Google Git
Sign in
apache / spark-website / 28656f2c00baf1bc2d26570a16b4f96f9a890723 / . / site / docs / 3.2.2 / api / python / _modules / pyspark / ml / stat.html
blob: d7467948561e9880631b83ccefe3e8f1af9562a2 [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>pyspark.ml.stat &#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.ml.stat</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">pyspark</span> <span class="kn">import</span> <span class="n">since</span><span class="p">,</span> <span class="n">SparkContext</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.common</span> <span class="kn">import</span> <span class="n">_java2py</span><span class="p">,</span> <span class="n">_py2java</span>
<span class="kn">from</span> <span class="nn">pyspark.ml.wrapper</span> <span class="kn">import</span> <span class="n">JavaWrapper</span><span class="p">,</span> <span class="n">_jvm</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.column</span> <span class="kn">import</span> <span class="n">Column</span><span class="p">,</span> <span class="n">_to_seq</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.functions</span> <span class="kn">import</span> <span class="n">lit</span>
<div class="viewcode-block" id="ChiSquareTest"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.ChiSquareTest.html#pyspark.ml.stat.ChiSquareTest">[docs]</a><span class="k">class</span> <span class="nc">ChiSquareTest</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Conduct Pearson&#39;s independence test for every feature against the label. For each feature,</span>
<span class="sd"> the (feature, label) pairs are converted into a contingency matrix for which the Chi-squared</span>
<span class="sd"> statistic is computed. All label and feature values must be categorical.</span>
<span class="sd"> The null hypothesis is that the occurrence of the outcomes is statistically independent.</span>
<span class="sd"> .. versionadded:: 2.2.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="ChiSquareTest.test"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.ChiSquareTest.html#pyspark.ml.stat.ChiSquareTest.test">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">test</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">featuresCol</span><span class="p">,</span> <span class="n">labelCol</span><span class="p">,</span> <span class="n">flatten</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Perform a Pearson&#39;s independence test using dataset.</span>
<span class="sd"> .. versionadded:: 2.2.0</span>
<span class="sd"> .. versionchanged:: 3.1.0</span>
<span class="sd"> Added optional ``flatten`` argument.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> DataFrame of categorical labels and categorical features.</span>
<span class="sd"> Real-valued features will be treated as categorical for each distinct value.</span>
<span class="sd"> featuresCol : str</span>
<span class="sd"> Name of features column in dataset, of type `Vector` (`VectorUDT`).</span>
<span class="sd"> labelCol : str</span>
<span class="sd"> Name of label column in dataset, of any numerical type.</span>
<span class="sd"> flatten : bool, optional</span>
<span class="sd"> if True, flattens the returned dataframe.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> DataFrame containing the test result for every feature against the label.</span>
<span class="sd"> If flatten is True, this DataFrame will contain one row per feature with the following</span>
<span class="sd"> fields:</span>
<span class="sd"> - `featureIndex: int`</span>
<span class="sd"> - `pValue: float`</span>
<span class="sd"> - `degreesOfFreedom: int`</span>
<span class="sd"> - `statistic: float`</span>
<span class="sd"> If flatten is False, this DataFrame will contain a single Row with the following fields:</span>
<span class="sd"> - `pValues: Vector`</span>
<span class="sd"> - `degreesOfFreedom: Array[int]`</span>
<span class="sd"> - `statistics: Vector`</span>
<span class="sd"> Each of these fields has one value per feature.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.stat import ChiSquareTest</span>
<span class="sd"> &gt;&gt;&gt; dataset = [[0, Vectors.dense([0, 0, 1])],</span>
<span class="sd"> ... [0, Vectors.dense([1, 0, 1])],</span>
<span class="sd"> ... [1, Vectors.dense([2, 1, 1])],</span>
<span class="sd"> ... [1, Vectors.dense([3, 1, 1])]]</span>
<span class="sd"> &gt;&gt;&gt; dataset = spark.createDataFrame(dataset, [&quot;label&quot;, &quot;features&quot;])</span>
<span class="sd"> &gt;&gt;&gt; chiSqResult = ChiSquareTest.test(dataset, &#39;features&#39;, &#39;label&#39;)</span>
<span class="sd"> &gt;&gt;&gt; chiSqResult.select(&quot;degreesOfFreedom&quot;).collect()[0]</span>
<span class="sd"> Row(degreesOfFreedom=[3, 1, 0])</span>
<span class="sd"> &gt;&gt;&gt; chiSqResult = ChiSquareTest.test(dataset, &#39;features&#39;, &#39;label&#39;, True)</span>
<span class="sd"> &gt;&gt;&gt; row = chiSqResult.orderBy(&quot;featureIndex&quot;).collect()</span>
<span class="sd"> &gt;&gt;&gt; row[0].statistic</span>
<span class="sd"> 4.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span>
<span class="n">javaTestObj</span> <span class="o">=</span> <span class="n">_jvm</span><span class="p">()</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">ml</span><span class="o">.</span><span class="n">stat</span><span class="o">.</span><span class="n">ChiSquareTest</span>
