| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>Statistics — PySpark 3.4.3 documentation</title> |
| |
| <link rel="stylesheet" href="../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css"> |
| |
| |
| <link rel="stylesheet" |
| href="../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| <link rel="stylesheet" |
| href="../../_static/vendor/open-sans_all/1.44.1/index.css"> |
| <link rel="stylesheet" |
| href="../../_static/vendor/lato_latin-ext/1.44.1/index.css"> |
| |
| |
| <link rel="stylesheet" href="../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../_static/js/index.3da636dd464baa7582d2.js"> |
| |
| <script id="documentation_options" data-url_root="../../" 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 src="../../_static/language_data.js"></script> |
| <script src="../../_static/clipboard.min.js"></script> |
| <script src="../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/reference/api/pyspark.mllib.stat.Statistics.html" /> |
| <link rel="search" title="Search" href="../../search.html" /> |
| <link rel="next" title="MultivariateStatisticalSummary" href="pyspark.mllib.stat.MultivariateStatisticalSummary.html" /> |
| <link rel="prev" title="StreamingLinearRegressionWithSGD" href="pyspark.mllib.regression.StreamingLinearRegressionWithSGD.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="en" /> |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"> |
| <div class="container-xl"> |
| |
| <a class="navbar-brand" href="../../index.html"> |
| |
| <img src="../../_static/spark-logo-reverse.png" class="logo" alt="logo" /> |
| |
| </a> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| <div id="navbar-menu" class="col-lg-9 collapse navbar-collapse"> |
| <ul id="navbar-main-elements" class="navbar-nav mr-auto"> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../index.html">Overview</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../getting_started/index.html">Getting Started</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../user_guide/index.html">User Guides</a> |
| </li> |
| |
| <li class="nav-item active"> |
| <a class="nav-link" href="../index.html">API Reference</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../development/index.html">Development</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../migration_guide/index.html">Migration Guides</a> |
| </li> |
| |
| |
| </ul> |
| |
| |
| |
| |
| <ul class="navbar-nav"> |
| |
| |
| </ul> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| <div class="col-12 col-md-3 bd-sidebar"><form class="bd-search d-flex align-items-center" action="../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form> |
| <nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| |
| <div class="bd-toc-item active"> |
| |
| |
| <ul class="nav bd-sidenav"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.sql/index.html">Spark SQL</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.pandas/index.html">Pandas API on Spark</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.ss/index.html">Structured Streaming</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.ml.html">MLlib (DataFrame-based)</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.streaming.html">Spark Streaming (Legacy)</a> |
| </li> |
| |
| |
| |
| <li class="active"> |
| <a href="../pyspark.mllib.html">MLlib (RDD-based)</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.html">Spark Core</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.resource.html">Resource Management</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.errors.html">Errors</a> |
| </li> |
| |
| |
| |
| |
| |
| |
| |
| |
| </ul> |
| |
| </nav> |
| </div> |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| |
| <nav id="bd-toc-nav"> |
| <ul class="nav section-nav flex-column"> |
| |
| </ul> |
| </nav> |
| |
| |
| |
| </div> |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <div class="section" id="statistics"> |
| <h1>Statistics<a class="headerlink" href="#statistics" title="Permalink to this headline">¶</a></h1> |
| <dl class="py class"> |
| <dt id="pyspark.mllib.stat.Statistics"> |
| <em class="property">class </em><code class="sig-prename descclassname">pyspark.mllib.stat.</code><code class="sig-name descname">Statistics</code><a class="reference internal" href="../../_modules/pyspark/mllib/stat/_statistics.html#Statistics"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.stat.Statistics" title="Permalink to this definition">¶</a></dt> |
| <dd><p class="rubric">Methods</p> |
| <table class="longtable table autosummary"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.stat.Statistics.chiSqTest" title="pyspark.mllib.stat.Statistics.chiSqTest"><code class="xref py py-obj docutils literal notranslate"><span class="pre">chiSqTest</span></code></a>(observed[, expected])</p></td> |
