Google Git
Sign in
apache / spark-website / 77b22e9b52e4b9406f14096c2c09f6c602f0987b / . / site / docs / 3.1.2 / api / python / _modules / pyspark / ml / functions.html
blob: 9184587dde187f458615f8ab78c5026511e886d7 [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>pyspark.ml.functions &#8212; PySpark 3.1.2 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="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/ml/functions.html" />
<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.functions</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">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</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_java_column</span>
<div class="viewcode-block" id="vector_to_array"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.functions.vector_to_array.html#pyspark.ml.functions.vector_to_array">[docs]</a><span class="k">def</span> <span class="nf">vector_to_array</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s2">&quot;float64&quot;</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Converts a column of MLlib sparse/dense vectors into a column of dense arrays.</span>
<span class="sd"> .. versionadded:: 3.0.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> col : :py:class:`pyspark.sql.Column` or str</span>
<span class="sd"> Input column</span>
<span class="sd"> dtype : str, optional</span>
<span class="sd"> The data type of the output array. Valid values: &quot;float64&quot; or &quot;float32&quot;.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> :py:class:`pyspark.sql.Column`</span>
<span class="sd"> The converted column of dense arrays.</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.functions import vector_to_array</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.mllib.linalg import Vectors as OldVectors</span>
<span class="sd"> &gt;&gt;&gt; df = spark.createDataFrame([</span>
<span class="sd"> ... (Vectors.dense(1.0, 2.0, 3.0), OldVectors.dense(10.0, 20.0, 30.0)),</span>
<span class="sd"> ... (Vectors.sparse(3, [(0, 2.0), (2, 3.0)]),</span>
<span class="sd"> ... OldVectors.sparse(3, [(0, 20.0), (2, 30.0)]))],</span>
<span class="sd"> ... [&quot;vec&quot;, &quot;oldVec&quot;])</span>
<span class="sd"> &gt;&gt;&gt; df1 = df.select(vector_to_array(&quot;vec&quot;).alias(&quot;vec&quot;),</span>
<span class="sd"> ... vector_to_array(&quot;oldVec&quot;).alias(&quot;oldVec&quot;))</span>
<span class="sd"> &gt;&gt;&gt; df1.collect()</span>
<span class="sd"> [Row(vec=[1.0, 2.0, 3.0], oldVec=[10.0, 20.0, 30.0]),</span>
<span class="sd"> Row(vec=[2.0, 0.0, 3.0], oldVec=[20.0, 0.0, 30.0])]</span>
<span class="sd"> &gt;&gt;&gt; df2 = df.select(vector_to_array(&quot;vec&quot;, &quot;float32&quot;).alias(&quot;vec&quot;),</span>
<span class="sd"> ... vector_to_array(&quot;oldVec&quot;, &quot;float32&quot;).alias(&quot;oldVec&quot;))</span>
<span class="sd"> &gt;&gt;&gt; df2.collect()</span>
<span class="sd"> [Row(vec=[1.0, 2.0, 3.0], oldVec=[10.0, 20.0, 30.0]),</span>
<span class="sd"> Row(vec=[2.0, 0.0, 3.0], oldVec=[20.0, 0.0, 30.0])]</span>
<span class="sd"> &gt;&gt;&gt; df1.schema.fields</span>
<span class="sd"> [StructField(vec,ArrayType(DoubleType,false),false),</span>
<span class="sd"> StructField(oldVec,ArrayType(DoubleType,false),false)]</span>
<span class="sd"> &gt;&gt;&gt; df2.schema.fields</span>
<span class="sd"> [StructField(vec,ArrayType(FloatType,false),false),</span>
<span class="sd"> StructField(oldVec,ArrayType(FloatType,false),false)]</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="k">return</span> <span class="n">Column</span><span class="p">(</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">ml</span><span class="o">.</span><span class="n">functions</span><span class="o">.</span><span class="n">vector_to_array</span><span class="p">(</span><span class="n">_to_java_column</span><span class="p">(</span><span class="n">col</span><span class="p">),</span> <span class="n">dtype</span><span class="p">))</span></div>
<div class="viewcode-block" id="array_to_vector"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.functions.array_to_vector.html#pyspark.ml.functions.array_to_vector">[docs]</a><span class="k">def</span> <span class="nf">array_to_vector</span><span class="p">(</span><span class="n">col</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Converts a column of array of numeric type into a column of dense vectors in MLlib</span>
<span class="sd"> .. versionadded:: 3.1.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> col : :py:class:`pyspark.sql.Column` or str</span>
<span class="sd"> Input column</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> :py:class:`pyspark.sql.Column`</span>
<span class="sd"> The converted column of MLlib dense vectors.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.ml.functions import array_to_vector</span>
<span class="sd"> &gt;&gt;&gt; df1 = spark.createDataFrame([([1.5, 2.5],),], schema=&#39;v1 array&lt;double&gt;&#39;)</span>
<span class="sd"> &gt;&gt;&gt; df1.select(array_to_vector(&#39;v1&#39;).alias(&#39;vec1&#39;)).collect()</span>
<span class="sd"> [Row(vec1=DenseVector([1.5, 2.5]))]</span>
<span class="sd"> &gt;&gt;&gt; df2 = spark.createDataFrame([([1.5, 3.5],),], schema=&#39;v1 array&lt;float&gt;&#39;)</span>
<span class="sd"> &gt;&gt;&gt; df2.select(array_to_vector(&#39;v1&#39;).alias(&#39;vec1&#39;)).collect()</span>
<span class="sd"> [Row(vec1=DenseVector([1.5, 3.5]))]</span>
<span class="sd"> &gt;&gt;&gt; df3 = spark.createDataFrame([([1, 3],),], schema=&#39;v1 array&lt;int&gt;&#39;)</span>
<span class="sd"> &gt;&gt;&gt; df3.select(array_to_vector(&#39;v1&#39;).alias(&#39;vec1&#39;)).collect()</span>
<span class="sd"> [Row(vec1=DenseVector([1.0, 3.0]))]</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="k">return</span> <span class="n">Column</span><span class="p">(</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">ml</span><span class="o">.</span><span class="n">functions</span><span class="o">.</span><span class="n">array_to_vector</span><span class="p">(</span><span class="n">_to_java_column</span><span class="p">(</span><span class="n">col</span><span class="p">)))</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.ml.functions</span>
<span class="kn">import</span> <span class="nn">sys</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">functions</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[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.functions 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="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">pyspark</span><span class="o">.</span><span class="n">ml</span><span class="o">.</span><span class="n">functions</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="o">|</span> <span class="n">doctest</span><span class="o">.</span><span class="n">NORMALIZE_WHITESPACE</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>
<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>