| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.sql.functions.pandas_udf — 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="canonical" href="https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.pandas_udf.html" /> |
| <link rel="search" title="Search" href="../../search.html" /> |
| <link rel="next" title="pyspark.sql.functions.percent_rank" href="pyspark.sql.functions.percent_rank.html" /> |
| <link rel="prev" title="pyspark.sql.functions.overlay" href="pyspark.sql.functions.overlay.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 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 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"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <li class="active"> |
| <a href="../pyspark.sql.html">Spark SQL</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.pandas/index.html">Pandas API on Spark</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.ss.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</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> |
| |
| |
| |
| |
| |
| |
| |
| |
| </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-functions-pandas-udf"> |
| <h1>pyspark.sql.functions.pandas_udf<a class="headerlink" href="#pyspark-sql-functions-pandas-udf" title="Permalink to this headline">¶</a></h1> |
| <dl class="py function"> |
| <dt id="pyspark.sql.functions.pandas_udf"> |
| <code class="sig-prename descclassname">pyspark.sql.functions.</code><code class="sig-name descname">pandas_udf</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">f</span><span class="o">=</span><span class="default_value">None</span></em>, <em class="sig-param"><span class="n">returnType</span><span class="o">=</span><span class="default_value">None</span></em>, <em class="sig-param"><span class="n">functionType</span><span class="o">=</span><span class="default_value">None</span></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/pyspark/sql/pandas/functions.html#pandas_udf"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.sql.functions.pandas_udf" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Creates a pandas user defined function (a.k.a. vectorized user defined function).</p> |
| <p>Pandas UDFs are user defined functions that are executed by Spark using Arrow to transfer |
| data and Pandas to work with the data, which allows vectorized operations. A Pandas UDF |
| is defined using the <cite>pandas_udf</cite> as a decorator or to wrap the function, and no |
| additional configuration is required. A Pandas UDF behaves as a regular PySpark function |
| API in general.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 2.3.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>f</strong><span class="classifier">function, optional</span></dt><dd><p>user-defined function. A python function if used as a standalone function</p> |
| </dd> |
| <dt><strong>returnType</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, optional</span></dt><dd><p>the return type of the user-defined function. 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> |
| <dt><strong>functionType</strong><span class="classifier">int, optional</span></dt><dd><p>an enum value in <code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.functions.PandasUDFType</span></code>. |
| Default: SCALAR. This parameter exists for compatibility. |
| Using Python type hints is encouraged.</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.GroupedData.agg.html#pyspark.sql.GroupedData.agg" title="pyspark.sql.GroupedData.agg"><code class="xref py py-obj docutils literal notranslate"><span class="pre">pyspark.sql.GroupedData.agg</span></code></a></dt><dd></dd> |
| <dt><a class="reference internal" href="pyspark.sql.DataFrame.mapInPandas.html#pyspark.sql.DataFrame.mapInPandas" title="pyspark.sql.DataFrame.mapInPandas"><code class="xref py py-obj docutils literal notranslate"><span class="pre">pyspark.sql.DataFrame.mapInPandas</span></code></a></dt><dd></dd> |
| <dt><a class="reference internal" href="pyspark.sql.GroupedData.applyInPandas.html#pyspark.sql.GroupedData.applyInPandas" title="pyspark.sql.GroupedData.applyInPandas"><code class="xref py py-obj docutils literal notranslate"><span class="pre">pyspark.sql.GroupedData.applyInPandas</span></code></a></dt><dd></dd> |
| <dt><a class="reference internal" href="pyspark.sql.PandasCogroupedOps.applyInPandas.html#pyspark.sql.PandasCogroupedOps.applyInPandas" title="pyspark.sql.PandasCogroupedOps.applyInPandas"><code class="xref py py-obj docutils literal notranslate"><span class="pre">pyspark.sql.PandasCogroupedOps.applyInPandas</span></code></a></dt><dd></dd> |
| <dt><code class="xref py py-obj docutils literal notranslate"><span class="pre">pyspark.sql.UDFRegistration.register</span></code></dt><dd></dd> |
| </dl> |
| </div> |
| <p class="rubric">Notes</p> |
| <p>The user-defined functions do not support conditional expressions or short circuiting |
| in boolean expressions and it ends up with being executed all internally. If the functions |
| can fail on special rows, the workaround is to incorporate the condition into the functions.</p> |
| <p>The user-defined functions do not take keyword arguments on the calling side.</p> |
| <p>The data type of returned <cite>pandas.Series</cite> from the user-defined functions should be |
