| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>RandomRDDs — 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.random.RandomRDDs.html" /> |
| <link rel="search" title="Search" href="../../search.html" /> |
| <link rel="next" title="MatrixFactorizationModel" href="pyspark.mllib.recommendation.MatrixFactorizationModel.html" /> |
| <link rel="prev" title="SingularValueDecomposition" href="pyspark.mllib.linalg.distributed.SingularValueDecomposition.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="randomrdds"> |
| <h1>RandomRDDs<a class="headerlink" href="#randomrdds" title="Permalink to this headline">ΒΆ</a></h1> |
| <dl class="py class"> |
| <dt id="pyspark.mllib.random.RandomRDDs"> |
| <em class="property">class </em><code class="sig-prename descclassname">pyspark.mllib.random.</code><code class="sig-name descname">RandomRDDs</code><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generator methods for creating RDDs comprised of i.i.d samples from |
| some distribution.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.1.0.</span></p> |
| </div> |
| <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.random.RandomRDDs.exponentialRDD" title="pyspark.mllib.random.RandomRDDs.exponentialRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exponentialRDD</span></code></a>(sc,Β mean,Β size[,Β β¦])</p></td> |
| <td><p>Generates an RDD comprised of i.i.d.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.exponentialVectorRDD" title="pyspark.mllib.random.RandomRDDs.exponentialVectorRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exponentialVectorRDD</span></code></a>(sc,Β mean,Β numRows,Β numCols)</p></td> |
| <td><p>Generates an RDD comprised of vectors containing i.i.d.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.gammaRDD" title="pyspark.mllib.random.RandomRDDs.gammaRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">gammaRDD</span></code></a>(sc,Β shape,Β scale,Β size[,Β β¦])</p></td> |
| <td><p>Generates an RDD comprised of i.i.d.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.gammaVectorRDD" title="pyspark.mllib.random.RandomRDDs.gammaVectorRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">gammaVectorRDD</span></code></a>(sc,Β shape,Β scale,Β numRows,Β β¦)</p></td> |
| <td><p>Generates an RDD comprised of vectors containing i.i.d.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.logNormalRDD" title="pyspark.mllib.random.RandomRDDs.logNormalRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">logNormalRDD</span></code></a>(sc,Β mean,Β std,Β size[,Β β¦])</p></td> |
| <td><p>Generates an RDD comprised of i.i.d.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.logNormalVectorRDD" title="pyspark.mllib.random.RandomRDDs.logNormalVectorRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">logNormalVectorRDD</span></code></a>(sc,Β mean,Β std,Β numRows,Β β¦)</p></td> |
| <td><p>Generates an RDD comprised of vectors containing i.i.d.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.normalRDD" title="pyspark.mllib.random.RandomRDDs.normalRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">normalRDD</span></code></a>(sc,Β size[,Β numPartitions,Β seed])</p></td> |
| <td><p>Generates an RDD comprised of i.i.d.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.normalVectorRDD" title="pyspark.mllib.random.RandomRDDs.normalVectorRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">normalVectorRDD</span></code></a>(sc,Β numRows,Β numCols[,Β β¦])</p></td> |
| <td><p>Generates an RDD comprised of vectors containing i.i.d.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.poissonRDD" title="pyspark.mllib.random.RandomRDDs.poissonRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">poissonRDD</span></code></a>(sc,Β mean,Β size[,Β numPartitions,Β seed])</p></td> |
| <td><p>Generates an RDD comprised of i.i.d.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.poissonVectorRDD" title="pyspark.mllib.random.RandomRDDs.poissonVectorRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">poissonVectorRDD</span></code></a>(sc,Β mean,Β numRows,Β numCols)</p></td> |
| <td><p>Generates an RDD comprised of vectors containing i.i.d.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.uniformRDD" title="pyspark.mllib.random.RandomRDDs.uniformRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">uniformRDD</span></code></a>(sc,Β size[,Β numPartitions,Β seed])</p></td> |
| <td><p>Generates an RDD comprised of i.i.d.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#pyspark.mllib.random.RandomRDDs.uniformVectorRDD" title="pyspark.mllib.random.RandomRDDs.uniformVectorRDD"><code class="xref py py-obj docutils literal notranslate"><span class="pre">uniformVectorRDD</span></code></a>(sc,Β numRows,Β numCols[,Β β¦])</p></td> |
| <td><p>Generates an RDD comprised of vectors containing i.i.d.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p class="rubric">Methods Documentation</p> |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.exponentialRDD"> |
| <em class="property">static </em><code class="sig-name descname">exponentialRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">mean</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">size</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → pyspark.rdd.RDD<span class="p">[</span>float<span class="p">]</span><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.exponentialRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.exponentialRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of i.i.d. samples from the Exponential |
