docs v0.7

arogozhnikov · Sep 10, 2021 · 1ab8a58 · 1ab8a58
1 parent ac0cce1
commit 1ab8a58
Show file tree

Hide file tree

Showing 112 changed files with 32,381 additions and 0 deletions.
diff --git a/docs/.nojekyll b/docs/.nojekyll
diff --git a/docs/_modules/hep_ml/gradientboosting.html b/docs/_modules/hep_ml/gradientboosting.html
diff --git a/docs/_modules/hep_ml/losses.html b/docs/_modules/hep_ml/losses.html
diff --git a/docs/_modules/hep_ml/metrics.html b/docs/_modules/hep_ml/metrics.html
diff --git a/docs/_modules/hep_ml/nnet.html b/docs/_modules/hep_ml/nnet.html
diff --git a/docs/_modules/hep_ml/preprocessing.html b/docs/_modules/hep_ml/preprocessing.html
diff --git a/docs/_modules/hep_ml/reweight.html b/docs/_modules/hep_ml/reweight.html
diff --git a/docs/_modules/hep_ml/speedup.html b/docs/_modules/hep_ml/speedup.html
diff --git a/docs/_modules/hep_ml/splot.html b/docs/_modules/hep_ml/splot.html
@@ -0,0 +1,272 @@
+
+
+<!DOCTYPE html>
+<html class="writer-html5" lang="en" >
+<head>
+  <meta charset="utf-8" />
+
+  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+
+  <title>hep_ml.splot &mdash; hep_ml 0.7.0 documentation</title>
+
+
+
+  <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
+  <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
+  <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
+  <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+
+
+
+
+
+  <!--[if lt IE 9]>
+    <script src="../../_static/js/html5shiv.min.js"></script>
+  <![endif]-->
+
+
+      <script type="text/javascript" id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script>
+        <script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
+        <script src="../../_static/jquery.js"></script>
+        <script src="../../_static/underscore.js"></script>
+        <script src="../../_static/doctools.js"></script>
+
+    <script type="text/javascript" src="../../_static/js/theme.js"></script>
+
+
+    <link rel="index" title="Index" href="../../genindex.html" />
+    <link rel="search" title="Search" href="../../search.html" /> 
+</head>
+
+<body class="wy-body-for-nav">
+
+
+  <div class="wy-grid-for-nav">
+
+    <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+      <div class="wy-side-scroll">
+        <div class="wy-side-nav-search" >
+
+
+
+            <a href="../../index.html" class="icon icon-home"> hep_ml
+
+
+
+          </a>
+
+
+
+
+              <div class="version">
+                0.7.0
+              </div>
+
+
+
+
+<div role="search">
+  <form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
+    <input type="text" name="q" placeholder="Search docs" />
+    <input type="hidden" name="check_keywords" value="yes" />
+    <input type="hidden" name="area" value="default" />
+  </form>
+</div>
+
+
+        </div>
+
+
+        <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+
+
+
+              <ul>
+<li class="toctree-l1"><a class="reference internal" href="../../index.html">hep_ml documentation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../gb.html">Gradient boosting</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../losses.html">Losses for Gradient Boosting</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../uboost.html">uBoost</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../metrics.html">Metric functions</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../nnet.html">Neural networks</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../preprocessing.html">Preprocessing data</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../reweight.html">Reweighting algorithms</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../speedup.html">Fast predictions</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../splot.html">sPlot</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../notebooks.html">Code Examples</a></li>
+</ul>
+
+
+
+        </div>
+
+      </div>
+    </nav>
+
+    <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+
+      <nav class="wy-nav-top" aria-label="top navigation">
+
+          <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+          <a href="../../index.html">hep_ml</a>
+
+      </nav>
+
+
+      <div class="wy-nav-content">
+
+        <div class="rst-content">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+<div role="navigation" aria-label="breadcrumbs navigation">
+
+  <ul class="wy-breadcrumbs">
+
+      <li><a href="../../index.html" class="icon icon-home"></a> &raquo;</li>
+
+          <li><a href="../index.html">Module code</a> &raquo;</li>
+
+      <li>hep_ml.splot</li>
+
+
+      <li class="wy-breadcrumbs-aside">
+
+      </li>
+
+  </ul>
+
+
+  <hr/>
+</div>
+          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
+           <div itemprop="articleBody">
+
+  <h1>Source code for hep_ml.splot</h1><div class="highlight"><pre>
+<span></span><span class="sd">&quot;&quot;&quot;</span>
+<span class="sd">**sPlot** is reweighting technique frequently used in HEP to reconstruct the distributions of features in mixture.</span>
+<span class="sd">Initial information used is the probabilities obtained after fitting.</span>
+
+<span class="sd">**hep_ml.splot** contains standalone python implementation of this technique.</span>
+<span class="sd">This implementation is brilliantly simple and clear - just as it should be.</span>
+
+<span class="sd">Example</span>
+<span class="sd">-------</span>
+
+<span class="sd">&gt;&gt;&gt; from hep_ml.splot import compute_sweights</span>
+<span class="sd">&gt;&gt;&gt; p = pandas.DataFrame({&#39;signal&#39;: p_signal, &#39;bkg&#39;, b_bkg})</span>
+<span class="sd">&gt;&gt;&gt; sWeights = compute_sweights(p)</span>
+<span class="sd">&gt;&gt;&gt; # plotting reconstructed distribution of some other variable</span>
+<span class="sd">&gt;&gt;&gt; plt.hist(other_var, weights=sWeights.signal)</span>
