Google Git
Sign in
apache / spark-website / dc8b61a479fcee33cddc5ebd4001e17e222f0d14 / . / site / docs / 3.5.0 / api / python / _modules / pyspark / sql / udtf.html
blob: 23d207336e3fc3baf91c608e6577285e503f6708 [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>pyspark.sql.udtf &#8212; PySpark 3.5.0 documentation</title>
<link href="../../../_static/styles/theme.css?digest=1999514e3f237ded88cf" rel="stylesheet">
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=1999514e3f237ded88cf" rel="stylesheet">
<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/styles/pydata-sphinx-theme.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/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf">
<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/sql/udtf.html" />
<link rel="search" title="Search" href="../../../search.html" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="docsearch:language" content="None">
<!-- Google Analytics -->
</head>
<body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80">
<div class="container-fluid" id="banner"></div>
<nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"><div class="container-xl">
<div id="navbar-start">
<a class="navbar-brand" href="../../../index.html">
<img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo">
</a>
</div>
<button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-collapsible" aria-controls="navbar-collapsible" aria-expanded="false" aria-label="Toggle navigation">
<span class="navbar-toggler-icon"></span>
</button>
<div id="navbar-collapsible" class="col-lg-9 collapse navbar-collapse">
<div id="navbar-center" class="mr-auto">
<div class="navbar-center-item">
<ul id="navbar-main-elements" class="navbar-nav">
<li class="toctree-l1 nav-item">
<a class="reference internal nav-link" href="../../../index.html">
Overview
</a>
</li>
<li class="toctree-l1 nav-item">
<a class="reference internal nav-link" href="../../../getting_started/index.html">
Getting Started
</a>
</li>
<li class="toctree-l1 nav-item">
<a class="reference internal nav-link" href="../../../user_guide/index.html">
User Guides
</a>
</li>
<li class="toctree-l1 nav-item">
<a class="reference internal nav-link" href="../../../reference/index.html">
API Reference
</a>
</li>
<li class="toctree-l1 nav-item">
<a class="reference internal nav-link" href="../../../development/index.html">
Development
</a>
</li>
<li class="toctree-l1 nav-item">
<a class="reference internal nav-link" href="../../../migration_guide/index.html">
Migration Guides
</a>
</li>
</ul>
</div>
</div>
<div id="navbar-end">
<div class="navbar-end-item">
<ul id="navbar-icon-links" class="navbar-nav" aria-label="Icon Links">
</ul>
</div>
</div>
</div>
</div>
</nav>
<div class="container-xl">
<div class="row">
<!-- Only show if we have sidebars configured, else just a small margin -->
<div class="col-12 col-md-3 bd-sidebar">
<div class="sidebar-start-items"><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">
</div>
</nav>
</div>
<div class="sidebar-end-items">
</div>
</div>
<div class="d-none d-xl-block col-xl-2 bd-toc">
</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.sql.udtf</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="sd">&quot;&quot;&quot;</span>
<span class="sd">User-defined table function related classes and functions</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">import</span> <span class="nn">pickle</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">warnings</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Type</span><span class="p">,</span> <span class="n">TYPE_CHECKING</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Union</span>
<span class="kn">from</span> <span class="nn">py4j.java_gateway</span> <span class="kn">import</span> <span class="n">JavaObject</span>
<span class="kn">from</span> <span class="nn">pyspark.errors</span> <span class="kn">import</span> <span class="n">PySparkAttributeError</span><span class="p">,</span> <span class="n">PySparkRuntimeError</span><span class="p">,</span> <span class="n">PySparkTypeError</span>
<span class="kn">from</span> <span class="nn">pyspark.rdd</span> <span class="kn">import</span> <span class="n">PythonEvalType</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.column</span> <span class="kn">import</span> <span class="n">_to_java_column</span><span class="p">,</span> <span class="n">_to_seq</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.pandas.utils</span> <span class="kn">import</span> <span class="n">require_minimum_pandas_version</span><span class="p">,</span> <span class="n">require_minimum_pyarrow_version</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="n">StructType</span><span class="p">,</span> <span class="n">_parse_datatype_string</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.udf</span> <span class="kn">import</span> <span class="n">_wrap_function</span>
<span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">pyspark.sql._typing</span> <span class="kn">import</span> <span class="n">ColumnOrName</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.dataframe</span> <span class="kn">import</span> <span class="n">DataFrame</span>
<span class="kn">from</span> <span class="nn">pyspark.sql.session</span> <span class="kn">import</span> <span class="n">SparkSession</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;UDTFRegistration&quot;</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">_create_udtf</span><span class="p">(</span>
<span class="bp">cls</span><span class="p">:</span> <span class="n">Type</span><span class="p">,</span>
