Skip to content

Commit ff1227b

Browse files
junpenglaojunpenglao
authored
Restructure docs.pymc.io, add developer guide (#3311)
* [WIP] Restructure docs.pymc.io, add developer guide Following #3303, this is a further restructure of our website. - Tutorial page include all our high level API guides (including theano.rst, prod_dist.rst, gp.rst etc) - renaming of some notebooks (some of them does not have title) - notebooks might appear under more than 1 categories (if it covers multiple topics) * Further formatting * Add developer guide * edit developer guide * small formatting * further formatting * final formatting * really final formatting * fix links * small edit + another proof reading * formatting
1 parent fc523cc commit ff1227b

11 files changed

+1200
-100
lines changed

‎docs/source/conf.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -147,6 +147,7 @@
147147
("Examples", "nb_examples/index"),
148148
("Books + Videos", "learn"),
149149
("API", "api"),
150+
("Developer Guide", "developer_guide"),
150151
("About PyMC3", "history")
151152
],
152153
# "fixed_sidebar": "false",

‎docs/source/developer_guide.rst

Lines changed: 1107 additions & 0 deletions
Large diffs are not rendered by default.

‎docs/source/index.rst

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,10 +10,10 @@
1010
<h3 class="ui header">Friendly modelling API</h3>
1111
<p>PyMC3 allows you to write down models using an intuitive syntax to describe a data generating
1212
process.</p>
13-
<h3 class="ui header">Cutting edge algorithms</h3>
13+
<h3 class="ui header">Cutting edge algorithms and model building blocks</h3>
1414
<p>Fit your model using gradient-based MCMC algorithms like NUTS, using ADVI for fast approximate
1515
inference &mdash; including minibatch-ADVI for scaling to large datasets &mdash; or using
16-
Gaussian processes to fit a regression model.</p>
16+
Gaussian processes to build Bayesian nonparametric models.</p>
1717
</div>
1818
<div class="eight wide right floated column">
1919

‎docs/source/notebooks/GLM.ipynb

Lines changed: 5 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
"cell_type": "markdown",
55
"metadata": {},
66
"source": [
7-
"# GLM: Linear Regression"
7+
"# (Generalized) Linear and Hierarchical Linear Models in PyMC3"
88
]
99
},
1010
{
@@ -28,8 +28,7 @@
2828
"cell_type": "markdown",
2929
"metadata": {},
3030
"source": [
31-
"Simple example\n",
32-
"==============\n",
31+
"## Linear Regression\n",
3332
"\n",
3433
"Lets generate some data with known slope and intercept and fit a simple linear GLM."
3534
]
@@ -146,8 +145,7 @@
146145
"cell_type": "markdown",
147146
"metadata": {},
148147
"source": [
149-
"Robust GLM\n",
150-
"==========\n",
148+
"## Robust GLM\n",
151149
"\n",
152150
"Lets try the same model but with a few outliers in the data."
153151
]
@@ -255,7 +253,7 @@
255253
"cell_type": "markdown",
256254
"metadata": {},
257255
"source": [
258-
"# Hierarchical GLM"
256+
"## Hierarchical GLM"
259257
]
260258
},
261259
{
@@ -452,7 +450,7 @@
452450
"cell_type": "markdown",
453451
"metadata": {},
454452
"source": [
455-
"# Logistic Regression"
453+
"## Logistic Regression"
456454
]
457455
},
458456
{

‎docs/source/notebooks/MvGaussianRandomWalk_demo.ipynb

Lines changed: 16 additions & 36 deletions
Large diffs are not rendered by default.

‎docs/source/notebooks/api_quickstart.ipynb

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
"cell_type": "markdown",
55
"metadata": {},
66
"source": [
7-
"# API quickstart"
7+
"# General API quickstart"
88
]
99
},
1010
{

‎docs/source/notebooks/cox_model.ipynb

Lines changed: 8 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,12 @@
11
{
22
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"metadata": {},
6+
"source": [
7+
"# Cox model"
8+
]
9+
},
310
{
411
"cell_type": "code",
512
"execution_count": 1,
@@ -284,7 +291,7 @@
284291
"name": "python",
285292
"nbconvert_exporter": "python",
286293
"pygments_lexer": "ipython3",
287-
"version": "3.6.1"
294+
"version": "3.6.5"
288295
},
289296
"latex_envs": {
290297
"bibliofile": "biblio.bib",