+<span class="sd">&gt;&gt;&gt; plt.hist(other_var, weights=sWeights.bkg)</span>
+
+<span class="sd">For more examples and explanations, see notebooks/Splot in repository.</span>
+
+<span class="sd">&quot;&quot;&quot;</span>
+
+<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">division</span><span class="p">,</span> <span class="n">print_function</span><span class="p">,</span> <span class="n">absolute_import</span>
+<span class="kn">import</span> <span class="nn">pandas</span>
+<span class="kn">import</span> <span class="nn">numpy</span>
+<span class="kn">from</span> <span class="nn">.commonutils</span> <span class="kn">import</span> <span class="n">check_sample_weight</span>
+
+<span class="n">__author__</span> <span class="o">=</span> <span class="s1">&#39;Alex Rogozhnikov&#39;</span>
+
+
+<div class="viewcode-block" id="compute_sweights"><a class="viewcode-back" href="../../splot.html#hep_ml.splot.compute_sweights">[docs]</a><span class="k">def</span> <span class="nf">compute_sweights</span><span class="p">(</span><span class="n">probabilities</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
+    <span class="sd">&quot;&quot;&quot;Computes sWeights based on probabilities obtained from distribution fit.</span>
+
+<span class="sd">    :param probabilities: pandas.DataFrame with probabilities of shape [n_samples, n_classes].</span>
+<span class="sd">        These probabilities are obtained after fit (typically, mass fit).</span>
+<span class="sd">        Pay attention, that for each sample sum of probabilities should be equal to 1.</span>
+<span class="sd">    :param sample_weight: optionally you can pass weights of events, numpy.array of shape [n_samples]</span>
+<span class="sd">    :return: pandas.DataFrame with sWeights of shape [n_samples, n_classes]</span>
+<span class="sd">    &quot;&quot;&quot;</span>
+    <span class="c1"># converting to pandas.DataFrame</span>
+    <span class="n">probabilities</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">probabilities</span><span class="p">)</span>
+    <span class="c1"># checking sample_weight</span>
+    <span class="n">sample_weight</span> <span class="o">=</span> <span class="n">check_sample_weight</span><span class="p">(</span><span class="n">probabilities</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="n">sample_weight</span><span class="p">)</span>
+    <span class="c1"># checking that all weights are positive</span>
+    <span class="k">assert</span> <span class="n">numpy</span><span class="o">.</span><span class="n">all</span><span class="p">(</span><span class="n">sample_weight</span> <span class="o">&gt;=</span> <span class="mi">0</span><span class="p">),</span> <span class="s1">&#39;sample weight are expected to be non-negative&#39;</span>
+
+    <span class="n">p</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">probabilities</span><span class="p">)</span>
+    <span class="c1"># checking that probabilities sum up to 1.</span>
+    <span class="k">assert</span> <span class="n">numpy</span><span class="o">.</span><span class="n">allclose</span><span class="p">(</span><span class="n">p</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span> <span class="mi">1</span><span class="p">,</span> <span class="n">atol</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">),</span> <span class="s1">&#39;sum of probabilities is not equal to 1.&#39;</span>
+
+    <span class="c1"># computations</span>
+    <span class="n">initial_stats</span> <span class="o">=</span> <span class="p">(</span><span class="n">p</span> <span class="o">*</span> <span class="n">sample_weight</span><span class="p">[:,</span> <span class="n">numpy</span><span class="o">.</span><span class="n">newaxis</span><span class="p">])</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
+    <span class="n">V_inv</span> <span class="o">=</span> <span class="n">p</span><span class="o">.</span><span class="n">T</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">p</span> <span class="o">*</span> <span class="n">sample_weight</span><span class="p">[:,</span> <span class="n">numpy</span><span class="o">.</span><span class="n">newaxis</span><span class="p">])</span>
+    <span class="n">V</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">inv</span><span class="p">(</span><span class="n">V_inv</span><span class="p">)</span> <span class="o">*</span> <span class="n">initial_stats</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">newaxis</span><span class="p">,</span> <span class="p">:]</span>
+
+    <span class="c1"># Final formula</span>
+    <span class="n">sweights</span> <span class="o">=</span> <span class="n">p</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">V</span><span class="p">)</span> <span class="o">*</span> <span class="n">sample_weight</span><span class="p">[:,</span> <span class="n">numpy</span><span class="o">.</span><span class="n">newaxis</span><span class="p">]</span>
+    <span class="k">return</span> <span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">sweights</span><span class="p">,</span> <span class="n">columns</span><span class="o">=</span><span class="n">probabilities</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span></div>
+</pre></div>
+
+           </div>
+
+          </div>
+          <footer>
+
+  <hr/>
+
+  <div role="contentinfo">
+    <p>
+        &#169; Copyright 2015-2017, Yandex; Alex Rogozhnikov and contributors.
+
+    </p>
+  </div>
+
+
+
+    Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
+
+    <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
+
+    provided by <a href="https://readthedocs.org">Read the Docs</a>. 
+
+</footer>
+        </div>
+      </div>
+
+    </section>
+
+  </div>
+
+
+  <script type="text/javascript">
+      jQuery(function () {
+          SphinxRtdTheme.Navigation.enable(true);
+      });
+  </script>
+
+
+
+
+
+
+</body>
+</html>