<span class="n">returnType</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">StructType</span><span class="p">,</span> <span class="nb">str</span><span class="p">],</span>
<span class="n">name</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">evalType</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">PythonEvalType</span><span class="o">.</span><span class="n">SQL_TABLE_UDF</span><span class="p">,</span>
<span class="n">deterministic</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;UserDefinedTableFunction&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Create a Python UDTF with the given eval type.&quot;&quot;&quot;</span>
<span class="n">udtf_obj</span> <span class="o">=</span> <span class="n">UserDefinedTableFunction</span><span class="p">(</span>
<span class="bp">cls</span><span class="p">,</span> <span class="n">returnType</span><span class="o">=</span><span class="n">returnType</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span> <span class="n">evalType</span><span class="o">=</span><span class="n">evalType</span><span class="p">,</span> <span class="n">deterministic</span><span class="o">=</span><span class="n">deterministic</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">udtf_obj</span>
<span class="k">def</span> <span class="nf">_create_py_udtf</span><span class="p">(</span>
<span class="bp">cls</span><span class="p">:</span> <span class="n">Type</span><span class="p">,</span>
<span class="n">returnType</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">StructType</span><span class="p">,</span> <span class="nb">str</span><span class="p">],</span>
<span class="n">name</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">deterministic</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
<span class="n">useArrow</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;UserDefinedTableFunction&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Create a regular or an Arrow-optimized Python UDTF.&quot;&quot;&quot;</span>
<span class="c1"># Determine whether to create Arrow-optimized UDTFs.</span>
<span class="k">if</span> <span class="n">useArrow</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">arrow_enabled</span> <span class="o">=</span> <span class="n">useArrow</span>
<span class="k">else</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span>
<span class="n">session</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">_instantiatedSession</span>
<span class="n">arrow_enabled</span> <span class="o">=</span> <span class="kc">False</span>
<span class="k">if</span> <span class="n">session</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">value</span> <span class="o">=</span> <span class="n">session</span><span class="o">.</span><span class="n">conf</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;spark.sql.execution.pythonUDTF.arrow.enabled&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="nb">str</span><span class="p">)</span> <span class="ow">and</span> <span class="n">value</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="s2">&quot;true&quot;</span><span class="p">:</span>
<span class="n">arrow_enabled</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">eval_type</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">PythonEvalType</span><span class="o">.</span><span class="n">SQL_TABLE_UDF</span>
<span class="k">if</span> <span class="n">arrow_enabled</span><span class="p">:</span>
<span class="c1"># Return the regular UDTF if the required dependencies are not satisfied.</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">require_minimum_pandas_version</span><span class="p">()</span>
<span class="n">require_minimum_pyarrow_version</span><span class="p">()</span>
<span class="n">eval_type</span> <span class="o">=</span> <span class="n">PythonEvalType</span><span class="o">.</span><span class="n">SQL_ARROW_TABLE_UDF</span>
<span class="k">except</span> <span class="ne">ImportError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Arrow optimization for Python UDTFs cannot be enabled: </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">)</span><span class="si">}</span><span class="s2">. &quot;</span>
<span class="sa">f</span><span class="s2">&quot;Falling back to using regular Python UDTFs.&quot;</span><span class="p">,</span>
<span class="ne">UserWarning</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">_create_udtf</span><span class="p">(</span>
<span class="bp">cls</span><span class="o">=</span><span class="bp">cls</span><span class="p">,</span>
<span class="n">returnType</span><span class="o">=</span><span class="n">returnType</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span>
<span class="n">evalType</span><span class="o">=</span><span class="n">eval_type</span><span class="p">,</span>
<span class="n">deterministic</span><span class="o">=</span><span class="n">deterministic</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">def</span> <span class="nf">_validate_udtf_handler</span><span class="p">(</span><span class="bp">cls</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Validate the handler class of a UDTF.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="nb">type</span><span class="p">):</span>
<span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span>
<span class="n">error_class</span><span class="o">=</span><span class="s2">&quot;INVALID_UDTF_HANDLER_TYPE&quot;</span><span class="p">,</span> <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span><span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="nb">type</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">}</span>
