6\n"
+      "INFO  2024-03-18 20:00:49,883 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  9.74s | train loss 0.0209 | validation NLL 0.0996 | best NLL 0.081762 from epoch 6\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,225 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement\n"
+      "INFO  2024-03-18 20:00:49,885 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,225 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
+      "INFO  2024-03-18 20:00:49,885 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,226 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 6 with NLL 0.08176225980122884 on validation set\n"
+      "INFO  2024-03-18 20:00:49,886 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 6 with NLL 0.08176225980122884 on validation set\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,237 sensai.vector_model:fit - Fitting completed in 90.36 seconds: TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7effa8da9850>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN]\n"
+      "INFO  2024-03-18 20:00:49,897 sensai.vector_model:fit - Fitting completed in 91.09 seconds: TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7ddfdbf90690>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:34:30,238 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:00:49,897 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:32,035 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]\n"
+      "INFO  2024-03-18 20:00:51,654 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]\n"
      ]
     },
     {
@@ -1249,10 +1249,10 @@
    "execution_count": 15,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:34:33.193305Z",
-     "iopub.status.busy": "2024-03-02T11:34:33.193055Z",
-     "iopub.status.idle": "2024-03-02T11:34:33.219444Z",
-     "shell.execute_reply": "2024-03-02T11:34:33.218900Z"
+     "iopub.execute_input": "2024-03-18T20:00:52.908927Z",
+     "iopub.status.busy": "2024-03-18T20:00:52.908717Z",
+     "iopub.status.idle": "2024-03-18T20:00:52.933887Z",
+     "shell.execute_reply": "2024-03-18T20:00:52.933254Z"
     }
    },
    "outputs": [],
@@ -1320,10 +1320,10 @@
    "execution_count": 16,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:34:33.222420Z",
-     "iopub.status.busy": "2024-03-02T11:34:33.221880Z",
-     "iopub.status.idle": "2024-03-02T11:35:56.717610Z",
-     "shell.execute_reply": "2024-03-02T11:35:56.716883Z"
+     "iopub.execute_input": "2024-03-18T20:00:52.937077Z",
+     "iopub.status.busy": "2024-03-18T20:00:52.936661Z",
+     "iopub.status.idle": "2024-03-18T20:02:17.070894Z",
+     "shell.execute_reply": "2024-03-18T20:02:17.070115Z"
     }
    },
    "outputs": [
@@ -1331,196 +1331,196 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:34:33,459 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7effac5a8e50> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
+      "DEBUG 2024-03-18 20:00:53,167 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7ddfded82c90> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,460 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=139636510019152, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN'] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effa893c7d0>\n"
+      "INFO  2024-03-18 20:00:53,168 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=138400413109712, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN'] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdb765610>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,461 sensai.vector_model:fit - Fitting CnnModel instance\n"
+      "INFO  2024-03-18 20:00:53,168 sensai.vector_model:fit - Fitting CnnModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:34:33,484 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
+      "DEBUG 2024-03-18 20:00:53,191 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,485 sensai.torch.torch_base:_fit_classifier - Fitting <__main__.ImageReshapingInputTensoriser object at 0x7effa893c450> ...\n"
+      "INFO  2024-03-18 20:00:53,192 sensai.torch.torch_base:_fit_classifier - Fitting <__main__.ImageReshapingInputTensoriser object at 0x7de00026d150> ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,544 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False\n"
+      "INFO  2024-03-18 20:00:53,252 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,545 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
+      "INFO  2024-03-18 20:00:53,254 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,981 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
+      "INFO  2024-03-18 20:00:55,687 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,981 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
+      "INFO  2024-03-18 20:00:55,688 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,986 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None]\n"
+      "INFO  2024-03-18 20:00:55,694 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,987 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862\n"
+      "INFO  2024-03-18 20:00:55,695 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,988 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]\n"
+      "INFO  2024-03-18 20:00:55,695 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,997 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
+      "INFO  2024-03-18 20:00:55,706 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,998 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
+      "INFO  2024-03-18 20:00:55,706 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:45,805 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.81s | train loss 0.8259 | validation NLL 0.2525 | best NLL 0.252539 from this epoch\n"
+      "INFO  2024-03-18 20:01:05,468 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.76s | train loss 0.8259 | validation NLL 0.2525 | best NLL 0.252539 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:55,478 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.66s | train loss 0.1533 | validation NLL 0.1433 | best NLL 0.143283 from this epoch\n"
+      "INFO  2024-03-18 20:01:15,233 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.76s | train loss 0.1533 | validation NLL 0.1433 | best NLL 0.143283 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:05,184 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.70s | train loss 0.0881 | validation NLL 0.0999 | best NLL 0.099880 from this epoch\n"
+      "INFO  2024-03-18 20:01:25,017 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.77s | train loss 0.0881 | validation NLL 0.0999 | best NLL 0.099880 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:14,892 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.70s | train loss 0.0596 | validation NLL 0.1221 | best NLL 0.099880 from epoch 3\n"
+      "INFO  2024-03-18 20:01:34,843 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.81s | train loss 0.0596 | validation NLL 0.1221 | best NLL 0.099880 from epoch 3\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:24,593 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.70s | train loss 0.0452 | validation NLL 0.0962 | best NLL 0.096233 from this epoch\n"
+      "INFO  2024-03-18 20:01:44,656 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.81s | train loss 0.0452 | validation NLL 0.0962 | best NLL 0.096233 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:34,295 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.69s | train loss 0.0380 | validation NLL 0.0974 | best NLL 0.096233 from epoch 5\n"
+      "INFO  2024-03-18 20:01:54,476 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.81s | train loss 0.0380 | validation NLL 0.0974 | best NLL 0.096233 from epoch 5\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:44,062 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.77s | train loss 0.0294 | validation NLL 0.0986 | best NLL 0.096233 from epoch 5\n"
+      "INFO  2024-03-18 20:02:04,319 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.84s | train loss 0.0294 | validation NLL 0.0986 | best NLL 0.096233 from epoch 5\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,811 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.75s | train loss 0.0223 | validation NLL 0.1068 | best NLL 0.096233 from epoch 5\n"
+      "INFO  2024-03-18 20:02:14,113 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.79s | train loss 0.0223 | validation NLL 0.1068 | best NLL 0.096233 from epoch 5\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,811 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement\n"
+      "INFO  2024-03-18 20:02:14,114 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,812 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
+      "INFO  2024-03-18 20:02:14,115 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,812 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 5 with NLL 0.09623306624094645 on validation set\n"
+      "INFO  2024-03-18 20:02:14,115 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 5 with NLL 0.09623306624094645 on validation set\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,824 sensai.vector_model:fit - Fitting completed in 80.36 seconds: CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=139636510019152, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']\n"
+      "INFO  2024-03-18 20:02:14,128 sensai.vector_model:fit - Fitting completed in 80.96 seconds: CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=138400413109712, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:53,825 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7effa893c450> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:02:14,129 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7de00026d150> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:55,558 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]\n"
+      "INFO  2024-03-18 20:02:15,905 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]\n"
      ]
     },
     {
@@ -1565,10 +1565,10 @@
    "execution_count": 17,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:35:56.720902Z",
-     "iopub.status.busy": "2024-03-02T11:35:56.720419Z",
-     "iopub.status.idle": "2024-03-02T11:36:05.373404Z",
-     "shell.execute_reply": "2024-03-02T11:36:05.372689Z"
+     "iopub.execute_input": "2024-03-18T20:02:17.074519Z",
+     "iopub.status.busy": "2024-03-18T20:02:17.073896Z",
+     "iopub.status.idle": "2024-03-18T20:02:25.799276Z",
+     "shell.execute_reply": "2024-03-18T20:02:25.798551Z"
     }
    },
    "outputs": [
@@ -1576,119 +1576,119 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:56,737 sensai.evaluation.eval_util:compare_models - Evaluating model 1/4 named 'MLP' ...\n"
+      "INFO  2024-03-18 20:02:17,091 sensai.evaluation.eval_util:compare_models - Evaluating model 1/4 named 'MLP' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:56,952 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7effac5a8e50> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
+      "DEBUG 2024-03-18 20:02:17,314 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7ddfded82c90> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:56,953 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7eff4cd88880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7eff4cd88880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7effab8fccb0>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050>\n"
+      "INFO  2024-03-18 20:02:17,315 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7ddf80988880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7ddf80988880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7ddfde8fa170>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:56,954 sensai.torch.torch_data:__init__ - Applying <sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7effaa1f3f90> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:02:17,316 sensai.torch.torch_data:__init__ - Applying <sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7ddfdb773bd0> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:57,085 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]\n"
+      "INFO  2024-03-18 20:02:17,450 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:57,483 sensai.evaluation.eval_util:compare_models - Evaluating model 2/4 named 'CNN' ...\n"
+      "INFO  2024-03-18 20:02:17,828 sensai.evaluation.eval_util:compare_models - Evaluating model 2/4 named 'CNN' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:57,484 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7effa8da9850>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050>\n"
+      "INFO  2024-03-18 20:02:17,829 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7ddfdbf90690>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:57,485 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:02:17,830 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:59,266 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]\n"
+      "INFO  2024-03-18 20:02:19,580 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:59,524 sensai.evaluation.eval_util:compare_models - Evaluating model 3/4 named 'CNN'' ...\n"
+      "INFO  2024-03-18 20:02:19,842 sensai.evaluation.eval_util:compare_models - Evaluating model 3/4 named 'CNN'' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:59,526 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=139636510019152, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN'] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050>\n"
+      "INFO  2024-03-18 20:02:19,843 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=138400413109712, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN'] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:59,527 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7effa893c450> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:02:19,844 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7de00026d150> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,269 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]\n"
+      "INFO  2024-03-18 20:02:21,603 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,531 sensai.evaluation.eval_util:compare_models - Evaluating model 4/4 named 'RandomForest' ...\n"
+      "INFO  2024-03-18 20:02:21,931 sensai.evaluation.eval_util:compare_models - Evaluating model 4/4 named 'RandomForest' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,532 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050>\n"
+      "INFO  2024-03-18 20:02:21,932 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,610 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]\n"
+      "INFO  2024-03-18 20:02:22,014 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,937 sensai.evaluation.eval_util:compare_models - Model comparison results:\n",
+      "INFO  2024-03-18 20:02:22,287 sensai.evaluation.eval_util:compare_models - Model comparison results:\n",
       "              accuracy  balancedAccuracy\n",
       "model_name                              \n",
       "MLP           0.962250          0.961897\n",
@@ -1865,10 +1865,10 @@
    "execution_count": 18,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:36:05.376411Z",
-     "iopub.status.busy": "2024-03-02T11:36:05.375988Z",
-     "iopub.status.idle": "2024-03-02T11:36:06.158725Z",
-     "shell.execute_reply": "2024-03-02T11:36:06.158011Z"
+     "iopub.execute_input": "2024-03-18T20:02:25.802373Z",
+     "iopub.status.busy": "2024-03-18T20:02:25.801976Z",
+     "iopub.status.idle": "2024-03-18T20:02:26.598400Z",
+     "shell.execute_reply": "2024-03-18T20:02:26.597622Z"
     }
    },
    "outputs": [
diff --git a/docs/intro.html b/docs/intro.html
index 38e30406..e2164b43 100644
--- a/docs/intro.html
+++ b/docs/intro.html
@@ -205,84 +205,84 @@ <h2>Training and Evaluating Models<a class="headerlink" href="#Training-and-Eval
   </thead>
   <tbody>
     <tr>
-      <th>102</th>
-      <td>7.1</td>
-      <td>3.0</td>
-      <td>5.9</td>
-      <td>2.1</td>
-      <td>virginica</td>
-    </tr>
-    <tr>
-      <th>52</th>
-      <td>6.9</td>
-      <td>3.1</td>
-      <td>4.9</td>
+      <th>78</th>
+      <td>6.0</td>
+      <td>2.9</td>
+      <td>4.5</td>
       <td>1.5</td>
       <td>versicolor</td>
     </tr>
     <tr>
-      <th>11</th>
-      <td>4.8</td>
+      <th>31</th>
+      <td>5.4</td>
       <td>3.4</td>
-      <td>1.6</td>
-      <td>0.2</td>
+      <td>1.5</td>
+      <td>0.4</td>
       <td>setosa</td>
     </tr>
     <tr>
-      <th>30</th>
-      <td>4.8</td>
-      <td>3.1</td>
-      <td>1.6</td>
-      <td>0.2</td>
+      <th>17</th>
+      <td>5.1</td>
+      <td>3.5</td>
+      <td>1.4</td>
+      <td>0.3</td>
       <td>setosa</td>
     </tr>
     <tr>
-      <th>142</th>
-      <td>5.8</td>
-      <td>2.7</td>
-      <td>5.1</td>
-      <td>1.9</td>
+      <th>107</th>
+      <td>7.3</td>
+      <td>2.9</td>
+      <td>6.3</td>
+      <td>1.8</td>
       <td>virginica</td>
     </tr>
     <tr>
-      <th>8</th>
-      <td>4.4</td>
+      <th>77</th>
+      <td>6.7</td>
+      <td>3.0</td>
+      <td>5.0</td>
+      <td>1.7</td>
+      <td>versicolor</td>
+    </tr>
+    <tr>
+      <th>97</th>
+      <td>6.2</td>
       <td>2.9</td>
-      <td>1.4</td>
-      <td>0.2</td>
-      <td>setosa</td>
+      <td>4.3</td>
+      <td>1.3</td>
+      <td>versicolor</td>
     </tr>
     <tr>
-      <th>138</th>
-      <td>6.0</td>
-      <td>3.0</td>
-      <td>4.8</td>
+      <th>108</th>
+      <td>6.7</td>
+      <td>2.5</td>
+      <td>5.8</td>
       <td>1.8</td>
       <td>virginica</td>
     </tr>
     <tr>
-      <th>17</th>
-      <td>5.1</td>
-      <td>3.5</td>
-      <td>1.4</td>
-      <td>0.3</td>
-      <td>setosa</td>
+      <th>54</th>
+      <td>6.5</td>
+      <td>2.8</td>
+      <td>4.6</td>
+      <td>1.5</td>
+      <td>versicolor</td>
     </tr>
     <tr>
-      <th>24</th>
-      <td>4.8</td>
-      <td>3.4</td>
-      <td>1.9</td>
-      <td>0.2</td>
-      <td>setosa</td>
+      <th>69</th>
+      <td>5.6</td>
+      <td>2.5</td>
+      <td>3.9</td>
+      <td>1.1</td>
+      <td>versicolor</td>
     </tr>
     <tr>
-      <th>137</th>
-      <td>6.4</td>
-      <td>3.1</td>
-      <td>5.5</td>
-      <td>1.8</td>
-      <td>virginica</td>
+      <th>32</th>
+      <td>5.2</td>
+      <td>4.1</td>
+      <td>1.5</td>
+      <td>0.1</td>
+      <td>setosa</td>
     </tr>
   </tbody>
 </table>
@@ -338,9 +338,9 @@ <h3>Low-Level Training and Inference<a class="headerlink" href="#Low-Level-Train
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-INFO  2024-03-02 11:32:30,788 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:30,791 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:30,887 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:49,384 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:49,385 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:49,474 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
 </pre></div></div>
 </div>
 <div class="nboutput nblast docutils container">
@@ -349,7 +349,7 @@ <h3>Low-Level Training and Inference<a class="headerlink" href="#Low-Level-Train
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-SkLearnRandomForestVectorClassificationModel[id=140271289194000, featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+SkLearnRandomForestVectorClassificationModel[id=140682438463888, featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
 </pre></div></div>
 </div>
 <p>We can now apply the trained model and predict the outputs for the test set we reserved.</p>
@@ -451,27 +451,27 @@ <h3>Low-Level Training and Inference<a class="headerlink" href="#Low-Level-Train
   </thead>
   <tbody>
     <tr>
-      <th>149</th>
+      <th>102</th>
       <td>virginica</td>
       <td>virginica</td>
     </tr>
     <tr>
-      <th>71</th>
+      <th>92</th>
       <td>versicolor</td>
       <td>versicolor</td>
     </tr>
     <tr>
-      <th>103</th>
+      <th>140</th>
       <td>virginica</td>
       <td>virginica</td>
     </tr>
     <tr>
-      <th>48</th>
-      <td>setosa</td>
-      <td>setosa</td>
+      <th>57</th>
+      <td>versicolor</td>
+      <td>versicolor</td>
     </tr>
     <tr>
-      <th>129</th>
+      <th>107</th>
       <td>virginica</td>
       <td>virginica</td>
     </tr>
@@ -481,24 +481,24 @@ <h3>Low-Level Training and Inference<a class="headerlink" href="#Low-Level-Train
       <td>versicolor</td>
     </tr>
     <tr>
-      <th>1</th>
-      <td>setosa</td>
-      <td>setosa</td>
+      <th>87</th>
+      <td>versicolor</td>
+      <td>versicolor</td>
     </tr>
     <tr>
-      <th>144</th>
+      <th>130</th>
       <td>virginica</td>
       <td>virginica</td>
     </tr>
     <tr>
-      <th>58</th>
-      <td>versicolor</td>
-      <td>versicolor</td>
+      <th>103</th>
+      <td>virginica</td>
+      <td>virginica</td>
     </tr>
     <tr>
-      <th>57</th>
-      <td>versicolor</td>
-      <td>versicolor</td>
+      <th>1</th>
+      <td>setosa</td>
+      <td>setosa</td>
     </tr>
   </tbody>
 </table>
@@ -534,9 +534,9 @@ <h3>Using Evaluators<a class="headerlink" href="#Using-Evaluators" title="Permal
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-INFO  2024-03-02 11:32:31,000 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:31,002 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:31,089 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:49,598 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:49,599 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:49,690 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
 </pre></div></div>
 </div>
 <p>The evaluation data holds, in particular, an <strong>EvalStats</strong> object, which can provide data on the quality of the results. Depending on the type of problem, many metrics will already be computed by default.</p>
@@ -555,7 +555,7 @@ <h3>Using Evaluators<a class="headerlink" href="#Using-Evaluators" title="Permal
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-ClassificationEvalStats[id=140271317975952, accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, N=30]
+ClassificationEvalStats[id=140682469084368, accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, N=30]
 </pre></div></div>
 </div>
 <p>We can get the metrics in a dictionary as follows:</p>
@@ -649,11 +649,11 @@ <h4>Simple Evaluation<a class="headerlink" href="#Simple-Evaluation" title="Perm
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-INFO  2024-03-02 11:32:31,521 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7f93741cc710&gt;
-INFO  2024-03-02 11:32:31,521 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:31,523 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:31,609 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:31,622 sensai.evaluation.eval_util:gather_results - Evaluation results for class: ClassificationEvalStats[accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, top2Accuracy=1.0, N=30]
+INFO  2024-03-18 19:58:50,136 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ff32e9eba50&gt;
+INFO  2024-03-18 19:58:50,137 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:50,139 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:50,227 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:50,238 sensai.evaluation.eval_util:gather_results - Evaluation results for class: ClassificationEvalStats[accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, top2Accuracy=1.0, N=30]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -662,7 +662,7 @@ <h4>Simple Evaluation<a class="headerlink" href="#Simple-Evaluation" title="Perm
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-&lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluationData at 0x7f93745d58d0&gt;
+&lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluationData at 0x7ff32e5ae650&gt;
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -731,57 +731,57 @@ <h4>Cross-Validation<a class="headerlink" href="#Cross-Validation" title="Permal
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-INFO  2024-03-02 11:32:32,202 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...
-INFO  2024-03-02 11:32:32,202 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:32,204 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:32,291 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:32,304 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]
-INFO  2024-03-02 11:32:32,305 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...
-INFO  2024-03-02 11:32:32,305 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:32,306 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:32,394 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:32,403 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]
-INFO  2024-03-02 11:32:32,404 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...
-INFO  2024-03-02 11:32:32,404 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:32,406 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:32,493 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:32,502 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]
-INFO  2024-03-02 11:32:32,502 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...
-INFO  2024-03-02 11:32:32,503 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:32,505 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:32,592 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:32,602 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]
-INFO  2024-03-02 11:32:32,602 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...
-INFO  2024-03-02 11:32:32,603 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:32,604 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:32,692 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:32,703 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]
-INFO  2024-03-02 11:32:32,704 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...
-INFO  2024-03-02 11:32:32,705 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:32,706 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:32,794 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:32,804 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]
-INFO  2024-03-02 11:32:32,805 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...
-INFO  2024-03-02 11:32:32,805 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:32,808 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:32,895 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:32,906 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]
-INFO  2024-03-02 11:32:32,907 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...
-INFO  2024-03-02 11:32:32,907 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:32,909 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:33,006 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:33,015 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]
-INFO  2024-03-02 11:32:33,016 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...
-INFO  2024-03-02 11:32:33,018 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:33,019 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:33,127 sensai.vector_model:fit - Fitting completed in 0.11 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:33,139 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]
-INFO  2024-03-02 11:32:33,140 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...
-INFO  2024-03-02 11:32:33,140 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:33,141 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:33,238 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:33,262 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]
-INFO  2024-03-02 11:32:33,278 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:
+INFO  2024-03-18 19:58:50,898 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...
+INFO  2024-03-18 19:58:50,898 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:50,900 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:50,990 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,000 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]
+INFO  2024-03-18 19:58:51,001 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...
+INFO  2024-03-18 19:58:51,002 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:51,003 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:51,092 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,104 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]
+INFO  2024-03-18 19:58:51,105 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...
+INFO  2024-03-18 19:58:51,106 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:51,107 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:51,196 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,208 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]
+INFO  2024-03-18 19:58:51,208 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...
+INFO  2024-03-18 19:58:51,210 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:51,211 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:51,300 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,309 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]
+INFO  2024-03-18 19:58:51,310 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...
+INFO  2024-03-18 19:58:51,311 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:51,312 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:51,401 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,413 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]
+INFO  2024-03-18 19:58:51,414 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...
+INFO  2024-03-18 19:58:51,414 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:51,416 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:51,505 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,517 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]
+INFO  2024-03-18 19:58:51,518 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...
+INFO  2024-03-18 19:58:51,518 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:51,520 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:51,609 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,621 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]
+INFO  2024-03-18 19:58:51,622 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...
+INFO  2024-03-18 19:58:51,623 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:51,624 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:51,727 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,742 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]
+INFO  2024-03-18 19:58:51,743 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...
+INFO  2024-03-18 19:58:51,743 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:51,744 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:51,843 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,854 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]
+INFO  2024-03-18 19:58:51,855 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...
+INFO  2024-03-18 19:58:51,856 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:51,858 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:51,956 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:51,972 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]
+INFO  2024-03-18 19:58:51,990 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:
        mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]
 class            0.96       0.053333                0.963571               0.050077                     0.89878                    0.10223
 </pre></div></div>
@@ -792,7 +792,7 @@ <h4>Cross-Validation<a class="headerlink" href="#Cross-Validation" title="Permal
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-&lt;sensai.evaluation.crossval.VectorClassificationModelCrossValidationData at 0x7f9373dc8bd0&gt;
+&lt;sensai.evaluation.crossval.VectorClassificationModelCrossValidationData at 0x7ff32e4864d0&gt;
 </pre></div></div>
 </div>
 <div class="nboutput nblast docutils container">
@@ -824,115 +824,115 @@ <h4>Comparing Models<a class="headerlink" href="#Comparing-Models" title="Permal
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-INFO  2024-03-02 11:32:33,572 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named &#39;RandomForest&#39; ...
-INFO  2024-03-02 11:32:33,648 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...
-INFO  2024-03-02 11:32:33,648 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:33,650 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:33,737 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:33,749 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]
-INFO  2024-03-02 11:32:33,750 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...
-INFO  2024-03-02 11:32:33,750 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:33,752 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:33,840 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:33,851 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]
-INFO  2024-03-02 11:32:33,851 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...
-INFO  2024-03-02 11:32:33,852 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:33,854 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:33,954 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:33,963 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]
-INFO  2024-03-02 11:32:33,964 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...
-INFO  2024-03-02 11:32:33,965 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:33,966 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:34,069 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:34,080 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]
-INFO  2024-03-02 11:32:34,082 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...
-INFO  2024-03-02 11:32:34,083 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,085 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:34,177 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:34,187 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]
-INFO  2024-03-02 11:32:34,188 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...
-INFO  2024-03-02 11:32:34,188 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,190 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:34,280 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:34,292 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]
-INFO  2024-03-02 11:32:34,292 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...
-INFO  2024-03-02 11:32:34,293 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,295 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:34,382 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:34,394 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]
-INFO  2024-03-02 11:32:34,396 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...
-INFO  2024-03-02 11:32:34,396 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,397 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:34,489 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:34,499 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]
-INFO  2024-03-02 11:32:34,499 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...
-INFO  2024-03-02 11:32:34,500 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,501 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:34,590 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:34,600 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]
-INFO  2024-03-02 11:32:34,601 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...
-INFO  2024-03-02 11:32:34,601 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,603 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:34,690 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:34,700 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]
-INFO  2024-03-02 11:32:34,710 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:
+INFO  2024-03-18 19:58:52,308 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named &#39;RandomForest&#39; ...
+INFO  2024-03-18 19:58:52,318 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...
+INFO  2024-03-18 19:58:52,392 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:52,394 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:52,483 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:52,493 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]
+INFO  2024-03-18 19:58:52,494 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...
+INFO  2024-03-18 19:58:52,494 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:52,496 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:52,584 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:52,594 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]
+INFO  2024-03-18 19:58:52,595 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...
+INFO  2024-03-18 19:58:52,596 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:52,597 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:52,699 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:52,713 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]
+INFO  2024-03-18 19:58:52,714 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...
+INFO  2024-03-18 19:58:52,715 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:52,717 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:52,814 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:52,827 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]
+INFO  2024-03-18 19:58:52,828 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...
+INFO  2024-03-18 19:58:52,829 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:52,831 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:52,934 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:52,949 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]
+INFO  2024-03-18 19:58:52,949 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...
+INFO  2024-03-18 19:58:52,950 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:52,952 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:53,075 sensai.vector_model:fit - Fitting completed in 0.12 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:53,085 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]
+INFO  2024-03-18 19:58:53,086 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...
+INFO  2024-03-18 19:58:53,087 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,088 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:53,177 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:53,189 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]
+INFO  2024-03-18 19:58:53,189 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...
+INFO  2024-03-18 19:58:53,190 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,192 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:53,280 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:53,290 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]
+INFO  2024-03-18 19:58:53,291 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...
+INFO  2024-03-18 19:58:53,292 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,293 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:53,383 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:53,395 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]
+INFO  2024-03-18 19:58:53,397 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...
+INFO  2024-03-18 19:58:53,397 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,399 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:53,487 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:53,498 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]
+INFO  2024-03-18 19:58:53,510 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:
        mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]
 class            0.96       0.053333                0.963571               0.050077                     0.89878                    0.10223
-INFO  2024-03-02 11:32:34,797 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named &#39;DecisionTree&#39; ...
-INFO  2024-03-02 11:32:34,798 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...
-INFO  2024-03-02 11:32:34,799 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,801 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,804 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,811 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]
-INFO  2024-03-02 11:32:34,811 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...
-INFO  2024-03-02 11:32:34,812 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,813 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,816 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,824 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]
-INFO  2024-03-02 11:32:34,824 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...
-INFO  2024-03-02 11:32:34,825 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,826 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,828 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,835 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]
-INFO  2024-03-02 11:32:34,836 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...
-INFO  2024-03-02 11:32:34,837 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,838 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,840 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,847 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]
-INFO  2024-03-02 11:32:34,847 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...
-INFO  2024-03-02 11:32:34,848 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,849 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,853 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,859 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9548416039104165, N=15]
-INFO  2024-03-02 11:32:34,860 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...
-INFO  2024-03-02 11:32:34,861 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,862 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,864 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,871 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.39810717055349726, N=15]
-INFO  2024-03-02 11:32:34,872 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...
-INFO  2024-03-02 11:32:34,872 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,873 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,875 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,882 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.39810717055349726, N=15]
-INFO  2024-03-02 11:32:34,883 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...
-INFO  2024-03-02 11:32:34,883 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,884 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,887 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,893 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9444444444444445, geoMeanTrueClassProb=0.9548416039104165, N=15]
-INFO  2024-03-02 11:32:34,894 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...
-INFO  2024-03-02 11:32:34,895 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,896 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,898 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,905 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]
-INFO  2024-03-02 11:32:34,905 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...
-INFO  2024-03-02 11:32:34,906 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
-INFO  2024-03-02 11:32:34,907 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
-INFO  2024-03-02 11:32:34,909 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
-INFO  2024-03-02 11:32:34,916 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.6309573444801932, N=15]
-INFO  2024-03-02 11:32:34,926 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:
+INFO  2024-03-18 19:58:53,586 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named &#39;DecisionTree&#39; ...
+INFO  2024-03-18 19:58:53,587 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...
+INFO  2024-03-18 19:58:53,588 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,590 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,593 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,601 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]
+INFO  2024-03-18 19:58:53,602 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...
+INFO  2024-03-18 19:58:53,603 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,604 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,607 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,615 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]
+INFO  2024-03-18 19:58:53,616 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...
+INFO  2024-03-18 19:58:53,617 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,618 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,621 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,628 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]
+INFO  2024-03-18 19:58:53,629 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...
+INFO  2024-03-18 19:58:53,630 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,632 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,635 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,642 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]
+INFO  2024-03-18 19:58:53,646 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...
+INFO  2024-03-18 19:58:53,647 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,649 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,652 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,660 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9548416039104165, N=15]
+INFO  2024-03-18 19:58:53,661 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...
+INFO  2024-03-18 19:58:53,662 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,663 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,667 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,675 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.39810717055349726, N=15]
+INFO  2024-03-18 19:58:53,676 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...
+INFO  2024-03-18 19:58:53,677 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,678 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,682 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,689 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.39810717055349726, N=15]
+INFO  2024-03-18 19:58:53,689 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...
+INFO  2024-03-18 19:58:53,690 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,692 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,695 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,701 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9444444444444445, geoMeanTrueClassProb=0.9548416039104165, N=15]
+INFO  2024-03-18 19:58:53,702 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...
+INFO  2024-03-18 19:58:53,703 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,705 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,708 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,714 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]
+INFO  2024-03-18 19:58:53,715 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...
+INFO  2024-03-18 19:58:53,716 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance
+INFO  2024-03-18 19:58:53,717 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier
+INFO  2024-03-18 19:58:53,720 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort=&#39;deprecated&#39;, random_state=42, splitter=&#39;best&#39;)]
+INFO  2024-03-18 19:58:53,727 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.6309573444801932, N=15]
+INFO  2024-03-18 19:58:53,740 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:
        mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]
 class            0.94       0.046667                0.944683                0.04441                    0.756512                   0.238693
-INFO  2024-03-02 11:32:35,001 sensai.evaluation.eval_util:compare_models - Model comparison results, aggregated across folds:
+INFO  2024-03-18 19:58:53,833 sensai.evaluation.eval_util:compare_models - Model comparison results, aggregated across folds:
               mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]
 model_name
 RandomForest            0.96       0.053333                0.963571               0.050077                    0.898780                   0.102230
diff --git a/docs/intro.ipynb b/docs/intro.ipynb
index f2fd0acb..eee8c2cf 100644
--- a/docs/intro.ipynb
+++ b/docs/intro.ipynb
@@ -13,10 +13,10 @@
    "metadata": {
     "collapsed": false,
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:29.202323Z",
-     "iopub.status.busy": "2024-03-02T11:32:29.202040Z",
-     "iopub.status.idle": "2024-03-02T11:32:29.302641Z",
-     "shell.execute_reply": "2024-03-02T11:32:29.301838Z"
+     "iopub.execute_input": "2024-03-18T19:58:47.591757Z",
+     "iopub.status.busy": "2024-03-18T19:58:47.591217Z",
+     "iopub.status.idle": "2024-03-18T19:58:47.755497Z",
+     "shell.execute_reply": "2024-03-18T19:58:47.754564Z"
     }
    },
    "outputs": [],
@@ -30,10 +30,10 @@
    "execution_count": 2,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:29.305761Z",
-     "iopub.status.busy": "2024-03-02T11:32:29.305197Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.569512Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.568731Z"
+     "iopub.execute_input": "2024-03-18T19:58:47.759064Z",
+     "iopub.status.busy": "2024-03-18T19:58:47.758749Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.155632Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.154677Z"
     }
    },
    "outputs": [],
@@ -61,10 +61,10 @@
    "execution_count": 3,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.574117Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.573415Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.591659Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.590860Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.160372Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.159563Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.179386Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.178559Z"
     }
    },
    "outputs": [],
@@ -105,10 +105,10 @@
    "execution_count": 4,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.596005Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.595546Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.632778Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.632040Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.184621Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.183980Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.223197Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.222301Z"
     }
    },
    "outputs": [],
@@ -133,10 +133,10 @@
    "execution_count": 5,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.636376Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.635927Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.665605Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.664746Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.227121Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.226648Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.259900Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.258788Z"
     }
    },
    "outputs": [
@@ -170,84 +170,84 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>102</th>\n",
-       "      <td>7.1</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>5.9</td>\n",
-       "      <td>2.1</td>\n",
-       "      <td>virginica</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>52</th>\n",
-       "      <td>6.9</td>\n",
-       "      <td>3.1</td>\n",
-       "      <td>4.9</td>\n",
+       "      <th>78</th>\n",
+       "      <td>6.0</td>\n",
+       "      <td>2.9</td>\n",
+       "      <td>4.5</td>\n",
        "      <td>1.5</td>\n",
        "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>4.8</td>\n",
+       "      <th>31</th>\n",
+       "      <td>5.4</td>\n",
        "      <td>3.4</td>\n",
-       "      <td>1.6</td>\n",
-       "      <td>0.2</td>\n",
+       "      <td>1.5</td>\n",
+       "      <td>0.4</td>\n",
        "      <td>setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>30</th>\n",
-       "      <td>4.8</td>\n",
-       "      <td>3.1</td>\n",
-       "      <td>1.6</td>\n",
-       "      <td>0.2</td>\n",
+       "      <th>17</th>\n",
+       "      <td>5.1</td>\n",
+       "      <td>3.5</td>\n",
+       "      <td>1.4</td>\n",
+       "      <td>0.3</td>\n",
        "      <td>setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>142</th>\n",
-       "      <td>5.8</td>\n",
-       "      <td>2.7</td>\n",
-       "      <td>5.1</td>\n",
-       "      <td>1.9</td>\n",
+       "      <th>107</th>\n",
+       "      <td>7.3</td>\n",
+       "      <td>2.9</td>\n",
+       "      <td>6.3</td>\n",
+       "      <td>1.8</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>4.4</td>\n",
+       "      <th>77</th>\n",
+       "      <td>6.7</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>1.7</td>\n",
+       "      <td>versicolor</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>97</th>\n",
+       "      <td>6.2</td>\n",
        "      <td>2.9</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>0.2</td>\n",
-       "      <td>setosa</td>\n",
+       "      <td>4.3</td>\n",
+       "      <td>1.3</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>138</th>\n",
-       "      <td>6.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>4.8</td>\n",
+       "      <th>108</th>\n",
+       "      <td>6.7</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>5.8</td>\n",
        "      <td>1.8</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>17</th>\n",
-       "      <td>5.1</td>\n",
-       "      <td>3.5</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>0.3</td>\n",
-       "      <td>setosa</td>\n",
+       "      <th>54</th>\n",
+       "      <td>6.5</td>\n",
+       "      <td>2.8</td>\n",
+       "      <td>4.6</td>\n",
+       "      <td>1.5</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>24</th>\n",
-       "      <td>4.8</td>\n",
-       "      <td>3.4</td>\n",
-       "      <td>1.9</td>\n",
-       "      <td>0.2</td>\n",
-       "      <td>setosa</td>\n",
+       "      <th>69</th>\n",
+       "      <td>5.6</td>\n",
+       "      <td>2.5</td>\n",
+       "      <td>3.9</td>\n",
+       "      <td>1.1</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>137</th>\n",
-       "      <td>6.4</td>\n",
-       "      <td>3.1</td>\n",
-       "      <td>5.5</td>\n",
-       "      <td>1.8</td>\n",
-       "      <td>virginica</td>\n",
+       "      <th>32</th>\n",
+       "      <td>5.2</td>\n",
+       "      <td>4.1</td>\n",
+       "      <td>1.5</td>\n",
+       "      <td>0.1</td>\n",
+       "      <td>setosa</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -255,28 +255,28 @@
       ],
       "text/plain": [
        "     sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
-       "102                7.1               3.0                5.9               2.1   \n",
-       "52                 6.9               3.1                4.9               1.5   \n",
-       "11                 4.8               3.4                1.6               0.2   \n",
-       "30                 4.8               3.1                1.6               0.2   \n",
-       "142                5.8               2.7                5.1               1.9   \n",
-       "8                  4.4               2.9                1.4               0.2   \n",
-       "138                6.0               3.0                4.8               1.8   \n",
+       "78                 6.0               2.9                4.5               1.5   \n",
+       "31                 5.4               3.4                1.5               0.4   \n",
        "17                 5.1               3.5                1.4               0.3   \n",
-       "24                 4.8               3.4                1.9               0.2   \n",
-       "137                6.4               3.1                5.5               1.8   \n",
+       "107                7.3               2.9                6.3               1.8   \n",
+       "77                 6.7               3.0                5.0               1.7   \n",
+       "97                 6.2               2.9                4.3               1.3   \n",
+       "108                6.7               2.5                5.8               1.8   \n",
+       "54                 6.5               2.8                4.6               1.5   \n",
+       "69                 5.6               2.5                3.9               1.1   \n",
+       "32                 5.2               4.1                1.5               0.1   \n",
        "\n",
        "          class  \n",
-       "102   virginica  \n",
-       "52   versicolor  \n",
-       "11       setosa  \n",
-       "30       setosa  \n",
-       "142   virginica  \n",
-       "8        setosa  \n",
-       "138   virginica  \n",
+       "78   versicolor  \n",
+       "31       setosa  \n",
        "17       setosa  \n",
-       "24       setosa  \n",
-       "137   virginica  "
+       "107   virginica  \n",
+       "77   versicolor  \n",
+       "97   versicolor  \n",
+       "108   virginica  \n",
+       "54   versicolor  \n",
+       "69   versicolor  \n",
+       "32       setosa  "
       ]
      },
      "execution_count": 5,
@@ -303,10 +303,10 @@
    "execution_count": 6,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.699948Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.699443Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.717824Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.716999Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.292750Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.292192Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.311120Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.310273Z"
     }
    },
    "outputs": [],
@@ -333,10 +333,10 @@
    "execution_count": 7,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.721297Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.720863Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.740272Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.739582Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.314792Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.314547Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.342288Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.341518Z"
     }
    },
    "outputs": [],
@@ -361,10 +361,10 @@
    "execution_count": 8,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.743659Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.743214Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.762191Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.761411Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.346071Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.345574Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.363865Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.363056Z"
     }
    },
    "outputs": [],
@@ -387,10 +387,10 @@
    "execution_count": 9,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.765575Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.765127Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.894169Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.893382Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.367675Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.367132Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.480199Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.479514Z"
     }
    },
    "outputs": [
@@ -398,27 +398,27 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:30,788 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:49,384 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:30,791 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:49,385 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:30,887 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:49,474 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "SkLearnRandomForestVectorClassificationModel[id=140271289194000, featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]"
+       "SkLearnRandomForestVectorClassificationModel[id=140682438463888, featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]"
       ]
      },
      "execution_count": 9,
@@ -443,10 +443,10 @@
    "execution_count": 10,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.897583Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.897140Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.922714Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.921913Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.483740Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.483181Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.520928Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.520106Z"
     }
    },
    "outputs": [
@@ -530,10 +530,10 @@
    "execution_count": 11,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.926220Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.925951Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.955821Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.954947Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.524709Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.524166Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.553367Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.552504Z"
     }
    },
    "outputs": [
@@ -564,27 +564,27 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>149</th>\n",
+       "      <th>102</th>\n",
        "      <td>virginica</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>71</th>\n",
+       "      <th>92</th>\n",
        "      <td>versicolor</td>\n",
        "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>103</th>\n",
+       "      <th>140</th>\n",
        "      <td>virginica</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>48</th>\n",
-       "      <td>setosa</td>\n",
-       "      <td>setosa</td>\n",
+       "      <th>57</th>\n",
+       "      <td>versicolor</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>129</th>\n",
+       "      <th>107</th>\n",
        "      <td>virginica</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
@@ -594,24 +594,24 @@
        "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>setosa</td>\n",
-       "      <td>setosa</td>\n",
+       "      <th>87</th>\n",
+       "      <td>versicolor</td>\n",
+       "      <td>versicolor</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>144</th>\n",
+       "      <th>130</th>\n",
        "      <td>virginica</td>\n",
        "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>58</th>\n",
-       "      <td>versicolor</td>\n",
-       "      <td>versicolor</td>\n",
+       "      <th>103</th>\n",
+       "      <td>virginica</td>\n",
+       "      <td>virginica</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>57</th>\n",
-       "      <td>versicolor</td>\n",
-       "      <td>versicolor</td>\n",
+       "      <th>1</th>\n",
+       "      <td>setosa</td>\n",
+       "      <td>setosa</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -619,16 +619,16 @@
       ],
       "text/plain": [
        "    predictedClass       class\n",
-       "149      virginica   virginica\n",
-       "71      versicolor  versicolor\n",
-       "103      virginica   virginica\n",
-       "48          setosa      setosa\n",
-       "129      virginica   virginica\n",
+       "102      virginica   virginica\n",
+       "92      versicolor  versicolor\n",
+       "140      virginica   virginica\n",
+       "57      versicolor  versicolor\n",
+       "107      virginica   virginica\n",
        "99      versicolor  versicolor\n",
-       "1           setosa      setosa\n",
-       "144      virginica   virginica\n",
-       "58      versicolor  versicolor\n",
-       "57      versicolor  versicolor"
+       "87      versicolor  versicolor\n",
+       "130      virginica   virginica\n",
+       "103      virginica   virginica\n",
+       "1           setosa      setosa"
       ]
      },
      "execution_count": 11,
@@ -663,10 +663,10 @@
    "execution_count": 12,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.959982Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.959756Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.981880Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.981147Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.556908Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.556663Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.576879Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.576067Z"
     }
    },
    "outputs": [],
@@ -687,10 +687,10 @@
    "execution_count": 13,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.985989Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.985538Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.102927Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.102180Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.581252Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.580832Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.702437Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.701496Z"
     }
    },
    "outputs": [
@@ -698,21 +698,21 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,000 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:49,598 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,002 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:49,599 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,089 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:49,690 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     }
    ],
@@ -734,17 +734,17 @@
    "execution_count": 14,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.106667Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.106198Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.126111Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.125368Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.706077Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.705789Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.732649Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.731763Z"
     }
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "ClassificationEvalStats[id=140271317975952, accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, N=30]"
+       "ClassificationEvalStats[id=140682469084368, accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, N=30]"
       ]
      },
      "execution_count": 14,
@@ -769,10 +769,10 @@
    "execution_count": 15,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.129853Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.129624Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.156934Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.156214Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.736791Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.736290Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.757957Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.757103Z"
     }
    },
    "outputs": [
@@ -807,10 +807,10 @@
    "execution_count": 16,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.160457Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.160058Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.178499Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.177767Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.761838Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.761268Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.788807Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.788063Z"
     }
    },
    "outputs": [
@@ -841,10 +841,10 @@
    "execution_count": 17,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.181390Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.181179Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.478429Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.477578Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.792785Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.792112Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.094266Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.093305Z"
     }
    },
    "outputs": [
@@ -879,10 +879,10 @@
    "execution_count": 18,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.482734Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.482098Z",
-     "iopub.status.idle": "2024-03-02T11:32:31.501169Z",
-     "shell.execute_reply": "2024-03-02T11:32:31.500404Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.097667Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.097181Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.116236Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.115495Z"
     }
    },
    "outputs": [],
@@ -917,10 +917,10 @@
    "execution_count": 19,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:31.504258Z",
-     "iopub.status.busy": "2024-03-02T11:32:31.504047Z",
-     "iopub.status.idle": "2024-03-02T11:32:32.128637Z",
-     "shell.execute_reply": "2024-03-02T11:32:32.127861Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.120228Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.119608Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.818388Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.817478Z"
     }
    },
    "outputs": [
@@ -928,41 +928,41 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,521 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7f93741cc710>\n"
+      "INFO  2024-03-18 19:58:50,136 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ff32e9eba50>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,521 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:50,137 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,523 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:50,139 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,609 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:50,227 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:31,622 sensai.evaluation.eval_util:gather_results - Evaluation results for class: ClassificationEvalStats[accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, top2Accuracy=1.0, N=30]\n"
+      "INFO  2024-03-18 19:58:50,238 sensai.evaluation.eval_util:gather_results - Evaluation results for class: ClassificationEvalStats[accuracy=0.9666666666666667, balancedAccuracy=0.9722222222222222, geoMeanTrueClassProb=0.8890980234758366, top2Accuracy=1.0, N=30]\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "<sensai.evaluation.evaluator.VectorClassificationModelEvaluationData at 0x7f93745d58d0>"
+       "<sensai.evaluation.evaluator.VectorClassificationModelEvaluationData at 0x7ff32e5ae650>"
       ]
      },
      "execution_count": 19,
@@ -1013,10 +1013,10 @@
    "execution_count": 20,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:32.132454Z",
-     "iopub.status.busy": "2024-03-02T11:32:32.131890Z",
-     "iopub.status.idle": "2024-03-02T11:32:32.156103Z",
-     "shell.execute_reply": "2024-03-02T11:32:32.155464Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.822602Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.822092Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.841847Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.841028Z"
     }
    },
    "outputs": [
@@ -1051,10 +1051,10 @@
    "execution_count": 21,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:32.159782Z",
-     "iopub.status.busy": "2024-03-02T11:32:32.159120Z",
-     "iopub.status.idle": "2024-03-02T11:32:32.175801Z",
-     "shell.execute_reply": "2024-03-02T11:32:32.175151Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.845149Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.844913Z",
+     "iopub.status.idle": "2024-03-18T19:58:50.868806Z",
+     "shell.execute_reply": "2024-03-18T19:58:50.867951Z"
     }
    },
    "outputs": [],
@@ -1088,10 +1088,10 @@
    "execution_count": 22,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:32.179977Z",
-     "iopub.status.busy": "2024-03-02T11:32:32.179739Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.549477Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.548747Z"
+     "iopub.execute_input": "2024-03-18T19:58:50.874032Z",
+     "iopub.status.busy": "2024-03-18T19:58:50.873530Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.286907Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.286155Z"
     }
    },
    "outputs": [
@@ -1099,357 +1099,357 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,202 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
+      "INFO  2024-03-18 19:58:50,898 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,202 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:50,898 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,204 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:50,900 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,291 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:50,990 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,304 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]\n"
+      "INFO  2024-03-18 19:58:51,000 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,305 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
+      "INFO  2024-03-18 19:58:51,001 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,305 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,002 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,306 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,003 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,394 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,092 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,403 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]\n"
+      "INFO  2024-03-18 19:58:51,104 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,404 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
+      "INFO  2024-03-18 19:58:51,105 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,404 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,106 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,406 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,107 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,493 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,196 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,502 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]\n"
+      "INFO  2024-03-18 19:58:51,208 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,502 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
+      "INFO  2024-03-18 19:58:51,208 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,503 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,210 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,505 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,211 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,592 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,300 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,602 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]\n"
+      "INFO  2024-03-18 19:58:51,309 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,602 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
+      "INFO  2024-03-18 19:58:51,310 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,603 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,311 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,604 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,312 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,692 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,401 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,703 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]\n"
+      "INFO  2024-03-18 19:58:51,413 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,704 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
+      "INFO  2024-03-18 19:58:51,414 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,705 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,414 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,706 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,416 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,794 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,505 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,804 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]\n"
+      "INFO  2024-03-18 19:58:51,517 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,805 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
+      "INFO  2024-03-18 19:58:51,518 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,805 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,518 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,808 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,520 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,895 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,609 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,906 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]\n"
+      "INFO  2024-03-18 19:58:51,621 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,907 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
+      "INFO  2024-03-18 19:58:51,622 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,907 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,623 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:32,909 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,624 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,006 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,727 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,015 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]\n"
+      "INFO  2024-03-18 19:58:51,742 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,016 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
+      "INFO  2024-03-18 19:58:51,743 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,018 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,743 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,019 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,744 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,127 sensai.vector_model:fit - Fitting completed in 0.11 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,843 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,139 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]\n"
+      "INFO  2024-03-18 19:58:51,854 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,140 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
+      "INFO  2024-03-18 19:58:51,855 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,140 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:51,856 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,141 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:51,858 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,238 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:51,956 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,262 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]\n"
+      "INFO  2024-03-18 19:58:51,972 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,278 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
+      "INFO  2024-03-18 19:58:51,990 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
       "       mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]\n",
       "class            0.96       0.053333                0.963571               0.050077                     0.89878                    0.10223\n"
      ]
@@ -1457,7 +1457,7 @@
     {
      "data": {
       "text/plain": [
-       "<sensai.evaluation.crossval.VectorClassificationModelCrossValidationData at 0x7f9373dc8bd0>"
+       "<sensai.evaluation.crossval.VectorClassificationModelCrossValidationData at 0x7ff32e4864d0>"
       ]
      },
      "execution_count": 22,
@@ -1502,10 +1502,10 @@
    "execution_count": 23,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.553247Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.553019Z",
-     "iopub.status.idle": "2024-03-02T11:32:35.334416Z",
-     "shell.execute_reply": "2024-03-02T11:32:35.333663Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.290259Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.290038Z",
+     "iopub.status.idle": "2024-03-18T19:58:54.169288Z",
+     "shell.execute_reply": "2024-03-18T19:58:54.168436Z"
     }
    },
    "outputs": [
@@ -1513,364 +1513,364 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,572 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named 'RandomForest' ...\n"
+      "INFO  2024-03-18 19:58:52,308 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named 'RandomForest' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,648 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
+      "INFO  2024-03-18 19:58:52,318 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,648 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,392 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,650 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,394 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,737 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,483 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,749 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]\n"
+      "INFO  2024-03-18 19:58:52,493 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9553599022560102, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,750 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
+      "INFO  2024-03-18 19:58:52,494 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,750 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,494 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,752 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,496 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,840 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,584 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,851 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]\n"
+      "INFO  2024-03-18 19:58:52,594 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9734228107223192, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,851 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
+      "INFO  2024-03-18 19:58:52,595 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,852 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,596 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,854 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,597 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,954 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,699 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,963 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]\n"
+      "INFO  2024-03-18 19:58:52,713 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.976458969438705, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,964 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
+      "INFO  2024-03-18 19:58:52,714 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,965 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,715 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,966 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,717 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,069 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,814 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,080 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]\n"
+      "INFO  2024-03-18 19:58:52,827 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9411926691126593, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,082 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
+      "INFO  2024-03-18 19:58:52,828 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,083 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,829 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,085 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,831 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,177 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:52,934 sensai.vector_model:fit - Fitting completed in 0.10 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,187 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]\n"
+      "INFO  2024-03-18 19:58:52,949 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9298964965102043, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,188 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
+      "INFO  2024-03-18 19:58:52,949 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,188 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,950 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,190 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,952 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,280 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,075 sensai.vector_model:fit - Fitting completed in 0.12 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,292 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]\n"
+      "INFO  2024-03-18 19:58:53,085 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.6379522029160006, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,292 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
+      "INFO  2024-03-18 19:58:53,086 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,293 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,087 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,295 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:53,088 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,382 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,177 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,394 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]\n"
+      "INFO  2024-03-18 19:58:53,189 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.8099785263057822, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,396 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
+      "INFO  2024-03-18 19:58:53,189 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,396 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,190 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,397 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:53,192 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,489 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,280 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,499 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]\n"
+      "INFO  2024-03-18 19:58:53,290 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9657414983648998, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,499 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
+      "INFO  2024-03-18 19:58:53,291 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,500 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,292 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,501 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:53,293 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,590 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,383 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,600 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]\n"
+      "INFO  2024-03-18 19:58:53,395 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=0.9560552426688266, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,601 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
+      "INFO  2024-03-18 19:58:53,397 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,601 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,397 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,603 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:53,399 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,690 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:53,487 sensai.vector_model:fit - Fitting completed in 0.09 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,700 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]\n"
+      "INFO  2024-03-18 19:58:53,498 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.841736920530503, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,710 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
+      "INFO  2024-03-18 19:58:53,510 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
       "       mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]\n",
       "class            0.96       0.053333                0.963571               0.050077                     0.89878                    0.10223\n"
      ]
@@ -1879,364 +1879,364 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,797 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named 'DecisionTree' ...\n"
+      "INFO  2024-03-18 19:58:53,586 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named 'DecisionTree' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,798 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
+      "INFO  2024-03-18 19:58:53,587 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 1/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,799 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,588 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,801 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,590 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,804 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,593 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,811 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
+      "INFO  2024-03-18 19:58:53,601 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 1/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,811 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
+      "INFO  2024-03-18 19:58:53,602 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 2/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,812 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,603 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,813 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,604 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,816 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,607 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,824 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
+      "INFO  2024-03-18 19:58:53,615 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 2/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,824 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
+      "INFO  2024-03-18 19:58:53,616 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 3/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,825 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,617 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,826 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,618 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,828 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,621 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,835 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
+      "INFO  2024-03-18 19:58:53,628 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 3/10: ClassificationEvalStats[accuracy=1.0, balancedAccuracy=1.0, geoMeanTrueClassProb=1.0, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,836 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
+      "INFO  2024-03-18 19:58:53,629 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 4/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,837 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,630 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,838 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,632 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,840 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,635 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,847 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]\n"
+      "INFO  2024-03-18 19:58:53,642 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 4/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,847 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
+      "INFO  2024-03-18 19:58:53,646 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 5/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,848 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,647 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,849 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,649 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,853 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,652 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,859 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9548416039104165, N=15]\n"
+      "INFO  2024-03-18 19:58:53,660 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 5/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.9548416039104165, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,860 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
+      "INFO  2024-03-18 19:58:53,661 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 6/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,861 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,662 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,862 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,663 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,864 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,667 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,871 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.39810717055349726, N=15]\n"
+      "INFO  2024-03-18 19:58:53,675 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 6/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8888888888888888, geoMeanTrueClassProb=0.39810717055349726, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,872 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
+      "INFO  2024-03-18 19:58:53,676 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 7/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,872 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,677 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,873 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,678 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,875 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,682 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,882 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.39810717055349726, N=15]\n"
+      "INFO  2024-03-18 19:58:53,689 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 7/10: ClassificationEvalStats[accuracy=0.8666666666666667, balancedAccuracy=0.8611111111111112, geoMeanTrueClassProb=0.39810717055349726, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,883 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
+      "INFO  2024-03-18 19:58:53,689 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 8/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,883 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,690 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,884 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,692 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,887 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,695 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,893 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9444444444444445, geoMeanTrueClassProb=0.9548416039104165, N=15]\n"
+      "INFO  2024-03-18 19:58:53,701 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 8/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9444444444444445, geoMeanTrueClassProb=0.9548416039104165, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,894 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
+      "INFO  2024-03-18 19:58:53,702 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 9/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,895 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,703 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,896 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,705 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,898 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,708 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,905 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]\n"
+      "INFO  2024-03-18 19:58:53,714 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 9/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9333333333333332, geoMeanTrueClassProb=0.6141303814089187, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,905 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
+      "INFO  2024-03-18 19:58:53,715 sensai.evaluation.crossval:eval_model - Training and evaluating model with fold 10/10 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,906 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:53,716 sensai.vector_model:fit - Fitting SkLearnDecisionTreeVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,907 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
+      "INFO  2024-03-18 19:58:53,717 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type DecisionTreeClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,909 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
+      "INFO  2024-03-18 19:58:53,720 sensai.vector_model:fit - Fitting completed in 0.00 seconds: SkLearnDecisionTreeVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=DecisionTree, model=DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=2, min_samples_split=2, min_weight_fraction_leaf=0.0, presort='deprecated', random_state=42, splitter='best')]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,916 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.6309573444801932, N=15]\n"
+      "INFO  2024-03-18 19:58:53,727 sensai.evaluation.crossval:eval_model - Evaluation result for class, fold 10/10: ClassificationEvalStats[accuracy=0.9333333333333333, balancedAccuracy=0.9523809523809524, geoMeanTrueClassProb=0.6309573444801932, N=15]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,926 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
+      "INFO  2024-03-18 19:58:53,740 sensai.evaluation.eval_util:perform_cross_validation - Cross-validation results:\n",
       "       mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]\n",
       "class            0.94       0.046667                0.944683                0.04441                    0.756512                   0.238693\n"
      ]
@@ -2245,7 +2245,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:35,001 sensai.evaluation.eval_util:compare_models - Model comparison results, aggregated across folds:\n",
+      "INFO  2024-03-18 19:58:53,833 sensai.evaluation.eval_util:compare_models - Model comparison results, aggregated across folds:\n",
       "              mean[accuracy]  std[accuracy]  mean[balancedAccuracy]  std[balancedAccuracy]  mean[geoMeanTrueClassProb]  std[geoMeanTrueClassProb]\n",
       "model_name                                                                                                                                       \n",
       "RandomForest            0.96       0.053333                0.963571               0.050077                    0.898780                   0.102230\n",
@@ -2292,10 +2292,10 @@
    "execution_count": 24,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:35.338287Z",
-     "iopub.status.busy": "2024-03-02T11:32:35.337714Z",
-     "iopub.status.idle": "2024-03-02T11:32:35.533235Z",
-     "shell.execute_reply": "2024-03-02T11:32:35.532492Z"
+     "iopub.execute_input": "2024-03-18T19:58:54.173182Z",
+     "iopub.status.busy": "2024-03-18T19:58:54.172636Z",
+     "iopub.status.idle": "2024-03-18T19:58:54.382964Z",
+     "shell.execute_reply": "2024-03-18T19:58:54.382079Z"
     }
    },
    "outputs": [
@@ -2410,10 +2410,10 @@
    "execution_count": 25,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:35.537194Z",
-     "iopub.status.busy": "2024-03-02T11:32:35.536586Z",
-     "iopub.status.idle": "2024-03-02T11:32:35.555897Z",
-     "shell.execute_reply": "2024-03-02T11:32:35.555207Z"
+     "iopub.execute_input": "2024-03-18T19:58:54.386785Z",
+     "iopub.status.busy": "2024-03-18T19:58:54.386162Z",
+     "iopub.status.idle": "2024-03-18T19:58:54.408153Z",
+     "shell.execute_reply": "2024-03-18T19:58:54.407270Z"
     }
    },
    "outputs": [
@@ -2442,10 +2442,10 @@
    "execution_count": 26,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:35.558794Z",
-     "iopub.status.busy": "2024-03-02T11:32:35.558369Z",
-     "iopub.status.idle": "2024-03-02T11:32:35.582171Z",
-     "shell.execute_reply": "2024-03-02T11:32:35.581547Z"
+     "iopub.execute_input": "2024-03-18T19:58:54.412258Z",
+     "iopub.status.busy": "2024-03-18T19:58:54.411546Z",
+     "iopub.status.idle": "2024-03-18T19:58:54.432172Z",
+     "shell.execute_reply": "2024-03-18T19:58:54.431317Z"
     }
    },
    "outputs": [
diff --git a/docs/neural_networks.html b/docs/neural_networks.html
index b2ba7410..0e7aa8f7 100644
--- a/docs/neural_networks.html
+++ b/docs/neural_networks.html
@@ -405,52 +405,52 @@ <h3>Applying Predefined Models<a class="headerlink" href="#Applying-Predefined-M
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-INFO  2024-03-02 11:32:33,899 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named &#39;RandomForest&#39; ...
-DEBUG 2024-03-02 11:32:34,125 sensai.evaluation.evaluator:__init__ - &lt;sensai.data.DataSplitterFractional object at 0x7effac5a8e50&gt; created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively
-INFO  2024-03-02 11:32:34,126 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, modelConstructor=RandomForestClassifier(random_state=42, min_samples_leaf=1, n_estimators=10)] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effac5a8790&gt;
-INFO  2024-03-02 11:32:34,127 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
-DEBUG 2024-03-02 11:32:34,151 sensai.vector_model:fit - Fitting with outputs[1]=[&#39;label&#39;], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points
-INFO  2024-03-02 11:32:34,152 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
-INFO  2024-03-02 11:32:36,908 sensai.vector_model:fit - Fitting completed in 2.78 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
-INFO  2024-03-02 11:32:36,983 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]
-INFO  2024-03-02 11:32:37,306 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named &#39;MLP&#39; ...
-INFO  2024-03-02 11:32:37,307 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=&lt;built-in method sigmoid of type object at 0x7eff4cd88880&gt;, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=None, inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effac5a8790&gt;
-INFO  2024-03-02 11:32:37,308 sensai.vector_model:fit - Fitting MultiLayerPerceptronVectorClassificationModel instance
-DEBUG 2024-03-02 11:32:37,316 sensai.vector_model:fit - Fitting with outputs[1]=[&#39;label&#39;], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points
-INFO  2024-03-02 11:32:37,482 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=&lt;built-in method sigmoid of type object at 0x7eff4cd88880&gt;, outputActivationFunction=functools.partial(&lt;function log_softmax at 0x7effab8fccb0&gt;, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]] with cuda=False
-INFO  2024-03-02 11:32:37,484 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances
-INFO  2024-03-02 11:32:37,657 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000
-INFO  2024-03-02 11:32:37,658 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1
-INFO  2024-03-02 11:32:37,660 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=&lt;built-in method sigmoid of type object at 0x7eff4cd88880&gt;, outputActivationFunction=functools.partial(&lt;function log_softmax at 0x7effab8fccb0&gt;, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None]
-INFO  2024-03-02 11:32:37,660 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 40480
-INFO  2024-03-02 11:32:37,661 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]]
-INFO  2024-03-02 11:32:37,669 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False
-INFO  2024-03-02 11:32:37,670 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early
-INFO  2024-03-02 11:32:38,818 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  1.15s | train loss 1.4059 | validation NLL 0.7300 | best NLL 0.730044 from this epoch
-INFO  2024-03-02 11:32:39,950 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  1.12s | train loss 0.5021 | validation NLL 0.3806 | best NLL 0.380582 from this epoch
-INFO  2024-03-02 11:32:41,111 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  1.15s | train loss 0.3138 | validation NLL 0.2847 | best NLL 0.284687 from this epoch
-INFO  2024-03-02 11:32:42,270 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  1.15s | train loss 0.2409 | validation NLL 0.2393 | best NLL 0.239259 from this epoch
-INFO  2024-03-02 11:32:43,440 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  1.16s | train loss 0.1981 | validation NLL 0.2081 | best NLL 0.208118 from this epoch
-INFO  2024-03-02 11:32:44,441 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  0.99s | train loss 0.1676 | validation NLL 0.1872 | best NLL 0.187202 from this epoch
-INFO  2024-03-02 11:32:45,450 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  1.00s | train loss 0.1450 | validation NLL 0.1697 | best NLL 0.169709 from this epoch
-INFO  2024-03-02 11:32:46,585 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  1.13s | train loss 0.1274 | validation NLL 0.1593 | best NLL 0.159322 from this epoch
-INFO  2024-03-02 11:32:47,590 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  1.00s | train loss 0.1131 | validation NLL 0.1509 | best NLL 0.150902 from this epoch
-INFO  2024-03-02 11:32:48,604 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  10/1000 completed in  1.01s | train loss 0.1013 | validation NLL 0.1440 | best NLL 0.144011 from this epoch
-INFO  2024-03-02 11:32:49,727 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  11/1000 completed in  1.11s | train loss 0.0906 | validation NLL 0.1381 | best NLL 0.138148 from this epoch
-INFO  2024-03-02 11:32:50,848 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  12/1000 completed in  1.11s | train loss 0.0816 | validation NLL 0.1334 | best NLL 0.133373 from this epoch
-INFO  2024-03-02 11:32:51,970 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  13/1000 completed in  1.12s | train loss 0.0739 | validation NLL 0.1315 | best NLL 0.131459 from this epoch
-INFO  2024-03-02 11:32:53,009 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  14/1000 completed in  1.03s | train loss 0.0667 | validation NLL 0.1281 | best NLL 0.128110 from this epoch
-INFO  2024-03-02 11:32:54,140 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  15/1000 completed in  1.12s | train loss 0.0610 | validation NLL 0.1271 | best NLL 0.127124 from this epoch
-INFO  2024-03-02 11:32:55,255 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  16/1000 completed in  1.11s | train loss 0.0553 | validation NLL 0.1222 | best NLL 0.122218 from this epoch
-INFO  2024-03-02 11:32:56,375 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  17/1000 completed in  1.11s | train loss 0.0504 | validation NLL 0.1258 | best NLL 0.122218 from epoch 16
-INFO  2024-03-02 11:32:57,485 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  18/1000 completed in  1.11s | train loss 0.0461 | validation NLL 0.1233 | best NLL 0.122218 from epoch 16
-INFO  2024-03-02 11:32:57,486 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 2 epochs without validation metric improvement
-INFO  2024-03-02 11:32:57,487 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete
-INFO  2024-03-02 11:32:57,487 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 16 with NLL 0.12221813999116421 on validation set
-INFO  2024-03-02 11:32:57,495 sensai.vector_model:fit - Fitting completed in 20.19 seconds: MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=&lt;built-in method sigmoid of type object at 0x7eff4cd88880&gt;, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=&lt;built-in method sigmoid of type object at 0x7eff4cd88880&gt;, outputActivationFunction=functools.partial(&lt;function log_softmax at 0x7effab8fccb0&gt;, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP]
-DEBUG 2024-03-02 11:32:57,496 sensai.torch.torch_data:__init__ - Applying &lt;sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7effae07b150&gt; to data frame of length 12000 ...
-INFO  2024-03-02 11:32:57,623 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]
-INFO  2024-03-02 11:32:57,900 sensai.evaluation.eval_util:compare_models - Model comparison results:
+INFO  2024-03-18 19:58:52,678 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named &#39;RandomForest&#39; ...
+DEBUG 2024-03-18 19:58:52,937 sensai.evaluation.evaluator:__init__ - &lt;sensai.data.DataSplitterFractional object at 0x7ddfded82c90&gt; created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively
+INFO  2024-03-18 19:58:52,939 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, modelConstructor=RandomForestClassifier(random_state=42, min_samples_leaf=1, n_estimators=10)] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfded82b50&gt;
+INFO  2024-03-18 19:58:52,940 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance
+DEBUG 2024-03-18 19:58:52,985 sensai.vector_model:fit - Fitting with outputs[1]=[&#39;label&#39;], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points
+INFO  2024-03-18 19:58:52,986 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier
+INFO  2024-03-18 19:58:55,860 sensai.vector_model:fit - Fitting completed in 2.92 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]
+INFO  2024-03-18 19:58:55,944 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]
+INFO  2024-03-18 19:58:56,221 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named &#39;MLP&#39; ...
+INFO  2024-03-18 19:58:56,223 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=&lt;built-in method sigmoid of type object at 0x7ddf80988880&gt;, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=None, inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfded82b50&gt;
+INFO  2024-03-18 19:58:56,224 sensai.vector_model:fit - Fitting MultiLayerPerceptronVectorClassificationModel instance
+DEBUG 2024-03-18 19:58:56,230 sensai.vector_model:fit - Fitting with outputs[1]=[&#39;label&#39;], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points
+INFO  2024-03-18 19:58:56,368 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=&lt;built-in method sigmoid of type object at 0x7ddf80988880&gt;, outputActivationFunction=functools.partial(&lt;function log_softmax at 0x7ddfde8fa170&gt;, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]] with cuda=False
+INFO  2024-03-18 19:58:56,370 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances
+INFO  2024-03-18 19:58:56,547 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000
+INFO  2024-03-18 19:58:56,549 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1
+INFO  2024-03-18 19:58:56,551 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=&lt;built-in method sigmoid of type object at 0x7ddf80988880&gt;, outputActivationFunction=functools.partial(&lt;function log_softmax at 0x7ddfde8fa170&gt;, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None]
+INFO  2024-03-18 19:58:56,551 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 40480
+INFO  2024-03-18 19:58:56,552 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]]
+INFO  2024-03-18 19:58:56,561 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False
+INFO  2024-03-18 19:58:56,562 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early
+INFO  2024-03-18 19:58:57,735 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  1.17s | train loss 1.4059 | validation NLL 0.7300 | best NLL 0.730044 from this epoch
+INFO  2024-03-18 19:58:58,930 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  1.19s | train loss 0.5021 | validation NLL 0.3806 | best NLL 0.380582 from this epoch
+INFO  2024-03-18 19:58:59,967 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  1.03s | train loss 0.3138 | validation NLL 0.2847 | best NLL 0.284687 from this epoch
+INFO  2024-03-18 19:59:01,003 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  1.03s | train loss 0.2409 | validation NLL 0.2393 | best NLL 0.239259 from this epoch
+INFO  2024-03-18 19:59:02,039 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  1.03s | train loss 0.1981 | validation NLL 0.2081 | best NLL 0.208118 from this epoch
+INFO  2024-03-18 19:59:03,075 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  1.03s | train loss 0.1676 | validation NLL 0.1872 | best NLL 0.187202 from this epoch
+INFO  2024-03-18 19:59:04,110 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  1.03s | train loss 0.1450 | validation NLL 0.1697 | best NLL 0.169709 from this epoch
+INFO  2024-03-18 19:59:05,149 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  1.03s | train loss 0.1274 | validation NLL 0.1593 | best NLL 0.159322 from this epoch
+INFO  2024-03-18 19:59:06,184 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  1.03s | train loss 0.1131 | validation NLL 0.1509 | best NLL 0.150902 from this epoch
+INFO  2024-03-18 19:59:07,215 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  10/1000 completed in  1.02s | train loss 0.1013 | validation NLL 0.1440 | best NLL 0.144011 from this epoch
+INFO  2024-03-18 19:59:08,244 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  11/1000 completed in  1.02s | train loss 0.0906 | validation NLL 0.1381 | best NLL 0.138148 from this epoch
+INFO  2024-03-18 19:59:09,276 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  12/1000 completed in  1.02s | train loss 0.0816 | validation NLL 0.1334 | best NLL 0.133373 from this epoch
+INFO  2024-03-18 19:59:10,451 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  13/1000 completed in  1.17s | train loss 0.0739 | validation NLL 0.1315 | best NLL 0.131459 from this epoch
+INFO  2024-03-18 19:59:11,623 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  14/1000 completed in  1.16s | train loss 0.0667 | validation NLL 0.1281 | best NLL 0.128110 from this epoch
+INFO  2024-03-18 19:59:12,817 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  15/1000 completed in  1.19s | train loss 0.0610 | validation NLL 0.1271 | best NLL 0.127124 from this epoch
+INFO  2024-03-18 19:59:13,995 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  16/1000 completed in  1.17s | train loss 0.0553 | validation NLL 0.1222 | best NLL 0.122218 from this epoch
+INFO  2024-03-18 19:59:15,149 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  17/1000 completed in  1.15s | train loss 0.0504 | validation NLL 0.1258 | best NLL 0.122218 from epoch 16
+INFO  2024-03-18 19:59:16,309 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  18/1000 completed in  1.16s | train loss 0.0461 | validation NLL 0.1233 | best NLL 0.122218 from epoch 16
+INFO  2024-03-18 19:59:16,310 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 2 epochs without validation metric improvement
+INFO  2024-03-18 19:59:16,311 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete
+INFO  2024-03-18 19:59:16,311 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 16 with NLL 0.12221813999116421 on validation set
+INFO  2024-03-18 19:59:16,320 sensai.vector_model:fit - Fitting completed in 20.10 seconds: MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=&lt;built-in method sigmoid of type object at 0x7ddf80988880&gt;, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=&lt;built-in method sigmoid of type object at 0x7ddf80988880&gt;, outputActivationFunction=functools.partial(&lt;function log_softmax at 0x7ddfde8fa170&gt;, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP]
+DEBUG 2024-03-18 19:59:16,321 sensai.torch.torch_data:__init__ - Applying &lt;sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7ddfdcd5c850&gt; to data frame of length 12000 ...
+INFO  2024-03-18 19:59:16,450 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]
+INFO  2024-03-18 19:59:16,732 sensai.evaluation.eval_util:compare_models - Model comparison results:
               accuracy  balancedAccuracy
 model_name
 RandomForest  0.946667          0.945917
@@ -463,7 +463,7 @@ <h3>Applying Predefined Models<a class="headerlink" href="#Applying-Predefined-M
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-&lt;sensai.evaluation.eval_util.ModelComparisonData at 0x7effaa5af390&gt;
+&lt;sensai.evaluation.eval_util.ModelComparisonData at 0x7ddfdbbdac10&gt;
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -584,35 +584,35 @@ <h4>Wrapping a Custom torch.nn.Module Instance<a class="headerlink" href="#Wrapp
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-DEBUG 2024-03-02 11:32:59,879 sensai.evaluation.evaluator:__init__ - &lt;sensai.data.DataSplitterFractional object at 0x7effac5a8e50&gt; created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively
-INFO  2024-03-02 11:32:59,880 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=&lt;sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7effa8da9850&gt;, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effa91a2c50&gt;
-INFO  2024-03-02 11:32:59,881 sensai.vector_model:fit - Fitting TorchVectorClassificationModel instance
-DEBUG 2024-03-02 11:32:59,910 sensai.vector_model:fit - Fitting with outputs[1]=[&#39;label&#39;], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points
-INFO  2024-03-02 11:32:59,911 sensai.torch.torch_base:_fit_classifier - Fitting &lt;__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10&gt; ...
-INFO  2024-03-02 11:32:59,970 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False
-INFO  2024-03-02 11:32:59,971 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances
-INFO  2024-03-02 11:33:02,405 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000
-INFO  2024-03-02 11:33:02,407 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1
-INFO  2024-03-02 11:33:02,408 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None]
-INFO  2024-03-02 11:33:02,408 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862
-INFO  2024-03-02 11:33:02,409 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]
-INFO  2024-03-02 11:33:02,420 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False
-INFO  2024-03-02 11:33:02,421 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early
-INFO  2024-03-02 11:33:12,225 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.80s | train loss 0.8318 | validation NLL 0.1962 | best NLL 0.196246 from this epoch
-INFO  2024-03-02 11:33:21,992 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.76s | train loss 0.1365 | validation NLL 0.1341 | best NLL 0.134100 from this epoch
-INFO  2024-03-02 11:33:31,736 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.73s | train loss 0.0724 | validation NLL 0.1154 | best NLL 0.115383 from this epoch
-INFO  2024-03-02 11:33:41,472 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.72s | train loss 0.0524 | validation NLL 0.1286 | best NLL 0.115383 from epoch 3
-INFO  2024-03-02 11:33:51,268 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.80s | train loss 0.0418 | validation NLL 0.1073 | best NLL 0.107293 from this epoch
-INFO  2024-03-02 11:34:01,017 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.74s | train loss 0.0345 | validation NLL 0.0818 | best NLL 0.081762 from this epoch
-INFO  2024-03-02 11:34:10,726 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.70s | train loss 0.0293 | validation NLL 0.0953 | best NLL 0.081762 from epoch 6
-INFO  2024-03-02 11:34:20,455 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.73s | train loss 0.0245 | validation NLL 0.1157 | best NLL 0.081762 from epoch 6
-INFO  2024-03-02 11:34:30,224 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  9.77s | train loss 0.0209 | validation NLL 0.0996 | best NLL 0.081762 from epoch 6
-INFO  2024-03-02 11:34:30,225 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement
-INFO  2024-03-02 11:34:30,225 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete
-INFO  2024-03-02 11:34:30,226 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 6 with NLL 0.08176225980122884 on validation set
-INFO  2024-03-02 11:34:30,237 sensai.vector_model:fit - Fitting completed in 90.36 seconds: TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=&lt;sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7effa8da9850&gt;, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN]
-DEBUG 2024-03-02 11:34:30,238 sensai.torch.torch_data:__init__ - Applying &lt;__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10&gt; to data frame of length 12000 ...
-INFO  2024-03-02 11:34:32,035 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]
+DEBUG 2024-03-18 19:59:18,801 sensai.evaluation.evaluator:__init__ - &lt;sensai.data.DataSplitterFractional object at 0x7ddfded82c90&gt; created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively
+INFO  2024-03-18 19:59:18,802 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=&lt;sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7ddfdbf90690&gt;, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdb7cc350&gt;
+INFO  2024-03-18 19:59:18,803 sensai.vector_model:fit - Fitting TorchVectorClassificationModel instance
+DEBUG 2024-03-18 19:59:18,825 sensai.vector_model:fit - Fitting with outputs[1]=[&#39;label&#39;], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points
+INFO  2024-03-18 19:59:18,826 sensai.torch.torch_base:_fit_classifier - Fitting &lt;__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0&gt; ...
+INFO  2024-03-18 19:59:18,886 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False
+INFO  2024-03-18 19:59:18,887 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances
+INFO  2024-03-18 19:59:21,321 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000
+INFO  2024-03-18 19:59:21,322 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1
+INFO  2024-03-18 19:59:21,323 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None]
+INFO  2024-03-18 19:59:21,323 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862
+INFO  2024-03-18 19:59:21,324 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]
+INFO  2024-03-18 19:59:21,335 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False
+INFO  2024-03-18 19:59:21,336 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early
+INFO  2024-03-18 19:59:31,168 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.83s | train loss 0.8318 | validation NLL 0.1962 | best NLL 0.196246 from this epoch
+INFO  2024-03-18 19:59:41,005 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.83s | train loss 0.1365 | validation NLL 0.1341 | best NLL 0.134100 from this epoch
+INFO  2024-03-18 19:59:50,892 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.88s | train loss 0.0724 | validation NLL 0.1154 | best NLL 0.115383 from this epoch
+INFO  2024-03-18 20:00:00,774 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.87s | train loss 0.0524 | validation NLL 0.1286 | best NLL 0.115383 from epoch 3
+INFO  2024-03-18 20:00:10,651 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.88s | train loss 0.0418 | validation NLL 0.1073 | best NLL 0.107293 from this epoch
+INFO  2024-03-18 20:00:20,471 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.81s | train loss 0.0345 | validation NLL 0.0818 | best NLL 0.081762 from this epoch
+INFO  2024-03-18 20:00:30,288 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.81s | train loss 0.0293 | validation NLL 0.0953 | best NLL 0.081762 from epoch 6
+INFO  2024-03-18 20:00:40,140 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.85s | train loss 0.0245 | validation NLL 0.1157 | best NLL 0.081762 from epoch 6
+INFO  2024-03-18 20:00:49,883 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  9.74s | train loss 0.0209 | validation NLL 0.0996 | best NLL 0.081762 from epoch 6
+INFO  2024-03-18 20:00:49,885 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement
+INFO  2024-03-18 20:00:49,885 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete
+INFO  2024-03-18 20:00:49,886 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 6 with NLL 0.08176225980122884 on validation set
+INFO  2024-03-18 20:00:49,897 sensai.vector_model:fit - Fitting completed in 91.09 seconds: TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=&lt;sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7ddfdbf90690&gt;, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN]
+DEBUG 2024-03-18 20:00:49,897 sensai.torch.torch_data:__init__ - Applying &lt;__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0&gt; to data frame of length 12000 ...
+INFO  2024-03-18 20:00:51,654 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -710,34 +710,34 @@ <h4>Creating an Input-/Output-Adaptive Custom Model<a class="headerlink" href="#
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-DEBUG 2024-03-02 11:34:33,459 sensai.evaluation.evaluator:__init__ - &lt;sensai.data.DataSplitterFractional object at 0x7effac5a8e50&gt; created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively
-INFO  2024-03-02 11:34:33,460 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(&lt;class &#39;__main__.CnnModel.VectorTorchModel&#39;&gt;, CnnModel[id=139636510019152, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7effa893c450&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;]), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7effa893c450&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effa893c7d0&gt;
-INFO  2024-03-02 11:34:33,461 sensai.vector_model:fit - Fitting CnnModel instance
-DEBUG 2024-03-02 11:34:33,484 sensai.vector_model:fit - Fitting with outputs[1]=[&#39;label&#39;], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points
-INFO  2024-03-02 11:34:33,485 sensai.torch.torch_base:_fit_classifier - Fitting &lt;__main__.ImageReshapingInputTensoriser object at 0x7effa893c450&gt; ...
-INFO  2024-03-02 11:34:33,544 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False
-INFO  2024-03-02 11:34:33,545 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances
-INFO  2024-03-02 11:34:35,981 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000
-INFO  2024-03-02 11:34:35,981 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1
-INFO  2024-03-02 11:34:35,986 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None]
-INFO  2024-03-02 11:34:35,987 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862
-INFO  2024-03-02 11:34:35,988 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]
-INFO  2024-03-02 11:34:35,997 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False
-INFO  2024-03-02 11:34:35,998 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early
-INFO  2024-03-02 11:34:45,805 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.81s | train loss 0.8259 | validation NLL 0.2525 | best NLL 0.252539 from this epoch
-INFO  2024-03-02 11:34:55,478 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.66s | train loss 0.1533 | validation NLL 0.1433 | best NLL 0.143283 from this epoch
-INFO  2024-03-02 11:35:05,184 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.70s | train loss 0.0881 | validation NLL 0.0999 | best NLL 0.099880 from this epoch
-INFO  2024-03-02 11:35:14,892 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.70s | train loss 0.0596 | validation NLL 0.1221 | best NLL 0.099880 from epoch 3
-INFO  2024-03-02 11:35:24,593 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.70s | train loss 0.0452 | validation NLL 0.0962 | best NLL 0.096233 from this epoch
-INFO  2024-03-02 11:35:34,295 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.69s | train loss 0.0380 | validation NLL 0.0974 | best NLL 0.096233 from epoch 5
-INFO  2024-03-02 11:35:44,062 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.77s | train loss 0.0294 | validation NLL 0.0986 | best NLL 0.096233 from epoch 5
-INFO  2024-03-02 11:35:53,811 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.75s | train loss 0.0223 | validation NLL 0.1068 | best NLL 0.096233 from epoch 5
-INFO  2024-03-02 11:35:53,811 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement
-INFO  2024-03-02 11:35:53,812 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete
-INFO  2024-03-02 11:35:53,812 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 5 with NLL 0.09623306624094645 on validation set
-INFO  2024-03-02 11:35:53,824 sensai.vector_model:fit - Fitting completed in 80.36 seconds: CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(&lt;class &#39;__main__.CnnModel.VectorTorchModel&#39;&gt;, CnnModel[id=139636510019152, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7effa893c450&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;]), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7effa893c450&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;]
-DEBUG 2024-03-02 11:35:53,825 sensai.torch.torch_data:__init__ - Applying &lt;__main__.ImageReshapingInputTensoriser object at 0x7effa893c450&gt; to data frame of length 12000 ...
-INFO  2024-03-02 11:35:55,558 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]
+DEBUG 2024-03-18 20:00:53,167 sensai.evaluation.evaluator:__init__ - &lt;sensai.data.DataSplitterFractional object at 0x7ddfded82c90&gt; created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively
+INFO  2024-03-18 20:00:53,168 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(&lt;class &#39;__main__.CnnModel.VectorTorchModel&#39;&gt;, CnnModel[id=138400413109712, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7de00026d150&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;]), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7de00026d150&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdb765610&gt;
+INFO  2024-03-18 20:00:53,168 sensai.vector_model:fit - Fitting CnnModel instance
+DEBUG 2024-03-18 20:00:53,191 sensai.vector_model:fit - Fitting with outputs[1]=[&#39;label&#39;], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points
+INFO  2024-03-18 20:00:53,192 sensai.torch.torch_base:_fit_classifier - Fitting &lt;__main__.ImageReshapingInputTensoriser object at 0x7de00026d150&gt; ...
+INFO  2024-03-18 20:00:53,252 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False
+INFO  2024-03-18 20:00:53,254 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances
+INFO  2024-03-18 20:00:55,687 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000
+INFO  2024-03-18 20:00:55,688 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1
+INFO  2024-03-18 20:00:55,694 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None]
+INFO  2024-03-18 20:00:55,695 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862
+INFO  2024-03-18 20:00:55,695 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]
+INFO  2024-03-18 20:00:55,706 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False
+INFO  2024-03-18 20:00:55,706 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early
+INFO  2024-03-18 20:01:05,468 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.76s | train loss 0.8259 | validation NLL 0.2525 | best NLL 0.252539 from this epoch
+INFO  2024-03-18 20:01:15,233 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.76s | train loss 0.1533 | validation NLL 0.1433 | best NLL 0.143283 from this epoch
+INFO  2024-03-18 20:01:25,017 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.77s | train loss 0.0881 | validation NLL 0.0999 | best NLL 0.099880 from this epoch
+INFO  2024-03-18 20:01:34,843 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.81s | train loss 0.0596 | validation NLL 0.1221 | best NLL 0.099880 from epoch 3
+INFO  2024-03-18 20:01:44,656 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.81s | train loss 0.0452 | validation NLL 0.0962 | best NLL 0.096233 from this epoch
+INFO  2024-03-18 20:01:54,476 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.81s | train loss 0.0380 | validation NLL 0.0974 | best NLL 0.096233 from epoch 5
+INFO  2024-03-18 20:02:04,319 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.84s | train loss 0.0294 | validation NLL 0.0986 | best NLL 0.096233 from epoch 5
+INFO  2024-03-18 20:02:14,113 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.79s | train loss 0.0223 | validation NLL 0.1068 | best NLL 0.096233 from epoch 5
+INFO  2024-03-18 20:02:14,114 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement
+INFO  2024-03-18 20:02:14,115 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete
+INFO  2024-03-18 20:02:14,115 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 5 with NLL 0.09623306624094645 on validation set
+INFO  2024-03-18 20:02:14,128 sensai.vector_model:fit - Fitting completed in 80.96 seconds: CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(&lt;class &#39;__main__.CnnModel.VectorTorchModel&#39;&gt;, CnnModel[id=138400413109712, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7de00026d150&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;]), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7de00026d150&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;]
+DEBUG 2024-03-18 20:02:14,129 sensai.torch.torch_data:__init__ - Applying &lt;__main__.ImageReshapingInputTensoriser object at 0x7de00026d150&gt; to data frame of length 12000 ...
+INFO  2024-03-18 20:02:15,905 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]
 </pre></div></div>
 </div>
 <div class="nboutput docutils container">
@@ -769,23 +769,23 @@ <h4>Creating an Input-/Output-Adaptive Custom Model<a class="headerlink" href="#
 </div>
 <div class="output_area docutils container">
 <div class="highlight"><pre>
-INFO  2024-03-02 11:35:56,737 sensai.evaluation.eval_util:compare_models - Evaluating model 1/4 named &#39;MLP&#39; ...
-DEBUG 2024-03-02 11:35:56,952 sensai.evaluation.evaluator:__init__ - &lt;sensai.data.DataSplitterFractional object at 0x7effac5a8e50&gt; created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively
-INFO  2024-03-02 11:35:56,953 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=&lt;built-in method sigmoid of type object at 0x7eff4cd88880&gt;, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=&lt;built-in method sigmoid of type object at 0x7eff4cd88880&gt;, outputActivationFunction=functools.partial(&lt;function log_softmax at 0x7effab8fccb0&gt;, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050&gt;
-DEBUG 2024-03-02 11:35:56,954 sensai.torch.torch_data:__init__ - Applying &lt;sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7effaa1f3f90&gt; to data frame of length 12000 ...
-INFO  2024-03-02 11:35:57,085 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]
-INFO  2024-03-02 11:35:57,483 sensai.evaluation.eval_util:compare_models - Evaluating model 2/4 named &#39;CNN&#39; ...
-INFO  2024-03-02 11:35:57,484 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=&lt;sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7effa8da9850&gt;, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050&gt;
-DEBUG 2024-03-02 11:35:57,485 sensai.torch.torch_data:__init__ - Applying &lt;__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10&gt; to data frame of length 12000 ...
-INFO  2024-03-02 11:35:59,266 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]
-INFO  2024-03-02 11:35:59,524 sensai.evaluation.eval_util:compare_models - Evaluating model 3/4 named &#39;CNN&#39;&#39; ...
-INFO  2024-03-02 11:35:59,526 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(&lt;class &#39;__main__.CnnModel.VectorTorchModel&#39;&gt;, CnnModel[id=139636510019152, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7effa893c450&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;]), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7effa893c450&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050&gt;
-DEBUG 2024-03-02 11:35:59,527 sensai.torch.torch_data:__init__ - Applying &lt;__main__.ImageReshapingInputTensoriser object at 0x7effa893c450&gt; to data frame of length 12000 ...
-INFO  2024-03-02 11:36:01,269 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]
-INFO  2024-03-02 11:36:01,531 sensai.evaluation.eval_util:compare_models - Evaluating model 4/4 named &#39;RandomForest&#39; ...
-INFO  2024-03-02 11:36:01,532 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050&gt;
-INFO  2024-03-02 11:36:01,610 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]
-INFO  2024-03-02 11:36:01,937 sensai.evaluation.eval_util:compare_models - Model comparison results:
+INFO  2024-03-18 20:02:17,091 sensai.evaluation.eval_util:compare_models - Evaluating model 1/4 named &#39;MLP&#39; ...
+DEBUG 2024-03-18 20:02:17,314 sensai.evaluation.evaluator:__init__ - &lt;sensai.data.DataSplitterFractional object at 0x7ddfded82c90&gt; created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively
+INFO  2024-03-18 20:02:17,315 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=&lt;built-in method sigmoid of type object at 0x7ddf80988880&gt;, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=&lt;built-in method sigmoid of type object at 0x7ddf80988880&gt;, outputActivationFunction=functools.partial(&lt;function log_softmax at 0x7ddfde8fa170&gt;, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190&gt;
+DEBUG 2024-03-18 20:02:17,316 sensai.torch.torch_data:__init__ - Applying &lt;sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7ddfdb773bd0&gt; to data frame of length 12000 ...
+INFO  2024-03-18 20:02:17,450 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]
+INFO  2024-03-18 20:02:17,828 sensai.evaluation.eval_util:compare_models - Evaluating model 2/4 named &#39;CNN&#39; ...
+INFO  2024-03-18 20:02:17,829 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=&lt;sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7ddfdbf90690&gt;, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190&gt;
+DEBUG 2024-03-18 20:02:17,830 sensai.torch.torch_data:__init__ - Applying &lt;__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0&gt; to data frame of length 12000 ...
+INFO  2024-03-18 20:02:19,580 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]
+INFO  2024-03-18 20:02:19,842 sensai.evaluation.eval_util:compare_models - Evaluating model 3/4 named &#39;CNN&#39;&#39; ...
+INFO  2024-03-18 20:02:19,843 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(&lt;class &#39;__main__.CnnModel.VectorTorchModel&#39;&gt;, CnnModel[id=138400413109712, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7de00026d150&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;]), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=&lt;__main__.ImageReshapingInputTensoriser object at 0x7de00026d150&gt;, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN&#39;] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190&gt;
+DEBUG 2024-03-18 20:02:19,844 sensai.torch.torch_data:__init__ - Applying &lt;__main__.ImageReshapingInputTensoriser object at 0x7de00026d150&gt; to data frame of length 12000 ...
+INFO  2024-03-18 20:02:21,603 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]
+INFO  2024-03-18 20:02:21,931 sensai.evaluation.eval_util:compare_models - Evaluating model 4/4 named &#39;RandomForest&#39; ...