| distribution with the input mean.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.3.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>SparkContext used to create the RDD.</p> |
| </dd> |
| <dt><strong>mean</strong><span class="classifier">float</span></dt><dd><p>Mean, or 1 / lambda, for the Exponential distribution.</p> |
| </dd> |
| <dt><strong>size</strong><span class="classifier">int</span></dt><dd><p>Size of the RDD.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>).</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of float comprised of i.i.d. samples ~ Exp(mean).</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">mean</span> <span class="o">=</span> <span class="mf">2.0</span> |
| <span class="gp">>>> </span><span class="n">x</span> <span class="o">=</span> <span class="n">RandomRDDs</span><span class="o">.</span><span class="n">exponentialRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="mi">1000</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">stats</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="n">stats</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> |
| <span class="go">1000</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">stdev</span><span class="p">()</span> <span class="o">-</span> <span class="n">sqrt</span><span class="p">(</span><span class="n">mean</span><span class="p">))</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.exponentialVectorRDD"> |
| <em class="property">static </em><code class="sig-name descname">exponentialVectorRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">mean</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">numRows</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numCols</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</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><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.exponentialVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.exponentialVectorRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn |
| from the Exponential distribution with the input mean.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.3.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>SparkContext used to create the RDD.</p> |
| </dd> |
| <dt><strong>mean</strong><span class="classifier">float</span></dt><dd><p>Mean, or 1 / lambda, for the Exponential distribution.</p> |
| </dd> |
| <dt><strong>numRows</strong><span class="classifier">int</span></dt><dd><p>Number of Vectors in the RDD.</p> |
| </dd> |
| <dt><strong>numCols</strong><span class="classifier">int</span></dt><dd><p>Number of elements in each Vector.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>)</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of Vector with vectors containing i.i.d. samples ~ Exp(mean).</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">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| <span class="gp">>>> </span><span class="n">mean</span> <span class="o">=</span> <span class="mf">0.5</span> |
| <span class="gp">>>> </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">RandomRDDs</span><span class="o">.</span><span class="n">exponentialVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">mat</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">mat</span><span class="p">(</span><span class="n">rdd</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span> |
| <span class="gp">>>> </span><span class="n">mat</span><span class="o">.</span><span class="n">shape</span> |
| <span class="go">(100, 100)</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">std</span><span class="p">()</span> <span class="o">-</span> <span class="n">sqrt</span><span class="p">(</span><span class="n">mean</span><span class="p">))</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.gammaRDD"> |
| <em class="property">static </em><code class="sig-name descname">gammaRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">shape</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">scale</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">size</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → pyspark.rdd.RDD<span class="p">[</span>float<span class="p">]</span><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.gammaRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.gammaRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of i.i.d. samples from the Gamma |
| distribution with the input shape and scale.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.3.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>SparkContext used to create the RDD.</p> |
| </dd> |
| <dt><strong>shape</strong><span class="classifier">float</span></dt><dd><p>shape (> 0) parameter for the Gamma distribution</p> |
| </dd> |
| <dt><strong>scale</strong><span class="classifier">float</span></dt><dd><p>scale (> 0) parameter for the Gamma distribution</p> |
| </dd> |
| <dt><strong>size</strong><span class="classifier">int</span></dt><dd><p>Size of the RDD.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>).</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of float comprised of i.i.d. samples ~ Gamma(shape, scale).</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">math</span> <span class="kn">import</span> <span class="n">sqrt</span> |
| <span class="gp">>>> </span><span class="n">shape</span> <span class="o">=</span> <span class="mf">1.0</span> |
| <span class="gp">>>> </span><span class="n">scale</span> <span class="o">=</span> <span class="mf">2.0</span> |