<span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="s2">&quot;eval&quot;</span><span class="p">):</span>
<span class="k">raise</span> <span class="n">PySparkAttributeError</span><span class="p">(</span>
<span class="n">error_class</span><span class="o">=</span><span class="s2">&quot;INVALID_UDTF_NO_EVAL&quot;</span><span class="p">,</span> <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span><span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="p">}</span>
<span class="p">)</span>
<div class="viewcode-block" id="UserDefinedTableFunction"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.udtf.UserDefinedTableFunction.html#pyspark.sql.UserDefinedTableFunction">[docs]</a><span class="k">class</span> <span class="nc">UserDefinedTableFunction</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> User-defined table function in Python</span>
<span class="sd"> .. versionadded:: 3.5.0</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> The constructor of this class is not supposed to be directly called.</span>
<span class="sd"> Use :meth:`pyspark.sql.functions.udtf` to create this instance.</span>
<span class="sd"> This API is evolving.</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">func</span><span class="p">:</span> <span class="n">Type</span><span class="p">,</span>
<span class="n">returnType</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">StructType</span><span class="p">,</span> <span class="nb">str</span><span class="p">],</span>
<span class="n">name</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">evalType</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">PythonEvalType</span><span class="o">.</span><span class="n">SQL_TABLE_UDF</span><span class="p">,</span>
<span class="n">deterministic</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
<span class="p">):</span>
<span class="n">_validate_udtf_handler</span><span class="p">(</span><span class="n">func</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">func</span> <span class="o">=</span> <span class="n">func</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_returnType</span> <span class="o">=</span> <span class="n">returnType</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_returnType_placeholder</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">StructType</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_inputTypes_placeholder</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_judtf_placeholder</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_name</span> <span class="o">=</span> <span class="n">name</span> <span class="ow">or</span> <span class="n">func</span><span class="o">.</span><span class="vm">__name__</span>
<span class="bp">self</span><span class="o">.</span><span class="n">evalType</span> <span class="o">=</span> <span class="n">evalType</span>
<span class="bp">self</span><span class="o">.</span><span class="n">deterministic</span> <span class="o">=</span> <span class="n">deterministic</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">returnType</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">StructType</span><span class="p">:</span>
<span class="c1"># `_parse_datatype_string` accesses to JVM for parsing a DDL formatted string.</span>
<span class="c1"># This makes sure this is called after SparkContext is initialized.</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_returnType_placeholder</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_returnType</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="n">parsed</span> <span class="o">=</span> <span class="n">_parse_datatype_string</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_returnType</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">parsed</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_returnType</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">parsed</span><span class="p">,</span> <span class="n">StructType</span><span class="p">):</span>
<span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span>
<span class="n">error_class</span><span class="o">=</span><span class="s2">&quot;UDTF_RETURN_TYPE_MISMATCH&quot;</span><span class="p">,</span>
<span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">,</span>
<span class="s2">&quot;return_type&quot;</span><span class="p">:</span> <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">parsed</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_returnType_placeholder</span> <span class="o">=</span> <span class="n">parsed</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_returnType_placeholder</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">_judtf</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">JavaObject</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_judtf_placeholder</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_judtf_placeholder</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_create_judtf</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">func</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_judtf_placeholder</span>
<span class="k">def</span> <span class="nf">_create_judtf</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">func</span><span class="p">:</span> <span class="n">Type</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">JavaObject</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span>
<span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">_getActiveSessionOrCreate</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="k">try</span><span class="p">:</span>