| matched with defined <cite>returnType</cite> (see <code class="xref py py-meth docutils literal notranslate"><span class="pre">types.to_arrow_type()</span></code> and |
| <code class="xref py py-meth docutils literal notranslate"><span class="pre">types.from_arrow_type()</span></code>). When there is mismatch between them, Spark might do |
| conversion on returned data. The conversion is not guaranteed to be correct and results |
| should be checked for accuracy by users.</p> |
| <p>Currently, |
| <a class="reference internal" href="pyspark.sql.types.ArrayType.html#pyspark.sql.types.ArrayType" title="pyspark.sql.types.ArrayType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.ArrayType</span></code></a> of <a class="reference internal" href="pyspark.sql.types.TimestampType.html#pyspark.sql.types.TimestampType" title="pyspark.sql.types.TimestampType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.TimestampType</span></code></a> and |
| nested <a class="reference internal" href="pyspark.sql.types.StructType.html#pyspark.sql.types.StructType" title="pyspark.sql.types.StructType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.StructType</span></code></a> |
| are currently not supported as output types.</p> |
| <p class="rubric">Examples</p> |
| <p>In order to use this API, customarily the below are imported:</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyspark.sql.functions</span> <span class="kn">import</span> <span class="n">pandas_udf</span> |
| </pre></div> |
| </div> |
| <p>From Spark 3.0 with Python 3.6+, <a class="reference external" href="https://www.python.org/dev/peps/pep-0484">Python type hints</a> |
| detect the function types as below:</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="n">IntegerType</span><span class="p">())</span> |
| <span class="gp">... </span><span class="k">def</span> <span class="nf">slen</span><span class="p">(</span><span class="n">s</span><span class="p">:</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">)</span> <span class="o">-></span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">str</span><span class="o">.</span><span class="n">len</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| <p>Prior to Spark 3.0, the pandas UDF used <cite>functionType</cite> to decide the execution type as below:</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyspark.sql.functions</span> <span class="kn">import</span> <span class="n">PandasUDFType</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="n">IntegerType</span> |
| <span class="gp">>>> </span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="n">PandasUDFType</span><span class="o">.</span><span class="n">SCALAR</span><span class="p">)</span> |
| <span class="gp">... </span><span class="k">def</span> <span class="nf">slen</span><span class="p">(</span><span class="n">s</span><span class="p">):</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">str</span><span class="o">.</span><span class="n">len</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| <p>It is preferred to specify type hints for the pandas UDF instead of specifying pandas UDF |
| type via <cite>functionType</cite> which will be deprecated in the future releases.</p> |
| <p>Note that the type hint should use <cite>pandas.Series</cite> in all cases but there is one variant |
| that <cite>pandas.DataFrame</cite> should be used for its input or output type hint instead when the input |
| or output column is of <a class="reference internal" href="pyspark.sql.types.StructType.html#pyspark.sql.types.StructType" title="pyspark.sql.types.StructType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.StructType</span></code></a>. The following example shows |
| a Pandas UDF which takes long column, string column and struct column, and outputs a struct |
| column. It requires the function to specify the type hints of <cite>pandas.Series</cite> and |
| <cite>pandas.DataFrame</cite> as below:</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="s2">"col1 string, col2 long"</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="k">def</span> <span class="nf">func</span><span class="p">(</span><span class="n">s1</span><span class="p">:</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">,</span> <span class="n">s2</span><span class="p">:</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">,</span> <span class="n">s3</span><span class="p">:</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">)</span> <span class="o">-></span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">s3</span><span class="p">[</span><span class="s1">'col2'</span><span class="p">]</span> <span class="o">=</span> <span class="n">s1</span> <span class="o">+</span> <span class="n">s2</span><span class="o">.</span><span class="n">str</span><span class="o">.</span><span class="n">len</span><span class="p">()</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">s3</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="c1"># Create a Spark DataFrame that has three columns including a struct column.</span> |
| <span class="gp">... </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="gp">... </span> <span class="p">[[</span><span class="mi">1</span><span class="p">,</span> <span class="s2">"a string"</span><span class="p">,</span> <span class="p">(</span><span class="s2">"a nested string"</span><span class="p">,)]],</span> |