<span class="n">args</span> <span class="o">=</span> <span class="p">[</span><span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">arg</span><span class="p">)</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">featuresCol</span><span class="p">,</span> <span class="n">labelCol</span><span class="p">,</span> <span class="n">flatten</span><span class="p">)]</span>
<span class="k">return</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">javaTestObj</span><span class="o">.</span><span class="n">test</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">))</span></div></div>
<div class="viewcode-block" id="Correlation"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Correlation.html#pyspark.ml.stat.Correlation">[docs]</a><span class="k">class</span> <span class="nc">Correlation</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Compute the correlation matrix for the input dataset of Vectors using the specified method.</span>
<span class="sd"> Methods currently supported: `pearson` (default), `spearman`.</span>
<span class="sd"> .. versionadded:: 2.2.0</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> For Spearman, a rank correlation, we need to create an RDD[Double] for each column</span>
<span class="sd"> and sort it in order to retrieve the ranks and then join the columns back into an RDD[Vector],</span>
<span class="sd"> which is fairly costly. Cache the input Dataset before calling corr with `method = &#39;spearman&#39;`</span>
<span class="sd"> to avoid recomputing the common lineage.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="Correlation.corr"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Correlation.html#pyspark.ml.stat.Correlation.corr">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">corr</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">column</span><span class="p">,</span> <span class="n">method</span><span class="o">=</span><span class="s2">&quot;pearson&quot;</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Compute the correlation matrix with specified method using dataset.</span>
<span class="sd"> .. versionadded:: 2.2.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> A DataFrame.</span>
<span class="sd"> column : str</span>
<span class="sd"> The name of the column of vectors for which the correlation coefficient needs</span>
<span class="sd"> to be computed. This must be a column of the dataset, and it must contain</span>
<span class="sd"> Vector objects.</span>
<span class="sd"> method : str, optional</span>
<span class="sd"> String specifying the method to use for computing correlation.</span>
<span class="sd"> Supported: `pearson` (default), `spearman`.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> A DataFrame that contains the correlation matrix of the column of vectors. This</span>
<span class="sd"> DataFrame contains a single row and a single column of name `METHODNAME(COLUMN)`.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import DenseMatrix, Vectors</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.stat import Correlation</span>
<span class="sd"> &gt;&gt;&gt; dataset = [[Vectors.dense([1, 0, 0, -2])],</span>
<span class="sd"> ... [Vectors.dense([4, 5, 0, 3])],</span>
<span class="sd"> ... [Vectors.dense([6, 7, 0, 8])],</span>
<span class="sd"> ... [Vectors.dense([9, 0, 0, 1])]]</span>
<span class="sd"> &gt;&gt;&gt; dataset = spark.createDataFrame(dataset, [&#39;features&#39;])</span>
<span class="sd"> &gt;&gt;&gt; pearsonCorr = Correlation.corr(dataset, &#39;features&#39;, &#39;pearson&#39;).collect()[0][0]</span>
<span class="sd"> &gt;&gt;&gt; print(str(pearsonCorr).replace(&#39;nan&#39;, &#39;NaN&#39;))</span>
<span class="sd"> DenseMatrix([[ 1. , 0.0556..., NaN, 0.4004...],</span>
<span class="sd"> [ 0.0556..., 1. , NaN, 0.9135...],</span>
<span class="sd"> [ NaN, NaN, 1. , NaN],</span>
<span class="sd"> [ 0.4004..., 0.9135..., NaN, 1. ]])</span>
<span class="sd"> &gt;&gt;&gt; spearmanCorr = Correlation.corr(dataset, &#39;features&#39;, method=&#39;spearman&#39;).collect()[0][0]</span>
<span class="sd"> &gt;&gt;&gt; print(str(spearmanCorr).replace(&#39;nan&#39;, &#39;NaN&#39;))</span>
<span class="sd"> DenseMatrix([[ 1. , 0.1054..., NaN, 0.4 ],</span>
<span class="sd"> [ 0.1054..., 1. , NaN, 0.9486... ],</span>
<span class="sd"> [ NaN, NaN, 1. , NaN],</span>
<span class="sd"> [ 0.4 , 0.9486... , NaN, 1. ]])</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span>
<span class="n">javaCorrObj</span> <span class="o">=</span> <span class="n">_jvm</span><span class="p">()</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">ml</span><span class="o">.</span><span class="n">stat</span><span class="o">.</span><span class="n">Correlation</span>
<span class="n">args</span> <span class="o">=</span> <span class="p">[</span><span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">arg</span><span class="p">)</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">column</span><span class="p">,</span> <span class="n">method</span><span class="p">)]</span>