+INFO  2024-03-18 20:02:21,932 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion=&#39;gini&#39;, max_depth=None, max_features=&#39;auto&#39;, max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via &lt;sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190&gt;
+INFO  2024-03-18 20:02:22,014 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]
+INFO  2024-03-18 20:02:22,287 sensai.evaluation.eval_util:compare_models - Model comparison results:
               accuracy  balancedAccuracy
 model_name
 MLP           0.962250          0.961897
diff --git a/docs/neural_networks.ipynb b/docs/neural_networks.ipynb
index 7e7603fe..1ca033ce 100644
--- a/docs/neural_networks.ipynb
+++ b/docs/neural_networks.ipynb
@@ -18,10 +18,10 @@
    "execution_count": 1,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:29.202455Z",
-     "iopub.status.busy": "2024-03-02T11:32:29.202180Z",
-     "iopub.status.idle": "2024-03-02T11:32:29.302609Z",
-     "shell.execute_reply": "2024-03-02T11:32:29.301772Z"
+     "iopub.execute_input": "2024-03-18T19:58:47.591719Z",
+     "iopub.status.busy": "2024-03-18T19:58:47.591290Z",
+     "iopub.status.idle": "2024-03-18T19:58:47.755497Z",
+     "shell.execute_reply": "2024-03-18T19:58:47.754564Z"
     }
    },
    "outputs": [],
@@ -35,10 +35,10 @@
    "execution_count": 2,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:29.305744Z",
-     "iopub.status.busy": "2024-03-02T11:32:29.305318Z",
-     "iopub.status.idle": "2024-03-02T11:32:30.601176Z",
-     "shell.execute_reply": "2024-03-02T11:32:30.600456Z"
+     "iopub.execute_input": "2024-03-18T19:58:47.759221Z",
+     "iopub.status.busy": "2024-03-18T19:58:47.758724Z",
+     "iopub.status.idle": "2024-03-18T19:58:49.116589Z",
+     "shell.execute_reply": "2024-03-18T19:58:49.115706Z"
     }
    },
    "outputs": [],
@@ -71,10 +71,10 @@
    "execution_count": 3,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:30.604770Z",
-     "iopub.status.busy": "2024-03-02T11:32:30.604289Z",
-     "iopub.status.idle": "2024-03-02T11:32:32.981472Z",
-     "shell.execute_reply": "2024-03-02T11:32:32.980746Z"
+     "iopub.execute_input": "2024-03-18T19:58:49.120322Z",
+     "iopub.status.busy": "2024-03-18T19:58:49.119982Z",
+     "iopub.status.idle": "2024-03-18T19:58:51.702376Z",
+     "shell.execute_reply": "2024-03-18T19:58:51.701359Z"
     }
    },
    "outputs": [],
@@ -94,10 +94,10 @@
    "execution_count": 4,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:32.985269Z",
-     "iopub.status.busy": "2024-03-02T11:32:32.984654Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.024673Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.023845Z"
+     "iopub.execute_input": "2024-03-18T19:58:51.706408Z",
+     "iopub.status.busy": "2024-03-18T19:58:51.705770Z",
+     "iopub.status.idle": "2024-03-18T19:58:51.753970Z",
+     "shell.execute_reply": "2024-03-18T19:58:51.753016Z"
     }
    },
    "outputs": [
@@ -310,10 +310,10 @@
    "execution_count": 5,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.057096Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.056490Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.129598Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.128640Z"
+     "iopub.execute_input": "2024-03-18T19:58:51.790144Z",
+     "iopub.status.busy": "2024-03-18T19:58:51.789387Z",
+     "iopub.status.idle": "2024-03-18T19:58:51.860708Z",
+     "shell.execute_reply": "2024-03-18T19:58:51.859814Z"
     }
    },
    "outputs": [],
@@ -333,10 +333,10 @@
    "execution_count": 6,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.134426Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.133799Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.527595Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.526817Z"
+     "iopub.execute_input": "2024-03-18T19:58:51.864775Z",
+     "iopub.status.busy": "2024-03-18T19:58:51.864561Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.295615Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.294806Z"
     }
    },
    "outputs": [
@@ -382,10 +382,10 @@
    "execution_count": 7,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.531056Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.530584Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.554854Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.554059Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.299537Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.299037Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.318771Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.317981Z"
     }
    },
    "outputs": [],
@@ -406,10 +406,10 @@
    "execution_count": 8,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.558381Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.558176Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.851513Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.850665Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.322757Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.322147Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.629621Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.628872Z"
     }
    },
    "outputs": [],
@@ -439,10 +439,10 @@
    "execution_count": 9,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.855930Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.855208Z",
-     "iopub.status.idle": "2024-03-02T11:32:33.874334Z",
-     "shell.execute_reply": "2024-03-02T11:32:33.873633Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.634411Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.633959Z",
+     "iopub.status.idle": "2024-03-18T19:58:52.653307Z",
+     "shell.execute_reply": "2024-03-18T19:58:52.652530Z"
     }
    },
    "outputs": [],
@@ -465,10 +465,10 @@
    "execution_count": 10,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:33.877572Z",
-     "iopub.status.busy": "2024-03-02T11:32:33.877003Z",
-     "iopub.status.idle": "2024-03-02T11:32:59.578534Z",
-     "shell.execute_reply": "2024-03-02T11:32:59.577861Z"
+     "iopub.execute_input": "2024-03-18T19:58:52.657100Z",
+     "iopub.status.busy": "2024-03-18T19:58:52.656454Z",
+     "iopub.status.idle": "2024-03-18T19:59:18.464651Z",
+     "shell.execute_reply": "2024-03-18T19:59:18.463925Z"
     }
    },
    "outputs": [
@@ -476,322 +476,322 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:33,899 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named 'RandomForest' ...\n"
+      "INFO  2024-03-18 19:58:52,678 sensai.evaluation.eval_util:compare_models - Evaluating model 1/2 named 'RandomForest' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:34,125 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7effac5a8e50> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
+      "DEBUG 2024-03-18 19:58:52,937 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7ddfded82c90> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,126 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, modelConstructor=RandomForestClassifier(random_state=42, min_samples_leaf=1, n_estimators=10)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effac5a8790>\n"
+      "INFO  2024-03-18 19:58:52,939 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, modelConstructor=RandomForestClassifier(random_state=42, min_samples_leaf=1, n_estimators=10)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfded82b50>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,127 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:52,940 sensai.vector_model:fit - Fitting SkLearnRandomForestVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:34,151 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
+      "DEBUG 2024-03-18 19:58:52,985 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:34,152 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
+      "INFO  2024-03-18 19:58:52,986 sensai.sklearn.sklearn_base:_fit_classifier - Fitting sklearn classifier of type RandomForestClassifier\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:36,908 sensai.vector_model:fit - Fitting completed in 2.78 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
+      "INFO  2024-03-18 19:58:55,860 sensai.vector_model:fit - Fitting completed in 2.92 seconds: SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:36,983 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]\n"
+      "INFO  2024-03-18 19:58:55,944 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,306 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named 'MLP' ...\n"
+      "INFO  2024-03-18 19:58:56,221 sensai.evaluation.eval_util:compare_models - Evaluating model 2/2 named 'MLP' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,307 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7eff4cd88880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=None, inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effac5a8790>\n"
+      "INFO  2024-03-18 19:58:56,223 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7ddf80988880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=None, inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfded82b50>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,308 sensai.vector_model:fit - Fitting MultiLayerPerceptronVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:58:56,224 sensai.vector_model:fit - Fitting MultiLayerPerceptronVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:37,316 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
+      "DEBUG 2024-03-18 19:58:56,230 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,482 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7eff4cd88880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7effab8fccb0>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]] with cuda=False\n"
+      "INFO  2024-03-18 19:58:56,368 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7ddf80988880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7ddfde8fa170>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]] with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,484 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
+      "INFO  2024-03-18 19:58:56,370 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,657 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
+      "INFO  2024-03-18 19:58:56,547 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,658 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
+      "INFO  2024-03-18 19:58:56,549 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,660 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7eff4cd88880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7effab8fccb0>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None]\n"
+      "INFO  2024-03-18 19:58:56,551 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7ddf80988880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7ddfde8fa170>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=None, totalEpochs=None]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,660 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 40480\n"
+      "INFO  2024-03-18 19:58:56,551 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 40480\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,661 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]]\n"
+      "INFO  2024-03-18 19:58:56,552 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True]]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,669 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
+      "INFO  2024-03-18 19:58:56,561 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:37,670 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
+      "INFO  2024-03-18 19:58:56,562 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:38,818 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  1.15s | train loss 1.4059 | validation NLL 0.7300 | best NLL 0.730044 from this epoch\n"
+      "INFO  2024-03-18 19:58:57,735 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  1.17s | train loss 1.4059 | validation NLL 0.7300 | best NLL 0.730044 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:39,950 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  1.12s | train loss 0.5021 | validation NLL 0.3806 | best NLL 0.380582 from this epoch\n"
+      "INFO  2024-03-18 19:58:58,930 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  1.19s | train loss 0.5021 | validation NLL 0.3806 | best NLL 0.380582 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:41,111 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  1.15s | train loss 0.3138 | validation NLL 0.2847 | best NLL 0.284687 from this epoch\n"
+      "INFO  2024-03-18 19:58:59,967 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  1.03s | train loss 0.3138 | validation NLL 0.2847 | best NLL 0.284687 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:42,270 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  1.15s | train loss 0.2409 | validation NLL 0.2393 | best NLL 0.239259 from this epoch\n"
+      "INFO  2024-03-18 19:59:01,003 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  1.03s | train loss 0.2409 | validation NLL 0.2393 | best NLL 0.239259 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:43,440 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  1.16s | train loss 0.1981 | validation NLL 0.2081 | best NLL 0.208118 from this epoch\n"
+      "INFO  2024-03-18 19:59:02,039 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  1.03s | train loss 0.1981 | validation NLL 0.2081 | best NLL 0.208118 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:44,441 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  0.99s | train loss 0.1676 | validation NLL 0.1872 | best NLL 0.187202 from this epoch\n"
+      "INFO  2024-03-18 19:59:03,075 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  1.03s | train loss 0.1676 | validation NLL 0.1872 | best NLL 0.187202 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:45,450 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  1.00s | train loss 0.1450 | validation NLL 0.1697 | best NLL 0.169709 from this epoch\n"
+      "INFO  2024-03-18 19:59:04,110 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  1.03s | train loss 0.1450 | validation NLL 0.1697 | best NLL 0.169709 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:46,585 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  1.13s | train loss 0.1274 | validation NLL 0.1593 | best NLL 0.159322 from this epoch\n"
+      "INFO  2024-03-18 19:59:05,149 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  1.03s | train loss 0.1274 | validation NLL 0.1593 | best NLL 0.159322 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:47,590 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  1.00s | train loss 0.1131 | validation NLL 0.1509 | best NLL 0.150902 from this epoch\n"
+      "INFO  2024-03-18 19:59:06,184 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  1.03s | train loss 0.1131 | validation NLL 0.1509 | best NLL 0.150902 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:48,604 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  10/1000 completed in  1.01s | train loss 0.1013 | validation NLL 0.1440 | best NLL 0.144011 from this epoch\n"
+      "INFO  2024-03-18 19:59:07,215 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  10/1000 completed in  1.02s | train loss 0.1013 | validation NLL 0.1440 | best NLL 0.144011 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:49,727 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  11/1000 completed in  1.11s | train loss 0.0906 | validation NLL 0.1381 | best NLL 0.138148 from this epoch\n"
+      "INFO  2024-03-18 19:59:08,244 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  11/1000 completed in  1.02s | train loss 0.0906 | validation NLL 0.1381 | best NLL 0.138148 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:50,848 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  12/1000 completed in  1.11s | train loss 0.0816 | validation NLL 0.1334 | best NLL 0.133373 from this epoch\n"
+      "INFO  2024-03-18 19:59:09,276 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  12/1000 completed in  1.02s | train loss 0.0816 | validation NLL 0.1334 | best NLL 0.133373 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:51,970 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  13/1000 completed in  1.12s | train loss 0.0739 | validation NLL 0.1315 | best NLL 0.131459 from this epoch\n"
+      "INFO  2024-03-18 19:59:10,451 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  13/1000 completed in  1.17s | train loss 0.0739 | validation NLL 0.1315 | best NLL 0.131459 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:53,009 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  14/1000 completed in  1.03s | train loss 0.0667 | validation NLL 0.1281 | best NLL 0.128110 from this epoch\n"
+      "INFO  2024-03-18 19:59:11,623 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  14/1000 completed in  1.16s | train loss 0.0667 | validation NLL 0.1281 | best NLL 0.128110 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:54,140 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  15/1000 completed in  1.12s | train loss 0.0610 | validation NLL 0.1271 | best NLL 0.127124 from this epoch\n"
+      "INFO  2024-03-18 19:59:12,817 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  15/1000 completed in  1.19s | train loss 0.0610 | validation NLL 0.1271 | best NLL 0.127124 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:55,255 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  16/1000 completed in  1.11s | train loss 0.0553 | validation NLL 0.1222 | best NLL 0.122218 from this epoch\n"
+      "INFO  2024-03-18 19:59:13,995 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  16/1000 completed in  1.17s | train loss 0.0553 | validation NLL 0.1222 | best NLL 0.122218 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:56,375 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  17/1000 completed in  1.11s | train loss 0.0504 | validation NLL 0.1258 | best NLL 0.122218 from epoch 16\n"
+      "INFO  2024-03-18 19:59:15,149 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  17/1000 completed in  1.15s | train loss 0.0504 | validation NLL 0.1258 | best NLL 0.122218 from epoch 16\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,485 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  18/1000 completed in  1.11s | train loss 0.0461 | validation NLL 0.1233 | best NLL 0.122218 from epoch 16\n"
+      "INFO  2024-03-18 19:59:16,309 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch  18/1000 completed in  1.16s | train loss 0.0461 | validation NLL 0.1233 | best NLL 0.122218 from epoch 16\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,486 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 2 epochs without validation metric improvement\n"
+      "INFO  2024-03-18 19:59:16,310 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 2 epochs without validation metric improvement\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,487 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
+      "INFO  2024-03-18 19:59:16,311 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,487 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 16 with NLL 0.12221813999116421 on validation set\n"
+      "INFO  2024-03-18 19:59:16,311 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 16 with NLL 0.12221813999116421 on validation set\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,495 sensai.vector_model:fit - Fitting completed in 20.19 seconds: MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7eff4cd88880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7eff4cd88880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7effab8fccb0>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP]\n"
+      "INFO  2024-03-18 19:59:16,320 sensai.vector_model:fit - Fitting completed in 20.10 seconds: MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7ddf80988880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7ddf80988880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7ddfde8fa170>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:57,496 sensai.torch.torch_data:__init__ - Applying <sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7effae07b150> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 19:59:16,321 sensai.torch.torch_data:__init__ - Applying <sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7ddfdcd5c850> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,623 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]\n"
+      "INFO  2024-03-18 19:59:16,450 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:57,900 sensai.evaluation.eval_util:compare_models - Model comparison results:\n",
+      "INFO  2024-03-18 19:59:16,732 sensai.evaluation.eval_util:compare_models - Model comparison results:\n",
       "              accuracy  balancedAccuracy\n",
       "model_name                              \n",
       "RandomForest  0.946667          0.945917\n",
@@ -801,7 +801,7 @@
     {
      "data": {
       "text/plain": [
-       "<sensai.evaluation.eval_util.ModelComparisonData at 0x7effaa5af390>"
+       "<sensai.evaluation.eval_util.ModelComparisonData at 0x7ddfdbbdac10>"
       ]
      },
      "execution_count": 10,
@@ -883,10 +883,10 @@
    "execution_count": 11,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:59.582054Z",
-     "iopub.status.busy": "2024-03-02T11:32:59.581518Z",
-     "iopub.status.idle": "2024-03-02T11:32:59.604642Z",
-     "shell.execute_reply": "2024-03-02T11:32:59.604134Z"
+     "iopub.execute_input": "2024-03-18T19:59:18.467916Z",
+     "iopub.status.busy": "2024-03-18T19:59:18.467709Z",
+     "iopub.status.idle": "2024-03-18T19:59:18.490220Z",
+     "shell.execute_reply": "2024-03-18T19:59:18.489601Z"
     }
    },
    "outputs": [],
@@ -933,10 +933,10 @@
    "execution_count": 12,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:59.607499Z",
-     "iopub.status.busy": "2024-03-02T11:32:59.607073Z",
-     "iopub.status.idle": "2024-03-02T11:32:59.624847Z",
-     "shell.execute_reply": "2024-03-02T11:32:59.624334Z"
+     "iopub.execute_input": "2024-03-18T19:59:18.493489Z",
+     "iopub.status.busy": "2024-03-18T19:59:18.492990Z",
+     "iopub.status.idle": "2024-03-18T19:59:18.513108Z",
+     "shell.execute_reply": "2024-03-18T19:59:18.512354Z"
     }
    },
    "outputs": [],
@@ -961,10 +961,10 @@
    "execution_count": 13,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:59.627639Z",
-     "iopub.status.busy": "2024-03-02T11:32:59.627108Z",
-     "iopub.status.idle": "2024-03-02T11:32:59.649461Z",
-     "shell.execute_reply": "2024-03-02T11:32:59.648947Z"
+     "iopub.execute_input": "2024-03-18T19:59:18.516683Z",
+     "iopub.status.busy": "2024-03-18T19:59:18.516103Z",
+     "iopub.status.idle": "2024-03-18T19:59:18.539346Z",
+     "shell.execute_reply": "2024-03-18T19:59:18.538810Z"
     }
    },
    "outputs": [],
@@ -996,10 +996,10 @@
    "execution_count": 14,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:32:59.652180Z",
-     "iopub.status.busy": "2024-03-02T11:32:59.651796Z",
-     "iopub.status.idle": "2024-03-02T11:34:33.190349Z",
-     "shell.execute_reply": "2024-03-02T11:34:33.189673Z"
+     "iopub.execute_input": "2024-03-18T19:59:18.542079Z",
+     "iopub.status.busy": "2024-03-18T19:59:18.541845Z",
+     "iopub.status.idle": "2024-03-18T20:00:52.906075Z",
+     "shell.execute_reply": "2024-03-18T20:00:52.905360Z"
     }
    },
    "outputs": [
@@ -1007,203 +1007,203 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:59,879 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7effac5a8e50> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
+      "DEBUG 2024-03-18 19:59:18,801 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7ddfded82c90> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,880 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7effa8da9850>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effa91a2c50>\n"
+      "INFO  2024-03-18 19:59:18,802 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7ddfdbf90690>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdb7cc350>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,881 sensai.vector_model:fit - Fitting TorchVectorClassificationModel instance\n"
+      "INFO  2024-03-18 19:59:18,803 sensai.vector_model:fit - Fitting TorchVectorClassificationModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:32:59,910 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
+      "DEBUG 2024-03-18 19:59:18,825 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,911 sensai.torch.torch_base:_fit_classifier - Fitting <__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10> ...\n"
+      "INFO  2024-03-18 19:59:18,826 sensai.torch.torch_base:_fit_classifier - Fitting <__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0> ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,970 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False\n"
+      "INFO  2024-03-18 19:59:18,886 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:32:59,971 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
+      "INFO  2024-03-18 19:59:18,887 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,405 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
+      "INFO  2024-03-18 19:59:21,321 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,407 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
+      "INFO  2024-03-18 19:59:21,322 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,408 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None]\n"
+      "INFO  2024-03-18 19:59:21,323 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of TorchModelFromModule[cuda=False, bestEpoch=None, totalEpochs=None]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,408 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862\n"
+      "INFO  2024-03-18 19:59:21,323 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,409 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]\n"
+      "INFO  2024-03-18 19:59:21,324 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,420 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
+      "INFO  2024-03-18 19:59:21,335 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:02,421 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
+      "INFO  2024-03-18 19:59:21,336 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:12,225 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.80s | train loss 0.8318 | validation NLL 0.1962 | best NLL 0.196246 from this epoch\n"
+      "INFO  2024-03-18 19:59:31,168 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.83s | train loss 0.8318 | validation NLL 0.1962 | best NLL 0.196246 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:21,992 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.76s | train loss 0.1365 | validation NLL 0.1341 | best NLL 0.134100 from this epoch\n"
+      "INFO  2024-03-18 19:59:41,005 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.83s | train loss 0.1365 | validation NLL 0.1341 | best NLL 0.134100 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:31,736 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.73s | train loss 0.0724 | validation NLL 0.1154 | best NLL 0.115383 from this epoch\n"
+      "INFO  2024-03-18 19:59:50,892 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.88s | train loss 0.0724 | validation NLL 0.1154 | best NLL 0.115383 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:41,472 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.72s | train loss 0.0524 | validation NLL 0.1286 | best NLL 0.115383 from epoch 3\n"
+      "INFO  2024-03-18 20:00:00,774 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.87s | train loss 0.0524 | validation NLL 0.1286 | best NLL 0.115383 from epoch 3\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:33:51,268 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.80s | train loss 0.0418 | validation NLL 0.1073 | best NLL 0.107293 from this epoch\n"
+      "INFO  2024-03-18 20:00:10,651 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.88s | train loss 0.0418 | validation NLL 0.1073 | best NLL 0.107293 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:01,017 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.74s | train loss 0.0345 | validation NLL 0.0818 | best NLL 0.081762 from this epoch\n"
+      "INFO  2024-03-18 20:00:20,471 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.81s | train loss 0.0345 | validation NLL 0.0818 | best NLL 0.081762 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:10,726 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.70s | train loss 0.0293 | validation NLL 0.0953 | best NLL 0.081762 from epoch 6\n"
+      "INFO  2024-03-18 20:00:30,288 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.81s | train loss 0.0293 | validation NLL 0.0953 | best NLL 0.081762 from epoch 6\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:20,455 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.73s | train loss 0.0245 | validation NLL 0.1157 | best NLL 0.081762 from epoch 6\n"
+      "INFO  2024-03-18 20:00:40,140 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.85s | train loss 0.0245 | validation NLL 0.1157 | best NLL 0.081762 from epoch 6\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,224 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  9.77s | train loss 0.0209 | validation NLL 0.0996 | best NLL 0.081762 from epoch 6\n"
+      "INFO  2024-03-18 20:00:49,883 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   9/1000 completed in  9.74s | train loss 0.0209 | validation NLL 0.0996 | best NLL 0.081762 from epoch 6\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,225 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement\n"
+      "INFO  2024-03-18 20:00:49,885 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,225 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
+      "INFO  2024-03-18 20:00:49,885 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,226 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 6 with NLL 0.08176225980122884 on validation set\n"
+      "INFO  2024-03-18 20:00:49,886 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 6 with NLL 0.08176225980122884 on validation set\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:30,237 sensai.vector_model:fit - Fitting completed in 90.36 seconds: TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7effa8da9850>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN]\n"
+      "INFO  2024-03-18 20:00:49,897 sensai.vector_model:fit - Fitting completed in 91.09 seconds: TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7ddfdbf90690>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:34:30,238 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:00:49,897 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:32,035 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]\n"
+      "INFO  2024-03-18 20:00:51,654 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]\n"
      ]
     },
     {
@@ -1249,10 +1249,10 @@
    "execution_count": 15,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:34:33.193305Z",
-     "iopub.status.busy": "2024-03-02T11:34:33.193055Z",
-     "iopub.status.idle": "2024-03-02T11:34:33.219444Z",
-     "shell.execute_reply": "2024-03-02T11:34:33.218900Z"
+     "iopub.execute_input": "2024-03-18T20:00:52.908927Z",
+     "iopub.status.busy": "2024-03-18T20:00:52.908717Z",
+     "iopub.status.idle": "2024-03-18T20:00:52.933887Z",
+     "shell.execute_reply": "2024-03-18T20:00:52.933254Z"
     }
    },
    "outputs": [],
@@ -1320,10 +1320,10 @@
    "execution_count": 16,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:34:33.222420Z",
-     "iopub.status.busy": "2024-03-02T11:34:33.221880Z",
-     "iopub.status.idle": "2024-03-02T11:35:56.717610Z",
-     "shell.execute_reply": "2024-03-02T11:35:56.716883Z"
+     "iopub.execute_input": "2024-03-18T20:00:52.937077Z",
+     "iopub.status.busy": "2024-03-18T20:00:52.936661Z",
+     "iopub.status.idle": "2024-03-18T20:02:17.070894Z",
+     "shell.execute_reply": "2024-03-18T20:02:17.070115Z"
     }
    },
    "outputs": [
@@ -1331,196 +1331,196 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:34:33,459 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7effac5a8e50> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
+      "DEBUG 2024-03-18 20:00:53,167 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7ddfded82c90> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,460 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=139636510019152, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN'] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effa893c7d0>\n"
+      "INFO  2024-03-18 20:00:53,168 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=138400413109712, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=None, inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN'] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdb765610>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,461 sensai.vector_model:fit - Fitting CnnModel instance\n"
+      "INFO  2024-03-18 20:00:53,168 sensai.vector_model:fit - Fitting CnnModel instance\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:34:33,484 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
+      "DEBUG 2024-03-18 20:00:53,191 sensai.vector_model:fit - Fitting with outputs[1]=['label'], inputs[784]=[1x1/int64, 1x2/int64, 1x3/int64, 1x4/int64, 1x5/int64, 1x6/int64, 1x7/int64, 1x8/int64, 1x9/int64, 1x10/int64, 1x11/int64, 1x12/int64, 1x13/int64, 1x14/int64, 1x15/int64, 1x16/int64, 1x17/int64, 1x18/int64, 1x19/int64, 1x20/int64, 1x21/int64, 1x22/int64, 1x23/int64, 1x24/int64, 1x25/int64, 1x26/int64, 1x27/int64, 1x28/int64, 2x1/int64, 2x2/int64, 2x3/int64, 2x4/int64, 2x5/int64, 2x6/int64, 2x7/int64, 2x8/int64, 2x9/int64, 2x10/int64, 2x11/int64, 2x12/int64, 2x13/int64, 2x14/int64, 2x15/int64, 2x16/int64, 2x17/int64, 2x18/int64, 2x19/int64, 2x20/int64, 2x21/int64, 2x22/int64, 2x23/int64, 2x24/int64, 2x25/int64, 2x26/int64, 2x27/int64, 2x28/int64, 3x1/int64, 3x2/int64, 3x3/int64, 3x4/int64, 3x5/int64, 3x6/int64, 3x7/int64, 3x8/int64, 3x9/int64, 3x10/int64, 3x11/int64, 3x12/int64, 3x13/int64, 3x14/int64, 3x15/int64, 3x16/int64, 3x17/int64, 3x18/int64, 3x19/int64, 3x20/int64, 3x21/int64, 3x22/int64, 3x23/int64, 3x24/int64, 3x25/int64, 3x26/int64, 3x27/int64, 3x28/int64, 4x1/int64, 4x2/int64, 4x3/int64, 4x4/int64, 4x5/int64, 4x6/int64, 4x7/int64, 4x8/int64, 4x9/int64, 4x10/int64, 4x11/int64, 4x12/int64, 4x13/int64, 4x14/int64, 4x15/int64, 4x16/int64, 4x17/int64, 4x18/int64, 4x19/int64, 4x20/int64, 4x21/int64, 4x22/int64, 4x23/int64, 4x24/int64, 4x25/int64, 4x26/int64, 4x27/int64, 4x28/int64, 5x1/int64, 5x2/int64, 5x3/int64, 5x4/int64, 5x5/int64, 5x6/int64, 5x7/int64, 5x8/int64, 5x9/int64, 5x10/int64, 5x11/int64, 5x12/int64, 5x13/int64, 5x14/int64, 5x15/int64, 5x16/int64, 5x17/int64, 5x18/int64, 5x19/int64, 5x20/int64, 5x21/int64, 5x22/int64, 5x23/int64, 5x24/int64, 5x25/int64, 5x26/int64, 5x27/int64, 5x28/int64, 6x1/int64, 6x2/int64, 6x3/int64, 6x4/int64, 6x5/int64, 6x6/int64, 6x7/int64, 6x8/int64, 6x9/int64, 6x10/int64, 6x11/int64, 6x12/int64, 6x13/int64, 6x14/int64, 6x15/int64, 6x16/int64, 6x17/int64, 6x18/int64, 6x19/int64, 6x20/int64, 6x21/int64, 6x22/int64, 6x23/int64, 6x24/int64, 6x25/int64, 6x26/int64, 6x27/int64, 6x28/int64, 7x1/int64, 7x2/int64, 7x3/int64, 7x4/int64, 7x5/int64, 7x6/int64, 7x7/int64, 7x8/int64, 7x9/int64, 7x10/int64, 7x11/int64, 7x12/int64, 7x13/int64, 7x14/int64, 7x15/int64, 7x16/int64, 7x17/int64, 7x18/int64, 7x19/int64, 7x20/int64, 7x21/int64, 7x22/int64, 7x23/int64, 7x24/int64, 7x25/int64, 7x26/int64, 7x27/int64, 7x28/int64, 8x1/int64, 8x2/int64, 8x3/int64, 8x4/int64, 8x5/int64, 8x6/int64, 8x7/int64, 8x8/int64, 8x9/int64, 8x10/int64, 8x11/int64, 8x12/int64, 8x13/int64, 8x14/int64, 8x15/int64, 8x16/int64, 8x17/int64, 8x18/int64, 8x19/int64, 8x20/int64, 8x21/int64, 8x22/int64, 8x23/int64, 8x24/int64, 8x25/int64, 8x26/int64, 8x27/int64, 8x28/int64, 9x1/int64, 9x2/int64, 9x3/int64, 9x4/int64, 9x5/int64, 9x6/int64, 9x7/int64, 9x8/int64, 9x9/int64, 9x10/int64, 9x11/int64, 9x12/int64, 9x13/int64, 9x14/int64, 9x15/int64, 9x16/int64, 9x17/int64, 9x18/int64, 9x19/int64, 9x20/int64, 9x21/int64, 9x22/int64, 9x23/int64, 9x24/int64, 9x25/int64, 9x26/int64, 9x27/int64, 9x28/int64, 10x1/int64, 10x2/int64, 10x3/int64, 10x4/int64, 10x5/int64, 10x6/int64, 10x7/int64, 10x8/int64, 10x9/int64, 10x10/int64, 10x11/int64, 10x12/int64, 10x13/int64, 10x14/int64, 10x15/int64, 10x16/int64, 10x17/int64, 10x18/int64, 10x19/int64, 10x20/int64, 10x21/int64, 10x22/int64, 10x23/int64, 10x24/int64, 10x25/int64, 10x26/int64, 10x27/int64, 10x28/int64, 11x1/int64, 11x2/int64, 11x3/int64, 11x4/int64, 11x5/int64, 11x6/int64, 11x7/int64, 11x8/int64, 11x9/int64, 11x10/int64, 11x11/int64, 11x12/int64, 11x13/int64, 11x14/int64, 11x15/int64, 11x16/int64, 11x17/int64, 11x18/int64, 11x19/int64, 11x20/int64, 11x21/int64, 11x22/int64, 11x23/int64, 11x24/int64, 11x25/int64, 11x26/int64, 11x27/int64, 11x28/int64, 12x1/int64, 12x2/int64, 12x3/int64, 12x4/int64, 12x5/int64, 12x6/int64, 12x7/int64, 12x8/int64, 12x9/int64, 12x10/int64, 12x11/int64, 12x12/int64, 12x13/int64, 12x14/int64, 12x15/int64, 12x16/int64, 12x17/int64, 12x18/int64, 12x19/int64, 12x20/int64, 12x21/int64, 12x22/int64, 12x23/int64, 12x24/int64, 12x25/int64, 12x26/int64, 12x27/int64, 12x28/int64, 13x1/int64, 13x2/int64, 13x3/int64, 13x4/int64, 13x5/int64, 13x6/int64, 13x7/int64, 13x8/int64, 13x9/int64, 13x10/int64, 13x11/int64, 13x12/int64, 13x13/int64, 13x14/int64, 13x15/int64, 13x16/int64, 13x17/int64, 13x18/int64, 13x19/int64, 13x20/int64, 13x21/int64, 13x22/int64, 13x23/int64, 13x24/int64, 13x25/int64, 13x26/int64, 13x27/int64, 13x28/int64, 14x1/int64, 14x2/int64, 14x3/int64, 14x4/int64, 14x5/int64, 14x6/int64, 14x7/int64, 14x8/int64, 14x9/int64, 14x10/int64, 14x11/int64, 14x12/int64, 14x13/int64, 14x14/int64, 14x15/int64, 14x16/int64, 14x17/int64, 14x18/int64, 14x19/int64, 14x20/int64, 14x21/int64, 14x22/int64, 14x23/int64, 14x24/int64, 14x25/int64, 14x26/int64, 14x27/int64, 14x28/int64, 15x1/int64, 15x2/int64, 15x3/int64, 15x4/int64, 15x5/int64, 15x6/int64, 15x7/int64, 15x8/int64, 15x9/int64, 15x10/int64, 15x11/int64, 15x12/int64, 15x13/int64, 15x14/int64, 15x15/int64, 15x16/int64, 15x17/int64, 15x18/int64, 15x19/int64, 15x20/int64, 15x21/int64, 15x22/int64, 15x23/int64, 15x24/int64, 15x25/int64, 15x26/int64, 15x27/int64, 15x28/int64, 16x1/int64, 16x2/int64, 16x3/int64, 16x4/int64, 16x5/int64, 16x6/int64, 16x7/int64, 16x8/int64, 16x9/int64, 16x10/int64, 16x11/int64, 16x12/int64, 16x13/int64, 16x14/int64, 16x15/int64, 16x16/int64, 16x17/int64, 16x18/int64, 16x19/int64, 16x20/int64, 16x21/int64, 16x22/int64, 16x23/int64, 16x24/int64, 16x25/int64, 16x26/int64, 16x27/int64, 16x28/int64, 17x1/int64, 17x2/int64, 17x3/int64, 17x4/int64, 17x5/int64, 17x6/int64, 17x7/int64, 17x8/int64, 17x9/int64, 17x10/int64, 17x11/int64, 17x12/int64, 17x13/int64, 17x14/int64, 17x15/int64, 17x16/int64, 17x17/int64, 17x18/int64, 17x19/int64, 17x20/int64, 17x21/int64, 17x22/int64, 17x23/int64, 17x24/int64, 17x25/int64, 17x26/int64, 17x27/int64, 17x28/int64, 18x1/int64, 18x2/int64, 18x3/int64, 18x4/int64, 18x5/int64, 18x6/int64, 18x7/int64, 18x8/int64, 18x9/int64, 18x10/int64, 18x11/int64, 18x12/int64, 18x13/int64, 18x14/int64, 18x15/int64, 18x16/int64, 18x17/int64, 18x18/int64, 18x19/int64, 18x20/int64, 18x21/int64, 18x22/int64, 18x23/int64, 18x24/int64, 18x25/int64, 18x26/int64, 18x27/int64, 18x28/int64, 19x1/int64, 19x2/int64, 19x3/int64, 19x4/int64, 19x5/int64, 19x6/int64, 19x7/int64, 19x8/int64, 19x9/int64, 19x10/int64, 19x11/int64, 19x12/int64, 19x13/int64, 19x14/int64, 19x15/int64, 19x16/int64, 19x17/int64, 19x18/int64, 19x19/int64, 19x20/int64, 19x21/int64, 19x22/int64, 19x23/int64, 19x24/int64, 19x25/int64, 19x26/int64, 19x27/int64, 19x28/int64, 20x1/int64, 20x2/int64, 20x3/int64, 20x4/int64, 20x5/int64, 20x6/int64, 20x7/int64, 20x8/int64, 20x9/int64, 20x10/int64, 20x11/int64, 20x12/int64, 20x13/int64, 20x14/int64, 20x15/int64, 20x16/int64, 20x17/int64, 20x18/int64, 20x19/int64, 20x20/int64, 20x21/int64, 20x22/int64, 20x23/int64, 20x24/int64, 20x25/int64, 20x26/int64, 20x27/int64, 20x28/int64, 21x1/int64, 21x2/int64, 21x3/int64, 21x4/int64, 21x5/int64, 21x6/int64, 21x7/int64, 21x8/int64, 21x9/int64, 21x10/int64, 21x11/int64, 21x12/int64, 21x13/int64, 21x14/int64, 21x15/int64, 21x16/int64, 21x17/int64, 21x18/int64, 21x19/int64, 21x20/int64, 21x21/int64, 21x22/int64, 21x23/int64, 21x24/int64, 21x25/int64, 21x26/int64, 21x27/int64, 21x28/int64, 22x1/int64, 22x2/int64, 22x3/int64, 22x4/int64, 22x5/int64, 22x6/int64, 22x7/int64, 22x8/int64, 22x9/int64, 22x10/int64, 22x11/int64, 22x12/int64, 22x13/int64, 22x14/int64, 22x15/int64, 22x16/int64, 22x17/int64, 22x18/int64, 22x19/int64, 22x20/int64, 22x21/int64, 22x22/int64, 22x23/int64, 22x24/int64, 22x25/int64, 22x26/int64, 22x27/int64, 22x28/int64, 23x1/int64, 23x2/int64, 23x3/int64, 23x4/int64, 23x5/int64, 23x6/int64, 23x7/int64, 23x8/int64, 23x9/int64, 23x10/int64, 23x11/int64, 23x12/int64, 23x13/int64, 23x14/int64, 23x15/int64, 23x16/int64, 23x17/int64, 23x18/int64, 23x19/int64, 23x20/int64, 23x21/int64, 23x22/int64, 23x23/int64, 23x24/int64, 23x25/int64, 23x26/int64, 23x27/int64, 23x28/int64, 24x1/int64, 24x2/int64, 24x3/int64, 24x4/int64, 24x5/int64, 24x6/int64, 24x7/int64, 24x8/int64, 24x9/int64, 24x10/int64, 24x11/int64, 24x12/int64, 24x13/int64, 24x14/int64, 24x15/int64, 24x16/int64, 24x17/int64, 24x18/int64, 24x19/int64, 24x20/int64, 24x21/int64, 24x22/int64, 24x23/int64, 24x24/int64, 24x25/int64, 24x26/int64, 24x27/int64, 24x28/int64, 25x1/int64, 25x2/int64, 25x3/int64, 25x4/int64, 25x5/int64, 25x6/int64, 25x7/int64, 25x8/int64, 25x9/int64, 25x10/int64, 25x11/int64, 25x12/int64, 25x13/int64, 25x14/int64, 25x15/int64, 25x16/int64, 25x17/int64, 25x18/int64, 25x19/int64, 25x20/int64, 25x21/int64, 25x22/int64, 25x23/int64, 25x24/int64, 25x25/int64, 25x26/int64, 25x27/int64, 25x28/int64, 26x1/int64, 26x2/int64, 26x3/int64, 26x4/int64, 26x5/int64, 26x6/int64, 26x7/int64, 26x8/int64, 26x9/int64, 26x10/int64, 26x11/int64, 26x12/int64, 26x13/int64, 26x14/int64, 26x15/int64, 26x16/int64, 26x17/int64, 26x18/int64, 26x19/int64, 26x20/int64, 26x21/int64, 26x22/int64, 26x23/int64, 26x24/int64, 26x25/int64, 26x26/int64, 26x27/int64, 26x28/int64, 27x1/int64, 27x2/int64, 27x3/int64, 27x4/int64, 27x5/int64, 27x6/int64, 27x7/int64, 27x8/int64, 27x9/int64, 27x10/int64, 27x11/int64, 27x12/int64, 27x13/int64, 27x14/int64, 27x15/int64, 27x16/int64, 27x17/int64, 27x18/int64, 27x19/int64, 27x20/int64, 27x21/int64, 27x22/int64, 27x23/int64, 27x24/int64, 27x25/int64, 27x26/int64, 27x27/int64, 27x28/int64, 28x1/int64, 28x2/int64, 28x3/int64, 28x4/int64, 28x5/int64, 28x6/int64, 28x7/int64, 28x8/int64, 28x9/int64, 28x10/int64, 28x11/int64, 28x12/int64, 28x13/int64, 28x14/int64, 28x15/int64, 28x16/int64, 28x17/int64, 28x18/int64, 28x19/int64, 28x20/int64, 28x21/int64, 28x22/int64, 28x23/int64, 28x24/int64, 28x25/int64, 28x26/int64, 28x27/int64, 28x28/int64]; N=48000 data points\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,485 sensai.torch.torch_base:_fit_classifier - Fitting <__main__.ImageReshapingInputTensoriser object at 0x7effa893c450> ...\n"
+      "INFO  2024-03-18 20:00:53,192 sensai.torch.torch_base:_fit_classifier - Fitting <__main__.ImageReshapingInputTensoriser object at 0x7de00026d150> ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,544 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False\n"
+      "INFO  2024-03-18 20:00:53,252 sensai.torch.torch_opt.NNOptimiser:fit - Preparing parameter learning of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None] via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]] with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:33,545 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
+      "INFO  2024-03-18 20:00:53,254 sensai.torch.torch_opt.NNOptimiser:fit - Obtaining input/output training instances\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,981 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
+      "INFO  2024-03-18 20:00:55,687 sensai.torch.torch_opt.NNOptimiser:training_log - Data set 1/1: #train=36000, #validation=12000\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,981 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
+      "INFO  2024-03-18 20:00:55,688 sensai.torch.torch_opt.NNOptimiser:training_log - Number of validation sets: 1\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,986 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None]\n"
+      "INFO  2024-03-18 20:00:55,694 sensai.torch.torch_opt.NNOptimiser:fit - Learning parameters of CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=None, totalEpochs=None]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,987 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862\n"
+      "INFO  2024-03-18 20:00:55,695 sensai.torch.torch_opt.NNOptimiser:training_log - Number of parameters: 926862\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,988 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]\n"
+      "INFO  2024-03-18 20:00:55,695 sensai.torch.torch_opt.NNOptimiser:training_log - Starting training process via NNOptimiser[params=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True]]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,997 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
+      "INFO  2024-03-18 20:00:55,706 sensai.torch.torch_opt.NNOptimiser:fit - Begin training with cuda=False\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:35,998 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
+      "INFO  2024-03-18 20:00:55,706 sensai.torch.torch_opt.NNOptimiser:fit - Press Ctrl+C to end training early\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:45,805 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.81s | train loss 0.8259 | validation NLL 0.2525 | best NLL 0.252539 from this epoch\n"
+      "INFO  2024-03-18 20:01:05,468 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   1/1000 completed in  9.76s | train loss 0.8259 | validation NLL 0.2525 | best NLL 0.252539 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:34:55,478 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.66s | train loss 0.1533 | validation NLL 0.1433 | best NLL 0.143283 from this epoch\n"
+      "INFO  2024-03-18 20:01:15,233 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   2/1000 completed in  9.76s | train loss 0.1533 | validation NLL 0.1433 | best NLL 0.143283 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:05,184 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.70s | train loss 0.0881 | validation NLL 0.0999 | best NLL 0.099880 from this epoch\n"
+      "INFO  2024-03-18 20:01:25,017 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   3/1000 completed in  9.77s | train loss 0.0881 | validation NLL 0.0999 | best NLL 0.099880 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:14,892 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.70s | train loss 0.0596 | validation NLL 0.1221 | best NLL 0.099880 from epoch 3\n"
+      "INFO  2024-03-18 20:01:34,843 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   4/1000 completed in  9.81s | train loss 0.0596 | validation NLL 0.1221 | best NLL 0.099880 from epoch 3\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:24,593 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.70s | train loss 0.0452 | validation NLL 0.0962 | best NLL 0.096233 from this epoch\n"
+      "INFO  2024-03-18 20:01:44,656 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   5/1000 completed in  9.81s | train loss 0.0452 | validation NLL 0.0962 | best NLL 0.096233 from this epoch\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:34,295 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.69s | train loss 0.0380 | validation NLL 0.0974 | best NLL 0.096233 from epoch 5\n"
+      "INFO  2024-03-18 20:01:54,476 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   6/1000 completed in  9.81s | train loss 0.0380 | validation NLL 0.0974 | best NLL 0.096233 from epoch 5\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:44,062 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.77s | train loss 0.0294 | validation NLL 0.0986 | best NLL 0.096233 from epoch 5\n"
+      "INFO  2024-03-18 20:02:04,319 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   7/1000 completed in  9.84s | train loss 0.0294 | validation NLL 0.0986 | best NLL 0.096233 from epoch 5\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,811 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.75s | train loss 0.0223 | validation NLL 0.1068 | best NLL 0.096233 from epoch 5\n"
+      "INFO  2024-03-18 20:02:14,113 sensai.torch.torch_opt.NNOptimiser:training_log - Epoch   8/1000 completed in  9.79s | train loss 0.0223 | validation NLL 0.1068 | best NLL 0.096233 from epoch 5\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,811 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement\n"
+      "INFO  2024-03-18 20:02:14,114 sensai.torch.torch_opt.NNOptimiser:training_log - Stopping early: 3 epochs without validation metric improvement\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,812 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
+      "INFO  2024-03-18 20:02:14,115 sensai.torch.torch_opt.NNOptimiser:training_log - Training complete\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,812 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 5 with NLL 0.09623306624094645 on validation set\n"
+      "INFO  2024-03-18 20:02:14,115 sensai.torch.torch_opt.NNOptimiser:training_log - Best model is from epoch 5 with NLL 0.09623306624094645 on validation set\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:53,824 sensai.vector_model:fit - Fitting completed in 80.36 seconds: CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=139636510019152, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']\n"
+      "INFO  2024-03-18 20:02:14,128 sensai.vector_model:fit - Fitting completed in 80.96 seconds: CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=138400413109712, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:53,825 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7effa893c450> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:02:14,129 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7de00026d150> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:55,558 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]\n"
+      "INFO  2024-03-18 20:02:15,905 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]\n"
      ]
     },
     {
@@ -1565,10 +1565,10 @@
    "execution_count": 17,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:35:56.720902Z",
-     "iopub.status.busy": "2024-03-02T11:35:56.720419Z",
-     "iopub.status.idle": "2024-03-02T11:36:05.373404Z",
-     "shell.execute_reply": "2024-03-02T11:36:05.372689Z"
+     "iopub.execute_input": "2024-03-18T20:02:17.074519Z",
+     "iopub.status.busy": "2024-03-18T20:02:17.073896Z",
+     "iopub.status.idle": "2024-03-18T20:02:25.799276Z",
+     "shell.execute_reply": "2024-03-18T20:02:25.798551Z"
     }
    },
    "outputs": [
@@ -1576,119 +1576,119 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:56,737 sensai.evaluation.eval_util:compare_models - Evaluating model 1/4 named 'MLP' ...\n"
+      "INFO  2024-03-18 20:02:17,091 sensai.evaluation.eval_util:compare_models - Evaluating model 1/4 named 'MLP' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:56,952 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7effac5a8e50> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
+      "DEBUG 2024-03-18 20:02:17,314 sensai.evaluation.evaluator:__init__ - <sensai.data.DataSplitterFractional object at 0x7ddfded82c90> created split with 48000 (80.00%) and 12000 (20.00%) training and test data points respectively\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:56,953 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7eff4cd88880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7eff4cd88880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7effab8fccb0>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050>\n"
+      "INFO  2024-03-18 20:02:17,315 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating MultiLayerPerceptronVectorClassificationModel[hidden_dims=(50, 20), hid_activation_function=<built-in method sigmoid of type object at 0x7ddf80988880>, output_activation_function=ActivationFunction.LOG_SOFTMAX, input_dim=None, cuda=False, p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=Method[_create_torch_model], normalisationMode=NormalisationMode.MAX_ALL, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=54, optimiser_lr=0.001, shrinkage_clip=10.0, optimiser=adam, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=2, shuffle=True], model=MultiLayerPerceptronTorchModel[cuda=False, inputDim=784, outputDim=10, hidActivationFunction=<built-in method sigmoid of type object at 0x7ddf80988880>, outputActivationFunction=functools.partial(<function log_softmax at 0x7ddfde8fa170>, dim=1), hiddenDims=(50, 20), pDropout=0.0, overrideInputDim=None, bestEpoch=16, totalEpochs=18], inputTensoriser=None, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=MLP] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:56,954 sensai.torch.torch_data:__init__ - Applying <sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7effaa1f3f90> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:02:17,316 sensai.torch.torch_data:__init__ - Applying <sensai.torch.torch_data.TensoriserDataFrameFloatValuesMatrix object at 0x7ddfdb773bd0> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:57,085 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]\n"
+      "INFO  2024-03-18 20:02:17,450 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.96225, balancedAccuracy=0.9618968610010363, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:57,483 sensai.evaluation.eval_util:compare_models - Evaluating model 2/4 named 'CNN' ...\n"
+      "INFO  2024-03-18 20:02:17,828 sensai.evaluation.eval_util:compare_models - Evaluating model 2/4 named 'CNN' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:57,484 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7effa8da9850>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050>\n"
+      "INFO  2024-03-18 20:02:17,829 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating TorchVectorClassificationModel[featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=<sensai.torch.torch_base.TorchModelFactoryFromModule object at 0x7ddfdbf90690>, normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=TorchModelFromModule[cuda=False, bestEpoch=6, totalEpochs=9], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:57,485 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7effa8da9f10> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:02:17,830 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7ddfdbab98d0> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:59,266 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]\n"
+      "INFO  2024-03-18 20:02:19,580 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9784166666666667, balancedAccuracy=0.9782716826784611, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:59,524 sensai.evaluation.eval_util:compare_models - Evaluating model 3/4 named 'CNN'' ...\n"
+      "INFO  2024-03-18 20:02:19,842 sensai.evaluation.eval_util:compare_models - Evaluating model 3/4 named 'CNN'' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:35:59,526 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=139636510019152, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7effa893c450>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN'] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050>\n"
+      "INFO  2024-03-18 20:02:19,843 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating CnnModel[cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=functools.partial(<class '__main__.CnnModel.VectorTorchModel'>, CnnModel[id=138400413109712, cuda=False, output_activation_fn=ActivationFunction.LOG_SOFTMAX, kernel_size=5, num_conv=32, pooling_kernel_size=2, mlp_hidden_dims=(200, 20), p_dropout=0.0, featureGenerator=None, outputMode=ClassificationOutputMode.LOG_PROBABILITIES, torch_model_factory=..., normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN']), normalisationMode=NormalisationMode.NONE, nnOptimiserParams=NNOptimiserParams[epochs=1000, batch_size=1024, optimiser_lr=0.01, shrinkage_clip=10.0, optimiser=Optimiser.ADAMW, gpu=None, train_fraction=0.75, scaled_outputs=False, loss_evaluator=NNLossEvaluatorClassification[LossFunction.NLL], optimiser_args={}, use_shrinkage=True, early_stopping_epochs=3, shuffle=True], model=CnnModel.VectorTorchModel[cuda=False, inputDim=784, outputDim=10, bestEpoch=5, totalEpochs=8], inputTensoriser=<__main__.ImageReshapingInputTensoriser object at 0x7de00026d150>, outputTensoriser=None, torchDataSetProviderFactory=None, dataFrameSplitter=None, name=CNN'] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "DEBUG 2024-03-02 11:35:59,527 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7effa893c450> to data frame of length 12000 ...\n"
+      "DEBUG 2024-03-18 20:02:19,844 sensai.torch.torch_data:__init__ - Applying <__main__.ImageReshapingInputTensoriser object at 0x7de00026d150> to data frame of length 12000 ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,269 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]\n"
+      "INFO  2024-03-18 20:02:21,603 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.97775, balancedAccuracy=0.9776402722798222, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,531 sensai.evaluation.eval_util:compare_models - Evaluating model 4/4 named 'RandomForest' ...\n"
+      "INFO  2024-03-18 20:02:21,931 sensai.evaluation.eval_util:compare_models - Evaluating model 4/4 named 'RandomForest' ...\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,532 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7effaa913050>\n"
+      "INFO  2024-03-18 20:02:21,932 sensai.evaluation.eval_util:perform_simple_evaluation - Evaluating SkLearnRandomForestVectorClassificationModel[featureGenerator=None, fitArgs={}, useBalancedClassWeights=False, useLabelEncoding=False, name=RandomForest, model=RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None, criterion='gini', max_depth=None, max_features='auto', max_leaf_nodes=None, max_samples=None, min_impurity_decrease=0.0, min_impurity_split=None, min_samples_leaf=1, min_samples_split=2, min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, oob_score=False, random_state=42, verbose=0, warm_start=False)] via <sensai.evaluation.evaluator.VectorClassificationModelEvaluator object at 0x7ddfdc5d6190>\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,610 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]\n"
+      "INFO  2024-03-18 20:02:22,014 sensai.evaluation.eval_util:gather_results - Evaluation results for label: ClassificationEvalStats[accuracy=0.9466666666666667, balancedAccuracy=0.945916926388699, N=12000]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "INFO  2024-03-02 11:36:01,937 sensai.evaluation.eval_util:compare_models - Model comparison results:\n",
+      "INFO  2024-03-18 20:02:22,287 sensai.evaluation.eval_util:compare_models - Model comparison results:\n",
       "              accuracy  balancedAccuracy\n",
       "model_name                              \n",
       "MLP           0.962250          0.961897\n",
@@ -1865,10 +1865,10 @@
    "execution_count": 18,
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-03-02T11:36:05.376411Z",
-     "iopub.status.busy": "2024-03-02T11:36:05.375988Z",
-     "iopub.status.idle": "2024-03-02T11:36:06.158725Z",
-     "shell.execute_reply": "2024-03-02T11:36:06.158011Z"
+     "iopub.execute_input": "2024-03-18T20:02:25.802373Z",
+     "iopub.status.busy": "2024-03-18T20:02:25.801976Z",
+     "iopub.status.idle": "2024-03-18T20:02:26.598400Z",
+     "shell.execute_reply": "2024-03-18T20:02:26.597622Z"
     }
    },
    "outputs": [
diff --git a/docs/searchindex.js b/docs/searchindex.js
index ede4990c..4c129591 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["index","intro","neural_networks","sensai/catboost","sensai/clustering","sensai/clustering/clustering_base","sensai/clustering/greedy_clustering","sensai/clustering/sklearn_clustering","sensai/columngen","sensai/data","sensai/data_transformation","sensai/data_transformation/dft","sensai/data_transformation/sklearn_transformer","sensai/data_transformation/value_transformation","sensai/distance_metric","sensai/ensemble","sensai/ensemble/ensemble_base","sensai/ensemble/models","sensai/evaluation","sensai/evaluation/crossval","sensai/evaluation/eval_stats","sensai/evaluation/eval_stats/eval_stats_base","sensai/evaluation/eval_stats/eval_stats_classification","sensai/evaluation/eval_stats/eval_stats_clustering","sensai/evaluation/eval_stats/eval_stats_regression","sensai/evaluation/eval_util","sensai/evaluation/evaluator","sensai/evaluation/evaluator_clustering","sensai/evaluation/metric_computation","sensai/feature_importance","sensai/feature_selection","sensai/feature_selection/rfe","sensai/featuregen","sensai/featuregen/feature_generator","sensai/featuregen/feature_generator_registry","sensai/geoanalytics","sensai/geoanalytics/geo_clustering","sensai/geoanalytics/geo_coords","sensai/geoanalytics/geopandas","sensai/geoanalytics/geopandas/coordinate_clustering","sensai/geoanalytics/geopandas/coordinate_clustering_ground_truth","sensai/geoanalytics/geopandas/coordinates","sensai/geoanalytics/geopandas/geometry","sensai/geoanalytics/geopandas/graph","sensai/geoanalytics/local_coords","sensai/geoanalytics/map_tiles","sensai/hyperopt","sensai/index","sensai/lightgbm","sensai/local_search","sensai/minizinc","sensai/multi_model","sensai/naive_bayes","sensai/nearest_neighbors","sensai/normalisation","sensai/pytorch_lightning","sensai/pytorch_lightning/pl_models","sensai/sklearn","sensai/sklearn/sklearn_base","sensai/sklearn/sklearn_classification","sensai/sklearn/sklearn_regression","sensai/sklearn_quantile","sensai/tensor_model","sensai/tensorflow","sensai/tensorflow/tf_base","sensai/tensorflow/tf_mlp","sensai/torch","sensai/torch/torch_base","sensai/torch/torch_data","sensai/torch/torch_enums","sensai/torch/torch_eval_util","sensai/torch/torch_models","sensai/torch/torch_models/lstnet","sensai/torch/torch_models/lstnet/lstnet_models","sensai/torch/torch_models/lstnet/lstnet_modules","sensai/torch/torch_models/mlp","sensai/torch/torch_models/mlp/mlp_models","sensai/torch/torch_models/mlp/mlp_modules","sensai/torch/torch_models/residualffn","sensai/torch/torch_models/residualffn/residualffn_models","sensai/torch/torch_models/residualffn/residualffn_modules","sensai/torch/torch_models/seq","sensai/torch/torch_models/seq/seq_models","sensai/torch/torch_models/seq/seq_modules","sensai/torch/torch_modules","sensai/torch/torch_opt","sensai/torch/torchtext","sensai/tracking","sensai/tracking/azure_tracking","sensai/tracking/clearml_tracking","sensai/tracking/mlflow_tracking","sensai/tracking/tracking_base","sensai/util","sensai/util/aggregation","sensai/util/cache","sensai/util/cache_azure","sensai/util/cache_mysql","sensai/util/datastruct","sensai/util/deprecation","sensai/util/dtype","sensai/util/hash","sensai/util/helper","sensai/util/io","sensai/util/jscode","sensai/util/logging","sensai/util/math","sensai/util/multiprocessing","sensai/util/pandas","sensai/util/pickle","sensai/util/plot","sensai/util/profiling","sensai/util/sequences","sensai/util/string","sensai/util/test","sensai/util/time","sensai/util/typing","sensai/util/version","sensai/vector_model","sensai/vectoriser","sensai/xgboost"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":5,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,nbsphinx:4,sphinx:56},filenames:["index.rst","intro.ipynb","neural_networks.ipynb","sensai/catboost.rst","sensai/clustering.rst","sensai/clustering/clustering_base.rst","sensai/clustering/greedy_clustering.rst","sensai/clustering/sklearn_clustering.rst","sensai/columngen.rst","sensai/data.rst","sensai/data_transformation.rst","sensai/data_transformation/dft.rst","sensai/data_transformation/sklearn_transformer.rst","sensai/data_transformation/value_transformation.rst","sensai/distance_metric.rst","sensai/ensemble.rst","sensai/ensemble/ensemble_base.rst","sensai/ensemble/models.rst","sensai/evaluation.rst","sensai/evaluation/crossval.rst","sensai/evaluation/eval_stats.rst","sensai/evaluation/eval_stats/eval_stats_base.rst","sensai/evaluation/eval_stats/eval_stats_classification.rst","sensai/evaluation/eval_stats/eval_stats_clustering.rst","sensai/evaluation/eval_stats/eval_stats_regression.rst","sensai/evaluation/eval_util.rst","sensai/evaluation/evaluator.rst","sensai/evaluation/evaluator_clustering.rst","sensai/evaluation/metric_computation.rst","sensai/feature_importance.rst","sensai/feature_selection.rst","sensai/feature_selection/rfe.rst","sensai/featuregen.rst","sensai/featuregen/feature_generator.rst","sensai/featuregen/feature_generator_registry.rst","sensai/geoanalytics.rst","sensai/geoanalytics/geo_clustering.rst","sensai/geoanalytics/geo_coords.rst","sensai/geoanalytics/geopandas.rst","sensai/geoanalytics/geopandas/coordinate_clustering.rst","sensai/geoanalytics/geopandas/coordinate_clustering_ground_truth.rst","sensai/geoanalytics/geopandas/coordinates.rst","sensai/geoanalytics/geopandas/geometry.rst","sensai/geoanalytics/geopandas/graph.rst","sensai/geoanalytics/local_coords.rst","sensai/geoanalytics/map_tiles.rst","sensai/hyperopt.rst","sensai/index.rst","sensai/lightgbm.rst","sensai/local_search.rst","sensai/minizinc.rst","sensai/multi_model.rst","sensai/naive_bayes.rst","sensai/nearest_neighbors.rst","sensai/normalisation.rst","sensai/pytorch_lightning.rst","sensai/pytorch_lightning/pl_models.rst","sensai/sklearn.rst","sensai/sklearn/sklearn_base.rst","sensai/sklearn/sklearn_classification.rst","sensai/sklearn/sklearn_regression.rst","sensai/sklearn_quantile.rst","sensai/tensor_model.rst","sensai/tensorflow.rst","sensai/tensorflow/tf_base.rst","sensai/tensorflow/tf_mlp.rst","sensai/torch.rst","sensai/torch/torch_base.rst","sensai/torch/torch_data.rst","sensai/torch/torch_enums.rst","sensai/torch/torch_eval_util.rst","sensai/torch/torch_models.rst","sensai/torch/torch_models/lstnet.rst","sensai/torch/torch_models/lstnet/lstnet_models.rst","sensai/torch/torch_models/lstnet/lstnet_modules.rst","sensai/torch/torch_models/mlp.rst","sensai/torch/torch_models/mlp/mlp_models.rst","sensai/torch/torch_models/mlp/mlp_modules.rst","sensai/torch/torch_models/residualffn.rst","sensai/torch/torch_models/residualffn/residualffn_models.rst","sensai/torch/torch_models/residualffn/residualffn_modules.rst","sensai/torch/torch_models/seq.rst","sensai/torch/torch_models/seq/seq_models.rst","sensai/torch/torch_models/seq/seq_modules.rst","sensai/torch/torch_modules.rst","sensai/torch/torch_opt.rst","sensai/torch/torchtext.rst","sensai/tracking.rst","sensai/tracking/azure_tracking.rst","sensai/tracking/clearml_tracking.rst","sensai/tracking/mlflow_tracking.rst","sensai/tracking/tracking_base.rst","sensai/util.rst","sensai/util/aggregation.rst","sensai/util/cache.rst","sensai/util/cache_azure.rst","sensai/util/cache_mysql.rst","sensai/util/datastruct.rst","sensai/util/deprecation.rst","sensai/util/dtype.rst","sensai/util/hash.rst","sensai/util/helper.rst","sensai/util/io.rst","sensai/util/jscode.rst","sensai/util/logging.rst","sensai/util/math.rst","sensai/util/multiprocessing.rst","sensai/util/pandas.rst","sensai/util/pickle.rst","sensai/util/plot.rst","sensai/util/profiling.rst","sensai/util/sequences.rst","sensai/util/string.rst","sensai/util/test.rst","sensai/util/time.rst","sensai/util/typing.rst","sensai/util/version.rst","sensai/vector_model.rst","sensai/vectoriser.rst","sensai/xgboost.rst"],objects:{"":[[47,0,0,"-","sensai"]],"sensai.catboost":[[3,1,1,"","CatBoostVectorClassificationModel"],[3,1,1,"","CatBoostVectorRegressionModel"]],"sensai.catboost.CatBoostVectorClassificationModel":[[3,2,1,"","__init__"]],"sensai.catboost.CatBoostVectorRegressionModel":[[3,2,1,"","__init__"]],"sensai.clustering":[[5,0,0,"-","clustering_base"],[6,0,0,"-","greedy_clustering"],[7,0,0,"-","sklearn_clustering"]],"sensai.clustering.clustering_base":[[5,1,1,"","EuclideanClusterer"]],"sensai.clustering.clustering_base.EuclideanClusterer":[[5,1,1,"","Cluster"],[5,2,1,"","__init__"],[5,3,1,"","cluster_identifiers"],[5,2,1,"","clusters"],[5,3,1,"","datapoints"],[5,2,1,"","fit"],[5,2,1,"","get_cluster"],[5,3,1,"","is_fitted"],[5,3,1,"","labels"],[5,2,1,"","noise_cluster"],[5,3,1,"","num_clusters"],[5,2,1,"","summary_df"]],"sensai.clustering.clustering_base.EuclideanClusterer.Cluster":[[5,2,1,"","__init__"],[5,2,1,"","centroid"],[5,2,1,"","radius"],[5,2,1,"","summary_dict"]],"sensai.clustering.greedy_clustering":[[6,1,1,"","GreedyAgglomerativeClustering"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering":[[6,1,1,"","Cluster"],[6,1,1,"","ClusterMerge"],[6,1,1,"","MergeCandidateDeterminationStrategy"],[6,1,1,"","MergeCandidateDeterminationStrategyDefault"],[6,1,1,"","WrappedCluster"],[6,2,1,"","__init__"],[6,2,1,"","apply_clustering"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.Cluster":[[6,2,1,"","merge"],[6,2,1,"","merge_cost"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.ClusterMerge":[[6,2,1,"","__init__"],[6,2,1,"","apply"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.MergeCandidateDeterminationStrategy":[[6,2,1,"","__init__"],[6,2,1,"","iter_candidate_indices"],[6,2,1,"","set_clusterer"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.MergeCandidateDeterminationStrategyDefault":[[6,2,1,"","iter_candidate_indices"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.WrappedCluster":[[6,2,1,"","__init__"],[6,2,1,"","compute_merges"],[6,2,1,"","get_cluster_association"],[6,2,1,"","is_merged"],[6,2,1,"","remove_merges"]],"sensai.clustering.sklearn_clustering":[[7,1,1,"","SkLearnClustererProtocol"],[7,1,1,"","SkLearnEuclideanClusterer"]],"sensai.clustering.sklearn_clustering.SkLearnClustererProtocol":[[7,2,1,"","__init__"],[7,2,1,"","fit"],[7,4,1,"","labels_"]],"sensai.clustering.sklearn_clustering.SkLearnEuclideanClusterer":[[7,2,1,"","__init__"]],"sensai.columngen":[[8,1,1,"","ColumnGenerator"],[8,1,1,"","ColumnGeneratorCachedByIndex"],[8,1,1,"","IndexCachedColumnGenerator"]],"sensai.columngen.ColumnGenerator":[[8,2,1,"","__init__"],[8,2,1,"","generate_column"],[8,2,1,"","to_feature_generator"]],"sensai.columngen.ColumnGeneratorCachedByIndex":[[8,2,1,"","__init__"]],"sensai.columngen.IndexCachedColumnGenerator":[[8,2,1,"","__init__"]],"sensai.data":[[9,1,1,"","BaseInputOutputData"],[9,1,1,"","DataFrameSplitter"],[9,1,1,"","DataFrameSplitterColumnEquivalenceClass"],[9,1,1,"","DataFrameSplitterFractional"],[9,1,1,"","DataSplitter"],[9,1,1,"","DataSplitterFractional"],[9,1,1,"","DataSplitterFromDataFrameSplitter"],[9,1,1,"","DataSplitterFromSkLearnSplitter"],[9,1,1,"","DataSplitterStratifiedShuffleSplit"],[9,1,1,"","InputOutputArrays"],[9,1,1,"","InputOutputData"]],"sensai.data.BaseInputOutputData":[[9,2,1,"","__init__"],[9,2,1,"","filter_indices"]],"sensai.data.DataFrameSplitter":[[9,2,1,"","compute_split_indices"],[9,2,1,"","split"],[9,2,1,"","split_with_indices"]],"sensai.data.DataFrameSplitterColumnEquivalenceClass":[[9,2,1,"","__init__"],[9,2,1,"","compute_split_indices"]],"sensai.data.DataFrameSplitterFractional":[[9,2,1,"","__init__"],[9,2,1,"","compute_split_indices"]],"sensai.data.DataSplitter":[[9,2,1,"","split"]],"sensai.data.DataSplitterFractional":[[9,2,1,"","__init__"],[9,2,1,"","split"],[9,2,1,"","split_with_indices"]],"sensai.data.DataSplitterFromDataFrameSplitter":[[9,2,1,"","__init__"],[9,2,1,"","split"]],"sensai.data.DataSplitterFromSkLearnSplitter":[[9,2,1,"","__init__"],[9,2,1,"","split"]],"sensai.data.DataSplitterStratifiedShuffleSplit":[[9,2,1,"","__init__"],[9,2,1,"","is_applicable"]],"sensai.data.InputOutputArrays":[[9,2,1,"","__init__"],[9,2,1,"","filter_indices"],[9,2,1,"","to_torch_data_loader"]],"sensai.data.InputOutputData":[[9,2,1,"","__init__"],[9,2,1,"","compute_input_output_correlation"],[9,2,1,"","filter_index"],[9,2,1,"","filter_indices"],[9,2,1,"","from_data_frame"],[9,3,1,"","input_dim"],[9,3,1,"","output_dim"]],"sensai.data_transformation":[[11,0,0,"-","dft"],[12,0,0,"-","sklearn_transformer"],[13,0,0,"-","value_transformation"]],"sensai.data_transformation.dft":[[11,1,1,"","DFTAggregationOnColumn"],[11,1,1,"","DFTCastCategoricalColumns"],[11,1,1,"","DFTColumnFilter"],[11,1,1,"","DFTConditionalRowFilterOnColumn"],[11,1,1,"","DFTCountEntries"],[11,1,1,"","DFTDRowFilterOnIndex"],[11,1,1,"","DFTDropNA"],[11,1,1,"","DFTFillNA"],[11,1,1,"","DFTFromColumnGenerators"],[11,1,1,"","DFTFromFeatureGenerator"],[11,1,1,"","DFTInSetComparisonRowFilterOnColumn"],[11,1,1,"","DFTKeepColumns"],[11,1,1,"","DFTModifyColumn"],[11,1,1,"","DFTModifyColumnVectorized"],[11,1,1,"","DFTNormalisation"],[11,1,1,"","DFTNotInSetComparisonRowFilterOnColumn"],[11,1,1,"","DFTOneHotEncoder"],[11,1,1,"","DFTRenameColumns"],[11,1,1,"","DFTRoundFloats"],[11,1,1,"","DFTRowFilter"],[11,1,1,"","DFTSkLearnTransformer"],[11,1,1,"","DFTSortColumns"],[11,1,1,"","DFTVectorizedConditionalRowFilterOnColumn"],[11,1,1,"","DataFrameTransformer"],[11,1,1,"","DataFrameTransformerChain"],[11,1,1,"","InverseDataFrameTransformer"],[11,1,1,"","InvertibleDataFrameTransformer"],[11,1,1,"","RuleBasedDataFrameTransformer"]],"sensai.data_transformation.dft.DFTAggregationOnColumn":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTCastCategoricalColumns":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTColumnFilter":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTConditionalRowFilterOnColumn":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTCountEntries":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTDRowFilterOnIndex":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTDropNA":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTFillNA":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTFromColumnGenerators":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTFromFeatureGenerator":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTInSetComparisonRowFilterOnColumn":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTModifyColumn":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTModifyColumnVectorized":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTNormalisation":[[11,1,1,"","Rule"],[11,1,1,"","RuleTemplate"],[11,2,1,"","__init__"],[11,2,1,"","find_rule"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTNormalisation.Rule":[[11,2,1,"","