| <td><p>If <cite>observed</cite> is Vector, conduct Pearson’s chi-squared goodness of fit test of the observed data against the expected distribution, or against the uniform distribution (by default), with each category having an expected frequency of <cite>1 / len(observed)</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.stat.Statistics.colStats" title="pyspark.mllib.stat.Statistics.colStats"><code class="xref py py-obj docutils literal notranslate"><span class="pre">colStats</span></code></a>(rdd)</p></td> |
| <td><p>Computes column-wise summary statistics for the input RDD[Vector].</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.stat.Statistics.corr" title="pyspark.mllib.stat.Statistics.corr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">corr</span></code></a>(x[, y, method])</p></td> |
| <td><p>Compute the correlation (matrix) for the input RDD(s) using the specified method.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.stat.Statistics.kolmogorovSmirnovTest" title="pyspark.mllib.stat.Statistics.kolmogorovSmirnovTest"><code class="xref py py-obj docutils literal notranslate"><span class="pre">kolmogorovSmirnovTest</span></code></a>(data[, distName])</p></td> |
| <td><p>Performs the Kolmogorov-Smirnov (KS) test for data sampled from a continuous distribution.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p class="rubric">Methods Documentation</p> |
| <dl class="py method"> |
| <dt id="pyspark.mllib.stat.Statistics.chiSqTest"> |
| <em class="property">static </em><code class="sig-name descname">chiSqTest</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">observed</span><span class="p">:</span> <span class="n">Union<span class="p">[</span><a class="reference internal" href="pyspark.mllib.linalg.Matrix.html#pyspark.mllib.linalg.Matrix" title="pyspark.mllib.linalg.Matrix">pyspark.mllib.linalg.Matrix</a><span class="p">, </span>pyspark.rdd.RDD<span class="p">[</span><a class="reference internal" href="pyspark.mllib.regression.LabeledPoint.html#pyspark.mllib.regression.LabeledPoint" title="pyspark.mllib.regression.LabeledPoint">pyspark.mllib.regression.LabeledPoint</a><span class="p">]</span><span class="p">, </span><a class="reference internal" href="pyspark.mllib.linalg.Vector.html#pyspark.mllib.linalg.Vector" title="pyspark.mllib.linalg.Vector">pyspark.mllib.linalg.Vector</a><span class="p">]</span></span></em>, <em class="sig-param"><span class="n">expected</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span><a class="reference internal" href="pyspark.mllib.linalg.Vector.html#pyspark.mllib.linalg.Vector" title="pyspark.mllib.linalg.Vector">pyspark.mllib.linalg.Vector</a><span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → Union<span class="p">[</span>pyspark.mllib.stat.test.ChiSqTestResult<span class="p">, </span>List<span class="p">[</span>pyspark.mllib.stat.test.ChiSqTestResult<span class="p">]</span><span class="p">]</span><a class="reference internal" href="../../_modules/pyspark/mllib/stat/_statistics.html#Statistics.chiSqTest"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.stat.Statistics.chiSqTest" title="Permalink to this definition">¶</a></dt> |
| <dd><p>If <cite>observed</cite> is Vector, conduct Pearson’s chi-squared goodness |
| of fit test of the observed data against the expected distribution, |
| or against the uniform distribution (by default), with each category |
| having an expected frequency of <cite>1 / len(observed)</cite>.</p> |
| <p>If <cite>observed</cite> is matrix, conduct Pearson’s independence test on the |
| input contingency matrix, which cannot contain negative entries or |
| columns or rows that sum up to 0.</p> |
| <p>If <cite>observed</cite> is an RDD of LabeledPoint, conduct Pearson’s independence |
| test for every feature against the label across the input RDD. |
| For each feature, the (feature, label) pairs are converted into a |
| contingency matrix for which the chi-squared statistic is computed. |
| All label and feature values must be categorical.</p> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>observed</strong><span class="classifier"><a class="reference internal" href="pyspark.mllib.linalg.Vector.html#pyspark.mllib.linalg.Vector" title="pyspark.mllib.linalg.Vector"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.mllib.linalg.Vector</span></code></a> or <a class="reference internal" href="pyspark.mllib.linalg.Matrix.html#pyspark.mllib.linalg.Matrix" title="pyspark.mllib.linalg.Matrix"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.mllib.linalg.Matrix</span></code></a></span></dt><dd><p>it could be a vector containing the observed categorical |
| counts/relative frequencies, or the contingency matrix |