<span class="n">wrapped_func</span> <span class="o">=</span> <span class="n">_wrap_function</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">func</span><span class="p">)</span>
<span class="k">except</span> <span class="n">pickle</span><span class="o">.</span><span class="n">PicklingError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="s2">&quot;CONTEXT_ONLY_VALID_ON_DRIVER&quot;</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">):</span>
<span class="k">raise</span> <span class="n">PySparkRuntimeError</span><span class="p">(</span>
<span class="n">error_class</span><span class="o">=</span><span class="s2">&quot;UDTF_SERIALIZATION_ERROR&quot;</span><span class="p">,</span>
<span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">,</span>
<span class="s2">&quot;message&quot;</span><span class="p">:</span> <span class="s2">&quot;it appears that you are attempting to reference SparkSession &quot;</span>
<span class="s2">&quot;inside a UDTF. SparkSession can only be used on the driver, &quot;</span>
<span class="s2">&quot;not in code that runs on workers. Please remove the reference &quot;</span>
<span class="s2">&quot;and try again.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">)</span> <span class="kn">from</span> <span class="kc">None</span>
<span class="k">raise</span> <span class="n">PySparkRuntimeError</span><span class="p">(</span>
<span class="n">error_class</span><span class="o">=</span><span class="s2">&quot;UDTF_SERIALIZATION_ERROR&quot;</span><span class="p">,</span>
<span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">,</span>
<span class="s2">&quot;message&quot;</span><span class="p">:</span> <span class="s2">&quot;Please check the stack trace and make sure the &quot;</span>
<span class="s2">&quot;function is serializable.&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">)</span>
<span class="n">jdt</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">_jsparkSession</span><span class="o">.</span><span class="n">parseDataType</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">returnType</span><span class="o">.</span><span class="n">json</span><span class="p">())</span>
<span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="n">judtf</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">sql</span><span class="o">.</span><span class="n">execution</span><span class="o">.</span><span class="n">python</span><span class="o">.</span><span class="n">UserDefinedPythonTableFunction</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">,</span> <span class="n">wrapped_func</span><span class="p">,</span> <span class="n">jdt</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">evalType</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">deterministic</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">judtf</span>
<span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="s2">&quot;ColumnOrName&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;DataFrame&quot;</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">DataFrame</span><span class="p">,</span> <span class="n">SparkSession</span>
<span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">_getActiveSessionOrCreate</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">judtf</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_judtf</span>
<span class="n">jPythonUDTF</span> <span class="o">=</span> <span class="n">judtf</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">spark</span><span class="o">.</span><span class="n">_jsparkSession</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">cols</span><span class="p">,</span> <span class="n">_to_java_column</span><span class="p">))</span>
<span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">jPythonUDTF</span><span class="p">,</span> <span class="n">spark</span><span class="p">)</span>
<div class="viewcode-block" id="UserDefinedTableFunction.asDeterministic"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.udtf.UserDefinedTableFunction.asDeterministic.html#pyspark.sql.UserDefinedTableFunction.asDeterministic">[docs]</a> <span class="k">def</span> <span class="nf">asDeterministic</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;UserDefinedTableFunction&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Updates UserDefinedTableFunction to deterministic.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># Explicitly clean the cache to create a JVM UDTF instance.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_judtf_placeholder</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">deterministic</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">return</span> <span class="bp">self</span></div></div>
<div class="viewcode-block" id="UDTFRegistration"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.UDTFRegistration.html#pyspark.sql.UDTFRegistration">[docs]</a><span class="k">class</span> <span class="nc">UDTFRegistration</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Wrapper for user-defined table function registration. This instance can be accessed by</span>
<span class="sd"> :attr:`spark.udtf` or :attr:`sqlContext.udtf`.</span>
<span class="sd"> .. versionadded:: 3.5.0</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">sparkSession</span><span class="p">:</span> <span class="s2">&quot;SparkSession&quot;</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sparkSession</span> <span class="o">=</span> <span class="n">sparkSession</span>