| <span class="gp">>>> </span><span class="n">expMean</span> <span class="o">=</span> <span class="n">shape</span> <span class="o">*</span> <span class="n">scale</span> |
| <span class="gp">>>> </span><span class="n">expStd</span> <span class="o">=</span> <span class="n">sqrt</span><span class="p">(</span><span class="n">shape</span> <span class="o">*</span> <span class="n">scale</span> <span class="o">*</span> <span class="n">scale</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">x</span> <span class="o">=</span> <span class="n">RandomRDDs</span><span class="o">.</span><span class="n">gammaRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">shape</span><span class="p">,</span> <span class="n">scale</span><span class="p">,</span> <span class="mi">1000</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">stats</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="n">stats</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> |
| <span class="go">1000</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="n">expMean</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">stdev</span><span class="p">()</span> <span class="o">-</span> <span class="n">expStd</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.gammaVectorRDD"> |
| <em class="property">static </em><code class="sig-name descname">gammaVectorRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">shape</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">scale</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">numRows</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numCols</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</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><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.gammaVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.gammaVectorRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn |
| from the Gamma distribution.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.3.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>SparkContext used to create the RDD.</p> |
| </dd> |
| <dt><strong>shape</strong><span class="classifier">float</span></dt><dd><p>Shape (> 0) of the Gamma distribution</p> |
| </dd> |
| <dt><strong>scale</strong><span class="classifier">float</span></dt><dd><p>Scale (> 0) of the Gamma distribution</p> |
| </dd> |
| <dt><strong>numRows</strong><span class="classifier">int</span></dt><dd><p>Number of Vectors in the RDD.</p> |
| </dd> |
| <dt><strong>numCols</strong><span class="classifier">int</span></dt><dd><p>Number of elements in each Vector.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>).</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional,</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of Vector with vectors containing i.i.d. samples ~ Gamma(shape, scale).</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">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span> |
| <span class="gp">>>> </span><span class="n">shape</span> <span class="o">=</span> <span class="mf">1.0</span> |
| <span class="gp">>>> </span><span class="n">scale</span> <span class="o">=</span> <span class="mf">2.0</span> |
| <span class="gp">>>> </span><span class="n">expMean</span> <span class="o">=</span> <span class="n">shape</span> <span class="o">*</span> <span class="n">scale</span> |
| <span class="gp">>>> </span><span class="n">expStd</span> <span class="o">=</span> <span class="n">sqrt</span><span class="p">(</span><span class="n">shape</span> <span class="o">*</span> <span class="n">scale</span> <span class="o">*</span> <span class="n">scale</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">mat</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matrix</span><span class="p">(</span><span class="n">RandomRDDs</span><span class="o">.</span><span class="n">gammaVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">shape</span><span class="p">,</span> <span class="n">scale</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span> |
| <span class="gp">>>> </span><span class="n">mat</span><span class="o">.</span><span class="n">shape</span> |
| <span class="go">(100, 100)</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="n">expMean</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.1</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">std</span><span class="p">()</span> <span class="o">-</span> <span class="n">expStd</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.1</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.logNormalRDD"> |
| <em class="property">static </em><code class="sig-name descname">logNormalRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">mean</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">std</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">size</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → pyspark.rdd.RDD<span class="p">[</span>float<span class="p">]</span><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.logNormalRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.logNormalRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of i.i.d. samples from the log normal |
| distribution with the input mean and standard distribution.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.3.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>used to create the RDD.</p> |
| </dd> |
| <dt><strong>mean</strong><span class="classifier">float</span></dt><dd><p>mean for the log Normal distribution</p> |
| </dd> |
| <dt><strong>std</strong><span class="classifier">float</span></dt><dd><p>std for the log Normal distribution</p> |
| </dd> |