| (containing either counts or relative frequencies), |
| or an RDD of LabeledPoint containing the labeled dataset |
| with categorical features. Real-valued features will be |
| treated as categorical for each distinct value.</p> |
| </dd> |
| <dt><strong>expected</strong><span class="classifier"><a class="reference internal" href="pyspark.mllib.linalg.Vector.html#pyspark.mllib.linalg.Vector" title="pyspark.mllib.linalg.Vector"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.mllib.linalg.Vector</span></code></a></span></dt><dd><p>Vector containing the expected categorical counts/relative |
| frequencies. <cite>expected</cite> is rescaled if the <cite>expected</cite> sum |
| differs from the <cite>observed</cite> sum.</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><a class="reference internal" href="pyspark.mllib.stat.ChiSqTestResult.html#pyspark.mllib.stat.ChiSqTestResult" title="pyspark.mllib.stat.ChiSqTestResult"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.mllib.stat.ChiSqTestResult</span></code></a></dt><dd><p>object containing the test statistic, degrees |
| of freedom, p-value, the method used, and the null hypothesis.</p> |
| </dd> |
| </dl> |
| </dd> |
| </dl> |
| <p class="rubric">Notes</p> |
| <p><cite>observed</cite> cannot contain negative values</p> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span><span class="p">,</span> <span class="n">Matrices</span> |
| <span class="gp">>>> </span><span class="n">observed</span> <span class="o">=</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">4</span><span class="p">,</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">5</span><span class="p">])</span> |
| <span class="gp">>>> </span><span class="n">pearson</span> <span class="o">=</span> <span class="n">Statistics</span><span class="o">.</span><span class="n">chiSqTest</span><span class="p">(</span><span class="n">observed</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="n">pearson</span><span class="o">.</span><span class="n">statistic</span><span class="p">)</span> |
| <span class="go">0.4</span> |
| <span class="gp">>>> </span><span class="n">pearson</span><span class="o">.</span><span class="n">degreesOfFreedom</span> |
| <span class="go">2</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">pearson</span><span class="o">.</span><span class="n">pValue</span><span class="p">,</span> <span class="mi">4</span><span class="p">))</span> |
| <span class="go">0.8187</span> |
| <span class="gp">>>> </span><span class="n">pearson</span><span class="o">.</span><span class="n">method</span> |
| <span class="go">'pearson'</span> |
| <span class="gp">>>> </span><span class="n">pearson</span><span class="o">.</span><span class="n">nullHypothesis</span> |
| <span class="go">'observed follows the same distribution as expected.'</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">observed</span> <span class="o">=</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">21</span><span class="p">,</span> <span class="mi">38</span><span class="p">,</span> <span class="mi">43</span><span class="p">,</span> <span class="mi">80</span><span class="p">])</span> |
| <span class="gp">>>> </span><span class="n">expected</span> <span class="o">=</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">3</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">20</span><span class="p">])</span> |
| <span class="gp">>>> </span><span class="n">pearson</span> <span class="o">=</span> <span class="n">Statistics</span><span class="o">.</span><span class="n">chiSqTest</span><span class="p">(</span><span class="n">observed</span><span class="p">,</span> <span class="n">expected</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">pearson</span><span class="o">.</span><span class="n">pValue</span><span class="p">,</span> <span class="mi">4</span><span class="p">))</span> |
| <span class="go">0.0027</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">data</span> <span class="o">=</span> <span class="p">[</span><span class="mf">40.0</span><span class="p">,</span> <span class="mf">24.0</span><span class="p">,</span> <span class="mf">29.0</span><span class="p">,</span> <span class="mf">56.0</span><span class="p">,</span> <span class="mf">32.0</span><span class="p">,</span> <span class="mf">42.0</span><span class="p">,</span> <span class="mf">31.0</span><span class="p">,</span> <span class="mf">10.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">30.0</span><span class="p">,</span> <span class="mf">15.0</span><span class="p">,</span> <span class="mf">12.0</span><span class="p">]</span> |