| <span class="gp">... </span> <span class="s2">"long_col long, string_col string, struct_col struct<col1:string>"</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">df</span><span class="o">.</span><span class="n">printSchema</span><span class="p">()</span> |
| <span class="go">root</span> |
| <span class="go">|-- long_column: long (nullable = true)</span> |
| <span class="go">|-- string_column: string (nullable = true)</span> |
| <span class="go">|-- struct_column: struct (nullable = true)</span> |
| <span class="go">| |-- col1: string (nullable = true)</span> |
| <span class="gp">>>> </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">func</span><span class="p">(</span><span class="s2">"long_col"</span><span class="p">,</span> <span class="s2">"string_col"</span><span class="p">,</span> <span class="s2">"struct_col"</span><span class="p">))</span><span class="o">.</span><span class="n">printSchema</span><span class="p">()</span> |
| <span class="go">|-- func(long_col, string_col, struct_col): struct (nullable = true)</span> |
| <span class="go">| |-- col1: string (nullable = true)</span> |
| <span class="go">| |-- col2: long (nullable = true)</span> |
| </pre></div> |
| </div> |
| <p>In the following sections, it describes the combinations of the supported type hints. For |
| simplicity, <cite>pandas.DataFrame</cite> variant is omitted.</p> |
| <ul> |
| <li><dl> |
| <dt>Series to Series</dt><dd><p><cite>pandas.Series</cite>, … -> <cite>pandas.Series</cite></p> |
| <p>The function takes one or more <cite>pandas.Series</cite> and outputs one <cite>pandas.Series</cite>. |
| The output of the function should always be of the same length as the input.</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="s2">"string"</span><span class="p">)</span> |
| <span class="gp">... </span><span class="k">def</span> <span class="nf">to_upper</span><span class="p">(</span><span class="n">s</span><span class="p">:</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">)</span> <span class="o">-></span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">str</span><span class="o">.</span><span class="n">upper</span><span class="p">()</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </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="s2">"John Doe"</span><span class="p">,)],</span> <span class="p">(</span><span class="s2">"name"</span><span class="p">,))</span> |
| <span class="gp">>>> </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">to_upper</span><span class="p">(</span><span class="s2">"name"</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">|to_upper(name)|</span> |
| <span class="go">+--------------+</span> |
| <span class="go">| JOHN DOE|</span> |
| <span class="go">+--------------+</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="s2">"first string, last string"</span><span class="p">)</span> |
| <span class="gp">... </span><span class="k">def</span> <span class="nf">split_expand</span><span class="p">(</span><span class="n">s</span><span class="p">:</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">)</span> <span class="o">-></span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">str</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">expand</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </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="s2">"John Doe"</span><span class="p">,)],</span> <span class="p">(</span><span class="s2">"name"</span><span class="p">,))</span> |
| <span class="gp">>>> </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">split_expand</span><span class="p">(</span><span class="s2">"name"</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">|split_expand(name)|</span> |
| <span class="go">+------------------+</span> |
| <span class="go">| [John, Doe]|</span> |
| <span class="go">+------------------+</span> |
| </pre></div> |
| </div> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>The length of the input is not that of the whole input column, but is the |
| length of an internal batch used for each call to the function.</p> |
| </div> |
| </dd> |
| </dl> |
| </li> |
| <li><dl> |
| <dt>Iterator of Series to Iterator of Series</dt><dd><p><cite>Iterator[pandas.Series]</cite> -> <cite>Iterator[pandas.Series]</cite></p> |
| <p>The function takes an iterator of <cite>pandas.Series</cite> and outputs an iterator of |
| <cite>pandas.Series</cite>. In this case, the created pandas UDF instance requires one input |
| column when this is called as a PySpark column. The length of the entire output from |
| the function should be the same length of the entire input; therefore, it can |
| prefetch the data from the input iterator as long as the lengths are the same.</p> |
| <p>It is also useful when the UDF execution |
| requires initializing some states although internally it works identically as |
| Series to Series case. The pseudocode below illustrates the example.</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="s2">"long"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">calculate</span><span class="p">(</span><span class="n">iterator</span><span class="p">:</span> <span class="n">Iterator</span><span class="p">[</span><span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">])</span> <span class="o">-></span> <span class="n">Iterator</span><span class="p">[</span><span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">]:</span> |