| <dt><strong>size</strong><span class="classifier">int</span></dt><dd><p>Size of the RDD.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>).</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt>RDD of float comprised of i.i.d. samples ~ log N(mean, std).</dt><dd></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">math</span> <span class="kn">import</span> <span class="n">sqrt</span><span class="p">,</span> <span class="n">exp</span> |
| <span class="gp">>>> </span><span class="n">mean</span> <span class="o">=</span> <span class="mf">0.0</span> |
| <span class="gp">>>> </span><span class="n">std</span> <span class="o">=</span> <span class="mf">1.0</span> |
| <span class="gp">>>> </span><span class="n">expMean</span> <span class="o">=</span> <span class="n">exp</span><span class="p">(</span><span class="n">mean</span> <span class="o">+</span> <span class="mf">0.5</span> <span class="o">*</span> <span class="n">std</span> <span class="o">*</span> <span class="n">std</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">expStd</span> <span class="o">=</span> <span class="n">sqrt</span><span class="p">((</span><span class="n">exp</span><span class="p">(</span><span class="n">std</span> <span class="o">*</span> <span class="n">std</span><span class="p">)</span> <span class="o">-</span> <span class="mf">1.0</span><span class="p">)</span> <span class="o">*</span> <span class="n">exp</span><span class="p">(</span><span class="mf">2.0</span> <span class="o">*</span> <span class="n">mean</span> <span class="o">+</span> <span class="n">std</span> <span class="o">*</span> <span class="n">std</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="n">x</span> <span class="o">=</span> <span class="n">RandomRDDs</span><span class="o">.</span><span class="n">logNormalRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="n">std</span><span class="p">,</span> <span class="mi">1000</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">stats</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="n">stats</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> |
| <span class="go">1000</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="n">expMean</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">stdev</span><span class="p">()</span> <span class="o">-</span> <span class="n">expStd</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.logNormalVectorRDD"> |
| <em class="property">static </em><code class="sig-name descname">logNormalVectorRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">mean</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">std</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">numRows</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numCols</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</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><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.logNormalVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.logNormalVectorRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn |
| from the log normal distribution.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.3.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>SparkContext used to create the RDD.</p> |
| </dd> |
| <dt><strong>mean</strong><span class="classifier">float</span></dt><dd><p>Mean of the log normal distribution</p> |
| </dd> |
| <dt><strong>std</strong><span class="classifier">float</span></dt><dd><p>Standard Deviation of the log normal distribution</p> |
| </dd> |
| <dt><strong>numRows</strong><span class="classifier">int</span></dt><dd><p>Number of Vectors in the RDD.</p> |
| </dd> |
| <dt><strong>numCols</strong><span class="classifier">int</span></dt><dd><p>Number of elements in each Vector.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>).</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of Vector with vectors containing i.i.d. samples ~ log <cite>N(mean, std)</cite>.</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">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span><span class="p">,</span> <span class="n">exp</span> |
| <span class="gp">>>> </span><span class="n">mean</span> <span class="o">=</span> <span class="mf">0.0</span> |
| <span class="gp">>>> </span><span class="n">std</span> <span class="o">=</span> <span class="mf">1.0</span> |
| <span class="gp">>>> </span><span class="n">expMean</span> <span class="o">=</span> <span class="n">exp</span><span class="p">(</span><span class="n">mean</span> <span class="o">+</span> <span class="mf">0.5</span> <span class="o">*</span> <span class="n">std</span> <span class="o">*</span> <span class="n">std</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">expStd</span> <span class="o">=</span> <span class="n">sqrt</span><span class="p">((</span><span class="n">exp</span><span class="p">(</span><span class="n">std</span> <span class="o">*</span> <span class="n">std</span><span class="p">)</span> <span class="o">-</span> <span class="mf">1.0</span><span class="p">)</span> <span class="o">*</span> <span class="n">exp</span><span class="p">(</span><span class="mf">2.0</span> <span class="o">*</span> <span class="n">mean</span> <span class="o">+</span> <span class="n">std</span> <span class="o">*</span> <span class="n">std</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="n">m</span> <span class="o">=</span> <span class="n">RandomRDDs</span><span class="o">.</span><span class="n">logNormalVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="n">std</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="n">mat</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matrix</span><span class="p">(</span><span class="n">m</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">mat</span><span class="o">.</span><span class="n">shape</span> |