| <span class="gp">>>> </span><span class="n">chi</span> <span class="o">=</span> <span class="n">Statistics</span><span class="o">.</span><span class="n">chiSqTest</span><span class="p">(</span><span class="n">Matrices</span><span class="o">.</span><span class="n">dense</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="n">data</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">chi</span><span class="o">.</span><span class="n">statistic</span><span class="p">,</span> <span class="mi">4</span><span class="p">))</span> |
| <span class="go">21.9958</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">data</span> <span class="o">=</span> <span class="p">[</span><span class="n">LabeledPoint</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">10.0</span><span class="p">])),</span> |
| <span class="gp">... </span> <span class="n">LabeledPoint</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mf">1.5</span><span class="p">,</span> <span class="mf">20.0</span><span class="p">])),</span> |
| <span class="gp">... </span> <span class="n">LabeledPoint</span><span class="p">(</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mf">1.5</span><span class="p">,</span> <span class="mf">30.0</span><span class="p">])),</span> |
| <span class="gp">... </span> <span class="n">LabeledPoint</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mf">3.5</span><span class="p">,</span> <span class="mf">30.0</span><span class="p">])),</span> |
| <span class="gp">... </span> <span class="n">LabeledPoint</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mf">3.5</span><span class="p">,</span> <span class="mf">40.0</span><span class="p">])),</span> |
| <span class="gp">... </span> <span class="n">LabeledPoint</span><span class="p">(</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mf">3.5</span><span class="p">,</span> <span class="mf">40.0</span><span class="p">])),]</span> |
| <span class="gp">>>> </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="mi">4</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">chi</span> <span class="o">=</span> <span class="n">Statistics</span><span class="o">.</span><span class="n">chiSqTest</span><span class="p">(</span><span class="n">rdd</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="n">chi</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">statistic</span><span class="p">)</span> |
| <span class="go">0.75</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="n">chi</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">statistic</span><span class="p">)</span> |
| <span class="go">1.5</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.stat.Statistics.colStats"> |
| <em class="property">static </em><code class="sig-name descname">colStats</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">rdd</span><span class="p">:</span> <span class="n">pyspark.rdd.RDD<span class="p">[</span><a class="reference internal" href="pyspark.mllib.linalg.Vector.html#pyspark.mllib.linalg.Vector" title="pyspark.mllib.linalg.Vector">pyspark.mllib.linalg.Vector</a><span class="p">]</span></span></em><span class="sig-paren">)</span> → pyspark.mllib.stat._statistics.MultivariateStatisticalSummary<a class="reference internal" href="../../_modules/pyspark/mllib/stat/_statistics.html#Statistics.colStats"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.stat.Statistics.colStats" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Computes column-wise summary statistics for the input RDD[Vector].</p> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>rdd</strong><span class="classifier"><a class="reference internal" href="pyspark.RDD.html#pyspark.RDD" title="pyspark.RDD"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.RDD</span></code></a></span></dt><dd><p>an RDD[Vector] for which column-wise summary statistics |
| are to be computed.</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><a class="reference internal" href="pyspark.mllib.stat.MultivariateStatisticalSummary.html#pyspark.mllib.stat.MultivariateStatisticalSummary" title="pyspark.mllib.stat.MultivariateStatisticalSummary"><code class="xref py py-class docutils literal notranslate"><span class="pre">MultivariateStatisticalSummary</span></code></a></dt><dd><p>object containing column-wise summary statistics.</p> |
| </dd> |
| </dl> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span> |
| <span class="gp">>>> </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="o">-</span><span class="mi">2</span><span class="p">]),</span> |
| <span class="gp">... </span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">3</span><span class="p">]),</span> |
| <span class="gp">... </span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">6</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">8</span><span class="p">])])</span> |
| <span class="gp">>>> </span><span class="n">cStats</span> <span class="o">=</span> <span class="n">Statistics</span><span class="o">.</span><span class="n">colStats</span><span class="p">(</span><span class="n">rdd</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">cStats</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> |
