update sphinx docs

erdogant · Mar 6, 2024 · bbd82b0 · bbd82b0
1 parent 473ecac
commit bbd82b0
Show file tree

Hide file tree

Showing 70 changed files with 624 additions and 512 deletions.
diff --git a/docs/pages/doctrees/Continuous Data.doctree b/docs/pages/doctrees/Continuous Data.doctree
diff --git a/docs/pages/doctrees/Create DAG.doctree b/docs/pages/doctrees/Create DAG.doctree
diff --git a/docs/pages/doctrees/Documentation.doctree b/docs/pages/doctrees/Documentation.doctree
diff --git a/docs/pages/doctrees/Example Datasets.doctree b/docs/pages/doctrees/Example Datasets.doctree
diff --git a/docs/pages/doctrees/Examples.doctree b/docs/pages/doctrees/Examples.doctree
diff --git a/docs/pages/doctrees/Inference.doctree b/docs/pages/doctrees/Inference.doctree
diff --git a/docs/pages/doctrees/Installation.doctree b/docs/pages/doctrees/Installation.doctree
diff --git a/docs/pages/doctrees/Introduction.doctree b/docs/pages/doctrees/Introduction.doctree
diff --git a/docs/pages/doctrees/Licence.doctree b/docs/pages/doctrees/Licence.doctree
diff --git a/docs/pages/doctrees/Parameter learning.doctree b/docs/pages/doctrees/Parameter learning.doctree
diff --git a/docs/pages/doctrees/Plot.doctree b/docs/pages/doctrees/Plot.doctree
diff --git a/docs/pages/doctrees/Predict.doctree b/docs/pages/doctrees/Predict.doctree
diff --git a/docs/pages/doctrees/Quickstart.doctree b/docs/pages/doctrees/Quickstart.doctree
diff --git a/docs/pages/doctrees/Sampling.doctree b/docs/pages/doctrees/Sampling.doctree
diff --git a/docs/pages/doctrees/Structure learning.doctree b/docs/pages/doctrees/Structure learning.doctree
diff --git a/docs/pages/doctrees/Structure_scores.doctree b/docs/pages/doctrees/Structure_scores.doctree
diff --git a/docs/pages/doctrees/UseCases.doctree b/docs/pages/doctrees/UseCases.doctree
diff --git a/docs/pages/doctrees/bnlearn.bnlearn.doctree b/docs/pages/doctrees/bnlearn.bnlearn.doctree
diff --git a/docs/pages/doctrees/bnlearn.inference.doctree b/docs/pages/doctrees/bnlearn.inference.doctree
diff --git a/docs/pages/doctrees/bnlearn.parameter_learning.doctree b/docs/pages/doctrees/bnlearn.parameter_learning.doctree
diff --git a/docs/pages/doctrees/bnlearn.structure_learning.doctree b/docs/pages/doctrees/bnlearn.structure_learning.doctree
diff --git a/docs/pages/doctrees/dataframe conversions.doctree b/docs/pages/doctrees/dataframe conversions.doctree
diff --git a/docs/pages/doctrees/environment.pickle b/docs/pages/doctrees/environment.pickle
diff --git a/docs/pages/doctrees/independence_test.doctree b/docs/pages/doctrees/independence_test.doctree
diff --git a/docs/pages/doctrees/index.doctree b/docs/pages/doctrees/index.doctree
diff --git a/docs/pages/doctrees/saving and loading.doctree b/docs/pages/doctrees/saving and loading.doctree
diff --git a/docs/pages/doctrees/sponsor.doctree b/docs/pages/doctrees/sponsor.doctree
diff --git a/docs/pages/doctrees/topological_sort.doctree b/docs/pages/doctrees/topological_sort.doctree
diff --git a/docs/pages/doctrees/whitelist_blacklist.doctree b/docs/pages/doctrees/whitelist_blacklist.doctree
diff --git a/docs/pages/html/Continuous Data.html b/docs/pages/html/Continuous Data.html
@@ -1,22 +1,24 @@
 <!DOCTYPE html>
-<html class="writer-html5" lang="en" >
+<html class="writer-html5" lang="en" data-content_root="./">
 <head>
-  <meta charset="utf-8" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
+  <meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
   <title>Advanced discretizing continous data &mdash; bnlearn bnlearn documentation</title>
-      <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
-      <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
-      <link rel="stylesheet" href="_static/css/custom.css" type="text/css" />
+      <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=fa44fd50" />
+      <link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
+      <link rel="stylesheet" type="text/css" href="_static/css/custom.css?v=e0179649" />
+
+
   <!--[if lt IE 9]>
     <script src="_static/js/html5shiv.min.js"></script>
   <![endif]-->
 