‎docs/source/notebooks/gaussian_process.ipynb

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
"cell_type": "markdown",
55
"metadata": {},
66
"source": [
7-
"# Gaussian Processes\n",
7+
"# Gaussian Processes using numpy kernel\n",
88
"\n",
99
"(c) 2016 by Chris Fonnesbeck"
1010
]

‎docs/source/notebooks/table_of_contents_examples.js

Lines changed: 41 additions & 38 deletions
Original file line numberDiff line numberDiff line change
@@ -1,21 +1,27 @@
11
Gallery.contents = {
2-
"AR": "Time Series",
3-
"BEST": "Applied",
4-
"Bayes_factor": "Other",
5-
"Diagnosing_biased_Inference_with_Divergences": "Diagnostics",
6-
"Euler-Maruyama_and_SDEs": "Time Series",
7-
"GLM-hierarchical-advi-minibatch": "Variational Inference",
8-
"GLM-hierarchical-binominal-model": "GLMs",
9-
"GLM-hierarchical": "GLMs",
10-
"GLM-linear": "GLMs",
11-
"GLM-logistic": "GLMs",
12-
"GLM-model-selection": "GLMs",
13-
"GLM-negative-binomial-regression": "GLMs",
14-
"GLM-poisson-regression": "GLMs",
15-
"GLM-robust-with-outlier-detection": "GLMs",
16-
"GLM-robust": "GLMs",
17-
"GLM-rolling-regression": "GLMs",
18-
"GLM": "GLMs",
2+
"BEST": "Case Studies",
3+
"LKJ": "Case Studies",
4+
"dawid-skene": "Case Studies",
5+
"stochastic_volatility": "Case Studies",
6+
"rugby_analytics": "Case Studies",
7+
"multilevel_modeling": "Case Studies",
8+
"Diagnosing_biased_Inference_with_Divergences": "Diagnostics and Model Criticism",
9+
"model_comparison": "Diagnostics and Model Criticism",
10+
"posterior_predictive": "Diagnostics and Model Criticism",
11+
"Bayes_factor": "Diagnostics and Model Criticism",
12+
"GLM": "(Generalized) Linear and Hierarchical Linear Models",
13+
"GLM-linear": "(Generalized) Linear and Hierarchical Linear Models",
14+
"GLM-logistic": "(Generalized) Linear and Hierarchical Linear Models",
15+
"GLM-hierarchical-binominal-model": "(Generalized) Linear and Hierarchical Linear Models",
16+
"GLM-hierarchical": "(Generalized) Linear and Hierarchical Linear Models",
17+
"hierarchical_partial_pooling": "(Generalized) Linear and Hierarchical Linear Models",
18+
"GLM-model-selection": "(Generalized) Linear and Hierarchical Linear Models",
19+
"GLM-negative-binomial-regression": "(Generalized) Linear and Hierarchical Linear Models",
20+
"GLM-poisson-regression": "(Generalized) Linear and Hierarchical Linear Models",
21+
"GLM-robust-with-outlier-detection": "(Generalized) Linear and Hierarchical Linear Models",
22+
"GLM-robust": "(Generalized) Linear and Hierarchical Linear Models",
23+
"GLM-rolling-regression": "(Generalized) Linear and Hierarchical Linear Models",
24+
"GLM-hierarchical-advi-minibatch": "(Generalized) Linear and Hierarchical Linear Models",
1925
"GP-Kron": "Gaussian Processes",
2026
"GP-Latent": "Gaussian Processes",
2127
"GP-Marginal": "Gaussian Processes",
@@ -26,32 +32,29 @@ Gallery.contents = {
2632
"GP-TProcess": "Gaussian Processes",
2733
"GP-slice-sampling": "Gaussian Processes",
2834
"GP-smoothing": "Gaussian Processes",
29-
"MvGaussianRandomWalk_demo": "Time Series",
30-
"SMC2_gaussians": "Other",
31-
"bayes_param_survival_pymc3": "Survival Analysis",
32-
"bayesian_neural_network_advi": "Variational Inference",
33-
"bayesian_neural_network_with_sgfs": "Stochastic Gradients",
34-
"censored_data": "Survival Analysis",
35-
"constant_stochastic_gradient": "Stochastic Gradients",
36-
"convolutional_vae_keras_advi": "Variational Inference",
37-
"cox_model": "Other",
38-
"dawid-skene": "Applied",
35+
"gaussian_process": "Gaussian Processes",
3936
"dependent_density_regression": "Mixture Models",
4037
"dp_mix": "Mixture Models",
41-
"empirical-approx-overview": "Variational Inference",
4238
"gaussian-mixture-model-advi": "Mixture Models",
4339
"gaussian_mixture_model": "Mixture Models",
44-
"gaussian_process": "Gaussian Processes",
45-
"hierarchical_partial_pooling": "GLMs",
46-
"lda-advi-aevb": "Variational Inference",
4740
"marginalized_gaussian_mixture_model": "Mixture Models",
48-
"model_comparison": "Diagnostics",
49-
"multilevel_modeling": "Applied",
50-
"normalizing_flows_overview": "Variational Inference",
51-
"posterior_predictive": "Diagnostics",
52-
"rugby_analytics": "Applied",
41+
"SMC2_gaussians": "Simulation-based Inference",
42+
"bayesian_neural_network_with_sgfs": "Stochastic Gradients",
43+
"constant_stochastic_gradient": "Stochastic Gradients",
5344
"sgfs_simple_optimization": "Stochastic Gradients",
54-
"stochastic_volatility": "Applied",
45+
"bayes_param_survival_pymc3": "Survival Analysis",
46+
"censored_data": "Survival Analysis",
5547
"survival_analysis": "Survival Analysis",
56-
"weibull_aft": "Survival Analysis"
48+
"weibull_aft": "Survival Analysis",
49+
"cox_model": "Survival Analysis",
50+
"MvGaussianRandomWalk_demo": "Time Series",
51+
"AR": "Time Series",
52+
"Euler-Maruyama_and_SDEs": "Time Series",
53+
"bayesian_neural_network_advi": "Variational Inference",
54+
"convolutional_vae_keras_advi": "Variational Inference",
55+
"empirical-approx-overview": "Variational Inference",
56+
"lda-advi-aevb": "Variational Inference",
57+
"normalizing_flows_overview": "Variational Inference",
58+
"gaussian-mixture-model-advi": "Variational Inference",
59+
"GLM-hierarchical-advi-minibatch": "Variational Inference"
5760
}