| <span class="go">array([ 4., 4., 0., 3.])</span> |
| <span class="gp">>>> </span><span class="n">cStats</span><span class="o">.</span><span class="n">variance</span><span class="p">()</span> |
| <span class="go">array([ 4., 13., 0., 25.])</span> |
| <span class="gp">>>> </span><span class="n">cStats</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> |
| <span class="go">3</span> |
| <span class="gp">>>> </span><span class="n">cStats</span><span class="o">.</span><span class="n">numNonzeros</span><span class="p">()</span> |
| <span class="go">array([ 3., 2., 0., 3.])</span> |
| <span class="gp">>>> </span><span class="n">cStats</span><span class="o">.</span><span class="n">max</span><span class="p">()</span> |
| <span class="go">array([ 6., 7., 0., 8.])</span> |
| <span class="gp">>>> </span><span class="n">cStats</span><span class="o">.</span><span class="n">min</span><span class="p">()</span> |
| <span class="go">array([ 2., 0., 0., -2.])</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.stat.Statistics.corr"> |
| <em class="property">static </em><code class="sig-name descname">corr</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">x</span><span class="p">:</span> <span class="n">Union<span class="p">[</span>pyspark.rdd.RDD<span class="p">[</span><a class="reference internal" href="pyspark.mllib.linalg.Vector.html#pyspark.mllib.linalg.Vector" title="pyspark.mllib.linalg.Vector">pyspark.mllib.linalg.Vector</a><span class="p">]</span><span class="p">, </span>pyspark.rdd.RDD<span class="p">[</span>float<span class="p">]</span><span class="p">]</span></span></em>, <em class="sig-param"><span class="n">y</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>pyspark.rdd.RDD<span class="p">[</span>float<span class="p">]</span><span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">method</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>CorrMethodType<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → Union<span class="p">[</span>float<span class="p">, </span><a class="reference internal" href="pyspark.mllib.linalg.Matrix.html#pyspark.mllib.linalg.Matrix" title="pyspark.mllib.linalg.Matrix">pyspark.mllib.linalg.Matrix</a><span class="p">]</span><a class="reference internal" href="../../_modules/pyspark/mllib/stat/_statistics.html#Statistics.corr"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.stat.Statistics.corr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Compute the correlation (matrix) for the input RDD(s) using the |
| specified method. |
| Methods currently supported: <cite>pearson (default), spearman</cite>.</p> |
| <p>If a single RDD of Vectors is passed in, a correlation matrix |
| comparing the columns in the input RDD is returned. Use <cite>method</cite> |
| to specify the method to be used for single RDD inout. |
| If two RDDs of floats are passed in, a single float is returned.</p> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>x</strong><span class="classifier"><a class="reference internal" href="pyspark.RDD.html#pyspark.RDD" title="pyspark.RDD"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.RDD</span></code></a></span></dt><dd><p>an RDD of vector for which the correlation matrix is to be computed, |
| or an RDD of float of the same cardinality as y when y is specified.</p> |
| </dd> |
| <dt><strong>y</strong><span class="classifier"><a class="reference internal" href="pyspark.RDD.html#pyspark.RDD" title="pyspark.RDD"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.RDD</span></code></a>, optional</span></dt><dd><p>an RDD of float of the same cardinality as x.</p> |
| </dd> |
| <dt><strong>method</strong><span class="classifier">str, optional</span></dt><dd><p>String specifying the method to use for computing correlation. |
| Supported: <cite>pearson</cite> (default), <cite>spearman</cite></p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><a class="reference internal" href="pyspark.mllib.linalg.Matrix.html#pyspark.mllib.linalg.Matrix" title="pyspark.mllib.linalg.Matrix"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.mllib.linalg.Matrix</span></code></a></dt><dd><p>Correlation matrix comparing columns in x.</p> |
| </dd> |
