blob: e3c7991b121262647d340a63b3c1172e735cee6c [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>pyspark.sql.DataFrame.mapInPandas &#8212; PySpark 3.4.3 documentation</title>
<link rel="stylesheet" href="../../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css">
<link rel="stylesheet"
href="../../../_static/vendor/fontawesome/5.13.0/css/all.min.css">
<link rel="preload" as="font" type="font/woff2" crossorigin
href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2">
<link rel="preload" as="font" type="font/woff2" crossorigin
href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2">
<link rel="stylesheet"
href="../../../_static/vendor/open-sans_all/1.44.1/index.css">
<link rel="stylesheet"
href="../../../_static/vendor/lato_latin-ext/1.44.1/index.css">
<link rel="stylesheet" href="../../../_static/basic.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" />
<link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" />
<link rel="preload" as="script" href="../../../_static/js/index.3da636dd464baa7582d2.js">
<script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
<script src="../../../_static/jquery.js"></script>
<script src="../../../_static/underscore.js"></script>
<script src="../../../_static/doctools.js"></script>
<script src="../../../_static/language_data.js"></script>
<script src="../../../_static/clipboard.min.js"></script>
<script src="../../../_static/copybutton.js"></script>
<script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script>
<script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script>
<link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.DataFrame.mapInPandas.html" />
<link rel="search" title="Search" href="../../../search.html" />
<link rel="next" title="pyspark.sql.DataFrame.mapInArrow" href="pyspark.sql.DataFrame.mapInArrow.html" />
<link rel="prev" title="pyspark.sql.DataFrame.localCheckpoint" href="pyspark.sql.DataFrame.localCheckpoint.html" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="docsearch:language" content="en" />
</head>
<body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80">
<nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main">
<div class="container-xl">
<a class="navbar-brand" href="../../../index.html">
<img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo" />
</a>
<button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>
<div id="navbar-menu" class="col-lg-9 collapse navbar-collapse">
<ul id="navbar-main-elements" class="navbar-nav mr-auto">
<li class="nav-item ">
<a class="nav-link" href="../../../index.html">Overview</a>
</li>
<li class="nav-item ">
<a class="nav-link" href="../../../getting_started/index.html">Getting Started</a>
</li>
<li class="nav-item ">
<a class="nav-link" href="../../../user_guide/index.html">User Guides</a>
</li>
<li class="nav-item active">
<a class="nav-link" href="../../index.html">API Reference</a>
</li>
<li class="nav-item ">
<a class="nav-link" href="../../../development/index.html">Development</a>
</li>
<li class="nav-item ">
<a class="nav-link" href="../../../migration_guide/index.html">Migration Guides</a>
</li>
</ul>
<ul class="navbar-nav">
</ul>
</div>
</div>
</nav>
<div class="container-xl">
<div class="row">
<div class="col-12 col-md-3 bd-sidebar"><form class="bd-search d-flex align-items-center" action="../../../search.html" method="get">
<i class="icon fas fa-search"></i>
<input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" >
</form>
<nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation">
<div class="bd-toc-item active">
<ul class="nav bd-sidenav">
<li class="active">
<a href="../index.html">Spark SQL</a>
<ul>
<li class="">
<a href="../core_classes.html">Core Classes</a>
</li>
<li class="">
<a href="../spark_session.html">Spark Session</a>
</li>
<li class="">
<a href="../configuration.html">Configuration</a>
</li>
<li class="">
<a href="../io.html">Input/Output</a>
</li>
<li class="active">
<a href="../dataframe.html">DataFrame</a>
</li>
<li class="">
<a href="../column.html">Column</a>
</li>
<li class="">
<a href="../data_types.html">Data Types</a>
</li>
<li class="">
<a href="../row.html">Row</a>
</li>
<li class="">
<a href="../functions.html">Functions</a>
</li>
<li class="">
<a href="../window.html">Window</a>
</li>
<li class="">
<a href="../grouping.html">Grouping</a>
</li>
<li class="">
<a href="../catalog.html">Catalog</a>
</li>
<li class="">
<a href="../avro.html">Avro</a>
</li>
<li class="">
<a href="../observation.html">Observation</a>
</li>
<li class="">
<a href="../udf.html">UDF</a>
</li>
<li class="">
<a href="../protobuf.html">Protobuf</a>
</li>
</ul>
</li>
<li class="">
<a href="../../pyspark.pandas/index.html">Pandas API on Spark</a>
</li>
<li class="">
<a href="../../pyspark.ss/index.html">Structured Streaming</a>
</li>
<li class="">
<a href="../../pyspark.ml.html">MLlib (DataFrame-based)</a>
</li>
<li class="">
<a href="../../pyspark.streaming.html">Spark Streaming (Legacy)</a>
</li>
<li class="">
<a href="../../pyspark.mllib.html">MLlib (RDD-based)</a>
</li>
<li class="">
<a href="../../pyspark.html">Spark Core</a>
</li>
<li class="">
<a href="../../pyspark.resource.html">Resource Management</a>
</li>
<li class="">
<a href="../../pyspark.errors.html">Errors</a>
</li>
</ul>
</nav>
</div>
<div class="d-none d-xl-block col-xl-2 bd-toc">
<nav id="bd-toc-nav">
<ul class="nav section-nav flex-column">
</ul>
</nav>
</div>
<main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main">
<div>
<div class="section" id="pyspark-sql-dataframe-mapinpandas">
<h1>pyspark.sql.DataFrame.mapInPandas<a class="headerlink" href="#pyspark-sql-dataframe-mapinpandas" title="Permalink to this headline"></a></h1>
<dl class="py method">
<dt id="pyspark.sql.DataFrame.mapInPandas">
<code class="sig-prename descclassname">DataFrame.</code><code class="sig-name descname">mapInPandas</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">func</span><span class="p">:</span> <span class="n">PandasMapIterFunction</span></em>, <em class="sig-param"><span class="n">schema</span><span class="p">:</span> <span class="n">Union<span class="p">[</span><a class="reference internal" href="pyspark.sql.types.StructType.html#pyspark.sql.types.StructType" title="pyspark.sql.types.StructType">pyspark.sql.types.StructType</a><span class="p">, </span>str<span class="p">]</span></span></em><span class="sig-paren">)</span> &#x2192; DataFrame<a class="headerlink" href="#pyspark.sql.DataFrame.mapInPandas" title="Permalink to this definition"></a></dt>
<dd><p>Maps an iterator of batches in the current <a class="reference internal" href="pyspark.sql.DataFrame.html#pyspark.sql.DataFrame" title="pyspark.sql.DataFrame"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataFrame</span></code></a> using a Python native
function that takes and outputs a pandas DataFrame, and returns the result as a
<a class="reference internal" href="pyspark.sql.DataFrame.html#pyspark.sql.DataFrame" title="pyspark.sql.DataFrame"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataFrame</span></code></a>.</p>
<p>The function should take an iterator of <cite>pandas.DataFrame</cite>s and return
another iterator of <cite>pandas.DataFrame</cite>s. All columns are passed
together as an iterator of <cite>pandas.DataFrame</cite>s to the function and the
returned iterator of <cite>pandas.DataFrame</cite>s are combined as a <a class="reference internal" href="pyspark.sql.DataFrame.html#pyspark.sql.DataFrame" title="pyspark.sql.DataFrame"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataFrame</span></code></a>.