<div class="viewcode-block" id="UDTFRegistration.register"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.UDTFRegistration.register.html#pyspark.sql.UDTFRegistration.register">[docs]</a> <span class="k">def</span> <span class="nf">register</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="n">f</span><span class="p">:</span> <span class="s2">&quot;UserDefinedTableFunction&quot;</span><span class="p">,</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;UserDefinedTableFunction&quot;</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Register a Python user-defined table function as a SQL table function.</span>
<span class="sd"> .. versionadded:: 3.5.0</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> name : str</span>
<span class="sd"> The name of the user-defined table function in SQL statements.</span>
<span class="sd"> f : function or :meth:`pyspark.sql.functions.udtf`</span>
<span class="sd"> The user-defined table function.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> function</span>
<span class="sd"> The registered user-defined table function.</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> Spark uses the return type of the given user-defined table function as the return</span>
<span class="sd"> type of the registered user-defined function.</span>
<span class="sd"> To register a nondeterministic Python table function, users need to first build</span>
<span class="sd"> a nondeterministic user-defined table function and then register it as a SQL function.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; from pyspark.sql.functions import udtf</span>
<span class="sd"> &gt;&gt;&gt; @udtf(returnType=&quot;c1: int, c2: int&quot;)</span>
<span class="sd"> ... class PlusOne:</span>
<span class="sd"> ... def eval(self, x: int):</span>
<span class="sd"> ... yield x, x + 1</span>
<span class="sd"> ...</span>
<span class="sd"> &gt;&gt;&gt; _ = spark.udtf.register(name=&quot;plus_one&quot;, f=PlusOne)</span>
<span class="sd"> &gt;&gt;&gt; spark.sql(&quot;SELECT * FROM plus_one(1)&quot;).collect()</span>
<span class="sd"> [Row(c1=1, c2=2)]</span>
<span class="sd"> Use it with lateral join</span>
<span class="sd"> &gt;&gt;&gt; spark.sql(&quot;SELECT * FROM VALUES (0, 1), (1, 2) t(x, y), LATERAL plus_one(x)&quot;).collect()</span>
<span class="sd"> [Row(x=0, y=1, c1=0, c2=1), Row(x=1, y=2, c1=1, c2=2)]</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">f</span><span class="o">.</span><span class="n">evalType</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="n">PythonEvalType</span><span class="o">.</span><span class="n">SQL_TABLE_UDF</span><span class="p">,</span> <span class="n">PythonEvalType</span><span class="o">.</span><span class="n">SQL_ARROW_TABLE_UDF</span><span class="p">]:</span>
<span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span>
<span class="n">error_class</span><span class="o">=</span><span class="s2">&quot;INVALID_UDTF_EVAL_TYPE&quot;</span><span class="p">,</span>
<span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="n">name</span><span class="p">,</span>
<span class="s2">&quot;eval_type&quot;</span><span class="p">:</span> <span class="s2">&quot;SQL_TABLE_UDF, SQL_ARROW_TABLE_UDF&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">)</span>
<span class="n">register_udtf</span> <span class="o">=</span> <span class="n">_create_udtf</span><span class="p">(</span>
<span class="bp">cls</span><span class="o">=</span><span class="n">f</span><span class="o">.</span><span class="n">func</span><span class="p">,</span>
<span class="n">returnType</span><span class="o">=</span><span class="n">f</span><span class="o">.</span><span class="n">returnType</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span>
<span class="n">evalType</span><span class="o">=</span><span class="n">f</span><span class="o">.</span><span class="n">evalType</span><span class="p">,</span>
<span class="n">deterministic</span><span class="o">=</span><span class="n">f</span><span class="o">.</span><span class="n">deterministic</span><span class="p">,</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sparkSession</span><span class="o">.</span><span class="n">_jsparkSession</span><span class="o">.</span><span class="n">udtf</span><span class="p">()</span><span class="o">.</span><span class="n">registerPython</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">register_udtf</span><span class="o">.</span><span class="n">_judtf</span><span class="p">)</span>
<span class="k">return</span> <span class="n">register_udtf</span></div></div>
<span class="k">def</span> <span class="nf">_test</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="kc">None</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.sql.udf</span>
<span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">sql</span><span class="o">.</span><span class="n">udtf</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">&quot;local[4]&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">&quot;sql.udtf tests&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span>
<span class="n">globs</span><span class="p">[</span><span class="s2">&quot;spark&quot;</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">sql</span><span class="o">.</span><span class="n">udtf</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>
<!-- Previous / next buttons -->
<div class='prev-next-area'>
</div>
</main>
</div>
</div>
<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"></script>
<footer class="footer mt-5 mt-md-0">
<div class="container">
<div class="footer-item">
<p class="copyright">
&copy; Copyright .<br>
</p>
</div>
<div class="footer-item">
<p class="sphinx-version">
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br>
</p>
</div>
</div>
</footer>
</body>
</html>