__init__"],[11,2,1,"","matches"],[11,2,1,"","matching_columns"],[11,2,1,"","set_regex"]],"sensai.data_transformation.dft.DFTNormalisation.RuleTemplate":[[11,2,1,"","__init__"],[11,2,1,"","to_placeholder_rule"],[11,2,1,"","to_rule"]],"sensai.data_transformation.dft.DFTNotInSetComparisonRowFilterOnColumn":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTOneHotEncoder":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTRenameColumns":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTRoundFloats":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTRowFilter":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTSkLearnTransformer":[[11,2,1,"","__init__"],[11,2,1,"","apply_inverse"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTVectorizedConditionalRowFilterOnColumn":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DataFrameTransformer":[[11,2,1,"","__init__"],[11,2,1,"","apply"],[11,2,1,"","fit"],[11,2,1,"","fit_apply"],[11,2,1,"","get_name"],[11,2,1,"","info"],[11,2,1,"","is_fitted"],[11,2,1,"","set_name"],[11,2,1,"","to_feature_generator"],[11,2,1,"","with_name"]],"sensai.data_transformation.dft.DataFrameTransformerChain":[[11,2,1,"","__init__"],[11,2,1,"","append"],[11,2,1,"","find_first_transformer_by_type"],[11,2,1,"","get_names"],[11,2,1,"","info"],[11,2,1,"","is_fitted"]],"sensai.data_transformation.dft.InverseDataFrameTransformer":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.InvertibleDataFrameTransformer":[[11,2,1,"","apply_inverse"],[11,2,1,"","get_inverse"]],"sensai.data_transformation.dft.RuleBasedDataFrameTransformer":[[11,2,1,"","fit"],[11,2,1,"","is_fitted"]],"sensai.data_transformation.sklearn_transformer":[[12,1,1,"","ManualScaler"],[12,1,1,"","SkLearnTransformerFactoryFactory"],[12,1,1,"","SkLearnTransformerProtocol"],[12,5,1,"","to_2d_array"]],"sensai.data_transformation.sklearn_transformer.ManualScaler":[[12,2,1,"","__init__"],[12,2,1,"","fit"],[12,2,1,"","inverse_transform"],[12,2,1,"","transform"]],"sensai.data_transformation.sklearn_transformer.SkLearnTransformerFactoryFactory":[[12,2,1,"","ManualScaler"],[12,2,1,"","MaxAbsScaler"],[12,2,1,"","MinMaxScaler"],[12,2,1,"","RobustScaler"],[12,2,1,"","StandardScaler"]],"sensai.data_transformation.sklearn_transformer.SkLearnTransformerProtocol":[[12,2,1,"","__init__"],[12,2,1,"","fit"],[12,2,1,"","inverse_transform"],[12,2,1,"","transform"]],"sensai.data_transformation.value_transformation":[[13,1,1,"","ValueOneHotEncoder"]],"sensai.data_transformation.value_transformation.ValueOneHotEncoder":[[13,2,1,"","__init__"],[13,2,1,"","fit"],[13,2,1,"","transform"]],"sensai.distance_metric":[[14,1,1,"","CachedDistanceMetric"],[14,1,1,"","DistanceMatrixDFCache"],[14,1,1,"","DistanceMetric"],[14,1,1,"","EuclideanDistanceMetric"],[14,1,1,"","HellingerDistanceMetric"],[14,1,1,"","IdentityDistanceMetric"],[14,1,1,"","LinearCombinationDistanceMetric"],[14,1,1,"","RelativeBitwiseEqualityDistanceMetric"],[14,1,1,"","SingleColumnDistanceMetric"]],"sensai.distance_metric.CachedDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","distance"],[14,2,1,"","fill_cache"]],"sensai.distance_metric.DistanceMatrixDFCache":[[14,2,1,"","__init__"],[14,2,1,"","get"],[14,2,1,"","get_all_cached"],[14,2,1,"","num_unfilled_entries"],[14,2,1,"","save"],[14,2,1,"","set"],[14,2,1,"","shape"]],"sensai.distance_metric.DistanceMetric":[[14,2,1,"","distance"]],"sensai.distance_metric.EuclideanDistanceMetric":[[14,2,1,"","__init__"]],"sensai.distance_metric.HellingerDistanceMetric":[[14,2,1,"","__init__"]],"sensai.distance_metric.IdentityDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","distance"]],"sensai.distance_metric.LinearCombinationDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","distance"]],"sensai.distance_metric.RelativeBitwiseEqualityDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","check_input_value"]],"sensai.distance_metric.SingleColumnDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","distance"]],"sensai.ensemble":[[16,0,0,"-","ensemble_base"],[17,0,0,"-","models"]],"sensai.ensemble.ensemble_base":[[16,1,1,"","EnsembleClassificationVectorModel"],[16,1,1,"","EnsembleRegressionVectorModel"],[16,1,1,"","EnsembleVectorModel"]],"sensai.ensemble.ensemble_base.EnsembleClassificationVectorModel":[[16,2,1,"","is_regression_model"]],"sensai.ensemble.ensemble_base.EnsembleRegressionVectorModel":[[16,2,1,"","is_regression_model"]],"sensai.ensemble.ensemble_base.EnsembleVectorModel":[[16,2,1,"","__init__"],[16,2,1,"","aggregate_predictions"],[16,2,1,"","compute_all_predictions"]],"sensai.ensemble.models":[[17,1,1,"","AveragingVectorRegressionModel"]],"sensai.ensemble.models.AveragingVectorRegressionModel":[[17,2,1,"","__init__"],[17,2,1,"","aggregate_predictions"]],"sensai.evaluation":[[19,0,0,"-","crossval"],[20,0,0,"-","eval_stats"],[25,0,0,"-","eval_util"],[26,0,0,"-","evaluator"],[27,0,0,"-","evaluator_clustering"],[28,0,0,"-","metric_computation"]],"sensai.evaluation.crossval":[[19,1,1,"","CrossValidationSplitter"],[19,1,1,"","CrossValidationSplitterDefault"],[19,1,1,"","CrossValidationSplitterNested"],[19,1,1,"","VectorClassificationModelCrossValidationData"],[19,1,1,"","VectorClassificationModelCrossValidator"],[19,1,1,"","VectorModelCrossValidationData"],[19,1,1,"","VectorModelCrossValidator"],[19,1,1,"","VectorModelCrossValidatorParams"],[19,1,1,"","VectorRegressionModelCrossValidationData"],[19,1,1,"","VectorRegressionModelCrossValidator"]],"sensai.evaluation.crossval.CrossValidationSplitter":[[19,2,1,"","create_folds"]],"sensai.evaluation.crossval.CrossValidationSplitterDefault":[[19,2,1,"","__init__"],[19,2,1,"","create_folds"]],"sensai.evaluation.crossval.CrossValidationSplitterNested":[[19,2,1,"","__init__"],[19,2,1,"","create_folds"]],"sensai.evaluation.crossval.VectorModelCrossValidationData":[[19,2,1,"","__init__"],[19,2,1,"","get_eval_stats_collection"],[19,2,1,"","iter_input_output_ground_truth_tuples"],[19,3,1,"","model_name"],[19,2,1,"","track_metrics"]],"sensai.evaluation.crossval.VectorModelCrossValidator":[[19,2,1,"","__init__"],[19,2,1,"","create_metrics_dict_provider"],[19,2,1,"","eval_model"],[19,2,1,"","for_model"]],"sensai.evaluation.crossval.VectorModelCrossValidatorParams":[[19,2,1,"","__init__"]],"sensai.evaluation.eval_stats":[[21,0,0,"-","eval_stats_base"],[22,0,0,"-","eval_stats_classification"],[23,0,0,"-","eval_stats_clustering"],[24,0,0,"-","eval_stats_regression"]],"sensai.evaluation.eval_stats.eval_stats_base":[[21,1,1,"","EvalStats"],[21,1,1,"","EvalStatsCollection"],[21,1,1,"","EvalStatsPlot"],[21,1,1,"","Metric"],[21,1,1,"","PredictionEvalStats"],[21,5,1,"","mean_stats"]],"sensai.evaluation.eval_stats.eval_stats_base.EvalStats":[[21,2,1,"","__init__"],[21,2,1,"","add_metric"],[21,2,1,"","compute_metric_value"],[21,2,1,"","get_all"],[21,2,1,"","metrics_dict"],[21,2,1,"","set_name"]],"sensai.evaluation.eval_stats.eval_stats_base.EvalStatsCollection":[[21,2,1,"","__init__"],[21,2,1,"","agg_metrics_dict"],[21,2,1,"","get_combined_eval_stats"],[21,2,1,"","get_global_stats"],[21,2,1,"","get_metric_by_name"],[21,2,1,"","get_metric_names"],[21,2,1,"","get_metrics"],[21,2,1,"","get_values"],[21,2,1,"","has_metric"],[21,2,1,"","mean_metrics_dict"],[21,2,1,"","plot_distribution"],[21,2,1,"","plot_heat_map"],[21,2,1,"","plot_scatter"],[21,2,1,"","to_data_frame"]],"sensai.evaluation.eval_stats.eval_stats_base.EvalStatsPlot":[[21,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_base.Metric":[[21,2,1,"","__init__"],[21,2,1,"","compute_value_for_eval_stats"],[21,2,1,"","get_paired_metrics"],[21,2,1,"","has_finite_bounds"],[21,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_base.PredictionEvalStats":[[21,2,1,"","__init__"],[21,2,1,"","add"],[21,2,1,"","add_all"]],"sensai.evaluation.eval_stats.eval_stats_classification":[[22,1,1,"","BinaryClassificationCounts"],[22,1,1,"","BinaryClassificationMetric"],[22,1,1,"","BinaryClassificationMetricF1Score"],[22,1,1,"","BinaryClassificationMetricPrecision"],[22,1,1,"","BinaryClassificationMetricPrecisionThreshold"],[22,1,1,"","BinaryClassificationMetricRecall"],[22,1,1,"","BinaryClassificationMetricRecallForPrecision"],[22,1,1,"","BinaryClassificationMetricRecallThreshold"],[22,1,1,"","BinaryClassificationProbabilityThresholdVariationData"],[22,1,1,"","ClassificationEvalStats"],[22,1,1,"","ClassificationEvalStatsCollection"],[22,1,1,"","ClassificationEvalStatsPlot"],[22,1,1,"","ClassificationEvalStatsPlotConfusionMatrix"],[22,1,1,"","ClassificationEvalStatsPlotPrecisionRecall"],[22,1,1,"","ClassificationEvalStatsPlotProbabilityThresholdCounts"],[22,1,1,"","ClassificationEvalStatsPlotProbabilityThresholdPrecisionRecall"],[22,1,1,"","ClassificationMetric"],[22,1,1,"","ClassificationMetricAccuracy"],[22,1,1,"","ClassificationMetricAccuracyMaxProbabilityBeyondThreshold"],[22,1,1,"","ClassificationMetricAccuracyWithoutLabels"],[22,1,1,"","ClassificationMetricBalancedAccuracy"],[22,1,1,"","ClassificationMetricGeometricMeanOfTrueClassProbability"],[22,1,1,"","ClassificationMetricRelFreqMaxProbabilityBeyondThreshold"],[22,1,1,"","ClassificationMetricTopNAccuracy"],[22,1,1,"","ConfusionMatrix"],[22,5,1,"","create_default_binary_classification_metrics"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationCounts":[[22,2,1,"","__init__"],[22,2,1,"","from_eval_stats"],[22,2,1,"","from_probability_threshold"],[22,2,1,"","get_f1"],[22,2,1,"","get_precision"],[22,2,1,"","get_recall"],[22,2,1,"","get_rel_freq_positive"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetric":[[22,2,1,"","__init__"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricF1Score":[[22,2,1,"","__init__"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricPrecision":[[22,2,1,"","__init__"],[22,2,1,"","get_paired_metrics"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricPrecisionThreshold":[[22,2,1,"","__init__"],[22,2,1,"","get_paired_metrics"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricRecall":[[22,2,1,"","__init__"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricRecallForPrecision":[[22,2,1,"","__init__"],[22,2,1,"","compute_value_for_eval_stats"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricRecallThreshold":[[22,2,1,"","__init__"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationProbabilityThresholdVariationData":[[22,2,1,"","__init__"],[22,2,1,"","plot_counts"],[22,2,1,"","plot_precision_recall"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStats":[[22,2,1,"","__init__"],[22,2,1,"","get_accuracy"],[22,2,1,"","get_binary_classification_probability_threshold_variation_data"],[22,2,1,"","get_confusion_matrix"],[22,2,1,"","get_misclassified_indices"],[22,2,1,"","metrics_dict"],[22,2,1,"","plot_confusion_matrix"],[22,2,1,"","plot_precision_recall_curve"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsCollection":[[22,2,1,"","__init__"],[22,2,1,"","get_combined_eval_stats"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsPlotConfusionMatrix":[[22,2,1,"","__init__"],[22,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsPlotPrecisionRecall":[[22,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsPlotProbabilityThresholdCounts":[[22,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsPlotProbabilityThresholdPrecisionRecall":[[22,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric":[[22,2,1,"","__init__"],[22,2,1,"","compute_value"],[22,2,1,"","compute_value_for_eval_stats"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricAccuracy":[[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricAccuracyMaxProbabilityBeyondThreshold":[[22,2,1,"","__init__"],[22,2,1,"","get_paired_metrics"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricAccuracyWithoutLabels":[[22,2,1,"","__init__"],[22,2,1,"","get_paired_metrics"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricBalancedAccuracy":[[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricGeometricMeanOfTrueClassProbability":[[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricRelFreqMaxProbabilityBeyondThreshold":[[22,2,1,"","__init__"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricTopNAccuracy":[[22,2,1,"","__init__"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ConfusionMatrix":[[22,2,1,"","__init__"],[22,2,1,"","plot"]],"sensai.evaluation.eval_stats.eval_stats_clustering":[[23,1,1,"","AdjustedMutualInfoScore"],[23,1,1,"","AdjustedRandScore"],[23,1,1,"","CalinskiHarabaszScore"],[23,1,1,"","ClusterLabelsEvalStats"],[23,1,1,"","ClusteringSupervisedEvalStats"],[23,1,1,"","ClusteringSupervisedMetric"],[23,1,1,"","ClusteringUnsupervisedEvalStats"],[23,1,1,"","ClusteringUnsupervisedMetric"],[23,1,1,"","DaviesBouldinScore"],[23,1,1,"","FowlkesMallowsScore"],[23,1,1,"","RemovedCommonNoiseSupervisedMetric"],[23,1,1,"","RemovedNoiseUnsupervisedMetric"],[23,1,1,"","SilhouetteScore"],[23,1,1,"","VMeasureScore"]],"sensai.evaluation.eval_stats.eval_stats_clustering.AdjustedMutualInfoScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.AdjustedRandScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.CalinskiHarabaszScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusterLabelsEvalStats":[[23,4,1,"","AV_SIZE"],[23,4,1,"","MAX_SIZE"],[23,4,1,"","MEDIAN_SIZE"],[23,4,1,"","MIN_SIZE"],[23,4,1,"","NOISE_SIZE"],[23,4,1,"","NUM_CLUSTERS"],[23,4,1,"","STDDEV_SIZE"],[23,2,1,"","__init__"],[23,2,1,"","get_distribution_summary"],[23,2,1,"","metrics_dict"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusteringSupervisedEvalStats":[[23,2,1,"","__init__"],[23,4,1,"","clusterLabelsMask"],[23,2,1,"","from_model"],[23,2,1,"","labels_with_removed_common_noise"],[23,4,1,"","noiseLabelsMask"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusteringSupervisedMetric":[[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusteringUnsupervisedEvalStats":[[23,2,1,"","__init__"],[23,4,1,"","clusterLabelsMask"],[23,2,1,"","from_model"],[23,4,1,"","noiseLabelsMask"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusteringUnsupervisedMetric":[[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.DaviesBouldinScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.FowlkesMallowsScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.RemovedCommonNoiseSupervisedMetric":[[23,2,1,"","compute_value"],[23,2,1,"","compute_value_for_eval_stats"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.RemovedNoiseUnsupervisedMetric":[[23,2,1,"","compute_value"],[23,2,1,"","compute_value_for_eval_stats"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.SilhouetteScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.VMeasureScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression":[[24,1,1,"","RegressionEvalStats"],[24,1,1,"","RegressionEvalStatsCollection"],[24,1,1,"","RegressionEvalStatsPlot"],[24,1,1,"","RegressionEvalStatsPlotErrorDistribution"],[24,1,1,"","RegressionEvalStatsPlotHeatmapGroundTruthPredictions"],[24,1,1,"","RegressionEvalStatsPlotScatterGroundTruthPredictions"],[24,1,1,"","RegressionMetric"],[24,1,1,"","RegressionMetricMAE"],[24,1,1,"","RegressionMetricMSE"],[24,1,1,"","RegressionMetricMedianAE"],[24,1,1,"","RegressionMetricPCC"],[24,1,1,"","RegressionMetricR2"],[24,1,1,"","RegressionMetricRMSE"],[24,1,1,"","RegressionMetricRRSE"],[24,1,1,"","RegressionMetricStdDevAE"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStats":[[24,2,1,"","HEATMAP_COLORMAP_FACTORY"],[24,4,1,"","HEATMAP_DIAGONAL_COLOR"],[24,4,1,"","HEATMAP_ERROR_BOUNDARY_COLOR"],[24,4,1,"","HEATMAP_ERROR_BOUNDARY_VALUE"],[24,4,1,"","SCATTER_PLOT_POINT_COLOR"],[24,2,1,"","__init__"],[24,2,1,"","compute_mae"],[24,2,1,"","compute_metric_value"],[24,2,1,"","compute_mse"],[24,2,1,"","compute_pcc"],[24,2,1,"","compute_r2"],[24,2,1,"","compute_rmse"],[24,2,1,"","compute_rrse"],[24,2,1,"","compute_std_dev_ae"],[24,2,1,"","create_eval_stats_collection"],[24,2,1,"","plot_error_distribution"],[24,2,1,"","plot_heatmap_ground_truth_predictions"],[24,2,1,"","plot_scatter_ground_truth_predictions"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStatsCollection":[[24,2,1,"","__init__"],[24,2,1,"","get_combined_eval_stats"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStatsPlotErrorDistribution":[[24,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStatsPlotHeatmapGroundTruthPredictions":[[24,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStatsPlotScatterGroundTruthPredictions":[[24,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetric":[[24,2,1,"","compute_abs_errors"],[24,2,1,"","compute_errors"],[24,2,1,"","compute_value"],[24,2,1,"","compute_value_for_eval_stats"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricMAE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricMSE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricMedianAE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricPCC":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricR2":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricRMSE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricRRSE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricStdDevAE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_util":[[25,1,1,"","ClassificationEvalStatsPlotCollector"],[25,1,1,"","ClassificationModelEvaluation"],[25,1,1,"","ClassificationMultiDataModelComparisonData"],[25,1,1,"","EvalStatsPlotCollector"],[25,1,1,"","EvaluationResultCollector"],[25,1,1,"","ModelComparisonData"],[25,1,1,"","ModelComparisonVisitor"],[25,1,1,"","ModelComparisonVisitorAggregatedFeatureImportance"],[25,1,1,"","ModelEvaluation"],[25,1,1,"","MultiDataModelComparisonData"],[25,1,1,"","MultiDataModelEvaluation"],[25,1,1,"","RegressionEvalStatsPlotCollector"],[25,1,1,"","RegressionModelEvaluation"],[25,1,1,"","RegressionMultiDataModelComparisonData"],[25,5,1,"","create_evaluation_util"],[25,5,1,"","create_vector_model_cross_validator"],[25,5,1,"","create_vector_model_evaluator"],[25,5,1,"","eval_model_via_evaluator"]],"sensai.evaluation.eval_util.ClassificationEvalStatsPlotCollector":[[25,2,1,"","__init__"]],"sensai.evaluation.eval_util.ClassificationModelEvaluation":[[25,2,1,"","__init__"]],"sensai.evaluation.eval_util.ClassificationMultiDataModelComparisonData":[[25,2,1,"","get_eval_stats_collection"]],"sensai.evaluation.eval_util.EvalStatsPlotCollector":[[25,2,1,"","__init__"],[25,2,1,"","add_plot"],[25,2,1,"","create_plots"],[25,2,1,"","disable_plots"],[25,2,1,"","get_enabled_plots"]],"sensai.evaluation.eval_util.EvaluationResultCollector":[[25,2,1,"","__init__"],[25,2,1,"","add_data_frame_csv_file"],[25,2,1,"","add_figure"],[25,2,1,"","child"]],"sensai.evaluation.eval_util.ModelComparisonData":[[25,1,1,"","Result"],[25,2,1,"","__init__"],[25,2,1,"","get_best_model"],[25,2,1,"","get_best_model_name"]],"sensai.evaluation.eval_util.ModelComparisonData.Result":[[25,2,1,"","__init__"],[25,4,1,"","cross_validation_data"],[25,4,1,"","eval_data"],[25,2,1,"","iter_evaluation_data"]],"sensai.evaluation.eval_util.ModelComparisonVisitor":[[25,2,1,"","collect_results"],[25,2,1,"","visit"]],"sensai.evaluation.eval_util.ModelComparisonVisitorAggregatedFeatureImportance":[[25,2,1,"","__init__"],[25,2,1,"","collect_results"],[25,2,1,"","get_feature_importance"],[25,2,1,"","plot_feature_importance"],[25,2,1,"","visit"]],"sensai.evaluation.eval_util.ModelEvaluation":[[25,2,1,"","__init__"],[25,2,1,"","compare_models"],[25,2,1,"","compare_models_cross_validation"],[25,2,1,"","create_cross_validator"],[25,2,1,"","create_evaluator"],[25,2,1,"","create_plots"],[25,2,1,"","perform_cross_validation"],[25,2,1,"","perform_simple_evaluation"]],"sensai.evaluation.eval_util.MultiDataModelComparisonData":[[25,2,1,"","__init__"],[25,2,1,"","create_distribution_plots"],[25,2,1,"","get_eval_stats_collection"],[25,2,1,"","get_eval_stats_list"],[25,2,1,"","get_model_description"],[25,2,1,"","get_model_names"],[25,2,1,"","iter_model_results"]],"sensai.evaluation.eval_util.MultiDataModelEvaluation":[[25,2,1,"","__init__"],[25,2,1,"","compare_models"]],"sensai.evaluation.eval_util.RegressionEvalStatsPlotCollector":[[25,2,1,"","__init__"]],"sensai.evaluation.eval_util.RegressionModelEvaluation":[[25,2,1,"","__init__"]],"sensai.evaluation.eval_util.RegressionMultiDataModelComparisonData":[[25,2,1,"","get_eval_stats_collection"]],"sensai.evaluation.evaluator":[[26,1,1,"","ClassificationEvaluatorParams"],[26,1,1,"","EvaluatorParams"],[26,1,1,"","MetricsDictProvider"],[26,1,1,"","MetricsDictProviderFromFunction"],[26,1,1,"","RegressionEvaluatorParams"],[26,1,1,"","RuleBasedVectorClassificationModelEvaluator"],[26,1,1,"","RuleBasedVectorRegressionModelEvaluator"],[26,1,1,"","VectorClassificationModelEvaluationData"],[26,1,1,"","VectorClassificationModelEvaluator"],[26,1,1,"","VectorClassificationModelEvaluatorParams"],[26,1,1,"","VectorModelEvaluationData"],[26,1,1,"","VectorModelEvaluator"],[26,1,1,"","VectorRegressionModelEvaluationData"],[26,1,1,"","VectorRegressionModelEvaluator"],[26,1,1,"","VectorRegressionModelEvaluatorParams"]],"sensai.evaluation.evaluator.ClassificationEvaluatorParams":[[26,2,1,"","__init__"],[26,2,1,"","from_dict_or_instance"]],"sensai.evaluation.evaluator.EvaluatorParams":[[26,2,1,"","__init__"],[26,2,1,"","get_data_splitter"],[26,2,1,"","set_data_splitter"]],"sensai.evaluation.evaluator.MetricsDictProvider":[[26,2,1,"","compute_metrics"]],"sensai.evaluation.evaluator.MetricsDictProviderFromFunction":[[26,2,1,"","__init__"]],"sensai.evaluation.evaluator.RegressionEvaluatorParams":[[26,2,1,"","__init__"],[26,2,1,"","from_dict_or_instance"]],"sensai.evaluation.evaluator.RuleBasedVectorClassificationModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","eval_model"]],"sensai.evaluation.evaluator.RuleBasedVectorRegressionModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","eval_model"]],"sensai.evaluation.evaluator.VectorClassificationModelEvaluationData":[[26,2,1,"","get_misclassified_inputs_data_frame"],[26,2,1,"","get_misclassified_triples_pred_true_input"]],"sensai.evaluation.evaluator.VectorClassificationModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","compute_test_data_outputs"]],"sensai.evaluation.evaluator.VectorClassificationModelEvaluatorParams":[[26,2,1,"","__init__"]],"sensai.evaluation.evaluator.VectorModelEvaluationData":[[26,2,1,"","__init__"],[26,2,1,"","get_data_frame"],[26,2,1,"","get_eval_stats"],[26,3,1,"","input_data"],[26,2,1,"","iter_input_output_ground_truth_tuples"],[26,3,1,"","model_name"]],"sensai.evaluation.evaluator.VectorModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","create_metrics_dict_provider"],[26,2,1,"","eval_model"],[26,2,1,"","fit_model"],[26,2,1,"","set_tracked_experiment"]],"sensai.evaluation.evaluator.VectorRegressionModelEvaluationData":[[26,2,1,"","get_eval_stats_collection"]],"sensai.evaluation.evaluator.VectorRegressionModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","compute_test_data_outputs"]],"sensai.evaluation.evaluator.VectorRegressionModelEvaluatorParams":[[26,2,1,"","__init__"]],"sensai.evaluation.evaluator_clustering":[[27,1,1,"","ClusteringModelEvaluator"],[27,1,1,"","ClusteringModelSupervisedEvaluator"],[27,1,1,"","ClusteringModelUnsupervisedEvaluator"]],"sensai.evaluation.evaluator_clustering.ClusteringModelEvaluator":[[27,2,1,"","eval_model"]],"sensai.evaluation.evaluator_clustering.ClusteringModelSupervisedEvaluator":[[27,2,1,"","__init__"],[27,2,1,"","eval_model"]],"sensai.evaluation.evaluator_clustering.ClusteringModelUnsupervisedEvaluator":[[27,2,1,"","__init__"],[27,2,1,"","eval_model"]],"sensai.evaluation.metric_computation":[[28,1,1,"","MetricComputation"],[28,1,1,"","MetricComputationMultiData"],[28,1,1,"","MetricComputationResult"]],"sensai.evaluation.metric_computation.MetricComputation":[[28,2,1,"","__init__"],[28,2,1,"","compute_metric_value"]],"sensai.evaluation.metric_computation.MetricComputationMultiData":[[28,2,1,"","__init__"],[28,2,1,"","compute_metric_value"]],"sensai.evaluation.metric_computation.MetricComputationResult":[[28,2,1,"","__init__"],[28,4,1,"","metric_value"],[28,4,1,"","models"]],"sensai.feature_importance":[[29,1,1,"","AggregatedFeatureImportance"],[29,1,1,"","AggregatedPermutationFeatureImportance"],[29,1,1,"","FeatureImportance"],[29,1,1,"","FeatureImportanceProvider"],[29,5,1,"","compute_permutation_feature_importance_dict"],[29,5,1,"","plot_feature_importance"]],"sensai.feature_importance.AggregatedFeatureImportance":[[29,2,1,"","__init__"],[29,2,1,"","add"],[29,2,1,"","get_aggregated_feature_importance"],[29,2,1,"","get_aggregated_feature_importance_dict"]],"sensai.feature_importance.AggregatedPermutationFeatureImportance":[[29,2,1,"","__init__"],[29,2,1,"","add"],[29,2,1,"","add_cross_validation_data"],[29,2,1,"","get_feature_importance"]],"sensai.feature_importance.FeatureImportance":[[29,2,1,"","__init__"],[29,2,1,"","get_data_frame"],[29,2,1,"","get_feature_importance_dict"],[29,2,1,"","get_sorted_tuples"],[29,2,1,"","plot"]],"sensai.feature_importance.FeatureImportanceProvider":[[29,2,1,"","get_feature_importance"],[29,2,1,"","get_feature_importance_dict"],[29,2,1,"","get_feature_importances"]],"sensai.feature_selection":[[31,0,0,"-","rfe"]],"sensai.feature_selection.rfe":[[31,1,1,"","RFEResult"],[31,1,1,"","RFEStep"],[31,1,1,"","RecursiveFeatureElimination"],[31,1,1,"","RecursiveFeatureEliminationCV"]],"sensai.feature_selection.rfe.RFEResult":[[31,2,1,"","__init__"],[31,2,1,"","get_metric_values_array"],[31,2,1,"","get_num_features_array"],[31,2,1,"","get_selected_features"],[31,2,1,"","get_sorted_steps"],[31,2,1,"","plot_metric_values"]],"sensai.feature_selection.rfe.RFEStep":[[31,2,1,"","__init__"],[31,4,1,"","features"],[31,4,1,"","metric_value"]],"sensai.feature_selection.rfe.RecursiveFeatureElimination":[[31,2,1,"","__init__"],[31,2,1,"","run"]],"sensai.feature_selection.rfe.RecursiveFeatureEliminationCV":[[31,2,1,"","__init__"],[31,2,1,"","run"]],"sensai.featuregen":[[33,0,0,"-","feature_generator"],[34,0,0,"-","feature_generator_registry"]],"sensai.featuregen.feature_generator":[[33,1,1,"","ChainedFeatureGenerator"],[33,1,1,"","FeatureGenerator"],[33,1,1,"","FeatureGeneratorFlattenColumns"],[33,1,1,"","FeatureGeneratorFromColumnGenerator"],[33,1,1,"","FeatureGeneratorFromDFT"],[33,1,1,"","FeatureGeneratorFromNamedTuples"],[33,1,1,"","FeatureGeneratorFromVectorModel"],[33,1,1,"","FeatureGeneratorMapColumn"],[33,1,1,"","FeatureGeneratorMapColumnDict"],[33,1,1,"","FeatureGeneratorNAMarker"],[33,1,1,"","FeatureGeneratorTakeColumns"],[33,1,1,"","FeatureGeneratorTargetDistribution"],[33,1,1,"","MultiFeatureGenerator"],[33,1,1,"","RuleBasedFeatureGenerator"],[33,5,1,"","flattened_feature_generator"]],"sensai.featuregen.feature_generator.ChainedFeatureGenerator":[[33,2,1,"","__init__"],[33,2,1,"","fit_generate"],[33,2,1,"","info"],[33,2,1,"","is_fitted"]],"sensai.featuregen.feature_generator.FeatureGenerator":[[33,2,1,"","__init__"],[33,2,1,"","chain"],[33,2,1,"","concat"],[33,2,1,"","fit"],[33,2,1,"","fit_generate"],[33,2,1,"","flattened"],[33,2,1,"","generate"],[33,2,1,"","get_categorical_feature_name_regex"],[33,2,1,"","get_generated_column_names"],[33,2,1,"","get_name"],[33,2,1,"","get_names"],[33,2,1,"","get_normalisation_rules"],[33,2,1,"","info"],[33,2,1,"","is_categorical_feature"],[33,2,1,"","is_fitted"],[33,2,1,"","set_name"],[33,2,1,"","to_dft"]],"sensai.featuregen.feature_generator.FeatureGeneratorFlattenColumns":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.FeatureGeneratorFromColumnGenerator":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.FeatureGeneratorFromDFT":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorFromNamedTuples":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorFromVectorModel":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.FeatureGeneratorMapColumn":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorMapColumnDict":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorNAMarker":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorTakeColumns":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.FeatureGeneratorTargetDistribution":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.MultiFeatureGenerator":[[33,2,1,"","__init__"],[33,2,1,"","fit_generate"],[33,2,1,"","get_names"],[33,2,1,"","info"],[33,2,1,"","is_fitted"]],"sensai.featuregen.feature_generator.RuleBasedFeatureGenerator":[[33,2,1,"","fit"],[33,2,1,"","is_fitted"]],"sensai.featuregen.feature_generator_registry":[[34,1,1,"","FeatureCollector"],[34,1,1,"","FeatureGeneratorRegistry"]],"sensai.featuregen.feature_generator_registry.FeatureCollector":[[34,2,1,"","__init__"],[34,2,1,"","create_dft_normalisation"],[34,2,1,"","create_dft_one_hot_encoder"],[34,2,1,"","create_feature_transformer_normalisation"],[34,2,1,"","create_feature_transformer_one_hot_encoder"],[34,2,1,"","create_multi_feature_generator"],[34,2,1,"","get_categorical_feature_name_regex"],[34,2,1,"","get_multi_feature_generator"],[34,2,1,"","get_normalisation_rules"]],"sensai.featuregen.feature_generator_registry.FeatureGeneratorRegistry":[[34,2,1,"","__init__"],[34,3,1,"","available_features"],[34,2,1,"","collect_features"],[34,2,1,"","get_feature_generator"],[34,2,1,"","register_factory"]],"sensai.geoanalytics":[[36,0,0,"-","geo_clustering"],[37,0,0,"-","geo_coords"],[38,0,0,"-","geopandas"],[44,0,0,"-","local_coords"],[45,0,0,"-","map_tiles"]],"sensai.geoanalytics.geo_clustering":[[36,1,1,"","DBSCANGeoCoordClusterer"],[36,1,1,"","GeoCoordClusterer"],[36,1,1,"","GreedyAgglomerativeGeoCoordClusterer"],[36,1,1,"","SkLearnGeoCoordClusterer"]],"sensai.geoanalytics.geo_clustering.DBSCANGeoCoordClusterer":[[36,2,1,"","__init__"]],"sensai.geoanalytics.geo_clustering.GeoCoordClusterer":[[36,2,1,"","clusters_indices"],[36,2,1,"","fit_geo_coords"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer":[[36,1,1,"","Cluster"],[36,1,1,"","LocalPoint"],[36,1,1,"","Matrix"],[36,1,1,"","MergeCandidateDeterminationStrategy"],[36,2,1,"","__init__"],[36,2,1,"","clusters_indices"],[36,2,1,"","fit_geo_coords"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer.Cluster":[[36,2,1,"","__init__"],[36,2,1,"","merge"],[36,2,1,"","merge_cost"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer.LocalPoint":[[36,2,1,"","__init__"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer.Matrix":[[36,4,1,"","UNSET_VALUE"],[36,2,1,"","__init__"],[36,2,1,"","get"],[36,2,1,"","set"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer.MergeCandidateDeterminationStrategy":[[36,2,1,"","__init__"],[36,2,1,"","iter_candidate_indices"],[36,2,1,"","set_clusterer"]],"sensai.geoanalytics.geo_clustering.SkLearnGeoCoordClusterer":[[36,2,1,"","__init__"],[36,2,1,"","clusters_indices"],[36,2,1,"","clusters_local_points"],[36,2,1,"","fit_geo_coords"]],"sensai.geoanalytics.geo_coords":[[37,1,1,"","GeoCoord"],[37,1,1,"","GeoRect"],[37,1,1,"","GpsTracePoint"],[37,5,1,"","abs_angle_difference"],[37,5,1,"","approximate_squared_distance"],[37,5,1,"","closest_point_on_polyline"],[37,5,1,"","closest_point_on_segment"],[37,5,1,"","latitude_per_m"],[37,5,1,"","longitude_per_m"],[37,5,1,"","orientation"]],"sensai.geoanalytics.geo_coords.GeoCoord":[[37,2,1,"","__init__"],[37,2,1,"","distance_to"],[37,2,1,"","latlon"],[37,2,1,"","local_coords"],[37,2,1,"","mean_coord"],[37,2,1,"","squared_distance_to"]],"sensai.geoanalytics.geo_coords.GeoRect":[[37,2,1,"","__init__"],[37,2,1,"","from_circle"]],"sensai.geoanalytics.geo_coords.GpsTracePoint":[[37,2,1,"","__init__"]],"sensai.geoanalytics.geopandas":[[39,0,0,"-","coordinate_clustering"],[40,0,0,"-","coordinate_clustering_ground_truth"],[41,0,0,"-","coordinates"],[42,0,0,"-","geometry"],[43,0,0,"-","graph"]],"sensai.geoanalytics.geopandas.coordinate_clustering":[[39,1,1,"","CoordinateEuclideanClusterer"],[39,1,1,"","SkLearnCoordinateClustering"]],"sensai.geoanalytics.geopandas.coordinate_clustering.CoordinateEuclideanClusterer":[[39,1,1,"","Cluster"],[39,2,1,"","__init__"],[39,2,1,"","clusters"],[39,2,1,"","fit"],[39,2,1,"","get_cluster"],[39,2,1,"","noise_cluster"],[39,2,1,"","plot"],[39,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.coordinate_clustering.CoordinateEuclideanClusterer.Cluster":[[39,2,1,"","__init__"],[39,2,1,"","as_multipoint"],[39,2,1,"","load"],[39,2,1,"","save"],[39,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.coordinate_clustering.SkLearnCoordinateClustering":[[39,2,1,"","__init__"]],"sensai.geoanalytics.geopandas.coordinate_clustering_ground_truth":[[40,1,1,"","PolygonAnnotatedCoordinates"]],"sensai.geoanalytics.geopandas.coordinate_clustering_ground_truth.PolygonAnnotatedCoordinates":[[40,2,1,"","__init__"],[40,2,1,"","get_coordinates_labels"],[40,2,1,"","plot"],[40,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.coordinates":[[41,1,1,"","GeoDataFrameWrapper"],[41,5,1,"","extract_coordinates_array"],[41,5,1,"","validate_coordinates"]],"sensai.geoanalytics.geopandas.coordinates.GeoDataFrameWrapper":[[41,2,1,"","plot"],[41,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.geometry":[[42,5,1,"","alpha_shape"]],"sensai.geoanalytics.geopandas.graph":[[43,1,1,"","CoordinateSpanningTree"],[43,1,1,"","SpanningTree"],[43,5,1,"","delaunay_graph"]],"sensai.geoanalytics.geopandas.graph.CoordinateSpanningTree":[[43,2,1,"","__init__"],[43,2,1,"","multi_line_string"],[43,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.graph.SpanningTree":[[43,2,1,"","__init__"],[43,2,1,"","mean_edge_weight"],[43,2,1,"","num_edges"],[43,2,1,"","summary_dict"],[43,2,1,"","total_weight"]],"sensai.geoanalytics.local_coords":[[44,1,1,"","LocalCoordinateSystem"],[44,1,1,"","LocalHexagonalGrid"],[44,5,1,"","fix_polygon"]],"sensai.geoanalytics.local_coords.LocalCoordinateSystem":[[44,2,1,"","__init__"],[44,2,1,"","get_lat_lon"],[44,2,1,"","get_local_coords"]],"sensai.geoanalytics.local_coords.LocalHexagonalGrid":[[44,2,1,"","__init__"],[44,2,1,"","get_hexagon"],[44,2,1,"","get_hexagon_coord_span_for_bounding_box"],[44,2,1,"","get_hexagon_coords_for_point"],[44,2,1,"","get_max_hexagon_column"],[44,2,1,"","get_max_hexagon_row"],[44,2,1,"","get_min_hexagon_column"],[44,2,1,"","get_min_hexagon_row"]],"sensai.geoanalytics.map_tiles":[[45,1,1,"","MapTile"],[45,1,1,"","MapTiles"]],"sensai.geoanalytics.map_tiles.MapTile":[[45,2,1,"","__init__"]],"sensai.geoanalytics.map_tiles.MapTiles":[[45,2,1,"","__init__"],[45,2,1,"","get_tile"],[45,2,1,"","get_tile_coordinates"],[45,2,1,"","get_tiles_in_rect"],[45,2,1,"","iter_tile_coordinates_in_rect"]],"sensai.hyperopt":[[46,1,1,"","GridSearch"],[46,1,1,"","ParameterCombinationEquivalenceClassValueCache"],[46,1,1,"","ParameterCombinationSkipDecider"],[46,1,1,"","ParametersMetricsCollection"],[46,1,1,"","SAHyperOpt"],[46,5,1,"","iter_param_combinations"]],"sensai.hyperopt.GridSearch":[[46,1,1,"","Result"],[46,2,1,"","__init__"],[46,2,1,"","run"]],"sensai.hyperopt.GridSearch.Result":[[46,1,1,"","BestParams"],[46,2,1,"","__init__"],[46,2,1,"","get_best_params"]],"sensai.hyperopt.GridSearch.Result.BestParams":[[46,2,1,"","__init__"],[46,4,1,"","metric_name"],[46,4,1,"","metric_value"],[46,4,1,"","params"]],"sensai.hyperopt.ParameterCombinationEquivalenceClassValueCache":[[46,2,1,"","__init__"],[46,2,1,"","get"],[46,2,1,"","set"]],"sensai.hyperopt.ParameterCombinationSkipDecider":[[46,2,1,"","is_skipped"],[46,2,1,"","tell"]],"sensai.hyperopt.ParametersMetricsCollection":[[46,2,1,"","__init__"],[46,2,1,"","add_values"],[46,2,1,"","contains"],[46,2,1,"","get_data_frame"]],"sensai.hyperopt.SAHyperOpt":[[46,1,1,"","ParameterChangeOperator"],[46,1,1,"","State"],[46,2,1,"","__init__"],[46,2,1,"","get_simulated_annealing"],[46,2,1,"","run"]],"sensai.hyperopt.SAHyperOpt.ParameterChangeOperator":[[46,2,1,"","__init__"],[46,2,1,"","apply_state_change"],[46,2,1,"","choose_params"],[46,2,1,"","cost_delta"]],"sensai.hyperopt.SAHyperOpt.State":[[46,2,1,"","__init__"],[46,2,1,"","apply_state_representation"],[46,2,1,"","compute_cost_value"],[46,2,1,"","get_state_representation"]],"sensai.lightgbm":[[48,1,1,"","LightGBMVectorClassificationModel"],[48,1,1,"","LightGBMVectorRegressionModel"]],"sensai.lightgbm.LightGBMVectorClassificationModel":[[48,2,1,"","__init__"]],"sensai.lightgbm.LightGBMVectorRegressionModel":[[48,2,1,"","__init__"]],"sensai.local_search":[[49,1,1,"","ParallelTempering"],[49,1,1,"","SAChain"],[49,1,1,"","SACostValue"],[49,1,1,"","SACostValueNumeric"],[49,1,1,"","SAOperator"],[49,1,1,"","SAProbabilityFunction"],[49,1,1,"","SAProbabilityFunctionConstant"],[49,1,1,"","SAProbabilityFunctionLinear"],[49,1,1,"","SAProbabilityFunctionReverseSigmoid"],[49,1,1,"","SAProbabilitySchedule"],[49,1,1,"","SAState"],[49,1,1,"","SATemperatureSchedule"],[49,1,1,"","SATemperatureScheduleExponential"],[49,1,1,"","SATemperatureScheduleFixed"],[49,1,1,"","SATemperatureSchedulePower"],[49,1,1,"","SATemperatureScheduleReverseSigmoid"],[49,1,1,"","SATemperatureScheduleReverseSigmoidSymmetric"],[49,1,1,"","SimulatedAnnealing"],[49,5,1,"","reverse_sigmoid"]],"sensai.local_search.ParallelTempering":[[49,2,1,"","__init__"],[49,2,1,"","optimise"],[49,2,1,"","plot_cost_progression"]],"sensai.local_search.SAChain":[[49,2,1,"","__init__"],[49,2,1,"","apply_best_state"],[49,2,1,"","get_series"],[49,2,1,"","log_stats"],[49,2,1,"","plot_series"],[49,2,1,"","step"]],"sensai.local_search.SACostValue":[[49,2,1,"","add"],[49,2,1,"","value"]],"sensai.local_search.SACostValueNumeric":[[49,2,1,"","__init__"],[49,2,1,"","add"],[49,2,1,"","value"]],"sensai.local_search.SAOperator":[[49,2,1,"","__init__"],[49,2,1,"","apply"],[49,2,1,"","apply_cost_change"],[49,2,1,"","apply_state_change"],[49,2,1,"","choose_params"],[49,2,1,"","cost_delta"]],"sensai.local_search.SAProbabilityFunction":[[49,2,1,"","__init__"]],"sensai.local_search.SAProbabilityFunctionConstant":[[49,2,1,"","__init__"]],"sensai.local_search.SAProbabilityFunctionLinear":[[49,2,1,"","__init__"]],"sensai.local_search.SAProbabilityFunctionReverseSigmoid":[[49,2,1,"","__init__"]],"sensai.local_search.SAProbabilitySchedule":[[49,2,1,"","__init__"],[49,2,1,"","probability"],[49,2,1,"","temperature"]],"sensai.local_search.SAState":[[49,2,1,"","__init__"],[49,2,1,"","apply_state_representation"],[49,2,1,"","compute_cost_value"],[49,2,1,"","get_state_representation"]],"sensai.local_search.SATemperatureSchedule":[[49,2,1,"","probability"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureScheduleExponential":[[49,2,1,"","__init__"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureScheduleFixed":[[49,2,1,"","__init__"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureSchedulePower":[[49,2,1,"","__init__"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureScheduleReverseSigmoid":[[49,2,1,"","__init__"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureScheduleReverseSigmoidSymmetric":[[49,2,1,"","__init__"]],"sensai.local_search.SimulatedAnnealing":[[49,2,1,"","__init__"],[49,2,1,"","get_chain"],[49,2,1,"","optimise"]],"sensai.minizinc":[[50,1,1,"","CostScaler"],[50,1,1,"","MiniZincProblem"],[50,1,1,"","MiniZincSolver"],[50,5,1,"","array_to_mini_zinc"],[50,5,1,"","extract_1d_array_from_output"],[50,5,1,"","extract_multi_dim_array_from_output"]],"sensai.minizinc.CostScaler":[[50,2,1,"","__init__"],[50,2,1,"","original_value"],[50,2,1,"","scaled_float"],[50,2,1,"","scaled_int"]],"sensai.minizinc.MiniZincProblem":[[50,2,1,"","create_mini_zinc_file"],[50,2,1,"","get_mini_zinc_code"]],"sensai.minizinc.MiniZincSolver":[[50,2,1,"","__init__"],[50,2,1,"","get_last_solver_time_secs"],[50,2,1,"","solve_path"],[50,2,1,"","solve_problem"]],"sensai.multi_model":[[51,1,1,"","MultiVectorRegressionModel"]],"sensai.multi_model.MultiVectorRegressionModel":[[51,2,1,"","__init__"]],"sensai.naive_bayes":[[52,1,1,"","CategoricalNaiveBayesVectorClassificationModel"]],"sensai.naive_bayes.CategoricalNaiveBayesVectorClassificationModel":[[52,2,1,"","__init__"]],"sensai.nearest_neighbors":[[53,1,1,"","AbstractKnnFinder"],[53,1,1,"","AllNeighborsProvider"],[53,1,1,"","CachingKNearestNeighboursFinder"],[53,1,1,"","FeatureGeneratorNeighbors"],[53,1,1,"","KNearestNeighboursClassificationModel"],[53,1,1,"","KNearestNeighboursFinder"],[53,1,1,"","KNearestNeighboursRegressionModel"],[53,1,1,"","Neighbor"],[53,1,1,"","NeighborProvider"],[53,1,1,"","TimerangeNeighborsProvider"]],"sensai.nearest_neighbors.AbstractKnnFinder":[[53,2,1,"","find_neighbors"]],"sensai.nearest_neighbors.AllNeighborsProvider":[[53,2,1,"","__init__"],[53,2,1,"","iter_potential_neighbors"]],"sensai.nearest_neighbors.CachingKNearestNeighboursFinder":[[53,1,1,"","CachedSeriesDistanceMetric"],[53,1,1,"","DistanceMetricCache"],[53,2,1,"","__init__"],[53,2,1,"","find_neighbors"]],"sensai.nearest_neighbors.CachingKNearestNeighboursFinder.CachedSeriesDistanceMetric":[[53,2,1,"","__init__"],[53,2,1,"","get_distance_series"]],"sensai.nearest_neighbors.CachingKNearestNeighboursFinder.DistanceMetricCache":[[53,2,1,"","__init__"],[53,2,1,"","get_cached_metric"]],"sensai.nearest_neighbors.FeatureGeneratorNeighbors":[[53,2,1,"","__init__"]],"sensai.nearest_neighbors.KNearestNeighboursClassificationModel":[[53,2,1,"","__init__"],[53,2,1,"","find_neighbors"]],"sensai.nearest_neighbors.KNearestNeighboursFinder":[[53,2,1,"","__init__"],[53,2,1,"","find_neighbors"]],"sensai.nearest_neighbors.KNearestNeighboursRegressionModel":[[53,2,1,"","__init__"]],"sensai.nearest_neighbors.Neighbor":[[53,2,1,"","__init__"]],"sensai.nearest_neighbors.NeighborProvider":[[53,2,1,"","__init__"],[53,2,1,"","iter_potential_neighbors"]],"sensai.nearest_neighbors.TimerangeNeighborsProvider":[[53,2,1,"","__init__"],[53,2,1,"","iter_potential_neighbors"]],"sensai.normalisation":[[54,1,1,"","NormalisationMode"],[54,1,1,"","VectorDataScaler"]],"sensai.normalisation.NormalisationMode":[[54,4,1,"","MAX_ALL"],[54,4,1,"","MAX_BY_COLUMN"],[54,4,1,"","NONE"],[54,4,1,"","STANDARDISED"]],"sensai.normalisation.VectorDataScaler":[[54,2,1,"","__init__"],[54,2,1,"","get_denormalised_array"],[54,2,1,"","get_normalised_array"]],"sensai.pytorch_lightning":[[56,0,0,"-","pl_models"]],"sensai.pytorch_lightning.pl_models":[[56,1,1,"","PLTensorToScalarClassificationModel"],[56,1,1,"","PLTensorToScalarRegressionModel"],[56,1,1,"","PLTensorToTensorClassificationModel"],[56,1,1,"","PLTensorToTensorRegressionModel"],[56,1,1,"","PLWrappedModel"]],"sensai.pytorch_lightning.pl_models.PLTensorToScalarClassificationModel":[[56,2,1,"","__init__"]],"sensai.pytorch_lightning.pl_models.PLTensorToScalarRegressionModel":[[56,2,1,"","__init__"]],"sensai.pytorch_lightning.pl_models.PLTensorToTensorClassificationModel":[[56,2,1,"","__init__"]],"sensai.pytorch_lightning.pl_models.PLTensorToTensorRegressionModel":[[56,2,1,"","__init__"]],"sensai.pytorch_lightning.pl_models.PLWrappedModel":[[56,2,1,"","__init__"],[56,2,1,"","fit"],[56,2,1,"","predict"]],"sensai.sklearn":[[58,0,0,"-","sklearn_base"],[59,0,0,"-","sklearn_classification"],[60,0,0,"-","sklearn_regression"]],"sensai.sklearn.sklearn_base":[[58,1,1,"","AbstractSkLearnMultiDimVectorRegressionModel"],[58,1,1,"","AbstractSkLearnMultipleOneDimVectorRegressionModel"],[58,1,1,"","AbstractSkLearnVectorClassificationModel"],[58,1,1,"","AbstractSkLearnVectorRegressionModel"],[58,1,1,"","FeatureImportanceProviderSkLearnClassification"],[58,1,1,"","FeatureImportanceProviderSkLearnRegressionMultiDim"],[58,1,1,"","FeatureImportanceProviderSkLearnRegressionMultipleOneDim"],[58,5,1,"","create_sklearn_model"],[58,5,1,"","str_sklearn_model"]],"sensai.sklearn.sklearn_base.AbstractSkLearnMultiDimVectorRegressionModel":[[58,2,1,"","__init__"]],"sensai.sklearn.sklearn_base.AbstractSkLearnMultipleOneDimVectorRegressionModel":[[58,2,1,"","__init__"],[58,2,1,"","get_sklearn_model"]],"sensai.sklearn.sklearn_base.AbstractSkLearnVectorClassificationModel":[[58,2,1,"","__init__"],[58,2,1,"","get_params"],[58,2,1,"","set_params"],[58,2,1,"","with_sklearn_input_transformer"]],"sensai.sklearn.sklearn_base.AbstractSkLearnVectorRegressionModel":[[58,2,1,"","__init__"],[58,2,1,"","with_sklearn_input_transformer"],[58,2,1,"","with_sklearn_output_transformer"]],"sensai.sklearn.sklearn_base.FeatureImportanceProviderSkLearnClassification":[[58,2,1,"","get_feature_importance_dict"]],"sensai.sklearn.sklearn_base.FeatureImportanceProviderSkLearnRegressionMultiDim":[[58,2,1,"","get_feature_importance_dict"]],"sensai.sklearn.sklearn_base.FeatureImportanceProviderSkLearnRegressionMultipleOneDim":[[58,2,1,"","get_feature_importance_dict"]],"sensai.sklearn.sklearn_classification":[[59,1,1,"","SkLearnDecisionTreeVectorClassificationModel"],[59,1,1,"","SkLearnKNeighborsVectorClassificationModel"],[59,1,1,"","SkLearnLogisticRegressionVectorClassificationModel"],[59,1,1,"","SkLearnMLPVectorClassificationModel"],[59,1,1,"","SkLearnMultinomialNBVectorClassificationModel"],[59,1,1,"","SkLearnRandomForestVectorClassificationModel"],[59,1,1,"","SkLearnSVCVectorClassificationModel"]],"sensai.sklearn.sklearn_classification.SkLearnDecisionTreeVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnKNeighborsVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnLogisticRegressionVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnMLPVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnMultinomialNBVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnRandomForestVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnSVCVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression":[[60,1,1,"","SkLearnDecisionTreeVectorRegressionModel"],[60,1,1,"","SkLearnDummyVectorRegressionModel"],[60,1,1,"","SkLearnExtraTreesVectorRegressionModel"],[60,1,1,"","SkLearnGradientBoostingVectorRegressionModel"],[60,1,1,"","SkLearnKNeighborsVectorRegressionModel"],[60,1,1,"","SkLearnLinearLassoRegressionVectorRegressionModel"],[60,1,1,"","SkLearnLinearRegressionVectorRegressionModel"],[60,1,1,"","SkLearnLinearRidgeRegressionVectorRegressionModel"],[60,1,1,"","SkLearnLinearSVRVectorRegressionModel"],[60,1,1,"","SkLearnMultiLayerPerceptronVectorRegressionModel"],[60,1,1,"","SkLearnRandomForestVectorRegressionModel"],[60,1,1,"","SkLearnSVRVectorRegressionModel"]],"sensai.sklearn.sklearn_regression.SkLearnDecisionTreeVectorRegressionModel":[[60,2,1,"","__init__"],[60,2,1,"","plot"],[60,2,1,"","plot_graphviz_pdf"]],"sensai.sklearn.sklearn_regression.SkLearnDummyVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnExtraTreesVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnGradientBoostingVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnKNeighborsVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnLinearLassoRegressionVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnLinearRegressionVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnLinearRidgeRegressionVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnLinearSVRVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnMultiLayerPerceptronVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnRandomForestVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnSVRVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn_quantile":[[61,1,1,"","QuantileRegressionMetric"],[61,1,1,"","QuantileRegressionMetricAccuracyInConfidenceInterval"],[61,1,1,"","QuantileRegressionMetricConfidenceIntervalMeanSize"],[61,1,1,"","QuantileRegressionMetricConfidenceIntervalMedianSize"],[61,1,1,"","QuantileRegressionMetricRelFreqMaxSizeConfidenceInterval"],[61,1,1,"","RandomForestQuantileRegressorVectorRegressionModel"]],"sensai.sklearn_quantile.QuantileRegressionMetric":[[61,2,1,"","compute_confidence_intervals"],[61,4,1,"","name"]],"sensai.sklearn_quantile.QuantileRegressionMetricAccuracyInConfidenceInterval":[[61,2,1,"","compute_value"],[61,4,1,"","name"]],"sensai.sklearn_quantile.QuantileRegressionMetricConfidenceIntervalMeanSize":[[61,2,1,"","compute_value"],[61,4,1,"","name"]],"sensai.sklearn_quantile.QuantileRegressionMetricConfidenceIntervalMedianSize":[[61,2,1,"","compute_value"],[61,4,1,"","name"]],"sensai.sklearn_quantile.QuantileRegressionMetricRelFreqMaxSizeConfidenceInterval":[[61,2,1,"","__init__"],[61,2,1,"","compute_value"],[61,4,1,"","name"]],"sensai.sklearn_quantile.RandomForestQuantileRegressorVectorRegressionModel":[[61,2,1,"","__init__"],[61,2,1,"","predict_confidence_intervals"]],"sensai.tensor_model":[[62,6,1,"","InvalidShapeError"],[62,1,1,"","TensorModel"],[62,1,1,"","TensorToScalarClassificationModel"],[62,1,1,"","TensorToScalarRegressionModel"],[62,1,1,"","TensorToTensorClassificationModel"],[62,1,1,"","TensorToTensorRegressionModel"]],"sensai.tensor_model.TensorModel":[[62,2,1,"","__init__"],[62,2,1,"","get_model_input_shape"],[62,2,1,"","get_model_output_shape"]],"sensai.tensor_model.TensorToScalarClassificationModel":[[62,2,1,"","__init__"],[62,2,1,"","predict"]],"sensai.tensor_model.TensorToScalarRegressionModel":[[62,2,1,"","__init__"],[62,2,1,"","predict"]],"sensai.tensor_model.TensorToTensorClassificationModel":[[62,2,1,"","__init__"],[62,2,1,"","convert_class_probabilities_to_predictions"],[62,2,1,"","fit"],[62,2,1,"","get_model_output_shape"],[62,2,1,"","get_num_predicted_classes"],[62,2,1,"","is_regression_model"],[62,2,1,"","predict"],[62,2,1,"","predict_class_probabilities"]],"sensai.tensor_model.TensorToTensorRegressionModel":[[62,2,1,"","__init__"],[62,2,1,"","predict"]],"sensai.tensorflow":[[64,0,0,"-","tf_base"],[65,0,0,"-","tf_mlp"]],"sensai.tensorflow.tf_base":[[64,1,1,"","KerasVectorRegressionModel"],[64,1,1,"","TensorFlowSession"]],"sensai.tensorflow.tf_base.KerasVectorRegressionModel":[[64,2,1,"","__init__"]],"sensai.tensorflow.tf_base.TensorFlowSession":[[64,2,1,"","configure_session"],[64,4,1,"","session"],[64,2,1,"","set_keras_session"]],"sensai.tensorflow.tf_mlp":[[65,1,1,"","KerasMultiLayerPerceptronVectorRegressionModel"]],"sensai.tensorflow.tf_mlp.KerasMultiLayerPerceptronVectorRegressionModel":[[65,2,1,"","__init__"]],"sensai.torch":[[67,0,0,"-","torch_base"],[68,0,0,"-","torch_data"],[69,0,0,"-","torch_enums"],[70,0,0,"-","torch_eval_util"],[71,0,0,"-","torch_models"],[84,0,0,"-","torch_modules"],[85,0,0,"-","torch_opt"],[86,0,0,"-","torchtext"]],"sensai.torch.torch_base":[[67,1,1,"","MCDropoutCapableNNModule"],[67,1,1,"","OutputTensorToArrayConverter"],[67,1,1,"","TorchAutoregressiveResultHandler"],[67,1,1,"","TorchDataSetProviderFactory"],[67,1,1,"","TorchDataSetProviderFactoryClassificationDefault"],[67,1,1,"","TorchDataSetProviderFactoryRegressionDefault"],[67,1,1,"","TorchModel"],[67,1,1,"","TorchModelFactoryFromModule"],[67,1,1,"","TorchModelFittingStrategy"],[67,1,1,"","TorchModelFittingStrategyDefault"],[67,1,1,"","TorchModelFromModule"],[67,1,1,"","TorchModelFromModuleFactory"],[67,1,1,"","TorchVectorClassificationModel"],[67,1,1,"","TorchVectorRegressionModel"],[67,1,1,"","VectorTorchModel"]],"sensai.torch.torch_base.MCDropoutCapableNNModule":[[67,2,1,"","__init__"],[67,2,1,"","infer_mc_dropout"]],"sensai.torch.torch_base.OutputTensorToArrayConverter":[[67,2,1,"","convert"]],"sensai.torch.torch_base.TorchAutoregressiveResultHandler":[[67,2,1,"","clear_results"],[67,2,1,"","save_results"]],"sensai.torch.torch_base.TorchDataSetProviderFactory":[[67,2,1,"","create_data_set_provider"]],"sensai.torch.torch_base.TorchDataSetProviderFactoryClassificationDefault":[[67,2,1,"","__init__"],[67,2,1,"","create_data_set_provider"]],"sensai.torch.torch_base.TorchDataSetProviderFactoryRegressionDefault":[[67,2,1,"","__init__"],[67,2,1,"","create_data_set_provider"]],"sensai.torch.torch_base.TorchModel":[[67,2,1,"","__init__"],[67,2,1,"","apply"],[67,2,1,"","apply_scaled"],[67,3,1,"","best_epoch"],[67,2,1,"","create_torch_module"],[67,2,1,"","fit"],[67,2,1,"","get_module_bytes"],[67,2,1,"","get_torch_module"],[67,2,1,"","scaled_output"],[67,2,1,"","set_module_bytes"],[67,2,1,"","set_normalisation_check_threshold"],[67,2,1,"","set_torch_module"],[67,3,1,"","total_epochs"]],"sensai.torch.torch_base.TorchModelFactoryFromModule":[[67,2,1,"","__init__"]],"sensai.torch.torch_base.TorchModelFittingStrategy":[[67,2,1,"","fit"]],"sensai.torch.torch_base.TorchModelFittingStrategyDefault":[[67,2,1,"","fit"]],"sensai.torch.torch_base.TorchModelFromModule":[[67,2,1,"","__init__"],[67,2,1,"","create_torch_module"]],"sensai.torch.torch_base.TorchModelFromModuleFactory":[[67,2,1,"","__init__"],[67,2,1,"","create_torch_module"]],"sensai.torch.torch_base.TorchVectorClassificationModel":[[67,2,1,"","__init__"],[67,2,1,"","from_module"],[67,2,1,"","with_data_frame_splitter"],[67,2,1,"","with_input_tensoriser"],[67,2,1,"","with_normalisation_check_threshold"],[67,2,1,"","with_output_tensoriser"],[67,2,1,"","with_torch_data_set_provider_factory"]],"sensai.torch.torch_base.TorchVectorRegressionModel":[[67,2,1,"","__init__"],[67,2,1,"","from_module"],[67,2,1,"","with_autoregressive_result_handler"],[67,2,1,"","with_data_frame_splitter"],[67,2,1,"","with_input_tensoriser"],[67,2,1,"","with_normalisation_check_threshold"],[67,2,1,"","with_output_tensor_to_array_converter"],[67,2,1,"","with_output_tensoriser"],[67,2,1,"","with_torch_data_set_provider_factory"]],"sensai.torch.torch_base.VectorTorchModel":[[67,2,1,"","__init__"],[67,2,1,"","create_torch_module"],[67,2,1,"","create_torch_module_for_dims"]],"sensai.torch.torch_data":[[68,1,1,"","ClassificationVectorDataUtil"],[68,1,1,"","DataUtil"],[68,1,1,"","RuleBasedTensoriser"],[68,1,1,"","TensorScaler"],[68,1,1,"","TensorScalerCentreAndScale"],[68,1,1,"","TensorScalerFromDFTSkLearnTransformer"],[68,1,1,"","TensorScalerFromVectorDataScaler"],[68,1,1,"","TensorScalerIdentity"],[68,1,1,"","TensorTransformer"],[68,1,1,"","TensorTuple"],[68,1,1,"","Tensoriser"],[68,1,1,"","TensoriserClassLabelIndices"],[68,1,1,"","TensoriserDataFrameFloatValuesMatrix"],[68,1,1,"","TorchDataSet"],[68,1,1,"","TorchDataSetFromDataFrames"],[68,1,1,"","TorchDataSetFromDataFramesDynamicallyTensorised"],[68,1,1,"","TorchDataSetFromDataFramesPreTensorised"],[68,1,1,"","TorchDataSetFromTensors"],[68,1,1,"","TorchDataSetProvider"],[68,1,1,"","TorchDataSetProviderFromDataUtil"],[68,1,1,"","TorchDataSetProviderFromVectorDataUtil"],[68,1,1,"","VectorDataUtil"],[68,5,1,"","to_tensor"]],"sensai.torch.torch_data.ClassificationVectorDataUtil":[[68,2,1,"","__init__"],[68,2,1,"","model_output_dim"]],"sensai.torch.torch_data.DataUtil":[[68,2,1,"","get_input_tensor_scaler"],[68,2,1,"","get_output_tensor_scaler"],[68,2,1,"","input_dim"],[68,2,1,"","model_output_dim"],[68,2,1,"","split_into_tensors"]],"sensai.torch.torch_data.RuleBasedTensoriser":[[68,2,1,"","fit"]],"sensai.torch.torch_data.TensorScaler":[[68,2,1,"","cuda"],[68,2,1,"","denormalise"],[68,2,1,"","normalise"]],"sensai.torch.torch_data.TensorScalerCentreAndScale":[[68,2,1,"","__init__"],[68,2,1,"","cuda"],[68,2,1,"","denormalise"],[68,2,1,"","normalise"]],"sensai.torch.torch_data.TensorScalerFromDFTSkLearnTransformer":[[68,2,1,"","__init__"]],"sensai.torch.torch_data.TensorScalerFromVectorDataScaler":[[68,2,1,"","__init__"]],"sensai.torch.torch_data.TensorScalerIdentity":[[68,2,1,"","cuda"],[68,2,1,"","denormalise"],[68,2,1,"","normalise"]],"sensai.torch.torch_data.TensorTransformer":[[68,2,1,"","transform"]],"sensai.torch.torch_data.TensorTuple":[[68,2,1,"","__init__"],[68,2,1,"","concat"],[68,2,1,"","cuda"],[68,2,1,"","item"],[68,2,1,"","tuple"]],"sensai.torch.torch_data.Tensoriser":[[68,2,1,"","fit"],[68,2,1,"","tensorise"]],"sensai.torch.torch_data.TorchDataSet":[[68,2,1,"","iter_batches"],[68,2,1,"","size"]],"sensai.torch.torch_data.TorchDataSetFromDataFrames":[[68,2,1,"","__init__"],[68,2,1,"","iter_batches"],[68,2,1,"","size"]],"sensai.torch.torch_data.TorchDataSetFromDataFramesDynamicallyTensorised":[[68,2,1,"","__init__"],[68,2,1,"","iter_batches"],[68,2,1,"","size"]],"sensai.torch.torch_data.TorchDataSetFromDataFramesPreTensorised":[[68,2,1,"","__init__"]],"sensai.torch.torch_data.TorchDataSetFromTensors":[[68,2,1,"","__init__"],[68,2,1,"","iter_batches"],[68,2,1,"","size"]],"sensai.torch.torch_data.TorchDataSetProvider":[[68,2,1,"","__init__"],[68,2,1,"","get_input_dim"],[68,2,1,"","get_input_tensor_scaler"],[68,2,1,"","get_model_output_dim"],[68,2,1,"","get_output_tensor_scaler"],[68,2,1,"","provide_split"]],"sensai.torch.torch_data.TorchDataSetProviderFromDataUtil":[[68,2,1,"","__init__"],[68,2,1,"","provide_split"]],"sensai.torch.torch_data.TorchDataSetProviderFromVectorDataUtil":[[68,2,1,"","__init__"],[68,2,1,"","provide_split"]],"sensai.torch.torch_data.VectorDataUtil":[[68,2,1,"","__init__"],[68,2,1,"","get_input_tensor_scaler"],[68,2,1,"","get_output_tensor_scaler"],[68,2,1,"","input_dim"],[68,2,1,"","model_output_dim"],[68,2,1,"","output_dim"],[68,2,1,"","split_into_data_sets"],[68,2,1,"","split_into_tensors"]],"sensai.torch.torch_enums":[[69,1,1,"","ActivationFunction"],[69,1,1,"","ClassificationOutputMode"]],"sensai.torch.torch_enums.ActivationFunction":[[69,4,1,"","LOG_SOFTMAX"],[69,4,1,"","NONE"],[69,4,1,"","RELU"],[69,4,1,"","SIGMOID"],[69,4,1,"","SOFTMAX"],[69,4,1,"","TANH"],[69,2,1,"","from_name"],[69,2,1,"","get_name"],[69,2,1,"","get_torch_function"],[69,2,1,"","torch_function_from_any"]],"sensai.torch.torch_enums.ClassificationOutputMode":[[69,4,1,"","LOG_PROBABILITIES"],[69,4,1,"","PROBABILITIES"],[69,4,1,"","UNNORMALISED_LOG_PROBABILITIES"],[69,2,1,"","for_activation_fn"]],"sensai.torch.torch_eval_util":[[70,1,1,"","TorchVectorRegressionModelEvaluationUtil"]],"sensai.torch.torch_models":[[72,0,0,"-","lstnet"],[75,0,0,"-","mlp"],[78,0,0,"-","residualffn"],[81,0,0,"-","seq"]],"sensai.torch.torch_models.lstnet":[[73,0,0,"-","lstnet_models"],[74,0,0,"-","lstnet_modules"]],"sensai.torch.torch_models.lstnet.lstnet_models":[[73,1,1,"","LSTNetworkVectorClassificationModel"]],"sensai.torch.torch_models.lstnet.lstnet_models.LSTNetworkVectorClassificationModel":[[73,1,1,"","DataUtil"],[73,2,1,"","__init__"]],"sensai.torch.torch_models.lstnet.lstnet_models.LSTNetworkVectorClassificationModel.DataUtil":[[73,2,1,"","__init__"],[73,2,1,"","get_input_output_pair"],[73,2,1,"","get_input_tensor_scaler"],[73,2,1,"","get_output_tensor_scaler"],[73,2,1,"","input_dim"],[73,2,1,"","model_output_dim"],[73,2,1,"","split_into_tensors"]],"sensai.torch.torch_models.lstnet.lstnet_modules":[[74,1,1,"","LSTNetwork"]],"sensai.torch.torch_models.lstnet.lstnet_modules.LSTNetwork":[[74,1,1,"","Mode"],[74,2,1,"","__init__"],[74,2,1,"","compute_encoder_dim"],[74,2,1,"","forward"],[74,2,1,"","get_encoder_dim"]],"sensai.torch.torch_models.lstnet.lstnet_modules.LSTNetwork.Mode":[[74,4,1,"","CLASSIFICATION"],[74,4,1,"","ENCODER"],[74,4,1,"","REGRESSION"]],"sensai.torch.torch_models.mlp":[[76,0,0,"-","mlp_models"],[77,0,0,"-","mlp_modules"]],"sensai.torch.torch_models.mlp.mlp_models":[[76,1,1,"","MultiLayerPerceptronTorchModel"],[76,1,1,"","MultiLayerPerceptronVectorClassificationModel"],[76,1,1,"","MultiLayerPerceptronVectorRegressionModel"]],"sensai.torch.torch_models.mlp.mlp_models.MultiLayerPerceptronTorchModel":[[76,2,1,"","__init__"],[76,2,1,"","create_torch_module_for_dims"]],"sensai.torch.torch_models.mlp.mlp_models.MultiLayerPerceptronVectorClassificationModel":[[76,2,1,"","__init__"]],"sensai.torch.torch_models.mlp.mlp_models.MultiLayerPerceptronVectorRegressionModel":[[76,2,1,"","__init__"]],"sensai.torch.torch_models.mlp.mlp_modules":[[77,1,1,"","MultiLayerPerceptron"]],"sensai.torch.torch_models.mlp.mlp_modules.MultiLayerPerceptron":[[77,2,1,"","__init__"],[77,2,1,"","forward"]],"sensai.torch.torch_models.residualffn":[[79,0,0,"-","residualffn_models"],[80,0,0,"-","residualffn_modules"]],"sensai.torch.torch_models.residualffn.residualffn_models":[[79,1,1,"","ResidualFeedForwardNetworkTorchModel"],[79,1,1,"","ResidualFeedForwardNetworkVectorRegressionModel"]],"sensai.torch.torch_models.residualffn.residualffn_models.ResidualFeedForwardNetworkTorchModel":[[79,2,1,"","__init__"],[79,2,1,"","create_torch_module_for_dims"]],"sensai.torch.torch_models.residualffn.residualffn_models.ResidualFeedForwardNetworkVectorRegressionModel":[[79,2,1,"","__init__"]],"sensai.torch.torch_models.residualffn.residualffn_modules":[[80,1,1,"","ResidualFeedForwardNetwork"]],"sensai.torch.torch_models.residualffn.residualffn_modules.ResidualFeedForwardNetwork":[[80,2,1,"","__init__"],[80,2,1,"","forward"]],"sensai.torch.torch_models.seq":[[82,0,0,"-","seq_models"],[83,0,0,"-","seq_modules"]],"sensai.torch.torch_models.seq.seq_models":[[82,1,1,"","EncoderDecoderVectorRegressionModel"]],"sensai.torch.torch_models.seq.seq_models.EncoderDecoderVectorRegressionModel":[[82,1,1,"","EncoderDecoderModel"],[82,1,1,"","InputTensoriser"],[82,2,1,"","__init__"]],"sensai.torch.torch_models.seq.seq_models.EncoderDecoderVectorRegressionModel.EncoderDecoderModel":[[82,2,1,"","__init__"],[82,2,1,"","create_torch_module"]],"sensai.torch.torch_models.seq.seq_models.EncoderDecoderVectorRegressionModel.InputTensoriser":[[82,2,1,"","__init__"],[82,2,1,"","fit"]],"sensai.torch.torch_models.seq.seq_modules":[[83,1,1,"","DecoderFactory"],[83,1,1,"","DecoderProtocol"],[83,1,1,"","EncoderDecoderModule"],[83,1,1,"","EncoderFactory"],[83,1,1,"","EncoderProtocol"],[83,1,1,"","LSTNetworkEncoder"],[83,1,1,"","LSTNetworkEncoderFactory"],[83,1,1,"","LinearPredictorFactory"],[83,1,1,"","MLPPredictorFactory"],[83,1,1,"","PredictorFactory"],[83,1,1,"","PredictorProtocol"],[83,1,1,"","RnnEncoderFactory"],[83,1,1,"","RnnEncoderModule"],[83,1,1,"","SingleTargetDecoderFactory"],[83,1,1,"","SingleTargetDecoderModule"],[83,1,1,"","TargetSequenceDecoderFactory"],[83,1,1,"","TargetSequenceDecoderModule"]],"sensai.torch.torch_models.seq.seq_modules.DecoderFactory":[[83,2,1,"","create_decoder"]],"sensai.torch.torch_models.seq.seq_modules.DecoderProtocol":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.EncoderDecoderModule":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.EncoderFactory":[[83,2,1,"","create_encoder"]],"sensai.torch.torch_models.seq.seq_modules.EncoderProtocol":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.LSTNetworkEncoder":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.LSTNetworkEncoderFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_encoder"],[83,2,1,"","get_latent_dim"]],"sensai.torch.torch_models.seq.seq_modules.LinearPredictorFactory":[[83,2,1,"","create_predictor"]],"sensai.torch.torch_models.seq.seq_modules.MLPPredictorFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_predictor"]],"sensai.torch.torch_models.seq.seq_modules.PredictorFactory":[[83,2,1,"","create_predictor"]],"sensai.torch.torch_models.seq.seq_modules.PredictorProtocol":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.RnnEncoderFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_encoder"]],"sensai.torch.torch_models.seq.seq_modules.RnnEncoderModule":[[83,1,1,"","RnnType"],[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.RnnEncoderModule.RnnType":[[83,4,1,"","GRU"],[83,4,1,"","LSTM"]],"sensai.torch.torch_models.seq.seq_modules.SingleTargetDecoderFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_decoder"]],"sensai.torch.torch_models.seq.seq_modules.SingleTargetDecoderModule":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_decoder"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderModule":[[83,1,1,"","LatentPassOnMode"],[83,1,1,"","OutputMode"],[83,1,1,"","PredictionMode"],[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderModule.LatentPassOnMode":[[83,4,1,"","CONCAT_INPUT"],[83,4,1,"","INIT_HIDDEN"],[83,4,1,"","NO_LATENT"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderModule.OutputMode":[[83,4,1,"","MULTI_OUTPUT"],[83,4,1,"","SINGLE_OUTPUT"],[83,4,1,"","SINGLE_OUTPUT_MEAN"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderModule.PredictionMode":[[83,4,1,"","DIRECT"],[83,4,1,"","MULTI_LATENT"],[83,4,1,"","SINGLE_LATENT"]],"sensai.torch.torch_opt":[[85,1,1,"","NNLossEvaluator"],[85,1,1,"","NNLossEvaluatorClassification"],[85,1,1,"","NNLossEvaluatorFixedDim"],[85,1,1,"","NNLossEvaluatorRegression"],[85,1,1,"","NNOptimiser"],[85,1,1,"","NNOptimiserParams"],[85,1,1,"","Optimiser"],[85,1,1,"","TrainingInfo"]],"sensai.torch.torch_opt.NNLossEvaluator":[[85,1,1,"","Evaluation"],[85,2,1,"","get_validation_metric_name"],[85,2,1,"","start_evaluation"]],"sensai.torch.torch_opt.NNLossEvaluator.Evaluation":[[85,2,1,"","compute_train_batch_loss"],[85,2,1,"","get_epoch_train_loss"],[85,2,1,"","get_validation_metrics"],[85,2,1,"","process_validation_batch"],[85,2,1,"","start_epoch"]],"sensai.torch.torch_opt.NNLossEvaluatorClassification":[[85,1,1,"","LossFunction"],[85,1,1,"","ValidationLossEvaluator"],[85,2,1,"","__init__"],[85,2,1,"","create_validation_loss_evaluator"],[85,2,1,"","get_output_dim_weights"],[85,2,1,"","get_training_criterion"],[85,2,1,"","get_validation_metric_name"]],"sensai.torch.torch_opt.NNLossEvaluatorClassification.LossFunction":[[85,4,1,"","CROSSENTROPY"],[85,4,1,"","NLL"],[85,2,1,"","create_criterion"],[85,2,1,"","default_for_output_mode"],[85,2,1,"","get_validation_metric_key"]],"sensai.torch.torch_opt.NNLossEvaluatorClassification.ValidationLossEvaluator":[[85,2,1,"","__init__"],[85,2,1,"","end_validation_collection"],[85,2,1,"","process_validation_result_batch"],[85,2,1,"","start_validation_collection"]],"sensai.torch.torch_opt.NNLossEvaluatorFixedDim":[[85,1,1,"","Evaluation"],[85,1,1,"","ValidationLossEvaluator"],[85,2,1,"","create_validation_loss_evaluator"],[85,2,1,"","get_output_dim_weights"],[85,2,1,"","get_training_criterion"],[85,2,1,"","get_validation_metric_name"],[85,2,1,"","start_evaluation"]],"sensai.torch.torch_opt.NNLossEvaluatorFixedDim.Evaluation":[[85,2,1,"","__init__"],[85,2,1,"","compute_train_batch_loss"],[85,2,1,"","get_epoch_train_loss"],[85,2,1,"","get_validation_metrics"],[85,2,1,"","process_validation_batch"],[85,2,1,"","start_epoch"]],"sensai.torch.torch_opt.NNLossEvaluatorFixedDim.ValidationLossEvaluator":[[85,2,1,"","end_validation_collection"],[85,2,1,"","process_validation_result_batch"],[85,2,1,"","start_validation_collection"]],"sensai.torch.torch_opt.NNLossEvaluatorRegression":[[85,1,1,"","LossFunction"],[85,1,1,"","ValidationLossEvaluator"],[85,2,1,"","__init__"],[85,2,1,"","create_validation_loss_evaluator"],[85,2,1,"","get_output_dim_weights"],[85,2,1,"","get_training_criterion"],[85,2,1,"","get_validation_metric_name"]],"sensai.torch.torch_opt.NNLossEvaluatorRegression.LossFunction":[[85,4,1,"","L1LOSS"],[85,4,1,"","L2LOSS"],[85,4,1,"","MSELOSS"],[85,4,1,"","SMOOTHL1LOSS"]],"sensai.torch.torch_opt.NNLossEvaluatorRegression.ValidationLossEvaluator":[[85,2,1,"","__init__"],[85,2,1,"","end_validation_collection"],[85,2,1,"","process_validation_result_batch"],[85,2,1,"","start_validation_collection"]],"sensai.torch.torch_opt.NNOptimiser":[[85,2,1,"","__init__"],[85,2,1,"","fit"]],"sensai.torch.torch_opt.NNOptimiserParams":[[85,4,1,"","REMOVED_PARAMS"],[85,4,1,"","RENAMED_PARAMS"],[85,2,1,"","__init__"],[85,2,1,"","from_dict"],[85,2,1,"","from_dict_or_instance"],[85,2,1,"","from_either_dict_or_instance"]],"sensai.torch.torch_opt.Optimiser":[[85,4,1,"","ADADELTA"],[85,4,1,"","ADAGRAD"],[85,4,1,"","ADAM"],[85,4,1,"","ADAMAX"],[85,4,1,"","ADAMW"],[85,4,1,"","ASGD"],[85,4,1,"","LBFGS"],[85,4,1,"","RMSPROP"],[85,4,1,"","RPROP"],[85,4,1,"","SGD"],[85,2,1,"","from_name"],[85,2,1,"","from_name_or_instance"]],"sensai.torch.torch_opt.TrainingInfo":[[85,2,1,"","__init__"],[85,2,1,"","get_training_loss_series"],[85,2,1,"","get_validation_metric_series"],[85,2,1,"","plot_all"]],"sensai.torch.torchtext":[[86,1,1,"","TorchDataSetFromTorchtextDataSet"],[86,1,1,"","TorchDataSetProviderFromTorchtextDataSet"],[86,1,1,"","TorchtextDataSetFromDataFrame"]],"sensai.torch.torchtext.TorchDataSetFromTorchtextDataSet":[[86,2,1,"","__init__"],[86,2,1,"","iter_batches"],[86,2,1,"","size"]],"sensai.torch.torchtext.TorchDataSetProviderFromTorchtextDataSet":[[86,2,1,"","__init__"],[86,2,1,"","provide_split"]],"sensai.torch.torchtext.TorchtextDataSetFromDataFrame":[[86,2,1,"","__init__"]],"sensai.tracking":[[88,0,0,"-","azure_tracking"],[89,0,0,"-","clearml_tracking"],[90,0,0,"-","mlflow_tracking"],[91,0,0,"-","tracking_base"]],"sensai.tracking.azure_tracking":[[88,1,1,"","TrackedAzureMLEvaluation"],[88,1,1,"","TrackedAzureMLExperiment"]],"sensai.tracking.azure_tracking.TrackedAzureMLEvaluation":[[88,2,1,"","__init__"],[88,2,1,"","eval_model"]],"sensai.tracking.azure_tracking.TrackedAzureMLExperiment":[[88,2,1,"","__init__"]],"sensai.tracking.clearml_tracking":[[89,1,1,"","ClearMLExperiment"],[89,1,1,"","ClearMLTrackingContext"]],"sensai.tracking.clearml_tracking.ClearMLExperiment":[[89,2,1,"","__init__"]],"sensai.tracking.clearml_tracking.ClearMLTrackingContext":[[89,2,1,"","__init__"],[89,2,1,"","track_figure"],[89,2,1,"","track_text"]],"sensai.tracking.mlflow_tracking":[[90,1,1,"","MLFlowExperiment"],[90,1,1,"","MLFlowTrackingContext"]],"sensai.tracking.mlflow_tracking.MLFlowExperiment":[[90,2,1,"","__init__"],[90,2,1,"","begin_context_for_model"],[90,2,1,"","end_context"]],"sensai.tracking.mlflow_tracking.MLFlowTrackingContext":[[90,2,1,"","__init__"],[90,2,1,"","track_figure"],[90,2,1,"","track_tag"],[90,2,1,"","track_text"]],"sensai.tracking.tracking_base":[[91,1,1,"","DummyTrackingContext"],[91,1,1,"","TrackedExperiment"],[91,1,1,"","TrackingContext"],[91,1,1,"","TrackingMixin"]],"sensai.tracking.tracking_base.DummyTrackingContext":[[91,2,1,"","__init__"],[91,2,1,"","is_enabled"],[91,2,1,"","track_figure"],[91,2,1,"","track_text"]],"sensai.tracking.tracking_base.TrackedExperiment":[[91,2,1,"","__init__"],[91,2,1,"","begin_context"],[91,2,1,"","begin_context_for_model"],[91,2,1,"","end_context"],[91,2,1,"","track_values"]],"sensai.tracking.tracking_base.TrackingContext":[[91,2,1,"","__init__"],[91,2,1,"","end"],[91,2,1,"","from_optional_experiment"],[91,2,1,"","is_enabled"],[91,2,1,"","track_figure"],[91,2,1,"","track_metrics"],[91,2,1,"","track_text"]],"sensai.tracking.tracking_base.TrackingMixin":[[91,2,1,"","begin_optional_tracking_context_for_model"],[91,2,1,"","set_tracked_experiment"],[91,3,1,"","tracked_experiment"],[91,2,1,"","unset_tracked_experiment"]],"sensai.util":[[93,0,0,"-","aggregation"],[94,0,0,"-","cache"],[95,0,0,"-","cache_azure"],[96,0,0,"-","cache_mysql"],[97,0,0,"-","datastruct"],[98,0,0,"-","deprecation"],[99,0,0,"-","dtype"],[100,0,0,"-","hash"],[101,0,0,"-","helper"],[102,0,0,"-","io"],[103,0,0,"-","jscode"],[104,0,0,"-","logging"],[105,0,0,"-","math"],[106,0,0,"-","multiprocessing"],[107,0,0,"-","pandas"],[108,0,0,"-","pickle"],[109,0,0,"-","plot"],[110,0,0,"-","profiling"],[111,0,0,"-","sequences"],[112,0,0,"-","string"],[113,0,0,"-","test"],[114,0,0,"-","time"],[115,0,0,"-","typing"],[116,0,0,"-","version"]],"sensai.util.aggregation":[[93,1,1,"","DistributionCounter"],[93,1,1,"","RelativeFrequencyCounter"],[93,1,1,"","WeightedMean"]],"sensai.util.aggregation.DistributionCounter":[[93,2,1,"","__init__"],[93,2,1,"","count"],[93,2,1,"","get_distribution"]],"sensai.util.aggregation.RelativeFrequencyCounter":[[93,2,1,"","__init__"],[93,2,1,"","add"],[93,2,1,"","count"],[93,2,1,"","get_relative_frequency"]],"sensai.util.aggregation.WeightedMean":[[93,2,1,"","__init__"],[93,2,1,"","add"],[93,2,1,"","get_weighted_mean"]],"sensai.util.cache":[[94,1,1,"","BoxedValue"],[94,1,1,"","CachedValueProviderMixin"],[94,1,1,"","DelayedUpdateHook"],[94,1,1,"","InMemoryKeyValueCache"],[94,1,1,"","KeyValueCache"],[94,1,1,"","LoadSaveInterface"],[94,1,1,"","PeriodicUpdateHook"],[94,1,1,"","PersistentKeyValueCache"],[94,1,1,"","PersistentList"],[94,5,1,"","PickleCached"],[94,1,1,"","PickleLoadSaveMixin"],[94,1,1,"","PicklePersistentKeyValueCache"],[94,1,1,"","SlicedPicklePersistentList"],[94,1,1,"","SqliteConnectionManager"],[94,1,1,"","SqlitePersistentKeyValueCache"],[94,1,1,"","SqlitePersistentList"],[94,5,1,"","cached"],[94,5,1,"","pickle_cached"]],"sensai.util.cache.BoxedValue":[[94,2,1,"","__init__"]],"sensai.util.cache.CachedValueProviderMixin":[[94,2,1,"","__init__"]],"sensai.util.cache.DelayedUpdateHook":[[94,2,1,"","__init__"],[94,2,1,"","handle_update"]],"sensai.util.cache.InMemoryKeyValueCache":[[94,2,1,"","__init__"],[94,2,1,"","empty"],[94,2,1,"","get"],[94,2,1,"","set"]],"sensai.util.cache.KeyValueCache":[[94,2,1,"","get"],[94,2,1,"","set"]],"sensai.util.cache.LoadSaveInterface":[[94,2,1,"","load"],[94,2,1,"","save"]],"sensai.util.cache.PeriodicUpdateHook":[[94,2,1,"","__init__"],[94,2,1,"","handle_update"]],"sensai.util.cache.PersistentList":[[94,2,1,"","append"],[94,2,1,"","iter_items"]],"sensai.util.cache.PickleLoadSaveMixin":[[94,2,1,"","load"],[94,2,1,"","save"]],"sensai.util.cache.PicklePersistentKeyValueCache":[[94,2,1,"","__init__"],[94,2,1,"","get"],[94,2,1,"","save"],[94,2,1,"","set"]],"sensai.util.cache.SlicedPicklePersistentList":[[94,2,1,"","__init__"],[94,2,1,"","append"],[94,2,1,"","cache_exists"],[94,2,1,"","clear"],[94,2,1,"","iter_items"]],"sensai.util.cache.SqliteConnectionManager":[[94,2,1,"","open_connection"]],"sensai.util.cache.SqlitePersistentKeyValueCache":[[94,1,1,"","KeyType"],[94,2,1,"","__init__"],[94,2,1,"","get"],[94,2,1,"","iter_items"],[94,2,1,"","set"]],"sensai.util.cache.SqlitePersistentKeyValueCache.KeyType":[[94,4,1,"","INTEGER"],[94,4,1,"","STRING"]],"sensai.util.cache.SqlitePersistentList":[[94,2,1,"","__init__"],[94,2,1,"","append"],[94,2,1,"","iter_items"]],"sensai.util.cache_azure":[[95,1,1,"","AzureLazyBatchCommitTable"],[95,1,1,"","AzureTableBlobBackend"],[95,1,1,"","AzureTablePersistentKeyValueCache"],[95,1,1,"","BlobBackedPropertyLoader"],[95,1,1,"","BlobBackedSerialisedPropertyLoader"],[95,1,1,"","BlobPerKeyAzureTableBlobBackend"],[95,1,1,"","JsonAzureTableBlobBackend"],[95,1,1,"","NumpyArrayJsonSerialiser"],[95,1,1,"","PickleAzureTableBlobBackend"],[95,1,1,"","PropertyLoader"],[95,1,1,"","SerialisedPropertyLoader"],[95,1,1,"","Serialiser"],[95,1,1,"","TextDumpAzureTableBlobBackend"]],"sensai.util.cache_azure.AzureLazyBatchCommitTable":[[95,4,1,"","AZURE_ALLOWED_TABLE_BATCH_SIZE"],[95,4,1,"","AZURE_ALLOWED_TABLE_NAME_PATTERN"],[95,1,1,"","PartitionCommandsPriorityQueue"],[95,2,1,"","__init__"],[95,2,1,"","commit_blocking_largest_partition_from_queue"],[95,2,1,"","commit_blocking_until_empty"],[95,2,1,"","commit_non_blocking_current_queue_state"],[95,2,1,"","exists"],[95,2,1,"","get_entity"],[95,2,1,"","insert_data_frame_to_table"],[95,2,1,"","insert_entity"],[95,2,1,"","insert_or_replace_entity"],[95,2,1,"","iter_data_frame_chunks"],[95,2,1,"","iter_records"],[95,2,1,"","load_table_to_data_frame"]],"sensai.util.cache_azure.AzureLazyBatchCommitTable.PartitionCommandsPriorityQueue":[[95,1,1,"","PartitionCommands"],[95,2,1,"","__init__"],[95,2,1,"","add_command"],[95,2,1,"","is_empty"],[95,2,1,"","pop"],[95,2,1,"","pop_all"]],"sensai.util.cache_azure.AzureLazyBatchCommitTable.PartitionCommandsPriorityQueue.PartitionCommands":[[95,2,1,"","__init__"],[95,2,1,"","append"],[95,2,1,"","execute"]],"sensai.util.cache_azure.AzureTableBlobBackend":[[95,2,1,"","get_value_from_reference"],[95,2,1,"","get_value_reference"],[95,2,1,"","set_value_for_reference"]],"sensai.util.cache_azure.AzureTablePersistentKeyValueCache":[[95,4,1,"","CACHE_VALUE_IDENTIFIER"],[95,2,1,"","__init__"],[95,2,1,"","get"],[95,2,1,"","set"]],"sensai.util.cache_azure.BlobBackedPropertyLoader":[[95,4,1,"","AZURE_ALLOWED_SIZE_PER_PROPERTY_BYTES"],[95,4,1,"","AZURE_ALLOWED_STRING_LENGTH_PER_PROPERTY"],[95,2,1,"","__init__"],[95,2,1,"","load_property_value"],[95,2,1,"","load_property_value_to_data_frame_column