<span class="k">return</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">javaCorrObj</span><span class="o">.</span><span class="n">corr</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">))</span></div></div>
<div class="viewcode-block" id="KolmogorovSmirnovTest"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.KolmogorovSmirnovTest.html#pyspark.ml.stat.KolmogorovSmirnovTest">[docs]</a><span class="k">class</span> <span class="nc">KolmogorovSmirnovTest</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Conduct the two-sided Kolmogorov Smirnov (KS) test for data sampled from a continuous</span>
<span class="sd"> distribution.</span>
<span class="sd"> By comparing the largest difference between the empirical cumulative</span>
<span class="sd"> distribution of the sample data and the theoretical distribution we can provide a test for the</span>
<span class="sd"> the null hypothesis that the sample data comes from that theoretical distribution.</span>
<span class="sd"> .. versionadded:: 2.4.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="KolmogorovSmirnovTest.test"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.KolmogorovSmirnovTest.html#pyspark.ml.stat.KolmogorovSmirnovTest.test">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">test</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">sampleCol</span><span class="p">,</span> <span class="n">distName</span><span class="p">,</span> <span class="o">*</span><span class="n">params</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Conduct a one-sample, two-sided Kolmogorov-Smirnov test for probability distribution</span>
<span class="sd"> equality. Currently supports the normal distribution, taking as parameters the mean and</span>
<span class="sd"> standard deviation.</span>
<span class="sd"> .. versionadded:: 2.4.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span>
<span class="sd"> a Dataset or a DataFrame containing the sample of data to test.</span>
<span class="sd"> sampleCol : str</span>
<span class="sd"> Name of sample column in dataset, of any numerical type.</span>
<span class="sd"> distName : str</span>
<span class="sd"> a `string` name for a theoretical distribution, currently only support &quot;norm&quot;.</span>
<span class="sd"> params : float</span>
<span class="sd"> a list of `float` values specifying the parameters to be used for the theoretical</span>
<span class="sd"> distribution. For &quot;norm&quot; distribution, the parameters includes mean and variance.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> A DataFrame that contains the Kolmogorov-Smirnov test result for the input sampled data.</span>
<span class="sd"> This DataFrame will contain a single Row with the following fields:</span>
<span class="sd"> - `pValue: Double`</span>
<span class="sd"> - `statistic: Double`</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.stat import KolmogorovSmirnovTest</span>
<span class="sd"> &gt;&gt;&gt; dataset = [[-1.0], [0.0], [1.0]]</span>
<span class="sd"> &gt;&gt;&gt; dataset = spark.createDataFrame(dataset, [&#39;sample&#39;])</span>
<span class="sd"> &gt;&gt;&gt; ksResult = KolmogorovSmirnovTest.test(dataset, &#39;sample&#39;, &#39;norm&#39;, 0.0, 1.0).first()</span>
<span class="sd"> &gt;&gt;&gt; round(ksResult.pValue, 3)</span>
<span class="sd"> 1.0</span>
<span class="sd"> &gt;&gt;&gt; round(ksResult.statistic, 3)</span>
<span class="sd"> 0.175</span>
<span class="sd"> &gt;&gt;&gt; dataset = [[2.0], [3.0], [4.0]]</span>
<span class="sd"> &gt;&gt;&gt; dataset = spark.createDataFrame(dataset, [&#39;sample&#39;])</span>
<span class="sd"> &gt;&gt;&gt; ksResult = KolmogorovSmirnovTest.test(dataset, &#39;sample&#39;, &#39;norm&#39;, 3.0, 1.0).first()</span>
<span class="sd"> &gt;&gt;&gt; round(ksResult.pValue, 3)</span>
<span class="sd"> 1.0</span>
<span class="sd"> &gt;&gt;&gt; round(ksResult.statistic, 3)</span>
<span class="sd"> 0.175</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span>
<span class="n">javaTestObj</span> <span class="o">=</span> <span class="n">_jvm</span><span class="p">()</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">ml</span><span class="o">.</span><span class="n">stat</span><span class="o">.</span><span class="n">KolmogorovSmirnovTest</span>
<span class="n">dataset</span> <span class="o">=</span> <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">dataset</span><span class="p">)</span>
<span class="n">params</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">param</span><span class="p">)</span> <span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="n">params</span><span class="p">]</span>
<span class="k">return</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">javaTestObj</span><span class="o">.</span><span class="n">test</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">sampleCol</span><span class="p">,</span> <span class="n">distName</span><span class="p">,</span>
<span class="n">_jvm</span><span class="p">()</span><span class="o">.</span><span class="n">PythonUtils</span><span class="o">.</span><span class="n">toSeq</span><span class="p">(</span><span class="n">params</span><span class="p">)))</span></div></div>
<div class="viewcode-block" id="Summarizer"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer">[docs]</a><span class="k">class</span> <span class="nc">Summarizer</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Tools for vectorized statistics on MLlib Vectors.</span>
