Google Git
Sign in
apache / spark-website / 28656f2c00baf1bc2d26570a16b4f96f9a890723 / . / site / docs / 3.2.2 / api / python / _modules / pyspark / mllib / fpm.html
blob: b84e066c9ffa092cdb995c57811f0c1a96661ed7 [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>pyspark.mllib.fpm &#8212; PySpark 3.2.2 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/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/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="search" title="Search" href="../../../search.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="../../../getting_started/index.html">Getting Started</a>
</li>
<li class="nav-item ">
<a class="nav-link" href="../../../user_guide/index.html">User Guide</a>
</li>
<li class="nav-item ">
<a class="nav-link" href="../../../reference/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 Guide</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">
</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>
<h1>Source code for pyspark.mllib.fpm</h1><div class="highlight"><pre>
<span></span><span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c1"># contributor license agreements. See the NOTICE file distributed with</span>
<span class="c1"># this work for additional information regarding copyright ownership.</span>
<span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c1"># (the &quot;License&quot;); you may not use this file except in compliance with</span>
<span class="c1"># the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">namedtuple</span>
<span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">since</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.common</span> <span class="kn">import</span> <span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">callMLlibFunc</span>
<span class="kn">from</span> <span class="nn">pyspark.mllib.util</span> <span class="kn">import</span> <span class="n">JavaSaveable</span><span class="p">,</span> <span class="n">JavaLoader</span><span class="p">,</span> <span class="n">inherit_doc</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;FPGrowth&#39;</span><span class="p">,</span> <span class="s1">&#39;FPGrowthModel&#39;</span><span class="p">,</span> <span class="s1">&#39;PrefixSpan&#39;</span><span class="p">,</span> <span class="s1">&#39;PrefixSpanModel&#39;</span><span class="p">]</span>
<div class="viewcode-block" id="FPGrowthModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowthModel.html#pyspark.mllib.fpm.FPGrowthModel">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">FPGrowthModel</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">JavaSaveable</span><span class="p">,</span> <span class="n">JavaLoader</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> A FP-Growth model for mining frequent itemsets</span>
<span class="sd"> using the Parallel FP-Growth algorithm.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; data = [[&quot;a&quot;, &quot;b&quot;, &quot;c&quot;], [&quot;a&quot;, &quot;b&quot;, &quot;d&quot;, &quot;e&quot;], [&quot;a&quot;, &quot;c&quot;, &quot;e&quot;], [&quot;a&quot;, &quot;c&quot;, &quot;f&quot;]]</span>
<span class="sd"> &gt;&gt;&gt; rdd = sc.parallelize(data, 2)</span>
<span class="sd"> &gt;&gt;&gt; model = FPGrowth.train(rdd, 0.6, 2)</span>
<span class="sd"> &gt;&gt;&gt; sorted(model.freqItemsets().collect())</span>
<span class="sd"> [FreqItemset(items=[&#39;a&#39;], freq=4), FreqItemset(items=[&#39;c&#39;], freq=3), ...</span>
<span class="sd"> &gt;&gt;&gt; model_path = temp_path + &quot;/fpm&quot;</span>
<span class="sd"> &gt;&gt;&gt; model.save(sc, model_path)</span>
<span class="sd"> &gt;&gt;&gt; sameModel = FPGrowthModel.load(sc, model_path)</span>
<span class="sd"> &gt;&gt;&gt; sorted(model.freqItemsets().collect()) == sorted(sameModel.freqItemsets().collect())</span>
<span class="sd"> True</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="FPGrowthModel.freqItemsets"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowthModel.html#pyspark.mllib.fpm.FPGrowthModel.freqItemsets">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">freqItemsets</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns the frequent itemsets of this model.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">&quot;getFreqItemsets&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="p">(</span><span class="n">FPGrowth</span><span class="o">.</span><span class="n">FreqItemset</span><span class="p">(</span><span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">])))</span></div>
<div class="viewcode-block" id="FPGrowthModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowthModel.html#pyspark.mllib.fpm.FPGrowthModel.load">[docs]</a> <span class="nd">@classmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Load a model from the given path.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">model</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_load_java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span>
<span class="n">wrapper</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">api</span><span class="o">.</span><span class="n">python</span><span class="o">.</span><span class="n">FPGrowthModelWrapper</span><span class="p">(</span><span class="n">model</span><span class="p">)</span>