"],[95,2,1,"","write_property_value"]],"sensai.util.cache_azure.BlobBackedSerialisedPropertyLoader":[[95,2,1,"","__init__"],[95,2,1,"","load_property_value"],[95,2,1,"","load_property_value_to_data_frame_column"],[95,2,1,"","write_property_value"]],"sensai.util.cache_azure.BlobPerKeyAzureTableBlobBackend":[[95,2,1,"","__init__"],[95,3,1,"","file_extension"],[95,2,1,"","get_value_from_reference"],[95,2,1,"","get_value_reference"],[95,2,1,"","set_value_for_reference"]],"sensai.util.cache_azure.JsonAzureTableBlobBackend":[[95,3,1,"","file_extension"]],"sensai.util.cache_azure.NumpyArrayJsonSerialiser":[[95,2,1,"","deserialise"],[95,2,1,"","serialise"]],"sensai.util.cache_azure.PickleAzureTableBlobBackend":[[95,3,1,"","file_extension"]],"sensai.util.cache_azure.PropertyLoader":[[95,2,1,"","load_property_value"],[95,2,1,"","load_property_value_to_data_frame_column"],[95,2,1,"","write_property_value"]],"sensai.util.cache_azure.SerialisedPropertyLoader":[[95,2,1,"","__init__"],[95,2,1,"","load_property_value"],[95,2,1,"","load_property_value_to_data_frame_column"],[95,2,1,"","write_property_value"]],"sensai.util.cache_azure.Serialiser":[[95,2,1,"","deserialise"],[95,2,1,"","serialise"]],"sensai.util.cache_azure.TextDumpAzureTableBlobBackend":[[95,3,1,"","file_extension"]],"sensai.util.cache_mysql":[[96,1,1,"","MySQLPersistentKeyValueCache"]],"sensai.util.cache_mysql.MySQLPersistentKeyValueCache":[[96,1,1,"","ValueType"],[96,2,1,"","__init__"],[96,2,1,"","get"],[96,2,1,"","set"]],"sensai.util.cache_mysql.MySQLPersistentKeyValueCache.ValueType":[[96,4,1,"","BLOB"],[96,4,1,"","DOUBLE"]],"sensai.util.datastruct":[[97,1,1,"","DeferredParams"],[97,1,1,"","Maybe"],[97,1,1,"","SortedKeyValuePairs"],[97,1,1,"","SortedKeyValueStructure"],[97,1,1,"","SortedKeysAndValues"],[97,1,1,"","SortedValues"],[97,1,1,"","Trivalent"]],"sensai.util.datastruct.DeferredParams":[[97,4,1,"","UNDEFINED"],[97,2,1,"","__init__"],[97,2,1,"","get_dict"],[97,2,1,"","get_param"],[97,2,1,"","set_param"]],"sensai.util.datastruct.Maybe":[[97,2,1,"","__init__"]],"sensai.util.datastruct.SortedKeyValuePairs":[[97,2,1,"","__init__"],[97,2,1,"","ceil_index"],[97,2,1,"","ceil_key_and_value"],[97,2,1,"","ceil_value"],[97,2,1,"","closest_index"],[97,2,1,"","closest_key_and_value"],[97,2,1,"","closest_value"],[97,2,1,"","floor_index"],[97,2,1,"","floor_key_and_value"],[97,2,1,"","floor_value"],[97,2,1,"","from_unsorted_key_value_pairs"],[97,2,1,"","key_for_index"],[97,2,1,"","value_for_index"],[97,2,1,"","value_slice"]],"sensai.util.datastruct.SortedKeyValueStructure":[[97,2,1,"","ceil_index"],[97,2,1,"","ceil_key_and_value"],[97,2,1,"","ceil_value"],[97,2,1,"","closest_index"],[97,2,1,"","closest_key_and_value"],[97,2,1,"","closest_value"],[97,2,1,"","floor_index"],[97,2,1,"","floor_key_and_value"],[97,2,1,"","floor_value"],[97,2,1,"","interpolated_value"],[97,2,1,"","slice"]],"sensai.util.datastruct.SortedKeysAndValues":[[97,2,1,"","__init__"],[97,2,1,"","ceil_index"],[97,2,1,"","ceil_key_and_value"],[97,2,1,"","ceil_value"],[97,2,1,"","closest_index"],[97,2,1,"","closest_key_and_value"],[97,2,1,"","closest_value"],[97,2,1,"","floor_index"],[97,2,1,"","floor_key_and_value"],[97,2,1,"","floor_value"],[97,2,1,"","from_series"],[97,2,1,"","value_slice_inner"],[97,2,1,"","value_slice_outer"]],"sensai.util.datastruct.SortedValues":[[97,2,1,"","__init__"],[97,2,1,"","ceil_index"],[97,2,1,"","ceil_value"],[97,2,1,"","closest_index"],[97,2,1,"","closest_value"],[97,2,1,"","floor_index"],[97,2,1,"","floor_value"],[97,2,1,"","value_slice"]],"sensai.util.datastruct.Trivalent":[[97,4,1,"","FALSE"],[97,4,1,"","TRUE"],[97,4,1,"","UNKNOWN"],[97,2,1,"","from_bool"],[97,2,1,"","is_false"],[97,2,1,"","is_true"]],"sensai.util.deprecation":[[98,5,1,"","deprecated"]],"sensai.util.dtype":[[99,5,1,"","dict_to_ordered_tuples"],[99,5,1,"","to_float_array"]],"sensai.util.hash":[[100,5,1,"","pickle_hash"],[100,5,1,"","str_hash"]],"sensai.util.helper":[[101,5,1,"","all_none"],[101,5,1,"","any_none"],[101,5,1,"","check_not_nan_dict"],[101,5,1,"","count_none"],[101,5,1,"","count_not_none"],[101,5,1,"","flatten_arguments"],[101,5,1,"","mark_used"]],"sensai.util.io":[[102,1,1,"","ResultWriter"],[102,1,1,"","S3Object"],[102,5,1,"","is_s3_path"],[102,5,1,"","read_text_file_lines"],[102,5,1,"","write_text_file_lines"]],"sensai.util.io.ResultWriter":[[102,2,1,"","__init__"],[102,2,1,"","child_for_subdirectory"],[102,2,1,"","child_with_added_prefix"],[102,2,1,"","path"],[102,2,1,"","write_data_frame_csv_file"],[102,2,1,"","write_data_frame_text_file"],[102,2,1,"","write_figure"],[102,2,1,"","write_figures"],[102,2,1,"","write_pickle"],[102,2,1,"","write_text_file"],[102,2,1,"","write_text_file_lines"]],"sensai.util.io.S3Object":[[102,1,1,"","OutputFile"],[102,2,1,"","__init__"],[102,2,1,"","get_file_content"],[102,2,1,"","open_file"],[102,2,1,"","put"]],"sensai.util.io.S3Object.OutputFile":[[102,2,1,"","__init__"],[102,2,1,"","write"]],"sensai.util.jscode":[[103,1,1,"","JsClassInstance"],[103,1,1,"","JsCode"],[103,1,1,"","JsCodeLiteral"],[103,1,1,"","JsList"],[103,1,1,"","JsObject"],[103,1,1,"","JsValue"],[103,1,1,"","JsValueLiteral"],[103,5,1,"","js_arg_list"],[103,5,1,"","js_value"]],"sensai.util.jscode.JsClassInstance":[[103,2,1,"","__init__"]],"sensai.util.jscode.JsCode":[[103,2,1,"","get_js_code"]],"sensai.util.jscode.JsCodeLiteral":[[103,2,1,"","__init__"],[103,2,1,"","get_js_code"]],"sensai.util.jscode.JsList":[[103,2,1,"","__init__"]],"sensai.util.jscode.JsObject":[[103,2,1,"","__init__"],[103,2,1,"","add"],[103,2,1,"","add_code_literal"],[103,2,1,"","add_float"],[103,2,1,"","add_json"],[103,2,1,"","add_string"],[103,2,1,"","get_js_code"]],"sensai.util.jscode.JsValue":[[103,2,1,"","bool_value"],[103,2,1,"","float_value"],[103,2,1,"","from_python"],[103,2,1,"","from_value"],[103,2,1,"","int_value"],[103,2,1,"","is_undefined"],[103,2,1,"","null"],[103,2,1,"","string_value"],[103,2,1,"","undefined"]],"sensai.util.jscode.JsValueLiteral":[[103,2,1,"","__init__"],[103,2,1,"","get_js_code"]],"sensai.util.logging":[[104,1,1,"","FileLoggerContext"],[104,1,1,"","LogTime"],[104,1,1,"","StopWatch"],[104,1,1,"","StopWatchManager"],[104,5,1,"","add_file_logger"],[104,5,1,"","add_memory_logger"],[104,5,1,"","configure"],[104,5,1,"","datetime_tag"],[104,5,1,"","get_memory_log"],[104,5,1,"","is_log_handler_active"],[104,5,1,"","remove_log_handler"],[104,5,1,"","remove_log_handlers"],[104,5,1,"","run_cli"],[104,5,1,"","run_main"],[104,5,1,"","set_configure_callback"]],"sensai.util.logging.FileLoggerContext":[[104,2,1,"","__init__"]],"sensai.util.logging.LogTime":[[104,2,1,"","__init__"],[104,2,1,"","start"],[104,2,1,"","stop"]],"sensai.util.logging.StopWatch":[[104,2,1,"","__init__"],[104,2,1,"","get_elapsed_time_secs"],[104,2,1,"","get_elapsed_time_string"],[104,2,1,"","get_elapsed_timedelta"],[104,2,1,"","pause"],[104,2,1,"","reset"],[104,2,1,"","restart"],[104,2,1,"","resume"]],"sensai.util.logging.StopWatchManager":[[104,2,1,"","__init__"],[104,2,1,"","get_instance"],[104,2,1,"","is_running"],[104,2,1,"","start"],[104,2,1,"","stop"]],"sensai.util.math":[[105,1,1,"","NormalDistribution"],[105,5,1,"","reduce_float_precision_decimals"],[105,5,1,"","reverse_sigmoid"],[105,5,1,"","sigmoid"]],"sensai.util.math.NormalDistribution":[[105,2,1,"","__init__"],[105,2,1,"","pdf"]],"sensai.util.multiprocessing":[[106,1,1,"","VectorModelWithSeparateFeatureGeneration"]],"sensai.util.multiprocessing.VectorModelWithSeparateFeatureGeneration":[[106,1,1,"","IntermediateFittingStep"],[106,1,1,"","PredictFinaliser"],[106,2,1,"","__init__"],[106,2,1,"","fit_end"],[106,2,1,"","fit_start"],[106,2,1,"","predict_start"]],"sensai.util.multiprocessing.VectorModelWithSeparateFeatureGeneration.IntermediateFittingStep":[[106,2,1,"","__init__"],[106,2,1,"","execute"]],"sensai.util.multiprocessing.VectorModelWithSeparateFeatureGeneration.PredictFinaliser":[[106,2,1,"","__init__"],[106,2,1,"","execute"]],"sensai.util.pandas":[[107,1,1,"","DataFrameColumnChangeTracker"],[107,5,1,"","extract_array"],[107,5,1,"","remove_duplicate_index_entries"]],"sensai.util.pandas.DataFrameColumnChangeTracker":[[107,2,1,"","__init__"],[107,2,1,"","assert_change_was_tracked"],[107,2,1,"","column_change_string"],[107,2,1,"","get_added_columns"],[107,2,1,"","get_removed_columns"],[107,2,1,"","track_change"]],"sensai.util.pickle":[[108,1,1,"","PickleFailureDebugger"],[108,5,1,"","dump_pickle"],[108,5,1,"","getstate"],[108,5,1,"","load_pickle"],[108,5,1,"","setstate"]],"sensai.util.pickle.PickleFailureDebugger":[[108,2,1,"","debug_failure"],[108,4,1,"","enabled"],[108,2,1,"","log_failure_if_enabled"]],"sensai.util.plot":[[109,1,1,"","Color"],[109,1,1,"","HeatMapPlot"],[109,1,1,"","HistogramPlot"],[109,1,1,"","LinearColorMap"],[109,1,1,"","Plot"],[109,1,1,"","ScatterPlot"],[109,5,1,"","plot_matrix"]],"sensai.util.plot.Color":[[109,2,1,"","__init__"],[109,2,1,"","alpha"],[109,2,1,"","darken"],[109,2,1,"","lighten"],[109,2,1,"","to_hex"]],"sensai.util.plot.HeatMapPlot":[[109,2,1,"","DEFAULT_CMAP_FACTORY"],[109,2,1,"","__init__"]],"sensai.util.plot.HistogramPlot":[[109,2,1,"","__init__"]],"sensai.util.plot.LinearColorMap":[[109,2,1,"","__init__"],[109,2,1,"","get_color"]],"sensai.util.plot.Plot":[[109,2,1,"","__init__"],[109,2,1,"","save"],[109,2,1,"","title"],[109,2,1,"","xlabel"],[109,2,1,"","xlim"],[109,2,1,"","xtick"],[109,2,1,"","xtick_major"],[109,2,1,"","xtick_minor"],[109,2,1,"","ylabel"],[109,2,1,"","ylim"],[109,2,1,"","ytick_major"]],"sensai.util.plot.ScatterPlot":[[109,4,1,"","MAX_OPACITY"],[109,4,1,"","MIN_OPACITY"],[109,4,1,"","N_MAX_TRANSPARENCY"],[109,4,1,"","N_MIN_TRANSPARENCY"],[109,2,1,"","__init__"]],"sensai.util.profiling":[[110,5,1,"","profiled"],[110,5,1,"","timed"]],"sensai.util.sequences":[[111,5,1,"","ceil_index"],[111,5,1,"","ceil_value"],[111,5,1,"","closest_index"],[111,5,1,"","closest_value"],[111,5,1,"","concat_sequences"],[111,5,1,"","floor_index"],[111,5,1,"","floor_value"],[111,5,1,"","get_first_duplicate"],[111,5,1,"","value_slice_inner"],[111,5,1,"","value_slice_outer"]],"sensai.util.string":[[112,1,1,"","StringConverter"],[112,1,1,"","TagBuilder"],[112,1,1,"","ToStringMixin"],[112,5,1,"","dict_string"],[112,5,1,"","function_name"],[112,5,1,"","list_string"],[112,5,1,"","object_repr"],[112,5,1,"","or_regex_group"],[112,5,1,"","pretty_string_repr"],[112,5,1,"","to_string"]],"sensai.util.string.StringConverter":[[112,2,1,"","to_string"]],"sensai.util.string.TagBuilder":[[112,2,1,"","__init__"],[112,2,1,"","build"],[112,2,1,"","with_alternative"],[112,2,1,"","with_component"],[112,2,1,"","with_conditional"]],"sensai.util.string.ToStringMixin":[[112,2,1,"","_tostring_additional_entries"],[112,2,1,"","_tostring_class_name"],[112,2,1,"","_tostring_exclude_exceptions"],[112,2,1,"","_tostring_exclude_private"],[112,2,1,"","_tostring_excludes"],[112,2,1,"","_tostring_includes"],[112,2,1,"","_tostring_includes_forced"],[112,2,1,"","_tostring_object_info"],[112,2,1,"","pprint"],[112,2,1,"","pprints"]],"sensai.util.test":[[113,5,1,"","convert_floats"],[113,5,1,"","json_mapper"],[113,5,1,"","reduce_float_precision"],[113,5,1,"","snapshot_compatible"]],"sensai.util.time":[[114,1,1,"","TimeInterval"],[114,5,1,"","time_of_day"],[114,5,1,"","ts_next_month"]],"sensai.util.time.TimeInterval":[[114,2,1,"","__init__"],[114,2,1,"","contains"],[114,2,1,"","contains_time"],[114,2,1,"","intersection"],[114,2,1,"","mid_timestamp"],[114,2,1,"","overlaps_with"],[114,2,1,"","time_delta"]],"sensai.util.typing":[[115,1,1,"","PandasNamedTuple"]],"sensai.util.typing.PandasNamedTuple":[[115,3,1,"","Index"]],"sensai.util.version":[[116,1,1,"","Version"]],"sensai.util.version.Version":[[116,2,1,"","__init__"],[116,2,1,"","is_at_least"]],"sensai.vector_model":[[117,1,1,"","RuleBasedVectorClassificationModel"],[117,1,1,"","RuleBasedVectorRegressionModel"],[117,1,1,"","TrainingContext"],[117,1,1,"","VectorClassificationModel"],[117,1,1,"","VectorModel"],[117,1,1,"","VectorModelBase"],[117,1,1,"","VectorModelFittableBase"],[117,1,1,"","VectorRegressionModel"]],"sensai.vector_model.RuleBasedVectorClassificationModel":[[117,2,1,"","__init__"]],"sensai.vector_model.RuleBasedVectorRegressionModel":[[117,2,1,"","__init__"]],"sensai.vector_model.TrainingContext":[[117,2,1,"","__init__"]],"sensai.vector_model.VectorClassificationModel":[[117,2,1,"","__init__"],[117,2,1,"","convert_class_probabilities_to_predictions"],[117,2,1,"","get_class_labels"],[117,2,1,"","is_regression_model"],[117,2,1,"","predict_class_probabilities"]],"sensai.vector_model.VectorModel":[[117,4,1,"","TOSTRING_INCLUDE_PREPROCESSORS"],[117,2,1,"","__init__"],[117,2,1,"","compute_model_inputs"],[117,2,1,"","compute_model_outputs"],[117,2,1,"","fit"],[117,2,1,"","fit_input_output_data"],[117,2,1,"","get_feature_generator"],[117,2,1,"","get_feature_transformer"],[117,2,1,"","get_feature_transformer_chain"],[117,2,1,"","get_input_transformer"],[117,2,1,"","get_input_transformer_chain"],[117,2,1,"","get_model_input_variable_names"],[117,2,1,"","get_predicted_variable_names"],[117,2,1,"","get_raw_input_transformer"],[117,2,1,"","get_raw_input_transformer_chain"],[117,2,1,"","is_being_fitted"],[117,2,1,"","is_fitted"],[117,2,1,"","predict"],[117,2,1,"","remove_input_preprocessors"],[117,2,1,"","set_feature_generator"],[117,2,1,"","with_feature_collector"],[117,2,1,"","with_feature_generator"],[117,2,1,"","with_feature_transformers"],[117,2,1,"","with_input_transformers"],[117,2,1,"","with_raw_input_transformers"]],"sensai.vector_model.VectorModelBase":[[117,2,1,"","__init__"],[117,2,1,"","get_name"],[117,2,1,"","get_predicted_variable_names"],[117,2,1,"","is_regression_model"],[117,2,1,"","predict"],[117,2,1,"","set_name"],[117,2,1,"","with_name"]],"sensai.vector_model.VectorModelFittableBase":[[117,2,1,"","fit"],[117,2,1,"","is_fitted"]],"sensai.vector_model.VectorRegressionModel":[[117,2,1,"","__init__"],[117,2,1,"","get_model_output_variable_names"],[117,2,1,"","get_output_transformer_chain"],[117,2,1,"","get_target_transformer"],[117,2,1,"","is_fitted"],[117,2,1,"","is_regression_model"],[117,2,1,"","predict"],[117,2,1,"","with_output_transformers"],[117,2,1,"","with_target_transformer"]],"sensai.vectoriser":[[118,1,1,"","EmptyVectoriser"],[118,1,1,"","ItemIdentifierProvider"],[118,1,1,"","SequenceVectoriser"],[118,1,1,"","Vectoriser"],[118,1,1,"","VectoriserRegistry"]],"sensai.vectoriser.EmptyVectoriser":[[118,2,1,"","__init__"]],"sensai.vectoriser.ItemIdentifierProvider":[[118,2,1,"","get_identifier"]],"sensai.vectoriser.SequenceVectoriser":[[118,1,1,"","FittingMode"],[118,2,1,"","__init__"],[118,2,1,"","apply"],[118,2,1,"","apply_multi"],[118,2,1,"","apply_multi_with_padding"],[118,2,1,"","fit"],[118,2,1,"","get_vector_dim"]],"sensai.vectoriser.SequenceVectoriser.FittingMode":[[118,4,1,"","CONCAT"],[118,4,1,"","NONE"],[118,4,1,"","UNIQUE"]],"sensai.vectoriser.Vectoriser":[[118,1,1,"","ResultType"],[118,2,1,"","__init__"],[118,2,1,"","apply"],[118,2,1,"","apply_multi"],[118,2,1,"","fit"],[118,2,1,"","get_name"],[118,2,1,"","is_fitted"],[118,2,1,"","set_name"]],"sensai.vectoriser.Vectoriser.ResultType":[[118,4,1,"","LIST"],[118,4,1,"","NUMPY_ARRAY"],[118,4,1,"","SCALAR"],[118,2,1,"","from_value"]],"sensai.vectoriser.VectoriserRegistry":[[118,2,1,"","__init__"],[118,2,1,"","get_available_vectorisers"],[118,2,1,"","get_vectoriser"],[118,2,1,"","get_vectorisers"],[118,2,1,"","register_factory"]],"sensai.xgboost":[[119,1,1,"","XGBGradientBoostedVectorClassificationModel"],[119,1,1,"","XGBGradientBoostedVectorRegressionModel"],[119,1,1,"","XGBRandomForestVectorClassificationModel"],[119,1,1,"","XGBRandomForestVectorRegressionModel"],[119,5,1,"","is_xgboost_version_at_least"]],"sensai.xgboost.XGBGradientBoostedVectorClassificationModel":[[119,2,1,"","__init__"]],"sensai.xgboost.XGBGradientBoostedVectorRegressionModel":[[119,2,1,"","__init__"]],"sensai.xgboost.XGBRandomForestVectorClassificationModel":[[119,2,1,"","__init__"]],"sensai.xgboost.XGBRandomForestVectorRegressionModel":[[119,2,1,"","__init__"]],sensai:[[3,0,0,"-","catboost"],[4,0,0,"-","clustering"],[8,0,0,"-","columngen"],[9,0,0,"-","data"],[10,0,0,"-","data_transformation"],[14,0,0,"-","distance_metric"],[15,0,0,"-","ensemble"],[18,0,0,"-","evaluation"],[29,0,0,"-","feature_importance"],[30,0,0,"-","feature_selection"],[32,0,0,"-","featuregen"],[35,0,0,"-","geoanalytics"],[46,0,0,"-","hyperopt"],[48,0,0,"-","lightgbm"],[49,0,0,"-","local_search"],[50,0,0,"-","minizinc"],[51,0,0,"-","multi_model"],[52,0,0,"-","naive_bayes"],[53,0,0,"-","nearest_neighbors"],[54,0,0,"-","normalisation"],[55,0,0,"-","pytorch_lightning"],[57,0,0,"-","sklearn"],[61,0,0,"-","sklearn_quantile"],[62,0,0,"-","tensor_model"],[63,0,0,"-","tensorflow"],[66,0,0,"-","torch"],[87,0,0,"-","tracking"],[92,0,0,"-","util"],[117,0,0,"-","vector_model"],[118,0,0,"-","vectoriser"],[119,0,0,"-","xgboost"]]},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","property","Python property"],"4":["py","attribute","Python attribute"],"5":["py","function","Python function"],"6":["py","exception","Python exception"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:property","4":"py:attribute","5":"py:function","6":"py:exception"},terms:{"0":[1,2,11,12,14,22,23,24,25,31,33,37,42,44,46,48,49,52,53,56,58,59,60,62,64,67,73,74,83,85,93,94,95,96,105,109,111,112,114,115,118],"00":[1,2],"000":1,"0001":60,"001":[1,2,53,60,85],"002":1,"006":1,"009":2,"01":[2,44],"015":1,"016":1,"017":2,"018":1,"019":1,"02":[1,2],"0209":2,"0223":2,"0245":2,"0293":2,"0294":2,"03":[1,2],"03167":80,"03385":80,"0345":2,"035":2,"0380":2,"0418":2,"04441":1,"044410":1,"0452":2,"0461":2,"046667":1,"05":[2,24,109],"050077":1,"05027":80,"0504":2,"0524":2,"053333":1,"0553":2,"0596":2,"0610":2,"062":2,"0667":2,"069":1,"0724":2,"0739":2,"080":1,"0816":2,"081762":2,"08176225980122884":2,"0818":2,"082":1,"083":1,"085":[1,2],"0881":2,"089":1,"09":1,"0906":2,"0953":2,"0962":2,"096233":2,"09623306624094645":2,"0974":2,"0986":2,"0996":2,"099880":2,"0999":2,"0x7eff4cd88880":2,"0x7effa893c450":2,"0x7effa893c7d0":2,"0x7effa8da9850":2,"0x7effa8da9f10":2,"0x7effa91a2c50":2,"0x7effaa1f3f90":2,"0x7effaa5af390":2,"0x7effaa913050":2,"0x7effab8fccb0":2,"0x7effac5a8790":2,"0x7effac5a8e50":2,"0x7effae07b150":2,"0x7f9373dc8bd0":1,"0x7f93741cc710":1,"0x7f93745d58d0":1,"1":[1,2,5,7,11,12,14,16,17,22,23,24,25,27,29,31,33,39,40,43,44,46,48,49,52,56,58,59,60,62,67,74,79,80,83,85,93,94,95,96,105,107,109,111,112,118],"10":[1,2,49,59,60,80,85,104],"100":[1,12,48,59,60,73,74,95,109],"1000":[2,60,64,85,109],"100000":94,"1013":2,"102":1,"10223":1,"102230":1,"1024":2,"103":1,"1068":2,"107293":2,"1073":2,"10x1":2,"10x10":2,"10x11":2,"10x12":2,"10x13":2,"10x14":2,"10x15":2,"10x16":2,"10x17":2,"10x18":2,"10x19":2,"10x2":2,"10x20":2,"10x21":2,"10x22":2,"10x23":2,"10x24":2,"10x25":2,"10x26":2,"10x27":2,"10x28":2,"10x3":2,"10x4":2,"10x5":2,"10x6":2,"10x7":2,"10x8":2,"10x9":2,"11":[1,2],"111":2,"1131":2,"115383":2,"1154":2,"1157":2,"11x1":2,"11x10":2,"11x11":2,"11x12":2,"11x13":2,"11x14":2,"11x15":2,"11x16":2,"11x17":2,"11x18":2,"11x19":2,"11x2":2,"11x20":2,"11x21":2,"11x22":2,"11x23":2,"11x24":2,"11x25":2,"11x26":2,"11x27":2,"11x28":2,"11x3":2,"11x4":2,"11x5":2,"11x6":2,"11x7":2,"11x8":2,"11x9":2,"12":[1,2,113],"120":53,"12000":2,"1221":2,"1222":2,"122218":2,"12221813999116421":2,"1233":2,"125":2,"1258":2,"126":2,"127":[1,2],"1271":2,"127124":2,"1274":2,"1281":2,"128110":2,"1286":2,"129":1,"12x1":2,"12x10":2,"12x11":2,"12x12":2,"12x13":2,"12x14":2,"12x15":2,"12x16":2,"12x17":2,"12x18":2,"12x19":2,"12x2":2,"12x20":2,"12x21":2,"12x22":2,"12x23":2,"12x24":2,"12x25":2,"12x26":2,"12x27":2,"12x28":2,"12x3":2,"12x4":2,"12x5":2,"12x6":2,"12x7":2,"12x8":2,"12x9":2,"13":[1,2,45,80],"131459":2,"1315":2,"133373":2,"1334":2,"1341":2,"134100":2,"1365":2,"137":1,"138":1,"1381":2,"138148":2,"139":1,"139636510019152":2,"13x1":2,"13x10":2,"13x11":2,"13x12":2,"13x13":2,"13x14":2,"13x15":2,"13x16":2,"13x17":2,"13x18":2,"13x19":2,"13x2":2,"13x20":2,"13x21":2,"13x22":2,"13x23":2,"13x24":2,"13x25":2,"13x26":2,"13x27":2,"13x28":2,"13x3":2,"13x4":2,"13x5":2,"13x6":2,"13x7":2,"13x8":2,"13x9":2,"14":[1,2],"140":[1,2],"140271289194000":1,"140271317975952":1,"141":1,"142":1,"143283":2,"1433":2,"144":1,"1440":2,"144011":2,"1450":2,"149":1,"14x1":2,"14x10":2,"14x11":2,"14x12":2,"14x13":2,"14x14":2,"14x15":2,"14x16":2,"14x17":2,"14x18":2,"14x19":2,"14x2":2,"14x20":2,"14x21":2,"14x22":2,"14x23":2,"14x24":2,"14x25":2,"14x26":2,"14x27":2,"14x28":2,"14x3":2,"14x4":2,"14x5":2,"14x6":2,"14x7":2,"14x8":2,"14x9":2,"15":[1,2,104],"1502":80,"1509":2,"150902":2,"151":2,"1512":80,"152":2,"1533":2,"1593":2,"159322":2,"15x1":2,"15x10":2,"15x11":2,"15x12":2,"15x13":2,"15x14":2,"15x15":2,"15x16":2,"15x17":2,"15x18":2,"15x19":2,"15x2":2,"15x20":2,"15x21":2,"15x22":2,"15x23":2,"15x24":2,"15x25":2,"15x26":2,"15x27":2,"15x28":2,"15x3":2,"15x4":2,"15x5":2,"15x6":2,"15x7":2,"15x8":2,"15x9":2,"16":[1,2],"1603":80,"1676":2,"1697":2,"169709":2,"16x1":2,"16x10":2,"16x11":2,"16x12":2,"16x13":2,"16x14":2,"16x15":2,"16x16":2,"16x17":2,"16x18":2,"16x19":2,"16x2":2,"16x20":2,"16x21":2,"16x22":2,"16x23":2,"16x24":2,"16x25":2,"16x26":2,"16x27":2,"16x28":2,"16x3":2,"16x4":2,"16x5":2,"16x6":2,"16x7":2,"16x8":2,"16x9":2,"17":[1,2],"177":1,"17x1":2,"17x10":2,"17x11":2,"17x12":2,"17x13":2,"17x14":2,"17x15":2,"17x16":2,"17x17":2,"17x18":2,"17x19":2,"17x2":2,"17x20":2,"17x21":2,"17x22":2,"17x23":2,"17x24":2,"17x25":2,"17x26":2,"17x27":2,"17x28":2,"17x3":2,"17x4":2,"17x5":2,"17x6":2,"17x7":2,"17x8":2,"17x9":2,"18":[1,2],"184":2,"187":1,"1872":2,"187202":2,"188":1,"18x1":2,"18x10":2,"18x11":2,"18x12":2,"18x13":2,"18x14":2,"18x15":2,"18x16":2,"18x17":2,"18x18":2,"18x19":2,"18x2":2,"18x20":2,"18x21":2,"18x22":2,"18x23":2,"18x24":2,"18x25":2,"18x26":2,"18x27":2,"18x28":2,"18x3":2,"18x4":2,"18x5":2,"18x6":2,"18x7":2,"18x8":2,"18x9":2,"19":[1,2],"190":1,"193":80,"1962":2,"196246":2,"1981":2,"19x1":2,"19x10":2,"19x11":2,"19x12":2,"19x13":2,"19x14":2,"19x15":2,"19x16":2,"19x17":2,"19x18":2,"19x19":2,"19x2":2,"19x20":2,"19x21":2,"19x22":2,"19x23":2,"19x24":2,"19x25":2,"19x26":2,"19x27":2,"19x28":2,"19x3":2,"19x4":2,"19x5":2,"19x6":2,"19x7":2,"19x8":2,"19x9":2,"1d":118,"1x1":2,"1x10":2,"1x11":2,"1x12":2,"1x13":2,"1x14":2,"1x15":2,"1x16":2,"1x17":2,"1x18":2,"1x19":2,"1x2":2,"1x20":2,"1x21":2,"1x22":2,"1x23":2,"1x24":2,"1x25":2,"1x26":2,"1x27":2,"1x28":2,"1x3":2,"1x4":2,"1x5":2,"1x6":2,"1x7":2,"1x8":2,"1x9":2,"2":[1,2,22,24,25,33,40,42,49,61,64,73,74,80,83,95,107,118],"20":[1,2,48,53],"200":[2,59,60],"2015":80,"2016":80,"202":1,"2020":80,"2024":[1,2],"204":1,"2081":2,"208118":2,"20x1":2,"20x10":2,"20x11":2,"20x12":2,"20x13":2,"20x14":2,"20x15":2,"20x16":2,"20x17":2,"20x18":2,"20x19":2,"20x2":2,"20x20":2,"20x21":2,"20x22":2,"20x23":2,"20x24":2,"20x25":2,"20x26":2,"20x27":2,"20x28":2,"20x3":2,"20x4":2,"20x5":2,"20x6":2,"20x7":2,"20x8":2,"20x9":2,"21":[1,2],"21x1":2,"21x10":2,"21x11":2,"21x12":2,"21x13":2,"21x14":2,"21x15":2,"21x16":2,"21x17":2,"21x18":2,"21x19":2,"21x2":2,"21x20":2,"21x21":2,"21x22":2,"21x23":2,"21x24":2,"21x25":2,"21x26":2,"21x27":2,"21x28":2,"21x3":2,"21x4":2,"21x5":2,"21x6":2,"21x7":2,"21x8":2,"21x9":2,"22":[1,80],"224":2,"225":2,"226":2,"22x1":2,"22x10":2,"22x11":2,"22x12":2,"22x13":2,"22x14":2,"22x15":2,"22x16":2,"22x17":2,"22x18":2,"22x19":2,"22x2":2,"22x20":2,"22x21":2,"22x22":2,"22x23":2,"22x24":2,"22x25":2,"22x26":2,"22x27":2,"22x28":2,"22x3":2,"22x4":2,"22x5":2,"22x6":2,"22x7":2,"22x8":2,"22x9":2,"23":1,"237":2,"238":[1,2],"238693":1,"239259":2,"2393":2,"23x1":2,"23x10":2,"23x11":2,"23x12":2,"23x13":2,"23x14":2,"23x15":2,"23x16":2,"23x17":2,"23x18":2,"23x19":2,"23x2":2,"23x20":2,"23x21":2,"23x22":2,"23x23":2,"23x24":2,"23x25":2,"23x26":2,"23x27":2,"23x28":2,"23x3":2,"23x4":2,"23x5":2,"23x6":2,"23x7":2,"23x8":2,"23x9":2,"24":[1,2,114],"2409":2,"24x1":2,"24x10":2,"24x11":2,"24x12":2,"24x13":2,"24x14":2,"24x15":2,"24x16":2,"24x17":2,"24x18":2,"24x19":2,"24x2":2,"24x20":2,"24x21":2,"24x22":2,"24x23":2,"24x24":2,"24x25":2,"24x26":2,"24x27":2,"24x28":2,"24x3":2,"24x4":2,"24x5":2,"24x6":2,"24x7":2,"24x8":2,"24x9":2,"25":[1,12,80],"2525":2,"252539":2,"255":[2,94],"25x1":2,"25x10":2,"25x11":2,"25x12":2,"25x13":2,"25x14":2,"25x15":2,"25x16":2,"25x17":2,"25x18":2,"25x19":2,"25x2":2,"25x20":2,"25x21":2,"25x22":2,"25x23":2,"25x24":2,"25x25":2,"25x26":2,"25x27":2,"25x28":2,"25x3":2,"25x4":2,"25x5":2,"25x6":2,"25x7":2,"25x8":2,"25x9":2,"26":1,"262":1,"266":2,"2672":80,"268":2,"269":2,"26x1":2,"26x10":2,"26x11":2,"26x12":2,"26x13":2,"26x14":2,"26x15":2,"26x16":2,"26x17":2,"26x18":2,"26x19":2,"26x2":2,"26x20":2,"26x21":2,"26x22":2,"26x23":2,"26x24":2,"26x25":2,"26x26":2,"26x27":2,"26x28":2,"26x3":2,"26x4":2,"26x5":2,"26x6":2,"26x7":2,"26x8":2,"26x9":2,"270":2,"278":1,"27x1":2,"27x10":2,"27x11":2,"27x12":2,"27x13":2,"27x14":2,"27x15":2,"27x16":2,"27x17":2,"27x18":2,"27x19":2,"27x2":2,"27x20":2,"27x21":2,"27x22":2,"27x23":2,"27x24":2,"27x25":2,"27x26":2,"27x27":2,"27x28":2,"27x3":2,"27x4":2,"27x5":2,"27x6":2,"27x7":2,"27x8":2,"27x9":2,"28":2,"280":1,"284687":2,"2847":2,"28x1":2,"28x10":2,"28x11":2,"28x12":2,"28x13":2,"28x14":2,"28x15":2,"28x16":2,"28x17":2,"28x18":2,"28x19":2,"28x2":2,"28x20":2,"28x21":2,"28x22":2,"28x23":2,"28x24":2,"28x25":2,"28x26":2,"28x27":2,"28x28":2,"28x3":2,"28x4":2,"28x5":2,"28x6":2,"28x7":2,"28x8":2,"28x9":2,"291":1,"292":1,"293":1,"295":[1,2],"2d":[2,67,80],"2x1":2,"2x10":2,"2x11":2,"2x12":2,"2x13":2,"2x14":2,"2x15":2,"2x16":2,"2x17":2,"2x18":2,"2x19":2,"2x2":2,"2x20":2,"2x21":2,"2x22":2,"2x23":2,"2x24":2,"2x25":2,"2x26":2,"2x27":2,"2x28":2,"2x3":2,"2x4":2,"2x5":2,"2x6":2,"2x7":2,"2x8":2,"2x9":2,"3":[1,2,33,80,107],"30":[1,2],"304":1,"305":1,"306":[1,2],"307":2,"308":2,"31":[1,2,3,48],"3138":2,"316":2,"32":[1,2,56],"32000":95,"33":[1,2],"3390":80,"34":[1,2],"35":[1,2],"35110632":44,"36":2,"36000":2,"37":2,"375":2,"38":2,"380582":2,"3806":2,"382":1,"3857":[39,40,43],"39":[1,2],"394":1,"396":1,"397":1,"39810717055349726":1,"3d":80,"3x1":2,"3x10":2,"3x11":2,"3x12":2,"3x13":2,"3x14":2,"3x15":2,"3x16":2,"3x17":2,"3x18":2,"3x19":2,"3x2":2,"3x20":2,"3x21":2,"3x22":2,"3x23":2,"3x24":2,"3x25":2,"3x26":2,"3x27":2,"3x28":2,"3x3":2,"3x4":2,"3x5":2,"3x6":2,"3x7":2,"3x8":2,"3x9":2,"4":[1,2,33,80,94,107,108],"403":1,"404":1,"40480":2,"405":2,"4059":2,"406":1,"407":2,"408":2,"409":2,"41":[1,2],"42":[1,2,3,9,19,26,29,46,48,49,59,60,61,119],"420":2,"421":2,"43":2,"44":2,"440":2,"441":2,"45":2,"450":2,"455":2,"459":2,"46":2,"460":2,"461":2,"47":2,"472":2,"478":2,"48":[1,2],"48000":2,"482":2,"483":2,"484":2,"485":2,"486":2,"487":2,"489":1,"49":2,"493":1,"495":2,"496":2,"499":1,"4x1":2,"4x10":2,"4x11":2,"4x12":2,"4x13":2,"4x14":2,"4x15":2,"4x16":2,"4x17":2,"4x18":2,"4x19":2,"4x2":2,"4x20":2,"4x21":2,"4x22":2,"4x23":2,"4x24":2,"4x25":2,"4x26":2,"4x27":2,"4x28":2,"4x3":2,"4x4":2,"4x5":2,"4x6":2,"4x7":2,"4x8":2,"4x9":2,"5":[1,2,12,19,22,29,42,46,49,65,73,74,76,80,107,109],"50":2,"500":1,"501":1,"502":1,"5021":2,"503":1,"505":1,"51":2,"52":1,"521":1,"523":1,"524":2,"526":2,"527":2,"53":2,"531":2,"532":2,"54":2,"544":2,"545":2,"55":2,"558":2,"56":2,"57":[1,2],"572":1,"58":1,"585":2,"59":2,"590":[1,2],"592":1,"593":2,"5s":104,"5x1":2,"5x10":2,"5x11":2,"5x12":2,"5x13":2,"5x14":2,"5x15":2,"5x16":2,"5x17":2,"5x18":2,"5x19":2,"5x2":2,"5x20":2,"5x21":2,"5x22":2,"5x23":2,"5x24":2,"5x25":2,"5x26":2,"5x27":2,"5x28":2,"5x3":2,"5x4":2,"5x5":2,"5x6":2,"5x7":2,"5x8":2,"5x9":2,"6":[1,2,73,74,113],"60":[24,25,109],"600":1,"601":1,"602":1,"603":1,"604":[1,2],"609":1,"610":2,"6141303814089187":1,"62":95,"622":1,"623":2,"6309573444801932":1,"6379522029160006":1,"64":[9,56,64,85],"64000":95,"648":1,"650":1,"657":2,"658":2,"66":2,"660":2,"661":2,"669":2,"670":2,"69":2,"690":1,"692":1,"6x1":2,"6x10":2,"6x11":2,"6x12":2,"6x13":2,"6x14":2,"6x15":2,"6x16":2,"6x17":2,"6x18":2,"6x19":2,"6x2":2,"6x20":2,"6x21":2,"6x22":2,"6x23":2,"6x24":2,"6x25":2,"6x26":2,"6x27":2,"6x28":2,"6x3":2,"6x4":2,"6x5":2,"6x6":2,"6x7":2,"6x8":2,"6x9":2,"7":[1,2],"70":2,"700":1,"703":1,"704":1,"705":1,"706":1,"71":1,"710":1,"72":2,"726":2,"727":2,"73":2,"7300":2,"730044":2,"736":2,"737":[1,2],"74":2,"749":1,"75":[2,12,85],"750":1,"752":1,"756512":1,"76":2,"77":2,"78":2,"784":2,"785":2,"788":1,"791":1,"794":1,"797":1,"798":1,"799":1,"7x1":2,"7x10":2,"7x11":2,"7x12":2,"7x13":2,"7x14":2,"7x15":2,"7x16":2,"7x17":2,"7x18":2,"7x19":2,"7x2":2,"7x20":2,"7x21":2,"7x22":2,"7x23":2,"7x24":2,"7x25":2,"7x26":2,"7x27":2,"7x28":2,"7x3":2,"7x4":2,"7x5":2,"7x6":2,"7x7":2,"7x8":2,"7x9":2,"8":[1,2,24,49,112],"80":2,"801":1,"804":1,"805":[1,2],"808":1,"8099785263057822":1,"81":2,"811":[1,2],"812":[1,2],"813":1,"816":1,"818":2,"824":[1,2],"825":[1,2],"8259":2,"826":1,"828":1,"8318":2,"835":1,"836":1,"837":1,"838":1,"840":1,"841736920530503":1,"847":1,"848":[1,2],"849":1,"851":1,"852":1,"853":1,"854":1,"859":1,"860":1,"861":1,"8611111111111112":1,"862":1,"864":1,"8666666666666667":1,"871":1,"872":1,"873":1,"875":1,"879":2,"880":2,"881":2,"882":1,"883":1,"884":1,"887":1,"8888888888888888":1,"8890980234758366":1,"892":2,"893":1,"894":1,"895":1,"896":1,"898":1,"89878":1,"898780":1,"899":2,"8x1":2,"8x10":2,"8x11":2,"8x12":2,"8x13":2,"8x14":2,"8x15":2,"8x16":2,"8x17":2,"8x18":2,"8x19":2,"8x2":2,"8x20":2,"8x21":2,"8x22":2,"8x23":2,"8x24":2,"8x25":2,"8x26":2,"8x27":2,"8x28":2,"8x3":2,"8x4":2,"8x5":2,"8x6":2,"8x7":2,"8x8":2,"8x9":2,"9":[1,2,95,109],"90":[1,2],"900":2,"905":1,"906":1,"907":1,"908":2,"909":1,"91":1,"910":2,"911":2,"916":1,"926":1,"926862":2,"9298964965102043":1,"9333333333333332":1,"9333333333333333":1,"937":2,"94":1,"9411926691126593":1,"9444444444444445":1,"944683":1,"945916926388699":2,"945917":2,"9466666666666667":2,"946667":2,"950":2,"952":2,"9523809523809524":1,"953":2,"954":[1,2],"9548416039104165":1,"9553599022560102":1,"9560552426688266":1,"96":1,"9618968610010363":2,"961897":2,"96225":2,"962250":2,"963":1,"963571":1,"964":1,"965":1,"9657414983648998":1,"966":1,"9666666666666667":1,"970":2,"971":2,"9722222222222222":1,"9734228107223192":1,"976458969438705":1,"977640":2,"9776402722798222":2,"97775":2,"977750":2,"9782716826784611":2,"978272":2,"9784166666666667":2,"978417":2,"981":2,"983":2,"986":2,"987":2,"988":2,"99":[1,2],"992":2,"997":2,"998":2,"9x1":2,"9x10":2,"9x11":2,"9x12":2,"9x13":2,"9x14":2,"9x15":2,"9x16":2,"9x17":2,"9x18":2,"9x19":2,"9x2":2,"9x20":2,"9x21":2,"9x22":2,"9x23":2,"9x24":2,"9x25":2,"9x26":2,"9x27":2,"9x28":2,"9x3":2,"9x4":2,"9x5":2,"9x6":2,"9x7":2,"9x8":2,"9x9":2,"abstract":[1,2,6,9,11,14,16,19,21,23,24,25,27,28,29,36,41,46,49,50,53,64,67,68,83,85,91,94,95,97,103,112,117,118],"boolean":[11,22,50,95],"break":[58,112],"byte":[67,102],"case":[1,2,3,8,11,12,19,21,22,24,25,26,29,31,33,34,48,49,56,58,62,64,68,74,80,82,83,85,86,90,91,94,97,101,107,108,109,111,112,117,118],"class":[1,2,3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,41,43,44,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,69,70,73,74,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,100,102,103,104,105,106,107,108,109,112,114,115,116,117,118,119],"default":[1,2,3,11,12,19,22,23,24,25,26,33,34,39,43,46,48,61,64,67,76,79,80,85,95,97,104,108,109,110,112,118],"do":[1,2,7,11,33,34,46,68,83,85,94,95,101,111,112,117],"enum":[34,54,69,74,76,83,85,94,96,97,118],"export":39,"final":[11,46,83],"float":[1,2,6,9,11,12,14,17,19,21,22,23,24,26,28,29,31,33,36,37,43,44,45,46,49,50,53,58,61,67,68,76,77,79,80,83,85,86,91,93,94,101,103,104,105,109,110,113,114,118],"function":[1,2,11,12,21,25,29,33,37,43,45,46,49,59,60,67,69,73,74,76,79,80,85,94,98,99,101,103,104,108,109,110,112,118],"import":[1,2,25,29,31,33,40,48,58,107,117],"int":[2,5,6,7,9,14,19,22,23,27,29,33,36,37,39,40,44,45,46,49,50,53,58,59,60,67,68,73,74,76,77,79,80,82,83,85,86,94,95,97,101,103,105,109,111,115,116,118,119],"long":[74,83,89,90,91,94],"m\u00b2":37,"new":[1,8,11,33,34,46,64,85,94,95,98,102,108,109,118],"null":103,"return":[2,5,6,8,9,11,12,14,19,21,22,23,24,25,26,27,29,31,33,34,36,37,39,40,42,43,44,46,49,50,58,61,62,67,68,69,73,74,76,79,83,85,86,90,91,93,94,95,96,97,98,100,101,102,103,104,107,108,109,110,111,112,113,114,116,117,118],"short":[74,83],"static":[9,12,19,23,24,37,46,49,61,74,91,103],"super":[2,53,108,112],"switch":104,"throw":13,"transient":108,"true":[1,2,8,9,11,12,13,14,19,21,22,23,24,25,26,27,29,33,34,40,46,49,50,56,58,60,61,62,64,67,68,73,76,79,80,85,86,91,94,96,97,100,101,102,103,104,105,108,109,110,111,112,114,116,117,118],"try":[2,26,46],"void":112,"while":[2,74,94],A:[1,2,11,12,13,14,19,33,34,44,49,53,67,68,73,80,82,83,85,86,91,94,95,104,107,108,117,118],As:[1,2,74,112],Being:33,By:[39,43,67,109,112,118],For:[1,2,6,8,21,24,25,29,31,33,44,49,53,56,62,67,68,73,74,79,83,94,111,112,117],If:[1,2,8,9,11,21,23,25,26,29,33,34,39,46,48,49,53,62,64,67,68,73,74,80,83,85,86,91,94,95,97,104,108,111,112,117,118],In:[1,2,3,12,31,42,48,56,62,82,107,112,118],It:[1,2,9,11,33,39,49,67,74,80,83,91,101,104,107],No:11,Not:117,One:[2,11],Or:1,The:[1,2,6,8,9,11,21,22,25,26,31,33,34,39,40,43,46,49,53,56,62,67,68,74,80,82,83,85,90,91,93,94,101,107,109,112,117],Then:[11,25,31,67],These:[33,40,51,117],To:[1,2,6,33,34,49,95,112],_:[2,33,53,112],__call__:67,__getstate__:108,__guess:[22,26],__init__:[2,3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,43,44,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,73,74,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,102,103,104,105,106,107,109,112,114,116,117,118,119],__len__:9,__main__:2,__name__:94,__repr__:112,__setstate__:108,__str__:112,__undefined__deferredparam:97,__version__:116,_create_torch_model:2,_d:[25,29],_distribut:33,_distribution_:33,_dropout:67,_fit_classifi:[1,2],_io:112,_lib:[37,104,114],_parent:2,_slicex:94,_tensoris:2,_tostring_additional_entri:112,_tostring_class_nam:112,_tostring_exclud:112,_tostring_exclude_except:112,_tostring_exclude_priv:112,_tostring_includ:112,_tostring_includes_forc:112,_tostring_object_info:112,_tostringadditionalentri:112,_tostringexclud:112,_tostringexcludeexcept:112,_tostringexcludepriv:112,_tostringinclud:112,_tostringincludesforc:112,_tostringobjectinfo:112,a1:37,a2:37,ab:[1,80],abc:[5,6,8,9,11,14,16,19,21,22,23,24,25,26,27,28,29,33,36,41,46,49,50,53,58,61,62,64,67,68,83,85,91,94,95,97,103,112,117,118],abl:[1,68,86],ablat:83,abort:85,about:[1,2,5,43,46,90,91],abov:[1,2,5,7,24,39,49,85,112],abs_angle_differ:37,absenc:[14,94,95,96],absolut:[24,37,67,93],abstractknnfind:53,abstractsklearnmultidimvectorregressionmodel:[58,60],abstractsklearnmultipleonedimvectorregressionmodel:[3,48,58,60,61,119],abstractsklearnvectorclassificationmodel:[1,3,48,58,59,119],abstractsklearnvectorregressionmodel:58,acceler:[2,76,80],accept:[2,11,46,49,62,67,68],access:[31,94],accord:[25,53,85],accuraci:[1,2,22,29,61],accuracyinci:61,achiev:[22,24,58,59],across:[1,2,11,21,25,31],act:95,action:108,activ:[1,13,59,60,69,73,74,76,80,83],activationfunct:[2,69,73,74,76,83],activi:1,actual:[2,3,11,29,31,69,73,83,85,90,91,94,95,104,108,112,117],ad:[1,2,22,24,25,26,29,33,34,43,53,60,67,80,93,94,95,102,108,112],adadelta:85,adagrad:85,adam:[2,59,60,65,85],adamax:85,adamw:[2,85],adapt:[0,49,74,83],add:[1,8,21,24,25,29,39,46,49,52,67,90,93,94,95,102,103,108,109,112,117],add_al:21,add_categorical_default_rul:[11,33],add_code_liter:103,add_combined_eval_stat:25,add_command:95,add_cross_validation_data:29,add_data_frame_csv_fil:25,add_figur:25,add_file_logg:[1,104],add_float:103,add_json:103,add_log_to_all_context:90,add_memory_logg:104,add_metr:21,add_plot:25,add_str:103,add_valu:46,add_values_dict:91,added_filename_prefix:25,addit:[1,6,21,25,26,33,36,39,43,49,53,59,60,67,88,91,94,104,108,112,118],addition:[1,2,21,22,23,24,25,112],additional_evaluation_on_training_data:25,additional_logging_values_dict:[88,89,90,91],additional_metr:[1,21,22,23,24,26],additional_nam:118,address:[1,80],adjust:9,adjustedmutualinfoscor:23,adjustedrandscor:23,admiss:[6,36,37,60,64,94,109],advanc:1,affect:[1,33,117],aforement:112,after:[12,25,31,33,46,49,59,60,73,74,76,85,94,102,117],again:2,against:[2,116],agg_fn:[1,21,29],agg_metrics_dict:[1,21],agg_results_df:25,agglom:6,agglomer:6,aggreg:[0,1,11,25,29,31,47,85,92],aggregate_predict:[16,17],aggregated_feature_import:29,aggregatedfeatureimport:29,aggregatedpermutationfeatureimport:29,ahead:80,ai:3,al:[74,80],albeit:1,algorithm:[2,5,6,7,23,36,40,43,49,85,100],alia:[21,34,115],align:95,all:[1,2,5,6,9,11,12,13,14,21,22,23,24,25,26,29,31,33,34,39,40,46,48,49,53,56,58,59,62,74,76,80,83,85,90,93,94,95,101,104,107,109,112,117,118],all_non:101,all_results_df:25,allneighborsprovid:53,allow:[1,2,33,36,67,83,95,104,118],allow_default:64,allowdefault:64,allowed_nam:112,alon:117,along:[37,83,112],alongsid:60,alpha:[42,60,109],alpha_shap:42,alreadi:[1,2,11,27,33,34,46,60,94,102,104,108,109,118],also:[1,2,24,25,40,49,62,80,85,104,109,112,118],also_include_cross_val_global_stat:25,also_include_unsorted_result:25,alwai:[1,8,11,25,33,53,59,60,68,86,93,112,117,118],amax:1,ambigu:2,amin:1,among:[1,6,49],amount:109,an:[0,1,6,7,8,9,11,13,21,22,24,25,26,31,33,34,36,37,39,40,46,49,50,53,54,58,60,61,62,64,67,68,69,73,74,80,83,85,86,90,93,94,95,96,97,102,104,107,108,109,111,112,113,117,118],analog:[1,22],analys:[1,2],angl:37,ani:[1,2,9,11,12,13,19,21,22,25,26,31,33,36,46,67,68,70,73,74,77,80,82,83,85,86,90,91,94,95,97,100,101,102,103,104,108,109,111,112,117,118],anneal:[46,49],annot:[110,115],anoth:[1,2,11,31,33,46,49,118],any_non:101,apart:74,api:[7,11,33,34,39,95],appear:[11,118],append:[1,11,33,94,95,102,118],appli:[0,1,6,8,9,11,12,22,25,26,29,31,33,34,36,43,46,49,58,59,60,62,67,68,69,73,74,76,79,85,94,104,112,117,118],applic:[6,11,21,22,24,46,49,56,62,67,94,118],apply_best_st:49,apply_clust:6,apply_converter_to_non_complex_object:112,apply_cost_chang:49,apply_invers:11,apply_multi:118,apply_multi_with_pad:118,apply_output_dim_weight:85,apply_output_dim_weights_in_valid:85,apply_sc:67,apply_state_chang:[46,49],apply_state_represent:[46,49],apply_to_input:9,applystaterepresent:[46,49],approach:[2,49,98],appropri:[1,11,26,49,67,85,104,108,113],approxim:[37,68,86],approximate_squared_dist:37,ar:[1,2,3,6,8,9,11,12,13,14,19,21,22,25,26,29,31,33,34,36,44,46,48,49,51,53,61,62,67,68,73,74,80,82,83,85,86,90,93,94,95,97,101,102,103,104,107,108,109,111,112,117,118],arbitari:1,arbitaririli:1,arbitrari:[1,2,11,33,46,49],arbitrarili:[89,90,91,117],architectur:[73,80],archiv:[46,49],area:[37,40,44],aren:112,arg:[7,9,12,21,22,24,26,27,41,67,74,77,80,83,86,94,97,101,103,118],argument:[1,12,36,46,58,59,60,61,69,85,94,101,103,104,109,118],arithmet:97,around:[7,39,43,90,91,112],arr:[12,111],arrai:[1,2,11,13,31,39,40,41,50,61,62,67,95,107,111,113,117,118],array_to_mini_zinc:50,array_valu:11,array_valued_result:11,arriv:94,articl:80,artifact:88,arxiv:80,as_multipoint:39,as_numpi:67,ascend:[11,25,29,46],asctim:104,asgd:85,aspect:1,assert_change_was_track:107,assign:[11,49],assist:[1,2,112,116],associ:[1,5,6,7,11,25,39,40,46,49,94,109],assum:[11,21,22,26,40,46,49,53,67,83,95,101,104,107,118],atom:94,attempt:11,attribut:[21,22,53,61,94,104,112,116],audio:2,auto:[1,2,21,24,59,60,74,109],automat:[2,3,25,46,48,49,88,94,109],autoregress:67,autoreload:[1,2],av_siz:23,avail:[33,85,104],available_featur:34,averag:[31,83,85],averageclusters:23,averagingvectorregressionmodel:17,avoid:[2,6,33,46,52,53,91],awar:101,ax:[2,109],axi:[1,11,21,109],azur:[88,95],azure_allowed_size_per_property_byt:95,azure_allowed_string_length_per_properti:95,azure_allowed_table_batch_s:95,azure_allowed_table_name_pattern:95,azure_track:[0,47,87],azurelazybatchcommitt:95,azureml:88,azuretableblobbackend:95,azuretablepersistentkeyvaluecach:95,b:[12,33,68,73,86,97,107,109],back:95,backend:[94,95,108],balancedaccuraci:[1,2,22],bar:[25,29,33,107],bar_1:[25,29],bar_2:[25,29],base:[1,2,3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,41,42,43,44,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,69,70,73,74,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,100,102,103,104,105,106,107,108,109,112,114,115,116,117,118,119],baseinputoutputdata:9,basi:46,basic:[2,67],batch:[59,60,67,68,80,85,86,95,107],batch_siz:[2,9,56,59,60,64,65,68,74,83,85,86,95],batchsiz:[74,85],bay:52,becaus:[2,11,31,46,67,97,112,117],becom:[1,2,105],been:[1,2,6,11,29,31,33,34,46,49,64,80,93,94,97,117,118],befor:[9,19,25,26,27,33,67,80,85,94,104,109,117,118],beforehand:95,begin:[2,49,85,90,91,104,112],begin_context:[90,91],begin_context_for_model:[90,91],begin_optional_tracking_context_for_model:91,behaviour:[3,24,80,104],behind:80,being:[1,2,6,8,11,12,21,22,25,26,31,46,67,73,74,85,94,95,102,108,112,117],belong:[9,11],below:[5,7,19,24,39,46,49],best:[1,2,31,46,49,85],best_epoch:[67,85],bestcostvalu:49,bestepoch:2,bestparam:46,better:[2,46,94],between:[2,36,37,93,94,107,109,117],beyond:[22,85],bfg:[59,60,85],bilinear:[73,74],bin:[1,21,24,33,109],binari:[1,2,22,26,56,62,97],binary_classification_positive_label_candid:22,binary_positive_label:[22,26],binaryclassificationcount:22,binaryclassificationmetr:22,binaryclassificationmetricf1scor:22,binaryclassificationmetricprecis:22,binaryclassificationmetricprecisionthreshold:22,binaryclassificationmetricrecal:22,binaryclassificationmetricrecallforprecis:22,binaryclassificationmetricrecallthreshold:22,binaryclassificationprobabilitythresholdvariationdata:22,binwidth:109,bisect:97,bit:2,black:109,blob:[95,96],blob_backend:95,blob_name_prefix:95,blob_prefix:95,blobbackedpropertyload:95,blobbackedserialisedpropertyload:95,blobperkeyazuretableblobbackend:95,block:[80,95,104],block_blob_servic:95,blockblobservic:95,bool:[2,5,6,8,11,14,19,21,22,25,26,28,31,33,34,36,39,46,59,60,62,67,68,76,79,80,82,83,85,86,91,94,97,101,103,112,114,117,118],bool_valu:103,boost:[48,119],bootstrap:[1,2],border:42,both:[1,2,9,12,14,26,67,83,85,97,101,107],bottleneck:80,bottleneck_dimension_factor:[79,80],bound:[21,22,23,24,37,44,61,97,111],boundari:[9,21,24,33],box:[44,94],box_valu:94,boxedvalu:94,bracket:112,buffer:104,build:[67,112],builder:112,built:[2,58],busi:94,bypass:[33,80],c1:[6,36],c2:[6,36],c:[2,33,80,109],c_base:109,c_opac:109,cach:[0,5,8,14,33,39,46,47,53,92,95,96,117,118],cache_azur:[0,47,92],cache_base_path:94,cache_exist:94,cache_factori:94,cache_mysql:[0,47,92],cache_valu:95,cache_value_identifi:95,cacheddistancemetr:14,cachedseriesdistancemetr:53,cachedvalueprovidermixin:[14,94],cachingknearestneighboursfind:53,cal:104,calcul:[27,93],calinskiharabaszscor:23,call:[1,12,25,26,33,46,49,67,74,80,91,94,95,98,104,108,112,117,118],callabl:[5,11,12,25,26,28,31,34,39,43,46,49,53,67,69,74,76,77,85,94,95,104,109,110,112,118],callback:104,can:[1,2,6,8,9,11,19,21,22,24,25,27,29,33,34,44,46,49,53,56,61,62,67,68,69,73,74,80,82,83,85,86,90,91,94,97,98,103,104,107,108,112,117,118],candid:[6,36],cannot:[11,21,22,24,25,33,44,62,67,79,95,101,108,117],caption:109,care:2,carri:1,cartesian:[6,44],cast:11,catboost:[0,1,47],catboostvectorclassificationmodel:3,catboostvectorregressionmodel:3,categor:[1,3,8,11,13,33,34,48,52],categori:[1,3,11,13,33,34,48],categorical_feature_nam:[3,11,33,48,53],categoricalnaivebayesvectorclassificationmodel:52,cater:[1,2,83],caus:[25,29,67,112,113],ccp_alpha:[1,2],cdf:[21,25,109],cdf_complementari:[21,25,109],cdf_secondary_axi:109,ceil:97,ceil_index:[97,111],ceil_key_and_valu:97,ceil_valu:[97,111],cell:[1,11,44,117],center:12,centr:[12,36,44,60,68],central:[1,24,44,117],centre_lat:37,centre_lon:37,centroid:5,certain:[56,62,80,90,94],certainli:1,cfg:2,chain:[11,33,49,117],chainedfeaturegener:33,chang:[2,25,33,44,46,49,85,104,107,117],changed_df:107,channel:[107,109],charact:[102,112],check:[2,22,56,62,67,94,101,116,117],check_input:14,check_input_column:[56,62,117],check_input_shap:[56,62],check_input_valu:14,check_interval_sec:94,check_not_nan_dict:101,check_output_shap:[56,62],checkintervalsec:94,chen:80,child:[25,48],child_for_subdirectori:102,child_with_added_prefix:102,choic:49,choos:[1,46,49],choose_param:[46,49],chosen:[46,49],christian:80,chunk:95,chunk_siz:95,circular:37,ck:[73,74],cl:[11,108,117],class_nam:103,class_weight:[1,2],classif:[0,1,3,22,25,26,29,33,56,62,67,73,74,76,79,85,119],classifi:[1,2,23,25,48,62,117],classificationevalstat:[1,2,19,22,25,26],classificationevalstatscollect:[19,22,25],classificationevalstatsplot:[1,22],classificationevalstatsplotcollector:25,classificationevalstatsplotconfusionmatrix:22,classificationevalstatsplotprecisionrecal:22,classificationevalstatsplotprobabilitythresholdcount:22,classificationevalstatsplotprobabilitythresholdprecisionrecal:22,classificationevaluatorparam:[1,2,19,25,26],classificationmetr:[22,26,28],classificationmetricaccuraci:22,classificationmetricaccuracymaxprobabilitybeyondthreshold:22,classificationmetricaccuracywithoutlabel:22,classificationmetricbalancedaccuraci:22,classificationmetricgeometricmeanoftrueclassprob:22,classificationmetricrelfreqmaxprobabilitybeyondthreshold:22,classificationmetrictopnaccuraci:[1,22],classificationmodelevalu:[1,2,25],classificationmultidatamodelcomparisondata:25,classificationoutputmod:[2,67,69,85],classificationvectordatautil:68,classmethod:[9,22,23,24,26,37,39,61,64,67,69,85,94,97,103,104,108,118],clean:58,cleanli:90,clear:94,clear_result:67,clearml:89,clearml_track:[0,47,87],clearmlexperi:89,clearmltrackingcontext:89,cli:104,client:104,clip:109,close:[90,102,111,112],close_figur:102,closer:[1,49],closest:[37,97,111],closest_index:[97,111],closest_key_and_valu:97,closest_point_on_polylin:37,closest_point_on_seg:37,closest_valu:[97,111],cluster:[0,5,6,7,23,27,36,39,40,41,42,47],cluster_id:[5,39],cluster_identifi:5,clustering_bas:[0,4,7,23,27,39,40,41,42,47],clustering_model:23,clusteringmodel:39,clusteringmodelevalu:27,clusteringmodelsupervisedevalu:27,clusteringmodelunsupervisedevalu:27,clusteringsupervisedevalstat:[23,27],clusteringsupervisedmetr:23,clusteringunsupervisedevalstat:[23,27],clusteringunsupervisedmetr:23,clusterlabelsevalstat:23,clusterlabelsmask:23,clustermerg:6,clusters_indic:36,clusters_local_point:36,clustersizestd:23,cm:1,cmap:[2,24,109],cmap_point:109,cmap_points_normalis:109,cnn:[0,56,62,74],cnn_model:2,cnn_model_from_modul:2,cnn_modul:2,cnnmodel:2,coars:[5,43],code:[1,2,50,91,94,100,103,104],coeffici:24,coerc:67,coincid:[26,56,62,117],col_nam:11,collect:[1,21,24,25,34,46,49,85,108,118],collect_data_fram:46,collect_featur:34,collect_result:25,collect_stat:[46,49],collectdatafram:46,collector:[1,25,34,117],collectstat:49,color:[39,109],colour:[2,24,109],column:[1,2,3,8,9,11,14,21,22,25,29,33,34,44,46,48,56,62,67,73,76,79,82,86,95,107,117],column_change_str:107,column_for_aggreg:11,column_for_entry_count:11,column_gen:33,column_gener:[8,11],column_name_for_model_rank:25,column_name_for_resulting_count:11,column_transform:11,columnchangetrack:107,columngen:[0,33,47],columngener:[8,11,33],columngeneratorcachedbyindex:8,columns_map:11,columns_to_flatten:33,columntransform:11,com:[44,95],combin:[1,2,21,22,24,25,46,51,53,73,74,83,95,109,117],come:[29,94],command:95,commit:[94,95],commit_blocking_largest_partition_from_queu:95,commit_blocking_until_empti:95,commit_non_blocking_current_queue_st:95,common:[1,83,109],common_rang:109,commonli:34,compact:[46,49,104],compar:[0,2,25],compare_model:[1,2,25],compare_models_cross_valid:25,comparison:[1,2,25],comparison_data:2,compat:[7,29,39,50,58,59,113],compil:95,complementari:[21,25,109],complet:[1,2,31,49,74,85,104,108,109],complex:[1,73,74,94,112,117],compon:[1,2,46,53,68,73,74,82,83,94,112,116],compos:109,composit:53,compromis:80,comput:[1,2,6,8,14,21,22,23,24,25,26,29,31,33,36,37,42,43,46,48,49,53,58,59,85,93,94,97,100,117,118],compute_abs_error:24,compute_all_predict:16,compute_confidence_interv:61,compute_cost_valu:[46,49],compute_encoder_dim:74,compute_error:24,compute_input_output_correl:9,compute_ma:24,compute_merg:6,compute_metr:[26,46],compute_metric_valu:[1,21,24,28],compute_metrics_fn:26,compute_model_input:117,compute_model_output:117,compute_ms:24,compute_pcc:24,compute_permutation_feature_importance_dict:29,compute_prob:[1,25,26],compute_r2:24,compute_rms:24,compute_rrs:24,compute_split_indic:9,compute_std_dev_a:24,compute_test_data_output:26,compute_train_batch_loss:85,compute_valu:[22,23,24,61],compute_value_for_eval_stat:[21,22,23,24],computemetr:26,computetrainbatchloss:85,concat:[1,33,68,118],concat_input:83,concat_sequ:111,concaten:[6,33,39,51,83,118],concav:42,concept:3,concis:[1,90],concret:[1,46,49],cond:112,condit:[5,11,22,33,39,90,91,112],condition:112,confid:61,config:2,configur:[1,2,46,53,64,67,80,104],configure_sess:64,configurelog:1,confus:1,confusionmatrix:22,conjunct:[33,104,117],connect:[37,80,95],consecut:53,consid:[6,21,22,31,33,36,40,46,53,73,74,85,93,94,112,113,117],consider:118,consist:[80,83],consol:110,constant:[43,49,60],constraint:44,construct:[1,2,6,11,24,26,33,49,53,67,94,95,97,104,118],constructor:[46,58,59,60],consum:33,consumpt:80,contain:[1,2,5,6,9,11,19,21,22,23,24,25,26,29,31,33,36,39,40,43,46,48,49,50,61,62,67,68,76,79,82,83,94,95,97,99,101,104,111,112,114,116,117,118],container_nam:95,contains_tim:114,content:[89,90,91,100,102,109],context:[11,25,29,33,68,82,90,91,104,112,117],context_info:108,context_manag:95,context_prefix:[90,91],continu:[24,33],contrari:117,contrast:42,control:[2,60,64],conv2d:2,conveni:[11,34,39,67,90,91,95,97,104,112,117],convers:[36,44,67,94,99,112,118],convert:[11,49,50,62,67,82,103,107,112,113,117],convert_class_probabilities_to_predict:[62,117],convert_float:113,convolut:[2,73,74],coordin:[0,6,35,36,37,38,39,40,42,43,44,45,47],coordinate_clust:[0,35,38,47],coordinate_clustering_ground_truth:[0,35,38,47],coordinate_pair_kei:43,coordinateclust:39,coordinateeuclideancluster:39,coordinatespanningtre:43,copi:[8,19,33],core:[8,9,11,14,16,17,21,22,24,25,26,29,33,46,53,54,61,62,67,68,73,82,85,86,88,95,97,99,102,106,107,117],correct:94,correctli:[25,67,73],correl:24,correspond:[8,9,12,21,24,33,46,49,58,59,62,67,68,74,80,85,86,95,97,107,111,112,117],cosmosdb:95,cost:[6,36,46,49,50],cost_delta:[46,49],cost_delta_for_symmetri:49,cost_valu:50,costdelta:49,costscal:50,costvalu:[46,49],could:[1,2,31,46,68,86,107],count:[1,11,21,22,52,58,59,93,101],count_non:101,count_not_non:101,countabl:22,counter:93,covari:80,cover:[40,44],cpu:2,cr:[39,40,43],craft:117,creat:[0,1,3,8,9,11,19,21,22,24,25,26,31,33,34,37,46,48,49,58,60,64,67,79,80,85,90,94,97,102,109,112,118],create_batch:67,create_combined_eval_stats_plot:25,create_criterion:85,create_cross_valid:25,create_data_set_provid:67,create_decod:83,create_default_binary_classification_metr:22,create_dft_normalis:34,create_dft_one_hot_encod:34,create_distribution_plot:25,create_encod:83,create_eval_stats_collect:24,create_evalu:25,create_evaluation_util:25,create_feature_transformer_normalis:34,create_feature_transformer_one_hot_encod:34,create_figur:[21,22,24],create_fold:19,create_metric_distribution_plot:25,create_metrics_dict_provid:[19,26],create_mini_zinc_fil:50,create_multi_feature_gener:34,create_plot:25,create_predictor:83,create_sklearn_model:58,create_torch_modul:[67,82,85],create_torch_module_for_dim:[2,67,76,79],create_validation_loss_evalu:85,create_vector_model_cross_valid:25,create_vector_model_evalu:25,createbatch:67,createtorchmodul:67,creation:[11,25,34,49,53,67,82,83,94],criterion:[1,2,85],crititc:1,cross:[0,19,25,31,46],cross_val_data:29,cross_valid:25,cross_validation_data:[1,25],cross_validator_param:[1,25,31,70],crossentropi:85,crossentropyloss:[74,85],crossval:[0,1,18,25,29,31,47,70],crossvalidationsplitt:19,crossvalidationsplitterdefault:19,crossvalidationsplitternest:19,cs:80,csv:[2,25,46],csv_path:46,csv_results_path:46,csvpath:46,csvresultspath:46,ctrl:2,ctx:33,cuda:[2,67,68,73,76,79,82,85,86],cumul:[21,25,109],current:[25,46,95,104,113,117],curv:49,custom:[0,24,67,112,118],customis:[0,95],cut:33,d:[46,49,67,68,94,99,101,112],dai:[80,114],darken:109,data:[0,2,3,5,6,8,11,12,19,21,22,23,24,25,26,27,29,31,33,34,36,39,43,44,46,47,48,49,53,54,56,58,59,60,61,62,67,68,70,73,74,76,79,82,85,86,93,94,95,97,99,107,109,113,117,118],data_fram:54,data_frame_splitt:[9,67,68],data_frame_transform:11,data_splitt:[1,26],data_transform:[0,8,11,12,26,33,34,47,53,68,117],data_util:68,databas:94,dataclass:104,datafile_path:2,datafram:[1,2,5,8,9,11,14,16,17,21,22,24,25,26,29,33,46,53,54,61,62,64,67,68,73,82,86,95,99,102,106,107,113,117],dataframecolumnchangetrack:107,dataframesplitt:[2,9,67,68],dataframesplittercolumnequivalenceclass:9,dataframesplitterfract:9,dataframetransform:[1,11,26,33,117],dataframetransformerchain:[11,117],datapoint:[5,23,27,43],dataset:[1,2,25,26,27,68,86,107],dataset_nam:25,datasplitt:[1,9,26],datasplitterfract:[1,2,9],datasplitterfromdataframesplitt:9,datasplitterfromsklearnsplitt:9,datasplitterstratifiedshufflesplit:9,datastruct:[0,47,92],datautil:[68,73,85],date:104,datetim:114,datetime_tag:104,daviesbouldinscor:23,db:96,dbscan:36,dbscangeocoordcluster:36,de:95,deactiv:80,deal:[1,2],debug:[2,50,112],debug_failur:108,decai:49,decemb:80,decid:[1,46],decim:[11,50,105,113],decis:[1,2,22],decisiontre:1,decisiontreeclassifi:1,declar:1,decod:[82,83,118],decoder_factori:82,decoderfactori:[82,83],decoderprotocol:83,decor:[8,14,94,98,110],decoupl:1,dedic:83,deep:[19,58,80],def:2,default_cmap_factori:109,default_for_output_mod:85,default_higher_is_bett:46,default_metr:23,default_metric_nam:46,default_multiclass_classification_metr:22,default_regression_metr:24,default_splitter_random_se:19,default_splitter_shuffl:19,default_transformer_factori:[11,34,118],defer:[94,95],deferred_commit_delay_sec:[94,95,96],deferred_save_delay_sec:[14,94],deferredparam:97,deferredsavedelaysec:94,defin:[1,2,6,9,11,12,19,21,24,26,37,53,59,60,67,79,83,85,97,111,112,117],definit:[42,111,112],degre:49,degree_of_complet:49,delai:[2,94],delaunai:43,delaunay_graph:43,delayedupdatehook:94,delta:[46,49],demand:67,democrat:53,denomin:[22,93],denormalis:68,denot:62,dens:74,densiti:[21,109],depend:[1,74,83,85,97,112],dependend:67,deploy:1,deprec:[0,1,21,47,92],depth:48,deriv:[2,46,49,102,110,112],descend:29,describ:[2,25,29,49,80],descript:[1,90,91],deserialis:95,design:[2,80,97,112],desir:[9,27,68,73,83,117,118],detail:25,detect:26,determin:[2,6,12,31,33,36,49,60,67,68,73,76,82,85,97,109,117,118],determinist:100,deviat:[24,67,105],devic:[68,82],df:[2,8,9,11,25,33,46,62,68,82,86,95,102,107,117],df_indexed_by_id:[14,53],dft:[0,2,8,10,26,33,34,47,53,68,117],dftaggregationoncolumn:11,dftcastcategoricalcolumn:11,dftcolumnfilt:11,dftconditionalrowfilteroncolumn:11,dftcountentri:11,dftdropna:11,dftdrowfilteronindex:11,dftfillna:[11,33],dftfromcolumngener:11,dftfromfeaturegener:11,dftinsetcomparisonrowfilteroncolumn:11,dftkeepcolumn:11,dftmodifycolumn:11,dftmodifycolumnvector:11,dftnormalis:[2,8,11,33,34,53],dftnotinsetcomparisonrowfilteroncolumn:11,dftonehotencod:11,dftrenamecolumn:11,dftroundfloat:11,dftrowfilt:11,dftsklearntransform:[2,11,68],dftsortcolumn:11,dftvectorizedconditionalrowfilteroncolumn:11,diagon:[24,109],diagonal_color:109,dict:[11,21,22,23,25,26,29,43,46,58,67,70,73,79,85,86,88,91,93,95,97,99,101,108,112],dict_str:112,dict_to_ordered_tupl:99,dictionari:[1,5,11,19,21,22,23,25,26,29,33,36,43,46,58,85,93,94,97,101,108,112],differ:[1,2,25,31,37,42,46,80,83,85,109,112,113,117],differenti:[1,94],differing_output_normalisation_mod:68,differingoutputnormalisationmod:68,digit:[2,50,73,113],dim1:33,dim2:33,dim:[2,36,40,50],dim_per_item:83,dim_per_window_item:83,dimens:[2,21,24,33,58,61,62,67,68,73,74,76,79,80,82,83,85,107,109,118],dimension:[21,42,58,68,73,74,117,118],dir_nam:102,direct:[21,22,74,83,97],directli:[1,25,46,67,74,83,94,97],directori:[46,94],disabl:[1,8,11,56,62,74,91,94,104,108,117],disable_plot:[1,25],discard:[29,31,33,94],discret:[1,49],discretis:33,displai:1,distanc:[6,14,36,37,53,97,111],distance_based_weight:53,distance_epsilon:53,distance_metr:[0,47,53],distance_metric_cach:53,distance_to:37,distancematrixdfcach:14,distancemetr:[14,53],distancemetriccach:53,distribut:[1,12,21,25,33,80,105,109],distribution_plots_cdf:25,distribution_plots_cdf_complementari:25,distributioncount:93,divid:[2,109],divisor:2,doc:[3,33,95],docstr:[74,104],docstring_pars:104,doe:[2,11,33,46,49,74,80,94,97,101,108,112,117],doesn:2,doi:80,domain:[1,2],don:[1,42],dongwei:80,dot:60,dot_path:60,doubl:96,down:85,downstream:[1,26],draw:[67,109],drawn:49,drop:[1,11,49,103,112],drop_trailing_undefin:103,dropout:[2,67,73,74,76,80,83],dtype:[0,3,11,33,47,48,92,107],due:[2,95],dummi:91,dummytrackingcontext:91,dump_pickl:108,dumppickl:94,duplic:[46,107,111],durat:[46,49,67],dure:[1,2,11,13,25,31,33,34,46,49,56,62,67,73,74,79,80,85,94,95,104,117],e22020193:80,e:[1,2,5,6,9,11,14,19,21,22,25,26,29,31,33,34,44,46,49,56,60,61,62,67,73,74,80,85,86,89,90,91,94,95,97,102,104,107,109,111,112,116,117,118],each:[1,2,6,8,11,12,19,21,24,25,26,29,31,33,34,36,44,46,49,52,53,58,59,68,73,74,76,80,82,83,85,86,88,91,94,95,102,107,109,112,117,118],earli:[2,59,60,85,117],earlier:[1,2,67],early_stop:[59,60],early_stopping_epoch:[2,85],earlystoppingepoch:85,easili:2,east:44,edg:[42,43],edge_weight:43,edit:2,effect:[11,46,91,104,112],either:[9,11,21,25,29,33,46,49,58,67,68,69,83,86,94,101,103,118],elabor:2,elaps:104,electr:80,element:[1,33,46,74,83,107,111,112],element_cast:50,elimin:31,els:25,empir:[33,49,52],empti:[62,94,95,97,102,107,111,117],emptyvectoris:118,en13102672:80,en:[48,95,119],enabl:[1,2,19,26,29,34,46,49,59,60,76,85,90,91,104,108,109,112],encapsul:[2,67,79],enclos:112,encod:[3,11,13,33,34,48,56,58,59,62,74,82,83,112,118],encoder_factori:82,encoderdecodermodel:82,encoderdecodermodul:83,encoderdecodervectorregressionmodel:82,encoderfactori:[82,83],encoderprotocol:83,encompass:[68,86,117],encount:[11,34],encourag:8,end:[1,2,9,25,46,49,73,74,85,91,94,97,104,114,117],end_context:[90,91],end_validation_collect:85,endvalidationcollect:85,energi:80,engin:2,enhanc:43,ensembl:[0,16,17,47,117],ensemble_bas:[0,15,17,47],ensembleclassificationvectormodel:16,ensembleregressionvectormodel:[16,17],ensemblevectormodel:16,ensur:[33,58,59,67,94,104,117],entir:[1,11,25,31,73,74,83,85,117],entiti:95,entri:[8,11,25,33,43,56,62,85,94,97,107,109,112],entropi:80,enumer:[2,54,69,74,85,94,96,97,118],ep:36,epoch:[2,59,60,64,65,85],epsg:[39,40,43],equal:[2,12,40,58,59,80,95,97,107,111],equidist:49,equival:[1,9,46,53,113],error:[11,24,33,34,108],error_boundari:24,esc_random_forest:1,especi:[2,34,118],essenc:1,essenti:1,estim:[21,109],et:[74,80],etc:[1,29,85,112,116],euclidean:43,euclideancluster:[5,7,23,27,39,40,41,42],euclideandistancemetr:14,euclidian:36,ev_util:28,eval_data:[1,2,25],eval_data_list:19,eval_model:[1,19,26,27,88],eval_model_via_evalu:25,eval_stat:[0,1,18,19,21,22,23,24,25,26,27,28,47,61],eval_stats_bas:[0,18,20,22,23,24,25,47],eval_stats_by_model_nam:25,eval_stats_classif:[0,1,18,19,20,25,26,28,47],eval_stats_clust:[0,18,20,27,47],eval_stats_list:[21,22,24],eval_stats_plot_collector:[1,25],eval_stats_regress:[0,18,19,20,25,26,28,47,61],eval_util:[0,1,2,18,28,47,70],evalmodel:[19,26],evalstat:[1,21,22,23,24,25],evalstatscollect:[21,22,24],evalstatsplot:[21,22,24,25],evalstatsplotcollector:25,evalu:[0,2,6,19,21,22,23,24,25,27,28,29,31,36,40,46,47,56,61,62,67,70,73,74,85,88,90,109],evaluationresultcollector:25,evaluator_clust:[0,18,47],evaluator_param:[1,2,19,25,70],evaluatorparam:[1,26],even:[1,2,82,83,91,112],event:[93,104],eventu:94,everi:[1,2,25,44,46,73,74,91,94,107,109,110,112,117],everyth:62,exactli:[25,29],exampl:[1,2,3,6,25,29,33,48,62,67,68,74,86,94,107,112],exce:[67,85],exceed:6,except:[11,13,25,26,34,62,68,86,104,111,112,117],except_column:33,exclud:[29,112],exclude_input_preprocessor:29,exclude_model_input_preprocessor:29,excluded_default_properti:108,excluded_properti:108,exclus:[93,112],execut:[33,90,94,95,104,106,110],exempt:112,exist:[8,33,34,36,46,85,94,95,108,111,117],exit:90,expect:[1,9,62,74,107],experi:[1,2,19,25,26,31,88,89,90,91],experiment_nam:[88,90],explicit:25,explicitli:112,expon:49,exponent_factor:49,exponenti:49,express:[11,25,29,34,112],extend:[2,11,25,97,112],extenion:102,extens:[89,90,91,94,102],extension_to_add:102,extensiontoadd:102,extrac:1,extract:[1,40,41,107],extract_1d_array_from_output:50,extract_arrai:107,extract_coordinates_arrai:41,extract_multi_dim_array_from_output:50,f1:22,f:[2,50,69,101,105,113,118],facilit:[1,2,25,34,109,112],fact:[25,49,118],factor:[49,80,83],factori:[2,11,24,25,31,33,34,46,49,53,67,79,82,83,85,94,118],fail:[108,117],fall:42,fallback:[97,111],fallback_bound:111,fallback_first:111,fallbackbound:111,fals:[1,2,6,8,9,11,13,14,19,21,22,25,26,27,29,31,33,34,36,39,46,48,49,50,53,58,59,60,67,68,79,85,86,90,91,94,95,96,97,100,101,102,104,105,108,109,110,111,114,116,117,118,119],false_compon:112,far:[1,2,12],faster:[49,118],featur:[0,2,3,8,11,25,29,31,33,34,39,48,52,53,58,60,62,67,73,74,82,83,117,118],feature_agg_reg_ex:29,feature_agg_regex:25,feature_col_nam:33,feature_collector:117,feature_gener:[0,32,34,47,53,117],feature_generator_registri:[0,32,47,117],feature_generators_or_nam:34,feature_import:[0,25,31,47,58],feature_importance_dict:29,feature_nam:[1,33],feature_select:[0,31,47],featurecollector:[11,34,117],featuregen:[0,11,33,34,47,53,117],featuregener:[1,2,3,11,33,34,48,117],featuregeneratorfactori:[33,118],featuregeneratorflattencolumn:33,featuregeneratorfromcolumngener:33,featuregeneratorfromdft:33,featuregeneratorfromnamedtupl:[33,53],featuregeneratorfromvectormodel:33,featuregeneratormapcolumn:33,featuregeneratormapcolumndict:33,featuregeneratornamark:33,featuregeneratorneighbor:53,featuregeneratorregistri:34,featuregeneratortakecolumn:33,featuregeneratortargetdistribut:33,featureimport:[25,29],featureimportanceprovid:[29,31,58],featureimportanceprovidersklearnclassif:[48,58,59,119],featureimportanceprovidersklearnregressionmultidim:[58,60],featureimportanceprovidersklearnregressionmultipleonedim:[48,58,60,119],februari:80,fed:[1,2,29,117],feed:80,few:1,fgen:[11,33],field:[21,86,115],fig:[2,25,89,90,91,102],figsiz:[2,60,109],figur:[21,22,24,25,29,31,60,85,89,90,91,102,109],file:[1,25,39,46,50,60,89,90,91,94,95,102,104,110,112],file_extens:95,file_nam:110,fileextens:95,fileloggercontext:104,filenam:[25,89,90,91,94,102],filename_prefix:[94,102],filename_suffix:102,fill:[11,14],fill_cach:14,fill_valu:11,filter:11,filter_index:9,filter_indic:9,filterwarn:2,find:[37,43,97,111],find_first_transformer_by_typ:11,find_neighbor:53,find_rul:11,finder:53,first:[1,2,9,22,29,31,33,37,40,46,61,68,83,85,86,95,97,107,111,117],fit:[1,2,5,7,11,12,13,19,25,26,27,33,36,39,48,56,62,67,68,82,85,95,117,118],fit_appli:11,fit_end:106,fit_gener:33,fit_geo_coord:36,fit_input_output_data:[1,117],fit_intercept:60,fit_model:[1,2,25,26,62,117],fit_preprocessor:[62,117],fit_start:106,fitarg:[1,2],fitinputoutputdata:1,fittabl:117,fitting_mod:118,fittingmod:118,fix:[11,25,42,44,73,83,85,108],fix_polygon:44,flag:[11,49,67,95,108,112],flatten:33,flatten_argu:101,flattened_feature_gener:33,flatzinc:50,float_decim:113,float_valu:103,floor:[97,111],floor_index:[97,111],floor_key_and_valu:97,floor_valu:[97,111],flower:1,fly:67,fn:[69,94],focus:1,fold:[1,19,25,31],follow:[1,2,6,11,73,74,80,85],foo:[25,29,33,107],foo_0:33,foo_1:[25,29,33],foo_2:[25,29],for_activation_fn:[2,69],for_model:19,forc:91,forecast:80,forest:[1,119],form:[1,6,9,36,46,62,101,112,117,118],format:[104,112],forward:[2,11,67,74,77,80,83],found:[2,8,14,22,37,39,46,49,94,95,96,97],fowlkesmallowsscor:23,fraction:[9,25,26,68,73,85,86],fractional_size_of_first_set:[9,68,73,86],fractional_split_random_se:26,fractional_split_shuffl:26,fractional_split_test_fract:[2,26],fractionalsplittestfract:26,frame:[0,2,8,9,11,14,16,17,21,22,24,25,26,29,33,34,46,53,54,56,61,62,67,68,73,76,79,82,86,94,95,99,102,106,107,117],framework:1,frequenc:[21,22,58,59,61,93],frequent:1,from:[1,2,8,9,11,12,19,21,22,24,25,26,29,31,33,34,36,37,39,40,46,48,49,50,58,59,62,67,68,69,73,74,76,82,83,85,86,94,95,97,102,107,108,109,110,111,112,117,118],from_bool:97,from_circl:37,from_data_fram:[2,9],from_dict:85,from_dict_or_inst:[26,85],from_either_dict_or_inst:85,from_eval_stat:22,from_model:23,from_modul:[2,67],from_nam:[69,85],from_name_or_inst:85,from_optional_experi:91,from_probability_threshold:22,from_python:103,from_seri:97,from_unsorted_key_value_pair:97,from_valu:[103,118],fulfil:[5,39],full:[1,2,25,26,29,83,91,94,102,112],fulli:[0,2,80,109,112],func:[104,110],funcnam:104,function_nam:[94,112],functool:[2,95],fundament:[2,117],further:[1,2,6,11,22,24,29,33,44,80,94],furthermor:[33,91],futur:[21,83],future_time_range_dai:53,fzn_output_path:50,g:[1,5,11,19,21,22,25,26,29,33,34,46,49,56,62,67,74,80,89,90,91,94,95,97,104,107,109,112,117,118],gain:48,gate:83,gather_result:[1,2],gb:95,gener:[0,2,3,5,8,9,11,14,19,21,22,24,25,26,27,29,31,33,34,36,39,45,46,48,49,53,58,59,60,62,67,68,82,83,86,90,91,94,95,97,103,108,112,117,118],generate_column:8,generated_column_nam:8,geo:44,geo_clust:[0,35,47],geo_coord:[0,35,36,45,47],geoanalyt:[0,36,37,39,40,43,45,47],geocoord:[36,37],geocoordcluster:36,geodatafram:[39,40,41,42,43],geodataframewrapp:[39,40,41,43],geograph:[37,44,45],geomeantrueclassprob:[1,22],geometri:[0,35,38,39,40,41,44,47],geopanda:[0,35,39,40,41,42,43,47],georect:[37,45],geospati:[39,43],get:[1,6,14,21,22,24,29,33,34,36,37,44,46,49,58,68,69,73,85,94,95,96,104,117,118],get_accuraci:22,get_added_column:107,get_aggregated_feature_import:29,get_aggregated_feature_importance_dict:29,get_al:21,get_all_cach:14,get_available_vectoris:118,get_best_model:25,get_best_model_nam:25,get_best_param:46,get_binary_classification_probability_threshold_variation_data:22,get_cached_metr:53,get_categorical_feature_name_regex:[33,34],get_chain:49,get_class_label:117,get_clust:[5,39],get_cluster_associ:6,get_color:109,get_combined_eval_stat:[21,22,24],get_config:2,get_confusion_matrix:22,get_coordinates_label:40,get_data_fram:[26,29,46],get_data_splitt:26,get_denormalised_arrai:54,get_dict:97,get_distance_seri:53,get_distribut:93,get_distribution_summari:23,get_elapsed_time_sec:104,get_elapsed_time_str:104,get_elapsed_timedelta:104,get_enabled_plot:[1,25],get_encoder_dim:74,get_ent:95,get_epoch_train_loss:85,get_eval_stat:[1,26],get_eval_stats_collect:[1,19,25,26],get_eval_stats_list:25,get_f1:22,get_feature_gener:[34,117],get_feature_import:[25,29],get_feature_importance_dict:[29,58],get_feature_transform:117,get_feature_transformer_chain:117,get_file_cont:102,get_first_dupl:111,get_generated_column_nam:33,get_global_stat:21,get_hexagon:44,get_hexagon_coord_span_for_bounding_box:44,get_hexagon_coords_for_point:44,get_identifi:118,get_input_dim:68,get_input_output_pair:73,get_input_tensor_scal:[68,73],get_input_transform:117,get_input_transformer_chain:117,get_inst:104,get_invers:11,get_js_cod:103,get_last_solver_time_sec:50,get_lat_lon:44,get_latent_dim:83,get_local_coord:44,get_max_hexagon_column:44,get_max_hexagon_row:44,get_memory_log:104,get_metr:21,get_metric_by_nam:21,get_metric_nam:21,get_metric_values_arrai:31,get_min_hexagon_column:44,get_min_hexagon_row:44,get_mini_zinc_cod:50,get_misclassified_indic:22,get_misclassified_inputs_data_fram:26,get_misclassified_triples_pred_true_input:[2,26],get_model_descript:25,get_model_input_shap:62,get_model_input_variable_nam:117,get_model_nam:25,get_model_output_dim:68,get_model_output_shap:62,get_model_output_variable_nam:117,get_module_byt:67,get_multi_feature_gener:34,get_nam:[11,33,69,117,118],get_normalisation_rul:[11,33,34],get_normalised_arrai:54,get_num_features_arrai:31,get_num_predicted_class:62,get_output_dim_weight:85,get_output_tensor_scal:[68,73],get_output_transformer_chain:117,get_paired_metr:[21,22],get_param:[58,97],get_precis:22,get_predicted_variable_nam:117,get_raw_input_transform:117,get_raw_input_transformer_chain:117,get_recal:22,get_rel_freq_posit:22,get_relative_frequ:93,get_removed_column:107,get_selected_featur:31,get_seri:49,get_simulated_ann:46,get_sklearn_model:58,get_sorted_step:31,get_sorted_tupl:29,get_state_represent:[46,49],get_target_transform:117,get_til:45,get_tile_coordin:45,get_tiles_in_rect:45,get_torch_funct:[2,69],get_torch_modul:67,get_training_criterion:85,get_training_loss_seri:85,get_validation_metr:85,get_validation_metric_kei:85,get_validation_metric_nam:85,get_validation_metric_seri:85,get_valu:[1,21],get_value_from_refer:95,get_value_refer:95,get_vector_dim:118,get_vectoris:118,get_weighted_mean:93,getcombinedevalstat:21,getepochtrainloss:85,getfeatureimport:29,getnam:34,getpredictedvariablenam:117,getseri:49,getstat:108,getstaterepresent:[46,49],getvalidationmetr:85,gini:[1,2],give:117,given:[1,2,6,8,9,11,14,19,22,25,26,29,31,33,34,36,37,43,44,46,48,49,50,53,61,62,67,68,69,83,85,86,91,93,94,97,100,101,102,104,108,109,110,111,112,113,114,116,117,118],glue:112,goe:49,good:[11,29,112],gooey:42,gps_posit:37,gpstracepoint:37,gpu:[2,76,85],gpu_allow_growth:64,gpu_per_process_memory_fract:64,gradient:[59,60,85,119],graph:[0,35,38,47],greater:[97,111],greedi:6,greedili:[46,49],greedy_clust:[0,4,36,47],greedyagglomerativeclust:[6,36],greedyagglomerativegeocoordcluster:36,green:[24,109],greyscal:2,grid:[44,46],gridsearch:46,gridsearch_:46,ground:[1,21,22,23,26,40,56,61,62,68,85,117],ground_truth:85,ground_truth_polygon:40,ground_truth_shap:85,groundtruth:26,group:[9,25,29,74],gru:[74,83],gt:[1,2],guess:[22,26],ha:[8,11,26,33,34,40,46,49,53,56,62,64,67,68,74,80,86,91,94,97,104,107,109,117,118],had:[2,6],half:[44,49],hand:[1,2,117],handl:[1,2,33,39,50,67,83,94,108,112],handle_upd:94,handler:[67,104],happen:94,hard:2,has_finite_bound:21,has_metr:21,hash:[0,47,92,94],hashabl:[34,93,94,111,118],hashlib:100,have:[1,2,3,6,8,9,11,21,25,29,31,33,34,46,48,49,56,61,62,67,73,83,91,93,94,95,97,102,107,109,111,112,117,118],he:80,head:[1,2],header:102,heat:[25,109],heatmap:24,heatmap_colormap_factori:24,heatmap_diagonal_color:24,heatmap_error_boundary_color:24,heatmap_error_boundary_valu:24,heatmapplot:109,height:107,held:26,hellingerdistancemetr:14,help:29,helper:[0,47,92,108],henc:[91,117],here:[1,2,26,33,42,49,101],heurist:117,hex:[44,100],hexagon:44,hid_activation_fn:[2,77,83],hid_activation_funct:[2,76],hid_rnn:[73,74,83],hid_skip:[73,74,83],hidactivationfunct:2,hidc:[73,74],hidden:[59,60,73,74,76,80,83],hidden_activ:65,hidden_dim:[2,65,76,77,79,80,83],hidden_layer_s:[59,60],hiddendim:2,hidrnn:74,hidskip:74,hierarchi:112,high:[2,117],higher:[25,46],higher_is_bett:46,highest_kei:97,highli:[1,82],highlight:48,highwai:[73,74],hint:7,histogram:[21,25],histogramplot:[24,109],histori:[82,83,107,118],history_featur:83,history_sequence_column_nam:82,history_sequence_variable_length:82,history_sequence_vector:82,history_sequence_vectoris:82,histplot:[21,109],hitherto:[46,49],hold:[1,2,9,11,24,25,46,85,94,97,112,117],holder:27,host:96,hot:[3,11,13,33,34,48,56,62],houseec:80,household:80,how:[1,6,24,49,83,94,117,118],howev:25,html:[3,9,21,29,33,36,48,59,60,110,119],http:[3,9,21,29,33,36,44,48,59,60,80,95,119],hw_combin:[73,74],hw_window:[73,74],hwwindow:74,hyper:46,hyper_param_valu:46,hyperopt:[0,47],hyperparamet:[2,19,26],i1:33,i2:33,i:[2,6,9,11,14,22,29,31,33,44,46,49,56,60,61,62,67,68,73,74,85,86,90,91,94,95,97,102,104,109,111,112,116,117,118],id:[1,2,34,112,118],idea:[11,29],ident:[2,59,60,80,118],identifi:[5,14,39,40,53,90,101,118],identitydistancemetr:14,idiosynchrasi:1,idx:[1,6,36,97],iff:[46,114],ignor:[2,6,11,13,22,25,36,83,112,117],ignore_unknown:[11,13,34],iloc:2,imag:[0,80,107],image_dim:2,imagereshapinginputtensoris:2,immedi:104,immut:49,implement:[1,2,6,11,29,31,33,34,42,58,59,67,85,108,112],importance_typ:48,improv:[2,59,60,80,85,117],imshow:[2,24,109],in_memori:[95,96],inadmiss:[6,36,46],includ:[1,2,5,21,25,27,39,53,85,89,90,91,97,102,108,111,112,113,117],include_generated_categorical_rul:[33,34],include_nois:[39,40],inclus:112,increment:[46,93],incremental_skip_exist:46,inde:2,indent:[58,112],indentation_str:112,independ:[8,11,29,31,33,34,58,73,74],independent_column:11,index:[0,6,8,14,21,33,36,37,39,40,53,58,59,62,85,95,97,102,107,111,115,117],index_el:9,indexcachedcolumngener:8,indic:[6,9,11,13,14,19,22,24,33,36,37,44,46,49,53,67,73,83,94,95,96,98,111],indices_pair:9,indirect:2,individu:[13,25,39,51,85,117,118],inf:[6,33,36],infer:[0,3,11,48,67,109,117],infer_mc_dropout:67,inference_batch_s:67,inferior:46,infermcdropout:67,infinit:112,inflect:49,influenc:42,info:[1,2,11,33,50,108,110,112],inform:[1,2,5,24,33,34,43,46,85,90,91,94,117],inherit:[1,2,94],init:[51,117],init_hidden:83,initi:[6,29,36,46,49,83,85,97,107,112],initial_compon:112,initial_df:107,initial_indentation_level:112,initial_paramet:46,initialis:[2,6,36,108],initialparamet:46,inject:83,inmemorykeyvaluecach:94,inner:[2,97],inplac:[11,34],input:[0,1,3,8,9,11,13,25,26,29,31,33,48,56,58,60,61,62,64,67,68,73,74,76,79,80,82,83,85,86,112,117,118],input_col_nam:33,input_data:26,input_df:[67,68],input_dim:[2,9,67,68,73,76,77,79,80,83,86],input_dim_per_time_slic:[73,74],input_feature_gener:33,input_onli:[68,86],input_tensor_scal:68,input_tensoris:[67,68],input_transform:117,input_valu:14,inputdim:2,inputdimpertimeslic:[73,74],inputfield:86,inputonli:[68,86],inputoutputarrai:9,inputoutputdata:[1,2,9,19,24,25,26,29,31,61,70,117],inputoutputdatadict:25,inputtensoris:[2,82],inputtensorshap:62,insert:95,insert_data_frame_to_t:95,insert_ent:95,insert_or_replace_ent:95,insignificantli:2,inspect:[1,2],inspir:80,instanc:[0,1,9,11,12,19,22,25,26,27,33,34,39,40,43,46,49,67,69,76,79,83,85,86,89,90,91,94,95,97,102,103,104,108,112,117,118],instanti:[1,2,7,25,33,39,67,94],instead:[1,11,13,21,25,29,33,34,46,62,94,111,112,117],instruct:1,int64:2,int_valu:103,integ:[1,2,44,50,62,94,109,118],integr:[0,25],intercept:60,interest:1,interfac:[1,11,29,67,68,83,85,101,117],interfer:94,intermedi:[1,11,83],intermediatefittingstep:106,intern:[6,34,80,85,94,112],interpol:97,interpolated_valu:97,interpret:[73,107,112],intersect:[44,114],interv:[2,33,49,61,114],intervalindex:33,introduc:112,introduct:0,invalid:[44,94,108],invalidshapeerror:62,invers:[11,53,68,117],inverse_transform:12,inversedataframetransform:11,invert:117,invertible_dft:11,invertibledataframetransform:[11,117],invok:117,involv:[2,67],inward:42,io:[0,25,47,48,92,119],io_data:[9,24,25,26,29,31,61,70,117],io_data_dict:25,ioff:80,iri:1,iris_combined_df:1,iris_data:1,iris_input_df:1,iris_io_data:1,iris_output_df:1,is_applic:9,is_at_least:116,is_being_fit:117,is_categor:[8,33],is_categorical_featur:33,is_empti:95,is_en:91,is_fals:97,is_fit:[5,11,33,117,118],is_log_handler_act:104,is_merg:6,is_positive_ground_truth:22,is_positive_predict:22,is_regress:25,is_regression_model:[16,62,117],is_relevant_ev:93,is_run:104,is_s3_path:102,is_skip:46,is_tru:97,is_undefin:103,is_xgboost_version_at_least:119,isn:[1,91],issu:98,item:[9,29,34,68,80,82,83,94,118],itemidentifierprovid:118,iter:[5,6,25,36,37,39,42,53,59,60,67,68,86,94,108,112,118],iter_batch:[68,86],iter_candidate_indic:[6,36],iter_data_frame_chunk:95,iter_evaluation_data:25,iter_input_output_ground_truth_tupl:[19,26],iter_item:94,iter_model_result:25,iter_param_combin:46,iter_potential_neighbor:53,iter_record:95,iter_tile_coordinates_in_rect:45,iterrow:2,its:[1,2,11,46,49,53,61,83,94,97,104,105,109,112],itself:[1,6,25,62,95,101,117],j:[109,111],januari:80,javascript:103,jian:80,job:29,joblib:[29,94],join:[6,36,112],jointli:[1,33,67],jpg:102,js_arg_list:103,js_code:103,js_valu:103,jsclassinst:103,jscode:[0,47,92],jscodeliter:103,jslist:103