blob: aa8a5bfbf4df8f541765c106f05dbee5e7c0c41c [file] [log] [blame]
<!DOCTYPE html>
<html lang="en" data-content_root="../../">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Common Operations &#8212; Apache Arrow DataFusion 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" type="text/css" href="../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../_static/styles/pydata-sphinx-theme.css?v=1140d252" />
<link rel="stylesheet" type="text/css" href="../../_static/graphviz.css?v=4ae1632d" />
<link rel="stylesheet" type="text/css" href="../../_static/theme_overrides.css?v=dca7052a" />
<link rel="preload" as="script" href="../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf">
<script src="../../_static/documentation_options.js?v=8a448e45"></script>
<script src="../../_static/doctools.js?v=9bcbadda"></script>
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
<link rel="index" title="Index" href="../../genindex.html" />
<link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="Registering Views" href="views.html" />
<link rel="prev" title="HTML Rendering in Jupyter" href="../dataframe/rendering.html" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="docsearch:language" content="en">
<!-- Google Analytics -->
</head>
<body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80">
<div class="container-fluid" id="banner"></div>
<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">
<a class="navbar-brand" href="../../index.html">
<img src="../../_static/images/2x_bgwhite_original.png" class="logo" alt="logo">
</a>
<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">
<p aria-level="2" class="caption" role="heading">
<span class="caption-text">
LINKS
</span>
</p>
<ul class="nav bd-sidenav">
<li class="toctree-l1">
<a class="reference external" href="https://github.com/apache/datafusion-python">
Github and Issue Tracker
</a>
</li>
<li class="toctree-l1">
<a class="reference external" href="https://docs.rs/datafusion/latest/datafusion/">
Rust's API Docs
</a>
</li>
<li class="toctree-l1">
<a class="reference external" href="https://github.com/apache/datafusion/blob/main/CODE_OF_CONDUCT.md">
Code of conduct
</a>
</li>
<li class="toctree-l1">
<a class="reference external" href="https://github.com/apache/datafusion-python/tree/main/examples">
Examples
</a>
</li>
</ul>
<p aria-level="2" class="caption" role="heading">
<span class="caption-text">
USER GUIDE
</span>
</p>
<ul class="current nav bd-sidenav">
<li class="toctree-l1">
<a class="reference internal" href="../introduction.html">
Introduction
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../basics.html">
Concepts
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../data-sources.html">
Data Sources
</a>
</li>
<li class="toctree-l1 has-children">
<a class="reference internal" href="../dataframe/index.html">
DataFrames
</a>
<input 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="../dataframe/rendering.html">
HTML Rendering in Jupyter
</a>
</li>
</ul>
</li>
<li class="toctree-l1 current active has-children">
<a class="current reference internal" href="#">
Common Operations
</a>
<input checked="" 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="views.html">
Registering Views
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="basic-info.html">
Basic Operations
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="select-and-filter.html">
Column Selections
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="expressions.html">
Expressions
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="joins.html">
Joins
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="functions.html">
Functions
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="aggregations.html">
Aggregation
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="windows.html">
Window Functions
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="udf-and-udfa.html">
User-Defined Functions
</a>
</li>
</ul>
</li>
<li class="toctree-l1 has-children">
<a class="reference internal" href="../io/index.html">
IO
</a>
<input class="toctree-checkbox" id="toctree-checkbox-3" name="toctree-checkbox-3" type="checkbox"/>
<label for="toctree-checkbox-3">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l2">
<a class="reference internal" href="../io/arrow.html">
Arrow
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/avro.html">
Avro
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/csv.html">
CSV
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/json.html">
JSON
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/parquet.html">
Parquet
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/table_provider.html">
Custom Table Provider
</a>
</li>
</ul>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../configuration.html">
Configuration
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../sql.html">
SQL
</a>
</li>
</ul>
<p aria-level="2" class="caption" role="heading">
<span class="caption-text">
CONTRIBUTOR GUIDE
</span>
</p>
<ul class="nav bd-sidenav">
<li class="toctree-l1">
<a class="reference internal" href="../../contributor-guide/introduction.html">
Introduction
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../../contributor-guide/ffi.html">
Python Extensions
</a>
</li>
</ul>
<p aria-level="2" class="caption" role="heading">
<span class="caption-text">
API
</span>
</p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children">
<a class="reference internal" href="../../autoapi/index.html">
API Reference
</a>
<input class="toctree-checkbox" id="toctree-checkbox-4" name="toctree-checkbox-4" type="checkbox"/>
<label for="toctree-checkbox-4">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l2 has-children">
<a class="reference internal" href="../../autoapi/datafusion/index.html">
datafusion
</a>
<input class="toctree-checkbox" id="toctree-checkbox-5" name="toctree-checkbox-5" type="checkbox"/>
<label for="toctree-checkbox-5">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/catalog/index.html">
datafusion.catalog
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/context/index.html">
datafusion.context
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/dataframe/index.html">
datafusion.dataframe
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/dataframe_formatter/index.html">
datafusion.dataframe_formatter
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/expr/index.html">
datafusion.expr
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/functions/index.html">
datafusion.functions
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/html_formatter/index.html">
datafusion.html_formatter
</a>
</li>