| <span class="go">(100, 100)</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="n">expMean</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.1</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">std</span><span class="p">()</span> <span class="o">-</span> <span class="n">expStd</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.1</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.normalRDD"> |
| <em class="property">static </em><code class="sig-name descname">normalRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">size</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → pyspark.rdd.RDD<span class="p">[</span>float<span class="p">]</span><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.normalRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.normalRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of i.i.d. samples from the standard normal |
| distribution.</p> |
| <p>To transform the distribution in the generated RDD from standard normal |
| to some other normal N(mean, sigma^2), use |
| <code class="docutils literal notranslate"><span class="pre">RandomRDDs.normal(sc,</span> <span class="pre">n,</span> <span class="pre">p,</span> <span class="pre">seed).map(lambda</span> <span class="pre">v:</span> <span class="pre">mean</span> <span class="pre">+</span> <span class="pre">sigma</span> <span class="pre">*</span> <span class="pre">v)</span></code></p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.1.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>used to create the RDD.</p> |
| </dd> |
| <dt><strong>size</strong><span class="classifier">int</span></dt><dd><p>Size of the RDD.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>).</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of float comprised of i.i.d. samples ~ N(0.0, 1.0).</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">RandomRDDs</span><span class="o">.</span><span class="n">normalRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="mi">1000</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">stats</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="n">stats</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> |
| <span class="go">1000</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="mf">0.0</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.1</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">stdev</span><span class="p">()</span> <span class="o">-</span> <span class="mf">1.0</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.1</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.normalVectorRDD"> |
| <em class="property">static </em><code class="sig-name descname">normalVectorRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">numRows</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numCols</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</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><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.normalVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.normalVectorRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn |
| from the standard normal distribution.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.1.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>SparkContext used to create the RDD.</p> |
| </dd> |
| <dt><strong>numRows</strong><span class="classifier">int</span></dt><dd><p>Number of Vectors in the RDD.</p> |
| </dd> |
| <dt><strong>numCols</strong><span class="classifier">int</span></dt><dd><p>Number of elements in each Vector.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>).</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of Vector with vectors containing i.i.d. samples ~ <cite>N(0.0, 1.0)</cite>.</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">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| <span class="gp">>>> </span><span class="n">mat</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matrix</span><span class="p">(</span><span class="n">RandomRDDs</span><span class="o">.</span><span class="n">normalVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span> |
| <span class="gp">>>> </span><span class="n">mat</span><span class="o">.</span><span class="n">shape</span> |
| <span class="go">(100, 100)</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="mf">0.0</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.1</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">std</span><span class="p">()</span> <span class="o">-</span> <span class="mf">1.0</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.1</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.poissonRDD"> |
| <em class="property">static </em><code class="sig-name descname">poissonRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">mean</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">size</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → pyspark.rdd.RDD<span class="p">[</span>float<span class="p">]</span><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.poissonRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.poissonRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of i.i.d. samples from the Poisson |
| distribution with the input mean.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.1.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>SparkContext used to create the RDD.</p> |