,jsobject:103,json:[95,103,113],json_mapp:113,jsonargpars:104,jsonazuretableblobbackend:95,jsvalu:103,jsvalueliter:103,juli:80,just:[6,24,25,36,62,67,90],justa:1,k:[2,58,59,60,73,74,105],kaim:80,kde:[1,21,109],keep:[9,11,50,53,107,118],keep_alpha:109,keep_other_column:33,keep_temp_fil:50,kei:[1,2,8,14,25,26,29,34,46,53,85,86,93,94,95,96,97,101,103,111,112],kera:64,kerasmultilayerperceptronvectorregressionmodel:65,kerasvectorregressionmodel:[64,65],kernel:[2,21,74,109],kernel_s:2,key_for_index:97,key_nam:25,key_typ:94,key_valu:111,key_value_cach:14,keyerror:97,keytyp:94,keyvalu:111,keyvaluecach:[8,14,33,53,94],keyword:[46,61,85],kind:90,kiprijanovska:80,knearestneighboursclassificationmodel:53,knearestneighboursfind:53,knearestneighboursregressionmodel:53,knn:53,know:[25,117],known:[34,51,68,80,86,117],kwarg:[7,12,21,24,26,27,36,39,40,41,53,61,65,67,74,77,80,83,86,109],kwd:[7,9,12,21,22,24,27,83,94,97,118],l1:60,l1loss:85,l2:60,l2loss:85,l:[59,60,80,85,112,118],label:[2,5,7,11,21,22,23,25,26,27,33,39,40,56,58,59,62,109,117],labels_:7,labels_with_removed_common_nois:23,lai:74,lambda:[67,79],larg:[1,31,67,94],larger:[6,34,40,42,49,56,62,109],largest:[58,59,95,97,111],lasso:60,last:[33,74,80,97,107,117],lat:[37,44,45],late:[2,97],latent:[74,82,83],latent_dim:[82,83],latent_pass_on_mod:83,latentpassonmod:83,later:[1,11,33,46,49,104],latest:[48,94,119],latitud:[37,44],latitude_per_m:37,latlon:37,latter:[49,74,101,118],layer:[2,59,60,74,76,80,83],lazi:95,lazybatchcommitt:95,lbfg:[59,60,85],lc:[36,37],lead:[26,68,86,102],leaf:[1,48],learn:[0,2,9,11,29,31,33,36,58,59,60,67,80,85,117],learner:48,learnt:[2,12],least:[1,22,31,49,50,60,94,109,114,116],leav:[3,33,48,85,109],left:25,leftmost:[97,111],len:111,length:[1,2,11,13,22,39,43,62,67,68,82,83,94,95,107,118],less:[31,95,97,111],let:[1,2],level:[0,2,9,25,31,33,50,104,108,110,112,113,117],levelnam:104,leverag:33,lgbmclassifi:48,lgbmregressor:48,librari:[1,104],lighten:109,lightgbm:[0,1,29,47],lightgbmvectorclassificationmodel:48,lightgbmvectorregressionmodel:48,lightningmodul:56,like:[1,11,22,31,33,39,62,67,104,108,113,117],limit:[1,21,22,33,48,50,104,112],line:[1,24,37,46,58,67,102,109,112],linear:[49,53,60,83,109],linear_model:60,linearcolormap:109,linearcombinationdistancemetr:[14,53],linearli:[49,97],linearpredictorfactori:83,linearregress:60,linspac:1,list:[1,2,3,6,9,11,14,16,17,19,21,22,23,24,25,26,28,29,31,33,36,37,45,46,49,50,53,58,59,62,67,68,73,80,82,85,94,95,101,102,108,109,111,112,117,118],list_str:112,liter:112,load:[1,2,39,94,95],load_ext:[1,2],load_iri:1,load_pickl:108,load_property_valu:95,load_property_value_to_data_frame_column:95,load_table_to_data_fram:95,loader:95,loadsaveinterfac:[39,94],local:[36,44,67,79,90],local_coord:[0,35,36,37,47],local_i:44,local_search:[0,46,47],local_x:44,localcoordinatesystem:[36,44],localhexagonalgrid:44,localpoint:36,locat:1,log:[0,2,25,33,46,47,49,50,85,88,89,90,91,92,94,108,110,112,118],log_cost_progress:49,log_failure_if_en:108,log_info:50,log_prob:[2,69],log_result:25,log_softmax:[2,69,73,76],log_stat:49,log_to_fil:110,logger:104,logic:11,logist:[49,59,60],logtim:104,lon:[37,44,45],longer:[1,108],longitud:[37,44],longitude_per_m:37,look:[2,33,117],lookup:[14,94,95,96,111],loop:94,lose:1,loss:[2,64,65,67,74,85,117],loss_evalu:[2,85],loss_fn:85,lossevalu:85,lossfn:85,lossfunct:[2,85],lot:1,low:[0,2,117],lower:[46,61,111],lower_bound_kei:[97,111],lowerboundkei:111,lowest:[6,31,111],lowest_kei:97,lstm:83,lstnet:[0,47,66,71,74,83],lstnet_model:[0,47,66,71,72],lstnet_modul:[0,47,66,71,72,83],lstnetwork:[73,74,83],lstnetworkencod:83,lstnetworkencoderfactori:83,lstnetworkvectorclassificationmodel:73,lt:[1,2],luckili:2,machin:1,made:[74,82,83,112,117],mae:24,mai:[1,3,6,11,19,21,22,25,26,29,33,36,37,46,48,49,58,59,61,67,68,82,83,85,86,94,95,102,108,112,117,118],main:[8,101,104],main_fn:104,mainli:2,maintain:[9,34,50],major:[73,74,109,116,119],make:[1,11,33,37,46,49,67,68,74,82,83,94,112,117],manag:[6,49,90,91,95,104],mani:[1,2,24,26,29,74,94,112],manipul:68,manner:[94,95],manual:12,manualscal:12,map:[11,12,21,22,23,24,25,26,29,36,43,46,49,58,64,80,83,86,93,101,108,109,112,113,118],map_til:[0,35,47],maptil:45,march:80,mark:[98,101],mark_us:101,markedli:31,marker:112,match:[11,25,29,33,34,48,68,74,94,95,111,117],matching_column:11,math:[0,6,36,37,47,92],mathemat:[1,117],matplotlib:[2,21,22,24,25,29,31,60,85,89,90,91,102,109],matric:[14,73,74],matrix:[1,36,73,74,109],max:[1,2,12,25,83],max_al:[2,54],max_angle_differ:37,max_batch_s:95,max_by_column:[54,65],max_cluster_s:[5,7,39],max_depth:[1,2,48],max_distance_m:36,max_featur:[1,2],max_i:44,max_it:[59,60],max_key_length:94,max_lat:37,max_leaf_nod:[1,2],max_lon:37,max_min_distance_for_merge_m:36,max_opac:109,max_row:44,max_sampl:[1,2],max_seq_length:83,max_siz:[23,61],max_step:[46,49],max_target_seq_length:83,max_valu:[105,109],max_work:95,max_x:44,maxabsscal:12,maxanglediffer:37,maxareadiff:44,maxclusters:23,maxcol:44,maxim:95,maximis:[31,46],maximum:[2,3,6,21,22,36,37,44,48,61,68,85,86,94,105,113,118],maxpool2d:2,maxstep:49,mayb:97,mc:67,mc_dropout_prob:67,mc_dropout_sampl:67,mcdropoutcapablennmodul:[67,74,77],mean:[1,21,24,29,36,40,42,46,48,49,60,61,67,83,85,93,105,117],mean_coord:37,mean_edge_weight:43,mean_metrics_dict:21,mean_results_df:25,mean_stat:21,meansizeci:61,meant:117,meantim:94,measur:1,mechan:[1,19,25,67,80,94,95,112,118],median:[12,61],median_s:23,mediana:24,medianclusters:23,mediansizeci:61,member:[14,24,46,109,112],member_names_or_dict:112,memori:[67,83,90,94,95,104],mercat:[39,43],mere:95,merg:[6,36],merge_candidate_determination_strategi:6,merge_cost:[6,36],mergecandidatedeterminationstrategi:[6,36],mergecandidatedeterminationstrategydefault:6,merged_cluster_indic:[6,36],messag:[98,104,108,112,118],meta:[1,33,34,67,85,117],meta_data_dict:25,meth:85,method:[1,2,6,23,25,26,29,31,33,39,43,48,67,68,85,91,95,104,108,112,117,118],metr:[36,37,44],metric:[1,2,14,19,21,22,23,24,25,26,27,28,31,46,53,61,64,65,85,88,91],metric_comput:[0,18,31,47],metric_nam:[21,25,31,46],metric_name_i:21,metric_name_x:21,metric_to_optimis:46,metric_valu:[28,31,46],metriccomput:[28,31],metriccomputationmultidata:28,metriccomputationresult:28,metrics_dict:[1,21,22,23],metrics_evalu:46,metricsdict:21,metricsdictprovid:[19,26,27,46,88],metricsdictproviderfromfunct:26,microsoft:95,mid_degre:49,mid_timestamp:114,might:[1,2],min:[1,12,25,59,60],min_child_sampl:48,min_cluster_s:[5,7,36,39],min_featur:31,min_i:44,min_impurity_decreas:[1,2],min_impurity_split:[1,2],min_lat:37,min_length:95,min_lon:37,min_opac:109,min_row:44,min_sampl:36,min_samples_leaf:[1,2,59,60],min_samples_split:[1,2],min_siz:23,min_size_for_periodic_commit:95,min_valu:[105,109],min_weight_fraction_leaf:[1,2],min_x:44,minclusters:23,mincol:44,minfeatur:31,minim:95,minimis:[31,46,49],minimise_metr:46,minims:31,minimum:[1,6,21,22,36,44,48,61,104],minimum_spanning_tre:43,minizinc:[0,47],minizincproblem:50,minizincsolv:50,minlength:95,minmaxscal:12,minor:[109,116,119],misclassifi:[2,26],miss:[1,33],mlflow_track:[0,47,87],mlflowexperi:90,mlflowtrackingcontext:90,mlp:[0,2,47,66,71],mlp_hidden_dim:2,mlp_model:[0,47,66,71,75],mlp_modul:[0,47,66,71,75],mlpclassifi:59,mlppredictorfactori:83,mlpregressor:60,mnist:2,mnist_df:2,mnist_train:2,mnistcnnmodul:2,mnistiodata:2,mode:[2,46,67,68,74,76,79,83,102,112,118],model:[0,3,11,15,16,19,21,22,24,25,26,27,28,29,31,33,34,39,46,47,48,51,53,56,58,59,60,61,62,64,67,68,73,74,80,82,83,85,88,90,91,95,109,117,119],model_arg:[3,48,58,59,60,119],model_byt:67,model_constructor:[58,59,60],model_evalu:29,model_factori:[25,28,31,46],model_input:67,model_nam:[1,2,19,25,26],model_name_to_string_repr:25,model_output:[67,85],model_output_dim:[68,73,86],model_save_directori:46,model_select:9,modelcomparisondata:[2,25],modelcomparisonvisitor:25,modelcomparisonvisitoraggregatedfeatureimport:25,modelconstructor:2,modelevalu:25,modifi:[6,11,107,108,109],modul:[1,9,25,29,36,40,59,60,62,67,76,79,80,82,83,85,101,104,117],module_factori:67,more:[1,2,11,22,33,49,58,67,68,74,80,82,91,94,112,117,118],moreov:[101,107],most:[1,11,22,29,33,34,49],mostli:83,move:[25,49,68],mse:[24,65],mseloss:85,much:42,multi:[2,21,34,46,58,67,74,83,85,117],multi_lat:83,multi_line_str:43,multi_model:[0,47],multi_output:83,multidatamodelcomparisondata:25,multidatamodelevalu:[25,28],multifeaturegener:[11,33,34,117],multilayerperceptron:[2,77],multilayerperceptrontorchmodel:[2,76],multilayerperceptronvectorclassificationmodel:[2,76],multilayerperceptronvectorregressionmodel:76,multilinestr:43,multipl:[1,2,11,24,29,33,34,53,56,58,60,62,83,85,109,117,118],multipli:[49,60],multipoint:[39,40,41,42],multipolygon:44,multiprocess:[0,47,92],multivectorregressionmodel:51,must:[1,6,9,11,22,25,26,29,33,34,36,49,67,68,73,74,82,93,94,95,112,116,118],mutat:6,mutual:93,mycach:94,mysqlpersistentkeyvaluecach:96,mzn_path:50,mzv:50,n:[1,2,11,22,31,33,53,61,67,73,80,85],n_column:107,n_estim:[1,2,48,59,60],n_imag:107,n_inputcolumn:62,n_iter_no_chang:[59,60],n_job:[1,2],n_max_transpar:109,n_min_transpar:109,n_neighbor:53,n_outputcolumn:62,n_row:[62,107],na:11,naiv:52,naive_bay:[0,47],name1:112,name:[1,2,3,8,9,11,19,21,22,23,24,25,26,29,33,34,46,48,49,50,53,58,59,60,61,69,73,76,82,85,86,88,89,90,91,94,95,97,100,104,108,109,110,112,117,118],name_or_inst:85,named_tupl:53,named_tuple_a:14,named_tuple_b:14,namen:112,nan:[11,33,101],natur:[1,2,67],ncol:2,ndarrai:[5,7,9,11,12,13,21,22,23,24,31,36,39,40,41,42,43,54,56,61,67,68,85,95,99,109,118],nearest:53,nearest_neighbor:[0,47],necessari:[1,2,11,67,85,89,117],necessarili:[46,49,117],necessit:[2,53,104],need:[1,2,3,11,25,46,48,49,67,83,85,94,95,104],neg:[6,36,49],negativeloglikelihood:85,neighbor:53,neighbor_attribut:53,neighbor_provid:53,neighbor_provider_factori:53,neighborprovid:53,neighbourhood:36,neither:11,nest:[19,21,112,113],network:[0,67,68,74,80,83],networkx:43,networx:43,neural:[0,67,68],neural_network:[59,60],neuron:76,never:[3,22,33,85],new_default_properti:108,new_optional_properti:108,newli:[85,94],newlin:102,nll:[2,85],nn:[0,67,69,76,79,80,82,83,85],nn_optimis:67,nn_optimiser_dict_param:85,nn_optimiser_param:[2,67,73,76,79,82,85],nnlossevalu:[2,85],nnlossevaluatorclassif:[2,85],nnlossevaluatorfixeddim:85,nnlossevaluatorregress:85,nnoptimis:[2,67,73,76,79,85],nnoptimiserdictparam:76,nnoptimiserparam:[2,67,73,76,79,82,85],no_lat:83,no_update_fn:94,no_update_time_period_sec:94,nois:[5,7,23,27,39,40],noise_clust:[5,39],noise_label:[5,7,23,27,39,40],noise_s:23,noiseclusters:23,noiselabelsmask:23,nomin:93,non:[6,22,25,26,36,40,49,56,62,67,80,94,95,112,117],none:[1,2,3,5,6,7,8,11,12,14,17,19,21,22,23,24,25,26,28,29,31,33,34,36,37,39,40,44,45,46,48,49,50,53,54,58,59,60,61,64,67,68,69,70,73,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,101,102,103,104,107,108,109,110,111,112,117,118,119],nonlinear:80,nor:11,norm:85,norm_max:109,norm_min:109,normal:[1,22,25,42,80,109,117],normaldistribut:105,normalis:[0,1,2,11,22,33,34,47,49,58,64,67,68,76,79,80,85,109,118],normalisation_mod:[2,54,64,65,67,68,76,79],normalisation_rul:[11,33,53],normalisation_rule_templ:[8,11,33],normalisationmod:[2,54,64,65,67,68,76,79],normalisationrul:33,normalize_plot:25,north:44,note:[1,2,11,22,25,31,33,46,49,58,59,67,82,85,97,112,117,118],notebook:1,noth:[80,93,101],notic:2,notifi:94,notion:46,noupdatefn:94,noupdatetimeperiodsec:94,now:[1,2,62],np:[1,2],nrow:2,num_chain:49,num_class:[68,73],num_clust:[5,23],num_cnn_time_slic:[73,74,83],num_conv:2,num_convolut:[73,74,83],num_edg:43,num_entries_per_slic:94,num_fold:19,num_input_time_slic:[73,74,83],num_job:29,num_leav:[3,48],num_memb:5,num_neighbor:53,num_output_time_slic:74,num_process:[16,17,46],num_record:95,num_repeat:29,num_sampl:67,num_split:19,num_unfilled_entri:14,number:[1,2,3,11,13,19,21,29,31,33,36,42,46,48,49,50,53,59,60,67,68,73,74,76,79,80,82,83,85,86,94,95,101,107,109,113,114,115,116,118],numchain:49,numclass:74,numclust:23,numcnntimeslic:74,numconvolut:74,numer:[1,2,11,34,49,117,118],numfold:19,numinputtimeslic:74,numlabel:[56,62],numoutputtimeslic:74,numpi:[1,2,5,7,9,11,12,13,21,22,23,24,31,36,39,40,41,42,43,50,54,56,61,67,68,85,95,99,107,109,113,118],numpy_arrai:118,numpyarrayjsonserialis:95,numrecord:95,nvidia:2,o:[2,68,86,100,113],obj:[102,108,112,113],object:[1,2,5,6,7,8,11,12,13,19,21,22,24,25,26,28,29,31,33,34,36,37,39,43,44,45,46,49,50,53,54,56,64,67,68,83,85,88,90,91,93,94,95,97,100,102,103,104,106,107,108,109,112,113,114,116,117,118],object_repr:112,observ:[1,46,49,117],obtain:[1,2,11,19,24,25,26,29,34,46,49,67,85,86,94,117,118],occur:[93,104],occurr:[22,107],odd:[44,112],off:25,often:[1,11],oftentim:1,old:[11,94,108],on_training_data:26,onc:[31,67,97,112,114,118],one:[1,2,3,9,11,13,21,22,24,25,26,27,29,31,33,34,36,37,39,44,46,48,49,56,58,59,60,61,62,67,68,73,74,82,83,85,91,94,97,101,102,104,107,117,118],ones:[22,62,112],ongo:[1,117],onli:[1,2,5,6,7,8,9,11,14,19,21,22,25,26,31,33,34,39,40,44,46,49,60,61,62,67,68,80,82,83,85,86,89,93,94,95,97,102,104,107,112,115,117],oob_scor:[1,2],opac:109,opaqu:109,open:[50,112],open_connect:94,open_fil:102,oper:[1,6,11,46,49,97],ops_and_weight:[46,49],opt:2,opt_dist:37,opt_point:37,opt_segment_start_idx:37,optim:[34,85],optimis:[2,11,19,26,31,46,49,64,65,67,82,85],optimiser_arg:[2,85],optimiser_clip:85,optimiser_lr:[2,85],optimiserclip:85,optimiserlr:85,optims:[46,49],option:[2,3,5,6,7,8,11,12,17,19,21,22,23,24,25,26,29,33,34,36,39,40,46,48,49,53,58,59,60,61,62,67,68,69,70,73,74,76,77,79,80,82,83,85,86,88,89,91,93,94,95,97,102,104,108,109,110,111,112,117,118,119],or_regex_group:112,order:[1,2,9,11,19,22,25,26,29,31,33,46,49,52,53,67,74,85,94,95,104,116,117,118],ordereddict:85,org:[9,21,29,33,36,59,60,80],orient:37,origin:[1,3,6,9,11,29,33,44,48,50,58,59,67,80,83,85,109,117,118],original_input:117,original_output:117,original_valu:50,os:50,osicbc:50,other:[2,6,9,11,21,22,25,33,36,49,59,60,68,73,74,102,107,112,114],otherwis:[11,25,94,101,108,112,114,116,117,118],our:[1,2,80],out:[1,26,68,73],outcom:31,outer:[2,111],outlier:36,output:[0,1,8,9,11,19,23,25,26,33,50,51,53,56,58,59,60,62,64,67,68,73,74,76,79,80,83,85,86,104,107,110,117,118],output_activ:[65,73,74],output_activation_fn:[2,77,83],output_activation_funct:[2,76],output_column:9,output_data_frame_transform:26,output_df:68,output_dim:[2,9,67,68,76,77,79,80,83],output_dim_per_time_slic:74,output_dim_weight:85,output_mod:[67,83,85],output_tensor_scal:68,output_tensor_to_array_convert:67,output_tensoris:[67,68],output_transform:[58,117],outputactivationfunct:2,outputdim:2,outputdimpertimeslic:74,outputfield:86,outputfil:102,outputmod:[2,83],outputtensoris:2,outputtensorshap:62,outputtensortoarrayconvert:67,over:[2,29,33,40,46,68,86,94],overal:[25,85,101],overfit:52,overlap:118,overlaps_with:114,overli:104,overrid:[67,68,112,117],overridden:112,override_properti:108,overrideinputdim:2,overwrit:46,own:[1,67],p0:[46,49],p1:[37,46,49],p2:37,p:[2,33,49,67],p_dropout:[2,76,77,79,80,83],p_recurrent_dropout:83,packag:[104,116],pad:[67,118],page:0,pair:[6,8,14,21,22,25,26,36,37,44,46,67,68,86,97,118],panda:[0,1,2,5,8,9,11,14,16,17,21,22,24,25,26,29,33,37,46,47,53,54,61,62,64,67,68,73,82,85,86,92,95,97,99,102,104,106,113,114,117],pandasnamedtupl:[14,19,26,53,115],parallel:[29,46,49,73,74],parallel_backend:29,parallelis:29,paralleltemp:49,param:[1,2,6,19,21,25,26,36,44,46,49,58,68,85,91,94,95,109,110],param_nam:46,paramet:[1,2,3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,29,31,33,34,36,37,39,40,42,43,44,46,48,49,50,51,52,53,56,58,59,60,61,62,64,65,67,68,69,73,74,76,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,98,100,101,102,103,104,105,107,108,109,110,111,112,113,114,116,117,118,119],parameter_combination_equivalence_class_value_cach:46,parameter_combination_skip_decid:46,parameter_opt:46,parameterchangeoper:46,parametercombinationequivalenceclassvaluecach:46,parametercombinationskipdecid:46,parametersmetricscollect:46,parametr:46,parametris:94,params_dict:49,paraqm:91,parent:[2,36,82,108],pars:104,part:[1,8,74,112,118],partial:[2,95],particular:[1,11,19,34,46,112,113,118],particularli:[1,2,53,58,59,112],partit:95,partition_kei:95,partition_key_gener:95,partitioncommand:95,partitioncommandspriorityqueu:95,partitioncommandsqueu:95,partitionkei:95,partli:118,partner:[6,36],pass:[1,2,3,11,19,21,24,25,26,34,36,39,46,48,53,58,59,60,61,62,67,83,85,90,91,93,94,101,104,107,109,112,117,118],past_time_range_dai:53,patch:[2,116,119],path:[1,2,39,40,46,50,60,73,74,80,94,102,104,108,109],pathlib:[94,108],pattern:11,paus:104,pcc:24,pd:[1,2,8,11,33,107,109],pdf:[60,105],pdropout:2,pearson:24,pend:[94,95],per:[11,21,25,26,33,39,46,73,74,80,83,85,95,118],percent:21,percentil:12,perceptron:[2,83],perform:[1,2,9,11,31,34,62,67,85,91,104,107,111,117,118],perform_cross_valid:[1,25],perform_simple_evalu:[1,2,25],perhap:117,period:[94,95],periodic_fn:94,periodically_executed_fn:94,periodicupdatehook:94,permut:29,persist:[8,14,46,67,94],persist_cach:[8,14,94],persistcach:94,persistentkeyvaluecach:[14,94,95,96],persistentlist:94,pertain:73,petal:1,phase:[33,117],pi:37,pickl:[0,8,47,67,92,94,95],picklabl:[67,79,94,100],pickle_base_nam:94,pickle_cach:94,pickle_hash:100,pickle_path:[14,94,108],pickleazuretableblobbackend:95,picklebasenam:94,picklecach:94,picklefailuredebugg:108,pickleloadsavemixin:[5,94,117],picklepersistentkeyvaluecach:94,piec:1,pipelin:[1,33],pixel:2,pl_model:[0,47,55],place:[11,34,60,67,68,82,94,95,113,117,118],placehold:[11,94],platform:113,plot:[0,21,22,24,25,26,29,31,39,40,41,47,49,60,85,92],plot_al:85,plot_confusion_matrix:[1,22],plot_cost_progress:49,plot_count:22,plot_distribut:[1,21],plot_error_distribut:24,plot_feature_import:[25,29],plot_graphviz_pdf:60,plot_heat_map:21,plot_heatmap_ground_truth_predict:24,plot_matrix:109,plot_metric_valu:31,plot_precision_recal:22,plot_precision_recall_curv:22,plot_scatt:21,plot_scatter_ground_truth_predict:24,plot_seri:49,plot_target_distribut:25,plotcostprogress:49,plt:[2,24,109],pltensortoscalarclassificationmodel:56,pltensortoscalarregressionmodel:56,pltensortotensorclassificationmodel:56,pltensortotensorregressionmodel:56,plu:[73,74],plwrappedmodel:56,png:102,point:[1,2,6,9,19,22,23,25,26,31,33,36,37,39,40,42,43,48,49,53,58,59,67,68,85,86,107,109,114,117],poli:44,polygon:[40,42,44],polygonannotatedcoordin:40,polylin:37,pool:[2,104],pooling_kernel_s:2,pop:95,pop_al:95,posit:[22,26,37,44,49],positive_class_label:22,possibl:[1,2,11,22,25,46,83,85,97,117],post:[2,117,118],potenti:[1,6,36,53,74,83,94],potential_neighbor_valu:53,power:[2,49],pprint:112,practic:[1,33,112],pre:[2,68,80,82],preced:33,precis:[1,22,26,50,80,113],precomput:67,predclass:2,predecessor:11,predefin:[0,68],predict:[1,19,21,22,23,24,25,26,29,33,56,58,60,61,62,67,74,82,83,91,117],predict_class_prob:[62,117],predict_confidence_interv:61,predict_start:106,predictclassprob:[62,117],predicted_outputs_df:1,predicted_var_nam:[19,26,29,58,60,91],predicted_variable_nam:[51,117],predictedclass:1,predictedlabel:117,predictfinalis:106,prediction_mod:83,prediction_shap:62,predictionevalstat:[21,22,24],predictionmod:83,predictions_data_fram:[16,17],predictionshap:[56,62],predictor:83,predictor_factori:83,predictorfactori:83,predictorprotocol:83,prefer:[3,11,48,91],prefix:[25,73,90,94,95,102],prepar:[1,2],prepend:[46,91,100],preprocess:[11,12,34,117,118],preprocessor:[26,29,31,58,62,67,117],presenc:33,present:[33,46,53,91,94,102,107,108,111,112],presort:1,press:2,pretti:112,prettili:112,pretty_string_repr:112,prevent:11,previou:[2,74,95],previous:[26,34,46,51,64,85,93,94,117,118],pricipl:1,primit:[1,112],principl:[1,2,112],print:[1,110,112],print_to_consol:110,prior:[74,85,117],prioriti:[6,95],privat:112,probability_funct:49,probability_threshold:22,probabilityfunct:49,probabl:[1,21,22,26,33,46,49,62,67,69,73,74,76,80,109,117],problem:[1,2,9,19,22,33,50,67,73,74,80,108,112,113],process:[1,2,11,25,31,33,46,49,67,68,73,74,82,83,85,90,97,117],process_validation_batch:85,process_validation_result_batch:85,processor:29,produc:[1,2,12,26,33,51,67,74,82,83,85,117],product:[73,74],profil:[0,47,92],progress:49,project:[34,39,43],project_nam:89,pronounc:49,proper:112,properti:[5,9,19,26,33,34,42,48,67,91,95,108,112,115],property_boolean_blob_status_nam:95,property_load:95,property_nam:95,propertyload:95,proport:[21,49,58,59],propos:74,protocol:[1,7,12,83,94,108],provid:[1,2,5,8,11,14,19,21,25,26,29,31,33,39,40,46,49,53,67,68,76,79,80,83,85,86,89,91,94,95,97,112,118],provide_split:[68,86],proxi:112,pseudo:[39,43],pseudo_count:52,purpos:[2,25,44,46,49,112,117],put:[56,62,102],pw:96,pydata:[21,33],pyinstrument:110,pyplot:2,python:[1,3,95,103,104,116,118,119],python_api:119,pythonapi:48,pytorch:[1,2],pytorch_lightn:[0,47,56],q:61,qualifi:112,qualiti:[1,85,109],quantil:[60,61],quantile_rang:12,quantileregressionmetr:61,quantileregressionmetricaccuracyinconfidenceinterv:61,quantileregressionmetricconfidenceintervalmeans:61,quantileregressionmetricconfidenceintervalmedians:61,quantileregressionmetricrelfreqmaxsizeconfidenceinterv:61,quantiti:109,question:[44,117],queue:[6,95],quot:112,r2:[24,29],r:[24,25,29,49,107,109],rad:37,radiu:[5,44],radius_m:[37,44],rais:[2,11,33,34,62,97,101,111,117],random:[1,2,3,19,26,29,39,46,48,49,59,60,119],random_forest_model:[1,2],random_se:[9,19,25,29,46,49],random_st:[1,2,3,29,46,48,59,60,61,119],randomforest:[1,2,29],randomforestclassifi:[1,2],randomforestquantileregressor:61,randomforestquantileregressorvectorregressionmodel:61,randomli:[2,26,46,49],randomse:[19,26],rang:[1,2,12,33,44],rank:25,rank_max:25,rate:85,rather:[2,11,25,26,29,33,50,67,68,85,86,94,117],raw:[1,29,117],re:[1,11,46,85,95],reach:[22,31,95,118],read:[1,25,86,94,95,102,104],read_csv:2,read_text_file_lin:102,readabl:[39,104],readi:[1,2],readthedoc:[48,119],real:1,realli:[1,2],realm:[2,50],reason:[1,2,31,58,59,98],recal:[1,22,26],receiv:[2,11,33,83,94,108],recent:[33,49],reciproc:[58,59],recognit:[2,80],recommend:[1,34,49,62,98],recomput:[6,53],recreat:94,rect:45,rectangl:37,recurr:83,recurs:[31,108,112],recursivefeatureelimin:31,recursivefeatureeliminationcv:31,redblobgam:44,reduc:[80,113],reduce_float_precis:113,reduce_float_precision_decim:105,reduced_dim:2,redund:46,refer:[33,44,49,80,95,104,107,117],referenc:[34,44,118],reference_cost_delta:49,reference_paramet:3,referencecostdelta:49,refit_vectoris:118,reflect:[25,46,49,61],reformat:112,regard:1,regardless:[22,91,104,112],regex:[11,25,29,33,48,112],region:40,regist:[33,34,118],register_atexit:104,register_factori:[34,118],registri:34,regress:[1,2,24,25,26,29,33,51,56,62,67,74,80,85,109,119],regressionevalstat:[19,24,25,26],regressionevalstatscollect:[19,24,25],regressionevalstatsplot:[24,25],regressionevalstatsplotcollector:25,regressionevalstatsploterrordistribut:24,regressionevalstatsplotheatmapgroundtruthpredict:24,regressionevalstatsplotscattergroundtruthpredict:24,regressionevaluatorparam:[19,25,26,70],regressionmetr:[24,26,28,61],regressionmetricma:24,regressionmetricmediana:24,regressionmetricms:[24,46],regressionmetricpcc:24,regressionmetricr2:24,regressionmetricrms:24,regressionmetricrrs:24,regressionmetricstddeva:24,regressionmodelevalu:[25,70],regressionmultidatamodelcomparisondata:25,regular:[2,11,21,25,29,33,34,67,112],regularis:[60,80],regularli:46,rel:[1,22,24,44,61,93],relabel:[5,39],relative_frequency_count:93,relativebitwiseequalitydistancemetr:14,relativefrequencycount:93,relev:[1,11,25,33,49,67,93,102],relu:[2,59,60,69,80,83],remain:[31,40,53],remaind:[68,85,86],remov:[12,23,31,58,102,104,107,108,112,117],remove_duplicate_index_entri:107,remove_input_preprocessor:[31,117],remove_log_handl:104,remove_merg:6,removed_param:85,removed_properti:108,removedcommonnoisesupervisedmetr:23,removednoiseunsupervisedmetr:23,ren:80,renam:1,renamed_param:85,renamed_properti:108,render:[60,108,109,113],repeat:[31,53],repeatedli:118,replac:[11,58,59,95,117],report:[25,29,67,76,79,101,112],repres:[1,2,6,23,34,37,40,44,46,49,67,68,83,94,95,97,104,117,118],represent:[1,2,26,46,49,53,58,74,83,90,91,94,95,100,104,107,109,112,113],reproduc:[59,60],reprsent:1,request:[33,95],requir:[1,2,6,11,19,26,33,56,58,59,62,67,68,73,74,85,97,104,112,117],require_all_handl:[11,34],requires_prob:22,reserv:1,reset:[85,104],reset_index:1,reshap:2,reshape_2d_imag:2,residu:80,residualfeedforwardnetwork:80,residualfeedforwardnetworktorchmodel:79,residualfeedforwardnetworkvectorregressionmodel:79,residualffn:[0,47,66,71],residualffn_model:[0,47,66,71,78],residualffn_modul:[0,47,66,71,78],resnet:80,resourc:95,respect:[1,2,9,12,19,22,25,33,37,48,67,94,101,104,112,116],rest:[9,95],restart:104,restor:2,restrict:[67,95],result:[1,2,8,11,12,13,19,22,23,24,25,26,31,33,34,39,42,46,48,49,62,67,80,83,85,90,91,94,102,104,107,108,109,112,117,118],result_by_model_nam:1,result_collector:25,result_dir:102,result_handl:67,result_writ:[1,25],results_by_model_nam:25,results_df:[1,2,25],resulttyp:118,resultwrit:[25,102],resum:104,retain:[11,33,53,112],retriev:[14,27,29,40,67,85,94,95,96,111],return_trained_model:19,reus:[53,67,118],revers:[29,49,67],reverse_sigmoid:[49,105],rfe:[0,30,47],rfecv:31,rferesult:31,rfestep:31,rgb:107,ridg:60,right:44,rightmost:[97,111],rmse:24,rmsprop:85,rng:109,rnn:[68,73,74],rnn_type:83,rnnencoderfactori:83,rnnencodermodul:83,rnntype:83,robust:49,robustscal:12,room:2,root:24,roughli:49,row:[2,9,11,26,39,44,46,67,95,107,117],row_filter_queri:95,row_kei:95,rowkei:95,rprop:85,rrse:24,rudimentari:2,rule:[11,25,26,33,34,51,53,67,68,95,112,117],rulebaseddataframetransform:11,rulebasedfeaturegener:33,rulebasedtensoris:[2,67,68],rulebasedvectorclassificationmodel:117,rulebasedvectorclassificationmodelevalu:26,rulebasedvectorregressionmodel:[51,117],rulebasedvectorregressionmodelevalu:26,ruletempl:[8,11,33],run:[1,29,31,46,49,88,90,91,104],run_cli:104,run_id:90,run_main:104,s3_object:102,s3object:102,s:[1,2,6,8,9,11,21,22,24,25,26,27,29,31,33,39,46,48,49,53,58,61,62,67,68,73,74,83,85,90,91,94,97,100,102,103,104,105,107,109,112,117,118,119],sachain:49,sacostvalu:[46,49],sacostvaluenumer:[46,49],safe:[101,108],sahyperopt:46,sai:[1,2],said:33,same:[1,8,9,11,21,22,25,26,33,36,46,49,53,56,58,62,67,68,73,74,83,90,94,97,107,109,111,117,118],sampl:[1,2,36,67,83,110],sampling_interval_second:110,saoper:[46,49],saprobabilityfunct:49,saprobabilityfunctionconst:49,saprobabilityfunctionlinear:49,saprobabilityfunctionreversesigmoid:49,saprobabilityschedul:49,sastat:[46,49],satemperatureschedul:49,satemperaturescheduleexponenti:49,satemperatureschedulefix:49,satemperatureschedulepow:49,satemperatureschedulereversesigmoid:49,satemperatureschedulereversesigmoidsymmetr:49,satisfi:83,save:[1,14,26,29,39,46,67,91,94,102,109],save_on_upd:[14,94],save_result:67,scalar:[11,33,49,56,62,67,85,107,118],scalarmapp:109,scale:[11,12,50,58,59,60,67,68,73,85,105],scale_input:67,scale_output:67,scaled_float:50,scaled_int:50,scaled_output:[2,67,85],scaled_valu:50,scaledoutput:85,scaler:[12,67,68,73],scatter:[24,25],scatter_plot_point_color:24,scatterplot:109,scenario:1,schedul:49,schedule_factori:49,scienc:1,scikit:[1,2,9,29,36,58,59,60],scope:104,score:[22,24,29,85],scratch:[46,49],sd:67,sdk:88,seaborn:21,search:[0,37,46,97,111],search_orientation_angl:37,search_po:37,search_radius_m:36,searchorientationangl:37,searchpo:37,second:[1,2,9,24,37,49,50,61,85,94,104,109,110],secondari:109,secret:104,see:[1,3,9,11,21,22,24,25,29,33,36,44,46,48,49,53,59,60,74,80,83,85,94,95,119],seed:[3,19,26,29,48,49,59,60],seek:1,seen:[13,97],segment:[37,109],segpoint1:37,segpoint2:37,segreg:[56,62],select:[2,11,31,68,85,112],self:[2,44,58,67,109,117],semant:[1,56,62,112,117],sens:[1,117],sensai:[2,3,5,6,7,8,9,11,12,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,41,42,43,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,69,70,73,74,76,77,79,82,83,85,86,88,89,90,91,93,94,95,96,97,101,102,103,105,106,107,109,111,112,114,117,118,119],sensibl:2,sensor:1,sepal:1,separ:[2,9,11,24,29,33,56,62,73,74,85,94],seq:[0,47,66,71,82,83,111,118],seq_length:83,seq_model:[0,47,66,71,81],seq_modul:[0,47,66,71,81,82],sequenc:[0,1,2,3,6,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,29,33,40,46,47,48,49,50,53,59,60,67,68,76,77,79,80,82,83,85,92,95,97,101,102,107,109,112,117,118],sequencevectoris:[82,118],sequenti:[1,109],sergei:80,seri:[2,8,11,19,21,22,24,26,49,53,73,74,85,97,109,113],serial:46,serialis:[94,95,108],serialisedpropertyload:95,series_nam:49,serv:[1,2,50,68,86,117],server:90,servic:95,session:64,set:[0,2,5,6,9,11,12,14,19,21,22,24,25,26,27,31,33,34,36,40,42,46,48,53,56,59,60,62,64,67,68,73,74,76,79,82,85,86,94,95,96,97,104,107,108,109,112,117,118],set_cluster:[6,36],set_configure_callback:104,set_data_splitt:26,set_feature_gener:117,set_keras_sess:64,set_module_byt:67,set_nam:[11,21,33,117,118],set_normalisation_check_threshold:67,set_param:[58,97],set_regex:11,set_titl:2,set_to_drop:11,set_to_keep:11,set_torch_modul:67,set_tracked_experi:[26,91],set_value_for_refer:95,setosa:1,setstat:108,settodrop:11,settokeep:11,sever:[1,11,19,25,51,58,94,118],sgd:[59,60,85],sha1:100,shall:[1,2,6,11,13,19,25,31,33,34,36,46,49,50,53,59,60,62,67,68,73,82,85,91,94,101,104,108,109,112,117,118],shaoq:80,shape:[2,9,14,21,39,40,41,42,44,49,56,61,62,67,74,80,83,85,107],shapefil:[39,40],share:[11,117],shift:[44,80],shorter:118,should:[1,2,3,6,8,14,21,22,25,29,33,36,40,50,56,62,67,68,83,86,89,90,91,94,95,96,101,109,112,117],show:[25,109],show_plot:[1,25],shown:[1,80],shrinkag:85,shrinkage_clip:[2,85],shrinkageclip:85,shuffl:[1,2,9,19,26,29,56,68,85,86],sigmoid:[2,49,65,69,74,76,77,105],signific:[50,113],significant_digit:[50,113],significantli:118,silhouettescor:23,similar:[31,42,80],similarli:[1,2,25,29],simpl:[0,2,13,25,64,94,107],simpli:[1,2,6,8,25,33,67,82],simplifi:83,simul:[46,49],simulatedann:[46,49],simultan:[68,101],sinc:[2,14,67,73,80,94,95,96,117],singl:[1,6,8,11,19,21,22,25,26,33,39,48,51,56,58,62,67,68,82,83,85,88,107,112,117,118],single_lat:83,single_output:83,single_output_mean:83,singlecolumndistancemetr:14,singletargetdecoderfactori:83,singletargetdecodermodul:83,singleton:[34,104],situat:1,size:[2,5,7,9,39,42,59,60,61,67,68,73,74,83,85,86,95,107,109],skip:[11,46,73,74,80,83,102],skip_empti:102,sklearn:[0,1,2,3,7,9,11,12,29,31,34,36,39,47,48,58,59,60,61,112,118,119],sklearn_bas:[0,1,2,3,47,48,57,59,60,61,119],sklearn_classif:[0,47,57],sklearn_clust:[0,4,39,47],sklearn_input_transform:58,sklearn_output_transform:58,sklearn_quantil:[0,47],sklearn_regress:[0,47,57],sklearn_splitt:9,sklearn_transform:[0,10,11,47],sklearnclustererprotocol:[7,39],sklearncoordinateclust:39,sklearndecisiontreevectorclassificationmodel:[1,59],sklearndecisiontreevectorregressionmodel:60,sklearndummyvectorregressionmodel:60,sklearneuclideancluster:7,sklearnextratreesvectorregressionmodel:60,sklearngeocoordcluster:36,sklearngradientboostingvectorregressionmodel:60,sklearnkneighborsvectorclassificationmodel:59,sklearnkneighborsvectorregressionmodel:60,sklearnlinearlassoregressionvectorregressionmodel:60,sklearnlinearregressionvectorregressionmodel:60,sklearnlinearridgeregressionvectorregressionmodel:60,sklearnlinearsvrvectorregressionmodel:60,sklearnlogisticregressionvectorclassificationmodel:59,sklearnmlpvectorclassificationmodel:59,sklearnmultilayerperceptronvectorregressionmodel:60,sklearnmultinomialnbvectorclassificationmodel:59,sklearnrandomforestvectorclassificationmodel:[1,2,59],sklearnrandomforestvectorregressionmodel:60,sklearnsvcvectorclassificationmodel:59,sklearnsvrvectorregressionmodel:60,sklearntransformerfactoryfactori:[11,12,34],sklearntransformerprotocol:[11,12],slice:[68,73,74,83,94,97,111],slicedpicklepersistentlist:94,slope:49,smaller:[36,42,49,97,109,111],smallest:[31,58,59,97,111],smoothl1loss:85,sn:109,snapshot:113,snapshot_compat:113,so:[1,2,6,67,74,80],softmax:69,sole:[46,49],solv:[2,50],solve_path:50,solve_problem:50,solver:[50,59,60],solver_time_second:50,some:[1,2,11,23,25,46,49,58,59,68,80,86,104,107,112,117,118],someth:117,soon:112,sort:[1,11,25,29,31,46,49,58,59,97,107,111],sort_ascend:25,sort_column:25,sort_column_move_to_left:25,sort_column_nam:46,sortcolumn:25,sortcolumnnam:46,sorted_key_value_pair:97,sorted_valu:97,sortedkeysandvalu:97,sortedkeyvaluepair:97,sortedkeyvaluestructur:97,sortedvalu:97,soundli:67,sourc:[3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,41,42,43,44,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,69,70,73,74,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119],space:36,span:44,spanningtre:43,special:[73,83,118],specialis:[1,86],specif:[1,2,11,12,24,39,43,46,49,59,60,83,91,94,97,109,112],specifi:[2,3,11,21,25,26,33,34,46,48,61,67,68,76,80,85,94,102,108],speed:[53,118],split:[1,2,9,19,25,26,31,44,48,67,68,73],split_into_data_set:68,split_into_tensor:[68,73],split_with_indic:9,splitter:[1,9,19,26,67],spread:40,sqlite:94,sqliteconnectionmanag:94,sqlitepersistentkeyvaluecach:94,sqlitepersistentlist:94,sqrt:2,squar:[24,37,60],squared_distance_to:37,src:[1,2],stabl:[9,29,33,36,59,60],stack:2,stackoverflow:44,stage:[1,67,73,74,83],stand:112,standard:[1,24,42,67,85,105],standardis:54,standardscal:[11,12,34],start:[1,2,6,36,46,49,73,85,97,104,112,114],start_epoch:85,start_evalu:85,start_logging_kwarg:88,start_validation_collect:85,stat:[1,21,22,24,25,49,109],state:[46,49,74,83,85,108],state_factori:49,statement:[90,91,104],statist:[21,23,26,27,85,109],stats_dict:26,std:[1,21,105],stddev_siz:23,stddeva:24,stdout:[104,112],steep:49,step:[1,2,31,49,59,60,67,73,74,80],stick:2,still:[2,58,59,62,94,112,117],stop:[2,59,60,85,104,117],stopwatch:104,stopwatchmanag:104,storag:95,storageservic:95,store:[1,6,8,14,25,46,50,53,67,94,95,96],str:[3,5,8,9,11,14,19,21,22,23,24,25,26,29,31,33,34,39,40,43,46,48,50,53,58,59,60,61,69,70,73,74,76,82,85,86,88,89,90,91,94,95,97,100,102,103,104,108,109,110,112,115,117],str_hash:100,str_sklearn_model:58,straightforward:1,straightforwardli:2,strategi:[6,36,60,67],strength:60,string:[0,9,11,21,24,26,29,33,34,37,47,48,53,58,67,83,85,90,91,92,93,94,95,97,100,104,105,107,108,117,118],string_identifi:50,string_valu:103,stringconvert:112,strip:[62,102,107],structur:[95,97,112],sub:112,subclass:[1,2,6,9,112],subdirectori:25,subgraph:43,subplot:2,subsequ:[33,34,67,83,90,91,97,111,118],subset:[6,11],subtitl:[21,22,24,25,29],subtitle_prefix:25,subtract:12,success:[6,107],successfulli:3,suffici:[49,85],suffix:[60,73,102],suggest:25,suit:74,suitabl:[1,11,25,42,46,49,74],sum:[25,29,58,59,85,109],summari:25,summary_df:5,summary_dict:[5,43],sun:80,superclass:112,superset:25,supervis:0,suppli:[1,33,118],support:[1,2,5,8,9,11,26,34,48,58,59,67,93,94,97,100,101,103,109,113,117,118],suppport:1,sure:94,sy:[1,2],symmetr:[12,14,49],system:[6,36,44,90],szegedi:80,t0:49,t1:[49,101],t2:101,t:[1,2,9,11,19,33,42,49,68,91,94,101,111,112,114,118],t_1:33,t_i:33,t_n:33,tabl:[25,46,94,95],table_nam:[94,95,96],table_servic:95,tablebatch:95,tablenam:95,tableservic:95,tag:104,tag_nam:90,tag_valu:90,tagbuild:112,take:[1,2,11,21,22,33,56,61,62,67,68,73,82,83,94,95,117,118],take_input_column_if_pres:[8,33],taken:[25,33,86,104,108],tanh:[59,60,69],target:[1,2,25,33,56,62,67,74,82,83,117,118],target_column:33,target_column_bin:33,target_column_in_features_df:33,target_featur:83,target_feature_dim:83,target_feature_gener:33,target_length:83,target_nam:1,target_seq_length:83,target_sequence_column_nam:82,target_sequence_vectoris:82,target_transform:117,targetcolumn:33,targetcolumnbin:33,targetfeaturegener:33,targetsequencedecoderfactori:83,targetsequencedecodermodul:83,targettransform:117,task:[1,89],task_nam:89,tclusteringevalstat:27,tcontext:91,tcrossvaldata:[19,25],tcrossvalid:25,tdata:94,technic:[1,112],tell:46,temper:49,temperatur:49,templat:[8,11,33],temporari:50,tensor:[2,56,62,67,68,69,74,76,77,80,83,85,86],tensor_model:[0,47,56],tensorflow:[0,1,2,47,65],tensorflowsess:64,tensoris:[2,67,68,82],tensorise_dynam:[67,68],tensoriserclasslabelindic:68,tensoriserdataframefloatvaluesmatrix:[2,68],tensormodel:62,tensorscal:[68,73],tensorscalercentreandscal:68,tensorscalerfromdftsklearntransform:68,tensorscalerfromvectordatascal:68,tensorscalerident:68,tensorshap:[62,107],tensortoscalarclassificationmodel:[56,62],tensortoscalarregressionmodel:[56,62],tensortotensorclassificationmodel:[56,62],tensortotensorregressionmodel:[56,62],tensortransform:[68,85],tensortupl:68,term:[60,74,83,91],termin:90,test:[0,1,2,3,25,26,47,53,83,92,95,108],test_data:[25,26],test_fract:[19,25],test_indices_list:19,test_io_data:[1,25,70],test_io_data_dict:25,testdata:26,tevaldata:[19,25,26],tevalstat:[19,21,25,26],tevalstatscollect:[19,25],tevalstatsplot:25,tevalu:25,text:[2,25,89,90,91,102],textdumpazuretableblobbackend:95,textiowrapp:112,tf_base:[0,47,63,65],tf_mlp:[0,47,63],th:[67,85],than:[1,2,11,25,26,29,33,44,49,50,56,58,62,67,68,85,86,91,94,97,111,117,118],thei:[1,2,9,11,33,56,62,67,68,108,111,117],them:[1,2,6,11,25,33,50,56,62,82,94,98,112,117,118],themselv:1,thereaft:[46,49],therefor:[1,2,49,74,80,91,97,117,118],thereof:33,thi:[1,2,3,5,6,7,8,11,19,21,22,24,25,26,27,29,31,33,34,36,39,40,42,46,49,56,58,59,62,67,68,73,74,76,79,80,82,83,85,90,91,93,94,97,98,99,101,102,104,107,108,111,112,115,116,117,118],thing:1,those:[31,56,62],though:[2,112],thread:95,three:[1,107],threshold:[1,6,22,67],through:[6,104,117],throughout:24,thu:[1,2,12,26,46,67,74,83,85,107,112,117,118],tick:109,tight_layout:2,time:[0,1,2,11,19,29,33,37,47,48,50,51,56,62,67,73,74,83,92,94,95,97,104,110,117],time_delta:114,time_of_dai:114,time_period_sec:94,timedelta:[104,114],timeinterv:114,timeperiodsec:94,timerangeneighborsprovid:53,timestamp:[37,46,53,114],timestamps_column:53,tinputoutputdata:9,titl:[24,109],title_add:[22,24,109],tkei:[94,97],tmetric:[21,22,23],tmodel:[19,25],to_2d_arrai:12,to_data_fram:21,to_dft:33,to_feature_gener:[8,11],to_float_arrai:99,to_geodf:[39,40,41,43],to_hex:109,to_placeholder_rul:11,to_rul:11,to_str:112,to_tensor:68,to_torch_data_load:9,togeth:[9,21,22],tol:60,told:46,too:[67,101],took:2,top2accuraci:1,top:[1,46],torch:[0,47,67,68,69,73,74,76,77,79,80,82,83,85,86],torch_bas:[0,2,47,66,73,74,76,77,79,82],torch_data:[0,2,47,66,67,73,82,85,86],torch_data_set_provider_factori:67,torch_enum:[0,47,66,67,74,76,83,85],torch_eval_util:[0,47,66],torch_function_from_ani:69,torch_mlp_model:2,torch_model:[0,47,66,74,82,83],torch_model_factori:[2,67,79],torch_modul:[0,47,66],torch_opt:[0,2,47,66,67,73,76,79,82],torchautoregressiveresulthandl:67,torchdataset:[67,68,85,86],torchdatasetfromdatafram:68,torchdatasetfromdataframesdynamicallytensoris:68,torchdatasetfromdataframespretensoris:68,torchdatasetfromtensor:68,torchdatasetfromtorchtextdataset:86,torchdatasetprovid:[2,67,68,85,86],torchdatasetproviderfactori:[2,67],torchdatasetproviderfactoryclassificationdefault:67,torchdatasetproviderfactoryregressiondefault:67,torchdatasetproviderfromdatautil:68,torchdatasetproviderfromtorchtextdataset:86,torchdatasetproviderfromvectordatautil:68,torchmodel:[67,79,82,85],torchmodelfactoryfrommodul:[2,67],torchmodelfittingstrategi:67,torchmodelfittingstrategydefault:67,torchmodelfrommodul:[2,67],torchmodelfrommodulefactori:67,torchtext:[0,47,66],torchtextdatasetfromdatafram:86,torchvectorclassificationmodel:[2,67,73,76],torchvectorregressionmodel:[2,67,76,79,82],torchvectorregressionmodelevaluationutil:70,tostring_include_preprocessor:117,tostringexcludeexcept:112,tostringmixin:[9,11,21,26,29,33,37,67,83,85,93,97,105,112,117,118],total:[48,68,74,86,104],total_epoch:[67,85],total_weight:43,totalepoch:2,toward:44,tplot:109,track:[0,1,19,25,26,46,47,88,89,90,91,107,118],track_chang:107,track_figur:[89,90,91],track_metr:[19,91],track_tag:90,track_text:[89,90,91],track_valu:91,tracked_experi:[25,26,91],trackedazuremlevalu:88,trackedazuremlexperi:88,trackedexperi:[25,26,88,89,90,91],tracking_bas:[0,19,25,26,46,47,87,88,89,90],tracking_context:[19,25],tracking_uri:90,trackingcontext:[19,25,89,90,91],trackingmixin:[26,46,91],trail:[102,103],train:[0,2,11,19,25,26,31,33,48,51,56,58,59,60,62,67,68,73,74,76,79,80,85,86,89,117,118],train_fract:[2,85],trained_model:19,trainer:56,trainfract:85,training_context:67,training_io_data:1,training_log:2,training_loss_sequ:85,trainingcontext:[67,117],traininginfo:[67,85],transact:[94,95],transform:[0,2,8,11,12,13,26,29,31,33,34,44,49,58,62,67,68,85,107,109,117,118],transformer_factori:11,transient_properti:108,transpar:109,treat:[22,83],tree:[1,2,3,43,48,119],tree_find:43,tri:108,triangul:43,trigger:[11,67],tripl:26,trival:97,trivial:67,true_compon:112,true_label:[23,27],trueclass:2,truth:[1,21,22,23,26,40,56,62,68,85,117],ts:114,ts_next_month:114,tsastat:49,tslib:[37,104,114],tsortedkeyvaluestructur:97,ttorchvectorclassificationmodel:67,ttorchvectorregressionmodel:67,tupl:[1,6,9,12,14,19,21,22,23,24,25,26,29,33,36,37,40,44,45,46,49,53,61,62,67,68,73,85,86,94,97,101,102,109,112,115,118],turn:1,tutori:[1,2],tvalu:[14,94,97],tvectormodel:117,tvectormodelbas:117,tvectorregressionmodel:117,two:[1,2,6,11,24,29,36,37,43,44,68,74,80,85,86,94,97,104,109,111,112],tx:45,txt:95,ty:45,type:[0,1,2,7,11,14,19,21,22,25,26,29,40,43,47,48,53,58,59,83,92,94,95,97,99,101,107,113,117,118],typic:[1,6,26,33,51,67,74,104,117],typing_extens:[7,12,83],ufunc:11,ultim:[2,6,36,74,85,94,117],unchang:109,undefin:[97,103],under:[14,25,26,29,90,94,95,96,118],underli:[2,26,33,67,117,118],underscor:112,understand:95,understood:[1,80,109],unfortun:108,uniform:117,uniformli:12,union:[2,3,5,6,11,12,14,19,21,22,24,25,26,28,29,31,33,34,39,40,41,42,44,46,48,54,59,60,67,68,69,70,73,74,76,79,83,85,86,94,95,99,101,103,108,112,115,117,118],uniqu:[9,11,109,118],unique_id_provid:118,unique_id_retriev:118,unit:[1,9,44,83,85],unit_max:105,unknown:[11,13,34,97],unless:[11,29,68,94,102,112],unmatch:[11,34],unmodifi:[1,25],unnecessari:6,unnormalised_log_prob:69,unpad:118,unpickl:94,unscal:50,unset_tracked_experi:91,unset_valu:36,unsort:25,unsorted_key_value_pair:97,unsqueez:2,unsupport:[11,33],until:[6,31,94,95,118],untransform:117,unwant:[67,112],up:[1,9,33,37,53,112,117,118],updat:[6,36,46,49,94,95],upon:[2,46,58,90,104,112],upper:[50,61,111],upper_bound_kei:[97,111],upperboundkei:111,uri:90,us:[0,2,3,6,7,8,11,14,19,21,22,24,25,26,27,29,31,33,34,36,44,46,48,49,53,56,58,59,60,61,62,64,67,68,73,74,76,80,82,83,85,86,90,91,94,95,96,97,101,104,108,109,110,111,112,115,117,118,119],usag:109,use_balanced_class_weight:[48,58,59,119],use_batch_normalis:[79,80],use_cach:118,use_combined_eval_stat:28,use_cross_valid:[1,25,28],use_label_encod:[58,59],use_shrinkag:[2,85],use_singleton:34,use_target_feature_generator_for_train:33,usearrayvalu:11,usebalancedclassweight:[1,2],usecrossvalid:25,uselabelencod:[1,2],user:[1,33,46,49,96,112],useshrinkag:85,usesingleton:34,usual:[1,11,23,25,31,49,107,112],utf:112,util:[0,2,5,8,9,11,14,19,21,25,26,29,33,37,39,40,45,46,47,53,67,83,85,93,94,95,96,97,101,102,103,105,106,107,109,111,112,114,117,118],utilis:11,utm:44,v0:49,v1:49,v:[46,109],va:12,valid:[0,2,19,25,31,36,43,46,67,68,85,86,94,102,117],valid_extens:102,valid_other_extens:102,validate_coordin:41,validation_fract:[56,64,65],validation_loss_evalu:85,validation_metric_nam:85,validation_metric_sequ:85,validation_tensor_transform:85,validationlossevalu:85,validationtensortransform:85,validity_check_fn:94,valu:[1,2,8,9,11,12,13,14,21,22,23,24,25,26,29,31,33,36,42,46,49,50,53,54,58,60,61,67,68,69,74,83,85,86,88,91,93,94,95,96,97,101,103,105,108,109,111,112,117,118],value_a:33,value_count:11,value_for_index:97,value_identifi:95,value_na:33,value_nam:95,value_slic:97,value_slice_inn:[97,111],value_slice_out:[97,111],value_transform:[0,10,47],value_typ:96,valueerror:[2,101],valuenam:95,valueonehotencod:13,values_dict:91,valuetyp:96,var_nam:61,varchar:94,vari:[11,22,53,83,118],variabl:[11,19,26,29,49,58,60,61,67,68,73,74,82,83,91,117],variable_history_length:83,variant:[49,85,94],variat:85,variou:[1,27,99,101],vb:12,vec1:33,vec1_:33,vec2:33,vec2_:33,vector:[1,2,11,26,33,37,64,74,82,83,85,117,118],vector_data_scal:68,vector_model:[0,1,2,11,16,17,19,24,25,26,28,29,31,33,46,47,51,52,53,58,61,62,64,67,88,90,91,106],vectorclassificationmodel:[1,19,25,28,31,52,53,58,62,67,117],vectorclassificationmodelcrossvalid:[19,25],vectorclassificationmodelcrossvalidationdata:[1,19,25],vectorclassificationmodelevalu:[1,2,25,26],vectorclassificationmodelevaluationdata:[1,19,25,26],vectorclassificationmodelevaluatorparam:26,vectordatascal:[54,68],vectordatautil:68,vectoris:[0,2,11,47,67,82],vectoriserregistri:118,vectorized_condit:11,vectormodel:[0,2,8,11,16,19,25,26,29,31,33,46,62,67,88,106,117],vectormodelbas:[25,26,28,90,91,117],vectormodelcrossvalid:[19,25],vectormodelcrossvalidationdata:[19,29],vectormodelcrossvalidatorparam:[1,19,25,31,70],vectormodelevalu:[25,26],vectormodelevaluationdata:26,vectormodelfittablebas:[26,117],vectormodelwithseparatefeaturegener:106,vectorregressionmodel:[1,17,19,24,25,28,31,51,53,58,61,62,64,67,117],vectorregressionmodelcrossvalid:[19,25],vectorregressionmodelcrossvalidationdata:[19,25],vectorregressionmodelevalu:[25,26],vectorregressionmodelevaluationdata:[19,25,26],vectorregressionmodelevaluatorparam:26,vectortorchmodel:[2,67,76,79],velid:85,verbos:[1,2,104,118],veri:[1,2,25,97],verify_column_nam:33,versa:[44,50],versicolor:1,version:[0,11,33,47,92,94,112],via:[1,2,3,6,11,25,26,29,33,34,46,48,49,67,74,82,85,91,94,95,104,112,118],vice:[44,50],view:[2,9,95],virginica:1,visit:25,visitor:25,visual:40,visualis:[21,22,25,26,44],vl:118,vmeasurescor:23,vote:53,vs:31,w:[25,29,83,112],wa:[1,2,26,27,31,33,34,37,40,46,49,62,64,93,94,102,117,118],wai:[11,56,62,67,95],wait:94,want:[1,2,11,25,90,91,112,118],warm_start:[1,2],warn:[2,67,98,104],watch:104,wc:[6,36],we:[1,2,3,6,24,36,42,58,59,62,67,73,83,90,91,93,107,117,118],weight:[14,17,43,46,48,49,53,58,59,85,93],weightedmean:93,well:[1,2,25,34,62,94,104,112,113],went:2,were:[6,9,23,25,31,33,36,67,107],wgs84:37,what:[1,2,6,74,76,101],whatev:[1,117],when:[1,8,9,11,12,25,33,34,36,46,49,74,94,98,101,104,112,113,117,118],whenev:[1,2,26,67,108],where:[1,2,6,8,9,11,12,13,19,22,23,24,25,26,29,31,33,34,36,37,43,44,46,49,53,58,61,62,64,67,68,73,74,80,83,85,86,90,91,94,95,97,107,108,109,111,112,117,118],whether:[6,8,9,11,12,13,19,21,22,24,25,26,27,29,31,33,34,36,39,46,48,49,50,53,56,58,59,60,62,64,67,68,76,80,82,83,85,86,90,91,93,94,102,103,104,108,109,111,112,117,118],which:[1,2,6,8,9,11,12,13,14,19,21,22,24,25,26,29,31,33,34,36,37,40,46,48,49,53,58,59,60,62,64,67,68,73,74,76,79,80,82,83,85,86,90,91,93,94,95,96,97,98,102,103,104,107,108,109,110,111,112,117,118],whilst:50,white:109,whitespac:102,whole:11,whose:[8,11,12,13,22,33,44,46,50,62,85,93,94,104,109,110,117],width:[1,107,109],wikipedia:80,window:[83,94,109],window_featur:83,window_length:83,wise:95,wish:27,with_altern:112,with_autoregressive_result_handl:67,with_cent:12,with_class_nam:100,with_compon:112,with_condit:112,with_data_frame_splitt:67,with_feature_collector:117,with_feature_gener:117,with_feature_transform:117,with_input_tensoris:[2,67],with_input_transform:117,with_mean:12,with_nam:[1,2,11,117],with_normalisation_check_threshold:67,with_output_tensor_to_array_convert:67,with_output_tensoris:67,with_output_transform:117,with_raw_input_transform:117,with_scal:12,with_sklearn_input_transform:58,with_sklearn_output_transform:58,with_std:12,with_target_transform:117,with_torch_data_set_provider_factori:67,withfeaturecollector:117,withfeaturegener:117,within:[1,2,11,14,33,36,40,67,68,80,82,90,94,95,97,103,112,117],without:[2,8,9,11,12,22,33,46,53,59,60,80,83,85,102,104,112],work:[1,2,6,25,33,62,64,83],worker:95,workflow:25,workspac:88,world:1,worst:31,worstvalu:23,would:[1,46,49,62,67,68,108,112,117],wrap:[0,6,8,36,48,53,67,95,110],wrappedclust:[6,36],wrapper:[1,6,7,33,39,43,83,90,91,95],write:[1,2,25,50,91,95,102],write_csv:25,write_data_frame_csv:25,write_data_frame_csv_fil:102,write_data_frame_text_fil:102,write_eval_stat:25,write_figur:[25,102],write_individual_result:25,write_per_dataset_result:25,write_pickl:102,write_property_valu:95,write_text_fil:102,write_text_file_lin:102,write_visitor_result:25,writer:[25,102],written:[1,2,25,46,102,104],wrong:2,www:44,x0:105,x:[2,7,16,21,22,25,33,44,56,61,62,67,68,74,77,80,83,85,105,106,109,112,117],x_column:44,x_data:73,x_label:109,xgbclassifi:119,xgbgradientboostedvectorclassificationmodel:119,xgbgradientboostedvectorregressionmodel:119,xgboost:[0,1,47,58,59],xgbrandomforestvectorclassificationmodel:119,xgbrandomforestvectorregressionmodel:119,xgbregressor:119,xgbrfclassifi:119,xgbrfregressor:119,xiangyu:80,xlabel:109,xlim:109,xtick:109,xtick_label:109,xtick_major:109,xtick_minor:109,xy:36,y:[21,22,25,33,44,56,62,67,68,85,106,109,117,118],y_data:73,y_label:109,y_predict:[21,22,24,61],y_predicted_class_prob:22,y_row:44,y_true:[21,22,24,61],yet:[1,2,29,80,94],yield:[11,31],ylabel:109,ylim:109,you:[1,2,11,25,27,46,67,108,117,118],your:[1,6,67,117],ytick_label:109,ytick_major:109,z0:95,z:95,za:95,zero:[11,13,22,34,62,104,118],zero_denominator_metric_valu:22,zero_valu:22,zerovalu:22,zhang:80,zip:2,zoom:45},titles:["sensAI - the Python library for sensible AI","Introduction to sensAI: Supervised Learning with VectorModels","Neural Networks","catboost","clustering","clustering_base","greedy_clustering","sklearn_clustering","columngen","data","data_transformation","dft","sklearn_transformer","value_transformation","distance_metric","ensemble","ensemble_base","models","evaluation","crossval","eval_stats","eval_stats_base","eval_stats_classification","eval_stats_clustering","eval_stats_regression","eval_util","evaluator","evaluator_clustering","metric_computation","feature_importance","feature_selection","rfe","featuregen","feature_generator","feature_generator_registry","geoanalytics","geo_clustering","geo_coords","geopandas","coordinate_clustering","coordinate_clustering_ground_truth","coordinates","geometry","graph","local_coords","map_tiles","hyperopt","Modules","lightgbm","local_search","minizinc","multi_model","naive_bayes","nearest_neighbors","normalisation","pytorch_lightning","pl_models","sklearn","sklearn_base","sklearn_classification","sklearn_regression","sklearn_quantile","tensor_model","tensorflow","tf_base","tf_mlp","torch","torch_base","torch_data","torch_enums","torch_eval_util","torch_models","lstnet","lstnet_models","lstnet_modules","mlp","mlp_models","mlp_modules","residualffn","residualffn_models","residualffn_modules","seq","seq_models","seq_modules","torch_modules","torch_opt","torchtext","tracking","azure_tracking","clearml_tracking","mlflow_tracking","tracking_base","util","aggregation","cache","cache_azure","cache_mysql","datastruct","deprecation","dtype","hash","helper","io","jscode","logging","math","multiprocessing","pandas","pickle","plot","profiling","sequences","string","test","time","typing","version","vector_model","vectoriser","xgboost"],titleterms:{adapt:2,aggreg:93,ai:0,an:2,appli:2,azure_track:88,cach:94,cache_azur:95,cache_mysql:96,catboost:3,classif:2,clearml_track:89,cluster:4,clustering_bas:5,cnn:2,columngen:8,compar:1,coordin:41,coordinate_clust:39,coordinate_clustering_ground_truth:40,creat:2,cross:1,crossval:19,custom:2,customis:1,data:[1,9],data_transform:10,datastruct:97,deprec:98,dft:11,distance_metr:14,dtype:99,ensembl:15,ensemble_bas:16,eval_stat:20,eval_stats_bas:21,eval_stats_classif:22,eval_stats_clust:23,eval_stats_regress:24,eval_util:25,evalu:[1,18,26],evaluator_clust:27,featur:1,feature_gener:33,feature_generator_registri:34,feature_import:29,feature_select:30,featuregen:32,frame:1,fulli:1,gener:1,geo_clust:36,geo_coord:37,geoanalyt:35,geometri:42,geopanda:38,graph:43,greedy_clust:6,guid:0,hash:100,helper:101,hyperopt:46,imag:2,indic:0,infer:1,input:2,instanc:2,integr:1,introduct:1,io:102,jscode:103,learn:1,level:1,librari:0,lightgbm:48,local_coord:44,local_search:49,log:[1,104],low:1,lstnet:72,lstnet_model:73,lstnet_modul:74,map_til:45,math:105,metric_comput:28,minizinc:50,mlflow_track:90,mlp:75,mlp_model:76,mlp_modul:77,model:[1,2,17],modul:[0,2,47],multi_model:51,multiprocess:106,naive_bay:52,nearest_neighbor:53,network:2,neural:2,nn:2,normalis:54,output:2,panda:107,pickl:108,pl_model:56,plot:[1,109],predefin:2,profil:110,python:0,pytorch_lightn:55,residualffn:78,residualffn_model:79,residualffn_modul:80,rfe:31,sensai:[0,1],sensibl:0,seq:81,seq_model:82,seq_modul:83,sequenc:111,set:1,simpl:1,sklearn:57,sklearn_bas:58,sklearn_classif:59,sklearn_clust:7,sklearn_quantil:61,sklearn_regress:60,sklearn_transform:12,string:112,supervis:1,tabl:0,tensor_model:62,tensorflow:63,test:113,tf_base:64,tf_mlp:65,time:114,torch:[2,66],torch_bas:67,torch_data:68,torch_enum:69,torch_eval_util:70,torch_model:71,torch_modul:84,torch_opt:85,torchtext:86,track:87,tracking_bas:91,train:1,transform:1,tutori:0,type:115,us:1,util:[1,92],valid:1,value_transform:13,vector_model:117,vectoris:118,vectormodel:1,version:116,wrap:2,xgboost:119}})
\ No newline at end of file
+Search.setIndex({docnames:["index","intro","neural_networks","sensai/catboost","sensai/clustering","sensai/clustering/clustering_base","sensai/clustering/greedy_clustering","sensai/clustering/sklearn_clustering","sensai/columngen","sensai/data","sensai/data_transformation","sensai/data_transformation/dft","sensai/data_transformation/sklearn_transformer","sensai/data_transformation/value_transformation","sensai/distance_metric","sensai/ensemble","sensai/ensemble/ensemble_base","sensai/ensemble/models","sensai/evaluation","sensai/evaluation/crossval","sensai/evaluation/eval_stats","sensai/evaluation/eval_stats/eval_stats_base","sensai/evaluation/eval_stats/eval_stats_classification","sensai/evaluation/eval_stats/eval_stats_clustering","sensai/evaluation/eval_stats/eval_stats_regression","sensai/evaluation/eval_util","sensai/evaluation/evaluator","sensai/evaluation/evaluator_clustering","sensai/evaluation/metric_computation","sensai/feature_importance","sensai/feature_selection","sensai/feature_selection/rfe","sensai/featuregen","sensai/featuregen/feature_generator","sensai/featuregen/feature_generator_registry","sensai/geoanalytics","sensai/geoanalytics/geo_clustering","sensai/geoanalytics/geo_coords","sensai/geoanalytics/geopandas","sensai/geoanalytics/geopandas/coordinate_clustering","sensai/geoanalytics/geopandas/coordinate_clustering_ground_truth","sensai/geoanalytics/geopandas/coordinates","sensai/geoanalytics/geopandas/geometry","sensai/geoanalytics/geopandas/graph","sensai/geoanalytics/local_coords","sensai/geoanalytics/map_tiles","sensai/hyperopt","sensai/index","sensai/lightgbm","sensai/local_search","sensai/minizinc","sensai/multi_model","sensai/naive_bayes","sensai/nearest_neighbors","sensai/normalisation","sensai/pytorch_lightning","sensai/pytorch_lightning/pl_models","sensai/sklearn","sensai/sklearn/sklearn_base","sensai/sklearn/sklearn_classification","sensai/sklearn/sklearn_regression","sensai/sklearn_quantile","sensai/tensor_model","sensai/tensorflow","sensai/tensorflow/tf_base","sensai/tensorflow/tf_mlp","sensai/torch","sensai/torch/torch_base","sensai/torch/torch_data","sensai/torch/torch_enums","sensai/torch/torch_eval_util","sensai/torch/torch_models","sensai/torch/torch_models/lstnet","sensai/torch/torch_models/lstnet/lstnet_models","sensai/torch/torch_models/lstnet/lstnet_modules","sensai/torch/torch_models/mlp","sensai/torch/torch_models/mlp/mlp_models","sensai/torch/torch_models/mlp/mlp_modules","sensai/torch/torch_models/residualffn","sensai/torch/torch_models/residualffn/residualffn_models","sensai/torch/torch_models/residualffn/residualffn_modules","sensai/torch/torch_models/seq","sensai/torch/torch_models/seq/seq_models","sensai/torch/torch_models/seq/seq_modules","sensai/torch/torch_modules","sensai/torch/torch_opt","sensai/torch/torchtext","sensai/tracking","sensai/tracking/azure_tracking","sensai/tracking/clearml_tracking","sensai/tracking/mlflow_tracking","sensai/tracking/tracking_base","sensai/util","sensai/util/aggregation","sensai/util/cache","sensai/util/cache_azure","sensai/util/cache_mysql","sensai/util/datastruct","sensai/util/deprecation","sensai/util/dtype","sensai/util/hash","sensai/util/helper","sensai/util/io","sensai/util/jscode","sensai/util/logging","sensai/util/math","sensai/util/multiprocessing","sensai/util/pandas","sensai/util/pickle","sensai/util/plot","sensai/util/profiling","sensai/util/sequences","sensai/util/string","sensai/util/test","sensai/util/time","sensai/util/typing","sensai/util/version","sensai/vector_model","sensai/vectoriser","sensai/xgboost"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":5,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,nbsphinx:4,sphinx:56},filenames:["index.rst","intro.ipynb","neural_networks.ipynb","sensai/catboost.rst","sensai/clustering.rst","sensai/clustering/clustering_base.rst","sensai/clustering/greedy_clustering.rst","sensai/clustering/sklearn_clustering.rst","sensai/columngen.rst","sensai/data.rst","sensai/data_transformation.rst","sensai/data_transformation/dft.rst","sensai/data_transformation/sklearn_transformer.rst","sensai/data_transformation/value_transformation.rst","sensai/distance_metric.rst","sensai/ensemble.rst","sensai/ensemble/ensemble_base.rst","sensai/ensemble/models.rst","sensai/evaluation.rst","sensai/evaluation/crossval.rst","sensai/evaluation/eval_stats.rst","sensai/evaluation/eval_stats/eval_stats_base.rst","sensai/evaluation/eval_stats/eval_stats_classification.rst","sensai/evaluation/eval_stats/eval_stats_clustering.rst","sensai/evaluation/eval_stats/eval_stats_regression.rst","sensai/evaluation/eval_util.rst","sensai/evaluation/evaluator.rst","sensai/evaluation/evaluator_clustering.rst","sensai/evaluation/metric_computation.rst","sensai/feature_importance.rst","sensai/feature_selection.rst","sensai/feature_selection/rfe.rst","sensai/featuregen.rst","sensai/featuregen/feature_generator.rst","sensai/featuregen/feature_generator_registry.rst","sensai/geoanalytics.rst","sensai/geoanalytics/geo_clustering.rst","sensai/geoanalytics/geo_coords.rst","sensai/geoanalytics/geopandas.rst","sensai/geoanalytics/geopandas/coordinate_clustering.rst","sensai/geoanalytics/geopandas/coordinate_clustering_ground_truth.rst","sensai/geoanalytics/geopandas/coordinates.rst","sensai/geoanalytics/geopandas/geometry.rst","sensai/geoanalytics/geopandas/graph.rst","sensai/geoanalytics/local_coords.rst","sensai/geoanalytics/map_tiles.rst","sensai/hyperopt.rst","sensai/index.rst","sensai/lightgbm.rst","sensai/local_search.rst","sensai/minizinc.rst","sensai/multi_model.rst","sensai/naive_bayes.rst","sensai/nearest_neighbors.rst","sensai/normalisation.rst","sensai/pytorch_lightning.rst","sensai/pytorch_lightning/pl_models.rst","sensai/sklearn.rst","sensai/sklearn/sklearn_base.rst","sensai/sklearn/sklearn_classification.rst","sensai/sklearn/sklearn_regression.rst","sensai/sklearn_quantile.rst","sensai/tensor_model.rst","sensai/tensorflow.rst","sensai/tensorflow/tf_base.rst","sensai/tensorflow/tf_mlp.rst","sensai/torch.rst","sensai/torch/torch_base.rst","sensai/torch/torch_data.rst","sensai/torch/torch_enums.rst","sensai/torch/torch_eval_util.rst","sensai/torch/torch_models.rst","sensai/torch/torch_models/lstnet.rst","sensai/torch/torch_models/lstnet/lstnet_models.rst","sensai/torch/torch_models/lstnet/lstnet_modules.rst","sensai/torch/torch_models/mlp.rst","sensai/torch/torch_models/mlp/mlp_models.rst","sensai/torch/torch_models/mlp/mlp_modules.rst","sensai/torch/torch_models/residualffn.rst","sensai/torch/torch_models/residualffn/residualffn_models.rst","sensai/torch/torch_models/residualffn/residualffn_modules.rst","sensai/torch/torch_models/seq.rst","sensai/torch/torch_models/seq/seq_models.rst","sensai/torch/torch_models/seq/seq_modules.rst","sensai/torch/torch_modules.rst","sensai/torch/torch_opt.rst","sensai/torch/torchtext.rst","sensai/tracking.rst","sensai/tracking/azure_tracking.rst","sensai/tracking/clearml_tracking.rst","sensai/tracking/mlflow_tracking.rst","sensai/tracking/tracking_base.rst","sensai/util.rst","sensai/util/aggregation.rst","sensai/util/cache.rst","sensai/util/cache_azure.rst","sensai/util/cache_mysql.rst","sensai/util/datastruct.rst","sensai/util/deprecation.rst","sensai/util/dtype.rst","sensai/util/hash.rst","sensai/util/helper.rst","sensai/util/io.rst","sensai/util/jscode.rst","sensai/util/logging.rst","sensai/util/math.rst","sensai/util/multiprocessing.rst","sensai/util/pandas.rst","sensai/util/pickle.rst","sensai/util/plot.rst","sensai/util/profiling.rst","sensai/util/sequences.rst","sensai/util/string.rst","sensai/util/test.rst","sensai/util/time.rst","sensai/util/typing.rst","sensai/util/version.rst","sensai/vector_model.rst","sensai/vectoriser.rst","sensai/xgboost.rst"],objects:{"":[[47,0,0,"-","sensai"]],"sensai.catboost":[[3,1,1,"","CatBoostVectorClassificationModel"],[3,1,1,"","CatBoostVectorRegressionModel"]],"sensai.catboost.CatBoostVectorClassificationModel":[[3,2,1,"","__init__"]],"sensai.catboost.CatBoostVectorRegressionModel":[[3,2,1,"","__init__"]],"sensai.clustering":[[5,0,0,"-","clustering_base"],[6,0,0,"-","greedy_clustering"],[7,0,0,"-","sklearn_clustering"]],"sensai.clustering.clustering_base":[[5,1,1,"","EuclideanClusterer"]],"sensai.clustering.clustering_base.EuclideanClusterer":[[5,1,1,"","Cluster"],[5,2,1,"","__init__"],[5,3,1,"","cluster_identifiers"],[5,2,1,"","clusters"],[5,3,1,"","datapoints"],[5,2,1,"","fit"],[5,2,1,"","get_cluster"],[5,3,1,"","is_fitted"],[5,3,1,"","labels"],[5,2,1,"","noise_cluster"],[5,3,1,"","num_clusters"],[5,2,1,"","summary_df"]],"sensai.clustering.clustering_base.EuclideanClusterer.Cluster":[[5,2,1,"","__init__"],[5,2,1,"","centroid"],[5,2,1,"","radius"],[5,2,1,"","summary_dict"]],"sensai.clustering.greedy_clustering":[[6,1,1,"","GreedyAgglomerativeClustering"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering":[[6,1,1,"","Cluster"],[6,1,1,"","ClusterMerge"],[6,1,1,"","MergeCandidateDeterminationStrategy"],[6,1,1,"","MergeCandidateDeterminationStrategyDefault"],[6,1,1,"","WrappedCluster"],[6,2,1,"","__init__"],[6,2,1,"","apply_clustering"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.Cluster":[[6,2,1,"","merge"],[6,2,1,"","merge_cost"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.ClusterMerge":[[6,2,1,"","__init__"],[6,2,1,"","apply"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.MergeCandidateDeterminationStrategy":[[6,2,1,"","__init__"],[6,2,1,"","iter_candidate_indices"],[6,2,1,"","set_clusterer"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.MergeCandidateDeterminationStrategyDefault":[[6,2,1,"","iter_candidate_indices"]],"sensai.clustering.greedy_clustering.GreedyAgglomerativeClustering.WrappedCluster":[[6,2,1,"","__init__"],[6,2,1,"","compute_merges"],[6,2,1,"","get_cluster_association"],[6,2,1,"","is_merged"],[6,2,1,"","remove_merges"]],"sensai.clustering.sklearn_clustering":[[7,1,1,"","SkLearnClustererProtocol"],[7,1,1,"","SkLearnEuclideanClusterer"]],"sensai.clustering.sklearn_clustering.SkLearnClustererProtocol":[[7,2,1,"","__init__"],[7,2,1,"","fit"],[7,4,1,"","labels_"]],"sensai.clustering.sklearn_clustering.SkLearnEuclideanClusterer":[[7,2,1,"","__init__"]],"sensai.columngen":[[8,1,1,"","ColumnGenerator"],[8,1,1,"","ColumnGeneratorCachedByIndex"],[8,1,1,"","IndexCachedColumnGenerator"]],"sensai.columngen.ColumnGenerator":[[8,2,1,"","__init__"],[8,2,1,"","generate_column"],[8,2,1,"","to_feature_generator"]],"sensai.columngen.ColumnGeneratorCachedByIndex":[[8,2,1,"","__init__"]],"sensai.columngen.IndexCachedColumnGenerator":[[8,2,1,"","__init__"]],"sensai.data":[[9,1,1,"","BaseInputOutputData"],[9,1,1,"","DataFrameSplitter"],[9,1,1,"","DataFrameSplitterColumnEquivalenceClass"],[9,1,1,"","DataFrameSplitterFractional"],[9,1,1,"","DataSplitter"],[9,1,1,"","DataSplitterFractional"],[9,1,1,"","DataSplitterFromDataFrameSplitter"],[9,1,1,"","DataSplitterFromSkLearnSplitter"],[9,1,1,"","DataSplitterStratifiedShuffleSplit"],[9,1,1,"","InputOutputArrays"],[9,1,1,"","InputOutputData"]],"sensai.data.BaseInputOutputData":[[9,2,1,"","__init__"],[9,2,1,"","filter_indices"]],"sensai.data.DataFrameSplitter":[[9,2,1,"","compute_split_indices"],[9,2,1,"","split"],[9,2,1,"","split_with_indices"]],"sensai.data.DataFrameSplitterColumnEquivalenceClass":[[9,2,1,"","__init__"],[9,2,1,"","compute_split_indices"]],"sensai.data.DataFrameSplitterFractional":[[9,2,1,"","__init__"],[9,2,1,"","compute_split_indices"]],"sensai.data.DataSplitter":[[9,2,1,"","split"]],"sensai.data.DataSplitterFractional":[[9,2,1,"","__init__"],[9,2,1,"","split"],[9,2,1,"","split_with_indices"]],"sensai.data.DataSplitterFromDataFrameSplitter":[[9,2,1,"","__init__"],[9,2,1,"","split"]],"sensai.data.DataSplitterFromSkLearnSplitter":[[9,2,1,"","__init__"],[9,2,1,"","split"]],"sensai.data.DataSplitterStratifiedShuffleSplit":[[9,2,1,"","__init__"],[9,2,1,"","is_applicable"]],"sensai.data.InputOutputArrays":[[9,2,1,"","__init__"],[9,2,1,"","filter_indices"],[9,2,1,"","to_torch_data_loader"]],"sensai.data.InputOutputData":[[9,2,1,"","__init__"],[9,2,1,"","compute_input_output_correlation"],[9,2,1,"","filter_index"],[9,2,1,"","filter_indices"],[9,2,1,"","from_data_frame"],[9,3,1,"","input_dim"],[9,3,1,"","output_dim"]],"sensai.data_transformation":[[11,0,0,"-","dft"],[12,0,0,"-","sklearn_transformer"],[13,0,0,"-","value_transformation"]],"sensai.data_transformation.dft":[[11,1,1,"","DFTAggregationOnColumn"],[11,1,1,"","DFTCastCategoricalColumns"],[11,1,1,"","DFTColumnFilter"],[11,1,1,"","DFTConditionalRowFilterOnColumn"],[11,1,1,"","DFTCountEntries"],[11,1,1,"","DFTDRowFilterOnIndex"],[11,1,1,"","DFTDropNA"],[11,1,1,"","DFTFillNA"],[11,1,1,"","DFTFromColumnGenerators"],[11,1,1,"","DFTFromFeatureGenerator"],[11,1,1,"","DFTInSetComparisonRowFilterOnColumn"],[11,1,1,"","DFTKeepColumns"],[11,1,1,"","DFTModifyColumn"],[11,1,1,"","DFTModifyColumnVectorized"],[11,1,1,"","DFTNormalisation"],[11,1,1,"","DFTNotInSetComparisonRowFilterOnColumn"],[11,1,1,"","DFTOneHotEncoder"],[11,1,1,"","DFTRenameColumns"],[11,1,1,"","DFTRoundFloats"],[11,1,1,"","DFTRowFilter"],[11,1,1,"","DFTSkLearnTransformer"],[11,1,1,"","DFTSortColumns"],[11,1,1,"","DFTVectorizedConditionalRowFilterOnColumn"],[11,1,1,"","DataFrameTransformer"],[11,1,1,"","DataFrameTransformerChain"],[11,1,1,"","InverseDataFrameTransformer"],[11,1,1,"","InvertibleDataFrameTransformer"],[11,1,1,"","RuleBasedDataFrameTransformer"]],"sensai.data_transformation.dft.DFTAggregationOnColumn":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTCastCategoricalColumns":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTColumnFilter":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTConditionalRowFilterOnColumn":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTCountEntries":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTDRowFilterOnIndex":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTDropNA":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTFillNA":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTFromColumnGenerators":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTFromFeatureGenerator":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTInSetComparisonRowFilterOnColumn":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTModifyColumn":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTModifyColumnVectorized":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTNormalisation":[[11,1,1,"","Rule"],[11,1,1,"","RuleTemplate"],[11,2,1,"","__init__"],[11,2,1,"","find_rule"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTNormalisation.Rule":[[11,2,1,"","__init__"],[11,2,1,"","matches"],[11,2,1,"","matching_columns"],[11,2,1,"","set_regex"]],"sensai.data_transformation.dft.DFTNormalisation.RuleTemplate":[[11,2,1,"","__init__"],[11,2,1,"","to_placeholder_rule"],[11,2,1,"","to_rule"]],"sensai.data_transformation.dft.DFTNotInSetComparisonRowFilterOnColumn":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTOneHotEncoder":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTRenameColumns":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTRoundFloats":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTRowFilter":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.DFTSkLearnTransformer":[[11,2,1,"","__init__"],[11,2,1,"","apply_inverse"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DFTVectorizedConditionalRowFilterOnColumn":[[11,2,1,"","__init__"],[11,2,1,"","info"]],"sensai.data_transformation.dft.DataFrameTransformer":[[11,2,1,"","__init__"],[11,2,1,"","apply"],[11,2,1,"","fit"],[11,2,1,"","fit_apply"],[11,2,1,"","get_name"],[11,2,1,"","info"],[11,2,1,"","is_fitted"],[11,2,1,"","set_name"],[11,2,1,"","to_feature_generator"],[11,2,1,"","with_name"]],"sensai.data_transformation.dft.DataFrameTransformerChain":[[11,2,1,"","__init__"],[11,2,1,"","append"],[11,2,1,"","find_first_transformer_by_type"],[11,2,1,"","get_names"],[11,2,1,"","info"],[11,2,1,"","is_fitted"]],"sensai.data_transformation.dft.InverseDataFrameTransformer":[[11,2,1,"","__init__"]],"sensai.data_transformation.dft.InvertibleDataFrameTransformer":[[11,2,1,"","apply_inverse"],[11,2,1,"","get_inverse"]],"sensai.data_transformation.dft.RuleBasedDataFrameTransformer":[[11,2,1,"","fit"],[11,2,1,"","is_fitted"]],"sensai.data_transformation.sklearn_transformer":[[12,1,1,"","ManualScaler"],[12,1,1,"","SkLearnTransformerFactoryFactory"],[12,1,1,"","SkLearnTransformerProtocol"],[12,5,1,"","to_2d_array"]],"sensai.data_transformation.sklearn_transformer.ManualScaler":[[12,2,1,"","__init__"],[12,2,1,"","fit"],[12,2,1,"","inverse_transform"],[12,2,1,"","transform"]],"sensai.data_transformation.sklearn_transformer.SkLearnTransformerFactoryFactory":[[12,2,1,"","ManualScaler"],[12,2,1,"","MaxAbsScaler"],[12,2,1,"","MinMaxScaler"],[12,2,1,"","RobustScaler"],[12,2,1,"","StandardScaler"]],"sensai.data_transformation.sklearn_transformer.SkLearnTransformerProtocol":[[12,2,1,"","__init__"],[12,2,1,"","fit"],[12,2,1,"","inverse_transform"],[12,2,1,"","transform"]],"sensai.data_transformation.value_transformation":[[13,1,1,"","ValueOneHotEncoder"]],"sensai.data_transformation.value_transformation.ValueOneHotEncoder":[[13,2,1,"","__init__"],[13,2,1,"","fit"],[13,2,1,"","transform"]],"sensai.distance_metric":[[14,1,1,"","CachedDistanceMetric"],[14,1,1,"","DistanceMatrixDFCache"],[14,1,1,"","DistanceMetric"],[14,1,1,"","EuclideanDistanceMetric"],[14,1,1,"","HellingerDistanceMetric"],[14,1,1,"","IdentityDistanceMetric"],[14,1,1,"","LinearCombinationDistanceMetric"],[14,1,1,"","RelativeBitwiseEqualityDistanceMetric"],[14,1,1,"","SingleColumnDistanceMetric"]],"sensai.distance_metric.CachedDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","distance"],[14,2,1,"","fill_cache"]],"sensai.distance_metric.DistanceMatrixDFCache":[[14,2,1,"","__init__"],[14,2,1,"","get"],[14,2,1,"","get_all_cached"],[14,2,1,"","num_unfilled_entries"],[14,2,1,"","save"],[14,2,1,"","set"],[14,2,1,"","shape"]],"sensai.distance_metric.DistanceMetric":[[14,2,1,"","distance"]],"sensai.distance_metric.EuclideanDistanceMetric":[[14,2,1,"","__init__"]],"sensai.distance_metric.HellingerDistanceMetric":[[14,2,1,"","__init__"]],"sensai.distance_metric.IdentityDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","distance"]],"sensai.distance_metric.LinearCombinationDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","distance"]],"sensai.distance_metric.RelativeBitwiseEqualityDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","check_input_value"]],"sensai.distance_metric.SingleColumnDistanceMetric":[[14,2,1,"","__init__"],[14,2,1,"","distance"]],"sensai.ensemble":[[16,0,0,"-","ensemble_base"],[17,0,0,"-","models"]],"sensai.ensemble.ensemble_base":[[16,1,1,"","EnsembleClassificationVectorModel"],[16,1,1,"","EnsembleRegressionVectorModel"],[16,1,1,"","EnsembleVectorModel"]],"sensai.ensemble.ensemble_base.EnsembleClassificationVectorModel":[[16,2,1,"","is_regression_model"]],"sensai.ensemble.ensemble_base.EnsembleRegressionVectorModel":[[16,2,1,"","is_regression_model"]],"sensai.ensemble.ensemble_base.EnsembleVectorModel":[[16,2,1,"","__init__"],[16,2,1,"","aggregate_predictions"],[16,2,1,"","compute_all_predictions"]],"sensai.ensemble.models":[[17,1,1,"","AveragingVectorRegressionModel"]],"sensai.ensemble.models.AveragingVectorRegressionModel":[[17,2,1,"","__init__"],[17,2,1,"","aggregate_predictions"]],"sensai.evaluation":[[19,0,0,"-","crossval"],[20,0,0,"-","eval_stats"],[25,0,0,"-","eval_util"],[26,0,0,"-","evaluator"],[27,0,0,"-","evaluator_clustering"],[28,0,0,"-","metric_computation"]],"sensai.evaluation.crossval":[[19,1,1,"","CrossValidationSplitter"],[19,1,1,"","CrossValidationSplitterDefault"],[19,1,1,"","CrossValidationSplitterNested"],[19,1,1,"","VectorClassificationModelCrossValidationData"],[19,1,1,"","VectorClassificationModelCrossValidator"],[19,1,1,"","VectorModelCrossValidationData"],[19,1,1,"","VectorModelCrossValidator"],[19,1,1,"","VectorModelCrossValidatorParams"],[19,1,1,"","VectorRegressionModelCrossValidationData"],[19,1,1,"","VectorRegressionModelCrossValidator"]],"sensai.evaluation.crossval.CrossValidationSplitter":[[19,2,1,"","create_folds"]],"sensai.evaluation.crossval.CrossValidationSplitterDefault":[[19,2,1,"","__init__"],[19,2,1,"","create_folds"]],"sensai.evaluation.crossval.CrossValidationSplitterNested":[[19,2,1,"","__init__"],[19,2,1,"","create_folds"]],"sensai.evaluation.crossval.VectorModelCrossValidationData":[[19,2,1,"","__init__"],[19,2,1,"","get_eval_stats_collection"],[19,2,1,"","iter_input_output_ground_truth_tuples"],[19,3,1,"","model_name"],[19,2,1,"","track_metrics"]],"sensai.evaluation.crossval.VectorModelCrossValidator":[[19,2,1,"","__init__"],[19,2,1,"","create_metrics_dict_provider"],[19,2,1,"","eval_model"],[19,2,1,"","for_model"]],"sensai.evaluation.crossval.VectorModelCrossValidatorParams":[[19,2,1,"","__init__"]],"sensai.evaluation.eval_stats":[[21,0,0,"-","eval_stats_base"],[22,0,0,"-","eval_stats_classification"],[23,0,0,"-","eval_stats_clustering"],[24,0,0,"-","eval_stats_regression"]],"sensai.evaluation.eval_stats.eval_stats_base":[[21,1,1,"","EvalStats"],[21,1,1,"","EvalStatsCollection"],[21,1,1,"","EvalStatsPlot"],[21,1,1,"","Metric"],[21,1,1,"","PredictionEvalStats"],[21,5,1,"","mean_stats"]],"sensai.evaluation.eval_stats.eval_stats_base.EvalStats":[[21,2,1,"","__init__"],[21,2,1,"","add_metric"],[21,2,1,"","compute_metric_value"],[21,2,1,"","get_all"],[21,2,1,"","metrics_dict"],[21,2,1,"","set_name"]],"sensai.evaluation.eval_stats.eval_stats_base.EvalStatsCollection":[[21,2,1,"","__init__"],[21,2,1,"","agg_metrics_dict"],[21,2,1,"","get_combined_eval_stats"],[21,2,1,"","get_global_stats"],[21,2,1,"","get_metric_by_name"],[21,2,1,"","get_metric_names"],[21,2,1,"","get_metrics"],[21,2,1,"","get_values"],[21,2,1,"","has_metric"],[21,2,1,"","mean_metrics_dict"],[21,2,1,"","plot_distribution"],[21,2,1,"","plot_heat_map"],[21,2,1,"","plot_scatter"],[21,2,1,"","to_data_frame"]],"sensai.evaluation.eval_stats.eval_stats_base.EvalStatsPlot":[[21,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_base.Metric":[[21,2,1,"","__init__"],[21,2,1,"","compute_value_for_eval_stats"],[21,2,1,"","get_paired_metrics"],[21,2,1,"","has_finite_bounds"],[21,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_base.PredictionEvalStats":[[21,2,1,"","__init__"],[21,2,1,"","add"],[21,2,1,"","add_all"]],"sensai.evaluation.eval_stats.eval_stats_classification