| </dl> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">x</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="o">-</span><span class="mf">2.0</span><span class="p">],</span> <span class="mi">2</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">y</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="mf">4.0</span><span class="p">,</span> <span class="mf">5.0</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">],</span> <span class="mi">2</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">zeros</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">],</span> <span class="mi">2</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">Statistics</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span> <span class="o">-</span> <span class="mf">0.6546537</span><span class="p">)</span> <span class="o"><</span> <span class="mf">1e-7</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="n">Statistics</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span> <span class="o">==</span> <span class="n">Statistics</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="s2">"pearson"</span><span class="p">)</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="n">Statistics</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="s2">"spearman"</span><span class="p">)</span> |
| <span class="go">0.5</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">isnan</span> |
| <span class="gp">>>> </span><span class="n">isnan</span><span class="p">(</span><span class="n">Statistics</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">zeros</span><span class="p">))</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span> |
| <span class="gp">>>> </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="o">-</span><span class="mi">2</span><span class="p">]),</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">3</span><span class="p">]),</span> |
| <span class="gp">... </span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">6</span><span class="p">,</span> <span class="mi">7</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">8</span><span class="p">]),</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">dense</span><span class="p">([</span><span class="mi">9</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">])])</span> |
| <span class="gp">>>> </span><span class="n">pearsonCorr</span> <span class="o">=</span> <span class="n">Statistics</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="n">rdd</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">pearsonCorr</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">'nan'</span><span class="p">,</span> <span class="s1">'NaN'</span><span class="p">))</span> |
| <span class="go">[[ 1. 0.05564149 NaN 0.40047142]</span> |
| <span class="go"> [ 0.05564149 1. NaN 0.91359586]</span> |
| <span class="go"> [ NaN NaN 1. NaN]</span> |
| <span class="go"> [ 0.40047142 0.91359586 NaN 1. ]]</span> |
| <span class="gp">>>> </span><span class="n">spearmanCorr</span> <span class="o">=</span> <span class="n">Statistics</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="n">method</span><span class="o">=</span><span class="s2">"spearman"</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">spearmanCorr</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">'nan'</span><span class="p">,</span> <span class="s1">'NaN'</span><span class="p">))</span> |
| <span class="go">[[ 1. 0.10540926 NaN 0.4 ]</span> |
| <span class="go"> [ 0.10540926 1. NaN 0.9486833 ]</span> |
| <span class="go"> [ NaN NaN 1. NaN]</span> |
| <span class="go"> [ 0.4 0.9486833 NaN 1. ]]</span> |
| <span class="gp">>>> </span><span class="k">try</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">Statistics</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="n">rdd</span><span class="p">,</span> <span class="s2">"spearman"</span><span class="p">)</span> |
| <span class="gp">... </span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Method name as second argument without 'method=' shouldn't be allowed."</span><span class="p">)</span> |
| <span class="gp">... </span><span class="k">except</span> <span class="ne">TypeError</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">pass</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.stat.Statistics.kolmogorovSmirnovTest"> |
| <em class="property">static </em><code class="sig-name descname">kolmogorovSmirnovTest</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">data</span><span class="p">:</span> <span class="n">pyspark.rdd.RDD<span class="p">[</span>float<span class="p">]</span></span></em>, <em class="sig-param"><span class="n">distName</span><span class="p">:</span> <span class="n">KolmogorovSmirnovTestDistNameType</span> <span class="o">=</span> <span class="default_value">'norm'</span></em>, <em class="sig-param"><span class="o">*</span><span class="n">params</span><span class="p">:</span> <span class="n">float</span></em><span class="sig-paren">)</span> → pyspark.mllib.stat.test.KolmogorovSmirnovTestResult<a class="reference internal" href="../../_modules/pyspark/mllib/stat/_statistics.html#Statistics.kolmogorovSmirnovTest"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.stat.Statistics.kolmogorovSmirnovTest" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Performs the Kolmogorov-Smirnov (KS) test for data sampled from |
