blob: b094acfdda6073f227995c3e3fc9c90b61aab191 [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>Spark SQL &#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/user_guide/sql/index.html" />
<link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="Apache Arrow in PySpark" href="arrow_pandas.html" />
<link rel="prev" title="Python Package Management" href="../python_packaging.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 current active nav-item">
<a class="reference internal nav-link" href="../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">
<ul class="current nav bd-sidenav">
<li class="toctree-l1">
<a class="reference internal" href="../python_packaging.html">
Python Package Management
</a>
</li>
<li class="toctree-l1 current active has-children">
<a class="current reference internal" href="#">
Spark SQL
</a>
<input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/>
<label for="toctree-checkbox-1">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l2">
<a class="reference internal" href="arrow_pandas.html">
Apache Arrow in PySpark
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="python_udtf.html">
Python User-defined Table Functions (UDTFs)
</a>
</li>
</ul>
</li>
<li class="toctree-l1 has-children">
<a class="reference internal" href="../pandas_on_spark/index.html">
Pandas API on Spark
</a>
<input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/>
<label for="toctree-checkbox-2">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l2">
<a class="reference internal" href="../pandas_on_spark/options.html">
Options and settings
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../pandas_on_spark/pandas_pyspark.html">
From/to pandas and PySpark DataFrames
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../pandas_on_spark/transform_apply.html">
Transform and apply a function
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../pandas_on_spark/types.html">
Type Support in Pandas API on Spark
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../pandas_on_spark/typehints.html">
Type Hints in Pandas API on Spark
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../pandas_on_spark/from_to_dbms.html">
From/to other DBMSes
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../pandas_on_spark/best_practices.html">
Best Practices
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../pandas_on_spark/supported_pandas_api.html">
Supported pandas API
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../pandas_on_spark/faq.html">
FAQ
</a>
</li>
</ul>
</li>
</ul>
</div>
</nav>
</div>
<div class="sidebar-end-items">
</div>
</div>
<div class="d-none d-xl-block col-xl-2 bd-toc">
<div class="toc-item">
<nav id="bd-toc-nav">
</nav>
</div>
<div class="toc-item">
</div>
</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="spark-sql">
<h1>Spark SQL<a class="headerlink" href="#spark-sql" title="Permalink to this headline">ΒΆ</a></h1>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="arrow_pandas.html">Apache Arrow in PySpark</a><ul>
<li class="toctree-l2"><a class="reference internal" href="arrow_pandas.html#ensure-pyarrow-installed">Ensure PyArrow Installed</a></li>
<li class="toctree-l2"><a class="reference internal" href="arrow_pandas.html#enabling-for-conversion-to-from-pandas">Enabling for Conversion to/from Pandas</a></li>
<li class="toctree-l2"><a class="reference internal" href="arrow_pandas.html#pandas-udfs-a-k-a-vectorized-udfs">Pandas UDFs (a.k.a. Vectorized UDFs)</a></li>
<li class="toctree-l2"><a class="reference internal" href="arrow_pandas.html#pandas-function-apis">Pandas Function APIs</a></li>
<li class="toctree-l2"><a class="reference internal" href="arrow_pandas.html#arrow-python-udfs">Arrow Python UDFs</a></li>
<li class="toctree-l2"><a class="reference internal" href="arrow_pandas.html#usage-notes">Usage Notes</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="python_udtf.html">Python User-defined Table Functions (UDTFs)</a><ul>
<li class="toctree-l2"><a class="reference internal" href="python_udtf.html#implementing-a-python-udtf">Implementing a Python UDTF</a></li>
<li class="toctree-l2"><a class="reference internal" href="python_udtf.html#registering-and-using-python-udtfs-in-sql">Registering and Using Python UDTFs in SQL</a></li>
<li class="toctree-l2"><a class="reference internal" href="python_udtf.html#arrow-optimization">Arrow Optimization</a></li>
<li class="toctree-l2"><a class="reference internal" href="python_udtf.html#more-examples">More Examples</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div>
<!-- Previous / next buttons -->
<div class='prev-next-area'>
<a class='left-prev' id="prev-link" href="../python_packaging.html" title="previous page">
<i class="fas fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Python Package Management</p>
</div>
</a>
<a class='right-next' id="next-link" href="arrow_pandas.html" title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Apache Arrow in PySpark</p>
</div>
<i class="fas fa-angle-right"></i>
</a>
</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>