‎docs/source/notebooks/table_of_contents_tutorials.js

Lines changed: 15 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,16 +1,20 @@
11
Gallery.contents = {
22
"api_quickstart": "Basics",
3-
"getting_started": "Basics",
4-
"sampler-stats": "Basics",
5-
"sampling_compound_step": "Basics",
6-
"howto_debugging": "Basics",
7-
"live_sample_plots": "How-To",
3+
"variational_api_quickstart": "Basics",
4+
"theano": "Basics",
5+
"prob_dists": "Basics",
6+
"gp": "Basics",
7+
"sampling_compound_step": "Deep dives",
8+
"sampler-stats": "Deep dives",
9+
"Diagnosing_biased_Inference_with_Divergences": "Deep dives",
10+
"advanced_theano": "Deep dives",
11+
"getting_started": "Deep dives",
12+
"PyMC3_tips_and_heuristic": "How-To",
13+
"blackbox_external_likelihood": "How-To",
814
"profiling": "How-To",
9-
"updating_priors": "How-To",
10-
"lasso_block_update": "How-To",
15+
"howto_debugging": "How-To",
1116
"model_averaging": "How-To",
12-
"blackbox_external_likelihood": "How-To",
13-
"LKJ": "How-To",
14-
"variational_api_quickstart": "How-To",
15-
"PyMC3_tips_and_heuristic": "How-To"
17+
"updating_priors": "How-To",
18+
"live_sample_plots": "How-To",
19+
"lasso_block_update": "How-To"
1620
}

‎docs/source/prob_dists.rst

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,8 @@
11
.. _prob_dists:
22

3-
*************************
4-
Probability Distributions
5-
*************************
3+
**********************************
4+
Probability Distributions in PyMC3
5+
**********************************
66

77
The most fundamental step in building Bayesian models is the specification of a full probability model for the problem at hand. This primarily involves assigning parametric statistical distributions to unknown quantities in the model, in addition to appropriate functional forms for likelihoods to represent the information from the data. To this end, PyMC3 includes a comprehensive set of pre-defined statistical distributions that can be used as model building blocks.
88

0 commit comments

Comments
 (0)