Each <cite>pandas.DataFrame</cite> size can be controlled by
<cite>spark.sql.execution.arrow.maxRecordsPerBatch</cite>. The size of the function’s input and
output can be different.</p>
<div class="versionadded">
<p><span class="versionmodified added">New in version 3.0.0.</span></p>
</div>
<div class="versionchanged">
<p><span class="versionmodified changed">Changed in version 3.4.0: </span>Supports Spark Connect.</p>
</div>
<dl class="field-list">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><dl>
<dt><strong>func</strong><span class="classifier">function</span></dt><dd><p>a Python native function that takes an iterator of <cite>pandas.DataFrame</cite>s, and
outputs an iterator of <cite>pandas.DataFrame</cite>s.</p>
</dd>
<dt><strong>schema</strong><span class="classifier"><a class="reference internal" href="pyspark.sql.types.DataType.html#pyspark.sql.types.DataType" title="pyspark.sql.types.DataType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.DataType</span></code></a> or str</span></dt><dd><p>the return type of the <cite>func</cite> in PySpark. The value can be either a
<a class="reference internal" href="pyspark.sql.types.DataType.html#pyspark.sql.types.DataType" title="pyspark.sql.types.DataType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.DataType</span></code></a> object or a DDL-formatted type string.</p>
</dd>
</dl>
</dd>
</dl>
<div class="admonition seealso">
<p class="admonition-title">See also</p>
<dl class="simple">
<dt><a class="reference internal" href="pyspark.sql.functions.pandas_udf.html#pyspark.sql.functions.pandas_udf" title="pyspark.sql.functions.pandas_udf"><code class="xref py py-obj docutils literal notranslate"><span class="pre">pyspark.sql.functions.pandas_udf</span></code></a></dt><dd></dd>
</dl>
</div>
<p class="rubric">Notes</p>
<p>This API is experimental</p>
<p class="rubric">Examples</p>
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">pyspark.sql.functions</span> <span class="kn">import</span> <span class="n">pandas_udf</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">([(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">21</span><span class="p">),</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">30</span><span class="p">)],</span> <span class="p">(</span><span class="s2">&quot;id&quot;</span><span class="p">,</span> <span class="s2">&quot;age&quot;</span><span class="p">))</span>
<span class="gp">&gt;&gt;&gt; </span><span class="k">def</span> <span class="nf">filter_func</span><span class="p">(</span><span class="n">iterator</span><span class="p">):</span>
<span class="gp">... </span> <span class="k">for</span> <span class="n">pdf</span> <span class="ow">in</span> <span class="n">iterator</span><span class="p">:</span>
<span class="gp">... </span> <span class="k">yield</span> <span class="n">pdf</span><span class="p">[</span><span class="n">pdf</span><span class="o">.</span><span class="n">id</span> <span class="o">==</span> <span class="mi">1</span><span class="p">]</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">df</span><span class="o">.</span><span class="n">mapInPandas</span><span class="p">(</span><span class="n">filter_func</span><span class="p">,</span> <span class="n">df</span><span class="o">.</span><span class="n">schema</span><span class="p">)</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
<span class="go">+---+---+</span>
<span class="go">| id|age|</span>
<span class="go">+---+---+</span>
<span class="go">| 1| 21|</span>
<span class="go">+---+---+</span>
</pre></div>
</div>
</dd></dl>
</div>
</div>
<div class='prev-next-bottom'>
<a class='left-prev' id="prev-link" href="pyspark.sql.DataFrame.localCheckpoint.html" title="previous page">pyspark.sql.DataFrame.localCheckpoint</a>
<a class='right-next' id="next-link" href="pyspark.sql.DataFrame.mapInArrow.html" title="next page">pyspark.sql.DataFrame.mapInArrow</a>
</div>
</main>
</div>
</div>
<script src="../../../_static/js/index.3da636dd464baa7582d2.js"></script>
<footer class="footer mt-5 mt-md-0">
<div class="container">
<p>
&copy; Copyright .<br/>
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/>
</p>
</div>
</footer>
</body>
</html>