-        <script src="_static/jquery.js"></script>
-        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
-        <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
-        <script src="_static/doctools.js"></script>
-        <script src="_static/sphinx_highlight.js"></script>
+        <script src="_static/jquery.js?v=5d32c60e"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
+        <script src="_static/documentation_options.js?v=441dd29d"></script>
+        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
     <link rel="search" title="Search" href="search.html" />
@@ -184,7 +186,7 @@
 <p>The underlying idea i that the implemented method now can perform structure learning by first discretizng the continuous
 variables and simultaneously learn Bayesian network structures.</p>
 <section id="advanced-discretizing-continous-data">
-<h1>Advanced discretizing continous data<a class="headerlink" href="#advanced-discretizing-continous-data" title="Permalink to this heading"></a></h1>
+<h1>Advanced discretizing continous data<a class="headerlink" href="#advanced-discretizing-continous-data" title="Link to this heading"></a></h1>
 <p>To demonstrate the usage of parameter learning on continuous data, I will use the well known <strong>auto mpg</strong> data set.</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Import</span>
 <span class="kn">import</span> <span class="nn">bnlearn</span> <span class="k">as</span> <span class="nn">bn</span>
@@ -252,7 +254,7 @@ <h1>Advanced discretizing continous data<a class="headerlink" href="#advanced-di
 discrete data frame and fit a model using <code class="docutils literal notranslate"><span class="pre">bnlearn</span></code>.</p>
 </section>
 <section id="structure-learning">
-<h1>Structure learning<a class="headerlink" href="#structure-learning" title="Permalink to this heading"></a></h1>
+<h1>Structure learning<a class="headerlink" href="#structure-learning" title="Link to this heading"></a></h1>
 <p>We will learn the structure on the continuous data. Note that the data is also discretezed on a set of edges which will
 likely introduce a bias in the learned structure.</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Learn the structure</span>
@@ -274,7 +276,7 @@ <h1>Structure learning<a class="headerlink" href="#structure-learning" title="Pe
 </figure>
 <iframe src="https://erdogant.github.io/docs/d3blocks/bnlearn_continous_example_1.html" height="700px" width="750px", frameBorder="0"></iframe></section>
 <section id="parameter-learning">
-<h1>Parameter learning<a class="headerlink" href="#parameter-learning" title="Permalink to this heading"></a></h1>
+<h1>Parameter learning<a class="headerlink" href="#parameter-learning" title="Link to this heading"></a></h1>
 <p>Let’s continue with parameter learning on the continuous data set and see whether we can estimate the CPDs.</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Fit model based on DAG and discretized continous columns</span>
 <span class="n">model</span> <span class="o">=</span> <span class="n">bn</span><span class="o">.</span><span class="n">parameter_learning</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">DAG</span><span class="p">,</span> <span class="n">df_discrete</span><span class="p">)</span>
@@ -340,7 +342,7 @@ <h1>Parameter learning<a class="headerlink" href="#parameter-learning" title="Pe
 </div>
 </section>
 <section id="inference">
-<h1>Inference<a class="headerlink" href="#inference" title="Permalink to this heading"></a></h1>
+<h1>Inference<a class="headerlink" href="#inference" title="Link to this heading"></a></h1>
 <p>Making inferences can be perfomred using the fitted model. Note that the evidence should be discretized for which we can
 use the <code class="docutils literal notranslate"><span class="pre">discretize_value</span></code> function.</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">evidence</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;weight&quot;</span><span class="p">:</span> <span class="n">bn</span><span class="o">.</span><span class="n">discretize_value</span><span class="p">(</span><span class="n">df_discrete</span><span class="p">[</span><span class="s2">&quot;weight&quot;</span><span class="p">],</span> <span class="mf">3000.0</span><span class="p">)}</span>
@@ -378,7 +380,7 @@ <h1>Inference<a class="headerlink" href="#inference" title="Permalink to this he
 </tbody>
 </table>
 <section id="references">
-<h2>References<a class="headerlink" href="#references" title="Permalink to this heading"></a></h2>
+<h2>References<a class="headerlink" href="#references" title="Link to this heading"></a></h2>
 <blockquote>
 <div><ol class="arabic simple">
 <li><p>Yi-Chun Chen, Tim Allan Wheeler, Mykel John Kochenderfer (2015),