":[[22,1,1,"","BinaryClassificationCounts"],[22,1,1,"","BinaryClassificationMetric"],[22,1,1,"","BinaryClassificationMetricF1Score"],[22,1,1,"","BinaryClassificationMetricPrecision"],[22,1,1,"","BinaryClassificationMetricPrecisionThreshold"],[22,1,1,"","BinaryClassificationMetricRecall"],[22,1,1,"","BinaryClassificationMetricRecallForPrecision"],[22,1,1,"","BinaryClassificationMetricRecallThreshold"],[22,1,1,"","BinaryClassificationProbabilityThresholdVariationData"],[22,1,1,"","ClassificationEvalStats"],[22,1,1,"","ClassificationEvalStatsCollection"],[22,1,1,"","ClassificationEvalStatsPlot"],[22,1,1,"","ClassificationEvalStatsPlotConfusionMatrix"],[22,1,1,"","ClassificationEvalStatsPlotPrecisionRecall"],[22,1,1,"","ClassificationEvalStatsPlotProbabilityThresholdCounts"],[22,1,1,"","ClassificationEvalStatsPlotProbabilityThresholdPrecisionRecall"],[22,1,1,"","ClassificationMetric"],[22,1,1,"","ClassificationMetricAccuracy"],[22,1,1,"","ClassificationMetricAccuracyMaxProbabilityBeyondThreshold"],[22,1,1,"","ClassificationMetricAccuracyWithoutLabels"],[22,1,1,"","ClassificationMetricBalancedAccuracy"],[22,1,1,"","ClassificationMetricGeometricMeanOfTrueClassProbability"],[22,1,1,"","ClassificationMetricRelFreqMaxProbabilityBeyondThreshold"],[22,1,1,"","ClassificationMetricTopNAccuracy"],[22,1,1,"","ConfusionMatrix"],[22,5,1,"","create_default_binary_classification_metrics"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationCounts":[[22,2,1,"","__init__"],[22,2,1,"","from_eval_stats"],[22,2,1,"","from_probability_threshold"],[22,2,1,"","get_f1"],[22,2,1,"","get_precision"],[22,2,1,"","get_recall"],[22,2,1,"","get_rel_freq_positive"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetric":[[22,2,1,"","__init__"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricF1Score":[[22,2,1,"","__init__"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricPrecision":[[22,2,1,"","__init__"],[22,2,1,"","get_paired_metrics"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricPrecisionThreshold":[[22,2,1,"","__init__"],[22,2,1,"","get_paired_metrics"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricRecall":[[22,2,1,"","__init__"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricRecallForPrecision":[[22,2,1,"","__init__"],[22,2,1,"","compute_value_for_eval_stats"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationMetricRecallThreshold":[[22,2,1,"","__init__"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.BinaryClassificationProbabilityThresholdVariationData":[[22,2,1,"","__init__"],[22,2,1,"","plot_counts"],[22,2,1,"","plot_precision_recall"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStats":[[22,2,1,"","__init__"],[22,2,1,"","get_accuracy"],[22,2,1,"","get_binary_classification_probability_threshold_variation_data"],[22,2,1,"","get_confusion_matrix"],[22,2,1,"","get_misclassified_indices"],[22,2,1,"","metrics_dict"],[22,2,1,"","plot_confusion_matrix"],[22,2,1,"","plot_precision_recall_curve"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsCollection":[[22,2,1,"","__init__"],[22,2,1,"","get_combined_eval_stats"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsPlotConfusionMatrix":[[22,2,1,"","__init__"],[22,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsPlotPrecisionRecall":[[22,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsPlotProbabilityThresholdCounts":[[22,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStatsPlotProbabilityThresholdPrecisionRecall":[[22,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric":[[22,2,1,"","__init__"],[22,2,1,"","compute_value"],[22,2,1,"","compute_value_for_eval_stats"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricAccuracy":[[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricAccuracyMaxProbabilityBeyondThreshold":[[22,2,1,"","__init__"],[22,2,1,"","get_paired_metrics"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricAccuracyWithoutLabels":[[22,2,1,"","__init__"],[22,2,1,"","get_paired_metrics"],[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricBalancedAccuracy":[[22,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricGeometricMeanOfTrueClassProbability":[[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricRelFreqMaxProbabilityBeyondThreshold":[[22,2,1,"","__init__"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetricTopNAccuracy":[[22,2,1,"","__init__"],[22,4,1,"","name"],[22,4,1,"","requires_probabilities"]],"sensai.evaluation.eval_stats.eval_stats_classification.ConfusionMatrix":[[22,2,1,"","__init__"],[22,2,1,"","plot"]],"sensai.evaluation.eval_stats.eval_stats_clustering":[[23,1,1,"","AdjustedMutualInfoScore"],[23,1,1,"","AdjustedRandScore"],[23,1,1,"","CalinskiHarabaszScore"],[23,1,1,"","ClusterLabelsEvalStats"],[23,1,1,"","ClusteringSupervisedEvalStats"],[23,1,1,"","ClusteringSupervisedMetric"],[23,1,1,"","ClusteringUnsupervisedEvalStats"],[23,1,1,"","ClusteringUnsupervisedMetric"],[23,1,1,"","DaviesBouldinScore"],[23,1,1,"","FowlkesMallowsScore"],[23,1,1,"","RemovedCommonNoiseSupervisedMetric"],[23,1,1,"","RemovedNoiseUnsupervisedMetric"],[23,1,1,"","SilhouetteScore"],[23,1,1,"","VMeasureScore"]],"sensai.evaluation.eval_stats.eval_stats_clustering.AdjustedMutualInfoScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.AdjustedRandScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.CalinskiHarabaszScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusterLabelsEvalStats":[[23,4,1,"","AV_SIZE"],[23,4,1,"","MAX_SIZE"],[23,4,1,"","MEDIAN_SIZE"],[23,4,1,"","MIN_SIZE"],[23,4,1,"","NOISE_SIZE"],[23,4,1,"","NUM_CLUSTERS"],[23,4,1,"","STDDEV_SIZE"],[23,2,1,"","__init__"],[23,2,1,"","get_distribution_summary"],[23,2,1,"","metrics_dict"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusteringSupervisedEvalStats":[[23,2,1,"","__init__"],[23,4,1,"","clusterLabelsMask"],[23,2,1,"","from_model"],[23,2,1,"","labels_with_removed_common_noise"],[23,4,1,"","noiseLabelsMask"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusteringSupervisedMetric":[[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusteringUnsupervisedEvalStats":[[23,2,1,"","__init__"],[23,4,1,"","clusterLabelsMask"],[23,2,1,"","from_model"],[23,4,1,"","noiseLabelsMask"]],"sensai.evaluation.eval_stats.eval_stats_clustering.ClusteringUnsupervisedMetric":[[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.DaviesBouldinScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.FowlkesMallowsScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_clustering.RemovedCommonNoiseSupervisedMetric":[[23,2,1,"","compute_value"],[23,2,1,"","compute_value_for_eval_stats"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.RemovedNoiseUnsupervisedMetric":[[23,2,1,"","compute_value"],[23,2,1,"","compute_value_for_eval_stats"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.SilhouetteScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"],[23,4,1,"","worstValue"]],"sensai.evaluation.eval_stats.eval_stats_clustering.VMeasureScore":[[23,2,1,"","compute_value"],[23,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression":[[24,1,1,"","RegressionEvalStats"],[24,1,1,"","RegressionEvalStatsCollection"],[24,1,1,"","RegressionEvalStatsPlot"],[24,1,1,"","RegressionEvalStatsPlotErrorDistribution"],[24,1,1,"","RegressionEvalStatsPlotHeatmapGroundTruthPredictions"],[24,1,1,"","RegressionEvalStatsPlotScatterGroundTruthPredictions"],[24,1,1,"","RegressionMetric"],[24,1,1,"","RegressionMetricMAE"],[24,1,1,"","RegressionMetricMSE"],[24,1,1,"","RegressionMetricMedianAE"],[24,1,1,"","RegressionMetricPCC"],[24,1,1,"","RegressionMetricR2"],[24,1,1,"","RegressionMetricRMSE"],[24,1,1,"","RegressionMetricRRSE"],[24,1,1,"","RegressionMetricStdDevAE"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStats":[[24,2,1,"","HEATMAP_COLORMAP_FACTORY"],[24,4,1,"","HEATMAP_DIAGONAL_COLOR"],[24,4,1,"","HEATMAP_ERROR_BOUNDARY_COLOR"],[24,4,1,"","HEATMAP_ERROR_BOUNDARY_VALUE"],[24,4,1,"","SCATTER_PLOT_POINT_COLOR"],[24,2,1,"","__init__"],[24,2,1,"","compute_mae"],[24,2,1,"","compute_metric_value"],[24,2,1,"","compute_mse"],[24,2,1,"","compute_pcc"],[24,2,1,"","compute_r2"],[24,2,1,"","compute_rmse"],[24,2,1,"","compute_rrse"],[24,2,1,"","compute_std_dev_ae"],[24,2,1,"","create_eval_stats_collection"],[24,2,1,"","plot_error_distribution"],[24,2,1,"","plot_heatmap_ground_truth_predictions"],[24,2,1,"","plot_scatter_ground_truth_predictions"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStatsCollection":[[24,2,1,"","__init__"],[24,2,1,"","get_combined_eval_stats"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStatsPlotErrorDistribution":[[24,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStatsPlotHeatmapGroundTruthPredictions":[[24,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionEvalStatsPlotScatterGroundTruthPredictions":[[24,2,1,"","create_figure"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetric":[[24,2,1,"","compute_abs_errors"],[24,2,1,"","compute_errors"],[24,2,1,"","compute_value"],[24,2,1,"","compute_value_for_eval_stats"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricMAE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricMSE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricMedianAE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricPCC":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricR2":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricRMSE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricRRSE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_stats.eval_stats_regression.RegressionMetricStdDevAE":[[24,2,1,"","compute_value"],[24,4,1,"","name"]],"sensai.evaluation.eval_util":[[25,1,1,"","ClassificationEvalStatsPlotCollector"],[25,1,1,"","ClassificationModelEvaluation"],[25,1,1,"","ClassificationMultiDataModelComparisonData"],[25,1,1,"","EvalStatsPlotCollector"],[25,1,1,"","EvaluationResultCollector"],[25,1,1,"","ModelComparisonData"],[25,1,1,"","ModelComparisonVisitor"],[25,1,1,"","ModelComparisonVisitorAggregatedFeatureImportance"],[25,1,1,"","ModelEvaluation"],[25,1,1,"","MultiDataModelComparisonData"],[25,1,1,"","MultiDataModelEvaluation"],[25,1,1,"","RegressionEvalStatsPlotCollector"],[25,1,1,"","RegressionModelEvaluation"],[25,1,1,"","RegressionMultiDataModelComparisonData"],[25,5,1,"","create_evaluation_util"],[25,5,1,"","create_vector_model_cross_validator"],[25,5,1,"","create_vector_model_evaluator"],[25,5,1,"","eval_model_via_evaluator"]],"sensai.evaluation.eval_util.ClassificationEvalStatsPlotCollector":[[25,2,1,"","__init__"]],"sensai.evaluation.eval_util.ClassificationModelEvaluation":[[25,2,1,"","__init__"]],"sensai.evaluation.eval_util.ClassificationMultiDataModelComparisonData":[[25,2,1,"","get_eval_stats_collection"]],"sensai.evaluation.eval_util.EvalStatsPlotCollector":[[25,2,1,"","__init__"],[25,2,1,"","add_plot"],[25,2,1,"","create_plots"],[25,2,1,"","disable_plots"],[25,2,1,"","get_enabled_plots"]],"sensai.evaluation.eval_util.EvaluationResultCollector":[[25,2,1,"","__init__"],[25,2,1,"","add_data_frame_csv_file"],[25,2,1,"","add_figure"],[25,2,1,"","child"]],"sensai.evaluation.eval_util.ModelComparisonData":[[25,1,1,"","Result"],[25,2,1,"","__init__"],[25,2,1,"","get_best_model"],[25,2,1,"","get_best_model_name"]],"sensai.evaluation.eval_util.ModelComparisonData.Result":[[25,2,1,"","__init__"],[25,4,1,"","cross_validation_data"],[25,4,1,"","eval_data"],[25,2,1,"","iter_evaluation_data"]],"sensai.evaluation.eval_util.ModelComparisonVisitor":[[25,2,1,"","collect_results"],[25,2,1,"","visit"]],"sensai.evaluation.eval_util.ModelComparisonVisitorAggregatedFeatureImportance":[[25,2,1,"","__init__"],[25,2,1,"","collect_results"],[25,2,1,"","get_feature_importance"],[25,2,1,"","plot_feature_importance"],[25,2,1,"","visit"]],"sensai.evaluation.eval_util.ModelEvaluation":[[25,2,1,"","__init__"],[25,2,1,"","compare_models"],[25,2,1,"","compare_models_cross_validation"],[25,2,1,"","create_cross_validator"],[25,2,1,"","create_evaluator"],[25,2,1,"","create_plots"],[25,2,1,"","perform_cross_validation"],[25,2,1,"","perform_simple_evaluation"]],"sensai.evaluation.eval_util.MultiDataModelComparisonData":[[25,2,1,"","__init__"],[25,2,1,"","create_distribution_plots"],[25,2,1,"","get_eval_stats_collection"],[25,2,1,"","get_eval_stats_list"],[25,2,1,"","get_model_description"],[25,2,1,"","get_model_names"],[25,2,1,"","iter_model_results"]],"sensai.evaluation.eval_util.MultiDataModelEvaluation":[[25,2,1,"","__init__"],[25,2,1,"","compare_models"]],"sensai.evaluation.eval_util.RegressionEvalStatsPlotCollector":[[25,2,1,"","__init__"]],"sensai.evaluation.eval_util.RegressionModelEvaluation":[[25,2,1,"","__init__"]],"sensai.evaluation.eval_util.RegressionMultiDataModelComparisonData":[[25,2,1,"","get_eval_stats_collection"]],"sensai.evaluation.evaluator":[[26,1,1,"","ClassificationEvaluatorParams"],[26,1,1,"","EvaluatorParams"],[26,1,1,"","MetricsDictProvider"],[26,1,1,"","MetricsDictProviderFromFunction"],[26,1,1,"","RegressionEvaluatorParams"],[26,1,1,"","RuleBasedVectorClassificationModelEvaluator"],[26,1,1,"","RuleBasedVectorRegressionModelEvaluator"],[26,1,1,"","VectorClassificationModelEvaluationData"],[26,1,1,"","VectorClassificationModelEvaluator"],[26,1,1,"","VectorClassificationModelEvaluatorParams"],[26,1,1,"","VectorModelEvaluationData"],[26,1,1,"","VectorModelEvaluator"],[26,1,1,"","VectorRegressionModelEvaluationData"],[26,1,1,"","VectorRegressionModelEvaluator"],[26,1,1,"","VectorRegressionModelEvaluatorParams"]],"sensai.evaluation.evaluator.ClassificationEvaluatorParams":[[26,2,1,"","__init__"],[26,2,1,"","from_dict_or_instance"]],"sensai.evaluation.evaluator.EvaluatorParams":[[26,2,1,"","__init__"],[26,2,1,"","get_data_splitter"],[26,2,1,"","set_data_splitter"]],"sensai.evaluation.evaluator.MetricsDictProvider":[[26,2,1,"","compute_metrics"]],"sensai.evaluation.evaluator.MetricsDictProviderFromFunction":[[26,2,1,"","__init__"]],"sensai.evaluation.evaluator.RegressionEvaluatorParams":[[26,2,1,"","__init__"],[26,2,1,"","from_dict_or_instance"]],"sensai.evaluation.evaluator.RuleBasedVectorClassificationModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","eval_model"]],"sensai.evaluation.evaluator.RuleBasedVectorRegressionModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","eval_model"]],"sensai.evaluation.evaluator.VectorClassificationModelEvaluationData":[[26,2,1,"","get_misclassified_inputs_data_frame"],[26,2,1,"","get_misclassified_triples_pred_true_input"]],"sensai.evaluation.evaluator.VectorClassificationModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","compute_test_data_outputs"]],"sensai.evaluation.evaluator.VectorClassificationModelEvaluatorParams":[[26,2,1,"","__init__"]],"sensai.evaluation.evaluator.VectorModelEvaluationData":[[26,2,1,"","__init__"],[26,2,1,"","get_data_frame"],[26,2,1,"","get_eval_stats"],[26,3,1,"","input_data"],[26,2,1,"","iter_input_output_ground_truth_tuples"],[26,3,1,"","model_name"]],"sensai.evaluation.evaluator.VectorModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","create_metrics_dict_provider"],[26,2,1,"","eval_model"],[26,2,1,"","fit_model"],[26,2,1,"","set_tracked_experiment"]],"sensai.evaluation.evaluator.VectorRegressionModelEvaluationData":[[26,2,1,"","get_eval_stats_collection"]],"sensai.evaluation.evaluator.VectorRegressionModelEvaluator":[[26,2,1,"","__init__"],[26,2,1,"","compute_test_data_outputs"]],"sensai.evaluation.evaluator.VectorRegressionModelEvaluatorParams":[[26,2,1,"","__init__"]],"sensai.evaluation.evaluator_clustering":[[27,1,1,"","ClusteringModelEvaluator"],[27,1,1,"","ClusteringModelSupervisedEvaluator"],[27,1,1,"","ClusteringModelUnsupervisedEvaluator"]],"sensai.evaluation.evaluator_clustering.ClusteringModelEvaluator":[[27,2,1,"","eval_model"]],"sensai.evaluation.evaluator_clustering.ClusteringModelSupervisedEvaluator":[[27,2,1,"","__init__"],[27,2,1,"","eval_model"]],"sensai.evaluation.evaluator_clustering.ClusteringModelUnsupervisedEvaluator":[[27,2,1,"","__init__"],[27,2,1,"","eval_model"]],"sensai.evaluation.metric_computation":[[28,1,1,"","MetricComputation"],[28,1,1,"","MetricComputationMultiData"],[28,1,1,"","MetricComputationResult"]],"sensai.evaluation.metric_computation.MetricComputation":[[28,2,1,"","__init__"],[28,2,1,"","compute_metric_value"]],"sensai.evaluation.metric_computation.MetricComputationMultiData":[[28,2,1,"","__init__"],[28,2,1,"","compute_metric_value"]],"sensai.evaluation.metric_computation.MetricComputationResult":[[28,2,1,"","__init__"],[28,4,1,"","metric_value"],[28,4,1,"","models"]],"sensai.feature_importance":[[29,1,1,"","AggregatedFeatureImportance"],[29,1,1,"","AggregatedPermutationFeatureImportance"],[29,1,1,"","FeatureImportance"],[29,1,1,"","FeatureImportanceProvider"],[29,5,1,"","compute_permutation_feature_importance_dict"],[29,5,1,"","plot_feature_importance"]],"sensai.feature_importance.AggregatedFeatureImportance":[[29,2,1,"","__init__"],[29,2,1,"","add"],[29,2,1,"","get_aggregated_feature_importance"],[29,2,1,"","get_aggregated_feature_importance_dict"]],"sensai.feature_importance.AggregatedPermutationFeatureImportance":[[29,2,1,"","__init__"],[29,2,1,"","add"],[29,2,1,"","add_cross_validation_data"],[29,2,1,"","get_feature_importance"]],"sensai.feature_importance.FeatureImportance":[[29,2,1,"","__init__"],[29,2,1,"","get_data_frame"],[29,2,1,"","get_feature_importance_dict"],[29,2,1,"","get_sorted_tuples"],[29,2,1,"","plot"]],"sensai.feature_importance.FeatureImportanceProvider":[[29,2,1,"","get_feature_importance"],[29,2,1,"","get_feature_importance_dict"],[29,2,1,"","get_feature_importances"]],"sensai.feature_selection":[[31,0,0,"-","rfe"]],"sensai.feature_selection.rfe":[[31,1,1,"","RFEResult"],[31,1,1,"","RFEStep"],[31,1,1,"","RecursiveFeatureElimination"],[31,1,1,"","RecursiveFeatureEliminationCV"]],"sensai.feature_selection.rfe.RFEResult":[[31,2,1,"","__init__"],[31,2,1,"","get_metric_values_array"],[31,2,1,"","get_num_features_array"],[31,2,1,"","get_selected_features"],[31,2,1,"","get_sorted_steps"],[31,2,1,"","plot_metric_values"]],"sensai.feature_selection.rfe.RFEStep":[[31,2,1,"","__init__"],[31,4,1,"","features"],[31,4,1,"","metric_value"]],"sensai.feature_selection.rfe.RecursiveFeatureElimination":[[31,2,1,"","__init__"],[31,2,1,"","run"]],"sensai.feature_selection.rfe.RecursiveFeatureEliminationCV":[[31,2,1,"","__init__"],[31,2,1,"","run"]],"sensai.featuregen":[[33,0,0,"-","feature_generator"],[34,0,0,"-","feature_generator_registry"]],"sensai.featuregen.feature_generator":[[33,1,1,"","ChainedFeatureGenerator"],[33,1,1,"","FeatureGenerator"],[33,1,1,"","FeatureGeneratorFlattenColumns"],[33,1,1,"","FeatureGeneratorFromColumnGenerator"],[33,1,1,"","FeatureGeneratorFromDFT"],[33,1,1,"","FeatureGeneratorFromNamedTuples"],[33,1,1,"","FeatureGeneratorFromVectorModel"],[33,1,1,"","FeatureGeneratorMapColumn"],[33,1,1,"","FeatureGeneratorMapColumnDict"],[33,1,1,"","FeatureGeneratorNAMarker"],[33,1,1,"","FeatureGeneratorTakeColumns"],[33,1,1,"","FeatureGeneratorTargetDistribution"],[33,1,1,"","MultiFeatureGenerator"],[33,1,1,"","RuleBasedFeatureGenerator"],[33,5,1,"","flattened_feature_generator"]],"sensai.featuregen.feature_generator.ChainedFeatureGenerator":[[33,2,1,"","__init__"],[33,2,1,"","fit_generate"],[33,2,1,"","info"],[33,2,1,"","is_fitted"]],"sensai.featuregen.feature_generator.FeatureGenerator":[[33,2,1,"","__init__"],[33,2,1,"","chain"],[33,2,1,"","concat"],[33,2,1,"","fit"],[33,2,1,"","fit_generate"],[33,2,1,"","flattened"],[33,2,1,"","generate"],[33,2,1,"","get_categorical_feature_name_regex"],[33,2,1,"","get_generated_column_names"],[33,2,1,"","get_name"],[33,2,1,"","get_names"],[33,2,1,"","get_normalisation_rules"],[33,2,1,"","info"],[33,2,1,"","is_categorical_feature"],[33,2,1,"","is_fitted"],[33,2,1,"","set_name"],[33,2,1,"","to_dft"]],"sensai.featuregen.feature_generator.FeatureGeneratorFlattenColumns":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.FeatureGeneratorFromColumnGenerator":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.FeatureGeneratorFromDFT":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorFromNamedTuples":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorFromVectorModel":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.FeatureGeneratorMapColumn":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorMapColumnDict":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorNAMarker":[[33,2,1,"","__init__"]],"sensai.featuregen.feature_generator.FeatureGeneratorTakeColumns":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.FeatureGeneratorTargetDistribution":[[33,2,1,"","__init__"],[33,2,1,"","info"]],"sensai.featuregen.feature_generator.MultiFeatureGenerator":[[33,2,1,"","__init__"],[33,2,1,"","fit_generate"],[33,2,1,"","get_names"],[33,2,1,"","info"],[33,2,1,"","is_fitted"]],"sensai.featuregen.feature_generator.RuleBasedFeatureGenerator":[[33,2,1,"","fit"],[33,2,1,"","is_fitted"]],"sensai.featuregen.feature_generator_registry":[[34,1,1,"","FeatureCollector"],[34,1,1,"","FeatureGeneratorRegistry"]],"sensai.featuregen.feature_generator_registry.FeatureCollector":[[34,2,1,"","__init__"],[34,2,1,"","create_dft_normalisation"],[34,2,1,"","create_dft_one_hot_encoder"],[34,2,1,"","create_feature_transformer_normalisation"],[34,2,1,"","create_feature_transformer_one_hot_encoder"],[34,2,1,"","create_multi_feature_generator"],[34,2,1,"","get_categorical_feature_name_regex"],[34,2,1,"","get_multi_feature_generator"],[34,2,1,"","get_normalisation_rules"]],"sensai.featuregen.feature_generator_registry.FeatureGeneratorRegistry":[[34,2,1,"","__init__"],[34,3,1,"","available_features"],[34,2,1,"","collect_features"],[34,2,1,"","get_feature_generator"],[34,2,1,"","register_factory"]],"sensai.geoanalytics":[[36,0,0,"-","geo_clustering"],[37,0,0,"-","geo_coords"],[38,0,0,"-","geopandas"],[44,0,0,"-","local_coords"],[45,0,0,"-","map_tiles"]],"sensai.geoanalytics.geo_clustering":[[36,1,1,"","DBSCANGeoCoordClusterer"],[36,1,1,"","GeoCoordClusterer"],[36,1,1,"","GreedyAgglomerativeGeoCoordClusterer"],[36,1,1,"","SkLearnGeoCoordClusterer"]],"sensai.geoanalytics.geo_clustering.DBSCANGeoCoordClusterer":[[36,2,1,"","__init__"]],"sensai.geoanalytics.geo_clustering.GeoCoordClusterer":[[36,2,1,"","clusters_indices"],[36,2,1,"","fit_geo_coords"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer":[[36,1,1,"","Cluster"],[36,1,1,"","LocalPoint"],[36,1,1,"","Matrix"],[36,1,1,"","MergeCandidateDeterminationStrategy"],[36,2,1,"","__init__"],[36,2,1,"","clusters_indices"],[36,2,1,"","fit_geo_coords"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer.Cluster":[[36,2,1,"","__init__"],[36,2,1,"","merge"],[36,2,1,"","merge_cost"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer.LocalPoint":[[36,2,1,"","__init__"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer.Matrix":[[36,4,1,"","UNSET_VALUE"],[36,2,1,"","__init__"],[36,2,1,"","get"],[36,2,1,"","set"]],"sensai.geoanalytics.geo_clustering.GreedyAgglomerativeGeoCoordClusterer.MergeCandidateDeterminationStrategy":[[36,2,1,"","__init__"],[36,2,1,"","iter_candidate_indices"],[36,2,1,"","set_clusterer"]],"sensai.geoanalytics.geo_clustering.SkLearnGeoCoordClusterer":[[36,2,1,"","__init__"],[36,2,1,"","clusters_indices"],[36,2,1,"","clusters_local_points"],[36,2,1,"","fit_geo_coords"]],"sensai.geoanalytics.geo_coords":[[37,1,1,"","GeoCoord"],[37,1,1,"","GeoRect"],[37,1,1,"","GpsTracePoint"],[37,5,1,"","abs_angle_difference"],[37,5,1,"","approximate_squared_distance"],[37,5,1,"","closest_point_on_polyline"],[37,5,1,"","closest_point_on_segment"],[37,5,1,"","latitude_per_m"],[37,5,1,"","longitude_per_m"],[37,5,1,"","orientation"]],"sensai.geoanalytics.geo_coords.GeoCoord":[[37,2,1,"","__init__"],[37,2,1,"","distance_to"],[37,2,1,"","latlon"],[37,2,1,"","local_coords"],[37,2,1,"","mean_coord"],[37,2,1,"","squared_distance_to"]],"sensai.geoanalytics.geo_coords.GeoRect":[[37,2,1,"","__init__"],[37,2,1,"","from_circle"]],"sensai.geoanalytics.geo_coords.GpsTracePoint":[[37,2,1,"","__init__"]],"sensai.geoanalytics.geopandas":[[39,0,0,"-","coordinate_clustering"],[40,0,0,"-","coordinate_clustering_ground_truth"],[41,0,0,"-","coordinates"],[42,0,0,"-","geometry"],[43,0,0,"-","graph"]],"sensai.geoanalytics.geopandas.coordinate_clustering":[[39,1,1,"","CoordinateEuclideanClusterer"],[39,1,1,"","SkLearnCoordinateClustering"]],"sensai.geoanalytics.geopandas.coordinate_clustering.CoordinateEuclideanClusterer":[[39,1,1,"","Cluster"],[39,2,1,"","__init__"],[39,2,1,"","clusters"],[39,2,1,"","fit"],[39,2,1,"","get_cluster"],[39,2,1,"","noise_cluster"],[39,2,1,"","plot"],[39,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.coordinate_clustering.CoordinateEuclideanClusterer.Cluster":[[39,2,1,"","__init__"],[39,2,1,"","as_multipoint"],[39,2,1,"","load"],[39,2,1,"","save"],[39,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.coordinate_clustering.SkLearnCoordinateClustering":[[39,2,1,"","__init__"]],"sensai.geoanalytics.geopandas.coordinate_clustering_ground_truth":[[40,1,1,"","PolygonAnnotatedCoordinates"]],"sensai.geoanalytics.geopandas.coordinate_clustering_ground_truth.PolygonAnnotatedCoordinates":[[40,2,1,"","__init__"],[40,2,1,"","get_coordinates_labels"],[40,2,1,"","plot"],[40,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.coordinates":[[41,1,1,"","GeoDataFrameWrapper"],[41,5,1,"","extract_coordinates_array"],[41,5,1,"","validate_coordinates"]],"sensai.geoanalytics.geopandas.coordinates.GeoDataFrameWrapper":[[41,2,1,"","plot"],[41,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.geometry":[[42,5,1,"","alpha_shape"]],"sensai.geoanalytics.geopandas.graph":[[43,1,1,"","CoordinateSpanningTree"],[43,1,1,"","SpanningTree"],[43,5,1,"","delaunay_graph"]],"sensai.geoanalytics.geopandas.graph.CoordinateSpanningTree":[[43,2,1,"","__init__"],[43,2,1,"","multi_line_string"],[43,2,1,"","to_geodf"]],"sensai.geoanalytics.geopandas.graph.SpanningTree":[[43,2,1,"","__init__"],[43,2,1,"","mean_edge_weight"],[43,2,1,"","num_edges"],[43,2,1,"","summary_dict"],[43,2,1,"","total_weight"]],"sensai.geoanalytics.local_coords":[[44,1,1,"","LocalCoordinateSystem"],[44,1,1,"","LocalHexagonalGrid"],[44,5,1,"","fix_polygon"]],"sensai.geoanalytics.local_coords.LocalCoordinateSystem":[[44,2,1,"","__init__"],[44,2,1,"","get_lat_lon"],[44,2,1,"","get_local_coords"]],"sensai.geoanalytics.local_coords.LocalHexagonalGrid":[[44,2,1,"","__init__"],[44,2,1,"","get_hexagon"],[44,2,1,"","get_hexagon_coord_span_for_bounding_box"],[44,2,1,"","get_hexagon_coords_for_point"],[44,2,1,"","get_max_hexagon_column"],[44,2,1,"","get_max_hexagon_row"],[44,2,1,"","get_min_hexagon_column"],[44,2,1,"","get_min_hexagon_row"]],"sensai.geoanalytics.map_tiles":[[45,1,1,"","MapTile"],[45,1,1,"","MapTiles"]],"sensai.geoanalytics.map_tiles.MapTile":[[45,2,1,"","__init__"]],"sensai.geoanalytics.map_tiles.MapTiles":[[45,2,1,"","__init__"],[45,2,1,"","get_tile"],[45,2,1,"","get_tile_coordinates"],[45,2,1,"","get_tiles_in_rect"],[45,2,1,"","iter_tile_coordinates_in_rect"]],"sensai.hyperopt":[[46,1,1,"","GridSearch"],[46,1,1,"","ParameterCombinationEquivalenceClassValueCache"],[46,1,1,"","ParameterCombinationSkipDecider"],[46,1,1,"","ParametersMetricsCollection"],[46,1,1,"","SAHyperOpt"],[46,5,1,"","iter_param_combinations"]],"sensai.hyperopt.GridSearch":[[46,1,1,"","Result"],[46,2,1,"","__init__"],[46,2,1,"","run"]],"sensai.hyperopt.GridSearch.Result":[[46,1,1,"","BestParams"],[46,2,1,"","__init__"],[46,2,1,"","get_best_params"]],"sensai.hyperopt.GridSearch.Result.BestParams":[[46,2,1,"","__init__"],[46,4,1,"","metric_name"],[46,4,1,"","metric_value"],[46,4,1,"","params"]],"sensai.hyperopt.ParameterCombinationEquivalenceClassValueCache":[[46,2,1,"","__init__"],[46,2,1,"","get"],[46,2,1,"","set"]],"sensai.hyperopt.ParameterCombinationSkipDecider":[[46,2,1,"","is_skipped"],[46,2,1,"","tell"]],"sensai.hyperopt.ParametersMetricsCollection":[[46,2,1,"","__init__"],[46,2,1,"","add_values"],[46,2,1,"","contains"],[46,2,1,"","get_data_frame"]],"sensai.hyperopt.SAHyperOpt":[[46,1,1,"","ParameterChangeOperator"],[46,1,1,"","State"],[46,2,1,"","__init__"],[46,2,1,"","get_simulated_annealing"],[46,2,1,"","run"]],"sensai.hyperopt.SAHyperOpt.ParameterChangeOperator":[[46,2,1,"","__init__"],[46,2,1,"","apply_state_change"],[46,2,1,"","choose_params"],[46,2,1,"","cost_delta"]],"sensai.hyperopt.SAHyperOpt.State":[[46,2,1,"","__init__"],[46,2,1,"","apply_state_representation"],[46,2,1,"","compute_cost_value"],[46,2,1,"","get_state_representation"]],"sensai.lightgbm":[[48,1,1,"","LightGBMVectorClassificationModel"],[48,1,1,"","LightGBMVectorRegressionModel"]],"sensai.lightgbm.LightGBMVectorClassificationModel":[[48,2,1,"","__init__"]],"sensai.lightgbm.LightGBMVectorRegressionModel":[[48,2,1,"","__init__"]],"sensai.local_search":[[49,1,1,"","ParallelTempering"],[49,1,1,"","SAChain"],[49,1,1,"","SACostValue"],[49,1,1,"","SACostValueNumeric"],[49,1,1,"","SAOperator"],[49,1,1,"","SAProbabilityFunction"],[49,1,1,"","SAProbabilityFunctionConstant"],[49,1,1,"","SAProbabilityFunctionLinear"],[49,1,1,"","SAProbabilityFunctionReverseSigmoid"],[49,1,1,"","SAProbabilitySchedule"],[49,1,1,"","SAState"],[49,1,1,"","SATemperatureSchedule"],[49,1,1,"","SATemperatureScheduleExponential"],[49,1,1,"","SATemperatureScheduleFixed"],[49,1,1,"","SATemperatureSchedulePower"],[49,1,1,"","SATemperatureScheduleReverseSigmoid"],[49,1,1,"","SATemperatureScheduleReverseSigmoidSymmetric"],[49,1,1,"","SimulatedAnnealing"],[49,5,1,"","reverse_sigmoid"]],"sensai.local_search.ParallelTempering":[[49,2,1,"","__init__"],[49,2,1,"","optimise"],[49,2,1,"","plot_cost_progression"]],"sensai.local_search.SAChain":[[49,2,1,"","__init__"],[49,2,1,"","apply_best_state"],[49,2,1,"","get_series"],[49,2,1,"","log_stats"],[49,2,1,"","plot_series"],[49,2,1,"","step"]],"sensai.local_search.SACostValue":[[49,2,1,"","add"],[49,2,1,"","value"]],"sensai.local_search.SACostValueNumeric":[[49,2,1,"","__init__"],[49,2,1,"","add"],[49,2,1,"","value"]],"sensai.local_search.SAOperator":[[49,2,1,"","__init__"],[49,2,1,"","apply"],[49,2,1,"","apply_cost_change"],[49,2,1,"","apply_state_change"],[49,2,1,"","choose_params"],[49,2,1,"","cost_delta"]],"sensai.local_search.SAProbabilityFunction":[[49,2,1,"","__init__"]],"sensai.local_search.SAProbabilityFunctionConstant":[[49,2,1,"","__init__"]],"sensai.local_search.SAProbabilityFunctionLinear":[[49,2,1,"","__init__"]],"sensai.local_search.SAProbabilityFunctionReverseSigmoid":[[49,2,1,"","__init__"]],"sensai.local_search.SAProbabilitySchedule":[[49,2,1,"","__init__"],[49,2,1,"","probability"],[49,2,1,"","temperature"]],"sensai.local_search.SAState":[[49,2,1,"","__init__"],[49,2,1,"","apply_state_representation"],[49,2,1,"","compute_cost_value"],[49,2,1,"","get_state_representation"]],"sensai.local_search.SATemperatureSchedule":[[49,2,1,"","probability"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureScheduleExponential":[[49,2,1,"","__init__"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureScheduleFixed":[[49,2,1,"","__init__"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureSchedulePower":[[49,2,1,"","__init__"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureScheduleReverseSigmoid":[[49,2,1,"","__init__"],[49,2,1,"","temperature"]],"sensai.local_search.SATemperatureScheduleReverseSigmoidSymmetric":[[49,2,1,"","__init__"]],"sensai.local_search.SimulatedAnnealing":[[49,2,1,"","__init__"],[49,2,1,"","get_chain"],[49,2,1,"","optimise"]],"sensai.minizinc":[[50,1,1,"","CostScaler"],[50,1,1,"","MiniZincProblem"],[50,1,1,"","MiniZincSolver"],[50,5,1,"","array_to_mini_zinc"],[50,5,1,"","extract_1d_array_from_output"],[50,5,1,"","extract_multi_dim_array_from_output"]],"sensai.minizinc.CostScaler":[[50,2,1,"","__init__"],[50,2,1,"","original_value"],[50,2,1,"","scaled_float"],[50,2,1,"","scaled_int"]],"sensai.minizinc.MiniZincProblem":[[50,2,1,"","create_mini_zinc_file"],[50,2,1,"","get_mini_zinc_code"]],"sensai.minizinc.MiniZincSolver":[[50,2,1,"","__init__"],[50,2,1,"","get_last_solver_time_secs"],[50,2,1,"","solve_path"],[50,2,1,"","solve_problem"]],"sensai.multi_model":[[51,1,1,"","MultiVectorRegressionModel"]],"sensai.multi_model.MultiVectorRegressionModel":[[51,2,1,"","__init__"]],"sensai.naive_bayes":[[52,1,1,"","CategoricalNaiveBayesVectorClassificationModel"]],"sensai.naive_bayes.CategoricalNaiveBayesVectorClassificationModel":[[52,2,1,"","__init__"]],"sensai.nearest_neighbors":[[53,1,1,"","AbstractKnnFinder"],[53,1,1,"","AllNeighborsProvider"],[53,1,1,"","CachingKNearestNeighboursFinder"],[53,1,1,"","FeatureGeneratorNeighbors"],[53,1,1,"","KNearestNeighboursClassificationModel"],[53,1,1,"","KNearestNeighboursFinder"],[53,1,1,"","KNearestNeighboursRegressionModel"],[53,1,1,"","Neighbor"],[53,1,1,"","NeighborProvider"],[53,1,1,"","TimerangeNeighborsProvider"]],"sensai.nearest_neighbors.AbstractKnnFinder":[[53,2,1,"","find_neighbors"]],"sensai.nearest_neighbors.AllNeighborsProvider":[[53,2,1,"","__init__"],[53,2,1,"","iter_potential_neighbors"]],"sensai.nearest_neighbors.CachingKNearestNeighboursFinder":[[53,1,1,"","CachedSeriesDistanceMetric"],[53,1,1,"","DistanceMetricCache"],[53,2,1,"","__init__"],[53,2,1,"","find_neighbors"]],"sensai.nearest_neighbors.CachingKNearestNeighboursFinder.CachedSeriesDistanceMetric":[[53,2,1,"","__init__"],[53,2,1,"","get_distance_series"]],"sensai.nearest_neighbors.CachingKNearestNeighboursFinder.DistanceMetricCache":[[53,2,1,"","__init__"],[53,2,1,"","get_cached_metric"]],"sensai.nearest_neighbors.FeatureGeneratorNeighbors":[[53,2,1,"","__init__"]],"sensai.nearest_neighbors.KNearestNeighboursClassificationModel":[[53,2,1,"","__init__"],[53,2,1,"","find_neighbors"]],"sensai.nearest_neighbors.KNearestNeighboursFinder":[[53,2,1,"","__init__"],[53,2,1,"","find_neighbors"]],"sensai.nearest_neighbors.KNearestNeighboursRegressionModel":[[53,2,1,"","__init__"]],"sensai.nearest_neighbors.Neighbor":[[53,2,1,"","__init__"]],"sensai.nearest_neighbors.NeighborProvider":[[53,2,1,"","__init__"],[53,2,1,"","iter_potential_neighbors"]],"sensai.nearest_neighbors.TimerangeNeighborsProvider":[[53,2,1,"","__init__"],[53,2,1,"","iter_potential_neighbors"]],"sensai.normalisation":[[54,1,1,"","NormalisationMode"],[54,1,1,"","VectorDataScaler"]],"sensai.normalisation.NormalisationMode":[[54,4,1,"","MAX_ALL"],[54,4,1,"","MAX_BY_COLUMN"],[54,4,1,"","NONE"],[54,4,1,"","STANDARDISED"]],"sensai.normalisation.VectorDataScaler":[[54,2,1,"","__init__"],[54,2,1,"","get_denormalised_array"],[54,2,1,"","get_normalised_array"]],"sensai.pytorch_lightning":[[56,0,0,"-","pl_models"]],"sensai.pytorch_lightning.pl_models":[[56,1,1,"","PLTensorToScalarClassificationModel"],[56,1,1,"","PLTensorToScalarRegressionModel"],[56,1,1,"","PLTensorToTensorClassificationModel"],[56,1,1,"","PLTensorToTensorRegressionModel"],[56,1,1,"","PLWrappedModel"]],"sensai.pytorch_lightning.pl_models.PLTensorToScalarClassificationModel":[[56,2,1,"","__init__"]],"sensai.pytorch_lightning.pl_models.PLTensorToScalarRegressionModel":[[56,2,1,"","__init__"]],"sensai.pytorch_lightning.pl_models.PLTensorToTensorClassificationModel":[[56,2,1,"","__init__"]],"sensai.pytorch_lightning.pl_models.PLTensorToTensorRegressionModel":[[56,2,1,"","__init__"]],"sensai.pytorch_lightning.pl_models.PLWrappedModel":[[56,2,1,"","__init__"],[56,2,1,"","fit"],[56,2,1,"","predict"]],"sensai.sklearn":[[58,0,0,"-","sklearn_base"],[59,0,0,"-","sklearn_classification"],[60,0,0,"-","sklearn_regression"]],"sensai.sklearn.sklearn_base":[[58,1,1,"","AbstractSkLearnMultiDimVectorRegressionModel"],[58,1,1,"","AbstractSkLearnMultipleOneDimVectorRegressionModel"],[58,1,1,"","AbstractSkLearnVectorClassificationModel"],[58,1,1,"","AbstractSkLearnVectorRegressionModel"],[58,1,1,"","FeatureImportanceProviderSkLearnClassification"],[58,1,1,"","FeatureImportanceProviderSkLearnRegressionMultiDim"],[58,1,1,"","FeatureImportanceProviderSkLearnRegressionMultipleOneDim"],[58,5,1,"","create_sklearn_model"],[58,5,1,"","str_sklearn_model"]],"sensai.sklearn.sklearn_base.AbstractSkLearnMultiDimVectorRegressionModel":[[58,2,1,"","__init__"]],"sensai.sklearn.sklearn_base.AbstractSkLearnMultipleOneDimVectorRegressionModel":[[58,2,1,"","__init__"],[58,2,1,"","get_sklearn_model"]],"sensai.sklearn.sklearn_base.AbstractSkLearnVectorClassificationModel":[[58,2,1,"","__init__"],[58,2,1,"","get_params"],[58,2,1,"","set_params"],[58,2,1,"","with_sklearn_input_transformer"]],"sensai.sklearn.sklearn_base.AbstractSkLearnVectorRegressionModel":[[58,2,1,"","__init__"],[58,2,1,"","with_sklearn_input_transformer"],[58,2,1,"","with_sklearn_output_transformer"]],"sensai.sklearn.sklearn_base.FeatureImportanceProviderSkLearnClassification":[[58,2,1,"","get_feature_importance_dict"]],"sensai.sklearn.sklearn_base.FeatureImportanceProviderSkLearnRegressionMultiDim":[[58,2,1,"","get_feature_importance_dict"]],"sensai.sklearn.sklearn_base.FeatureImportanceProviderSkLearnRegressionMultipleOneDim":[[58,2,1,"","get_feature_importance_dict"]],"sensai.sklearn.sklearn_classification":[[59,1,1,"","SkLearnDecisionTreeVectorClassificationModel"],[59,1,1,"","SkLearnKNeighborsVectorClassificationModel"],[59,1,1,"","SkLearnLogisticRegressionVectorClassificationModel"],[59,1,1,"","SkLearnMLPVectorClassificationModel"],[59,1,1,"","SkLearnMultinomialNBVectorClassificationModel"],[59,1,1,"","SkLearnRandomForestVectorClassificationModel"],[59,1,1,"","SkLearnSVCVectorClassificationModel"]],"sensai.sklearn.sklearn_classification.SkLearnDecisionTreeVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnKNeighborsVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnLogisticRegressionVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnMLPVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnMultinomialNBVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnRandomForestVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_classification.SkLearnSVCVectorClassificationModel":[[59,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression":[[60,1,1,"","SkLearnDecisionTreeVectorRegressionModel"],[60,1,1,"","SkLearnDummyVectorRegressionModel"],[60,1,1,"","SkLearnExtraTreesVectorRegressionModel"],[60,1,1,"","SkLearnGradientBoostingVectorRegressionModel"],[60,1,1,"","SkLearnKNeighborsVectorRegressionModel"],[60,1,1,"","SkLearnLinearLassoRegressionVectorRegressionModel"],[60,1,1,"","SkLearnLinearRegressionVectorRegressionModel"],[60,1,1,"","SkLearnLinearRidgeRegressionVectorRegressionModel"],[60,1,1,"","SkLearnLinearSVRVectorRegressionModel"],[60,1,1,"","SkLearnMultiLayerPerceptronVectorRegressionModel"],[60,1,1,"","SkLearnRandomForestVectorRegressionModel"],[60,1,1,"","SkLearnSVRVectorRegressionModel"]],"sensai.sklearn.sklearn_regression.SkLearnDecisionTreeVectorRegressionModel":[[60,2,1,"","__init__"],[60,2,1,"","plot"],[60,2,1,"","plot_graphviz_pdf"]],"sensai.sklearn.sklearn_regression.SkLearnDummyVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnExtraTreesVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnGradientBoostingVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnKNeighborsVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnLinearLassoRegressionVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnLinearRegressionVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnLinearRidgeRegressionVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnLinearSVRVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnMultiLayerPerceptronVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnRandomForestVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn.sklearn_regression.SkLearnSVRVectorRegressionModel":[[60,2,1,"","__init__"]],"sensai.sklearn_quantile":[[61,1,1,"","QuantileRegressionMetric"],[61,1,1,"","QuantileRegressionMetricAccuracyInConfidenceInterval"],[61,1,1,"","QuantileRegressionMetricConfidenceIntervalMeanSize"],[61,1,1,"","QuantileRegressionMetricConfidenceIntervalMedianSize"],[61,1,1,"","QuantileRegressionMetricRelFreqMaxSizeConfidenceInterval"],[61,1,1,"","RandomForestQuantileRegressorVectorRegressionModel"]],"sensai.sklearn_quantile.QuantileRegressionMetric":[[61,2,1,"","compute_confidence_intervals"],[61,4,1,"","name"]],"sensai.sklearn_quantile.QuantileRegressionMetricAccuracyInConfidenceInterval":[[61,2,1,"","compute_value"],[61,4,1,"","name"]],"sensai.sklearn_quantile.QuantileRegressionMetricConfidenceIntervalMeanSize":[[61,2,1,"","compute_value"],[61,4,1,"","name"]],"sensai.sklearn_quantile.QuantileRegressionMetricConfidenceIntervalMedianSize":[[61,2,1,"","compute_value"],[61,4,1,"","name"]],"sensai.sklearn_quantile.QuantileRegressionMetricRelFreqMaxSizeConfidenceInterval":[[61,2,1,"","__init__"],[61,2,1,"","compute_value"],[61,4,1,"","name"]],"sensai.sklearn_quantile.RandomForestQuantileRegressorVectorRegressionModel":[[61,2,1,"","__init__"],[61,2,1,"","predict_confidence_intervals"]],"sensai.tensor_model":[[62,6,1,"","InvalidShapeError"],[62,1,1,"","TensorModel"],[62,1,1,"","TensorToScalarClassificationModel"],[62,1,1,"","TensorToScalarRegressionModel"],[62,1,1,"","TensorToTensorClassificationModel"],[62,1,1,"","TensorToTensorRegressionModel"]],"sensai.tensor_model.TensorModel":[[62,2,1,"","__init__"],[62,2,1,"","get_model_input_shape"],[62,2,1,"","get_model_output_shape"]],"sensai.tensor_model.TensorToScalarClassificationModel":[[62,2,1,"","__init__"],[62,2,1,"","predict"]],"sensai.tensor_model.TensorToScalarRegressionModel":[[62,2,1,"","__init__"],[62,2,1,"","predict"]],"sensai.tensor_model.TensorToTensorClassificationModel":[[62,2,1,"","__init__"],[62,2,1,"","convert_class_probabilities_to_predictions"],[62,2,1,"","fit"],[62,2,1,"","get_model_output_shape"],[62,2,1,"","get_num_predicted_classes"],[62,2,1,"","is_regression_model"],[62,2,1,"","predict"],[62,2,1,"","predict_class_probabilities"]],"sensai.tensor_model.TensorToTensorRegressionModel":[[62,2,1,"","__init__"],[62,2,1,"","predict"]],"sensai.tensorflow":[[64,0,0,"-","tf_base"],[65,0,0,"-","tf_mlp"]],"sensai.tensorflow.tf_base":[[64,1,1,"","KerasVectorRegressionModel"],[64,1,1,"","TensorFlowSession"]],"sensai.tensorflow.tf_base.KerasVectorRegressionModel":[[64,2,1,"","__init__"]],"sensai.tensorflow.tf_base.TensorFlowSession":[[64,2,1,"","configure_session"],[64,4,1,"","session"],[64,2,1,"","set_keras_session"]],"sensai.tensorflow.tf_mlp":[[65,1,1,"","KerasMultiLayerPerceptronVectorRegressionModel"]],"sensai.tensorflow.tf_mlp.KerasMultiLayerPerceptronVectorRegressionModel":[[65,2,1,"","__init__"]],"sensai.torch":[[67,0,0,"-","torch_base"],[68,0,0,"-","torch_data"],[69,0,0,"-","torch_enums"],[70,0,0,"-","torch_eval_util"],[71,0,0,"-","torch_models"],[84,0,0,"-","torch_modules"],[85,0,0,"-","torch_opt"],[86,0,0,"-","torchtext"]],"sensai.torch.torch_base":[[67,1,1,"","MCDropoutCapableNNModule"],[67,1,1,"","OutputTensorToArrayConverter"],[67,1,1,"","TorchAutoregressiveResultHandler"],[67,1,1,"","TorchDataSetProviderFactory"],[67,1,1,"","TorchDataSetProviderFactoryClassificationDefault"],[67,1,1,"","TorchDataSetProviderFactoryRegressionDefault"],[67,1,1,"","TorchModel"],[67,1,1,"","TorchModelFactoryFromModule"],[67,1,1,"","TorchModelFittingStrategy"],[67,1,1,"","TorchModelFittingStrategyDefault"],[67,1,1,"","TorchModelFromModule"],[67,1,1,"","TorchModelFromModuleFactory"],[67,1,1,"","TorchVectorClassificationModel"],[67,1,1,"","TorchVectorRegressionModel"],[67,1,1,"","VectorTorchModel"]],"sensai.torch.torch_base.MCDropoutCapableNNModule":[[67,2,1,"","__init__"],[67,2,1,"","infer_mc_dropout"]],"sensai.torch.torch_base.OutputTensorToArrayConverter":[[67,2,1,"","convert"]],"sensai.torch.torch_base.TorchAutoregressiveResultHandler":[[67,2,1,"","clear_results"],[67,2,1,"","save_results"]],"sensai.torch.torch_base.TorchDataSetProviderFactory":[[67,2,1,"","create_data_set_provider"]],"sensai.torch.torch_base.TorchDataSetProviderFactoryClassificationDefault":[[67,2,1,"","__init__"],[67,2,1,"","create_data_set_provider"]],"sensai.torch.torch_base.TorchDataSetProviderFactoryRegressionDefault":[[67,2,1,"","__init__"],[67,2,1,"","create_data_set_provider"]],"sensai.torch.torch_base.TorchModel":[[67,2,1,"","__init__"],[67,2,1,"","apply"],[67,2,1,"","apply_scaled"],[67,3,1,"","best_epoch"],[67,2,1,"","create_torch_module"],[67,2,1,"","fit"],[67,2,1,"","get_module_bytes"],[67,2,1,"","get_torch_module"],[67,2,1,"","scaled_output"],[67,2,1,"","set_module_bytes"],[67,2,1,"","set_normalisation_check_threshold"],[67,2,1,"","set_torch_module"],[67,3,1,"","total_epochs"]],"sensai.torch.torch_base.TorchModelFactoryFromModule":[[67,2,1,"","__init__"]],"sensai.torch.torch_base.TorchModelFittingStrategy":[[67,2,1,"","fit"]],"sensai.torch.torch_base.TorchModelFittingStrategyDefault":[[67,2,1,"","fit"]],"sensai.torch.torch_base.TorchModelFromModule":[[67,2,1,"","__init__"],[67,2,1,"","create_torch_module"]],"sensai.torch.torch_base.TorchModelFromModuleFactory":[[67,2,1,"","__init__"],[67,2,1,"","create_torch_module"]],"sensai.torch.torch_base.TorchVectorClassificationModel":[[67,2,1,"","__init__"],[67,2,1,"","from_module"],[67,2,1,"","with_data_frame_splitter"],[67,2,1,"","with_input_tensoriser"],[67,2,1,"","with_normalisation_check_threshold"],[67,2,1,"","with_output_tensoriser"],[67,2,1,"","with_torch_data_set_provider_factory"]],"sensai.torch.torch_base.TorchVectorRegressionModel":[[67,2,1,"","__init__"],[67,2,1,"","from_module"],[67,2,1,"","with_autoregressive_result_handler"],[67,2,1,"","with_data_frame_splitter"],[67,2,1,"","with_input_tensoriser"],[67,2,1,"","with_normalisation_check_threshold"],[67,2,1,"","with_output_tensor_to_array_converter"],[67,2,1,"","with_output_tensoriser"],[67,2,1,"","with_torch_data_set_provider_factory"]],"sensai.torch.torch_base.VectorTorchModel":[[67,2,1,"","__init__"],[67,2,1,"","create_torch_module"],[67,2,1,"","create_torch_module_for_dims"]],"sensai.torch.torch_data":[[68,1,1,"","ClassificationVectorDataUtil"],[68,1,1,"","DataUtil"],[68,1,1,"","RuleBasedTensoriser"],[68,1,1,"","TensorScaler"],[68,1,1,"","TensorScalerCentreAndScale"],[68,1,1,"","TensorScalerFromDFTSkLearnTransformer"],[68,1,1,"","TensorScalerFromVectorDataScaler"],[68,1,1,"","TensorScalerIdentity"],[68,1,1,"","TensorTransformer"],[68,1,1,"","TensorTuple"],[68,1,1,"","Tensoriser"],[68,1,1,"","TensoriserClassLabelIndices"],[68,1,1,"","TensoriserDataFrameFloatValuesMatrix"],[68,1,1,"","TorchDataSet"],[68,1,1,"","TorchDataSetFromDataFrames"],[68,1,1,"","TorchDataSetFromDataFramesDynamicallyTensorised"],[68,1,1,"","TorchDataSetFromDataFramesPreTensorised"],[68,1,1,"","TorchDataSetFromTensors"],[68,1,1,"","TorchDataSetProvider"],[68,1,1,"","TorchDataSetProviderFromDataUtil"],[68,1,1,"","TorchDataSetProviderFromVectorDataUtil"],[68,1,1,"","VectorDataUtil"],[68,5,1,"","to_tensor"]],"sensai.torch.torch_data.ClassificationVectorDataUtil":[[68,2,1,"","__init__"],[68,2,1,"","model_output_dim"]],"sensai.torch.torch_data.DataUtil":[[68,2,1,"","get_input_tensor_scaler"],[68,2,1,"","get_output_tensor_scaler"],[68,2,1,"","input_dim"],[68,2,1,"","model_output_dim"],[68,2,1,"","split_into_tensors"]],"sensai.torch.torch_data.RuleBasedTensoriser":[[68,2,1,"","fit"]],"sensai.torch.torch_data.TensorScaler":[[68,2,1,"","cuda"],[68,2,1,"","denormalise"],[68,2,1,"","normalise"]],"sensai.torch.torch_data.TensorScalerCentreAndScale":[[68,2,1,"","__init__"],[68,2,1,"","cuda"],[68,2,1,"","denormalise"],[68,2,1,"","normalise"]],"sensai.torch.torch_data.TensorScalerFromDFTSkLearnTransformer":[[68,2,1,"","__init__"]],"sensai.torch.torch_data.TensorScalerFromVectorDataScaler":[[68,2,1,"","__init__"]],"sensai.torch.torch_data.TensorScalerIdentity":[[68,2,1,"","cuda"],[68,2,1,"","denormalise"],[68,2,1,"","normalise"]],"sensai.torch.torch_data.TensorTransformer":[[68,2,1,"","transform"]],"sensai.torch.torch_data.TensorTuple":[[68,2,1,"","__init__"],[68,2,1,"","concat"],[68,2,1,"","cuda"],[68,2,1,"","item"],[68,2,1,"","tuple"]],"sensai.torch.torch_data.Tensoriser":[[68,2,1,"","fit"],[68,2,1,"","tensorise"]],"sensai.torch.torch_data.TorchDataSet":[[68,2,1,"","iter_batches"],[68,2,1,"","size"]],"sensai.torch.torch_data.TorchDataSetFromDataFrames":[[68,2,1,"","__init__"],[68,2,1,"","iter_batches"],[68,2,1,"","size"]],"sensai.torch.torch_data.TorchDataSetFromDataFramesDynamicallyTensorised":[[68,2,1,"","__init__"],[68,2,1,"","iter_batches"],[68,2,1,"","size"]],"sensai.torch.torch_data.TorchDataSetFromDataFramesPreTensorised":[[68,2,1,"","__init__"]],"sensai.torch.torch_data.TorchDataSetFromTensors":[[68,2,1,"","__init__"],[68,2,1,"","iter_batches"],[68,2,1,"","size"]],"sensai.torch.torch_data.TorchDataSetProvider":[[68,2,1,"","__init__"],[68,2,1,"","get_input_dim"],[68,2,1,"","get_input_tensor_scaler"],[68,2,1,"","get_model_output_dim"],[68,2,1,"","get_output_tensor_scaler"],[68,2,1,"","provide_split"]],"sensai.torch.torch_data.TorchDataSetProviderFromDataUtil":[[68,2,1,"","__init__"],[68,2,1,"","provide_split"]],"sensai.torch.torch_data.TorchDataSetProviderFromVectorDataUtil":[[68,2,1,"","__init__"],[68,2,1,"","provide_split"]],"sensai.torch.torch_data.VectorDataUtil":[[68,2,1,"","__init__"],[68,2,1,"","get_input_tensor_scaler"],[68,2,1,"","get_output_tensor_scaler"],[68,2,1,"","input_dim"],[68,2,1,"","model_output_dim"],[68,2,1,"","output_dim"],[68,2,1,"","split_into_data_sets"],[68,2,1,"","split_into_tensors"]],"sensai.torch.torch_enums":[[69,1,1,"","ActivationFunction"],[69,1,1,"","ClassificationOutputMode"]],"sensai.torch.torch_enums.ActivationFunction":[[69,4,1,"","LOG_SOFTMAX"],[69,4,1,"","NONE"],[69,4,1,"","RELU"],[69,4,1,"","SIGMOID"],[69,4,1,"","SOFTMAX"],[69,4,1,"","TANH"],[69,2,1,"","from_name"],[69,2,1,"","get_name"],[69,2,1,"","get_torch_function"],[69,2,1,"","torch_function_from_any"]],"sensai.torch.torch_enums.ClassificationOutputMode":[[69,4,1,"","LOG_PROBABILITIES"],[69,4,1,"","PROBABILITIES"],[69,4,1,"","UNNORMALISED_LOG_PROBABILITIES"],[69,2,1,"","for_activation_fn"]],"sensai.torch.torch_eval_util":[[70,1,1,"","TorchVectorRegressionModelEvaluationUtil"]],"sensai.torch.torch_models":[[72,0,0,"-","lstnet"],[75,0,0,"-","mlp"],[78,0,0,"-","residualffn"],[81,0,0,"-","seq"]],"sensai.torch.torch_models.lstnet":[[73,0,0,"-","lstnet_models"],[74,0,0,"-","lstnet_modules"]],"sensai.torch.torch_models.lstnet.lstnet_models":[[73,1,1,"","LSTNetworkVectorClassificationModel"]],"sensai.torch.torch_models.lstnet.lstnet_models.LSTNetworkVectorClassificationModel":[[73,1,1,"","DataUtil"],[73,2,1,"","__init__"]],"sensai.torch.torch_models.lstnet.lstnet_models.LSTNetworkVectorClassificationModel.DataUtil":[[73,2,1,"","__init__"],[73,2,1,"","get_input_output_pair"],[73,2,1,"","get_input_tensor_scaler"],[73,2,1,"","get_output_tensor_scaler"],[73,2,1,"","input_dim"],[73,2,1,"","model_output_dim"],[73,2,1,"","split_into_tensors"]],"sensai.torch.torch_models.lstnet.lstnet_modules":[[74,1,1,"","LSTNetwork"]],"sensai.torch.torch_models.lstnet.lstnet_modules.LSTNetwork":[[74,1,1,"","Mode"],[74,2,1,"","__init__"],[74,2,1,"","compute_encoder_dim"],[74,2,1,"","forward"],[74,2,1,"","get_encoder_dim"]],"sensai.torch.torch_models.lstnet.lstnet_modules.LSTNetwork.Mode":[[74,4,1,"","CLASSIFICATION"],[74,4,1,"","ENCODER"],[74,4,1,"","REGRESSION"]],"sensai.torch.torch_models.mlp":[[76,0,0,"-","mlp_models"],[77,0,0,"-","mlp_modules"]],"sensai.torch.torch_models.mlp.mlp_models":[[76,1,1,"","MultiLayerPerceptronTorchModel"],[76,1,1,"","MultiLayerPerceptronVectorClassificationModel"],[76,1,1,"","MultiLayerPerceptronVectorRegressionModel"]],"sensai.torch.torch_models.mlp.mlp_models.MultiLayerPerceptronTorchModel":[[76,2,1,"","__init__"],[76,2,1,"","create_torch_module_for_dims"]],"sensai.torch.torch_models.mlp.mlp_models.MultiLayerPerceptronVectorClassificationModel":[[76,2,1,"","__init__"]],"sensai.torch.torch_models.mlp.mlp_models.MultiLayerPerceptronVectorRegressionModel":[[76,2,1,"","__init__"]],"sensai.torch.torch_models.mlp.mlp_modules":[[77,1,1,"","MultiLayerPerceptron"]],"sensai.torch.torch_models.mlp.mlp_modules.MultiLayerPerceptron":[[77,2,1,"","__init__"],[77,2,1,"","forward"]],"sensai.torch.torch_models.residualffn":[[79,0,0,"-","residualffn_models"],[80,0,0,"-","residualffn_modules"]],"sensai.torch.torch_models.residualffn.residualffn_models":[[79,1,1,"","ResidualFeedForwardNetworkTorchModel"],[79,1,1,"","ResidualFeedForwardNetworkVectorRegressionModel"]],"sensai.torch.torch_models.residualffn.residualffn_models.ResidualFeedForwardNetworkTorchModel":[[79,2,1,"","__init__"],[79,2,1,"","create_torch_module_for_dims"]],"sensai.torch.torch_models.residualffn.residualffn_models.ResidualFeedForwardNetworkVectorRegressionModel":[[79,2,1,"","__init__"]],"sensai.torch.torch_models.residualffn.residualffn_modules":[[80,1,1,"","ResidualFeedForwardNetwork"]],"sensai.torch.torch_models.residualffn.residualffn_modules.ResidualFeedForwardNetwork":[[80,2,1,"","__init__"],[80,2,1,"","forward"]],"sensai.torch.torch_models.seq":[[82,0,0,"-","seq_models"],[83,0,0,"-","seq_modules"]],"sensai.torch.torch_models.seq.seq_models":[[82,1,1,"","EncoderDecoderVectorRegressionModel"]],"sensai.torch.torch_models.seq.seq_models.EncoderDecoderVectorRegressionModel":[[82,1,1,"","EncoderDecoderModel"],[82,1,1,"","InputTensoriser"],[82,2,1,"","__init__"]],"sensai.torch.torch_models.seq.seq_models.EncoderDecoderVectorRegressionModel.EncoderDecoderModel":[[82,2,1,"","__init__"],[82,2,1,"","create_torch_module"]],"sensai.torch.torch_models.seq.seq_models.EncoderDecoderVectorRegressionModel.InputTensoriser":[[82,2,1,"","__init__"],[82,2,1,"","fit"]],"sensai.torch.torch_models.seq.seq_modules":[[83,1,1,"","DecoderFactory"],[83,1,1,"","DecoderProtocol"],[83,1,1,"","EncoderDecoderModule"],[83,1,1,"","EncoderFactory"],[83,1,1,"","EncoderProtocol"],[83,1,1,"","LSTNetworkEncoder"],[83,1,1,"","LSTNetworkEncoderFactory"],[83,1,1,"","LinearPredictorFactory"],[83,1,1,"","MLPPredictorFactory"],[83,1,1,"","PredictorFactory"],[83,1,1,"","PredictorProtocol"],[83,1,1,"","RnnEncoderFactory"],[83,1,1,"","RnnEncoderModule"],[83,1,1,"","SingleTargetDecoderFactory"],[83,1,1,"","SingleTargetDecoderModule"],[83,1,1,"","TargetSequenceDecoderFactory"],[83,1,1,"","TargetSequenceDecoderModule"]],"sensai.torch.torch_models.seq.seq_modules.DecoderFactory":[[83,2,1,"","create_decoder"]],"sensai.torch.torch_models.seq.seq_modules.DecoderProtocol":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.EncoderDecoderModule":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.EncoderFactory":[[83,2,1,"","create_encoder"]],"sensai.torch.torch_models.seq.seq_modules.EncoderProtocol":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.LSTNetworkEncoder":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.LSTNetworkEncoderFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_encoder"],[83,2,1,"","get_latent_dim"]],"sensai.torch.torch_models.seq.seq_modules.LinearPredictorFactory":[[83,2,1,"","create_predictor"]],"sensai.torch.torch_models.seq.seq_modules.MLPPredictorFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_predictor"]],"sensai.torch.torch_models.seq.seq_modules.PredictorFactory":[[83,2,1,"","create_predictor"]],"sensai.torch.torch_models.seq.seq_modules.PredictorProtocol":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.RnnEncoderFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_encoder"]],"sensai.torch.torch_models.seq.seq_modules.RnnEncoderModule":[[83,1,1,"","RnnType"],[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.RnnEncoderModule.RnnType":[[83,4,1,"","GRU"],[83,4,1,"","LSTM"]],"sensai.torch.torch_models.seq.seq_modules.SingleTargetDecoderFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_decoder"]],"sensai.torch.torch_models.seq.seq_modules.SingleTargetDecoderModule":[[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderFactory":[[83,2,1,"","__init__"],[83,2,1,"","create_decoder"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderModule":[[83,1,1,"","LatentPassOnMode"],[83,1,1,"","OutputMode"],[83,1,1,"","PredictionMode"],[83,2,1,"","__init__"],[83,2,1,"","forward"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderModule.LatentPassOnMode":[[83,4,1,"","CONCAT_INPUT"],[83,4,1,"","INIT_HIDDEN"],[83,4,1,"","NO_LATENT"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderModule.OutputMode":[[83,4,1,"","MULTI_OUTPUT"],[83,4,1,"","SINGLE_OUTPUT"],[83,4,1,"","SINGLE_OUTPUT_MEAN"]],"sensai.torch.torch_models.seq.seq_modules.TargetSequenceDecoderModule.PredictionMode":[[83,4,1,"","DIRECT"],[83,4,1,"","MULTI_LATENT"],[83,4,1,"","SINGLE_LATENT"]],"sensai.torch.torch_opt":[[85,1,1,"","NNLossEvaluator"],[85,1,1,"","NNLossEvaluatorClassification"],[85,1,1,"","NNLossEvaluatorFixedDim"],[85,1,1,"","NNLossEvaluatorRegression"],[85,1,1,"","NNOptimiser"],[85,1,1,"","NNOptimiserParams"],[85,1,1,"","Optimiser"],[85,1,1,"","TrainingInfo"]],"sensai.torch.torch_opt.NNLossEvaluator":[[85,1,1,"","Evaluation"],[85,2,1,"","get_validation_metric_name"],[85,2,1,"","start_evaluation"]],"sensai.torch.torch_opt.NNLossEvaluator.Evaluation":[[85,2,1,"","compute_train_batch_loss"],[85,2,1,"","get_epoch_train_loss"],[85,2,1,"","get_validation_metrics"],[85,2,1,"","process_validation_batch"],[85,2,1,"","start_epoch"]],"sensai.torch.torch_opt.NNLossEvaluatorClassification":[[85,1,1,"","LossFunction"],[85,1,1,"","ValidationLossEvaluator"],[85,2,1,"","__init__"],[85,2,1,"","create_validation_loss_evaluator"],[85,2,1,"","get_output_dim_weights"],[85,2,1,"","get_training_criterion"],[85,2,1,"","get_validation_metric_name"]],"sensai.torch.torch_opt.NNLossEvaluatorClassification.LossFunction":[[85,4,1,"","CROSSENTROPY"],[85,4,1,"","NLL"],[85,2,1,"","create_criterion"],[85,2,1,"","default_for_output_mode"],[85,2,1,"","get_validation_metric_key"]],"sensai.torch.torch_opt.NNLossEvaluatorClassification.ValidationLossEvaluator":[[85,2,1,"","__init__"],[85,2,1,"","end_validation_collection"],[85,2,1,"","process_validation_result_batch"],[85,2,1,"","start_validation_collection"]],"sensai.torch.torch_opt.NNLossEvaluatorFixedDim":[[85,1,1,"","Evaluation"],[85,1,1,"","ValidationLossEvaluator"],[85,2,1,"","create_validation_loss_evaluator"],[85,2,1,"","get_output_dim_weights"],[85,2,1,"","get_training_criterion"],[85,2,1,"","get_validation_metric_name"],[85,2,1,"","start_evaluation"]],"sensai.torch.torch_opt.NNLossEvaluatorFixedDim.Evaluation":[[85,2,1,"","__init__"],[85,2,1,"","compute_train_batch_loss"],[85,2,1,"","get_epoch_train_loss"],[85,2,1,"","get_validation_metrics"],[85,2,1,"","process_validation_batch"],[85,2,1,"","start_epoch"]],"sensai.torch.torch_opt.NNLossEvaluatorFixedDim.ValidationLossEvaluator":[[85,2,1,"","end_validation_collection"],[85,2,1,"","process_validation_result_batch"],[85,2,1,"","start_validation_collection"]],"sensai.torch.torch_opt.NNLossEvaluatorRegression":[[85,1,1,"","LossFunction"],[85,1,1,"","ValidationLossEvaluator"],[85,2,1,"","__init__"],[85,2,1,"","create_validation_loss_evaluator"],[85,2,1,"","get_output_dim_weights"],[85,2,1,"","get_training_criterion"],[85,2,1,"","get_validation_metric_name"]],"sensai.torch.torch_opt.NNLossEvaluatorRegression.LossFunction":[[85,4,1,"","L1LOSS"],[85,4,1,"","L2LOSS"],[85,4,1,"","MSELOSS"],[85,4,1,"","SMOOTHL1LOSS"]],"sensai.torch.torch_opt.NNLossEvaluatorRegression.ValidationLossEvaluator":[[85,2,1,"","__init__"],[85,2,1,"","end_validation_collection"],[85,2,1,"","process_validation_result_batch"],[85,2,1,"","start_validation_collection"]],"sensai.torch.torch_opt.NNOptimiser":[[85,2,1,"","__init__"],[85,2,1,"","fit"]],"sensai.torch.torch_opt.NNOptimiserParams":[[85,4,1,"","REMOVED_PARAMS"],[85,4,1,"","RENAMED_PARAMS"],[85,2,1,"","__init__"],[85,2,1,"","from_dict"],[85,2,1,"","from_dict_or_instance"],[85,2,1,"","from_either_dict_or_instance"]],"sensai.torch.torch_opt.Optimiser":[[85,4,1,"","ADADELTA"],[85,4,1,"","ADAGRAD"],[85,4,1,"","ADAM"],[85,4,1,"","ADAMAX"],[85,4,1,"","ADAMW"],[85,4,1,"","ASGD"],[85,4,1,"","LBFGS"],[85,4,1,"","RMSPROP"],[85,4,1,"","RPROP"],[85,4,1,"","SGD"],[85,2,1,"","from_name"],[85,2,1,"","from_name_or_instance"]],"sensai.torch.torch_opt.TrainingInfo":[[85,2,1,"","__init__"],[85,2,1,"","get_training_loss_series"],[85,2,1,"","get_validation_metric_series"],[85,2,1,"","plot_all"]],"sensai.torch.torchtext":[[86,1,1,"","TorchDataSetFromTorchtextDataSet"],[86,1,1,"","TorchDataSetProviderFromTorchtextDataSet"],[86,1,1,"","TorchtextDataSetFromDataFrame"]],"sensai.torch.torchtext.TorchDataSetFromTorchtextDataSet":[[86,2,1,"","__init__"],[86,2,1,"","iter_batches"],[86,2,1,"","size"]],"sensai.torch.torchtext.TorchDataSetProviderFromTorchtextDataSet":[[86,2,1,"","__init__"],[86,2,1,"","provide_split"]],"sensai.torch.torchtext.TorchtextDataSetFromDataFrame":[[86,2,1,"","__init__"]],"sensai.tracking":[[88,0,0,"-","azure_tracking"],[89,0,0,"-","clearml_tracking"],[90,0,0,"-","mlflow_tracking"],[91,0,0,"-","tracking_base"]],"sensai.tracking.azure_tracking":[[88,1,1,"","TrackedAzureMLEvaluation"],[88,1,1,"","TrackedAzureMLExperiment"]],"sensai.tracking.azure_tracking.TrackedAzureMLEvaluation":[[88,2,1,"","__init__"],[88,2,1,"","eval_model"]],"sensai.tracking.azure_tracking.TrackedAzureMLExperiment":[[88,2,1,"","__init__"]],"sensai.tracking.clearml_tracking":[[89,1,1,"","ClearMLExperiment"],[89,1,1,"","ClearMLTrackingContext"]],"sensai.tracking.clearml_tracking.ClearMLExperiment":[[89,2,1,"","__init__"]],"sensai.tracking.clearml_tracking.ClearMLTrackingContext":[[89,2,1,"","__init__"],[89,2,1,"","track_figure"],[89,2,1,"","track_text"]],"sensai.tracking.mlflow_tracking":[[90,1,1,"","MLFlowExperiment"],[90,1,1,"","MLFlowTrackingContext"]],"sensai.tracking.mlflow_tracking.MLFlowExperiment":[[90,2,1,"","__init__"],[90,2,1,"","begin_context_for_model"],[90,2,1,"","end_context"]],"sensai.tracking.mlflow_tracking.MLFlowTrackingContext":[[90,2,1,"","__init__"],[90,2,1,"","track_figure"],[90,2,1,"","track_tag"],[90,2,1,"","track_text"]],"sensai.tracking.tracking_base":[[91,1,1,"","DummyTrackingContext"],[91,1,1,"","TrackedExperiment"],[91,1,1,"","TrackingContext"],[91,1,1,"","TrackingMixin"]],"sensai.tracking.tracking_base.DummyTrackingContext":[[91,2,1,"","__init__"],[91,2,1,"","is_enabled"],[91,2,1,"","track_figure"],[91,2,1,"","track_text"]],"sensai.tracking.tracking_base.TrackedExperiment":[[91,2,1,"","__init__"],[91,2,1,"","begin_context"],[91,2,1,"","begin_context_for_model"],[91,2,1,"","end_context"],[91,2,1,"","track_values"]],"sensai.tracking.tracking_base.TrackingContext":[[91,2,1,"","__init__"],[91,2,1,"","end"],[91,2,1,"","from_optional_experiment"],[91,2,1,"","is_enabled"],[91,2,1,"","track_figure"],[91,2,1,"","track_metrics"],[91,2,1,"","track_text"]],"sensai.tracking.tracking_base.TrackingMixin":[[91,2,1,"","begin_optional_tracking_context_for_model"],[91,2,1,"","set_tracked_experiment"],[91,3,1,"","tracked_experiment"],[91,2,1,"","unset_tracked_experiment"]],"sensai.util":[[93,0,0,"-","aggregation"],[94,0,0,"-","cache"],[95,0,0,"-","cache_azure"],[96,0,0,"-","cache_mysql"],[97,0,0,"-","datastruct"],[98,0,0,"-","deprecation"],[99,0,0,"-","dtype"],[100,0,0,"-","hash"],[101,0,0,"-","helper"],[102,0,0,"-","io"],[103,0,0,"-","jscode"],[104,0,0,"-","logging"],[105,0,0,"-","math"],[106,0,0,"-","multiprocessing"],[107,0,0,"-","pandas"],[108,0,0,"-","pickle"],[109,0,0,"-","plot"],[110,0,0,"-","profiling"],[111,0,0,"-","sequences"],[112,0,0,"-","string"],[113,0,0,"-","test"],[114,0,0,"-","time"],[115,0,0,"-","typing"],[116,0,0,"-","version"]],"sensai.util.aggregation":[[93,1,1,"","DistributionCounter"],[93,1,1,"","RelativeFrequencyCounter"],[93,1,1,"","WeightedMean"]],"sensai.util.aggregation.DistributionCounter":[[93,2,1,"","__init__"],[93,2,1,"","count"],[93,2,1,"","get_distribution"]],"sensai.util.aggregation.RelativeFrequencyCounter":[[93,2,1,"","__init__"],[93,2,1,"","add"],[93,2,1,"","count"],[93,2,1,"","get_relative_frequency"]],"sensai.util.aggregation.WeightedMean":[[93,2,1,"","__init__"],[93,2,1,"","add"],[93,2,1,"","get_weighted_mean"]],"sensai.util.cache":[[94,1,1,"","BoxedValue"],[94,1,1,"","CachedValueProviderMixin"],[94,1,1,"","DelayedUpdateHook"],[94,1,1,"","InMemoryKeyValueCache"],[94,1,1,"","KeyValueCache"],[94,1,1,"","LoadSaveInterface"],[94,1,1,"","PeriodicUpdateHook"],[94,1,1,"","PersistentKeyValueCache"],[94,1,1,"","PersistentList"],[94,5,1,"","PickleCached"],[94,1,1,"","PickleLoadSaveMixin"],[94,1,1,"","PicklePersistentKeyValueCache"],[94,1,1,"","SlicedPicklePersistentList"],[94,1,1,"","SqliteConnectionManager"],[94,1,1,"","SqlitePersistentKeyValueCache"],[94,1,1,"","SqlitePersistentList"],[94,5,1,"","cached"],[94,5,1,"","pickle_cached"]],"sensai.util.cache.BoxedValue":[[94,2,1,"","__init__"]],"sensai.util.cache.CachedValueProviderMixin":[[94,2,1,"","__init__"]],"sensai.util.cache.DelayedUpdateHook":[[94,2,1,"","__init__"],[94,2,1,"","handle_update"]],"sensai.util.cache.InMemoryKeyValueCache":[[94,2,1,"","__init__"],[94,2,1,"","empty"],[94,2,1,"","get"],[94,2,1,"","set"]],"sensai.util.cache.KeyValueCache":[[94,2,1,"","get"],[94,2,1,"","set"]],"sensai.util.cache.LoadSaveInterface":[[94,2,1,"","load"],[94,2,1,"","save"]],"sensai.util.cache.PeriodicUpdateHook":[[94,2,1,"","__init__"],[94,2,1,"","handle_update"]],"sensai.util.cache.PersistentList":[[94,2,1,"","append"],[94,2,1,"","iter_items"]],"sensai.util.cache.PickleLoadSaveMixin":[[94,2,1,"","load"],[94,2,1,"","save"]],"sensai.util.cache.PicklePersistentKeyValueCache":[[94,2,1,"","__init__"],[94,2,1,"","get"],[94,2,1,"","save"],[94,2,1,"","set"]],"sensai.util.cache.SlicedPicklePersistentList":[[94,2,1,"","__init__"],[94,2,1,"","append"],[94,2,1,"","cache_exists"],[94,2,1,"","clear"],[94,2,1,"","iter_items"]],"sensai.util.cache.SqliteConnectionManager":[[94,2,1,"","open_connection"]],"sensai.util.cache.SqlitePersistentKeyValueCache":[[94,1,1,"","KeyType"],[94,2,1,"","__init__"],[94,2,1,"","get"],[94,2,1,"","iter_items"],[94,2,1,"","set"]],"sensai.util.cache.SqlitePersistentKeyValueCache.KeyType":[[94,4,1,"","INTEGER"],[94,4,1,"","STRING"]],"sensai.util.cache.SqlitePersistentList":[[94,2,1,"","__init__"],[94,2,1,"","append"],[94,2,1,"","iter_items"]],"sensai.util.cache_azure":[[95,1,1,"","AzureLazyBatchCommitTable"],[95,1,1,"","AzureTableBlobBackend"],[95,1,1,"","AzureTablePersistentKeyValueCache"],[95,1,1,"","BlobBackedPropertyLoader"],[95,1,1,"","BlobBackedSerialisedPropertyLoader"],[95,1,1,"","BlobPerKeyAzureTableBlobBackend"],[95,1,1,"","JsonAzureTableBlobBackend"],[95,1,1,"","NumpyArrayJsonSerialiser"],[95,1,1,"","PickleAzureTableBlobBackend"],[95,1,1,"","PropertyLoader"],[95,1,1,"","SerialisedPropertyLoader"],[95,1,1,"","Serialiser"],[95,1,1,"","TextDumpAzureTableBlobBackend"]],"sensai.util.cache_azure.AzureLazyBatchCommitTable":[[95,4,1,"","AZURE_ALLOWED_TABLE_BATCH_SIZE"],[95,4,1,"","AZURE_ALLOWED_TABLE_NAME_PATTERN"],[95,1,1,"","PartitionCommandsPriorityQueue"],[95,2,1,"","__init__"],[95,2,1,"","commit_blocking_largest_partition_from_queue"],[95,2,1,"","commit_blocking_until_empty"],[95,2,1,"","commit_non_blocking_current_queue_state"],[95,2,1,"","exists"],[95,2,1,"","get_entity"],[95,2,1,"","insert_data_frame_to_table"],[95,2,1,"","insert_entity"],[95,2,1,"","insert_or_replace_entity"],[95,2,1,"","iter_data_frame_chunks"],[95,2,1,"","iter_records"],[95,2,1,"","load_table_to_data_frame"]],"sensai.util.cache_azure.AzureLazyBatchCommitTable.PartitionCommandsPriorityQueue":[[95,1,1,"","PartitionCommands"],[95,2,1,"","__init__"],[95,2,1,"","add_command"],[95,2,1,"","is_empty"],[95,2,1,"","pop"],[95,2,1,"","pop_all"]],"sensai.util.cache_azure.AzureLazyBatchCommitTable.PartitionCommandsPriorityQueue.PartitionCommands":[[95,2,1,"","__init__"],[95,2,1,"","append"],[95,2,1,"","execute"]],"sensai.util.cache_azure.AzureTableBlobBackend":[[95,2,1,"","get_value_from_reference"],[95,2,1,"","get_value_reference"],[95,2,1,"","set_value_for_reference"]],"sensai.util.cache_azure.AzureTablePersistentKeyValueCache":[[95,4,1,"","CACHE_VALUE_IDENTIFIER"],[95,2,1,"","__init__"],[95,2,1,"","get"],[95,2,1,"","set"]],"sensai.util.cache_azure.BlobBackedPropertyLoader":[[95,4,1,"","AZURE_ALLOWED_SIZE_PER_PROPERTY_BYTES"],[95,4,1,"","AZURE_ALLOWED_STRING_LENGTH_PER_PROPERTY"],[95,2,1,"","__init__"],[95,2,1,"","load_property_value"],[95,2,1,"","load_property_value_to_data_frame_column"],[95,2,1,"","write_property_value"]],"sensai.util.cache_azure.BlobBackedSerialisedPropertyLoader":[[95,2,1,"","__init__"],[95,2,1,"","load_property_value"],[95,2,1,"","load_property_value_to_data_frame_column"],[95,2,1,"","write_property_value"]],"sensai.util.cache_azure.BlobPerKeyAzureTableBlobBackend":[[95,2,1,"","__init__"],[95,3,1,"","file_extension"],[95,2,1,"","get_value_from_reference"],[95,2,1,"","get_value_reference"],[95,2,1,"","set_value_for_reference"]],"sensai.util.cache_azure.JsonAzureTableBlobBackend":[[95,3,1,"","file_extension"]],"sensai.util.cache_azure.NumpyArrayJsonSerialiser":[[95,2,1,"","deserialise"],[95,2,1,"","serialise"]],"sensai.util.cache_azure.PickleAzureTableBlobBackend":[[95,3,1,"","file_extension"]],"sensai.util.cache_azure.PropertyLoader":[[95,2,1,"","load_property_value"],[95,2,1,"","load_property_value_to_data_frame_column"],[95,2,1,"","write_property_value"]],"sensai.util.cache_azure.SerialisedPropertyLoader":[[95,2,1,"","__init__"],[95,2,1,"","load_property_value"],[95,2,1,"","load_property_value_to_data_frame_column"],[95,2,1,"","write_property_value"]],"sensai.util.cache_azure.Serialiser":[[95,2,1,"","deserialise"],[95,2,1,"","serialise"]],"sensai.util.cache_azure.TextDumpAzureTableBlobBackend":[[95,3,1,"","file_extension"]],"sensai.util.cache_mysql":[[96,1,1,"","MySQLPersistentKeyValueCache"]],"sensai.util.cache_mysql.MySQLPersistentKeyValueCache":[[96,1,1,"","ValueType"],[96,2,1,"","__init__"],[96,2,1,"","get"],[96,2,1,"","set"]],"sensai.util.cache_mysql.MySQLPersistentKeyValueCache.ValueType":[[96,4,1,"","BLOB"],[96,4,1,"","DOUBLE"]],"sensai.util.datastruct":[[97,1,1,"","DeferredParams"],[97,1,1,"","Maybe"],[97,1,1,"","SortedKeyValuePairs"],[97,1,1,"","SortedKeyValueStructure"],[97,1,1,"","SortedKeysAndValues"],[97,1,1,"","SortedValues"],[97,1,1,"","Trivalent"]],"sensai.util.datastruct.DeferredParams":[[97,4,1,"","UNDEFINED"],[97,2,1,"","__init__"],[97,2,1,"","get_dict"],[97,2,1,"","get_param"],[97,2,1,"","set_param"]],"sensai.util.datastruct.Maybe":[[97,2,1,"","__init__"]],"sensai.util.datastruct.SortedKeyValuePairs":[[97,2,1,"","__init__"],[97,2,1,"","ceil_index"],[97,2,1,"","ceil_key_and_value"],[97,2,1,"","ceil_value"],[97,2,1,"","closest_index"],[97,2,1,"","closest_key_and_value"],[97,2,1,"","closest_value"],[97,2,1,"","floor_index"],[97,2,1,"","floor_key_and_value"],[97,2,1,"","floor_value"],[97,2,1,"","from_unsorted_key_value_pairs"],[97,2,1,"","key_for_index"],[97,2,1,"","value_for_index"],[97,2,1,"","value_slice"]],"sensai.util.datastruct.SortedKeyValueStructure":[[97,2,1,"","ceil_index"],[97,2,1,"","ceil_key_and_value"],[97,2,1,"","ceil_value"],[97,2,1,"","closest_index"],[97,2,1,"","closest_key_and_value"],[97,2,1,"","closest_value"],[97,2,1,"","floor_index"],[97,2,1,"","floor_key_and_value"],[97,2,1,"","floor_value"],[97,2,1,"","interpolated_value"],[97,2,1,"","slice"]],"sensai.util.datastruct.SortedKeysAndValues":[[97,2,1,"","__init__"],[97,2,1,"","ceil_index"],[97,2,1,"","ceil_key_and_value"],[97,2,1,"","ceil_value"],[97,2,1,"","closest_index"],[97,2,1,"","closest_key_and_value"],[97,2,1,"","closest_value"],[97,2,1,"","floor_index"],[97,2,1,"","floor_key_and_value"],[97,2,1,"","floor_value"],[97,2,1,"","from_series"],[97,2,1,"","value_slice_inner"],[97,2,1,"","value_slice_outer"]],"sensai.util.datastruct.SortedValues":[[97,2,1,"","__init__"],[97,2,1,"","ceil_index"],[97,2,1,"","ceil_value"],[97,2,1,"","closest_index"],[97,2,1,"","closest_value"],[97,2,1,"","floor_index"],[97,2,1,"","floor_value"],[97,2,1,"","value_slice"]],"sensai.util.datastruct.Trivalent":[[97,4,1,"","FALSE"],[97,4,1,"","TRUE"],[97,4,1,"","UNKNOWN"],[97,2,1,"","from_bool"],[97,2,1,"","is_false"],[97,2,1,"","is_true"]],"sensai.util.deprecation":[[98,5,1,"","deprecated"]],"sensai.util.dtype":[[99,5,1,"","dict_to_ordered_tuples"],[99,5,1,"","to_float_array"]],"sensai.util.hash":[[100,5,1,"","pickle_hash"],[100,5,1,"","str_hash"]],"sensai.util.helper":[[101,5,1,"","all_none"],[101,5,1,"","any_none"],[101,5,1,"","check_not_nan_dict"],[101,5,1,"","count_none"],[101,5,1,"","count_not_none"],[101,5,1,"","flatten_arguments"],[101,5,1,"","mark_used"]],"sensai.util.io":[[102,1,1,"","ResultWriter"],[102,1,1,"","S3Object"],[102,5,1,"","is_s3_path"],[102,5,1,"","read_text_file_lines"],[102,5,1,"","write_text_file_lines"]],"sensai.util.io.ResultWriter":[[102,2,1,"","__init__"],[102,2,1,"","child_for_subdirectory"],[102,2,1,"","child_with_added_prefix"],[102,2,1,"","path"],[102,2,1,"","write_data_frame_csv_file"],[102,2,1,"","write_data_frame_text_file"],[102,2,1,"","write_figure"],[102,2,1,"","write_figures"],[102,2,1,"","write_pickle"],[102,2,1,"","write_text_file"],[102,2,1,"","write_text_file_lines"]],"sensai.util.io.S3Object":[[102,1,1,"","OutputFile"],[102,2,1,"","__init__"],[102,2,1,"","get_file_content"],[102,2,1,"","open_file"],[102,2,1,"","put"]],"sensai.util.io.S3Object.OutputFile":[[102,2,1,"","__init__"],[102,2,1,"","write"]],"sensai.util.jscode":[[103,1,1,"","JsClassInstance"],[103,1,1,"","JsCode"],[103,1,1,"","JsCodeLiteral"],[103,1,1,"","JsList"],[103,1,1,"","JsObject"],[103,1,1,"","JsValue"],[103,1,1,"","JsValueLiteral"],[103,5,1,"","js_arg_list"],[103,5,1,"","js_value"]],"sensai.util.jscode.JsClassInstance":[[103,2,1,"","__init__"]],"sensai.util.jscode.JsCode":[[103,2,1,"","get_js_code"]],"sensai.util.jscode.JsCodeLiteral":[[103,2,1,"","__init__"],[103,2,1,"","get_js_code"]],"sensai.util.jscode.JsList":[[103,2,1,"","__init__"]],"sensai.util.jscode.JsObject":[[103,2,1,"","__init__"],[103,2,1,"","add"],[103,2,1,"","add_code_literal"],[103,2,1,"","add_float"],[103,2,1,"","add_json"],[103,2,1,"","add_string"],[103,2,1,"","get_js_code"]],"sensai.util.jscode.JsValue":[[103,2,1,"","bool_value"],[103,2,1,"","float_value"],[103,2,1,"","from_python"],[103,2,1,"","from_value"],[103,2,1,"","int_value"],[103,2,1,"","is_undefined"],[103,2,1,"","null"],[103,2,1,"","string_value"],[103,2,1,"","undefined"]],"sensai.util.jscode.JsValueLiteral":[[103,2,1,"","__init__"],[103,2,1,"","get_js_code"]],"sensai.util.logging":[[104,1,1,"","FileLoggerContext"],[104,1,1,"","LogTime"],[104,1,1,"","StopWatch"],[104,1,1,"","StopWatchManager"],[104,5,1,"","add_file_logger"],[104,5,1,"","add_memory_logger"],[104,5,1,"","configure"],[104,5,1,"","datetime_tag"],[104,5,1,"","get_memory_log"],[104,5,1,"","is_log_handler_active"],[104,5,1,"","remove_log_handler"],[104,5,1,"","remove_log_handlers"],[104,5,1,"","run_cli"],[104,5,1,"","run_main"],[104,5,1,"","set_configure_callback"]],"sensai.util.logging.FileLoggerContext":[[104,2,1,"","__init__"]],"sensai.util.logging.LogTime":[[104,2,1,"","__init__"],[104,2,1,"","start"],[104,2,1,"","stop"]],"sensai.util.logging.StopWatch":[[104,2,1,"","__init__"],[104,2,1,"","get_elapsed_time_secs"],[104,2,1,"","get_elapsed_time_string"],[104,2,1,"","get_elapsed_timedelta"],[104,2,1,"","pause"],[104,2,1,"","reset"],[104,2,1,"","restart"],[104,2,1,"","resume"]],"sensai.util.logging.StopWatchManager":[[104,2,1,"","__init__"],[104,2,1,"","get_instance"],[104,2,1,"","is_running"],[104,2,1,"","start"],[104,2,1,"","stop"]],"sensai.util.math":[[105,1,1,"","NormalDistribution"],[105,5,1,"","reduce_float_precision_decimals"],[105,5,1,"","reverse_sigmoid"],[105,5,1,"","sigmoid"]],"sensai.util.math.NormalDistribution":[[105,2,1,"","__init__"],[105,2,1,"","pdf"]],"sensai.util.multiprocessing":[[106,1,1,"","VectorModelWithSeparateFeatureGeneration"]],"sensai.util.multiprocessing.VectorModelWithSeparateFeatureGeneration":[[106,1,1,"","IntermediateFittingStep"],[106,1,1,"","PredictFinaliser"],[106,2,1,"","__init__"],[106,2,1,"","fit_end"],[106,2,1,"","fit_start"],[106,2,1,"","predict_start"]],"sensai.util.multiprocessing.VectorModelWithSeparateFeatureGeneration.IntermediateFittingStep":[[106,2,1,"","__init__"],[106,2,1,"","execute"]],"sensai.util.multiprocessing.VectorModelWithSeparateFeatureGeneration.PredictFinaliser":[[106,2,1,"","__init__"],[106,2,1,"","execute"]],"sensai.util.pandas":[[107,1,1,"","DataFrameColumnChangeTracker"],[107,5,1,"","extract_array"],[107,5,1,"","remove_duplicate_index_entries"]],"sensai.util.pandas.DataFrameColumnChangeTracker":[[107,2,1,"","__init__"],[107,2,1,"","assert_change_was_tracked"],[107,2,1,"","column_change_string"],[107,2,1,"","get_added_columns"],[107,2,1,"","get_removed_columns"],[107,2,1,"","track_change"]],"sensai.util.pickle":[[108,1,1,"","PickleFailureDebugger"],[108,5,1,"","dump_pickle"],[108,5,1,"","getstate"],[108,5,1,"","load_pickle"],[108,5,1,"","setstate"]],"sensai.util.pickle.PickleFailureDebugger":[[108,2,1,"","debug_failure"],[108,4,1,"","enabled"],[108,2,1,"","log_failure_if_enabled"]],"sensai.util.plot":[[109,1,1,"","Color"],[109,1,1,"","HeatMapPlot"],[109,1,1,"","HistogramPlot"],[109,1,1,"","LinearColorMap"],[109,1,1,"","Plot"],[109,1,1,"","ScatterPlot"],[109,5,1,"","plot_matrix"]],"sensai.util.plot.Color":[[109,2,1,"","__init__"],[109,2,1,"","alpha"],[109,2,1,"","darken"],[109,2,1,"","lighten"],[109,2,1,"","to_hex"]],"sensai.util.plot.HeatMapPlot":[[109,2,1,"","DEFAULT_CMAP_FACTORY"],[109,2,1,"","__init__"]],"sensai.util.plot.HistogramPlot":[[109,2,1,"","__init__"]],"sensai.util.plot.LinearColorMap":[[109,2,1,"","__init__"],[109,2,1,"","get_color"]],"sensai.util.plot.Plot":[[109,2,1,"","__init__"],[109,2,1,"","save"],[109,2,1,"","title"],[109,2,1,"","xlabel"],[109,2,1,"","xlim"],[109,2,1,"","xtick"],[109,2,1,"","xtick_major"],[109,2,1,"","xtick_minor"],[109,2,1,"","ylabel"],[109,2,1,"","ylim"],[109,2,1,"","ytick_major"]],"sensai.util.plot.ScatterPlot":[[109,4,1,"","MAX_OPACITY"],[109,4,1,"","MIN_OPACITY"],[109,4,1,"","N_MAX_TRANSPARENCY"],[109,4,1,"","N_MIN_TRANSPARENCY"],[109,2,1,"","__init__"]],"sensai.util.profiling":[[110,5,1,"","profiled"],[110,5,1,"","timed"]],"sensai.util.sequences":[[111,5,1,"","ceil_index"],[111,5,1,"","ceil_value"],[111,5,1,"","closest_index"],[111,5,1,"","closest_value"],[111,5,1,"","concat_sequences"],[111,5,1,"","floor_index"],[111,5,1,"","floor_value"],[111,5,1,"","get_first_duplicate"],[111,5,1,"","value_slice_inner"],[111,5,1,"","value_slice_outer"]],"sensai.util.string":[[112,1,1,"","StringConverter"],[112,1,1,"","TagBuilder"],[112,1,1,"","ToStringMixin"],[112,5,1,"","dict_string"],[112,5,1,"","function_name"],[112,5,1,"","list_string"],[112,5,1,"","object_repr"],[112,5,1,"","or_regex_group"],[112,5,1,"","pretty_string_repr"],[112,5,1,"","to_string"]],"sensai.util.string.StringConverter":[[112,2,1,"","to_string"]],"sensai.util.string.TagBuilder":[[112,2,1,"","__init__"],[112,2,1,"","build"],[112,2,1,"","with_alternative"],[112,2,1,"","with_component"],[112,2,1,"","with_conditional"]],"sensai.util.string.ToStringMixin":[[112,2,1,"","_tostring_additional_entries"],[112,2,1,"","_tostring_class_name"],[112,2,1,"","_tostring_exclude_exceptions"],[112,2,1,"","_tostring_exclude_private"],[112,2,1,"","_tostring_excludes"],[112,2,1,"","_tostring_includes"],[112,2,1,"","_tostring_includes_forced"],[112,2,1,"","_tostring_object_info"],[112,2,1,"","pprint"],[112,2,1,"","pprints"]],"sensai.util.test":[[113,5,1,"","convert_floats"],[113,5,1,"","json_mapper"],[113,5,1,"","reduce_float_precision"],[113,5,1,"","snapshot_compatible"]],"sensai.util.time":[[114,1,1,"","TimeInterval"],[114,5,1,"","time_of_day"],[114,5,1,"","ts_next_month"]],"sensai.util.time.TimeInterval":[[114,2,1,"","__init__"],[114,2,1,"","contains"],[114,2,1,"","contains_time"],[114,2,1,"","intersection"],[114,2,1,"","mid_timestamp"],[114,2,1,"","overlaps_with"],[114,2,1,"","time_delta"]],"sensai.util.typing":[[115,1,1,"","PandasNamedTuple"]],"sensai.util.typing.PandasNamedTuple":[[115,3,1,"","Index"]],"sensai.util.version":[[116,1,1,"","Version"]],"sensai.util.version.Version":[[116,2,1,"","__init__"],[116,2,1,"","is_at_least"]],"sensai.vector_model":[[117,1,1,"","RuleBasedVectorClassificationModel"],[117,1,1,"","RuleBasedVectorRegressionModel"],[117,1,1,"","TrainingContext"],[117,1,1,"","VectorClassificationModel"],[117,1,1,"","VectorModel"],[117,1,1,"","VectorModelBase"],[117,1,1,"","VectorModelFittableBase"],[117,1,1,"","VectorRegressionModel"]],"sensai.vector_model.RuleBasedVectorClassificationModel":[[117,2,1,"","__init__"]],"sensai.vector_model.RuleBasedVectorRegressionModel":[[117,2,1,"","__init__"]],"sensai.vector_model.TrainingContext":[[117,2,1,"","__init__"]],"sensai.vector_model.VectorClassificationModel":[[117,2,1,"","__init__"],[117,2,1,"","convert_class_probabilities_to_predictions"],[117,2,1,"","get_class_labels"],[117,2,1,"","is_regression_model"],[117,2,1,"","predict_class_probabilities"]],"sensai.vector_model.VectorModel":[[117,4,1,"","TOSTRING_INCLUDE_PREPROCESSORS"],[117,2,1,"","__init__"],[117,2,1,"","compute_model_inputs"],[117,2,1,"","compute_model_outputs"],[117,2,1,"","fit"],[117,2,1,"","fit_input_output_data"],[117,2,1,"","get_feature_generator"],[117,2,1,"","get_feature_transformer"],[117,2,1,"","get_feature_transformer_chain"],[117,2,1,"","get_input_transformer"],[117,2,1,"","get_input_transformer_chain"],[117,2,1,"","get_model_input_variable_names"],[117,2,1,"","get_predicted_variable_names"],[117,2,1,"","get_raw_input_transformer"],[117,2,1,"","get_raw_input_transformer_chain"],[117,2,1,"","is_being_fitted"],[117,2,1,"","is_fitted"],[117,2,1,"","predict"],[117,2,1,"","remove_input_preprocessors"],[117,2,1,"","set_feature_generator"],[117,2,1,"","with_feature_collector"],[117,2,1,"","with_feature_generator"],[117,2,1,"","with_feature_transformers"],[117,2,1,"","with_input_transformers"],[117,2,1,"","with_raw_input_transformers"]],"sensai.vector_model.VectorModelBase":[[117,2,1,"","__init__"],[117,2,1,"","get_name"],[117,2,1,"","get_predicted_variable_names"],[117,2,1,"","is_regression_model"],[117,2,1,"","predict"],[117,2,1,"","set_name"],[117,2,1,"","with_name"]],"sensai.vector_model.VectorModelFittableBase":[[117,2,1,"","fit"],[117,2,1,"","is_fitted"]],"sensai.vector_model.VectorRegressionModel":[[117,2,1,"","__init__"],[117,2,1,"","get_model_output_variable_names"],[117,2,1,"","get_output_transformer_chain"],[117,2,1,"","get_target_transformer"],[117,2,1,"","is_fitted"],[117,2,1,"","is_regression_model"],[117,2,1,"","predict"],[117,2,1,"","with_output_transformers"],[117,2,1,"","with_target_transformer"]],"sensai.vectoriser":[[118,1,1,"","EmptyVectoriser"],[118,1,1,"","ItemIdentifierProvider"],[118,1,1,"","SequenceVectoriser"],[118,1,1,"","Vectoriser"],[118,1,1,"","VectoriserRegistry"]],"sensai.vectoriser.EmptyVectoriser":[[118,2,1,"","__init__"]],"sensai.vectoriser.ItemIdentifierProvider":[[118,2,1,"","get_identifier"]],"sensai.vectoriser.SequenceVectoriser":[[118,1,1,"","FittingMode"],[118,2,1,"","__init__"],[118,2,1,"","apply"],[118,2,1,"","apply_multi"],[118,2,1,"","apply_multi_with_padding"],[118,2,1,"","fit"],[118,2,1,"","get_vector_dim"]],"sensai.vectoriser.SequenceVectoriser.FittingMode":[[118,4,1,"","CONCAT"],[118,4,1,"","NONE"],[118,4,1,"","UNIQUE"]],"sensai.vectoriser.Vectoriser":[[118,1,1,"","ResultType"],[118,2,1,"","__init__"],[118,2,1,"","apply"],[118,2,1,"","apply_multi"],[118,2,1,"","fit"],[118,2,1,"","get_name"],[118,2,1,"","is_fitted"],[118,2,1,"","set_name"]],"sensai.vectoriser.Vectoriser.ResultType":[[118,4,1,"","LIST"],[118,4,1,"","NUMPY_ARRAY"],[118,4,1,"","SCALAR"],[118,2,1,"","from_value"]],"sensai.vectoriser.VectoriserRegistry":[[118,2,1,"","__init__"],[118,2,1,"","get_available_vectorisers"],[118,2,1,"","get_vectoriser"],[118,2,1,"","get_vectorisers"],[118,2,1,"","register_factory"]],"sensai.xgboost":[[119,1,1,"","XGBGradientBoostedVectorClassificationModel"],[119,1,1,"","XGBGradientBoostedVectorRegressionModel"],[119,1,1,"","XGBRandomForestVectorClassificationModel"],[119,1,1,"","XGBRandomForestVectorRegressionModel"],[119,5,1,"","is_xgboost_version_at_least"]],"sensai.xgboost.XGBGradientBoostedVectorClassificationModel":[[119,2,1,"","__init__"]],"sensai.xgboost.XGBGradientBoostedVectorRegressionModel":[[119,2,1,"","__init__"]],"sensai.xgboost.XGBRandomForestVectorClassificationModel":[[119,2,1,"","__init__"]],"sensai.xgboost.XGBRandomForestVectorRegressionModel":[[119,2,1,"","__init__"]],sensai:[[3,0,0,"-","catboost"],[4,0,0,"-","clustering"],[8,0,0,"-","columngen"],[9,0,0,"-","data"],[10,0,0,"-","data_transformation"],[14,0,0,"-","distance_metric"],[15,0,0,"-","ensemble"],[18,0,0,"-","evaluation"],[29,0,0,"-","feature_importance"],[30,0,0,"-","feature_selection"],[32,0,0,"-","featuregen"],[35,0,0,"-","geoanalytics"],[46,0,0,"-","hyperopt"],[48,0,0,"-","lightgbm"],[49,0,0,"-","local_search"],[50,0,0,"-","minizinc"],[51,0,0,"-","multi_model"],[52,0,0,"-","naive_bayes"],[53,0,0,"-","nearest_neighbors"],[54,0,0,"-","normalisation"],[55,0,0,"-","pytorch_lightning"],[57,0,0,"-","sklearn"],[61,0,0,"-","sklearn_quantile"],[62,0,0,"-","tensor_model"],[63,0,0,"-","tensorflow"],[66,0,0,"-","torch"],[87,0,0,"-","tracking"],[92,0,0,"-","util"],[117,0,0,"-","vector_model"],[118,0,0,"-","vectoriser"],[119,0,0,"-","xgboost"]]},objnames:{"0":["py","module","Python