<span class="k">return</span> <span class="n">FPGrowthModel</span><span class="p">(</span><span class="n">wrapper</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="FPGrowth"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowth.html#pyspark.mllib.fpm.FPGrowth">[docs]</a><span class="k">class</span> <span class="nc">FPGrowth</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> A Parallel FP-growth algorithm to mine frequent itemsets.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="FPGrowth.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.FPGrowth.html#pyspark.mllib.fpm.FPGrowth.train">[docs]</a> <span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">minSupport</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">numPartitions</span><span class="o">=-</span><span class="mi">1</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Computes an FP-Growth model that contains frequent itemsets.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> data : :py:class:`pyspark.RDD`</span>
<span class="sd"> The input data set, each element contains a transaction.</span>
<span class="sd"> minSupport : float, optional</span>
<span class="sd"> The minimal support level.</span>
<span class="sd"> (default: 0.3)</span>
<span class="sd"> numPartitions : int, optional</span>
<span class="sd"> The number of partitions used by parallel FP-growth. A value</span>
<span class="sd"> of -1 will use the same number as input data.</span>
<span class="sd"> (default: -1)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">&quot;trainFPGrowthModel&quot;</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">minSupport</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">numPartitions</span><span class="p">))</span>
<span class="k">return</span> <span class="n">FPGrowthModel</span><span class="p">(</span><span class="n">model</span><span class="p">)</span></div>
<span class="k">class</span> <span class="nc">FreqItemset</span><span class="p">(</span><span class="n">namedtuple</span><span class="p">(</span><span class="s2">&quot;FreqItemset&quot;</span><span class="p">,</span> <span class="p">[</span><span class="s2">&quot;items&quot;</span><span class="p">,</span> <span class="s2">&quot;freq&quot;</span><span class="p">])):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Represents an (items, freq) tuple.</span>
<span class="sd"> .. versionadded:: 1.4.0</span>
<span class="sd"> &quot;&quot;&quot;</span></div>
<div class="viewcode-block" id="PrefixSpanModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.PrefixSpanModel.html#pyspark.mllib.fpm.PrefixSpanModel">[docs]</a><span class="nd">@inherit_doc</span>
<span class="k">class</span> <span class="nc">PrefixSpanModel</span><span class="p">(</span><span class="n">JavaModelWrapper</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Model fitted by PrefixSpan</span>
<span class="sd"> .. versionadded:: 1.6.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; data = [</span>
<span class="sd"> ... [[&quot;a&quot;, &quot;b&quot;], [&quot;c&quot;]],</span>
<span class="sd"> ... [[&quot;a&quot;], [&quot;c&quot;, &quot;b&quot;], [&quot;a&quot;, &quot;b&quot;]],</span>
<span class="sd"> ... [[&quot;a&quot;, &quot;b&quot;], [&quot;e&quot;]],</span>
<span class="sd"> ... [[&quot;f&quot;]]]</span>
<span class="sd"> &gt;&gt;&gt; rdd = sc.parallelize(data, 2)</span>
<span class="sd"> &gt;&gt;&gt; model = PrefixSpan.train(rdd)</span>
<span class="sd"> &gt;&gt;&gt; sorted(model.freqSequences().collect())</span>
<span class="sd"> [FreqSequence(sequence=[[&#39;a&#39;]], freq=3), FreqSequence(sequence=[[&#39;a&#39;], [&#39;a&#39;]], freq=1), ...</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="PrefixSpanModel.freqSequences"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.PrefixSpanModel.html#pyspark.mllib.fpm.PrefixSpanModel.freqSequences">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;1.6.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">freqSequences</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Gets frequent sequences&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">&quot;getFreqSequences&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">PrefixSpan</span><span class="o">.</span><span class="n">FreqSequence</span><span class="p">(</span><span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]))</span></div></div>
<div class="viewcode-block" id="PrefixSpan"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.PrefixSpan.html#pyspark.mllib.fpm.PrefixSpan">[docs]</a><span class="k">class</span> <span class="nc">PrefixSpan</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> A parallel PrefixSpan algorithm to mine frequent sequential patterns.</span>
<span class="sd"> The PrefixSpan algorithm is described in Jian Pei et al (2001) [1]_</span>
<span class="sd"> .. versionadded:: 1.6.0</span>
<span class="sd"> .. [1] Jian Pei et al.,</span>
<span class="sd"> &quot;PrefixSpan,: mining sequential patterns efficiently by prefix-projected pattern growth,&quot;</span>
<span class="sd"> Proceedings 17th International Conference on Data Engineering, Heidelberg,</span>
<span class="sd"> Germany, 2001, pp. 215-224,</span>
