Skip to content

Commit dd5e8b4

Browse files
mzwiesselemzwiessele
committed
[notebooks] run and updated for new GPy to come
1 parent 0c301d2 commit dd5e8b4

18 files changed

+67458
-82428
lines changed

‎GPy/ParametricNonParametricInference.ipynb

+15-15
Large diffs are not rendered by default.

‎GPy/Poisson regression tutorial.ipynb

+29-29
Large diffs are not rendered by default.

‎GPy/SVI.ipynb

+21,149-21,145
Large diffs are not rendered by default.

‎GPy/basic_classification.ipynb

+36,895-36,531
Large diffs are not rendered by default.

‎GPy/basic_gp.ipynb

+39-39
Original file line numberDiff line numberDiff line change
@@ -159,7 +159,7 @@
159159
"\n",
160160
"<p class=pd>\n",
161161
"<b>Model</b>: GP regression<br>\n",
162-
"<b>Objective</b>: 22.5774452129<br>\n",
162+
"<b>Objective</b>: 22.9717924697<br>\n",
163163
"<b>Number of Parameters</b>: 3<br>\n",
164164
"<b>Number of Optimization Parameters</b>: 3<br>\n",
165165
"<b>Updates</b>: True<br>\n",
@@ -179,7 +179,7 @@
179179
"</table>"
180180
],
181181
"text/plain": [
182-
"<GPy.models.gp_regression.GPRegression at 0x7fd232dca750>"
182+
"<GPy.models.gp_regression.GPRegression at 0x7fd96a202690>"
183183
]
184184
},
185185
"metadata": {},
@@ -264,32 +264,32 @@
264264
"name": "stdout",
265265
"output_type": "stream",
266266
"text": [
267-
"Optimization restart 1/10, f = -14.9522903397\n",
268-
"Optimization restart 2/10, f = -14.9522903397\n",
269-
"Optimization restart 3/10, f = -14.9522903391\n",
270-
"Optimization restart 4/10, f = -14.9522903397\n",
271-
"Optimization restart 5/10, f = -14.9522903396\n",
272-
"Optimization restart 6/10, f = -14.9522903397\n",
273-
"Optimization restart 7/10, f = -14.9522903397\n",
274-
"Optimization restart 8/10, f = -14.9522903397\n",
275-
"Optimization restart 9/10, f = -14.9522903397\n",
276-
"Optimization restart 10/10, f = -14.9522903397\n"
267+
"Optimization restart 1/10, f = -15.1436482683\n",
268+
"Optimization restart 2/10, f = -15.1436482683\n",
269+
"Optimization restart 3/10, f = -15.1436482682\n",
270+
"Optimization restart 4/10, f = -15.1436482682\n",
271+
"Optimization restart 5/10, f = -15.1436482682\n",
272+
"Optimization restart 6/10, f = -15.1436482682\n",
273+
"Optimization restart 7/10, f = -15.1436482683\n",
274+
"Optimization restart 8/10, f = -15.1436482682\n",
275+
"Optimization restart 9/10, f = -15.1436482683\n",
276+
"Optimization restart 10/10, f = -15.1436482683\n"
277277
]
278278
},
279279
{
280280
"data": {
281281
"text/plain": [
282-
"[<paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e06390>,\n",
283-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e32bd0>,\n",
284-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e901d0>,\n",
285-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e063d0>,\n",
286-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232dcaf10>,\n",
287-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e328d0>,\n",
288-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e32c90>,\n",
289-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e32b90>,\n",
290-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e32ad0>,\n",
291-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e90210>,\n",
292-
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd232e32d10>]"
282+
"[<paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a244210>,\n",
283+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a388810>,\n",
284+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a3b3250>,\n",
285+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a244350>,\n",
286+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a388b90>,\n",
287+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a388c10>,\n",
288+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a388850>,\n",
289+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a388c50>,\n",
290+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a388c90>,\n",
291+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a202e90>,\n",
292+
" <paramz.optimization.optimization.opt_lbfgsb at 0x7fd96a388ad0>]"
293293
]
294294
},
295295
"execution_count": 11,
@@ -330,7 +330,7 @@
330330
"\n",
331331
"<p class=pd>\n",
332332
"<b>Model</b>: GP regression<br>\n",
333-
"<b>Objective</b>: -14.9522903397<br>\n",
333+
"<b>Objective</b>: -15.1436482683<br>\n",
334334
"<b>Number of Parameters</b>: 3<br>\n",
335335
"<b>Number of Optimization Parameters</b>: 3<br>\n",
336336
"<b>Updates</b>: True<br>\n",
@@ -344,13 +344,13 @@
344344
".tg .tg-right{font-family:\"Courier New\", Courier, monospace !important;font-weight:normal;text-align:right;}\n",
345345
"</style>\n",
346346
"<table class=\"tg\"><tr><th><b> GP_regression. </b></th><th><b> value</b></th><th><b>constraints</b></th><th><b>priors</b></th></tr>\n",
347-
"<tr><td class=tg-left> rbf.variance </td><td class=tg-right> 0.559999766514</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
348-
"<tr><td class=tg-left> rbf.lengthscale </td><td class=tg-right> 1.45696406073</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