<span class="sd"> The methods in this package provide various statistics for Vectors contained inside DataFrames.</span>
<span class="sd"> This class lets users pick the statistics they would like to extract for a given column.</span>
<span class="sd"> .. versionadded:: 2.4.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.stat import Summarizer</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.sql import Row</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import Vectors</span>
<span class="sd"> &gt;&gt;&gt; summarizer = Summarizer.metrics(&quot;mean&quot;, &quot;count&quot;)</span>
<span class="sd"> &gt;&gt;&gt; df = sc.parallelize([Row(weight=1.0, features=Vectors.dense(1.0, 1.0, 1.0)),</span>
<span class="sd"> ... Row(weight=0.0, features=Vectors.dense(1.0, 2.0, 3.0))]).toDF()</span>
<span class="sd"> &gt;&gt;&gt; df.select(summarizer.summary(df.features, df.weight)).show(truncate=False)</span>
<span class="sd"> +-----------------------------------+</span>
<span class="sd"> |aggregate_metrics(features, weight)|</span>
<span class="sd"> +-----------------------------------+</span>
<span class="sd"> |{[1.0,1.0,1.0], 1} |</span>
<span class="sd"> +-----------------------------------+</span>
<span class="sd"> &lt;BLANKLINE&gt;</span>
<span class="sd"> &gt;&gt;&gt; df.select(summarizer.summary(df.features)).show(truncate=False)</span>
<span class="sd"> +--------------------------------+</span>
<span class="sd"> |aggregate_metrics(features, 1.0)|</span>
<span class="sd"> +--------------------------------+</span>
<span class="sd"> |{[1.0,1.5,2.0], 2} |</span>
<span class="sd"> +--------------------------------+</span>
<span class="sd"> &lt;BLANKLINE&gt;</span>
<span class="sd"> &gt;&gt;&gt; df.select(Summarizer.mean(df.features, df.weight)).show(truncate=False)</span>
<span class="sd"> +--------------+</span>
<span class="sd"> |mean(features)|</span>
<span class="sd"> +--------------+</span>
<span class="sd"> |[1.0,1.0,1.0] |</span>
<span class="sd"> +--------------+</span>
<span class="sd"> &lt;BLANKLINE&gt;</span>
<span class="sd"> &gt;&gt;&gt; df.select(Summarizer.mean(df.features)).show(truncate=False)</span>
<span class="sd"> +--------------+</span>
<span class="sd"> |mean(features)|</span>
<span class="sd"> +--------------+</span>
<span class="sd"> |[1.0,1.5,2.0] |</span>
<span class="sd"> +--------------+</span>
<span class="sd"> &lt;BLANKLINE&gt;</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="Summarizer.mean"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.mean">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">mean</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of mean summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;mean&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="Summarizer.sum"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.sum">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">sum</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of sum summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;sum&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="Summarizer.variance"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.variance">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">variance</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of variance summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;variance&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="Summarizer.std"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.std">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;3.0.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">std</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of std summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;std&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="Summarizer.count"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.count">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">count</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of count summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;count&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="Summarizer.numNonZeros"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.numNonZeros">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">numNonZeros</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of numNonZero summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;numNonZeros&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="Summarizer.max"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.max">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">max</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of max summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;max&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="Summarizer.min"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.min">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">min</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of min summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;min&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="Summarizer.normL1"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.normL1">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">normL1</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of normL1 summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;normL1&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="Summarizer.normL2"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.normL2">[docs]</a> <span class="nd">@staticmethod</span>