| a continuous distribution. It tests the null hypothesis that |
| the data is generated from a particular distribution.</p> |
| <p>The given data is sorted and the Empirical Cumulative |
| Distribution Function (ECDF) is calculated |
| which for a given point is the number of points having a CDF |
| value lesser than it divided by the total number of points.</p> |
| <p>Since the data is sorted, this is a step function |
| that rises by (1 / length of data) for every ordered point.</p> |
| <p>The KS statistic gives us the maximum distance between the |
| ECDF and the CDF. Intuitively if this statistic is large, the |
| probability that the null hypothesis is true becomes small. |
| For specific details of the implementation, please have a look |
| at the Scala documentation.</p> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>data</strong><span class="classifier"><a class="reference internal" href="pyspark.RDD.html#pyspark.RDD" title="pyspark.RDD"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.RDD</span></code></a></span></dt><dd><p>RDD, samples from the data</p> |
| </dd> |
| <dt><strong>distName</strong><span class="classifier">str, optional</span></dt><dd><p>string, currently only “norm” is supported. |
| (Normal distribution) to calculate the |
| theoretical distribution of the data.</p> |
| </dd> |
| <dt><strong>params</strong></dt><dd><p>additional values which need to be provided for |
| a certain distribution. |
| If not provided, the default values are used.</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><a class="reference internal" href="pyspark.mllib.stat.KolmogorovSmirnovTestResult.html#pyspark.mllib.stat.KolmogorovSmirnovTestResult" title="pyspark.mllib.stat.KolmogorovSmirnovTestResult"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.mllib.stat.KolmogorovSmirnovTestResult</span></code></a></dt><dd><p>object containing the test statistic, degrees of freedom, p-value, |
| the method used, and the null hypothesis.</p> |
| </dd> |
| </dl> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">kstest</span> <span class="o">=</span> <span class="n">Statistics</span><span class="o">.</span><span class="n">kolmogorovSmirnovTest</span> |
| <span class="gp">>>> </span><span class="n">data</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="o">-</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">])</span> |
| <span class="gp">>>> </span><span class="n">ksmodel</span> <span class="o">=</span> <span class="n">kstest</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="s2">"norm"</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">ksmodel</span><span class="o">.</span><span class="n">pValue</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span> |
| <span class="go">1.0</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">ksmodel</span><span class="o">.</span><span class="n">statistic</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span> |
| <span class="go">0.175</span> |
| <span class="gp">>>> </span><span class="n">ksmodel</span><span class="o">.</span><span class="n">nullHypothesis</span> |
| <span class="go">'Sample follows theoretical distribution'</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">data</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([</span><span class="mf">2.0</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">,</span> <span class="mf">4.0</span><span class="p">])</span> |
| <span class="gp">>>> </span><span class="n">ksmodel</span> <span class="o">=</span> <span class="n">kstest</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="s2">"norm"</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">ksmodel</span><span class="o">.</span><span class="n">pValue</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span> |
| <span class="go">1.0</span> |
| <span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">ksmodel</span><span class="o">.</span><span class="n">statistic</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span> |
| <span class="go">0.175</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| <a class='left-prev' id="prev-link" href="pyspark.mllib.regression.StreamingLinearRegressionWithSGD.html" title="previous page">StreamingLinearRegressionWithSGD</a> |
| <a class='right-next' id="next-link" href="pyspark.mllib.stat.MultivariateStatisticalSummary.html" title="next page">MultivariateStatisticalSummary</a> |
| |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| |
| <script src="../../_static/js/index.3da636dd464baa7582d2.js"></script> |
| |
| |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| <p> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