<span class="sd"> doi: https://doi.org/10.1109/ICDE.2001.914830</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="PrefixSpan.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.fpm.PrefixSpan.html#pyspark.mllib.fpm.PrefixSpan.train">[docs]</a> <span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">train</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">minSupport</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">maxPatternLength</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxLocalProjDBSize</span><span class="o">=</span><span class="mi">32000000</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Finds the complete set of frequent sequential patterns in the</span>
<span class="sd"> input sequences of itemsets.</span>
<span class="sd"> .. versionadded:: 1.6.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> data : :py:class:`pyspark.RDD`</span>
<span class="sd"> The input data set, each element contains a sequence of</span>
<span class="sd"> itemsets.</span>
<span class="sd"> minSupport : float, optional</span>
<span class="sd"> The minimal support level of the sequential pattern, any</span>
<span class="sd"> pattern that appears more than (minSupport *</span>
<span class="sd"> size-of-the-dataset) times will be output.</span>
<span class="sd"> (default: 0.1)</span>
<span class="sd"> maxPatternLength : int, optional</span>
<span class="sd"> The maximal length of the sequential pattern, any pattern</span>
<span class="sd"> that appears less than maxPatternLength will be output.</span>
<span class="sd"> (default: 10)</span>
<span class="sd"> maxLocalProjDBSize : int, optional</span>
<span class="sd"> The maximum number of items (including delimiters used in the</span>
<span class="sd"> internal storage format) allowed in a projected database before</span>
<span class="sd"> local processing. If a projected database exceeds this size,</span>
<span class="sd"> another iteration of distributed prefix growth is run.</span>
<span class="sd"> (default: 32000000)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">&quot;trainPrefixSpanModel&quot;</span><span class="p">,</span>
<span class="n">data</span><span class="p">,</span> <span class="n">minSupport</span><span class="p">,</span> <span class="n">maxPatternLength</span><span class="p">,</span> <span class="n">maxLocalProjDBSize</span><span class="p">)</span>
<span class="k">return</span> <span class="n">PrefixSpanModel</span><span class="p">(</span><span class="n">model</span><span class="p">)</span></div>
<span class="k">class</span> <span class="nc">FreqSequence</span><span class="p">(</span><span class="n">namedtuple</span><span class="p">(</span><span class="s2">&quot;FreqSequence&quot;</span><span class="p">,</span> <span class="p">[</span><span class="s2">&quot;sequence&quot;</span><span class="p">,</span> <span class="s2">&quot;freq&quot;</span><span class="p">])):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Represents a (sequence, freq) tuple.</span>
<span class="sd"> .. versionadded:: 1.6.0</span>
<span class="sd"> &quot;&quot;&quot;</span></div>
<span class="k">def</span> <span class="nf">_test</span><span class="p">():</span>
<span class="kn">import</span> <span class="nn">doctest</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span>
<span class="kn">import</span> <span class="nn">pyspark.mllib.fpm</span>
<span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">fpm</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span>\
<span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">&quot;local[4]&quot;</span><span class="p">)</span>\
<span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">&quot;mllib.fpm tests&quot;</span><span class="p">)</span>\
<span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span>
<span class="n">globs</span><span class="p">[</span><span class="s1">&#39;sc&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</span>
<span class="kn">import</span> <span class="nn">tempfile</span>
<span class="n">temp_path</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">mkdtemp</span><span class="p">()</span>
<span class="n">globs</span><span class="p">[</span><span class="s1">&#39;temp_path&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">temp_path</span>
<span class="k">try</span><span class="p">:</span>
<span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span> <span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span><span class="p">)</span>
<span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span>
<span class="k">finally</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">shutil</span> <span class="kn">import</span> <span class="n">rmtree</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">rmtree</span><span class="p">(</span><span class="n">temp_path</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">OSError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span>
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</span><span class="p">:</span>
<span class="n">_test</span><span class="p">()</span>
</pre></div>
</div>
<div class='prev-next-bottom'>
</div>
</main>
</div>
</div>
<script src="../../../_static/js/index.3da636dd464baa7582d2.js"></script>
<footer class="footer mt-5 mt-md-0">
<div class="container">
<p>
&copy; Copyright .<br/>
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/>
</p>
</div>
</footer>
</body>
</html>