<span class="nd">@since</span><span class="p">(</span><span class="s2">&quot;2.4.0&quot;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">normL2</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> return a column of normL2 summary</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="s2">&quot;normL2&quot;</span><span class="p">)</span></div>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">_check_param</span><span class="p">(</span><span class="n">featuresCol</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">):</span>
<span class="k">if</span> <span class="n">weightCol</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">weightCol</span> <span class="o">=</span> <span class="n">lit</span><span class="p">(</span><span class="mf">1.0</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">featuresCol</span><span class="p">,</span> <span class="n">Column</span><span class="p">)</span> <span class="ow">or</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">weightCol</span><span class="p">,</span> <span class="n">Column</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">&quot;featureCol and weightCol should be a Column&quot;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">featuresCol</span><span class="p">,</span> <span class="n">weightCol</span>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">_get_single_metric</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">,</span> <span class="n">metric</span><span class="p">):</span>
<span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span> <span class="o">=</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_check_param</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">)</span>
<span class="k">return</span> <span class="n">Column</span><span class="p">(</span><span class="n">JavaWrapper</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span><span class="s2">&quot;org.apache.spark.ml.stat.Summarizer.&quot;</span> <span class="o">+</span> <span class="n">metric</span><span class="p">,</span>
<span class="n">col</span><span class="o">.</span><span class="n">_jc</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">.</span><span class="n">_jc</span><span class="p">))</span>
<div class="viewcode-block" id="Summarizer.metrics"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.Summarizer.html#pyspark.ml.stat.Summarizer.metrics">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">metrics</span><span class="p">(</span><span class="o">*</span><span class="n">metrics</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Given a list of metrics, provides a builder that it turns computes metrics from a column.</span>
<span class="sd"> See the documentation of :py:class:`Summarizer` for an example.</span>
<span class="sd"> The following metrics are accepted (case sensitive):</span>
<span class="sd"> - mean: a vector that contains the coefficient-wise mean.</span>
<span class="sd"> - sum: a vector that contains the coefficient-wise sum.</span>
<span class="sd"> - variance: a vector tha contains the coefficient-wise variance.</span>
<span class="sd"> - std: a vector tha contains the coefficient-wise standard deviation.</span>
<span class="sd"> - count: the count of all vectors seen.</span>
<span class="sd"> - numNonzeros: a vector with the number of non-zeros for each coefficients</span>
<span class="sd"> - max: the maximum for each coefficient.</span>
<span class="sd"> - min: the minimum for each coefficient.</span>
<span class="sd"> - normL2: the Euclidean norm for each coefficient.</span>
<span class="sd"> - normL1: the L1 norm of each coefficient (sum of the absolute values).</span>
<span class="sd"> .. versionadded:: 2.4.0</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> Currently, the performance of this interface is about 2x~3x slower than using the RDD</span>
<span class="sd"> interface.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> metrics : str</span>
<span class="sd"> metrics that can be provided.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> :py:class:`pyspark.ml.stat.SummaryBuilder`</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span>
<span class="n">js</span> <span class="o">=</span> <span class="n">JavaWrapper</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span><span class="s2">&quot;org.apache.spark.ml.stat.Summarizer.metrics&quot;</span><span class="p">,</span>
<span class="n">_to_seq</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">metrics</span><span class="p">))</span>
<span class="k">return</span> <span class="n">SummaryBuilder</span><span class="p">(</span><span class="n">js</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="SummaryBuilder"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.SummaryBuilder.html#pyspark.ml.stat.SummaryBuilder">[docs]</a><span class="k">class</span> <span class="nc">SummaryBuilder</span><span class="p">(</span><span class="n">JavaWrapper</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> A builder object that provides summary statistics about a given column.</span>