<li class="toctree-l3 has-children">
<a class="reference internal" href="../../autoapi/datafusion/input/index.html">
datafusion.input
</a>
<input class="toctree-checkbox" id="toctree-checkbox-6" name="toctree-checkbox-6" type="checkbox"/>
<label for="toctree-checkbox-6">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l4">
<a class="reference internal" href="../../autoapi/datafusion/input/base/index.html">
datafusion.input.base
</a>
</li>
<li class="toctree-l4">
<a class="reference internal" href="../../autoapi/datafusion/input/location/index.html">
datafusion.input.location
</a>
</li>
</ul>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/io/index.html">
datafusion.io
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/object_store/index.html">
datafusion.object_store
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/plan/index.html">
datafusion.plan
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/record_batch/index.html">
datafusion.record_batch
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/substrait/index.html">
datafusion.substrait
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/unparser/index.html">
datafusion.unparser
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/user_defined/index.html">
datafusion.user_defined
</a>
</li>
</ul>
</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>
<section id="common-operations">
<h1>Common Operations<a class="headerlink" href="#common-operations" title="Link to this heading">ΒΆ</a></h1>
<p>The contents of this section are designed to guide a new user through how to use DataFusion.</p>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="views.html">Registering Views</a></li>
<li class="toctree-l1"><a class="reference internal" href="basic-info.html">Basic Operations</a></li>
<li class="toctree-l1"><a class="reference internal" href="select-and-filter.html">Column Selections</a></li>
<li class="toctree-l1"><a class="reference internal" href="expressions.html">Expressions</a><ul>
<li class="toctree-l2"><a class="reference internal" href="expressions.html#column">Column</a></li>
<li class="toctree-l2"><a class="reference internal" href="expressions.html#literal">Literal</a></li>
<li class="toctree-l2"><a class="reference internal" href="expressions.html#boolean">Boolean</a></li>
<li class="toctree-l2"><a class="reference internal" href="expressions.html#arrays">Arrays</a></li>
<li class="toctree-l2"><a class="reference internal" href="expressions.html#structs">Structs</a></li>
<li class="toctree-l2"><a class="reference internal" href="expressions.html#functions">Functions</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="joins.html">Joins</a><ul>
<li class="toctree-l2"><a class="reference internal" href="joins.html#inner-join">Inner Join</a></li>
<li class="toctree-l2"><a class="reference internal" href="joins.html#left-join">Left Join</a></li>
<li class="toctree-l2"><a class="reference internal" href="joins.html#full-join">Full Join</a></li>
<li class="toctree-l2"><a class="reference internal" href="joins.html#left-semi-join">Left Semi Join</a></li>
<li class="toctree-l2"><a class="reference internal" href="joins.html#left-anti-join">Left Anti Join</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="functions.html">Functions</a><ul>
<li class="toctree-l2"><a class="reference internal" href="functions.html#mathematical">Mathematical</a></li>
<li class="toctree-l2"><a class="reference internal" href="functions.html#conditional">Conditional</a></li>
<li class="toctree-l2"><a class="reference internal" href="functions.html#temporal">Temporal</a></li>
<li class="toctree-l2"><a class="reference internal" href="functions.html#string">String</a></li>
<li class="toctree-l2"><a class="reference internal" href="functions.html#casting">Casting</a></li>
<li class="toctree-l2"><a class="reference internal" href="functions.html#other">Other</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="functions.html#handling-missing-values">Handling Missing Values</a><ul>
<li class="toctree-l2"><a class="reference internal" href="functions.html#fill-null">fill_null</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="aggregations.html">Aggregation</a><ul>
<li class="toctree-l2"><a class="reference internal" href="aggregations.html#setting-parameters">Setting Parameters</a></li>
<li class="toctree-l2"><a class="reference internal" href="aggregations.html#aggregate-functions">Aggregate Functions</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="windows.html">Window Functions</a><ul>
<li class="toctree-l2"><a class="reference internal" href="windows.html#setting-parameters">Setting Parameters</a></li>
<li class="toctree-l2"><a class="reference internal" href="windows.html#aggregate-functions">Aggregate Functions</a></li>
<li class="toctree-l2"><a class="reference internal" href="windows.html#available-functions">Available Functions</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="udf-and-udfa.html">User-Defined Functions</a><ul>
<li class="toctree-l2"><a class="reference internal" href="udf-and-udfa.html#scalar-functions">Scalar Functions</a></li>
<li class="toctree-l2"><a class="reference internal" href="udf-and-udfa.html#aggregate-functions">Aggregate Functions</a></li>
<li class="toctree-l2"><a class="reference internal" href="udf-and-udfa.html#window-functions">Window Functions</a></li>
<li class="toctree-l2"><a class="reference internal" href="udf-and-udfa.html#table-functions">Table Functions</a></li>
</ul>
</li>
</ul>
</div>
</section>
</div>
<!-- Previous / next buttons -->
<div class='prev-next-area'>
<a class='left-prev' id="prev-link" href="../dataframe/rendering.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">HTML Rendering in Jupyter</p>
</div>
</a>
<a class='right-next' id="next-link" href="views.html" title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Registering Views</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>
<!-- Based on pydata_sphinx_theme/footer.html -->
<footer class="footer mt-5 mt-md-0">
<div class="container">
<div class="footer-item">
<p class="copyright">
&copy; Copyright 2019-2024, Apache Software Foundation.<br>
</p>
</div>
<div class="footer-item">
<p class="sphinx-version">
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 8.1.3.<br>
</p>
</div>
<div class="footer-item">
<p>Apache Arrow DataFusion, Arrow DataFusion, Apache, the Apache feather logo, and the Apache Arrow DataFusion project logo</p>
<p>are either registered trademarks or trademarks of The Apache Software Foundation in the United States and other countries.</p>
</div>
</div>
</footer>
</body>
</html>