| </dd> |
| <dt><strong>mean</strong><span class="classifier">float</span></dt><dd><p>Mean, or lambda, for the Poisson distribution.</p> |
| </dd> |
| <dt><strong>size</strong><span class="classifier">int</span></dt><dd><p>Size of the RDD.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>).</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of float comprised of i.i.d. samples ~ Pois(mean).</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">mean</span> <span class="o">=</span> <span class="mf">100.0</span> |
| <span class="gp">>>> </span><span class="n">x</span> <span class="o">=</span> <span class="n">RandomRDDs</span><span class="o">.</span><span class="n">poissonRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="mi">1000</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">stats</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">stats</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="n">stats</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> |
| <span class="go">1000</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">stdev</span><span class="p">()</span> <span class="o">-</span> <span class="n">sqrt</span><span class="p">(</span><span class="n">mean</span><span class="p">))</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.poissonVectorRDD"> |
| <em class="property">static </em><code class="sig-name descname">poissonVectorRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">mean</span><span class="p">:</span> <span class="n">float</span></em>, <em class="sig-param"><span class="n">numRows</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numCols</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</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><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.poissonVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.poissonVectorRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn |
| from the Poisson distribution with the input mean.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.1.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>SparkContext used to create the RDD.</p> |
| </dd> |
| <dt><strong>mean</strong><span class="classifier">float</span></dt><dd><p>Mean, or lambda, for the Poisson distribution.</p> |
| </dd> |
| <dt><strong>numRows</strong><span class="classifier">float</span></dt><dd><p>Number of Vectors in the RDD.</p> |
| </dd> |
| <dt><strong>numCols</strong><span class="classifier">int</span></dt><dd><p>Number of elements in each Vector.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>)</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of Vector with vectors containing i.i.d. samples ~ Pois(mean).</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">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| <span class="gp">>>> </span><span class="n">mean</span> <span class="o">=</span> <span class="mf">100.0</span> |
| <span class="gp">>>> </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">RandomRDDs</span><span class="o">.</span><span class="n">poissonVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">mat</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">mat</span><span class="p">(</span><span class="n">rdd</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span> |
| <span class="gp">>>> </span><span class="n">mat</span><span class="o">.</span><span class="n">shape</span> |
| <span class="go">(100, 100)</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> <span class="o">-</span> <span class="n">mean</span><span class="p">)</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span> |
| <span class="gp">>>> </span><span class="nb">abs</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">std</span><span class="p">()</span> <span class="o">-</span> <span class="n">sqrt</span><span class="p">(</span><span class="n">mean</span><span class="p">))</span> <span class="o"><</span> <span class="mf">0.5</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.uniformRDD"> |
| <em class="property">static </em><code class="sig-name descname">uniformRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">size</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</span> → pyspark.rdd.RDD<span class="p">[</span>float<span class="p">]</span><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.uniformRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.uniformRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of i.i.d. samples from the |
| uniform distribution U(0.0, 1.0).</p> |
| <p>To transform the distribution in the generated RDD from U(0.0, 1.0) |
| to U(a, b), use |
| <code class="docutils literal notranslate"><span class="pre">RandomRDDs.uniformRDD(sc,</span> <span class="pre">n,</span> <span class="pre">p,</span> <span class="pre">seed).map(lambda</span> <span class="pre">v:</span> <span class="pre">a</span> <span class="pre">+</span> <span class="pre">(b</span> <span class="pre">-</span> <span class="pre">a)</span> <span class="pre">*</span> <span class="pre">v)</span></code></p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.1.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>used to create the RDD.</p> |
| </dd> |
| <dt><strong>size</strong><span class="classifier">int</span></dt><dd><p>Size of the RDD.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD (default: <cite>sc.defaultParallelism</cite>).</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Random seed (default: a random long integer).</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of float comprised of i.i.d. samples ~ <cite>U(0.0, 1.0)</cite>.</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">RandomRDDs</span><span class="o">.</span><span class="n">uniformRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="mi">100</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> |
