added wiki to tutorial

ContextLab · Apr 18, 2018 · c267b3d · c267b3d
1 parent 04b8697
commit c267b3d
Show file tree

Hide file tree

Showing 20 changed files with 78 additions and 26 deletions.
diff --git a/docs/tutorials/cluster.rst b/docs/tutorials/cluster.rst
@@ -247,7 +247,7 @@ We can further examine the number of datapoints assigned each label.
 
 .. parsed-literal::
 
-    Counter({0: 1761, 1: 5067, 2: 1296})
+    Counter({0: 1296, 1: 5067, 2: 1761})
 
 
 

diff --git a/docs/tutorials/cluster_files/cluster_20_0.png b/docs/tutorials/cluster_files/cluster_20_0.png
diff --git a/docs/tutorials/geo.rst b/docs/tutorials/geo.rst
@@ -48,7 +48,7 @@ We can plot a ``geo`` by calling the plot method
 
 .. parsed-literal::
 
-    <hypertools.datageometry.DataGeometry at 0x10d457048>
+    <hypertools.datageometry.DataGeometry at 0x11bcd9080>
 
 
 
@@ -351,7 +351,7 @@ First, let's plot without making any changes.
 
 .. parsed-literal::
 
-    <hypertools.datageometry.DataGeometry at 0x10d5bd4a8>
+    <hypertools.datageometry.DataGeometry at 0x11be41588>
 
 
 
@@ -374,7 +374,7 @@ specified by the reduce model set to 2.
 
 .. parsed-literal::
 
-    <hypertools.datageometry.DataGeometry at 0x10d9c4e10>
+    <hypertools.datageometry.DataGeometry at 0x11c2ddcf8>
 
 
 

diff --git a/docs/tutorials/normalize_files/normalize_13_0.png b/docs/tutorials/normalize_files/normalize_13_0.png
diff --git a/docs/tutorials/normalize_files/normalize_16_0.png b/docs/tutorials/normalize_files/normalize_16_0.png
diff --git a/docs/tutorials/normalize_files/normalize_18_0.png b/docs/tutorials/normalize_files/normalize_18_0.png
diff --git a/docs/tutorials/normalize_files/normalize_8_0.png b/docs/tutorials/normalize_files/normalize_8_0.png
diff --git a/docs/tutorials/plot.rst b/docs/tutorials/plot.rst
@@ -536,6 +536,6 @@ transformed to a topic vector and then reduced for plotting.
 
 .. parsed-literal::
 
-    <hypertools.datageometry.DataGeometry at 0x116a621d0>
+    <hypertools.datageometry.DataGeometry at 0x11448fcc0>
 
 
diff --git a/docs/tutorials/plot_files/plot_22_0.png b/docs/tutorials/plot_files/plot_22_0.png
diff --git a/docs/tutorials/plot_files/plot_31_1.png b/docs/tutorials/plot_files/plot_31_1.png
diff --git a/docs/tutorials/plot_files/plot_37_0.png b/docs/tutorials/plot_files/plot_37_0.png
diff --git a/docs/tutorials/text.ipynb b/docs/tutorials/text.ipynb
@@ -57,7 +57,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "dog[0][:1000]"
@@ -73,7 +75,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "hue=['dog']*chunk_size+['cat']*chunk_size\n",
@@ -90,7 +94,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "bball_text = wiki.page('Basketball').content\n",
@@ -120,6 +126,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
+    "collapsed": true,
     "scrolled": false
    },
    "outputs": [],
@@ -128,6 +135,30 @@
     "nips.plot(size=[8, 6])"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Visualizing Wikipedia pages\n",
+    "\n",
+    "Here, we will plot a collection of wikipedia pages, transformed using a topic\n",
+    "model (the default 'wiki' model) that was fit on the same articles. We will\n",
+    "reduce the dimensionality of the data with TSNE, and then discover cluster with\n",
+    "the 'HDBSCAN' algorithm."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "wiki = hyp.load('wiki')\n",
+    "wiki.plot(size=[8, 6])"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -140,7 +171,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "sotus = hyp.load('sotus')\n",
@@ -159,7 +192,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "sotus.plot(reduce='UMAP', size=[10, 8])"
@@ -177,7 +212,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "sotus.plot(reduce='UMAP', corpus='nips', size=[10, 8])"

diff --git a/docs/tutorials/text.rst b/docs/tutorials/text.rst
@@ -93,26 +93,41 @@ example dataset can be loaded using the code below.
     nips.plot(size=[8, 6])
 