| <span class="c1"># Do some expensive initialization with a state</span> |
| <span class="n">state</span> <span class="o">=</span> <span class="n">very_expensive_initialization</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">iterator</span><span class="p">:</span> |
| <span class="c1"># Use that state for whole iterator.</span> |
| <span class="k">yield</span> <span class="n">calculate_with_state</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">state</span><span class="p">)</span> |
| |
| <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">calculate</span><span class="p">(</span><span class="s2">"value"</span><span class="p">))</span><span class="o">.</span><span class="n">show</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Iterator</span> |
| <span class="gp">>>> </span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="s2">"long"</span><span class="p">)</span> |
| <span class="gp">... </span><span class="k">def</span> <span class="nf">plus_one</span><span class="p">(</span><span class="n">iterator</span><span class="p">:</span> <span class="n">Iterator</span><span class="p">[</span><span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">])</span> <span class="o">-></span> <span class="n">Iterator</span><span class="p">[</span><span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">]:</span> |
| <span class="gp">... </span> <span class="k">for</span> <span class="n">s</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">s</span> <span class="o">+</span> <span class="mi">1</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </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="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">],</span> <span class="n">columns</span><span class="o">=</span><span class="p">[</span><span class="s2">"v"</span><span class="p">]))</span> |
| <span class="gp">>>> </span><span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">plus_one</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">v</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">|plus_one(v)|</span> |
| <span class="go">+-----------+</span> |
| <span class="go">| 2|</span> |
| <span class="go">| 3|</span> |
| <span class="go">| 4|</span> |
| <span class="go">+-----------+</span> |
| </pre></div> |
| </div> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>The length of each series is the length of a batch internally used.</p> |
| </div> |
| </dd> |
| </dl> |
| </li> |
| <li><dl> |
| <dt>Iterator of Multiple Series to Iterator of Series</dt><dd><p><cite>Iterator[Tuple[pandas.Series, …]]</cite> -> <cite>Iterator[pandas.Series]</cite></p> |
| <p>The function takes an iterator of a tuple of multiple <cite>pandas.Series</cite> and outputs an |
| iterator of <cite>pandas.Series</cite>. In this case, the created pandas UDF instance requires |
| input columns as many as the series when this is called as a PySpark column. |
| Otherwise, it has the same characteristics and restrictions as Iterator of Series |
| to Iterator of Series case.</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Iterator</span><span class="p">,</span> <span class="n">Tuple</span> |
| <span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyspark.sql.functions</span> <span class="kn">import</span> <span class="n">struct</span><span class="p">,</span> <span class="n">col</span> |
| <span class="gp">>>> </span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="s2">"long"</span><span class="p">)</span> |
| <span class="gp">... </span><span class="k">def</span> <span class="nf">multiply</span><span class="p">(</span><span class="n">iterator</span><span class="p">:</span> <span class="n">Iterator</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">]])</span> <span class="o">-></span> <span class="n">Iterator</span><span class="p">[</span><span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">]:</span> |
| <span class="gp">... </span> <span class="k">for</span> <span class="n">s1</span><span class="p">,</span> <span class="n">df</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">s1</span> <span class="o">*</span> <span class="n">df</span><span class="o">.</span><span class="n">v</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </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="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">],</span> <span class="n">columns</span><span class="o">=</span><span class="p">[</span><span class="s2">"v"</span><span class="p">]))</span> |
| <span class="gp">>>> </span><span class="n">df</span><span class="o">.</span><span class="n">withColumn</span><span class="p">(</span><span class="s1">'output'</span><span class="p">,</span> <span class="n">multiply</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s2">"v"</span><span class="p">),</span> <span class="n">struct</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s2">"v"</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">| v|output|</span> |
| <span class="go">+---+------+</span> |
| <span class="go">| 1| 1|</span> |
| <span class="go">| 2| 4|</span> |
| <span class="go">| 3| 9|</span> |
| <span class="go">+---+------+</span> |
| </pre></div> |
| </div> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>The length of each series is the length of a batch internally used.</p> |