diff --git a/docs/pages/html/Create DAG.html b/docs/pages/html/Create DAG.html
@@ -1,22 +1,24 @@
 <!DOCTYPE html>
-<html class="writer-html5" lang="en" >
+<html class="writer-html5" lang="en" data-content_root="./">
 <head>
-  <meta charset="utf-8" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
+  <meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
   <title>Directed Acyclic Graphs &mdash; bnlearn bnlearn documentation</title>
-      <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
-      <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
-      <link rel="stylesheet" href="_static/css/custom.css" type="text/css" />
+      <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=fa44fd50" />
+      <link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
+      <link rel="stylesheet" type="text/css" href="_static/css/custom.css?v=e0179649" />
+
+
   <!--[if lt IE 9]>
     <script src="_static/js/html5shiv.min.js"></script>
   <![endif]-->
 
-        <script src="_static/jquery.js"></script>
-        <script src="_static/_sphinx_javascript_frameworks_compat.js"></script>
-        <script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
-        <script src="_static/doctools.js"></script>
-        <script src="_static/sphinx_highlight.js"></script>
+        <script src="_static/jquery.js?v=5d32c60e"></script>
+        <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
+        <script src="_static/documentation_options.js?v=441dd29d"></script>
+        <script src="_static/doctools.js?v=888ff710"></script>
+        <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
     <script src="_static/js/theme.js"></script>
     <link rel="index" title="Index" href="genindex.html" />
     <link rel="search" title="Search" href="search.html" />
@@ -179,10 +181,10 @@
            <div itemprop="articleBody">
 