349-
"<tr><td class=tg-left> Gaussian_noise.variance</td><td class=tg-right>0.00275791997688</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
347+
"<tr><td class=tg-left> rbf.variance </td><td class=tg-right> 1.35354271667</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
348+
"<tr><td class=tg-left> rbf.lengthscale </td><td class=tg-right> 1.94630136743</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
349+
"<tr><td class=tg-left> Gaussian_noise.variance</td><td class=tg-right>0.00248112830273</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
350350
"</table>"
351351
],
352352
"text/plain": [
353-
"<GPy.models.gp_regression.GPRegression at 0x7fd232dca750>"
353+
"<GPy.models.gp_regression.GPRegression at 0x7fd96a202690>"
354354
]
355355
},
356356
"metadata": {},
@@ -413,7 +413,7 @@
413413
"\n",
414414
"<p class=pd>\n",
415415
"<b>Model</b>: GP regression<br>\n",
416-
"<b>Objective</b>: -14.9522903397<br>\n",
416+
"<b>Objective</b>: -15.1436482683<br>\n",
417417
"<b>Number of Parameters</b>: 3<br>\n",
418418
"<b>Number of Optimization Parameters</b>: 3<br>\n",
419419
"<b>Updates</b>: True<br>\n",
@@ -427,13 +427,13 @@
427427
".tg .tg-right{font-family:\"Courier New\", Courier, monospace !important;font-weight:normal;text-align:right;}\n",
428428
"</style>\n",
429429
"<table class=\"tg\"><tr><th><b> GP_regression. </b></th><th><b> value</b></th><th><b>constraints</b></th><th><b>priors</b></th></tr>\n",
430-
"<tr><td class=tg-left> rbf.variance </td><td class=tg-right> 0.559999766514</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
431-
"<tr><td class=tg-left> rbf.lengthscale </td><td class=tg-right> 1.45696406073</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
432-
"<tr><td class=tg-left> Gaussian_noise.variance</td><td class=tg-right>0.00275791997688</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
430+
"<tr><td class=tg-left> rbf.variance </td><td class=tg-right> 1.35354271667</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
431+
"<tr><td class=tg-left> rbf.lengthscale </td><td class=tg-right> 1.94630136743</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
432+
"<tr><td class=tg-left> Gaussian_noise.variance</td><td class=tg-right>0.00248112830273</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
433433
"</table>"
434434
],
435435
"text/plain": [
436-
"<GPy.models.gp_regression.GPRegression at 0x7fd232dca750>"
436+
"<GPy.models.gp_regression.GPRegression at 0x7fd96a202690>"
437437
]
438438
},
439439
"metadata": {},
@@ -518,7 +518,7 @@
518518
"\n",
519519
"<p class=pd>\n",
520520
"<b>Model</b>: GP regression<br>\n",
521-
"<b>Objective</b>: -25.8853039459<br>\n",
521+
"<b>Objective</b>: -24.7900663215<br>\n",
522522
"<b>Number of Parameters</b>: 5<br>\n",
523523
"<b>Number of Optimization Parameters</b>: 5<br>\n",
524524
"<b>Updates</b>: True<br>\n",
@@ -532,14 +532,14 @@
532532
".tg .tg-right{font-family:\"Courier New\", Courier, monospace !important;font-weight:normal;text-align:right;}\n",
533533
"</style>\n",
534534
"<table class=\"tg\"><tr><th><b> GP_regression. </b></th><th><b> value</b></th><th><b>constraints</b></th><th><b>priors</b></th></tr>\n",
535-
"<tr><td class=tg-left> sum.Mat52.variance </td><td class=tg-right> 0.313961135834</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
535+
"<tr><td class=tg-left> sum.Mat52.variance </td><td class=tg-right> 0.361421808902</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
536536
"<tr><td class=tg-left> sum.Mat52.lengthscale </td><td class=tg-right> (2,)</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
537-
"<tr><td class=tg-left> sum.white.variance </td><td class=tg-right>0.000921807350829</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
538-
"<tr><td class=tg-left> Gaussian_noise.variance</td><td class=tg-right>0.000921807350829</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
537+
"<tr><td class=tg-left> sum.white.variance </td><td class=tg-right>0.000644606566433</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
538+
"<tr><td class=tg-left> Gaussian_noise.variance</td><td class=tg-right>0.000644606566433</td><td class=tg-center> +ve </td><td class=tg-center> </td></tr>\n",
539539
"</table>"
540540
],
541541
"text/plain": [
542-
"<GPy.models.gp_regression.GPRegression at 0x7fd232e4bf50>"
542+
"<GPy.models.gp_regression.GPRegression at 0x7fd96a278e90>"
543543
]
544544
},
545545
"metadata": {},
@@ -575,7 +575,7 @@
575575
"cell_type": "markdown",
576576
"metadata": {},
577577
"source": [
578-
"##Plotting slices\n",
578+
"## Plotting slices\n",
579579
"To see the uncertaintly associated with the above predictions, we can plot slices through the surface. this is done by passing the optional `fixed_inputs` argument to the plot function. `fixed_inputs` is a list of tuples containing which of the inputs to fix, and to which value.\n",
580580
"\n",
581581
"To get horixontal slices of the above GP, we'll fix second (index 1) input to -1, 0, and 1.5:"

0 commit comments

Comments
 (0)