| <span class="go">100</span> |
| <span class="gp">>>> </span><span class="nb">max</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o"><=</span> <span class="mf">1.0</span> <span class="ow">and</span> <span class="nb">min</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">>=</span> <span class="mf">0.0</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="n">RandomRDDs</span><span class="o">.</span><span class="n">uniformRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="mi">4</span><span class="p">)</span><span class="o">.</span><span class="n">getNumPartitions</span><span class="p">()</span> |
| <span class="go">4</span> |
| <span class="gp">>>> </span><span class="n">parts</span> <span class="o">=</span> <span class="n">RandomRDDs</span><span class="o">.</span><span class="n">uniformRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="mi">100</span><span class="p">,</span> <span class="n">seed</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span><span class="o">.</span><span class="n">getNumPartitions</span><span class="p">()</span> |
| <span class="gp">>>> </span><span class="n">parts</span> <span class="o">==</span> <span class="n">sc</span><span class="o">.</span><span class="n">defaultParallelism</span> |
| <span class="go">True</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt id="pyspark.mllib.random.RandomRDDs.uniformVectorRDD"> |
| <em class="property">static </em><code class="sig-name descname">uniformVectorRDD</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">sc</span><span class="p">:</span> <span class="n">pyspark.context.SparkContext</span></em>, <em class="sig-param"><span class="n">numRows</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numCols</span><span class="p">:</span> <span class="n">int</span></em>, <em class="sig-param"><span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em>, <em class="sig-param"><span class="n">seed</span><span class="p">:</span> <span class="n">Optional<span class="p">[</span>int<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">None</span></em><span class="sig-paren">)</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><a class="reference internal" href="../../_modules/pyspark/mllib/random.html#RandomRDDs.uniformVectorRDD"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.mllib.random.RandomRDDs.uniformVectorRDD" title="Permalink to this definition">ΒΆ</a></dt> |
| <dd><p>Generates an RDD comprised of vectors containing i.i.d. samples drawn |
| from the uniform distribution U(0.0, 1.0).</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 1.1.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>sc</strong><span class="classifier"><a class="reference internal" href="pyspark.SparkContext.html#pyspark.SparkContext" title="pyspark.SparkContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.SparkContext</span></code></a></span></dt><dd><p>SparkContext used to create the RDD.</p> |
| </dd> |
| <dt><strong>numRows</strong><span class="classifier">int</span></dt><dd><p>Number of Vectors in the RDD.</p> |
| </dd> |
| <dt><strong>numCols</strong><span class="classifier">int</span></dt><dd><p>Number of elements in each Vector.</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>Number of partitions in the RDD.</p> |
| </dd> |
| <dt><strong>seed</strong><span class="classifier">int, optional</span></dt><dd><p>Seed for the RNG that generates the seed for the generator in each partition.</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><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></dt><dd><p>RDD of Vector with vectors containing i.i.d samples ~ <cite>U(0.0, 1.0)</cite>.</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">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| <span class="gp">>>> </span><span class="n">mat</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matrix</span><span class="p">(</span><span class="n">RandomRDDs</span><span class="o">.</span><span class="n">uniformVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span> |
| <span class="gp">>>> </span><span class="n">mat</span><span class="o">.</span><span class="n">shape</span> |
| <span class="go">(10, 10)</span> |
| <span class="gp">>>> </span><span class="n">mat</span><span class="o">.</span><span class="n">max</span><span class="p">()</span> <span class="o"><=</span> <span class="mf">1.0</span> <span class="ow">and</span> <span class="n">mat</span><span class="o">.</span><span class="n">min</span><span class="p">()</span> <span class="o">>=</span> <span class="mf">0.0</span> |
| <span class="go">True</span> |
| <span class="gp">>>> </span><span class="n">RandomRDDs</span><span class="o">.</span><span class="n">uniformVectorRDD</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="mi">4</span><span class="p">)</span><span class="o">.</span><span class="n">getNumPartitions</span><span class="p">()</span> |
| <span class="go">4</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.linalg.distributed.SingularValueDecomposition.html" title="previous page">SingularValueDecomposition</a> |
| <a class='right-next' id="next-link" href="pyspark.mllib.recommendation.MatrixFactorizationModel.html" title="next page">MatrixFactorizationModel</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> |