| </div> |
| </dd> |
| </dl> |
| </li> |
| <li><dl> |
| <dt>Series to Scalar</dt><dd><p><cite>pandas.Series</cite>, … -> <cite>Any</cite></p> |
| <p>The function takes <cite>pandas.Series</cite> and returns a scalar value. The <cite>returnType</cite> |
| should be a primitive data type, and the returned scalar can be either a python primitive |
| type, e.g., int or float or a numpy data type, e.g., numpy.int64 or numpy.float64. |
| <cite>Any</cite> should ideally be a specific scalar type accordingly.</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="s2">"double"</span><span class="p">)</span> |
| <span class="gp">... </span><span class="k">def</span> <span class="nf">mean_udf</span><span class="p">(</span><span class="n">v</span><span class="p">:</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">v</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </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="gp">... </span> <span class="p">[(</span><span class="mi">1</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mf">2.0</span><span class="p">),</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">),</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mf">5.0</span><span class="p">),</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mf">10.0</span><span class="p">)],</span> <span class="p">(</span><span class="s2">"id"</span><span class="p">,</span> <span class="s2">"v"</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="n">df</span><span class="o">.</span><span class="n">groupby</span><span class="p">(</span><span class="s2">"id"</span><span class="p">)</span><span class="o">.</span><span class="n">agg</span><span class="p">(</span><span class="n">mean_udf</span><span class="p">(</span><span class="n">df</span><span class="p">[</span><span class="s1">'v'</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|mean_udf(v)|</span> |
| <span class="go">+---+-----------+</span> |
| <span class="go">| 1| 1.5|</span> |
| <span class="go">| 2| 6.0|</span> |
| <span class="go">+---+-----------+</span> |
| </pre></div> |
| </div> |
| <p>This UDF can also be used as window functions as below:</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">Window</span> |
| <span class="gp">>>> </span><span class="nd">@pandas_udf</span><span class="p">(</span><span class="s2">"double"</span><span class="p">)</span> |
| <span class="gp">... </span><span class="k">def</span> <span class="nf">mean_udf</span><span class="p">(</span><span class="n">v</span><span class="p">:</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">v</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </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="gp">... </span> <span class="p">[(</span><span class="mi">1</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">),</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mf">2.0</span><span class="p">),</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">),</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mf">5.0</span><span class="p">),</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mf">10.0</span><span class="p">)],</span> <span class="p">(</span><span class="s2">"id"</span><span class="p">,</span> <span class="s2">"v"</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="n">w</span> <span class="o">=</span> <span class="n">Window</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="s1">'id'</span><span class="p">)</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="s1">'v'</span><span class="p">)</span><span class="o">.</span><span class="n">rowsBetween</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">df</span><span class="o">.</span><span class="n">withColumn</span><span class="p">(</span><span class="s1">'mean_v'</span><span class="p">,</span> <span class="n">mean_udf</span><span class="p">(</span><span class="s2">"v"</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="n">w</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| v|mean_v|</span> |
| <span class="go">+---+----+------+</span> |
| <span class="go">| 1| 1.0| 1.0|</span> |
| <span class="go">| 1| 2.0| 1.5|</span> |
| <span class="go">| 2| 3.0| 3.0|</span> |
| <span class="go">| 2| 5.0| 4.0|</span> |
| <span class="go">| 2|10.0| 7.5|</span> |
| <span class="go">+---+----+------+</span> |
| </pre></div> |
| </div> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>For performance reasons, the input series to window functions are not copied. |
| Therefore, mutating the input series is not allowed and will cause incorrect results. |
| For the same reason, users should also not rely on the index of the input series.</p> |
| </div> |
| </dd> |
| </dl> |
| </li> |
| </ul> |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| <a class='left-prev' id="prev-link" href="pyspark.sql.functions.overlay.html" title="previous page">pyspark.sql.functions.overlay</a> |
| <a class='right-next' id="next-link" href="pyspark.sql.functions.percent_rank.html" title="next page">pyspark.sql.functions.percent_rank</a> |
| |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| |
| <script src="../../_static/js/index.3da636dd464baa7582d2.js"></script> |
| |
| |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| <p> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