   <section id="directed-acyclic-graphs">
-<h1>Directed Acyclic Graphs<a class="headerlink" href="#directed-acyclic-graphs" title="Permalink to this heading"></a></h1>
+<h1>Directed Acyclic Graphs<a class="headerlink" href="#directed-acyclic-graphs" title="Link to this heading"></a></h1>
 <p>This example is to better understand the importance and working of a Directed Acyclic Graph. The underneath topics are going to be explained:</p>
 <section id="overview">
-<h2>Overview<a class="headerlink" href="#overview" title="Permalink to this heading"></a></h2>
+<h2>Overview<a class="headerlink" href="#overview" title="Link to this heading"></a></h2>
 <ul class="simple">
 <li><p>Building a DAG</p></li>
 <li><p>plotting a DAG</p></li>
@@ -192,7 +194,7 @@ <h2>Overview<a class="headerlink" href="#overview" title="Permalink to this head
 </ul>
 </section>
 <section id="building-a-causal-dag">
-<h2>Building a causal DAG<a class="headerlink" href="#building-a-causal-dag" title="Permalink to this heading"></a></h2>
+<h2>Building a causal DAG<a class="headerlink" href="#building-a-causal-dag" title="Link to this heading"></a></h2>
 <p>If you readily know (or you have domain knowledge) of the relationships between variables, we can setup the (causal) relationships between the variables with a directed graph (DAG).
 Each node corresponds to a variable and each edge represents conditional dependencies between pairs of variables.
 In bnlearn, we can graphically represent the relationships between variables. To demonstrate this I will create the simple Sprinkler example by hand.</p>
@@ -223,13 +225,13 @@ <h2>Building a causal DAG<a class="headerlink" href="#building-a-causal-dag" tit
 <figure class="align-default" id="id1">
 <span id="fig-sprinkler"></span><img alt="_images/fig_sprinkler_sl.png" src="_images/fig_sprinkler_sl.png" />
 <figcaption>
-<p><span class="caption-text">Causal DAG.</span><a class="headerlink" href="#id1" title="Permalink to this image"></a></p>
+<p><span class="caption-text">Causal DAG.</span><a class="headerlink" href="#id1" title="Link to this image"></a></p>
 </figcaption>
 </figure>
 <p>We call this a causal DAG because we have assumed that the edges we encoded represent our causal assumptions about the system.</p>
 </section>
 <section id="the-causal-dag-as-a-generative-representation-of-joint-probability">
-<h2>The causal DAG as a generative representation of joint probability<a class="headerlink" href="#the-causal-dag-as-a-generative-representation-of-joint-probability" title="Permalink to this heading"></a></h2>
+<h2>The causal DAG as a generative representation of joint probability<a class="headerlink" href="#the-causal-dag-as-a-generative-representation-of-joint-probability" title="Link to this heading"></a></h2>
 <p>Any DAG (causal or otherwise) that we might specify for this data represents a factorization of the joint probability distribution of the variables.</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">bnlearn</span><span class="o">.</span><span class="n">print_CPD</span><span class="p">(</span><span class="n">DAG</span><span class="p">)</span>
 
@@ -239,7 +241,7 @@ <h2>The causal DAG as a generative representation of joint probability<a class="
 <p>There are no CPDs attached to the DAG yet. Therefore there is nothing to show.</p>
 </section>
 <section id="specifying-the-probability-distributions-on-your-own">
-<h2>Specifying the probability distributions on your own<a class="headerlink" href="#specifying-the-probability-distributions-on-your-own" title="Permalink to this heading"></a></h2>
+<h2>Specifying the probability distributions on your own<a class="headerlink" href="#specifying-the-probability-distributions-on-your-own" title="Link to this heading"></a></h2>
 <p>Each factor is a conditional probability distribution (CPD). In the discrete case the CPD is sometimes called a conditional probability table (CPT).
 Though we can factorize over any DAG and get a set of CPDs, when we factorize along a DAG we consider to be a representation of causality, we call each CPD a causal Markov kernel (CMK).
 The factorization that provides a set of CMKs is the most useful factorization because CMKs correspond to independent causal mechanisms we assume to be invariant across data sets.
@@ -297,7 +299,7 @@ <h2>Specifying the probability distributions on your own<a class="headerlink" hr
 </div>
 </section>
 <section id="inference-on-the-causal-generative-model">
-<h2>Inference on the causal generative model<a class="headerlink" href="#inference-on-the-causal-generative-model" title="Permalink to this heading"></a></h2>
+<h2>Inference on the causal generative model<a class="headerlink" href="#inference-on-the-causal-generative-model" title="Link to this heading"></a></h2>
 <p>This is an great basis to make inferences or update your this model with new data (parameter learning).</p>
 <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">q1</span> <span class="o">=</span> <span class="n">bnlearn</span><span class="o">.</span><span class="n">inference</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">DAG</span><span class="p">,</span> <span class="n">variables</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;Wet_Grass&#39;</span><span class="p">],</span> <span class="n">evidence</span><span class="o">=</span><span class="p">{</span><span class="s1">&#39;Rain&#39;</span><span class="p">:</span><span class="mi">1</span><span class="p">,</span> <span class="s1">&#39;Sprinkler&#39;</span><span class="p">:</span><span class="mi">0</span><span class="p">,</span> <span class="s1">&#39;Cloudy&#39;</span><span class="p">:</span><span class="mi">1</span><span class="p">})</span>
 </pre></div>