module"],"1":["py","class","Python class"],"2":["py","method","Python method"],"3":["py","property","Python property"],"4":["py","attribute","Python attribute"],"5":["py","function","Python function"],"6":["py","exception","Python exception"]},objtypes:{"0":"py:module","1":"py:class","2":"py:method","3":"py:property","4":"py:attribute","5":"py:function","6":"py:exception"},terms:{"0":[1,2,11,12,14,22,23,24,25,31,33,37,42,44,46,48,49,52,53,56,58,59,60,62,64,67,73,74,83,85,93,94,95,96,105,109,111,112,114,115,118],"00":[1,2],"000":1,"0001":60,"001":[1,2,53,60,85],"002":1,"003":[1,2],"005":2,"01":[2,44],"014":2,"017":2,"02":2,"0209":2,"0223":2,"0245":2,"0293":2,"0294":2,"03":[1,2],"03167":80,"03385":80,"0345":2,"0380":2,"039":2,"04":2,"0418":2,"04441":1,"044410":1,"0452":2,"0461":2,"046667":1,"05":[2,24,109],"050077":1,"05027":80,"0504":2,"0524":2,"053333":1,"0553":2,"0596":2,"06":2,"0610":2,"0667":2,"07":2,"0724":2,"0739":2,"075":[1,2],"08":2,"0816":2,"081762":2,"08176225980122884":2,"0818":2,"085":1,"086":1,"087":1,"088":1,"0881":2,"09":[1,2],"0906":2,"091":2,"092":1,"0953":2,"0962":2,"096233":2,"09623306624094645":2,"0974":2,"0986":2,"0996":2,"099880":2,"0999":2,"0x7ddf80988880":2,"0x7ddfdb765610":2,"0x7ddfdb773bd0":2,"0x7ddfdb7cc350":2,"0x7ddfdbab98d0":2,"0x7ddfdbbdac10":2,"0x7ddfdbf90690":2,"0x7ddfdc5d6190":2,"0x7ddfdcd5c850":2,"0x7ddfde8fa170":2,"0x7ddfded82b50":2,"0x7ddfded82c90":2,"0x7de00026d150":2,"0x7ff32e4864d0":1,"0x7ff32e5ae650":1,"0x7ff32e9eba50":1,"1":[1,2,5,7,11,12,14,16,17,22,23,24,25,27,29,31,33,39,40,43,44,46,48,49,52,56,58,59,60,62,67,74,79,80,83,85,93,94,95,96,105,107,109,111,112,118],"10":[1,2,49,59,60,80,85,104],"100":[1,12,48,59,60,73,74,95,109],"1000":[2,60,64,85,109],"100000":94,"1013":2,"102":1,"10223":1,"102230":1,"1024":2,"103":1,"104":1,"105":1,"106":1,"1068":2,"107":1,"107293":2,"1073":2,"108":1,"10x1":2,"10x10":2,"10x11":2,"10x12":2,"10x13":2,"10x14":2,"10x15":2,"10x16":2,"10x17":2,"10x18":2,"10x19":2,"10x2":2,"10x20":2,"10x21":2,"10x22":2,"10x23":2,"10x24":2,"10x25":2,"10x26":2,"10x27":2,"10x28":2,"10x3":2,"10x4":2,"10x5":2,"10x6":2,"10x7":2,"10x8":2,"10x9":2,"11":[1,2],"110":2,"113":2,"1131":2,"114":2,"115":2,"115383":2,"1154":2,"1157":2,"11x1":2,"11x10":2,"11x11":2,"11x12":2,"11x13":2,"11x14":2,"11x15":2,"11x16":2,"11x17":2,"11x18":2,"11x19":2,"11x2":2,"11x20":2,"11x21":2,"11x22":2,"11x23":2,"11x24":2,"11x25":2,"11x26":2,"11x27":2,"11x28":2,"11x3":2,"11x4":2,"11x5":2,"11x6":2,"11x7":2,"11x8":2,"11x9":2,"12":[1,2,113],"120":53,"12000":2,"1221":2,"1222":2,"122218":2,"12221813999116421":2,"1233":2,"1258":2,"1271":2,"127124":2,"1274":2,"128":2,"1281":2,"128110":2,"1286":2,"129":2,"12x1":2,"12x10":2,"12x11":2,"12x12":2,"12x13":2,"12x14":2,"12x15":2,"12x16":2,"12x17":2,"12x18":2,"12x19":2,"12x2":2,"12x20":2,"12x21":2,"12x22":2,"12x23":2,"12x24":2,"12x25":2,"12x26":2,"12x27":2,"12x28":2,"12x3":2,"12x4":2,"12x5":2,"12x6":2,"12x7":2,"12x8":2,"12x9":2,"13":[1,2,45,80],"130":1,"131459":2,"1315":2,"133373":2,"1334":2,"1341":2,"134100":2,"136":1,"1365":2,"137":1,"1381":2,"138148":2,"138400413109712":2,"139":1,"13x1":2,"13x10":2,"13x11":2,"13x12":2,"13x13":2,"13x14":2,"13x15":2,"13x16":2,"13x17":2,"13x18":2,"13x19":2,"13x2":2,"13x20":2,"13x21":2,"13x22":2,"13x23":2,"13x24":2,"13x25":2,"13x26":2,"13x27":2,"13x28":2,"13x3":2,"13x4":2,"13x5":2,"13x6":2,"13x7":2,"13x8":2,"13x9":2,"14":[1,2],"140":[1,2],"140682438463888":1,"140682469084368":1,"143283":2,"1433":2,"1440":2,"144011":2,"1450":2,"149":2,"14x1":2,"14x10":2,"14x11":2,"14x12":2,"14x13":2,"14x14":2,"14x15":2,"14x16":2,"14x17":2,"14x18":2,"14x19":2,"14x2":2,"14x20":2,"14x21":2,"14x22":2,"14x23":2,"14x24":2,"14x25":2,"14x26":2,"14x27":2,"14x28":2,"14x3":2,"14x4":2,"14x5":2,"14x6":2,"14x7":2,"14x8":2,"14x9":2,"15":[1,2,104],"1502":80,"1509":2,"150902":2,"1512":80,"1533":2,"1593":2,"159322":2,"15x1":2,"15x10":2,"15x11":2,"15x12":2,"15x13":2,"15x14":2,"15x15":2,"15x16":2,"15x17":2,"15x18":2,"15x19":2,"15x2":2,"15x20":2,"15x21":2,"15x22":2,"15x23":2,"15x24":2,"15x25":2,"15x26":2,"15x27":2,"15x28":2,"15x3":2,"15x4":2,"15x5":2,"15x6":2,"15x7":2,"15x8":2,"15x9":2,"16":[1,2],"1603":80,"167":2,"1676":2,"168":2,"1697":2,"169709":2,"16x1":2,"16x10":2,"16x11":2,"16x12":2,"16x13":2,"16x14":2,"16x15":2,"16x16":2,"16x17":2,"16x18":2,"16x19":2,"16x2":2,"16x20":2,"16x21":2,"16x22":2,"16x23":2,"16x24":2,"16x25":2,"16x26":2,"16x27":2,"16x28":2,"16x3":2,"16x4":2,"16x5":2,"16x6":2,"16x7":2,"16x8":2,"16x9":2,"17":[1,2],"177":1,"17x1":2,"17x10":2,"17x11":2,"17x12":2,"17x13":2,"17x14":2,"17x15":2,"17x16":2,"17x17":2,"17x18":2,"17x19":2,"17x2":2,"17x20":2,"17x21":2,"17x22":2,"17x23":2,"17x24":2,"17x25":2,"17x26":2,"17x27":2,"17x28":2,"17x3":2,"17x4":2,"17x5":2,"17x6":2,"17x7":2,"17x8":2,"17x9":2,"18":[1,2],"184":2,"1872":2,"187202":2,"189":1,"18x1":2,"18x10":2,"18x11":2,"18x12":2,"18x13":2,"18x14":2,"18x15":2,"18x16":2,"18x17":2,"18x18":2,"18x19":2,"18x2":2,"18x20":2,"18x21":2,"18x22":2,"18x23":2,"18x24":2,"18x25":2,"18x26":2,"18x27":2,"18x28":2,"18x3":2,"18x4":2,"18x5":2,"18x6":2,"18x7":2,"18x8":2,"18x9":2,"19":[1,2],"190":1,"191":2,"192":[1,2],"193":80,"196":1,"1962":2,"196246":2,"1981":2,"19x1":2,"19x10":2,"19x11":2,"19x12":2,"19x13":2,"19x14":2,"19x15":2,"19x16":2,"19x17":2,"19x18":2,"19x19":2,"19x2":2,"19x20":2,"19x21":2,"19x22":2,"19x23":2,"19x24":2,"19x25":2,"19x26":2,"19x27":2,"19x28":2,"19x3":2,"19x4":2,"19x5":2,"19x6":2,"19x7":2,"19x8":2,"19x9":2,"1d":118,"1x1":2,"1x10":2,"1x11":2,"1x12":2,"1x13":2,"1x14":2,"1x15":2,"1x16":2,"1x17":2,"1x18":2,"1x19":2,"1x2":2,"1x20":2,"1x21":2,"1x22":2,"1x23":2,"1x24":2,"1x25":2,"1x26":2,"1x27":2,"1x28":2,"1x3":2,"1x4":2,"1x5":2,"1x6":2,"1x7":2,"1x8":2,"1x9":2,"2":[1,2,22,24,25,33,40,42,49,61,64,73,74,80,83,95,107,118],"20":[1,2,48,53],"200":[2,59,60],"2015":80,"2016":80,"2020":80,"2024":[1,2],"208":1,"2081":2,"208118":2,"20x1":2,"20x10":2,"20x11":2,"20x12":2,"20x13":2,"20x14":2,"20x15":2,"20x16":2,"20x17":2,"20x18":2,"20x19":2,"20x2":2,"20x20":2,"20x21":2,"20x22":2,"20x23":2,"20x24":2,"20x25":2,"20x26":2,"20x27":2,"20x28":2,"20x3":2,"20x4":2,"20x5":2,"20x6":2,"20x7":2,"20x8":2,"20x9":2,"21":[1,2],"210":1,"211":1,"215":2,"21x1":2,"21x10":2,"21x11":2,"21x12":2,"21x13":2,"21x14":2,"21x15":2,"21x16":2,"21x17":2,"21x18":2,"21x19":2,"21x2":2,"21x20":2,"21x21":2,"21x22":2,"21x23":2,"21x24":2,"21x25":2,"21x26":2,"21x27":2,"21x28":2,"21x3":2,"21x4":2,"21x5":2,"21x6":2,"21x7":2,"21x8":2,"21x9":2,"22":[1,2,80],"221":2,"223":2,"224":2,"227":1,"22x1":2,"22x10":2,"22x11":2,"22x12":2,"22x13":2,"22x14":2,"22x15":2,"22x16":2,"22x17":2,"22x18":2,"22x19":2,"22x2":2,"22x20":2,"22x21":2,"22x22":2,"22x23":2,"22x24":2,"22x25":2,"22x26":2,"22x27":2,"22x28":2,"22x3":2,"22x4":2,"22x5":2,"22x6":2,"22x7":2,"22x8":2,"22x9":2,"23":1,"230":2,"233":2,"238":1,"238693":1,"239259":2,"2393":2,"23x1":2,"23x10":2,"23x11":2,"23x12":2,"23x13":2,"23x14":2,"23x15":2,"23x16":2,"23x17":2,"23x18":2,"23x19":2,"23x2":2,"23x20":2,"23x21":2,"23x22":2,"23x23":2,"23x24":2,"23x25":2,"23x26":2,"23x27":2,"23x28":2,"23x3":2,"23x4":2,"23x5":2,"23x6":2,"23x7":2,"23x8":2,"23x9":2,"24":[1,114],"2409":2,"244":2,"24x1":2,"24x10":2,"24x11":2,"24x12":2,"24x13":2,"24x14":2,"24x15":2,"24x16":2,"24x17":2,"24x18":2,"24x19":2,"24x2":2,"24x20":2,"24x21":2,"24x22":2,"24x23":2,"24x24":2,"24x25":2,"24x26":2,"24x27":2,"24x28":2,"24x3":2,"24x4":2,"24x5":2,"24x6":2,"24x7":2,"24x8":2,"24x9":2,"25":[1,2,12,80],"252":2,"2525":2,"252539":2,"254":2,"255":[2,94],"25x1":2,"25x10":2,"25x11":2,"25x12":2,"25x13":2,"25x14":2,"25x15":2,"25x16":2,"25x17":2,"25x18":2,"25x19":2,"25x2":2,"25x20":2,"25x21":2,"25x22":2,"25x23":2,"25x24":2,"25x25":2,"25x26":2,"25x27":2,"25x28":2,"25x3":2,"25x4":2,"25x5":2,"25x6":2,"25x7":2,"25x8":2,"25x9":2,"26":1,"2672":80,"26x1":2,"26x10":2,"26x11":2,"26x12":2,"26x13":2,"26x14":2,"26x15":2,"26x16":2,"26x17":2,"26x18":2,"26x19":2,"26x2":2,"26x20":2,"26x21":2,"26x22":2,"26x23":2,"26x24":2,"26x25":2,"26x26":2,"26x27":2,"26x28":2,"26x3":2,"26x4":2,"26x5":2,"26x6":2,"26x7":2,"26x8":2,"26x9":2,"276":2,"27x1":2,"27x10":2,"27x11":2,"27x12":2,"27x13":2,"27x14":2,"27x15":2,"27x16":2,"27x17":2,"27x18":2,"27x19":2,"27x2":2,"27x20":2,"27x21":2,"27x22":2,"27x23":2,"27x24":2,"27x25":2,"27x26":2,"27x27":2,"27x28":2,"27x3":2,"27x4":2,"27x5":2,"27x6":2,"27x7":2,"27x8":2,"27x9":2,"28":2,"280":1,"284687":2,"2847":2,"287":2,"288":2,"28x1":2,"28x10":2,"28x11":2,"28x12":2,"28x13":2,"28x14":2,"28x15":2,"28x16":2,"28x17":2,"28x18":2,"28x19":2,"28x2":2,"28x20":2,"28x21":2,"28x22":2,"28x23":2,"28x24":2,"28x25":2,"28x26":2,"28x27":2,"28x28":2,"28x3":2,"28x4":2,"28x5":2,"28x6":2,"28x7":2,"28x8":2,"28x9":2,"290":1,"291":1,"292":1,"293":1,"2d":[2,67,80],"2x1":2,"2x10":2,"2x11":2,"2x12":2,"2x13":2,"2x14":2,"2x15":2,"2x16":2,"2x17":2,"2x18":2,"2x19":2,"2x2":2,"2x20":2,"2x21":2,"2x22":2,"2x23":2,"2x24":2,"2x25":2,"2x26":2,"2x27":2,"2x28":2,"2x3":2,"2x4":2,"2x5":2,"2x6":2,"2x7":2,"2x8":2,"2x9":2,"3":[1,2,33,80,107],"30":[1,2],"300":1,"308":1,"309":[1,2],"31":[1,2,3,48],"310":[1,2],"311":[1,2],"312":1,"3138":2,"314":2,"315":2,"316":2,"318":1,"319":2,"32":[1,2,56],"320":2,"32000":95,"321":2,"322":2,"323":2,"324":2,"335":2,"336":2,"3390":80,"34":2,"35110632":44,"36000":2,"368":2,"370":2,"380582":2,"3806":2,"383":1,"384":1,"385":1,"3857":[39,40,43],"39":[1,2],"392":1,"394":1,"395":1,"397":1,"39810717055349726":1,"399":1,"3d":80,"3x1":2,"3x10":2,"3x11":2,"3x12":2,"3x13":2,"3x14":2,"3x15":2,"3x16":2,"3x17":2,"3x18":2,"3x19":2,"3x2":2,"3x20":2,"3x21":2,"3x22":2,"3x23":2,"3x24":2,"3x25":2,"3x26":2,"3x27":2,"3x28":2,"3x3":2,"3x4":2,"3x5":2,"3x6":2,"3x7":2,"3x8":2,"3x9":2,"4":[1,2,33,80,94,107,108],"40":2,"401":1,"40480":2,"4059":2,"41":[1,2],"413":1,"414":1,"416":1,"42":[1,2,3,9,19,26,29,46,48,49,59,60,61,119],"44":2,"450":2,"451":2,"468":2,"471":2,"474":1,"476":2,"48":1,"48000":2,"483":1,"487":1,"49":[1,2],"493":1,"494":1,"496":1,"498":1,"4x1":2,"4x10":2,"4x11":2,"4x12":2,"4x13":2,"4x14":2,"4x15":2,"4x16":2,"4x17":2,"4x18":2,"4x19":2,"4x2":2,"4x20":2,"4x21":2,"4x22":2,"4x23":2,"4x24":2,"4x25":2,"4x26":2,"4x27":2,"4x28":2,"4x3":2,"4x4":2,"4x5":2,"4x6":2,"4x7":2,"4x8":2,"4x9":2,"5":[1,2,12,19,22,29,42,46,49,65,73,74,76,80,107,109],"50":[1,2],"5021":2,"505":1,"51":[1,2],"510":1,"517":1,"518":1,"52":[1,2],"520":1,"53":[1,2],"54":[1,2],"547":2,"549":2,"55":2,"551":2,"552":2,"56":2,"561":2,"562":2,"57":[1,2],"58":[1,2],"580":2,"584":1,"586":1,"587":1,"588":1,"59":2,"590":1,"593":1,"594":1,"595":1,"596":1,"597":1,"598":1,"599":1,"5s":104,"5x1":2,"5x10":2,"5x11":2,"5x12":2,"5x13":2,"5x14":2,"5x15":2,"5x16":2,"5x17":2,"5x18":2,"5x19":2,"5x2":2,"5x20":2,"5x21":2,"5x22":2,"5x23":2,"5x24":2,"5x25":2,"5x26":2,"5x27":2,"5x28":2,"5x3":2,"5x4":2,"5x5":2,"5x6":2,"5x7":2,"5x8":2,"5x9":2,"6":[1,2,73,74,113],"60":[24,25,109],"601":1,"602":1,"603":[1,2],"604":1,"607":1,"609":1,"6141303814089187":1,"615":1,"616":1,"617":1,"618":1,"62":95,"621":1,"622":1,"623":[1,2],"624":1,"628":1,"629":1,"630":1,"6309573444801932":1,"632":1,"635":1,"6379522029160006":1,"64":[9,56,64,85],"64000":95,"642":1,"646":1,"647":1,"649":1,"651":2,"652":1,"654":2,"656":2,"660":1,"661":1,"662":1,"663":1,"667":1,"675":1,"676":1,"677":1,"678":[1,2],"682":1,"687":2,"688":2,"689":1,"69":1,"690":1,"692":1,"694":2,"695":[1,2],"699":1,"6x1":2,"6x10":2,"6x11":2,"6x12":2,"6x13":2,"6x14":2,"6x15":2,"6x16":2,"6x17":2,"6x18":2,"6x19":2,"6x2":2,"6x20":2,"6x21":2,"6x22":2,"6x23":2,"6x24":2,"6x25":2,"6x26":2,"6x27":2,"6x28":2,"6x3":2,"6x4":2,"6x5":2,"6x6":2,"6x7":2,"6x8":2,"6x9":2,"7":[1,2],"701":1,"702":1,"703":1,"705":1,"706":2,"708":1,"713":1,"714":1,"715":1,"716":1,"717":1,"720":1,"727":1,"7300":2,"730044":2,"732":2,"735":2,"74":2,"740":1,"742":1,"743":1,"744":1,"75":[2,12,85],"756512":1,"76":2,"77":[1,2],"774":2,"78":1,"784":2,"785":2,"79":2,"7x1":2,"7x10":2,"7x11":2,"7x12":2,"7x13":2,"7x14":2,"7x15":2,"7x16":2,"7x17":2,"7x18":2,"7x19":2,"7x2":2,"7x20":2,"7x21":2,"7x22":2,"7x23":2,"7x24":2,"7x25":2,"7x26":2,"7x27":2,"7x28":2,"7x3":2,"7x4":2,"7x5":2,"7x6":2,"7x7":2,"7x8":2,"7x9":2,"8":[1,2,24,49,112],"80":2,"801":2,"802":2,"803":2,"8099785263057822":1,"81":2,"814":1,"817":2,"825":2,"8259":2,"826":2,"827":1,"828":[1,2],"829":[1,2],"83":2,"830":2,"831":1,"8318":2,"833":1,"84":2,"841736920530503":1,"842":2,"843":[1,2],"844":2,"85":2,"854":1,"855":1,"856":1,"858":1,"860":2,"8611111111111112":1,"8666666666666667":1,"87":[1,2],"88":2,"883":2,"885":2,"886":2,"887":2,"8888888888888888":1,"8890980234758366":1,"892":2,"897":2,"898":1,"89878":1,"898780":1,"8x1":2,"8x10":2,"8x11":2,"8x12":2,"8x13":2,"8x14":2,"8x15":2,"8x16":2,"8x17":2,"8x18":2,"8x19":2,"8x2":2,"8x20":2,"8x21":2,"8x22":2,"8x23":2,"8x24":2,"8x25":2,"8x26":2,"8x27":2,"8x28":2,"8x3":2,"8x4":2,"8x5":2,"8x6":2,"8x7":2,"8x8":2,"8x9":2,"9":[1,2,95,109],"90":1,"900":1,"905":2,"91":[1,2],"92":[1,2],"926862":2,"9298964965102043":1,"930":2,"931":2,"932":2,"9333333333333332":1,"9333333333333333":1,"934":1,"937":2,"939":2,"94":1,"940":2,"9411926691126593":1,"944":2,"9444444444444445":1,"944683":1,"945916926388699":2,"945917":2,"9466666666666667":2,"946667":2,"949":1,"950":1,"952":1,"9523809523809524":1,"9548416039104165":1,"9553599022560102":1,"956":1,"9560552426688266":1,"96":[1,2],"9618968610010363":2,"961897":2,"96225":2,"962250":2,"963571":1,"9657414983648998":1,"9666666666666667":1,"967":2,"97":1,"972":1,"9722222222222222":1,"9734228107223192":1,"976458969438705":1,"977640":2,"9776402722798222":2,"97775":2,"977750":2,"9782716826784611":2,"978272":2,"9784166666666667":2,"978417":2,"985":2,"986":2,"99":1,"990":1,"995":2,"9x1":2,"9x10":2,"9x11":2,"9x12":2,"9x13":2,"9x14":2,"9x15":2,"9x16":2,"9x17":2,"9x18":2,"9x19":2,"9x2":2,"9x20":2,"9x21":2,"9x22":2,"9x23":2,"9x24":2,"9x25":2,"9x26":2,"9x27":2,"9x28":2,"9x3":2,"9x4":2,"9x5":2,"9x6":2,"9x7":2,"9x8":2,"9x9":2,"abstract":[1,2,6,9,11,14,16,19,21,23,24,25,27,28,29,36,41,46,49,50,53,64,67,68,83,85,91,94,95,97,103,112,117,118],"boolean":[11,22,50,95],"break":[58,112],"byte":[67,102],"case":[1,2,3,8,11,12,19,21,22,24,25,26,29,31,33,34,48,49,56,58,62,64,68,74,80,82,83,85,86,90,91,94,97,101,107,108,109,111,112,117,118],"class":[1,2,3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,41,43,44,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,69,70,73,74,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,100,102,103,104,105,106,107,108,109,112,114,115,116,117,118,119],"default":[1,2,3,11,12,19,22,23,24,25,26,33,34,39,43,46,48,61,64,67,76,79,80,85,95,97,104,108,109,110,112,118],"do":[1,2,7,11,33,34,46,68,83,85,94,95,101,111,112,117],"enum":[34,54,69,74,76,83,85,94,96,97,118],"export":39,"final":[11,46,83],"float":[1,2,6,9,11,12,14,17,19,21,22,23,24,26,28,29,31,33,36,37,43,44,45,46,49,50,53,58,61,67,68,76,77,79,80,83,85,86,91,93,94,101,103,104,105,109,110,113,114,118],"function":[1,2,11,12,21,25,29,33,37,43,45,46,49,59,60,67,69,73,74,76,79,80,85,94,98,99,101,103,104,108,109,110,112,118],"import":[1,2,25,29,31,33,40,48,58,107,117],"int":[2,5,6,7,9,14,19,22,23,27,29,33,36,37,39,40,44,45,46,49,50,53,58,59,60,67,68,73,74,76,77,79,80,82,83,85,86,94,95,97,101,103,105,109,111,115,116,118,119],"long":[74,83,89,90,91,94],"m\u00b2":37,"new":[1,8,11,33,34,46,64,85,94,95,98,102,108,109,118],"null":103,"return":[2,5,6,8,9,11,12,14,19,21,22,23,24,25,26,27,29,31,33,34,36,37,39,40,42,43,44,46,49,50,58,61,62,67,68,69,73,74,76,79,83,85,86,90,91,93,94,95,96,97,98,100,101,102,103,104,107,108,109,110,111,112,113,114,116,117,118],"short":[74,83],"static":[9,12,19,23,24,37,46,49,61,74,91,103],"super":[2,53,108,112],"switch":104,"throw":13,"transient":108,"true":[1,2,8,9,11,12,13,14,19,21,22,23,24,25,26,27,29,33,34,40,46,49,50,56,58,60,61,62,64,67,68,73,76,79,80,85,86,91,94,96,97,100,101,102,103,104,105,108,109,110,111,112,114,116,117,118],"try":[2,26,46],"void":112,"while":[2,74,94],A:[1,2,11,12,13,14,19,33,34,44,49,53,67,68,73,80,82,83,85,86,91,94,95,104,107,108,117,118],As:[1,2,74,112],Being:33,By:[39,43,67,109,112,118],For:[1,2,6,8,21,24,25,29,31,33,44,49,53,56,62,67,68,73,74,79,83,94,111,112,117],If:[1,2,8,9,11,21,23,25,26,29,33,34,39,46,48,49,53,62,64,67,68,73,74,80,83,85,86,91,94,95,97,104,108,111,112,117,118],In:[1,2,3,12,31,42,48,56,62,82,107,112,118],It:[1,2,9,11,33,39,49,67,74,80,83,91,101,104,107],No:11,Not:117,One:[2,11],Or:1,The:[1,2,6,8,9,11,21,22,25,26,31,33,34,39,40,43,46,49,53,56,62,67,68,74,80,82,83,85,90,91,93,94,101,107,109,112,117],Then:[11,25,31,67],These:[33,40,51,117],To:[1,2,6,33,34,49,95,112],_:[2,33,53,112],__call__:67,__getstate__:108,__guess:[22,26],__init__:[2,3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,43,44,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,73,74,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,102,103,104,105,106,107,109,112,114,116,117,118,119],__len__:9,__main__:2,__name__:94,__repr__:112,__setstate__:108,__str__:112,__undefined__deferredparam:97,__version__:116,_create_torch_model:2,_d:[25,29],_distribut:33,_distribution_:33,_dropout:67,_fit_classifi:[1,2],_io:112,_lib:[37,104,114],_parent:2,_slicex:94,_tensoris:2,_tostring_additional_entri:112,_tostring_class_nam:112,_tostring_exclud:112,_tostring_exclude_except:112,_tostring_exclude_priv:112,_tostring_includ:112,_tostring_includes_forc:112,_tostring_object_info:112,_tostringadditionalentri:112,_tostringexclud:112,_tostringexcludeexcept:112,_tostringexcludepriv:112,_tostringinclud:112,_tostringincludesforc:112,_tostringobjectinfo:112,a1:37,a2:37,ab:[1,80],abc:[5,6,8,9,11,14,16,19,21,22,23,24,25,26,27,28,29,33,36,41,46,49,50,53,58,61,62,64,67,68,83,85,91,94,95,97,103,112,117,118],abl:[1,68,86],ablat:83,abort:85,about:[1,2,5,43,46,90,91],abov:[1,2,5,7,24,39,49,85,112],abs_angle_differ:37,absenc:[14,94,95,96],absolut:[24,37,67,93],abstractknnfind:53,abstractsklearnmultidimvectorregressionmodel:[58,60],abstractsklearnmultipleonedimvectorregressionmodel:[3,48,58,60,61,119],abstractsklearnvectorclassificationmodel:[1,3,48,58,59,119],abstractsklearnvectorregressionmodel:58,acceler:[2,76,80],accept:[2,11,46,49,62,67,68],access:[31,94],accord:[25,53,85],accuraci:[1,2,22,29,61],accuracyinci:61,achiev:[22,24,58,59],across:[1,2,11,21,25,31],act:95,action:108,activ:[1,13,59,60,69,73,74,76,80,83],activationfunct:[2,69,73,74,76,83],activi:1,actual:[2,3,11,29,31,69,73,83,85,90,91,94,95,104,108,112,117],ad:[1,2,22,24,25,26,29,33,34,43,53,60,67,80,93,94,95,102,108,112],adadelta:85,adagrad:85,adam:[2,59,60,65,85],adamax:85,adamw:[2,85],adapt:[0,49,74,83],add:[1,8,21,24,25,29,39,46,49,52,67,90,93,94,95,102,103,108,109,112,117],add_al:21,add_categorical_default_rul:[11,33],add_code_liter:103,add_combined_eval_stat:25,add_command:95,add_cross_validation_data:29,add_data_frame_csv_fil:25,add_figur:25,add_file_logg:[1,104],add_float:103,add_json:103,add_log_to_all_context:90,add_memory_logg:104,add_metr:21,add_plot:25,add_str:103,add_valu:46,add_values_dict:91,added_filename_prefix:25,addit:[1,6,21,25,26,33,36,39,43,49,53,59,60,67,88,91,94,104,108,112,118],addition:[1,2,21,22,23,24,25,112],additional_evaluation_on_training_data:25,additional_logging_values_dict:[88,89,90,91],additional_metr:[1,21,22,23,24,26],additional_nam:118,address:[1,80],adjust:9,adjustedmutualinfoscor:23,adjustedrandscor:23,admiss:[6,36,37,60,64,94,109],advanc:1,affect:[1,33,117],aforement:112,after:[12,25,31,33,46,49,59,60,73,74,76,85,94,102,117],again:2,against:[2,116],agg_fn:[1,21,29],agg_metrics_dict:[1,21],agg_results_df:25,agglom:6,agglomer:6,aggreg:[0,1,11,25,29,31,47,85,92],aggregate_predict:[16,17],aggregated_feature_import:29,aggregatedfeatureimport:29,aggregatedpermutationfeatureimport:29,ahead:80,ai:3,al:[74,80],albeit:1,algorithm:[2,5,6,7,23,36,40,43,49,85,100],alia:[21,34,115],align:95,all:[1,2,5,6,9,11,12,13,14,21,22,23,24,25,26,29,31,33,34,39,40,46,48,49,53,56,58,59,62,74,76,80,83,85,90,93,94,95,101,104,107,109,112,117,118],all_non:101,all_results_df:25,allneighborsprovid:53,allow:[1,2,33,36,67,83,95,104,118],allow_default:64,allowdefault:64,allowed_nam:112,alon:117,along:[37,83,112],alongsid:60,alpha:[42,60,109],alpha_shap:42,alreadi:[1,2,11,27,33,34,46,60,94,102,104,108,109,118],also:[1,2,24,25,40,49,62,80,85,104,109,112,118],also_include_cross_val_global_stat:25,also_include_unsorted_result:25,alwai:[1,8,11,25,33,53,59,60,68,86,93,112,117,118],amax:1,ambigu:2,amin:1,among:[1,6,49],amount:109,an:[0,1,6,7,8,9,11,13,21,22,24,25,26,31,33,34,36,37,39,40,46,49,50,53,54,58,60,61,62,64,67,68,69,73,74,80,83,85,86,90,93,94,95,96,97,102,104,107,108,109,111,112,113,117,118],analog:[1,22],analys:[1,2],angl:37,ani:[1,2,9,11,12,13,19,21,22,25,26,31,33,36,46,67,68,70,73,74,77,80,82,83,85,86,90,91,94,95,97,100,101,102,103,104,108,109,111,112,117,118],anneal:[46,49],annot:[110,115],anoth:[1,2,11,31,33,46,49,118],any_non:101,apart:74,api:[7,11,33,34,39,95],appear:[11,118],append:[1,11,33,94,95,102,104,118],appli:[0,1,6,8,9,11,12,22,25,26,29,31,33,34,36,43,46,49,58,59,60,62,67,68,69,73,74,76,79,85,94,104,112,117,118],applic:[6,11,21,22,24,46,49,56,62,67,94,118],apply_best_st:49,apply_clust:6,apply_converter_to_non_complex_object:112,apply_cost_chang:49,apply_invers:11,apply_multi:118,apply_multi_with_pad:118,apply_output_dim_weight:85,apply_output_dim_weights_in_valid:85,apply_sc:67,apply_state_chang:[46,49],apply_state_represent:[46,49],apply_to_input:9,applystaterepresent:[46,49],approach:[2,49,98],appropri:[1,11,26,49,67,85,104,108,113],approxim:[37,68,86],approximate_squared_dist:37,ar:[1,2,3,6,8,9,11,12,13,14,19,21,22,25,26,29,31,33,34,36,44,46,48,49,51,53,61,62,67,68,73,74,80,82,83,85,86,90,93,94,95,97,101,102,103,104,107,108,109,111,112,117,118],arbitari:1,arbitaririli:1,arbitrari:[1,2,11,33,46,49],arbitrarili:[89,90,91,117],architectur:[73,80],archiv:[46,49],area:[37,40,44],aren:112,arg:[7,9,12,21,22,24,26,27,41,67,74,77,80,83,86,94,97,101,103,118],argument:[1,12,36,46,58,59,60,61,69,85,94,101,103,104,109,118],arithmet:97,around:[7,39,43,90,91,112],arr:[12,111],arrai:[1,2,11,13,31,39,40,41,50,61,62,67,95,107,111,113,117,118],array_to_mini_zinc:50,array_valu:11,array_valued_result:11,arriv:94,articl:80,artifact:88,arxiv:80,as_multipoint:39,as_numpi:67,ascend:[11,25,29,46],asctim:104,asgd:85,aspect:1,assert_change_was_track:107,assign:[11,49],assist:[1,2,112,116],associ:[1,5,6,7,11,25,39,40,46,49,94,109],assum:[11,21,22,26,40,46,49,53,67,83,95,101,104,107,118],atom:94,attempt:11,attribut:[21,22,53,61,94,104,112,116],audio:2,auto:[1,2,21,24,59,60,74,109],automat:[2,3,25,46,48,49,88,94,109],autoregress:67,autoreload:[1,2],av_siz:23,avail:[33,85,104],available_featur:34,averag:[31,83,85],averageclusters:23,averagingvectorregressionmodel:17,avoid:[2,6,33,46,52,53,91],awar:101,ax:[2,109],axi:[1,11,21,109],azur:[88,95],azure_allowed_size_per_property_byt:95,azure_allowed_string_length_per_properti:95,azure_allowed_table_batch_s:95,azure_allowed_table_name_pattern:95,azure_track:[0,47,87],azurelazybatchcommitt:95,azureml:88,azuretableblobbackend:95,azuretablepersistentkeyvaluecach:95,b:[12,33,68,73,86,97,107,109],back:95,backend:[94,95,108],balancedaccuraci:[1,2,22],bar:[25,29,33,107],bar_1:[25,29],bar_2:[25,29],base:[1,2,3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,41,42,43,44,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,69,70,73,74,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,100,102,103,104,105,106,107,108,109,112,114,115,116,117,118,119],baseinputoutputdata:9,basi:46,basic:[2,67],batch:[59,60,67,68,80,85,86,95,107],batch_siz:[2,9,56,59,60,64,65,68,74,83,85,86,95],batchsiz:[74,85],bay:52,becaus:[2,11,31,46,67,97,112,117],becom:[1,2,105],been:[1,2,6,11,29,31,33,34,46,49,64,80,93,94,97,117,118],befor:[9,19,25,26,27,33,67,80,85,94,104,109,117,118],beforehand:95,begin:[2,49,85,90,91,104,112],begin_context:[90,91],begin_context_for_model:[90,91],begin_optional_tracking_context_for_model:91,behaviour:[3,24,80,104],behind:80,being:[1,2,6,8,11,12,21,22,25,26,31,46,67,73,74,85,94,95,102,108,112,117],belong:[9,11],below:[5,7,19,24,39,46,49],best:[1,2,31,46,49,85],best_epoch:[67,85],bestcostvalu:49,bestepoch:2,bestparam:46,better:[2,46,94],between:[2,36,37,93,94,107,109,117],beyond:[22,85],bfg:[59,60,85],bilinear:[73,74],bin:[1,21,24,33,109],binari:[1,2,22,26,56,62,97],binary_classification_positive_label_candid:22,binary_positive_label:[22,26],binaryclassificationcount:22,binaryclassificationmetr:22,binaryclassificationmetricf1scor:22,binaryclassificationmetricprecis:22,binaryclassificationmetricprecisionthreshold:22,binaryclassificationmetricrecal:22,binaryclassificationmetricrecallforprecis:22,binaryclassificationmetricrecallthreshold:22,binaryclassificationprobabilitythresholdvariationdata:22,binwidth:109,bisect:97,bit:2,black:109,blob:[95,96],blob_backend:95,blob_name_prefix:95,blob_prefix:95,blobbackedpropertyload:95,blobbackedserialisedpropertyload:95,blobperkeyazuretableblobbackend:95,block:[80,95,104],block_blob_servic:95,blockblobservic:95,bool:[2,5,6,8,11,14,19,21,22,25,26,28,31,33,34,36,39,46,59,60,62,67,68,76,79,80,82,83,85,86,91,94,97,101,103,104,112,114,117,118],bool_valu:103,boost:[48,119],bootstrap:[1,2],border:42,both:[1,2,9,12,14,26,67,83,85,97,101,107],bottleneck:80,bottleneck_dimension_factor:[79,80],bound:[21,22,23,24,37,44,61,97,111],boundari:[9,21,24,33],box:[44,94],box_valu:94,boxedvalu:94,bracket:112,buffer:104,build:[67,112],builder:112,built:[2,58],busi:94,bypass:[33,80],c1:[6,36],c2:[6,36],c:[2,33,80,109],c_base:109,c_opac:109,cach:[0,5,8,14,33,39,46,47,53,92,95,96,117,118],cache_azur:[0,47,92],cache_base_path:94,cache_exist:94,cache_factori:94,cache_mysql:[0,47,92],cache_valu:95,cache_value_identifi:95,cacheddistancemetr:14,cachedseriesdistancemetr:53,cachedvalueprovidermixin:[14,94],cachingknearestneighboursfind:53,calcul:[27,93],calinskiharabaszscor:23,call:[1,12,25,26,33,46,49,67,74,80,91,94,95,98,104,108,112,117,118],callabl:[5,11,12,25,26,28,31,34,39,43,46,49,53,67,69,74,76,77,85,94,95,104,109,110,112,118],callback:104,can:[1,2,6,8,9,11,19,21,22,24,25,27,29,33,34,44,46,49,53,56,61,62,67,68,69,73,74,80,82,83,85,86,90,91,94,97,98,103,104,107,108,112,117,118],candid:[6,36],cannot:[11,21,22,24,25,33,44,62,67,79,95,101,108,117],caption:109,care:2,carri:1,cartesian:[6,44],cast:11,catboost:[0,1,47],catboostvectorclassificationmodel:3,catboostvectorregressionmodel:3,categor:[1,3,8,11,13,33,34,48,52],categori:[1,3,11,13,33,34,48],categorical_feature_nam:[3,11,33,48,53],categoricalnaivebayesvectorclassificationmodel:52,cater:[1,2,83],caus:[25,29,67,112,113],ccp_alpha:[1,2],cdf:[21,25,109],cdf_complementari:[21,25,109],cdf_secondary_axi:109,ceil:97,ceil_index:[97,111],ceil_key_and_valu:97,ceil_valu:[97,111],cell:[1,11,44,117],center:12,centr:[12,36,44,60,68],central:[1,24,44,117],centre_lat:37,centre_lon:37,centroid:5,certain:[56,62,80,90,94],certainli:1,cfg:2,chain:[11,33,49,117],chainedfeaturegener:33,chang:[2,25,33,44,46,49,85,104,107,117],changed_df:107,channel:[107,109],charact:[102,112],check:[2,22,56,62,67,94,101,116,117],check_input:14,check_input_column:[56,62,117],check_input_shap:[56,62],check_input_valu:14,check_interval_sec:94,check_not_nan_dict:101,check_output_shap:[56,62],checkintervalsec:94,chen:80,child:[25,48],child_for_subdirectori:102,child_with_added_prefix:102,choic:49,choos:[1,46,49],choose_param:[46,49],chosen:[46,49],christian:80,chunk:95,chunk_siz:95,circular:37,ck:[73,74],cl:[11,108,117],class_nam:103,class_weight:[1,2],classif:[0,1,3,22,25,26,29,33,56,62,67,73,74,76,79,85,119],classifi:[1,2,23,25,48,62,117],classificationevalstat:[1,2,19,22,25,26],classificationevalstatscollect:[19,22,25],classificationevalstatsplot:[1,22],classificationevalstatsplotcollector:25,classificationevalstatsplotconfusionmatrix:22,classificationevalstatsplotprecisionrecal:22,classificationevalstatsplotprobabilitythresholdcount:22,classificationevalstatsplotprobabilitythresholdprecisionrecal:22,classificationevaluatorparam:[1,2,19,25,26],classificationmetr:[22,26,28],classificationmetricaccuraci:22,classificationmetricaccuracymaxprobabilitybeyondthreshold:22,classificationmetricaccuracywithoutlabel:22,classificationmetricbalancedaccuraci:22,classificationmetricgeometricmeanoftrueclassprob:22,classificationmetricrelfreqmaxprobabilitybeyondthreshold:22,classificationmetrictopnaccuraci:[1,22],classificationmodelevalu:[1,2,25],classificationmultidatamodelcomparisondata:25,classificationoutputmod:[2,67,69,85],classificationvectordatautil:68,classmethod:[9,22,23,24,26,37,39,61,64,67,69,85,94,97,103,104,108,118],clean:58,cleanli:90,clear:94,clear_result:67,clearml:89,clearml_track:[0,47,87],clearmlexperi:89,clearmltrackingcontext:89,cli:104,client:104,clip:109,close:[90,102,111,112],close_figur:102,closer:[1,49],closest:[37,97,111],closest_index:[97,111],closest_key_and_valu:97,closest_point_on_polylin:37,closest_point_on_seg:37,closest_valu:[97,111],cloudpickl:94,cluster:[0,5,6,7,23,27,36,39,40,41,42,47],cluster_id:[5,39],cluster_identifi:5,clustering_bas:[0,4,7,23,27,39,40,41,42,47],clustering_model:23,clusteringmodel:39,clusteringmodelevalu:27,clusteringmodelsupervisedevalu:27,clusteringmodelunsupervisedevalu:27,clusteringsupervisedevalstat:[23,27],clusteringsupervisedmetr:23,clusteringunsupervisedevalstat:[23,27],clusteringunsupervisedmetr:23,clusterlabelsevalstat:23,clusterlabelsmask:23,clustermerg:6,clusters_indic:36,clusters_local_point:36,clustersizestd:23,cm:1,cmap:[2,24,109],cmap_point:109,cmap_points_normalis:109,cnn:[0,56,62,74],cnn_model:2,cnn_model_from_modul:2,cnn_modul:2,cnnmodel:2,coars:[5,43],code:[1,2,50,91,94,100,103,104],coeffici:24,coerc:67,coincid:[26,56,62,117],col_nam:11,collect:[1,21,24,25,34,46,49,85,108,118],collect_data_fram:46,collect_featur:34,collect_result:25,collect_stat:[46,49],collectdatafram:46,collector:[1,25,34,117],collectstat:49,color:[39,109],colour:[2,24,109],column:[1,2,3,8,9,11,14,21,22,25,29,33,34,44,46,48,56,62,67,73,76,79,82,86,95,107,117],column_change_str:107,column_for_aggreg:11,column_for_entry_count:11,column_gen:33,column_gener:[8,11],column_name_for_model_rank:25,column_name_for_resulting_count:11,column_transform:11,columnchangetrack:107,columngen:[0,33,47],columngener:[8,11,33],columngeneratorcachedbyindex:8,columns_map:11,columns_to_flatten:33,columntransform:11,com:[44,95],combin:[1,2,21,22,24,25,46,51,53,73,74,83,95,109,117],come:[29,94],command:95,commit:[94,95],commit_blocking_largest_partition_from_queu:95,commit_blocking_until_empti:95,commit_non_blocking_current_queue_st:95,common:[1,83,109],common_rang:109,commonli:34,compact:[46,49,104],compar:[0,2,25],compare_model:[1,2,25],compare_models_cross_valid:25,comparison:[1,2,25],comparison_data:2,compat:[7,29,39,50,58,59,113],compil:95,complementari:[21,25,109],complet:[1,2,31,49,74,85,104,108,109],complex:[1,73,74,94,112,117],compon:[1,2,46,53,68,73,74,82,83,94,112,116],compos:109,composit:53,compromis:80,comput:[1,2,6,8,14,21,22,23,24,25,26,29,31,33,36,37,42,43,46,48,49,53,58,59,85,93,94,97,100,117,118],compute_abs_error:24,compute_all_predict:16,compute_confidence_interv:61,compute_cost_valu:[46,49],compute_encoder_dim:74,compute_error:24,compute_input_output_correl:9,compute_ma:24,compute_merg:6,compute_metr:[26,46],compute_metric_valu:[1,21,24,28],compute_metrics_fn:26,compute_model_input:117,compute_model_output:117,compute_ms:24,compute_pcc:24,compute_permutation_feature_importance_dict:29,compute_prob:[1,25,26],compute_r2:24,compute_rms:24,compute_rrs:24,compute_split_indic:9,compute_std_dev_a:24,compute_test_data_output:26,compute_train_batch_loss:85,compute_valu:[22,23,24,61],compute_value_for_eval_stat:[21,22,23,24],computemetr:26,computetrainbatchloss:85,concat:[1,33,68,118],concat_input:83,concat_sequ:111,concaten:[6,33,39,51,83,118],concav:42,concept:3,concis:[1,90],concret:[1,46,49],cond:112,condit:[5,11,22,33,39,90,91,112],condition:112,confid:61,config:2,configur:[1,2,46,53,64,67,80,104],configure_sess:64,configurelog:1,confus:1,confusionmatrix:22,conjunct:[33,104,117],connect:[37,80,95],consecut:53,consid:[6,21,22,31,33,36,40,46,53,73,74,85,93,94,112,113,117],consider:118,consist:[80,83],consol:110,constant:[43,49,60],constraint:44,construct:[1,2,6,11,24,26,33,49,53,67,94,95,97,104,118],constructor:[46,58,59,60],consum:33,consumpt:80,contain:[1,2,5,6,9,11,19,21,22,23,24,25,26,29,31,33,36,39,40,43,46,48,49,50,61,62,67,68,76,79,82,83,94,95,97,99,101,104,111,112,114,116,117,118],container_nam:95,contains_tim:114,content:[89,90,91,100,102,109],context:[11,25,29,33,68,82,90,91,104,112,117],context_info:108,context_manag:95,context_prefix:[90,91],continu:[24,33],contrari:117,contrast:42,control:[2,60,64],conv2d:2,conveni:[11,34,39,67,90,91,95,97,104,112,117],convers:[36,44,67,94,99,112,118],convert:[11,49,50,62,67,82,103,107,112,113,117],convert_class_probabilities_to_predict:[62,117],convert_float:113,convolut:[2,73,74],coordin:[0,6,35,36,37,38,39,40,42,43,44,45,47],coordinate_clust:[0,35,38,47],coordinate_clustering_ground_truth:[0,35,38,47],coordinate_pair_kei:43,coordinateclust:39,coordinateeuclideancluster:39,coordinatespanningtre:43,copi:[8,19,33],core:[8,9,11,14,16,17,21,22,24,25,26,29,33,46,53,54,61,62,67,68,73,82,85,86,88,95,97,99,102,106,107,117],correct:94,correctli:[25,67,73],correl:24,correspond:[8,9,12,21,24,33,46,49,58,59,62,67,68,74,80,85,86,95,97,107,111,112,117],cosmosdb:95,cost:[6,36,46,49,50],cost_delta:[46,49],cost_delta_for_symmetri:49,cost_valu:50,costdelta:49,costscal:50,costvalu:[46,49],could:[1,2,31,46,68,86,107],count:[1,11,21,22,52,58,59,93,101],count_non:101,count_not_non:101,countabl:22,counter:93,covari:80,cover:[40,44],cpu:2,cr:[39,40,43],craft:117,creat:[0,1,3,8,9,11,19,21,22,24,25,26,31,33,34,37,46,48,49,58,60,64,67,79,80,85,90,94,97,102,109,112,118],create_batch:67,create_combined_eval_stats_plot:25,create_criterion:85,create_cross_valid:25,create_data_set_provid:67,create_decod:83,create_default_binary_classification_metr:22,create_dft_normalis:34,create_dft_one_hot_encod:34,create_distribution_plot:25,create_encod:83,create_eval_stats_collect:24,create_evalu:25,create_evaluation_util:25,create_feature_transformer_normalis:34,create_feature_transformer_one_hot_encod:34,create_figur:[21,22,24],create_fold:19,create_metric_distribution_plot:25,create_metrics_dict_provid:[19,26],create_mini_zinc_fil:50,create_multi_feature_gener:34,create_plot:25,create_predictor:83,create_sklearn_model:58,create_torch_modul:[67,82,85],create_torch_module_for_dim:[2,67,76,79],create_validation_loss_evalu:85,create_vector_model_cross_valid:25,create_vector_model_evalu:25,createbatch:67,createtorchmodul:67,creation:[11,25,34,49,53,67,82,83,94],criterion:[1,2,85],crititc:1,cross:[0,19,25,31,46],cross_val_data:29,cross_valid:25,cross_validation_data:[1,25],cross_validator_param:[1,25,31,70],crossentropi:85,crossentropyloss:[74,85],crossval:[0,1,18,25,29,31,47,70],crossvalidationsplitt:19,crossvalidationsplitterdefault:19,crossvalidationsplitternest:19,cs:80,csv:[2,25,46],csv_path:46,csv_results_path:46,csvpath:46,csvresultspath:46,ctrl:2,ctx:33,cuda:[2,67,68,73,76,79,82,85,86],cumul:[21,25,109],current:[25,46,95,104,113,117],curv:49,custom:[0,24,67,112,118],customis:[0,95],cut:33,d:[46,49,67,68,94,99,101,112],dai:[80,114],darken:109,data:[0,2,3,5,6,8,11,12,19,21,22,23,24,25,26,27,29,31,33,34,36,39,43,44,46,47,48,49,53,54,56,58,59,60,61,62,67,68,70,73,74,76,79,82,85,86,93,94,95,97,99,107,109,113,117,118],data_fram:54,data_frame_splitt:[9,67,68],data_frame_transform:11,data_splitt:[1,26],data_transform:[0,8,11,12,26,33,34,47,53,68,117],data_util:68,databas:94,dataclass:104,datafile_path:2,datafram:[1,2,5,8,9,11,14,16,17,21,22,24,25,26,29,33,46,53,54,61,62,64,67,68,73,82,86,95,99,102,106,107,113,117],dataframecolumnchangetrack:107,dataframesplitt:[2,9,67,68],dataframesplittercolumnequivalenceclass:9,dataframesplitterfract:9,dataframetransform:[1,11,26,33,117],dataframetransformerchain:[11,117],datapoint:[5,23,27,43],dataset:[1,2,25,26,27,68,86,107],dataset_nam:25,datasplitt:[1,9,26],datasplitterfract:[1,2,9],datasplitterfromdataframesplitt:9,datasplitterfromsklearnsplitt:9,datasplitterstratifiedshufflesplit:9,datastruct:[0,47,92],datautil:[68,73,85],date:104,datetim:114,datetime_tag:104,daviesbouldinscor:23,db:96,dbscan:36,dbscangeocoordcluster:36,de:95,deactiv:80,deal:[1,2],debug:[2,50,112],debug_failur:108,decai:49,decemb:80,decid:[1,46],decim:[11,50,105,113],decis:[1,2,22],decisiontre:1,decisiontreeclassifi:1,declar:1,decod:[82,83,118],decoder_factori:82,decoderfactori:[82,83],decoderprotocol:83,decor:[8,14,94,98,110],decoupl:1,dedic:83,deep:[19,58,80],def:2,default_cmap_factori:109,default_for_output_mod:85,default_higher_is_bett:46,default_metr:23,default_metric_nam:46,default_multiclass_classification_metr:22,default_regression_metr:24,default_splitter_random_se:19,default_splitter_shuffl:19,default_transformer_factori:[11,34,118],defer:[94,95],deferred_commit_delay_sec:[94,95,96],deferred_save_delay_sec:[14,94],deferredparam:97,deferredsavedelaysec:94,defin:[1,2,6,9,11,12,19,21,24,26,37,53,59,60,67,79,83,85,97,111,112,117],definit:[42,111,112],degre:49,degree_of_complet:49,delai:[2,94],delaunai:43,delaunay_graph:43,delayedupdatehook:94,delta:[46,49],demand:67,democrat:53,denomin:[22,93],denormalis:68,denot:62,dens:74,densiti:[21,109],depend:[1,74,83,85,97,112],dependend:67,deploy:1,deprec:[0,1,21,47,92],depth:48,deriv:[2,46,49,102,110,112],descend:29,describ:[2,25,29,49,80],descript:[1,90,91],deserialis:95,design:[2,80,97,112],desir:[9,27,68,73,83,117,118],detail:25,detect:26,determin:[2,6,12,31,33,36,49,60,67,68,73,76,82,85,97,109,117,118],determinist:100,deviat:[24,67,105],devic:[68,82],df:[2,8,9,11,25,33,46,62,68,82,86,95,102,107,117],df_indexed_by_id:[14,53],dft:[0,2,8,10,26,33,34,47,53,68,117],dftaggregationoncolumn:11,dftcastcategoricalcolumn:11,dftcolumnfilt:11,dftconditionalrowfilteroncolumn:11,dftcountentri:11,dftdropna:11,dftdrowfilteronindex:11,dftfillna:[11,33],dftfromcolumngener:11,dftfromfeaturegener:11,dftinsetcomparisonrowfilteroncolumn:11,dftkeepcolumn:11,dftmodifycolumn:11,dftmodifycolumnvector:11,dftnormalis:[2,8,11,33,34,53],dftnotinsetcomparisonrowfilteroncolumn:11,dftonehotencod:11,dftrenamecolumn:11,dftroundfloat:11,dftrowfilt:11,dftsklearntransform:[2,11,68],dftsortcolumn:11,dftvectorizedconditionalrowfilteroncolumn:11,diagon:[24,109],diagonal_color:109,dict:[11,21,22,23,25,26,29,43,46,58,67,70,73,79,85,86,88,91,93,95,97,99,101,108,112],dict_str:112,dict_to_ordered_tupl:99,dictionari:[1,5,11,19,21,22,23,25,26,29,33,36,43,46,58,85,93,94,97,101,108,112],differ:[1,2,25,31,37,42,46,80,83,85,109,112,113,117],differenti:[1,94],differing_output_normalisation_mod:68,differingoutputnormalisationmod:68,digit:[2,50,73,113],dim1:33,dim2:33,dim:[2,36,40,50],dim_per_item:83,dim_per_window_item:83,dimens:[2,21,24,33,58,61,62,67,68,73,74,76,79,80,82,83,85,107,109,118],dimension:[21,42,58,68,73,74,117,118],dir_nam:102,direct:[21,22,74,83,97],directli:[1,25,46,67,74,83,94,97],directori:[46,94],disabl:[1,8,11,56,62,74,91,94,104,108,117],disable_plot:[1,25],discard:[29,31,33,94],discret:[1,49],discretis:33,displai:1,distanc:[6,14,36,37,53,97,111],distance_based_weight:53,distance_epsilon:53,distance_metr:[0,47,53],distance_metric_cach:53,distance_to:37,distancematrixdfcach:14,distancemetr:[14,53],distancemetriccach:53,distribut:[1,12,21,25,33,80,105,109],distribution_plots_cdf:25,distribution_plots_cdf_complementari:25,distributioncount:93,divid:[2,109],divisor:2,doc:[3,33,95],docstr:[74,104],docstring_pars:104,doe:[2,11,33,46,49,74,80,94,97,101,108,112,117],doesn:2,doi:80,domain:[1,2],don:[1,42],dongwei:80,dot:60,dot_path:60,doubl:96,down:85,downstream:[1,26],draw:[67,109],drawn:49,drop:[1,11,49,103,112],drop_trailing_undefin:103,dropout:[2,67,73,74,76,80,83],dtype:[0,3,11,33,47,48,92,107],due:[2,95],dummi:91,dummytrackingcontext:91,dump_pickl:108,dumppickl:94,duplic:[46,107,111],durat:[46,49,67],dure:[1,2,11,13,25,31,33,34,46,49,56,62,67,73,74,79,80,85,94,95,104,117],e22020193:80,e:[1,2,5,6,9,11,14,19,21,22,25,26,29,31,33,34,44,46,49,56,60,61,62,67,73,74,80,85,86,89,90,91,94,95,97,102,104,107,109,111,112,116,117,118],each:[1,2,6,8,11,12,19,21,24,25,26,29,31,33,34,36,44,46,49,52,53,58,59,68,73,74,76,80,82,83,85,86,88,91,94,95,102,107,109,112,117,118],earli:[2,59,60,85,117],earlier:[1,2,67],early_stop:[59,60],early_stopping_epoch:[2,85],earlystoppingepoch:85,easili:2,east:44,edg:[42,43],edge_weight:43,edit:2,effect:[11,46,91,104,112],either:[9,11,21,25,29,33,46,49,58,67,68,69,83,86,94,101,103,118],elabor:2,elaps:104,electr:80,element:[1,33,46,74,83,107,111,112],element_cast:50,elimin:31,els:25,empir:[33,49,52],empti:[62,94,95,97,102,107,111,117],emptyvectoris:118,en13102672:80,en:[48,95,119],enabl:[1,2,19,26,29,34,46,49,59,60,76,85,90,91,104,108,109,112],encapsul:[2,67,79],enclos:112,encod:[3,11,13,33,34,48,56,58,59,62,74,82,83,112,118],encoder_factori:82,encoderdecodermodel:82,encoderdecodermodul:83,encoderdecodervectorregressionmodel:82,encoderfactori:[82,83],encoderprotocol:83,encompass:[68,86,117],encount:[11,34],encourag:8,end:[1,2,9,25,46,49,73,74,85,91,94,97,104,114,117],end_context:[90,91],end_validation_collect:85,endvalidationcollect:85,energi:80,engin:2,enhanc:43,ensembl:[0,16,17,47,117],ensemble_bas:[0,15,17,47],ensembleclassificationvectormodel:16,ensembleregressionvectormodel:[16,17],ensemblevectormodel:16,ensur:[33,58,59,67,94,104,117],entir:[1,11,25,31,73,74,83,85,117],entiti:95,entri:[8,11,25,33,43,56,62,85,94,97,107,109,112],entropi:80,enumer:[2,54,69,74,85,94,96,97,118],ep:36,epoch:[2,59,60,64,65,85],epsg:[39,40,43],equal:[2,12,40,58,59,80,95,97,107,111],equidist:49,equival:[1,9,46,53,113],error:[11,24,33,34,108],error_boundari:24,esc_random_forest:1,especi:[2,34,118],essenc:1,essenti:1,estim:[21,109],et:[74,80],etc:[1,29,85,112,116],euclidean:43,euclideancluster:[5,7,23,27,39,40,41,42],euclideandistancemetr:14,euclidian:36,ev_util:28,eval_data:[1,2,25],eval_data_list:19,eval_model:[1,19,26,27,88],eval_model_via_evalu:25,eval_stat:[0,1,18,19,21,22,23,24,25,26,27,28,47,61],eval_stats_bas:[0,18,20,22,23,24,25,47],eval_stats_by_model_nam:25,eval_stats_classif:[0,1,18,19,20,25,26,28,47],eval_stats_clust:[0,18,20,27,47],eval_stats_list:[21,22,24],eval_stats_plot_collector:[1,25],eval_stats_regress:[0,18,19,20,25,26,28,47,61],eval_util:[0,1,2,18,28,47,70],evalmodel:[19,26],evalstat:[1,21,22,23,24,25],evalstatscollect:[21,22,24],evalstatsplot:[21,22,24,25],evalstatsplotcollector:25,evalu:[0,2,6,19,21,22,23,24,25,27,28,29,31,36,40,46,47,56,61,62,67,70,73,74,85,88,90,109],evaluationresultcollector:25,evaluator_clust:[0,18,47],evaluator_param:[1,2,19,25,70],evaluatorparam:[1,26],even:[1,2,82,83,91,112],event:[93,104],eventu:94,everi:[1,2,25,44,46,73,74,91,94,107,109,110,112,117],everyth:62,exactli:[25,29],exampl:[1,2,3,6,25,29,33,48,62,67,68,74,86,94,107,112],exce:[67,85],exceed:6,except:[11,13,25,26,34,62,68,86,104,111,112,117],except_column:33,exclud:[29,112],exclude_input_preprocessor:29,exclude_model_input_preprocessor:29,excluded_default_properti:108,excluded_properti:108,exclus:[93,112],execut:[33,90,94,95,104,106,110],exempt:112,exist:[8,33,34,36,46,85,94,95,104,108,111,117],exit:90,expect:[1,9,62,74,107],experi:[1,2,19,25,26,31,88,89,90,91],experiment_nam:[88,90],explicit:25,explicitli:112,expon:49,exponent_factor:49,exponenti:49,express:[11,25,29,34,112],extend:[2,11,25,97,112],extenion:102,extens:[89,90,91,94,102],extension_to_add:102,extensiontoadd:102,extrac:1,extract:[1,40,41,107],extract_1d_array_from_output:50,extract_arrai:107,extract_coordinates_arrai:41,extract_multi_dim_array_from_output:50,f1:22,f:[2,50,69,101,105,113,118],facilit:[1,2,25,34,109,112],fact:[25,49,118],factor:[49,80,83],factori:[2,11,24,25,31,33,34,46,49,53,67,79,82,83,85,94,118],fail:[108,117],fall:42,fallback:[97,111],fallback_bound:111,fallback_first:111,fallbackbound:111,fals:[1,2,6,8,9,11,13,14,19,21,22,25,26,27,29,31,33,34,36,39,46,48,49,50,53,58,59,60,67,68,79,85,86,90,91,94,95,96,97,100,101,102,104,105,108,109,110,111,114,116,117,118,119],false_compon:112,far:[1,2,12],faster:[49,118],featur:[0,2,3,8,11,25,29,31,33,34,39,48,52,53,58,60,62,67,73,74,82,83,117,118],feature_agg_reg_ex:29,feature_agg_regex:25,feature_col_nam:33,feature_collector:117,feature_gener:[0,32,34,47,53,117],feature_generator_registri:[0,32,47,117],feature_generators_or_nam:34,feature_import:[0,25,31,47,58],feature_importance_dict:29,feature_nam:[1,33],feature_select:[0,31,47],featurecollector:[11,34,117],featuregen:[0,11,33,34,47,53,117],featuregener:[1,2,3,11,33,34,48,117],featuregeneratorfactori:[33,118],featuregeneratorflattencolumn:33,featuregeneratorfromcolumngener:33,featuregeneratorfromdft:33,featuregeneratorfromnamedtupl:[33,53],featuregeneratorfromvectormodel:33,featuregeneratormapcolumn:33,featuregeneratormapcolumndict:33,featuregeneratornamark:33,featuregeneratorneighbor:53,featuregeneratorregistri:34,featuregeneratortakecolumn:33,featuregeneratortargetdistribut:33,featureimport:[25,29],featureimportanceprovid:[29,31,58],featureimportanceprovidersklearnclassif:[48,58,59,119],featureimportanceprovidersklearnregressionmultidim:[58,60],featureimportanceprovidersklearnregressionmultipleonedim:[48,58,60,119],februari:80,fed:[1,2,29,117],feed:80,few:1,fgen:[11,33],field:[21,86,115],fig:[2,25,89,90,91,102],figsiz:[2,60,109],figur:[21,22,24,25,29,31,60,85,89,90,91,102,109],file:[1,25,39,46,50,60,89,90,91,94,95,102,104,110,112],file_extens:95,file_nam:110,fileextens:95,fileloggercontext:104,filenam:[25,89,90,91,94,102],filename_prefix:[94,102],filename_suffix:102,fill:[11,14],fill_cach:14,fill_valu:11,filter:11,filter_index:9,filter_indic:9,filterwarn:2,find:[37,43,97,111],find_first_transformer_by_typ:11,find_neighbor:53,find_rul:11,finder:53,first:[1,2,9,22,29,31,33,37,40,46,61,68,83,85,86,95,97,107,111,117],fit:[1,2,5,7,11,12,13,19,25,26,27,33,36,39,48,56,62,67,68,82,85,95,117,118],fit_appli:11,fit_end:106,fit_gener:33,fit_geo_coord:36,fit_input_output_data:[1,117],fit_intercept:60,fit_model:[1,2,25,26,62,117],fit_preprocessor:[62,117],fit_start:106,fitarg:[1,2],fitinputoutputdata:1,fittabl:117,fitting_mod:118,fittingmod:118,fix:[11,25,42,44,73,83,85,108],fix_polygon:44,flag:[11,49,67,95,108,112],flatten:33,flatten_argu:101,flattened_feature_gener:33,flatzinc:50,float_decim:113,float_valu:103,floor:[97,111],floor_index:[97,111],floor_key_and_valu:97,floor_valu:[97,111],flower:1,fly:67,fn:[69,94],focus:1,fold:[1,19,25,31],follow:[1,2,6,11,73,74,80,85],foo:[25,29,33,107],foo_0:33,foo_1:[25,29,33],foo_2:[25,29],for_activation_fn:[2,69],for_model:19,forc:91,forecast:80,forest:[1,119],form:[1,6,9,36,46,62,101,112,117,118],format:[104,112],forward:[2,11,67,74,77,80,83],found:[2,8,14,22,37,39,46,49,94,95,96,97],fowlkesmallowsscor:23,fraction:[9,25,26,68,73,85,86],fractional_size_of_first_set:[9,68,73,86],fractional_split_random_se:26,fractional_split_shuffl:26,fractional_split_test_fract:[2,26],fractionalsplittestfract:26,frame:[0,2,8,9,11,14,16,17,21,22,24,25,26,29,33,34,46,53,54,56,61,62,67,68,73,76,79,82,86,94,95,99,102,106,107,117],framework:1,frequenc:[21,22,58,59,61,93],frequent:1,from:[1,2,8,9,11,12,19,21,22,24,25,26,29,31,33,34,36,37,39,40,46,48,49,50,58,59,62,67,68,69,73,74,76,82,83,85,86,94,95,97,102,107,108,109,110,111,112,117,118],from_bool:97,from_circl:37,from_data_fram:[2,9],from_dict:85,from_dict_or_inst:[26,85],from_either_dict_or_inst:85,from_eval_stat:22,from_model:23,from_modul:[2,67],from_nam:[69,85],from_name_or_inst:85,from_optional_experi:91,from_probability_threshold:22,from_python:103,from_seri:97,from_unsorted_key_value_pair:97,from_valu:[103,118],fulfil:[5,39],full:[1,2,25,26,29,83,91,94,102,112],fulli:[0,2,80,109,112],func:[104,110],funcnam:104,function_nam:[94,112],functool:[2,95],fundament:[2,117],further:[1,2,6,11,22,24,29,33,44,80,94],furthermor:[33,91],futur:[21,83],future_time_range_dai:53,fzn_output_path:50,g:[1,5,11,19,21,22,25,26,29,33,34,46,49,56,62,67,74,80,89,90,91,94,95,97,104,107,109,112,117,118],gain:48,gate:83,gather_result:[1,2],gb:95,gener:[0,2,3,5,8,9,11,14,19,21,22,24,25,26,27,29,31,33,34,36,39,45,46,48,49,53,58,59,60,62,67,68,82,83,86,90,91,94,95,97,103,108,112,117,118],generate_column:8,generated_column_nam:8,geo:44,geo_clust:[0,35,47],geo_coord:[0,35,36,45,47],geoanalyt:[0,36,37,39,40,43,45,47],geocoord:[36,37],geocoordcluster:36,geodatafram:[39,40,41,42,43],geodataframewrapp:[39,40,41,43],geograph:[37,44,45],geomeantrueclassprob:[1,22],geometri:[0,35,38,39,40,41,44,47],geopanda:[0,35,39,40,41,42,43,47],georect:[37,45],geospati:[39,43],get:[1,6,14,21,22,24,29,33,34,36,37,44,46,49,58,68,69,73,85,94,95,96,104,117,118],get_accuraci:22,get_added_column:107,get_aggregated_feature_import:29,get_aggregated_feature_importance_dict:29,get_al:21,get_all_cach:14,get_available_vectoris:118,get_best_model:25,get_best_model_nam:25,get_best_param:46,get_binary_classification_probability_threshold_variation_data:22,get_cached_metr:53,get_categorical_feature_name_regex:[33,34],get_chain:49,get_class_label:117,get_clust:[5,39],get_cluster_associ:6,get_color:109,get_combined_eval_stat:[21,22,24],get_config:2,get_confusion_matrix:22,get_coordinates_label:40,get_data_fram:[26,29,46],get_data_splitt:26,get_denormalised_arrai:54,get_dict:97,get_distance_seri:53,get_distribut:93,get_distribution_summari:23,get_elapsed_time_sec:104,get_elapsed_time_str:104,get_elapsed_timedelta:104,get_enabled_plot:[1,25],get_encoder_dim:74,get_ent:95,get_epoch_train_loss:85,get_eval_stat:[1,26],get_eval_stats_collect:[1,19,25,26],get_eval_stats_list:25,get_f1:22,get_feature_gener:[34,117],get_feature_import:[25,29],get_feature_importance_dict:[29,58],get_feature_transform:117,get_feature_transformer_chain:117,get_file_cont:102,get_first_dupl:111,get_generated_column_nam:33,get_global_stat:21,get_hexagon:44,get_hexagon_coord_span_for_bounding_box:44,get_hexagon_coords_for_point:44,get_identifi:118,get_input_dim:68,get_input_output_pair:73,get_input_tensor_scal:[68,73],get_input_transform:117,get_input_transformer_chain:117,get_inst:104,get_invers:11,get_js_cod:103,get_last_solver_time_sec:50,get_lat_lon:44,get_latent_dim:83,get_local_coord:44,get_max_hexagon_column:44,get_max_hexagon_row:44,get_memory_log:104,get_metr:21,get_metric_by_nam:21,get_metric_nam:21,get_metric_values_arrai:31,get_min_hexagon_column:44,get_min_hexagon_row:44,get_mini_zinc_cod:50,get_misclassified_indic:22,get_misclassified_inputs_data_fram:26,get_misclassified_triples_pred_true_input:[2,26],get_model_descript:25,get_model_input_shap:62,get_model_input_variable_nam:117,get_model_nam:25,get_model_output_dim:68,get_model_output_shap:62,get_model_output_variable_nam:117,get_module_byt:67,get_multi_feature_gener:34,get_nam:[11,33,69,117,118],get_normalisation_rul:[11,33,34],get_normalised_arrai:54,get_num_features_arrai:31,get_num_predicted_class:62,get_output_dim_weight:85,get_output_tensor_scal:[68,73],get_output_transformer_chain:117,get_paired_metr:[21,22],get_param:[58,97],get_precis:22,get_predicted_variable_nam:117,get_raw_input_transform:117,get_raw_input_transformer_chain:117,get_recal:22,get_rel_freq_posit:22,get_relative_frequ:93,get_removed_column:107,get_selected_featur:31,get_seri:49,get_simulated_ann:46,get_sklearn_model:58,get_sorted_step:31,get_sorted_tupl:29,get_state_represent:[46,49],get_target_transform:117,get_til:45,get_tile_coordin:45,get_tiles_in_rect:45,get_torch_funct:[2,69],get_torch_modul:67,get_training_criterion:85,get_training_loss_seri:85,get_validation_metr:85,get_validation_metric_kei:85,get_validation_metric_nam:85,get_validation_metric_seri:85,get_valu:[1,21],get_value_from_refer:95,get_value_refer:95,get_vector_dim:118,get_vectoris:118,get_weighted_mean:93,getcombinedevalstat:21,getepochtrainloss:85,getfeatureimport:29,getnam:34,getpredictedvariablenam:117,getseri:49,getstat:108,getstaterepresent:[46,49],getvalidationmetr:85,gini:[1,2],give:117,given:[1,2,6,8,9,11,14,19,22,25,26,29,31,33,34,36,37,43,44,46,48,49,50,53,61,62,67,68,69,83,85,86,91,93,94,97,100,101,102,104,108,109,110,111,112,113,114,116,117,118],glue:112,goe:49,good:[11,29,112],gooey:42,gps_posit:37,gpstracepoint:37,gpu:[2,76,85],gpu_allow_growth:64,gpu_per_process_memory_fract:64,gradient:[59,60,85,119],graph:[0,35,38,47],greater:[97,111],greedi:6,greedili:[46,49],greedy_clust:[0,4,36,47],greedyagglomerativeclust:[6,36],greedyagglomerativegeocoordcluster:36,green:[24,109],greyscal:2,grid:[44,46],gridsearch:46,gridsearch_:46,ground:[1,21,22,23,26,40,56,61,62,68,85,117],ground_truth:85,ground_truth_polygon:40,ground_truth_shap:85,groundtruth:26,group:[9,25,29,74],gru:[74,83],gt:[1,2],guess:[22,26],ha:[8,11,26,33,34,40,46,49,53,56,62,64,67,68,74,80,86,91,94,97,104,107,109,117,118],had:[2,6],half:[44,49],hand:[1,2,117],handl:[1,2,33,39,50,67,83,94,108,112],handle_upd:94,handler:[67,104],happen:94,hard:2,has_finite_bound:21,has_metr:21,hash:[0,47,92,94],hashabl:[34,93,94,111,118],hashlib:100,have:[1,2,3,6,8,9,11,21,25,29,31,33,34,46,48,49,56,61,62,67,73,83,91,93,94,95,97,102,107,109,111,112,117,118],he:80,head:[1,2],header:102,heat:[25,109],heatmap:24,heatmap_colormap_factori:24,heatmap_diagonal_color:24,heatmap_error_boundary_color:24,heatmap_error_boundary_valu:24,heatmapplot:109,height:107,held:26,hellingerdistancemetr:14,help:29,helper:[0,47,92,108],henc:[91,117],here:[1,2,26,33,42,49,101],heurist:117,hex:[44,100],hexagon:44,hid_activation_fn:[2,77,83],hid_activation_funct:[2,76],hid_rnn:[73,74,83],hid_skip:[73,74,83],hidactivationfunct:2,hidc:[73,74],hidden:[59,60,73,74,76,80,83],hidden_activ:65,hidden_dim:[2,65,76,77,79,80,83],hidden_layer_s:[59,60],hiddendim:2,hidrnn:74,hidskip:74,hierarchi:112,high:[2,117],higher:[25,46],higher_is_bett:46,highest_kei:97,highli:[1,82],highlight:48,highwai:[73,74],hint:7,histogram:[21,25],histogramplot:[24,109],histori:[82,83,107,118],history_featur:83,history_sequence_column_nam:82,history_sequence_variable_length:82,history_sequence_vector:82,history_sequence_vectoris:82,histplot:[21,109],hitherto:[46,49],hold:[1,2,9,11,24,25,46,85,94,97,112,117],holder:27,host:96,hot:[3,11,13,33,34,48,56,62],houseec:80,household:80,how:[1,6,24,49,83,94,117,118],howev:25,html:[3,9,21,29,33,36,48,59,60,110,119],http:[3,9,21,29,33,36,44,48,59,60,80,95,119],hw_combin:[73,74],hw_window:[73,74],hwwindow:74,hyper:46,hyper_param_valu:46,hyperopt:[0,47],hyperparamet:[2,19,26],i1:33,i2:33,i:[2,6,9,11,14,22,29,31,33,44,46,49,56,60,61,62,67,68,73,74,85,86,90,91,94,95,97,102,104,109,111,112,116,117,118],id:[1,2,34,112,118],idea:[11,29],ident:[2,59,60,80,118],identifi:[5,14,39,40,53,90,101,118],identitydistancemetr:14,idiosynchrasi:1,idx:[1,6,36,97],iff:[46,114],ignor:[2,6,11,13,22,25,36,83,112,117],ignore_unknown:[11,13,34],iloc:2,imag:[0,80,107],image_dim:2,imagereshapinginputtensoris:2,immedi:104,immut:49,implement:[1,2,6,11,29,31,33,34,42,58,59,67,85,108,112],importance_typ:48,improv:[2,59,60,80,85,117],imshow:[2,24,109],in_memori:[95,96],inadmiss:[6,36,46],includ:[1,2,5,21,25,27,39,53,85,89,90,91,97,102,108,111,112,113,117],include_generated_categorical_rul:[33,34],include_nois:[39,40],inclus:112,increment:[46,93],incremental_skip_exist:46,inde:2,indent:[58,112],indentation_str:112,independ:[8,11,29,31,33,34,58,73,74],independent_column:11,index:[0,6,8,14,21,33,36,37,39,40,53,58,59,62,85,95,97,102,107,111,115,117],index_el:9,indexcachedcolumngener:8,indic:[6,9,11,13,14,19,22,24,33,36,37,44,46,49,53,67,73,83,94,95,96,98,111],indices_pair:9,indirect:2,individu:[13,25,39,51,85,117,118],inf:[6,33,36],infer:[0,3,11,48,67,109,117],infer_mc_dropout:67,inference_batch_s:67,inferior:46,infermcdropout:67,infinit:112,inflect:49,influenc:42,info:[1,2,11,33,50,108,110,112],inform:[1,2,5,24,33,34,43,46,85,90,91,94,117],inherit:[1,2,94],init:[51,117],init_hidden:83,initi:[6,29,36,46,49,83,85,97,107,112],initial_compon:112,initial_df:107,initial_indentation_level:112,initial_paramet:46,initialis:[2,6,36,108],initialparamet:46,inject:83,inmemorykeyvaluecach:94,inner:[2,97],inplac:[11,34],input:[0,1,3,8,9,11,13,25,26,29,31,33,48,56,58,60,61,62,64,67,68,73,74,76,79,80,82,83,85,86,112,117,118],input_col_nam:33,input_data:26,input_df:[67,68],input_dim:[2,9,67,68,73,76,77,79,80,83,86],input_dim_per_time_slic:[73,74],input_feature_gener:33,input_onli:[68,86],input_tensor_scal:68,input_tensoris:[67,68],input_transform:117,input_valu:14,inputdim:2,inputdimpertimeslic:[73,74],inputfield:86,inputonli:[68,86],inputoutputarrai:9,inputoutputdata:[1,2,9,19,24,25,26,29,31,61,70,117],inputoutputdatadict:25,inputtensoris:[2,82],inputtensorshap:62,insert:95,insert_data_frame_to_t:95,insert_ent:95,insert_or_replace_ent:95,insignificantli:2,inspect:[1,2],inspir:80,instanc:[0,1,9,11,12,19,22,25,26,27,33,34,39,40,43,46,49,67,69,76,79,83,85,86,89,90,91,94,95,97,102,103,104,108,112,117,118],instanti:[1,2,7,25,33,39,67,94],instead:[1,11,13,21,25,29,33,34,46,62,94,111,112,117],instruct:1,int64:2,int_valu:103,integ:[1,2,44,50,62,94,109,118],integr:[0,25],intercept:60,interest:1,interfac:[1,11,29,67,68,83,85,101,117],interfer:94,intermedi:[1,11,83],intermediatefittingstep:106,intern:[6,34,80,85,94,112],interpol:97,interpolated_valu:97,interpret:[73,107,112],intersect:[44,114],interv:[2,33,49,61,114],intervalindex:33,introduc:112,introduct:0,invalid:[44,94,108],invalidshapeerror:62,invers:[11,53,68,117],inverse_transform:12,inversedataframetransform:11,invert:117,invertible_dft:11,invertibledataframetransform:[11,117],invok:117,involv:[2,67],inward:42,io:[0,25,47,48,92,119],io_data:[9,24,25,26,29,31,61,70,117],io_data_dict:25,ioff:80,iri:1,iris_combined_df:1,iris_data:1,iris_input_df:1,iris_io_data:1,iris_output_df:1,is_applic:9,is_at_least:116,is_being_fit:117,is_categor:[8,33],is_categorical_featur:33,is_empti:95,is_en:91,is_fals:97,is_fit:[5,11,33,117,118],is_log_handler_act:104,is_merg:6,is_positive_ground_truth:22,is_positive_predict:22,is_regress:25,is_regression_model:[16,62,117],is_relevant_ev:93,is_run:104,is_s3_path:102,is_skip:46,is_tru:97,is_undefin:103,is_xgboost_version_at_least:119,isn:[1,91],issu:98,item:[9,29,34,68,80,82,83,94,118],itemidentifierprovid:118,iter:[5,6,25,36,37,39,42,53,59,60,67,68,86,94,108,112,118],iter_batch:[68,86],iter_candidate_indic:[6,36],iter_data_frame_chunk:95,iter_evaluation_data:25,iter_input_output_ground_truth_tupl:[19,26],iter_item:94,iter_model_result:25,iter_param_combin:46,iter_potential_neighbor:53,iter_record:95,iter_tile_coordinates_in_rect:45,iterrow:2,its:[1,2,11,46,49,53,61,83,94,97,104,105,109,112],itself:[1,6,25,62,95,101,117],j:[109,111],januari:80,javascript:103,jian:80,job:29,joblib:[29,94],join:[6,36,112],jointli:[1,33,67],jpg:102,js_arg_list:103,js_code:103,js_valu:103,jsclassinst:103,jscode:[0,47,92],jscodeliter:103,jslist:103,jsobject:103,json:[95,103,113],json_mapp:113,jsonargpars:104,jsonazuretableblobbackend:95,jsvalu:103,jsvalueliter:103,juli:80,just:[6,24,25,36,62,67,90],justa:1,k:[2,58,59,60,73,74,105],kaim:80,kde:[1,21,109],keep:[9,11,50,53,107,118],keep_alpha:109,keep_other_column:33,keep_temp_fil:50,kei:[1,2,8,14,25,26,29,34,46,53,85,86,93,94,95,96,97,101,103,111,112],kera:64,kerasmultilayerperceptronvectorregressionmodel:65,kerasvectorregressionmodel:[64,65],kernel:[2,21,74,109],kernel_s:2,key_for_index:97,key_nam:25,key_typ:94,key_valu:111,key_value_cach:14,keyerror:97,keytyp:94,keyvalu:111,keyvaluecach:[8,14,33,53,94],keyword:[46,61,85],kind:90,kiprijanovska:80,knearestneighboursclassificationmodel:53,knearestneighboursfind:53,knearestneighboursregressionmodel:53,knn:53,know:[25,117],known:[34,51,68,80,86,117],kwarg:[7,12,21,24,26,27,36,39,40,41,53,61,65,67,74,77,80,83,86,109],kwd:[7,9,12,21,22,24,27,83,94,97,118],l1:60,l1loss:85,l2:60,l2loss:85,l:[59,60,80,85,112,118],label:[2,5,7,11,21,22,23,25,26,27,33,39,40,56,58,59,62,109,117],labels_:7,labels_with_removed_common_nois:23,lai:74,lambda:[67,79],larg:[1,31,67,94],larger:[6,34,40,42,49,56,62,109],largest:[58,59,95,97,111],lasso:60,last:[33,74,80,97,107,117],lat:[37,44,45],late:[2,97],latent:[74,82,83],latent_dim:[82,83],latent_pass_on_mod:83,latentpassonmod:83,later:[1,11,33,46,49,104],latest:[48,94,119],latitud:[37,44],latitude_per_m:37,latlon:37,latter:[49,74,101,118],layer:[2,59,60,74,76,80,83],lazi:95,lazybatchcommitt:95,lbfg:[59,60,85],lc:[36,37],lead:[26,68,86,102],leaf:[1,48],learn:[0,2,9,11,29,31,33,36,58,59,60,67,80,85,117],learner:48,learnt:[2,12],least:[1,22,31,49,50,60,94,109,114,116],leav:[3,33,48,85,109],left:25,leftmost:[97,111],len:111,length:[1,2,11,13,22,39,43,62,67,68,82,83,94,95,107,118],less:[31,95,97,111],let:[1,2],level:[0,2,9,25,31,33,50,104,108,110,112,113,117],levelnam:104,leverag:33,lgbmclassifi:48,lgbmregressor:48,librari:[1,104],lighten:109,lightgbm:[0,1,29,47],lightgbmvectorclassificationmodel:48,lightgbmvectorregressionmodel:48,lightningmodul:56,like:[1,11,22,31,33,39,62,67,104,108,113,117],limit:[1,21,22,33,48,50,104,112],line:[1,24,37,46,58,67,102,109,112],linear:[49,53,60,83,109],linear_model:60,linearcolormap:109,linearcombinationdistancemetr:[14,53],linearli:[49,97],linearpredictorfactori:83,linearregress:60,linspac:1,list:[1,2,3,6,9,11,14,16,17,19,21,22,23,24,25,26,28,29,31,33,36,37,45,46,49,50,53,58,59,62,67,68,73,80,82,85,94,95,101,102,104,108,109,111,112,117,118],list_str:112,liter:112,load:[1,2,39,94,95],load_ext:[1,2],load_iri:1,load_pickl:108,load_property_valu:95,load_property_value_to_data_frame_column:95,load_table_to_data_fram:95,loader:95,loadsaveinterfac:[39,94],local:[36,44,67,79,90],local_coord:[0,35,36,37,47],local_i:44,local_search:[0,46,47],local_x:44,localcoordinatesystem:[36,44],localhexagonalgrid:44,localpoint:36,locat:1,log:[0,2,25,33,46,47,49,50,85,88,89,90,91,92,94,108,110,112,118],log_cost_progress:49,log_failure_if_en:108,log_info:50,log_prob:[2,69],log_result:25,log_softmax:[2,69,73,76],log_stat:49,log_to_fil:110,logger:104,logic:11,logist:[49,59,60],logtim:104,lon:[37,44,45],longer:[1,108],longitud:[37,44],longitude_per_m:37,look:[2,33,117],lookup:[14,94,95,96,111],loop:94,lose:1,loss:[2,64,65,67,74,85,117],loss_evalu:[2,85],loss_fn:85,lossevalu:85,lossfn:85,lossfunct:[2,85],lot:1,low:[0,2,117],lower:[46,61,111],lower_bound_kei:[97,111],lowerboundkei:111,lowest:[6,31,111],lowest_kei:97,lstm:83,lstnet:[0,47,66,71,74,83],lstnet_model:[0,47,66,71,72],lstnet_modul:[0,47,66,71,72,83],lstnetwork:[73,74,83],lstnetworkencod:83,lstnetworkencoderfactori:83,lstnetworkvectorclassificationmodel:73,lt:[1,2],luckili:2,machin:1,made:[74,82,83,112,117],mae:24,mai:[1,3,6,11,19,21,22,25,26,29,33,36,37,46,48,49,58,59,61,67,68,82,83,85,86,94,95,102,108,112,117,118],main:[8,101,104],main_fn:104,mainli:2,maintain:[9,34,50],major:[73,74,109,116,119],make:[1,11,33,37,46,49,67,68,74,82,83,94,112,117],manag:[6,49,90,91,95,104],mani:[1,2,24,26,29,74,94,112],manipul:68,manner:[94,95],manual:12,manualscal:12,map:[11,12,21,22,23,24,25,26,29,36,43,46,49,58,64,80,83,86,93,101,108,109,112,113,118],map_til:[0,35,47],maptil:45,march:80,mark:[98,101],mark_us:101,markedli:31,marker:112,match:[11,25,29,33,34,48,68,74,94,95,111,117],matching_column:11,math:[0,6,36,37,47,92],mathemat:[1,117],matplotlib:[2,21,22,24,25,29,31,60,85,89,90,91,102,109],matric:[14,73,74],matrix:[1,36,73,74,109],max:[1,2,12,25,83],max_al:[2,54],max_angle_differ:37,max_batch_s:95,max_by_column:[54,65],max_cluster_s:[5,7,39],max_depth:[1,2,48],max_distance_m:36,max_featur:[1,2],max_i:44,max_it:[59,60],max_key_length:94,max_lat:37,max_leaf_nod:[1,2],max_lon:37,max_min_distance_for_merge_m:36,max_opac:109,max_row:44,max_sampl:[1,2],max_seq_length:83,max_siz:[23,61],max_step:[46,49],max_target_seq_length:83,max_valu:[105,109],max_work:95,max_x:44,maxabsscal:12,maxanglediffer:37,maxareadiff:44,maxclusters:23,maxcol:44,maxim:95,maximis:[31,46],maximum:[2,3,6,21,22,36,37,44,48,61,68,85,86,94,105,113,118],maxpool2d:2,maxstep:49,mayb:97,mc:67,mc_dropout_prob:67,mc_dropout_sampl:67,mcdropoutcapablennmodul:[67,74,77],mean:[1,21,24,29,36,40,42,46,48,49,60,61,67,83,85,93,105,117],mean_coord:37,mean_edge_weight:43,mean_metrics_dict:21,mean_results_df:25,mean_stat:21,meansizeci:61,meant:117,meantim:94,measur:1,mechan:[1,19,25,67,80,94,95,112,118],median:[12,61],median_s:23,mediana:24,medianclusters:23,mediansizeci:61,member:[14,24,46,109,112],member_names_or_dict:112,memori:[67,83,90,94,95,104],mercat:[39,43],mere:95,merg:[6,36],merge_candidate_determination_strategi:6,merge_cost:[6,36],mergecandidatedeterminationstrategi:[6,36],mergecandidatedeterminationstrategydefault:6,merged_cluster_indic:[6,36],messag:[98,104,108,112,118],meta:[1,33,34,67,85,117],meta_data_dict:25,meth:85,method:[1,2,6,23,25,26,29,31,33,39,43,48,67,68,85,91,95,104,108,112,117,118],metr:[36,37,44],metric:[1,2,14,19,21,22,23,24,25,26,27,28,31,46,53,61,64,65,85,88,91],metric_comput:[0,18,31,47],metric_nam:[21,25,31,46],metric_name_i:21,metric_name_x:21,metric_to_optimis:46,metric_valu:[28,31,46],metriccomput:[28,31],metriccomputationmultidata:28,metriccomputationresult:28,metrics_dict:[1,21,22,23],metrics_evalu:46,metricsdict:21,metricsdictprovid:[19,26,27,46,88],metricsdictproviderfromfunct:26,microsoft:95,mid_degre:49,mid_timestamp:114,might:[1,2],min:[1,12,25,59,60],min_child_sampl:48,min_cluster_s:[5,7,36,39],min_featur:31,min_i:44,min_impurity_decreas:[1,2],min_impurity_split:[1,2],min_lat:37,min_length:95,min_lon:37,min_opac:109,min_row:44,min_sampl:36,min_samples_leaf:[1,2,59,60],min_samples_split:[1,2],min_siz:23,min_size_for_periodic_commit:95,min_valu:[105,109],min_weight_fraction_leaf:[1,2],min_x:44,minclusters:23,mincol:44,minfeatur:31,minim:95,minimis:[31,46,49],minimise_metr:46,minims:31,minimum:[1,6,21,22,36,44,48,61,104],minimum_spanning_tre:43,minizinc:[0,47],minizincproblem:50,minizincsolv:50,minlength:95,minmaxscal:12,minor:[109,116