 
+
+.. image:: text_files/text_12_0.png
+
+
+
+
 .. parsed-literal::
 
-    /Users/andyheusser/Library/Enthought/Canopy_64bit/User/lib/python2.7/site-packages/tables/leaf.py:396: PerformanceWarning: The Leaf ``/data`` is exceeding the maximum recommended rowsize (104857600 bytes);
-    be ready to see PyTables asking for *lots* of memory and possibly slow
-    I/O.  You may want to reduce the rowsize by trimming the value of
-    dimensions that are orthogonal (and preferably close) to the *main*
-    dimension of this leave.  Alternatively, in case you have specified a
-    very small/large chunksize, you may want to increase/decrease it.
-      PerformanceWarning)
+    <hypertools.datageometry.DataGeometry at 0x10ebe1750>
+
+
+
+Visualizing Wikipedia pages
+---------------------------
+
+Here, we will plot a collection of wikipedia pages, transformed using a
+topic model (the default 'wiki' model) that was fit on the same
+articles. We will reduce the dimensionality of the data with TSNE, and
+then discover cluster with the 'HDBSCAN' algorithm.
 
+.. code:: ipython2
+
+    wiki = hyp.load('wiki')
+    wiki.plot(size=[8, 6])
 
 
-.. image:: text_files/text_12_1.png
+
+.. image:: text_files/text_14_0.png
 
 
 
 
 .. parsed-literal::
 
-    <hypertools.datageometry.DataGeometry at 0x11c7bdcd0>
+    <hypertools.datageometry.DataGeometry at 0x11db6e790>
 
 
 
@@ -134,14 +149,14 @@ the left and republicans mostly on the right).
 
 
 
-.. image:: text_files/text_14_0.png
+.. image:: text_files/text_16_0.png
 
 
 
 
 .. parsed-literal::
 
-    <hypertools.datageometry.DataGeometry at 0x1200e3750>
+    <hypertools.datageometry.DataGeometry at 0x117e040d0>
 
 
 
@@ -159,14 +174,14 @@ the data.
 
 
 
-.. image:: text_files/text_16_0.png
+.. image:: text_files/text_18_0.png
 
 
 
 
 .. parsed-literal::
 
-    <hypertools.datageometry.DataGeometry at 0x116c23050>
+    <hypertools.datageometry.DataGeometry at 0x11bf57610>
 
 
 
@@ -184,14 +199,14 @@ list of text samples) to train the model.
 
 
 
-.. image:: text_files/text_18_0.png
+.. image:: text_files/text_20_0.png
 
 
 
 
 .. parsed-literal::
 
-    <hypertools.datageometry.DataGeometry at 0x11e5976d0>
+    <hypertools.datageometry.DataGeometry at 0x11c0cf210>
 
 
 

diff --git a/docs/tutorials/text_files/text_12_0.png b/docs/tutorials/text_files/text_12_0.png
diff --git a/docs/tutorials/text_files/text_14_0.png b/docs/tutorials/text_files/text_14_0.png
diff --git a/docs/tutorials/text_files/text_16_0.png b/docs/tutorials/text_files/text_16_0.png
diff --git a/docs/tutorials/text_files/text_18_0.png b/docs/tutorials/text_files/text_18_0.png
diff --git a/docs/tutorials/text_files/text_20_0.png b/docs/tutorials/text_files/text_20_0.png
diff --git a/docs/tutorials/text_files/text_7_0.png b/docs/tutorials/text_files/text_7_0.png
diff --git a/docs/tutorials/text_files/text_9_0.png b/docs/tutorials/text_files/text_9_0.png
Original file line number	Diff line number	Diff line change
Expand Up		@@ -247,7 +247,7 @@ We can further examine the number of datapoints assigned each label.

		.. parsed-literal::

		Counter({0: 1761, 1: 5067, 2: 1296})
		Counter({0: 1296, 1: 5067, 2: 1761})



Expand Down
Original file line number	Diff line number	Diff line change
Expand Up		@@ -536,6 +536,6 @@ transformed to a topic vector and then reduced for plotting.

		.. parsed-literal::

		<hypertools.datageometry.DataGeometry at 0x116a621d0>
		<hypertools.datageometry.DataGeometry at 0x11448fcc0>