<span class="sd"> Users should not directly create such builders, but instead use one of the methods in</span>
<span class="sd"> :py:class:`pyspark.ml.stat.Summarizer`</span>
<span class="sd"> .. versionadded:: 2.4.0</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">jSummaryBuilder</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">SummaryBuilder</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">jSummaryBuilder</span><span class="p">)</span>
<div class="viewcode-block" id="SummaryBuilder.summary"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.SummaryBuilder.html#pyspark.ml.stat.SummaryBuilder.summary">[docs]</a> <span class="k">def</span> <span class="nf">summary</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">featuresCol</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns an aggregate object that contains the summary of the column with the requested</span>
<span class="sd"> metrics.</span>
<span class="sd"> .. versionadded:: 2.4.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> featuresCol : str</span>
<span class="sd"> a column that contains features Vector object.</span>
<span class="sd"> weightCol : str, optional</span>
<span class="sd"> a column that contains weight value. Default weight is 1.0.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> :py:class:`pyspark.sql.Column`</span>
<span class="sd"> an aggregate column that contains the statistics. The exact content of this</span>
<span class="sd"> structure is determined during the creation of the builder.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">featuresCol</span><span class="p">,</span> <span class="n">weightCol</span> <span class="o">=</span> <span class="n">Summarizer</span><span class="o">.</span><span class="n">_check_param</span><span class="p">(</span><span class="n">featuresCol</span><span class="p">,</span> <span class="n">weightCol</span><span class="p">)</span>
<span class="k">return</span> <span class="n">Column</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_java_obj</span><span class="o">.</span><span class="n">summary</span><span class="p">(</span><span class="n">featuresCol</span><span class="o">.</span><span class="n">_jc</span><span class="p">,</span> <span class="n">weightCol</span><span class="o">.</span><span class="n">_jc</span><span class="p">))</span></div></div>
<div class="viewcode-block" id="MultivariateGaussian"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.stat.MultivariateGaussian.html#pyspark.ml.stat.MultivariateGaussian">[docs]</a><span class="k">class</span> <span class="nc">MultivariateGaussian</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Represents a (mean, cov) tuple</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.linalg import DenseMatrix, Vectors</span>
<span class="sd"> &gt;&gt;&gt; m = MultivariateGaussian(Vectors.dense([11,12]), DenseMatrix(2, 2, (1.0, 3.0, 5.0, 2.0)))</span>
<span class="sd"> &gt;&gt;&gt; (m.mean, m.cov.toArray())</span>
<span class="sd"> (DenseVector([11.0, 12.0]), array([[ 1., 5.],</span>
<span class="sd"> [ 3., 2.]]))</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">mean</span><span class="p">,</span> <span class="n">cov</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">mean</span> <span class="o">=</span> <span class="n">mean</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cov</span> <span class="o">=</span> <span class="n">cov</span></div>
<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="kn">import</span> <span class="nn">doctest</span>
<span class="kn">import</span> <span class="nn">numpy</span>
<span class="kn">import</span> <span class="nn">pyspark.ml.stat</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># Numpy 1.14+ changed it&#39;s string format.</span>
<span class="n">numpy</span><span class="o">.</span><span class="n">set_printoptions</span><span class="p">(</span><span class="n">legacy</span><span class="o">=</span><span class="s1">&#39;1.13&#39;</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">TypeError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">ml</span><span class="o">.</span><span class="n">stat</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="c1"># The small batch size here ensures that we see multiple batches,</span>
<span class="c1"># even in these small test examples:</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[2]&quot;</span><span class="p">)</span> \
<span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">&quot;ml.stat tests&quot;</span><span class="p">)</span> \
<span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span>
<span class="n">sc</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</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">sc</span>
<span class="n">globs</span><span class="p">[</span><span class="s1">&#39;spark&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span>
<span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</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">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>
</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>