,119],misclassifi:[2,26],miss:[1,33],mlflow_track:[0,47,87],mlflowexperi:90,mlflowtrackingcontext:90,mlp:[0,2,47,66,71],mlp_hidden_dim:2,mlp_model:[0,47,66,71,75],mlp_modul:[0,47,66,71,75],mlpclassifi:59,mlppredictorfactori:83,mlpregressor:60,mnist:2,mnist_df:2,mnist_train:2,mnistcnnmodul:2,mnistiodata:2,mode:[2,46,67,68,74,76,79,83,102,112,118],model:[0,3,11,15,16,19,21,22,24,25,26,27,28,29,31,33,34,39,46,47,48,51,53,56,58,59,60,61,62,64,67,68,73,74,80,82,83,85,88,90,91,95,109,117,119],model_arg:[3,48,58,59,60,119],model_byt:67,model_constructor:[58,59,60],model_evalu:29,model_factori:[25,28,31,46],model_input:67,model_nam:[1,2,19,25,26],model_name_to_string_repr:25,model_output:[67,85],model_output_dim:[68,73,86],model_save_directori:46,model_select:9,modelcomparisondata:[2,25],modelcomparisonvisitor:25,modelcomparisonvisitoraggregatedfeatureimport:25,modelconstructor:2,modelevalu:25,modifi:[6,11,107,108,109],modul:[1,9,25,29,36,40,59,60,62,67,76,79,80,82,83,85,101,104,117],module_factori:67,more:[1,2,11,22,33,49,58,67,68,74,80,82,91,94,112,117,118],moreov:[101,107],most:[1,11,22,29,33,34,49],mostli:83,move:[25,49,68],mse:[24,65],mseloss:85,much:42,multi:[2,21,34,46,58,67,74,83,85,117],multi_lat:83,multi_line_str:43,multi_model:[0,47],multi_output:83,multidatamodelcomparisondata:25,multidatamodelevalu:[25,28],multifeaturegener:[11,33,34,117],multilayerperceptron:[2,77],multilayerperceptrontorchmodel:[2,76],multilayerperceptronvectorclassificationmodel:[2,76],multilayerperceptronvectorregressionmodel:76,multilinestr:43,multipl:[1,2,11,24,29,33,34,53,56,58,60,62,83,85,109,117,118],multipli:[49,60],multipoint:[39,40,41,42],multipolygon:44,multiprocess:[0,47,92],multivectorregressionmodel:51,must:[1,6,9,11,22,25,26,29,33,34,36,49,67,68,73,74,82,93,94,95,112,116,118],mutat:6,mutual:93,mycach:94,mysqlpersistentkeyvaluecach:96,mzn_path:50,mzv:50,n:[1,2,11,22,31,33,53,61,67,73,80,85],n_column:107,n_estim:[1,2,48,59,60],n_imag:107,n_inputcolumn:62,n_iter_no_chang:[59,60],n_job:[1,2],n_max_transpar:109,n_min_transpar:109,n_neighbor:53,n_outputcolumn:62,n_row:[62,107],na:11,naiv:52,naive_bay:[0,47],name1:112,name:[1,2,3,8,9,11,19,21,22,23,24,25,26,29,33,34,46,48,49,50,53,58,59,60,61,69,73,76,82,85,86,88,89,90,91,94,95,97,100,104,108,109,110,112,117,118],name_or_inst:85,named_tupl:53,named_tuple_a:14,named_tuple_b:14,namen:112,nan:[11,33,101],natur:[1,2,67],ncol:2,ndarrai:[5,7,9,11,12,13,21,22,23,24,31,36,39,40,41,42,43,54,56,61,67,68,85,95,99,109,118],nearest:53,nearest_neighbor:[0,47],necessari:[1,2,11,67,85,89,117],necessarili:[46,49,117],necessit:[2,53,104],need:[1,2,3,11,25,46,48,49,67,83,85,94,95,104],neg:[6,36,49],negativeloglikelihood:85,neighbor:53,neighbor_attribut:53,neighbor_provid:53,neighbor_provider_factori:53,neighborprovid:53,neighbourhood:36,neither:11,nest:[19,21,112,113],network:[0,67,68,74,80,83],networkx:43,networx:43,neural:[0,67,68],neural_network:[59,60],neuron:76,never:[3,22,33,85],new_default_properti:108,new_optional_properti:108,newli:[85,94],newlin:102,nll:[2,85],nn:[0,67,69,76,79,80,82,83,85],nn_optimis:67,nn_optimiser_dict_param:85,nn_optimiser_param:[2,67,73,76,79,82,85],nnlossevalu:[2,85],nnlossevaluatorclassif:[2,85],nnlossevaluatorfixeddim:85,nnlossevaluatorregress:85,nnoptimis:[2,67,73,76,79,85],nnoptimiserdictparam:76,nnoptimiserparam:[2,67,73,76,79,82,85],no_lat:83,no_update_fn:94,no_update_time_period_sec:94,nois:[5,7,23,27,39,40],noise_clust:[5,39],noise_label:[5,7,23,27,39,40],noise_s:23,noiseclusters:23,noiselabelsmask:23,nomin:93,non:[6,22,25,26,36,40,49,56,62,67,80,94,95,112,117],none:[1,2,3,5,6,7,8,11,12,14,17,19,21,22,23,24,25,26,28,29,31,33,34,36,37,39,40,44,45,46,48,49,50,53,54,58,59,60,61,64,67,68,69,70,73,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,101,102,103,104,107,108,109,110,111,112,117,118,119],nonlinear:80,nor:11,norm:85,norm_max:109,norm_min:109,normal:[1,22,25,42,80,109,117],normaldistribut:105,normalis:[0,1,2,11,22,33,34,47,49,58,64,67,68,76,79,80,85,109,118],normalisation_mod:[2,54,64,65,67,68,76,79],normalisation_rul:[11,33,53],normalisation_rule_templ:[8,11,33],normalisationmod:[2,54,64,65,67,68,76,79],normalisationrul:33,normalize_plot:25,north:44,note:[1,2,11,22,25,31,33,46,49,58,59,67,82,85,97,112,117,118],notebook:1,noth:[80,93,101],notic:2,notifi:94,notion:46,noupdatefn:94,noupdatetimeperiodsec:94,now:[1,2,62],np:[1,2],nrow:2,num_chain:49,num_class:[68,73],num_clust:[5,23],num_cnn_time_slic:[73,74,83],num_conv:2,num_convolut:[73,74,83],num_edg:43,num_entries_per_slic:94,num_fold:19,num_input_time_slic:[73,74,83],num_job:29,num_leav:[3,48],num_memb:5,num_neighbor:53,num_output_time_slic:74,num_process:[16,17,46],num_record:95,num_repeat:29,num_sampl:67,num_split:19,num_unfilled_entri:14,number:[1,2,3,11,13,19,21,29,31,33,36,42,46,48,49,50,53,59,60,67,68,73,74,76,79,80,82,83,85,86,94,95,101,107,109,113,114,115,116,118],numchain:49,numclass:74,numclust:23,numcnntimeslic:74,numconvolut:74,numer:[1,2,11,34,49,117,118],numfold:19,numinputtimeslic:74,numlabel:[56,62],numoutputtimeslic:74,numpi:[1,2,5,7,9,11,12,13,21,22,23,24,31,36,39,40,41,42,43,50,54,56,61,67,68,85,95,99,107,109,113,118],numpy_arrai:118,numpyarrayjsonserialis:95,numrecord:95,nvidia:2,o:[2,68,86,100,113],obj:[102,108,112,113],object:[1,2,5,6,7,8,11,12,13,19,21,22,24,25,26,28,29,31,33,34,36,37,39,43,44,45,46,49,50,53,54,56,64,67,68,83,85,88,90,91,93,94,95,97,100,102,103,104,106,107,108,109,112,113,114,116,117,118],object_repr:112,observ:[1,46,49,117],obtain:[1,2,11,19,24,25,26,29,34,46,49,67,85,86,94,117,118],occur:[93,104],occurr:[22,107],odd:[44,112],off:25,often:[1,11],oftentim:1,old:[11,94,108],on_training_data:26,onc:[31,67,97,112,114,118],one:[1,2,3,9,11,13,21,22,24,25,26,27,29,31,33,34,36,37,39,44,46,48,49,56,58,59,60,61,62,67,68,73,74,82,83,85,91,94,97,101,102,104,107,117,118],ones:[22,62,112],ongo:[1,117],onli:[1,2,5,6,7,8,9,11,14,19,21,22,25,26,31,33,34,39,40,44,46,49,60,61,62,67,68,80,82,83,85,86,89,93,94,95,97,102,104,107,112,115,117],oob_scor:[1,2],opac:109,opaqu:109,open:[50,112],open_connect:94,open_fil:102,oper:[1,6,11,46,49,97],ops_and_weight:[46,49],opt:2,opt_dist:37,opt_point:37,opt_segment_start_idx:37,optim:[34,85],optimis:[2,11,19,26,31,46,49,64,65,67,82,85],optimiser_arg:[2,85],optimiser_clip:85,optimiser_lr:[2,85],optimiserclip:85,optimiserlr:85,optims:[46,49],option:[2,3,5,6,7,8,11,12,17,19,21,22,23,24,25,26,29,33,34,36,39,40,46,48,49,53,58,59,60,61,62,67,68,69,70,73,74,76,77,79,80,82,83,85,86,88,89,91,93,94,95,97,102,104,108,109,110,111,112,117,118,119],or_regex_group:112,order:[1,2,9,11,19,22,25,26,29,31,33,46,49,52,53,67,74,85,94,95,104,116,117,118],ordereddict:85,org:[9,21,29,33,36,59,60,80],orient:37,origin:[1,3,6,9,11,29,33,44,48,50,58,59,67,80,83,85,109,117,118],original_input:117,original_output:117,original_valu:50,os:50,osicbc:50,other:[2,6,9,11,21,22,25,33,36,49,59,60,68,73,74,102,107,112,114],otherwis:[11,25,94,101,108,112,114,116,117,118],our:[1,2,80],out:[1,26,68,73],outcom:31,outer:[2,111],outlier:36,output:[0,1,8,9,11,19,23,25,26,33,50,51,53,56,58,59,60,62,64,67,68,73,74,76,79,80,83,85,86,104,107,110,117,118],output_activ:[65,73,74],output_activation_fn:[2,77,83],output_activation_funct:[2,76],output_column:9,output_data_frame_transform:26,output_df:68,output_dim:[2,9,67,68,76,77,79,80,83],output_dim_per_time_slic:74,output_dim_weight:85,output_mod:[67,83,85],output_tensor_scal:68,output_tensor_to_array_convert:67,output_tensoris:[67,68],output_transform:[58,117],outputactivationfunct:2,outputdim:2,outputdimpertimeslic:74,outputfield:86,outputfil:102,outputmod:[2,83],outputtensoris:2,outputtensorshap:62,outputtensortoarrayconvert:67,over:[2,29,33,40,46,68,86,94],overal:[25,85,101],overfit:52,overlap:118,overlaps_with:114,overli:104,overrid:[67,68,112,117],overridden:112,override_properti:108,overrideinputdim:2,overwrit:46,own:[1,67],p0:[46,49],p1:[37,46,49],p2:37,p:[2,33,49,67],p_dropout:[2,76,77,79,80,83],p_recurrent_dropout:83,packag:[104,116],pad:[67,118],page:0,pair:[6,8,14,21,22,25,26,36,37,44,46,67,68,86,97,118],panda:[0,1,2,5,8,9,11,14,16,17,21,22,24,25,26,29,33,37,46,47,53,54,61,62,64,67,68,73,82,85,86,92,95,97,99,102,104,106,113,114,117],pandasnamedtupl:[14,19,26,53,115],parallel:[29,46,49,73,74],parallel_backend:29,parallelis:29,paralleltemp:49,param:[1,2,6,19,21,25,26,36,44,46,49,58,68,85,91,94,95,109,110],param_nam:46,paramet:[1,2,3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,29,31,33,34,36,37,39,40,42,43,44,46,48,49,50,51,52,53,56,58,59,60,61,62,64,65,67,68,69,73,74,76,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,98,100,101,102,103,104,105,107,108,109,110,111,112,113,114,116,117,118,119],parameter_combination_equivalence_class_value_cach:46,parameter_combination_skip_decid:46,parameter_opt:46,parameterchangeoper:46,parametercombinationequivalenceclassvaluecach:46,parametercombinationskipdecid:46,parametersmetricscollect:46,parametr:46,parametris:94,params_dict:49,paraqm:91,parent:[2,36,82,108],pars:104,part:[1,8,74,112,118],partial:[2,95],particular:[1,11,19,34,46,112,113,118],particularli:[1,2,53,58,59,112],partit:95,partition_kei:95,partition_key_gener:95,partitioncommand:95,partitioncommandspriorityqueu:95,partitioncommandsqueu:95,partitionkei:95,partli:118,partner:[6,36],pass:[1,2,3,11,19,21,24,25,26,34,36,39,46,48,53,58,59,60,61,62,67,83,85,90,91,93,94,101,104,107,109,112,117,118],past_time_range_dai:53,patch:[2,116,119],path:[1,2,39,40,46,50,60,73,74,80,94,102,104,108,109],pathlib:[94,108],pattern:11,paus:104,pcc:24,pd:[1,2,8,11,33,107,109],pdf:[60,105],pdropout:2,pearson:24,pend:[94,95],per:[11,21,25,26,33,39,46,73,74,80,83,85,95,118],percent:21,percentil:12,perceptron:[2,83],perform:[1,2,9,11,31,34,62,67,85,91,104,107,111,117,118],perform_cross_valid:[1,25],perform_simple_evalu:[1,2,25],perhap:117,period:[94,95],periodic_fn:94,periodically_executed_fn:94,periodicupdatehook:94,permut:29,persist:[8,14,46,67,94],persist_cach:[8,14,94],persistcach:94,persistentkeyvaluecach:[14,94,95,96],persistentlist:94,pertain:73,petal:1,phase:[33,117],pi:37,pickl:[0,8,47,67,92,94,95],picklabl:[67,79,94,100],pickle_base_nam:94,pickle_cach:94,pickle_hash:100,pickle_path:[14,94,108],pickleazuretableblobbackend:95,picklebasenam:94,picklecach:94,picklefailuredebugg:108,pickleloadsavemixin:[5,94,117],picklepersistentkeyvaluecach:94,piec:1,pipelin:[1,33],pixel:2,pl_model:[0,47,55],place:[11,34,60,67,68,82,94,95,113,117,118],placehold:[11,94],platform:113,plot:[0,21,22,24,25,26,29,31,39,40,41,47,49,60,85,92],plot_al:85,plot_confusion_matrix:[1,22],plot_cost_progress:49,plot_count:22,plot_distribut:[1,21],plot_error_distribut:24,plot_feature_import:[25,29],plot_graphviz_pdf:60,plot_heat_map:21,plot_heatmap_ground_truth_predict:24,plot_matrix:109,plot_metric_valu:31,plot_precision_recal:22,plot_precision_recall_curv:22,plot_scatt:21,plot_scatter_ground_truth_predict:24,plot_seri:49,plot_target_distribut:25,plotcostprogress:49,plt:[2,24,109],pltensortoscalarclassificationmodel:56,pltensortoscalarregressionmodel:56,pltensortotensorclassificationmodel:56,pltensortotensorregressionmodel:56,plu:[73,74],plwrappedmodel:56,png:102,point:[1,2,6,9,19,22,23,25,26,31,33,36,37,39,40,42,43,48,49,53,58,59,67,68,85,86,107,109,114,117],poli:44,polygon:[40,42,44],polygonannotatedcoordin:40,polylin:37,pool:[2,104],pooling_kernel_s:2,pop:95,pop_al:95,posit:[22,26,37,44,49],positive_class_label:22,possibl:[1,2,11,22,25,46,83,85,97,117],post:[2,117,118],potenti:[1,6,36,53,74,83,94],potential_neighbor_valu:53,power:[2,49],pprint:112,practic:[1,33,112],pre:[2,68,80,82],preced:33,precis:[1,22,26,50,80,113],precomput:67,predclass:2,predecessor:11,predefin:[0,68],predict:[1,19,21,22,23,24,25,26,29,33,56,58,60,61,62,67,74,82,83,91,117],predict_class_prob:[62,117],predict_confidence_interv:61,predict_start:106,predictclassprob:[62,117],predicted_outputs_df:1,predicted_var_nam:[19,26,29,58,60,91],predicted_variable_nam:[51,117],predictedclass:1,predictedlabel:117,predictfinalis:106,prediction_mod:83,prediction_shap:62,predictionevalstat:[21,22,24],predictionmod:83,predictions_data_fram:[16,17],predictionshap:[56,62],predictor:83,predictor_factori:83,predictorfactori:83,predictorprotocol:83,prefer:[3,11,48,91],prefix:[25,73,90,94,95,102],prepar:[1,2],prepend:[46,91,100],preprocess:[11,12,34,117,118],preprocessor:[26,29,31,58,62,67,117],presenc:33,present:[33,46,53,91,94,102,107,108,111,112],presort:1,press:2,pretti:112,prettili:112,pretty_string_repr:112,prevent:11,previou:[2,74,95],previous:[26,34,46,51,64,85,93,94,117,118],pricipl:1,primit:[1,112],principl:[1,2,112],print:[1,110,112],print_to_consol:110,prior:[74,85,117],prioriti:[6,95],privat:112,probability_funct:49,probability_threshold:22,probabilityfunct:49,probabl:[1,21,22,26,33,46,49,62,67,69,73,74,76,80,109,117],problem:[1,2,9,19,22,33,50,67,73,74,80,108,112,113],process:[1,2,11,25,31,33,46,49,67,68,73,74,82,83,85,90,97,117],process_validation_batch:85,process_validation_result_batch:85,processor:29,produc:[1,2,12,26,33,51,67,74,82,83,85,117],product:[73,74],profil:[0,47,92],progress:49,project:[34,39,43],project_nam:89,pronounc:49,proper:112,properti:[5,9,19,26,33,34,42,48,67,91,95,108,112,115],property_boolean_blob_status_nam:95,property_load:95,property_nam:95,propertyload:95,proport:[21,49,58,59],propos:74,protocol:[1,7,12,83,94,108],provid:[1,2,5,8,11,14,19,21,25,26,29,31,33,39,40,46,49,53,67,68,76,79,80,83,85,86,89,91,94,95,97,112,118],provide_split:[68,86],proxi:112,pseudo:[39,43],pseudo_count:52,purpos:[2,25,44,46,49,112,117],put:[56,62,102],pw:96,pydata:[21,33],pyinstrument:110,pyplot:2,python:[1,3,95,103,104,116,118,119],python_api:119,pythonapi:48,pytorch:[1,2],pytorch_lightn:[0,47,56],q:61,qualifi:112,qualiti:[1,85,109],quantil:[60,61],quantile_rang:12,quantileregressionmetr:61,quantileregressionmetricaccuracyinconfidenceinterv:61,quantileregressionmetricconfidenceintervalmeans:61,quantileregressionmetricconfidenceintervalmedians:61,quantileregressionmetricrelfreqmaxsizeconfidenceinterv:61,quantiti:109,question:[44,117],queue:[6,95],quot:112,r2:[24,29],r:[24,25,29,49,107,109],rad:37,radiu:[5,44],radius_m:[37,44],rais:[2,11,33,34,62,97,101,111,117],random:[1,2,3,19,26,29,39,46,48,49,59,60,119],random_forest_model:[1,2],random_se:[9,19,25,29,46,49],random_st:[1,2,3,29,46,48,59,60,61,119],randomforest:[1,2,29],randomforestclassifi:[1,2],randomforestquantileregressor:61,randomforestquantileregressorvectorregressionmodel:61,randomli:[2,26,46,49],randomse:[19,26],rang:[1,2,12,33,44],rank:25,rank_max:25,rate:85,rather:[2,11,25,26,29,33,50,67,68,85,86,94,117],raw:[1,29,117],re:[1,11,46,85,95],reach:[22,31,95,118],read:[1,25,86,94,95,102,104],read_csv:2,read_text_file_lin:102,readabl:[39,104],readi:[1,2],readthedoc:[48,119],real:1,realli:[1,2],realm:[2,50],reason:[1,2,31,58,59,98],recal:[1,22,26],receiv:[2,11,33,83,94,108],recent:[33,49],reciproc:[58,59],recognit:[2,80],recommend:[1,34,49,62,98],recomput:[6,53],recreat:94,rect:45,rectangl:37,recurr:83,recurs:[31,108,112],recursivefeatureelimin:31,recursivefeatureeliminationcv:31,redblobgam:44,reduc:[80,113],reduce_float_precis:113,reduce_float_precision_decim:105,reduced_dim:2,redund:46,refer:[33,44,49,80,95,104,107,117],referenc:[34,44,118],reference_cost_delta:49,reference_paramet:3,referencecostdelta:49,refit_vectoris:118,reflect:[25,46,49,61],reformat:112,regard:1,regardless:[22,91,104,112],regex:[11,25,29,33,48,112],region:40,regist:[33,34,118],register_atexit:104,register_factori:[34,118],registri:34,regress:[1,2,24,25,26,29,33,51,56,62,67,74,80,85,109,119],regressionevalstat:[19,24,25,26],regressionevalstatscollect:[19,24,25],regressionevalstatsplot:[24,25],regressionevalstatsplotcollector:25,regressionevalstatsploterrordistribut:24,regressionevalstatsplotheatmapgroundtruthpredict:24,regressionevalstatsplotscattergroundtruthpredict:24,regressionevaluatorparam:[19,25,26,70],regressionmetr:[24,26,28,61],regressionmetricma:24,regressionmetricmediana:24,regressionmetricms:[24,46],regressionmetricpcc:24,regressionmetricr2:24,regressionmetricrms:24,regressionmetricrrs:24,regressionmetricstddeva:24,regressionmodelevalu:[25,70],regressionmultidatamodelcomparisondata:25,regular:[2,11,21,25,29,33,34,67,112],regularis:[60,80],regularli:46,rel:[1,22,24,44,61,93],relabel:[5,39],relative_frequency_count:93,relativebitwiseequalitydistancemetr:14,relativefrequencycount:93,relev:[1,11,25,33,49,67,93,102],relu:[2,59,60,69,80,83],remain:[31,40,53],remaind:[68,85,86],remov:[12,23,31,58,102,104,107,108,112,117],remove_duplicate_index_entri:107,remove_input_preprocessor:[31,117],remove_log_handl:104,remove_merg:6,removed_param:85,removed_properti:108,removedcommonnoisesupervisedmetr:23,removednoiseunsupervisedmetr:23,ren:80,renam:1,renamed_param:85,renamed_properti:108,render:[60,108,109,113],repeat:[31,53],repeatedli:118,replac:[11,58,59,95,117],report:[25,29,67,76,79,101,112],repres:[1,2,6,23,34,37,40,44,46,49,67,68,83,94,95,97,104,117,118],represent:[1,2,26,46,49,53,58,74,83,90,91,94,95,100,104,107,109,112,113],reproduc:[59,60],reprsent:1,request:[33,95],requir:[1,2,6,11,19,26,33,56,58,59,62,67,68,73,74,85,97,104,112,117],require_all_handl:[11,34],requires_prob:22,reserv:1,reset:[85,104],reset_index:1,reshap:2,reshape_2d_imag:2,residu:80,residualfeedforwardnetwork:80,residualfeedforwardnetworktorchmodel:79,residualfeedforwardnetworkvectorregressionmodel:79,residualffn:[0,47,66,71],residualffn_model:[0,47,66,71,78],residualffn_modul:[0,47,66,71,78],resnet:80,resourc:95,respect:[1,2,9,12,19,22,25,33,37,48,67,94,101,104,112,116],rest:[9,95],restart:104,restor:2,restrict:[67,95],result:[1,2,8,11,12,13,19,22,23,24,25,26,31,33,34,39,42,46,48,49,62,67,80,83,85,90,91,94,102,104,107,108,109,112,117,118],result_by_model_nam:1,result_collector:25,result_dir:102,result_handl:67,result_writ:[1,25],results_by_model_nam:25,results_df:[1,2,25],resulttyp:118,resultwrit:[25,102],resum:104,retain:[11,33,53,112],retriev:[14,27,29,40,67,85,94,95,96,111],return_trained_model:19,reus:[53,67,118],revers:[29,49,67],reverse_sigmoid:[49,105],rfe:[0,30,47],rfecv:31,rferesult:31,rfestep:31,rgb:107,ridg:60,right:44,rightmost:[97,111],rmse:24,rmsprop:85,rng:109,rnn:[68,73,74],rnn_type:83,rnnencoderfactori:83,rnnencodermodul:83,rnntype:83,robust:49,robustscal:12,room:2,root:24,roughli:49,row:[2,9,11,26,39,44,46,67,95,107,117],row_filter_queri:95,row_kei:95,rowkei:95,rprop:85,rrse:24,rudimentari:2,rule:[11,25,26,33,34,51,53,67,68,95,112,117],rulebaseddataframetransform:11,rulebasedfeaturegener:33,rulebasedtensoris:[2,67,68],rulebasedvectorclassificationmodel:117,rulebasedvectorclassificationmodelevalu:26,rulebasedvectorregressionmodel:[51,117],rulebasedvectorregressionmodelevalu:26,ruletempl:[8,11,33],run:[1,29,31,46,49,88,90,91,104],run_cli:104,run_id:90,run_main:104,s3_object:102,s3object:102,s:[1,2,6,8,9,11,21,22,24,25,26,27,29,31,33,39,46,48,49,53,58,61,62,67,68,73,74,83,85,90,91,94,97,100,102,103,104,105,107,109,112,117,118,119],sachain:49,sacostvalu:[46,49],sacostvaluenumer:[46,49],safe:[101,108],sahyperopt:46,sai:[1,2],said:33,same:[1,8,9,11,21,22,25,26,33,36,46,49,53,56,58,62,67,68,73,74,83,90,94,97,107,109,111,117,118],sampl:[1,2,36,67,83,110],sampling_interval_second:110,saoper:[46,49],saprobabilityfunct:49,saprobabilityfunctionconst:49,saprobabilityfunctionlinear:49,saprobabilityfunctionreversesigmoid:49,saprobabilityschedul:49,sastat:[46,49],satemperatureschedul:49,satemperaturescheduleexponenti:49,satemperatureschedulefix:49,satemperatureschedulepow:49,satemperatureschedulereversesigmoid:49,satemperatureschedulereversesigmoidsymmetr:49,satisfi:83,save:[1,14,26,29,39,46,67,91,94,102,109],save_on_upd:[14,94],save_result:67,scalar:[11,33,49,56,62,67,85,107,118],scalarmapp:109,scale:[11,12,50,58,59,60,67,68,73,85,105],scale_input:67,scale_output:67,scaled_float:50,scaled_int:50,scaled_output:[2,67,85],scaled_valu:50,scaledoutput:85,scaler:[12,67,68,73],scatter:[24,25],scatter_plot_point_color:24,scatterplot:109,scenario:1,schedul:49,schedule_factori:49,scienc:1,scikit:[1,2,9,29,36,58,59,60],scope:104,score:[22,24,29,85],scratch:[46,49],sd:67,sdk:88,seaborn:21,search:[0,37,46,97,111],search_orientation_angl:37,search_po:37,search_radius_m:36,searchorientationangl:37,searchpo:37,second:[1,2,9,24,37,49,50,61,85,94,104,109,110],secondari:109,secret:104,see:[1,3,9,11,21,22,24,25,29,33,36,44,46,48,49,53,59,60,74,80,83,85,94,95,119],seed:[3,19,26,29,48,49,59,60],seek:1,seen:[13,97],segment:[37,109],segpoint1:37,segpoint2:37,segreg:[56,62],select:[2,11,31,68,85,112],self:[2,44,58,67,109,117],semant:[1,56,62,112,117],sens:[1,117],sensai:[2,3,5,6,7,8,9,11,12,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,41,42,43,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,69,70,73,74,76,77,79,82,83,85,86,88,89,90,91,93,94,95,96,97,101,102,103,105,106,107,109,111,112,114,117,118,119],sensibl:2,sensor:1,sepal:1,separ:[2,9,11,24,29,33,56,62,73,74,85,94],seq:[0,47,66,71,82,83,111,118],seq_length:83,seq_model:[0,47,66,71,81],seq_modul:[0,47,66,71,81,82],sequenc:[0,1,2,3,6,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,29,33,40,46,47,48,49,50,53,59,60,67,68,76,77,79,80,82,83,85,92,95,97,101,102,107,109,112,117,118],sequencevectoris:[82,118],sequenti:[1,109],sergei:80,seri:[2,8,11,19,21,22,24,26,49,53,73,74,85,97,109,113],serial:46,serialis:[94,95,108],serialisedpropertyload:95,series_nam:49,serv:[1,2,50,68,86,117],server:90,servic:95,session:64,set:[0,2,5,6,9,11,12,14,19,21,22,24,25,26,27,31,33,34,36,40,42,46,48,53,56,59,60,62,64,67,68,73,74,76,79,82,85,86,94,95,96,97,104,107,108,109,112,117,118],set_cluster:[6,36],set_configure_callback:104,set_data_splitt:26,set_feature_gener:117,set_keras_sess:64,set_module_byt:67,set_nam:[11,21,33,117,118],set_normalisation_check_threshold:67,set_param:[58,97],set_regex:11,set_titl:2,set_to_drop:11,set_to_keep:11,set_torch_modul:67,set_tracked_experi:[26,91],set_value_for_refer:95,setosa:1,setstat:108,settodrop:11,settokeep:11,sever:[1,11,19,25,51,58,94,118],sgd:[59,60,85],sha1:100,shall:[1,2,6,11,13,19,25,31,33,34,36,46,49,50,53,59,60,62,67,68,73,82,85,91,94,101,104,108,109,112,117,118],shaoq:80,shape:[2,9,14,21,39,40,41,42,44,49,56,61,62,67,74,80,83,85,107],shapefil:[39,40],share:[11,117],shift:[44,80],shorter:118,should:[1,2,3,6,8,14,21,22,25,29,33,36,40,50,56,62,67,68,83,86,89,90,91,94,95,96,101,109,112,117],show:[25,109],show_plot:[1,25],shown:[1,80],shrinkag:85,shrinkage_clip:[2,85],shrinkageclip:85,shuffl:[1,2,9,19,26,29,56,68,85,86],sigmoid:[2,49,65,69,74,76,77,105],signific:[50,113],significant_digit:[50,113],significantli:118,silhouettescor:23,similar:[31,42,80],similarli:[1,2,25,29],simpl:[0,2,13,25,64,94,107],simpli:[1,2,6,8,25,33,67,82],simplifi:83,simul:[46,49],simulatedann:[46,49],simultan:[68,101],sinc:[2,14,67,73,80,94,95,96,117],singl:[1,6,8,11,19,21,22,25,26,33,39,48,51,56,58,62,67,68,82,83,85,88,107,112,117,118],single_lat:83,single_output:83,single_output_mean:83,singlecolumndistancemetr:14,singletargetdecoderfactori:83,singletargetdecodermodul:83,singleton:[34,104],situat:1,size:[2,5,7,9,39,42,59,60,61,67,68,73,74,83,85,86,95,107,109],skip:[11,46,73,74,80,83,102],skip_empti:102,sklearn:[0,1,2,3,7,9,11,12,29,31,34,36,39,47,48,58,59,60,61,112,118,119],sklearn_bas:[0,1,2,3,47,48,57,59,60,61,119],sklearn_classif:[0,47,57],sklearn_clust:[0,4,39,47],sklearn_input_transform:58,sklearn_output_transform:58,sklearn_quantil:[0,47],sklearn_regress:[0,47,57],sklearn_splitt:9,sklearn_transform:[0,10,11,47],sklearnclustererprotocol:[7,39],sklearncoordinateclust:39,sklearndecisiontreevectorclassificationmodel:[1,59],sklearndecisiontreevectorregressionmodel:60,sklearndummyvectorregressionmodel:60,sklearneuclideancluster:7,sklearnextratreesvectorregressionmodel:60,sklearngeocoordcluster:36,sklearngradientboostingvectorregressionmodel:60,sklearnkneighborsvectorclassificationmodel:59,sklearnkneighborsvectorregressionmodel:60,sklearnlinearlassoregressionvectorregressionmodel:60,sklearnlinearregressionvectorregressionmodel:60,sklearnlinearridgeregressionvectorregressionmodel:60,sklearnlinearsvrvectorregressionmodel:60,sklearnlogisticregressionvectorclassificationmodel:59,sklearnmlpvectorclassificationmodel:59,sklearnmultilayerperceptronvectorregressionmodel:60,sklearnmultinomialnbvectorclassificationmodel:59,sklearnrandomforestvectorclassificationmodel:[1,2,59],sklearnrandomforestvectorregressionmodel:60,sklearnsvcvectorclassificationmodel:59,sklearnsvrvectorregressionmodel:60,sklearntransformerfactoryfactori:[11,12,34],sklearntransformerprotocol:[11,12],slice:[68,73,74,83,94,97,111],slicedpicklepersistentlist:94,slope:49,smaller:[36,42,49,97,109,111],smallest:[31,58,59,97,111],smoothl1loss:85,sn:109,snapshot:113,snapshot_compat:113,so:[1,2,6,67,74,80],softmax:69,sole:[46,49],solv:[2,50],solve_path:50,solve_problem:50,solver:[50,59,60],solver_time_second:50,some:[1,2,11,23,25,46,49,58,59,68,80,86,104,107,112,117,118],someth:117,soon:112,sort:[1,11,25,29,31,46,49,58,59,97,107,111],sort_ascend:25,sort_column:25,sort_column_move_to_left:25,sort_column_nam:46,sortcolumn:25,sortcolumnnam:46,sorted_key_value_pair:97,sorted_valu:97,sortedkeysandvalu:97,sortedkeyvaluepair:97,sortedkeyvaluestructur:97,sortedvalu:97,soundli:67,sourc:[3,5,6,7,8,9,11,12,13,14,16,17,19,21,22,23,24,25,26,27,28,29,31,33,34,36,37,39,40,41,42,43,44,45,46,48,49,50,51,52,53,54,56,58,59,60,61,62,64,65,67,68,69,70,73,74,76,77,79,80,82,83,85,86,88,89,90,91,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119],space:36,span:44,spanningtre:43,special:[73,83,118],specialis:[1,86],specif:[1,2,11,12,24,39,43,46,49,59,60,83,91,94,97,109,112],specifi:[2,3,11,21,25,26,33,34,46,48,61,67,68,76,80,85,94,102,108],speed:[53,118],split:[1,2,9,19,25,26,31,44,48,67,68,73],split_into_data_set:68,split_into_tensor:[68,73],split_with_indic:9,splitter:[1,9,19,26,67],spread:40,sqlite:94,sqliteconnectionmanag:94,sqlitepersistentkeyvaluecach:94,sqlitepersistentlist:94,sqrt:2,squar:[24,37,60],squared_distance_to:37,src:[1,2],stabl:[9,29,33,36,59,60],stack:2,stackoverflow:44,stage:[1,67,73,74,83],stand:112,standard:[1,24,42,67,85,105],standardis:54,standardscal:[11,12,34],start:[1,2,6,36,46,49,73,85,97,104,112,114],start_epoch:85,start_evalu:85,start_logging_kwarg:88,start_validation_collect:85,stat:[1,21,22,24,25,49,109],state:[46,49,74,83,85,108],state_factori:49,statement:[90,91,104],statist:[21,23,26,27,85,109],stats_dict:26,std:[1,21,105],stddev_siz:23,stddeva:24,stdout:[104,112],steep:49,step:[1,2,31,49,59,60,67,73,74,80],stick:2,still:[2,58,59,62,94,112,117],stop:[2,59,60,85,104,117],stopwatch:104,stopwatchmanag:104,storag:95,storageservic:95,store:[1,6,8,14,25,46,50,53,67,94,95,96],str:[3,5,8,9,11,14,19,21,22,23,24,25,26,29,31,33,34,39,40,43,46,48,50,53,58,59,60,61,69,70,73,74,76,82,85,86,88,89,90,91,94,95,97,100,102,103,104,108,109,110,112,115,117],str_hash:100,str_sklearn_model:58,straightforward:1,straightforwardli:2,strategi:[6,36,60,67],strength:60,string:[0,9,11,21,24,26,29,33,34,37,47,48,53,58,67,83,85,90,91,92,93,94,95,97,100,104,105,107,108,117,118],string_identifi:50,string_valu:103,stringconvert:112,strip:[62,102,107],structur:[95,97,112],sub:112,subclass:[1,2,6,9,112],subdirectori:25,subgraph:43,subplot:2,subsequ:[33,34,67,83,90,91,97,111,118],subset:[6,11],subtitl:[21,22,24,25,29],subtitle_prefix:25,subtract:12,success:[6,107],successfulli:3,suffici:[49,85],suffix:[60,73,102],suggest:25,suit:74,suitabl:[1,11,25,42,46,49,74],sum:[25,29,58,59,85,109],summari:25,summary_df:5,summary_dict:[5,43],sun:80,superclass:112,superset:25,supervis:0,suppli:[1,33,118],support:[1,2,5,8,9,11,26,34,48,58,59,67,93,94,97,100,101,103,109,113,117,118],suppport:1,sure:94,sy:[1,2],symmetr:[12,14,49],system:[6,36,44,90],szegedi:80,t0:49,t1:[49,101],t2:101,t:[1,2,9,11,19,33,42,49,68,91,94,101,111,112,114,118],t_1:33,t_i:33,t_n:33,tabl:[25,46,94,95],table_nam:[94,95,96],table_servic:95,tablebatch:95,tablenam:95,tableservic:95,tag:104,tag_nam:90,tag_valu:90,tagbuild:112,take:[1,2,11,21,22,33,56,61,62,67,68,73,82,83,94,95,117,118],take_input_column_if_pres:[8,33],taken:[25,33,86,104,108],tanh:[59,60,69],target:[1,2,25,33,56,62,67,74,82,83,117,118],target_column:33,target_column_bin:33,target_column_in_features_df:33,target_featur:83,target_feature_dim:83,target_feature_gener:33,target_length:83,target_nam:1,target_seq_length:83,target_sequence_column_nam:82,target_sequence_vectoris:82,target_transform:117,targetcolumn:33,targetcolumnbin:33,targetfeaturegener:33,targetsequencedecoderfactori:83,targetsequencedecodermodul:83,targettransform:117,task:[1,89],task_nam:89,tclusteringevalstat:27,tcontext:91,tcrossvaldata:[19,25],tcrossvalid:25,tdata:94,technic:[1,112],tell:46,temper:49,temperatur:49,templat:[8,11,33],temporari:50,tensor:[2,56,62,67,68,69,74,76,77,80,83,85,86],tensor_model:[0,47,56],tensorflow:[0,1,2,47,65],tensorflowsess:64,tensoris:[2,67,68,82],tensorise_dynam:[67,68],tensoriserclasslabelindic:68,tensoriserdataframefloatvaluesmatrix:[2,68],tensormodel:62,tensorscal:[68,73],tensorscalercentreandscal:68,tensorscalerfromdftsklearntransform:68,tensorscalerfromvectordatascal:68,tensorscalerident:68,tensorshap:[62,107],tensortoscalarclassificationmodel:[56,62],tensortoscalarregressionmodel:[56,62],tensortotensorclassificationmodel:[56,62],tensortotensorregressionmodel:[56,62],tensortransform:[68,85],tensortupl:68,term:[60,74,83,91],termin:90,test:[0,1,2,3,25,26,47,53,83,92,95,108],test_data:[25,26],test_fract:[19,25],test_indices_list:19,test_io_data:[1,25,70],test_io_data_dict:25,testdata:26,tevaldata:[19,25,26],tevalstat:[19,21,25,26],tevalstatscollect:[19,25],tevalstatsplot:25,tevalu:25,text:[2,25,89,90,91,102],textdumpazuretableblobbackend:95,textiowrapp:112,tf_base:[0,47,63,65],tf_mlp:[0,47,63],th:[67,85],than:[1,2,11,25,26,29,33,44,49,50,56,58,62,67,68,85,86,91,94,97,111,117,118],thei:[1,2,9,11,33,56,62,67,68,108,111,117],them:[1,2,6,11,25,33,50,56,62,82,94,98,112,117,118],themselv:1,thereaft:[46,49],therefor:[1,2,49,74,80,91,97,117,118],thereof:33,thi:[1,2,3,5,6,7,8,11,19,21,22,24,25,26,27,29,31,33,34,36,39,40,42,46,49,56,58,59,62,67,68,73,74,76,79,80,82,83,85,90,91,93,94,97,98,99,101,102,104,107,108,111,112,115,116,117,118],thing:1,those:[31,56,62],though:[2,112],thread:95,three:[1,107],threshold:[1,6,22,67],through:[6,104,117],throughout:24,thu:[1,2,12,26,46,67,74,83,85,107,112,117,118],tick:109,tight_layout:2,time:[0,1,2,11,19,29,33,37,47,48,50,51,56,62,67,73,74,83,92,94,95,97,104,110,117],time_delta:114,time_of_dai:114,time_period_sec:94,timedelta:[104,114],timeinterv:114,timeperiodsec:94,timerangeneighborsprovid:53,timestamp:[37,46,53,114],timestamps_column:53,tinputoutputdata:9,titl:[24,109],title_add:[22,24,109],tkei:[94,97],tmetric:[21,22,23],tmodel:[19,25],to_2d_arrai:12,to_data_fram:21,to_dft:33,to_feature_gener:[8,11],to_float_arrai:99,to_geodf:[39,40,41,43],to_hex:109,to_placeholder_rul:11,to_rul:11,to_str:112,to_tensor:68,to_torch_data_load:9,togeth:[9,21,22],tol:60,told:46,too:[67,101],took:2,top2accuraci:1,top:[1,46],torch:[0,47,67,68,69,73,74,76,77,79,80,82,83,85,86],torch_bas:[0,2,47,66,73,74,76,77,79,82],torch_data:[0,2,47,66,67,73,82,85,86],torch_data_set_provider_factori:67,torch_enum:[0,47,66,67,74,76,83,85],torch_eval_util:[0,47,66],torch_function_from_ani:69,torch_mlp_model:2,torch_model:[0,47,66,74,82,83],torch_model_factori:[2,67,79],torch_modul:[0,47,66],torch_opt:[0,2,47,66,67,73,76,79,82],torchautoregressiveresulthandl:67,torchdataset:[67,68,85,86],torchdatasetfromdatafram:68,torchdatasetfromdataframesdynamicallytensoris:68,torchdatasetfromdataframespretensoris:68,torchdatasetfromtensor:68,torchdatasetfromtorchtextdataset:86,torchdatasetprovid:[2,67,68,85,86],torchdatasetproviderfactori:[2,67],torchdatasetproviderfactoryclassificationdefault:67,torchdatasetproviderfactoryregressiondefault:67,torchdatasetproviderfromdatautil:68,torchdatasetproviderfromtorchtextdataset:86,torchdatasetproviderfromvectordatautil:68,torchmodel:[67,79,82,85],torchmodelfactoryfrommodul:[2,67],torchmodelfittingstrategi:67,torchmodelfittingstrategydefault:67,torchmodelfrommodul:[2,67],torchmodelfrommodulefactori:67,torchtext:[0,47,66],torchtextdatasetfromdatafram:86,torchvectorclassificationmodel:[2,67,73,76],torchvectorregressionmodel:[2,67,76,79,82],torchvectorregressionmodelevaluationutil:70,tostring_include_preprocessor:117,tostringexcludeexcept:112,tostringmixin:[9,11,21,26,29,33,37,67,83,85,93,97,105,112,117,118],total:[48,68,74,86,104],total_epoch:[67,85],total_weight:43,totalepoch:2,toward:44,tplot:109,track:[0,1,19,25,26,46,47,88,89,90,91,107,118],track_chang:107,track_figur:[89,90,91],track_metr:[19,91],track_tag:90,track_text:[89,90,91],track_valu:91,tracked_experi:[25,26,91],trackedazuremlevalu:88,trackedazuremlexperi:88,trackedexperi:[25,26,88,89,90,91],tracking_bas:[0,19,25,26,46,47,87,88,89,90],tracking_context:[19,25],tracking_uri:90,trackingcontext:[19,25,89,90,91],trackingmixin:[26,46,91],trail:[102,103],train:[0,2,11,19,25,26,31,33,48,51,56,58,59,60,62,67,68,73,74,76,79,80,85,86,89,117,118],train_fract:[2,85],trained_model:19,trainer:56,trainfract:85,training_context:67,training_io_data:1,training_log:2,training_loss_sequ:85,trainingcontext:[67,117],traininginfo:[67,85],transact:[94,95],transform:[0,2,8,11,12,13,26,29,31,33,34,44,49,58,62,67,68,85,107,109,117,118],transformer_factori:11,transient_properti:108,transpar:109,treat:[22,83],tree:[1,2,3,43,48,119],tree_find:43,tri:108,triangul:43,trigger:[11,67],tripl:26,trival:97,trivial:67,true_compon:112,true_label:[23,27],trueclass:2,truth:[1,21,22,23,26,40,56,62,68,85,117],ts:114,ts_next_month:114,tsastat:49,tslib:[37,104,114],tsortedkeyvaluestructur:97,ttorchvectorclassificationmodel:67,ttorchvectorregressionmodel:67,tupl:[1,6,9,12,14,19,21,22,23,24,25,26,29,33,36,37,40,44,45,46,49,53,61,62,67,68,73,85,86,94,97,101,102,109,112,115,118],turn:1,tutori:[1,2],tvalu:[14,94,97],tvectormodel:117,tvectormodelbas:117,tvectorregressionmodel:117,two:[1,2,6,11,24,29,36,37,43,44,68,74,80,85,86,94,97,104,109,111,112],tx:45,txt:95,ty:45,type:[0,1,2,7,11,14,19,21,22,25,26,29,40,43,47,48,53,58,59,83,92,94,95,97,99,101,107,113,117,118],typic:[1,6,26,33,51,67,74,104,117],typing_extens:[7,12,83],ufunc:11,ultim:[2,6,36,74,85,94,117],unchang:109,undefin:[97,103],under:[14,25,26,29,90,94,95,96,118],underli:[2,26,33,67,117,118],underscor:112,understand:95,understood:[1,80,109],unfortun:108,uniform:117,uniformli:12,union:[2,3,5,6,11,12,14,19,21,22,24,25,26,28,29,31,33,34,39,40,41,42,44,46,48,54,59,60,67,68,69,70,73,74,76,79,83,85,86,94,95,99,101,103,108,112,115,117,118],uniqu:[9,11,109,118],unique_id_provid:118,unique_id_retriev:118,unit:[1,9,44,83,85],unit_max:105,unknown:[11,13,34,97],unless:[11,29,68,94,102,112],unmatch:[11,34],unmodifi:[1,25],unnecessari:6,unnormalised_log_prob:69,unpad:118,unpickl:94,unscal:50,unset_tracked_experi:91,unset_valu:36,unsort:25,unsorted_key_value_pair:97,unsqueez:2,unsupport:[11,33],until:[6,31,94,95,118],untransform:117,unwant:[67,112],up:[1,9,33,37,53,112,117,118],updat:[6,36,46,49,94,95],upon:[2,46,58,90,104,112],upper:[50,61,111],upper_bound_kei:[97,111],upperboundkei:111,uri:90,us:[0,2,3,6,7,8,11,14,19,21,22,24,25,26,27,29,31,33,34,36,44,46,48,49,53,56,58,59,60,61,62,64,67,68,73,74,76,80,82,83,85,86,90,91,94,95,96,97,101,104,108,109,110,111,112,115,117,118,119],usag:109,use_balanced_class_weight:[48,58,59,119],use_batch_normalis:[79,80],use_cach:118,use_combined_eval_stat:28,use_cross_valid:[1,25,28],use_label_encod:[58,59],use_shrinkag:[2,85],use_singleton:34,use_target_feature_generator_for_train:33,usearrayvalu:11,usebalancedclassweight:[1,2],usecrossvalid:25,uselabelencod:[1,2],user:[1,33,46,49,96,112],useshrinkag:85,usesingleton:34,usual:[1,11,23,25,31,49,107,112],utf:112,util:[0,2,5,8,9,11,14,19,21,25,26,29,33,37,39,40,45,46,47,53,67,83,85,93,94,95,96,97,101,102,103,105,106,107,109,111,112,114,117,118],utilis:11,utm:44,v0:49,v1:49,v:[46,109],va:12,valid:[0,2,19,25,31,36,43,46,67,68,85,86,94,102,117],valid_extens:102,valid_other_extens:102,validate_coordin:41,validation_fract:[56,64,65],validation_loss_evalu:85,validation_metric_nam:85,validation_metric_sequ:85,validation_tensor_transform:85,validationlossevalu:85,validationtensortransform:85,validity_check_fn:94,valu:[1,2,8,9,11,12,13,14,21,22,23,24,25,26,29,31,33,36,42,46,49,50,53,54,58,60,61,67,68,69,74,83,85,86,88,91,93,94,95,96,97,101,103,105,108,109,111,112,117,118],value_a:33,value_count:11,value_for_index:97,value_identifi:95,value_na:33,value_nam:95,value_slic:97,value_slice_inn:[97,111],value_slice_out:[97,111],value_transform:[0,10,47],value_typ:96,valueerror:[2,101],valuenam:95,valueonehotencod:13,values_dict:91,valuetyp:96,var_nam:61,varchar:94,vari:[11,22,53,83,118],variabl:[11,19,26,29,49,58,60,61,67,68,73,74,82,83,91,117],variable_history_length:83,variant:[49,85,94],variat:85,variou:[1,27,99,101],vb:12,vec1:33,vec1_:33,vec2:33,vec2_:33,vector:[1,2,11,26,33,37,64,74,82,83,85,117,118],vector_data_scal:68,vector_model:[0,1,2,11,16,17,19,24,25,26,28,29,31,33,46,47,51,52,53,58,61,62,64,67,88,90,91,106],vectorclassificationmodel:[1,19,25,28,31,52,53,58,62,67,117],vectorclassificationmodelcrossvalid:[19,25],vectorclassificationmodelcrossvalidationdata:[1,19,25],vectorclassificationmodelevalu:[1,2,25,26],vectorclassificationmodelevaluationdata:[1,19,25,26],vectorclassificationmodelevaluatorparam:26,vectordatascal:[54,68],vectordatautil:68,vectoris:[0,2,11,47,67,82],vectoriserregistri:118,vectorized_condit:11,vectormodel:[0,2,8,11,16,19,25,26,29,31,33,46,62,67,88,106,117],vectormodelbas:[25,26,28,90,91,117],vectormodelcrossvalid:[19,25],vectormodelcrossvalidationdata:[19,29],vectormodelcrossvalidatorparam:[1,19,25,31,70],vectormodelevalu:[25,26],vectormodelevaluationdata:26,vectormodelfittablebas:[26,117],vectormodelwithseparatefeaturegener:106,vectorregressionmodel:[1,17,19,24,25,28,31,51,53,58,61,62,64,67,117],vectorregressionmodelcrossvalid:[19,25],vectorregressionmodelcrossvalidationdata:[19,25],vectorregressionmodelevalu:[25,26],vectorregressionmodelevaluationdata:[19,25,26],vectorregressionmodelevaluatorparam:26,vectortorchmodel:[2,67,76,79],velid:85,verbos:[1,2,104,118],veri:[1,2,25,97],verify_column_nam:33,versa:[44,50],versicolor:1,version:[0,11,33,47,92,94,112],via:[1,2,3,6,11,25,26,29,33,34,46,48,49,67,74,82,85,91,94,95,104,112,118],vice:[44,50],view:[2,9,95],virginica:1,visit:25,visitor:25,visual:40,visualis:[21,22,25,26,44],vl:118,vmeasurescor:23,vote:53,vs:31,w:[25,29,83,112],wa:[1,2,26,27,31,33,34,37,40,46,49,62,64,93,94,102,117,118],wai:[11,56,62,67,95],wait:94,want:[1,2,11,25,90,91,112,118],warm_start:[1,2],warn:[2,67,98,104],watch:104,wc:[6,36],we:[1,2,3,6,24,36,42,58,59,62,67,73,83,90,91,93,107,117,118],weight:[14,17,43,46,48,49,53,58,59,85,93],weightedmean:93,well:[1,2,25,34,62,94,104,112,113],went:2,were:[6,9,23,25,31,33,36,67,107],wgs84:37,what:[1,2,6,74,76,101],whatev:[1,117],when:[1,8,9,11,12,25,33,34,36,46,49,74,94,98,101,104,112,113,117,118],whenev:[1,2,26,67,108],where:[1,2,6,8,9,11,12,13,19,22,23,24,25,26,29,31,33,34,36,37,43,44,46,49,53,58,61,62,64,67,68,73,74,80,83,85,86,90,91,94,95,97,107,108,109,111,112,117,118],whether:[6,8,9,11,12,13,19,21,22,24,25,26,27,29,31,33,34,36,39,46,48,49,50,53,56,58,59,60,62,64,67,68,76,80,82,83,85,86,90,91,93,94,102,103,104,108,109,111,112,117,118],which:[1,2,6,8,9,11,12,13,14,19,21,22,24,25,26,29,31,33,34,36,37,40,46,48,49,53,58,59,60,62,64,67,68,73,74,76,79,80,82,83,85,86,90,91,93,94,95,96,97,98,102,103,104,107,108,109,110,111,112,117,118],whilst:50,white:109,whitespac:102,whole:11,whose:[8,11,12,13,22,33,44,46,50,62,85,93,94,104,109,110,117],width:[1,107,109],wikipedia:80,window:[83,94,109],window_featur:83,window_length:83,wise:95,wish:27,with_altern:112,with_autoregressive_result_handl:67,with_cent:12,with_class_nam:100,with_compon:112,with_condit:112,with_data_frame_splitt:67,with_feature_collector:117,with_feature_gener:117,with_feature_transform:117,with_input_tensoris:[2,67],with_input_transform:117,with_mean:12,with_nam:[1,2,11,117],with_normalisation_check_threshold:67,with_output_tensor_to_array_convert:67,with_output_tensoris:67,with_output_transform:117,with_raw_input_transform:117,with_scal:12,with_sklearn_input_transform:58,with_sklearn_output_transform:58,with_std:12,with_target_transform:117,with_torch_data_set_provider_factori:67,withfeaturecollector:117,withfeaturegener:117,within:[1,2,11,14,33,36,40,67,68,80,82,90,94,95,97,103,112,117],without:[2,8,9,11,12,22,33,46,53,59,60,80,83,85,102,104,112],work:[1,2,6,25,33,62,64,83],worker:95,workflow:25,workspac:88,world:1,worst:31,worstvalu:23,would:[1,46,49,62,67,68,108,112,117],wrap:[0,6,8,36,48,53,67,95,110],wrappedclust:[6,36],wrapper:[1,6,7,33,39,43,83,90,91,95],write:[1,2,25,50,91,95,102],write_csv:25,write_data_frame_csv:25,write_data_frame_csv_fil:102,write_data_frame_text_fil:102,write_eval_stat:25,write_figur:[25,102],write_individual_result:25,write_per_dataset_result:25,write_pickl:102,write_property_valu:95,write_text_fil:102,write_text_file_lin:102,write_visitor_result:25,writer:[25,102],written:[1,2,25,46,102,104],wrong:2,www:44,x0:105,x:[2,7,16,21,22,25,33,44,56,61,62,67,68,74,77,80,83,85,105,106,109,112,117],x_column:44,x_data:73,x_label:109,xgbclassifi:119,xgbgradientboostedvectorclassificationmodel:119,xgbgradientboostedvectorregressionmodel:119,xgboost:[0,1,47,58,59],xgbrandomforestvectorclassificationmodel:119,xgbrandomforestvectorregressionmodel:119,xgbregressor:119,xgbrfclassifi:119,xgbrfregressor:119,xiangyu:80,xlabel:109,xlim:109,xtick:109,xtick_label:109,xtick_major:109,xtick_minor:109,xy:36,y:[21,22,25,33,44,56,62,67,68,85,106,109,117,118],y_data:73,y_label:109,y_predict:[21,22,24,61],y_predicted_class_prob:22,y_row:44,y_true:[21,22,24,61],yet:[1,2,29,80,94],yield:[11,31],ylabel:109,ylim:109,you:[1,2,11,25,27,46,67,108,117,118],your:[1,6,67,117],ytick_label:109,ytick_major:109,z0:95,z:95,za:95,zero:[11,13,22,34,62,104,118],zero_denominator_metric_valu:22,zero_valu:22,zerovalu:22,zhang:80,zip:2,zoom:45},titles:["sensAI - the Python library for sensible AI","Introduction to sensAI: Supervised Learning with VectorModels","Neural Networks","catboost","clustering","clustering_base","greedy_clustering","sklearn_clustering","columngen","data","data_transformation","dft","sklearn_transformer","value_transformation","distance_metric","ensemble","ensemble_base","models","evaluation","crossval","eval_stats","eval_stats_base","eval_stats_classification","eval_stats_clustering","eval_stats_regression","eval_util","evaluator","evaluator_clustering","metric_computation","feature_importance","feature_selection","rfe","featuregen","feature_generator","feature_generator_registry","geoanalytics","geo_clustering","geo_coords","geopandas","coordinate_clustering","coordinate_clustering_ground_truth","coordinates","geometry","graph","local_coords","map_tiles","hyperopt","Modules","lightgbm","local_search","minizinc","multi_model","naive_bayes","nearest_neighbors","normalisation","pytorch_lightning","pl_models","sklearn","sklearn_base","sklearn_classification","sklearn_regression","sklearn_quantile","tensor_model","tensorflow","tf_base","tf_mlp","torch","torch_base","torch_data","torch_enums","torch_eval_util","torch_models","lstnet","lstnet_models","lstnet_modules","mlp","mlp_models","mlp_modules","residualffn","residualffn_models","residualffn_modules","seq","seq_models","seq_modules","torch_modules","torch_opt","torchtext","tracking","azure_tracking","clearml_tracking","mlflow_tracking","tracking_base","util","aggregation","cache","cache_azure","cache_mysql","datastruct","deprecation","dtype","hash","helper","io","jscode","logging","math","multiprocessing","pandas","pickle","plot","profiling","sequences","string","test","time","typing","version","vector_model","vectoriser","xgboost"],titleterms:{adapt:2,aggreg:93,ai:0,an:2,appli:2,azure_track:88,cach:94,cache_azur:95,cache_mysql:96,catboost:3,classif:2,clearml_track:89,cluster:4,clustering_bas:5,cnn:2,columngen:8,compar:1,coordin:41,coordinate_clust:39,coordinate_clustering_ground_truth:40,creat:2,cross:1,crossval:19,custom:2,customis:1,data:[1,9],data_transform:10,datastruct:97,deprec:98,dft:11,distance_metr:14,dtype:99,ensembl:15,ensemble_bas:16,eval_stat:20,eval_stats_bas:21,eval_stats_classif:22,eval_stats_clust:23,eval_stats_regress:24,eval_util:25,evalu:[1,18,26],evaluator_clust:27,featur:1,feature_gener:33,feature_generator_registri:34,feature_import:29,feature_select:30,featuregen:32,frame:1,fulli:1,gener:1,geo_clust:36,geo_coord:37,geoanalyt:35,geometri:42,geopanda:38,graph:43,greedy_clust:6,guid:0,hash:100,helper:101,hyperopt:46,imag:2,indic:0,infer:1,input:2,instanc:2,integr:1,introduct:1,io:102,jscode:103,learn:1,level:1,librari:0,lightgbm:48,local_coord:44,local_search:49,log:[1,104],low:1,lstnet:72,lstnet_model:73,lstnet_modul:74,map_til:45,math:105,metric_comput:28,minizinc:50,mlflow_track:90,mlp:75,mlp_model:76,mlp_modul:77,model:[1,2,17],modul:[0,2,47],multi_model:51,multiprocess:106,naive_bay:52,nearest_neighbor:53,network:2,neural:2,nn:2,normalis:54,output:2,panda:107,pickl:108,pl_model:56,plot:[1,109],predefin:2,profil:110,python:0,pytorch_lightn:55,residualffn:78,residualffn_model:79,residualffn_modul:80,rfe:31,sensai:[0,1],sensibl:0,seq:81,seq_model:82,seq_modul:83,sequenc:111,set:1,simpl:1,sklearn:57,sklearn_bas:58,sklearn_classif:59,sklearn_clust:7,sklearn_quantil:61,sklearn_regress:60,sklearn_transform:12,string:112,supervis:1,tabl:0,tensor_model:62,tensorflow:63,test:113,tf_base:64,tf_mlp:65,time:114,torch:[2,66],torch_bas:67,torch_data:68,torch_enum:69,torch_eval_util:70,torch_model:71,torch_modul:84,torch_opt:85,torchtext:86,track:87,tracking_bas:91,train:1,transform:1,tutori:0,type:115,us:1,util:[1,92],valid:1,value_transform:13,vector_model:117,vectoris:118,vectormodel:1,version:116,wrap:2,xgboost:119}})
\ No newline at end of file
diff --git a/docs/sensai/evaluation/eval_stats/eval_stats_classification.html b/docs/sensai/evaluation/eval_stats/eval_stats_classification.html
index 2137f8d8..5f2ce812 100644
--- a/docs/sensai/evaluation/eval_stats/eval_stats_classification.html
+++ b/docs/sensai/evaluation/eval_stats/eval_stats_classification.html
@@ -628,12 +628,12 @@
 
 <dl class="py method">
 <dt class="sig sig-object py" id="sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStats.plot_confusion_matrix">
-<span class="sig-name descname"><span class="pre">plot_confusion_matrix</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">title_add</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStats.plot_confusion_matrix" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">plot_confusion_matrix</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalize</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">title_add</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">matplotlib.figure.Figure</span></span></span><a class="headerlink" href="#sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStats.plot_confusion_matrix" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
 <dl class="py method">
 <dt class="sig sig-object py" id="sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStats.plot_precision_recall_curve">
-<span class="sig-name descname"><span class="pre">plot_precision_recall_curve</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">title_add</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStats.plot_precision_recall_curve" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">plot_precision_recall_curve</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">title_add</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">matplotlib.figure.Figure</span></span></span><a class="headerlink" href="#sensai.evaluation.eval_stats.eval_stats_classification.ClassificationEvalStats.plot_precision_recall_curve" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
 </dd></dl>
diff --git a/docs/sensai/evaluation/evaluator.html b/docs/sensai/evaluation/evaluator.html
index f1955283..54085612 100644
--- a/docs/sensai/evaluation/evaluator.html
+++ b/docs/sensai/evaluation/evaluator.html
@@ -452,11 +452,11 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="sensai.evaluation.evaluator.ClassificationEvaluatorParams">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">ClassificationEvaluatorParams</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_splitter</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../data.html#sensai.data.DataSplitter" title="sensai.data.DataSplitter"><span class="pre">sensai.data.DataSplitter</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_test_fraction</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">float</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_random_seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">42</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">additional_metrics</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Sequence</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="eval_stats/eval_stats_classification.html#sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric" title="sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric"><span class="pre">sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_probabilities</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">binary_positive_label</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">('__guess',)</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/evaluation/evaluator.py#L366"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.evaluation.evaluator.ClassificationEvaluatorParams" title="Permalink to this definition"></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">ClassificationEvaluatorParams</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_splitter</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../data.html#sensai.data.DataSplitter" title="sensai.data.DataSplitter"><span class="pre">sensai.data.DataSplitter</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_test_fraction</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">float</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_random_seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">42</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">additional_metrics</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Sequence</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="eval_stats/eval_stats_classification.html#sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric" title="sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric"><span class="pre">sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_probabilities</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">binary_positive_label</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">('__guess',)</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/evaluation/evaluator.py#L366"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.evaluation.evaluator.ClassificationEvaluatorParams" title="Permalink to this definition"></a></dt>
 <dd><p>Bases: <a class="reference internal" href="#sensai.evaluation.evaluator.EvaluatorParams" title="sensai.evaluation.evaluator.EvaluatorParams"><code class="xref py py-class docutils literal notranslate"><span class="pre">sensai.evaluation.evaluator.EvaluatorParams</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="sensai.evaluation.evaluator.ClassificationEvaluatorParams.__init__">
-<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_splitter</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../data.html#sensai.data.DataSplitter" title="sensai.data.DataSplitter"><span class="pre">sensai.data.DataSplitter</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_test_fraction</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">float</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_random_seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">42</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">additional_metrics</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Sequence</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="eval_stats/eval_stats_classification.html#sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric" title="sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric"><span class="pre">sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_probabilities</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">binary_positive_label</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">('__guess',)</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#sensai.evaluation.evaluator.ClassificationEvaluatorParams.__init__" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data_splitter</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="../data.html#sensai.data.DataSplitter" title="sensai.data.DataSplitter"><span class="pre">sensai.data.DataSplitter</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_test_fraction</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">float</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_random_seed</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">42</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fractional_split_shuffle</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">additional_metrics</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Sequence</span><span class="p"><span class="pre">[</span></span><a class="reference internal" href="eval_stats/eval_stats_classification.html#sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric" title="sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric"><span class="pre">sensai.evaluation.eval_stats.eval_stats_classification.ClassificationMetric</span></a><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_probabilities</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">binary_positive_label</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">('__guess',)</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#sensai.evaluation.evaluator.ClassificationEvaluatorParams.__init__" title="Permalink to this definition"></a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
 <dd class="field-odd"><ul class="simple">
diff --git a/docs/sensai/util/cache.html b/docs/sensai/util/cache.html
index 0c474620..9b0ad36c 100644
--- a/docs/sensai/util/cache.html
+++ b/docs/sensai/util/cache.html
@@ -678,7 +678,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="sensai.util.cache.LoadSaveInterface">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">LoadSaveInterface</span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/cache.py#L754"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.cache.LoadSaveInterface" title="Permalink to this definition"></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">LoadSaveInterface</span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/cache.py#L756"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.cache.LoadSaveInterface" title="Permalink to this definition"></a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">abc.ABC</span></code></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="sensai.util.cache.LoadSaveInterface.save">
@@ -694,7 +694,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="sensai.util.cache.PickleLoadSaveMixin">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">PickleLoadSaveMixin</span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/cache.py#L765"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.cache.PickleLoadSaveMixin" title="Permalink to this definition"></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">PickleLoadSaveMixin</span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/cache.py#L767"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.cache.PickleLoadSaveMixin" title="Permalink to this definition"></a></dt>
 <dd><p>Bases: <a class="reference internal" href="#sensai.util.cache.LoadSaveInterface" title="sensai.util.cache.LoadSaveInterface"><code class="xref py py-class docutils literal notranslate"><span class="pre">sensai.util.cache.LoadSaveInterface</span></code></a></p>
 <dl class="py method">
 <dt class="sig sig-object py" id="sensai.util.cache.PickleLoadSaveMixin.save">
@@ -704,7 +704,7 @@
 <dt class="field-odd">Parameters</dt>
 <dd class="field-odd"><ul class="simple">
 <li><p><strong>path</strong> – </p></li>
-<li><p><strong>backend</strong> – pickle or joblib</p></li>
+<li><p><strong>backend</strong> – pickle, cloudpickle, or joblib</p></li>
 </ul>
 </dd>
 </dl>
@@ -718,7 +718,7 @@
 <dt class="field-odd">Parameters</dt>
 <dd class="field-odd"><ul class="simple">
 <li><p><strong>path</strong> – </p></li>
-<li><p><strong>backend</strong> – pickle or joblib</p></li>
+<li><p><strong>backend</strong> – pickle, cloudpickle, or joblib</p></li>
 </ul>
 </dd>
 <dt class="field-even">Returns</dt>
diff --git a/docs/sensai/util/logging.html b/docs/sensai/util/logging.html
index 8ffce86d..80577c32 100644
--- a/docs/sensai/util/logging.html
+++ b/docs/sensai/util/logging.html
@@ -160,23 +160,23 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.logging.set_configure_callback">
-<span class="sig-name descname"><span class="pre">set_configure_callback</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Callable</span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">None</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.set_configure_callback" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">set_configure_callback</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">callback</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Callable</span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">None</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">append</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L41"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.set_configure_callback" title="Permalink to this definition"></a></dt>
 <dd><p>Configures a function to be called when logging is configured, e.g. through <code class="xref py py-func docutils literal notranslate"><span class="pre">configure,</span> <span class="pre">:func:`run_main()</span></code> or
 <a class="reference internal" href="#sensai.util.logging.run_cli" title="sensai.util.logging.run_cli"><code class="xref py py-func docutils literal notranslate"><span class="pre">run_cli()</span></code></a>.
 A typical use for the callback is to configure the logging behaviour of packages, setting appropriate log levels.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Parameters</dt>
-<dd class="field-odd"><p><strong>callback</strong> – the function to cal</p>
-</dd>
-<dt class="field-even">Returns</dt>
-<dd class="field-even"><p></p>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>callback</strong> – the function to call</p></li>
+<li><p><strong>append</strong> – whether to append to the list of callbacks; if False, any existing callbacks will be removed</p></li>
+</ul>
 </dd>
 </dl>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.logging.configure">
-<span class="sig-name descname"><span class="pre">configure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'%(levelname)-5s</span> <span class="pre">%(asctime)-15s</span> <span class="pre">%(name)s:%(funcName)s</span> <span class="pre">-</span> <span class="pre">%(message)s'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L55"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.configure" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">configure</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'%(levelname)-5s</span> <span class="pre">%(asctime)-15s</span> <span class="pre">%(name)s:%(funcName)s</span> <span class="pre">-</span> <span class="pre">%(message)s'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L57"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.configure" title="Permalink to this definition"></a></dt>
 <dd><p>Configures logging to stdout with the given format and log level,
 also configuring the default log levels of some overly verbose libraries as well as some pandas output options.</p>
 <dl class="field-list simple">
@@ -191,7 +191,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.logging.run_main">
-<span class="sig-name descname"><span class="pre">run_main</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">main_fn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Callable</span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'%(levelname)-5s</span> <span class="pre">%(asctime)-15s</span> <span class="pre">%(name)s:%(funcName)s</span> <span class="pre">-</span> <span class="pre">%(message)s'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L76"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.run_main" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">run_main</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">main_fn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Callable</span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'%(levelname)-5s</span> <span class="pre">%(asctime)-15s</span> <span class="pre">%(name)s:%(funcName)s</span> <span class="pre">-</span> <span class="pre">%(message)s'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L78"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.run_main" title="Permalink to this definition"></a></dt>
 <dd><p>Configures logging with the given parameters, ensuring that any exceptions that occur during
 the execution of the given function are logged.
 Logs two additional messages, one before the execution of the function, and one upon its completion.</p>
@@ -211,7 +211,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.logging.run_cli">
-<span class="sig-name descname"><span class="pre">run_cli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">main_fn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Callable</span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'%(levelname)-5s</span> <span class="pre">%(asctime)-15s</span> <span class="pre">%(name)s:%(funcName)s</span> <span class="pre">-</span> <span class="pre">%(message)s'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L97"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.run_cli" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">run_cli</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">main_fn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Callable</span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">[</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">format</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'%(levelname)-5s</span> <span class="pre">%(asctime)-15s</span> <span class="pre">%(name)s:%(funcName)s</span> <span class="pre">-</span> <span class="pre">%(message)s'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L99"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.run_cli" title="Permalink to this definition"></a></dt>
 <dd><p>Configures logging with the given parameters and runs the given main function as a
 CLI using <cite>jsonargparse</cite> (which is configured to also parse attribute docstrings, such
 that dataclasses can be used as function arguments).
@@ -234,7 +234,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.logging.datetime_tag">
-<span class="sig-name descname"><span class="pre">datetime_tag</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">str</span></span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L117"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.datetime_tag" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">datetime_tag</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">str</span></span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L119"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.datetime_tag" title="Permalink to this definition"></a></dt>
 <dd><dl class="field-list simple">
 <dt class="field-odd">Returns</dt>
 <dd class="field-odd"><p>a string tag for use in log file names which contains the current date and time (compact but readable)</p>
@@ -244,24 +244,24 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.logging.add_file_logger">
-<span class="sig-name descname"><span class="pre">add_file_logger</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">register_atexit</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L134"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.add_file_logger" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">add_file_logger</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">register_atexit</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L136"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.add_file_logger" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.logging.add_memory_logger">
-<span class="sig-name descname"><span class="pre">add_memory_logger</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L147"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.add_memory_logger" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">add_memory_logger</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L149"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.add_memory_logger" title="Permalink to this definition"></a></dt>
 <dd><p>Enables in-memory logging (if it is not already enabled), i.e. all log statements are written to a memory buffer and can later be
 read via function <cite>get_memory_log()</cite></p>
 </dd></dl>
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.logging.get_memory_log">
-<span class="sig-name descname"><span class="pre">get_memory_log</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L161"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.get_memory_log" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">get_memory_log</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L163"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.get_memory_log" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="sensai.util.logging.StopWatch">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">StopWatch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">start</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L165"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.StopWatch" title="Permalink to this definition"></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">StopWatch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">start</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L167"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.StopWatch" title="Permalink to this definition"></a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
 <p>Represents a stop watch for timing an execution. Constructing an instance starts the stopwatch.</p>
 <dl class="py method">
@@ -334,7 +334,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="sensai.util.logging.StopWatchManager">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">StopWatchManager</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">secret</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L239"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.StopWatchManager" title="Permalink to this definition"></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">StopWatchManager</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">secret</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L241"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.StopWatchManager" title="Permalink to this definition"></a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
 <p>A singleton which manages a pool of named stopwatches, such that executions to be timed by referring to a name only -
 without the need for a limited scope.</p>
@@ -375,7 +375,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="sensai.util.logging.LogTime">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">LogTime</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logger</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">logging.Logger</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L273"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.LogTime" title="Permalink to this definition"></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">LogTime</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">logger</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">logging.Logger</span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L275"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.LogTime" title="Permalink to this definition"></a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
 <p>An execution time logger which can be conveniently applied using a with-statement - in order to log the executing time of the respective
 with-block.</p>
@@ -410,7 +410,7 @@
 
 <dl class="py class">
 <dt class="sig sig-object py" id="sensai.util.logging.FileLoggerContext">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">FileLoggerContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L314"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.FileLoggerContext" title="Permalink to this definition"></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">FileLoggerContext</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enabled</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/logging.py#L316"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.logging.FileLoggerContext" title="Permalink to this definition"></a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
 <p>A context handler to be used in conjunction with Python’s <cite>with</cite> statement which enables file-based logging.</p>
 <dl class="py method">
diff --git a/docs/sensai/util/pickle.html b/docs/sensai/util/pickle.html
index 09c99c1d..6fcc50f6 100644
--- a/docs/sensai/util/pickle.html
+++ b/docs/sensai/util/pickle.html
@@ -149,12 +149,12 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.pickle.dump_pickle">
-<span class="sig-name descname"><span class="pre">dump_pickle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">pathlib.Path</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'pickle'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/pickle.py#L36"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.pickle.dump_pickle" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">dump_pickle</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pickle_path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Union</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">pathlib.Path</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">backend</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'pickle'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">protocol</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">4</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/pickle.py#L42"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.pickle.dump_pickle" title="Permalink to this definition"></a></dt>
 <dd></dd></dl>
 
 <dl class="py class">
 <dt class="sig sig-object py" id="sensai.util.pickle.PickleFailureDebugger">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">PickleFailureDebugger</span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/pickle.py#L62"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.pickle.PickleFailureDebugger" title="Permalink to this definition"></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">PickleFailureDebugger</span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/pickle.py#L71"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.pickle.PickleFailureDebugger" title="Permalink to this definition"></a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
 <p>A collection of methods for testing whether objects can be pickled and logging useful infos in case they cannot</p>
 <dl class="py attribute">
@@ -197,7 +197,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.pickle.setstate">
-<span class="sig-name descname"><span class="pre">setstate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cls</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">renamed_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new_optional_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new_default_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">removed_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/pickle.py#L141"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.pickle.setstate" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">setstate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cls</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">renamed_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new_optional_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new_default_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">removed_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/pickle.py#L154"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.pickle.setstate" title="Permalink to this definition"></a></dt>
 <dd><p>Helper function for safe implementations of __setstate__ in classes, which appropriately handles the cases where
 a parent class already implements __setstate__ and where it does not. Call this function whenever you would actually
 like to call the super-class’ implementation.
@@ -219,7 +219,7 @@
 
 <dl class="py function">
 <dt class="sig sig-object py" id="sensai.util.pickle.getstate">
-<span class="sig-name descname"><span class="pre">getstate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cls</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transient_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Iterable</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">excluded_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Iterable</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">override_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">excluded_default_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/pickle.py#L188"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.pickle.getstate" title="Permalink to this definition"></a></dt>
+<span class="sig-name descname"><span class="pre">getstate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">cls</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">obj</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">transient_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Iterable</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">excluded_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Iterable</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">override_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">excluded_default_properties</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Any</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference external" href="https://github.com/jambit/sensAI/blob/master/src/sensai/util/pickle.py#L203"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#sensai.util.pickle.getstate" title="Permalink to this definition"></a></dt>
 <dd><p>Helper function for safe implementations of __getstate__ in classes, which appropriately handles the cases where
 a parent class already implements __getstate__ and where it does not. Call this function whenever you would actually
 like to call the super-class’ implementation.