blob: f1be5894fa2dd58b3cfee4cf65938773e288bb3a [file]
<!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>Data Sources &#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="DataFrames" href="dataframe.html" />
<link rel="prev" title="Concepts" href="basics.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 current active">
<a class="current reference internal" href="#">
Data Sources
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="dataframe.html">
DataFrames
</a>
</li>
<li class="toctree-l1 has-children">
<a class="reference internal" href="common-operations/index.html">
Common Operations
</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="common-operations/views.html">
Registering Views
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="common-operations/basic-info.html">
Basic Operations
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="common-operations/select-and-filter.html">
Column Selections
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="common-operations/expressions.html">
Expressions
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="common-operations/joins.html">
Joins
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="common-operations/functions.html">
Functions
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="common-operations/aggregations.html">
Aggregation
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="common-operations/windows.html">
Window Functions
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="common-operations/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-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="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-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 has-children">
<a class="reference internal" href="../autoapi/datafusion/index.html">
datafusion
</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-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/col/index.html">
datafusion.col
</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/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-5" name="toctree-checkbox-5" type="checkbox"/>
<label for="toctree-checkbox-5">
<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/udf/index.html">
datafusion.udf
</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">
<div class="tocsection onthispage pt-5 pb-3">
<i class="fas fa-list"></i> On this page
</div>
<nav id="bd-toc-nav">
<ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#local-file">
Local file
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#create-in-memory">
Create in-memory
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#object-store">
Object Store
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#other-dataframe-libraries">
Other DataFrame Libraries
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#delta-lake">
Delta Lake
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#iceberg">
Iceberg
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#custom-table-provider">
Custom Table Provider
</a>
</li>
</ul>
</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="data-sources">
<span id="user-guide-data-sources"></span><h1>Data Sources<a class="headerlink" href="#data-sources" title="Link to this heading"></a></h1>
<p>DataFusion provides a wide variety of ways to get data into a DataFrame to perform operations.</p>
<section id="local-file">
<h2>Local file<a class="headerlink" href="#local-file" title="Link to this heading"></a></h2>
<p>DataFusion has the abilty to read from a variety of popular file formats, such as <a class="reference internal" href="io/parquet.html#io-parquet"><span class="std std-ref">Parquet</span></a>,
<a class="reference internal" href="io/csv.html#io-csv"><span class="std std-ref">CSV</span></a>, <a class="reference internal" href="io/json.html#io-json"><span class="std std-ref">JSON</span></a>, and <a class="reference internal" href="io/avro.html#io-avro"><span class="std std-ref">AVRO</span></a>.</p>
<div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">1</span><span class="p">]:</span> <span class="kn">from</span><span class="w"> </span><span class="nn">datafusion</span><span class="w"> </span><span class="kn">import</span> <span class="n">SessionContext</span>
<span class="n">In</span> <span class="p">[</span><span class="mi">2</span><span class="p">]:</span> <span class="n">ctx</span> <span class="o">=</span> <span class="n">SessionContext</span><span class="p">()</span>
<span class="n">In</span> <span class="p">[</span><span class="mi">3</span><span class="p">]:</span> <span class="n">df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">read_csv</span><span class="p">(</span><span class="s2">&quot;pokemon.csv&quot;</span><span class="p">)</span>
<span class="n">In</span> <span class="p">[</span><span class="mi">4</span><span class="p">]:</span> <span class="n">df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
<span class="n">DataFrame</span><span class="p">()</span>
<span class="o">+----+---------------------------+--------+--------+-------+----+--------+---------+---------+---------+-------+------------+-----------+</span>
<span class="o">|</span> <span class="c1"># | Name | Type 1 | Type 2 | Total | HP | Attack | Defense | Sp. Atk | Sp. Def | Speed | Generation | Legendary |</span>
<span class="o">+----+---------------------------+--------+--------+-------+----+--------+---------+---------+---------+-------+------------+-----------+</span>
<span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">Bulbasaur</span> <span class="o">|</span> <span class="n">Grass</span> <span class="o">|</span> <span class="n">Poison</span> <span class="o">|</span> <span class="mi">318</span> <span class="o">|</span> <span class="mi">45</span> <span class="o">|</span> <span class="mi">49</span> <span class="o">|</span> <span class="mi">49</span> <span class="o">|</span> <span class="mi">65</span> <span class="o">|</span> <span class="mi">65</span> <span class="o">|</span> <span class="mi">45</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">2</span> <span class="o">|</span> <span class="n">Ivysaur</span> <span class="o">|</span> <span class="n">Grass</span> <span class="o">|</span> <span class="n">Poison</span> <span class="o">|</span> <span class="mi">405</span> <span class="o">|</span> <span class="mi">60</span> <span class="o">|</span> <span class="mi">62</span> <span class="o">|</span> <span class="mi">63</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">60</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">3</span> <span class="o">|</span> <span class="n">Venusaur</span> <span class="o">|</span> <span class="n">Grass</span> <span class="o">|</span> <span class="n">Poison</span> <span class="o">|</span> <span class="mi">525</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">82</span> <span class="o">|</span> <span class="mi">83</span> <span class="o">|</span> <span class="mi">100</span> <span class="o">|</span> <span class="mi">100</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">3</span> <span class="o">|</span> <span class="n">VenusaurMega</span> <span class="n">Venusaur</span> <span class="o">|</span> <span class="n">Grass</span> <span class="o">|</span> <span class="n">Poison</span> <span class="o">|</span> <span class="mi">625</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">100</span> <span class="o">|</span> <span class="mi">123</span> <span class="o">|</span> <span class="mi">122</span> <span class="o">|</span> <span class="mi">120</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">4</span> <span class="o">|</span> <span class="n">Charmander</span> <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> <span class="o">|</span> <span class="mi">309</span> <span class="o">|</span> <span class="mi">39</span> <span class="o">|</span> <span class="mi">52</span> <span class="o">|</span> <span class="mi">43</span> <span class="o">|</span> <span class="mi">60</span> <span class="o">|</span> <span class="mi">50</span> <span class="o">|</span> <span class="mi">65</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">5</span> <span class="o">|</span> <span class="n">Charmeleon</span> <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> <span class="o">|</span> <span class="mi">405</span> <span class="o">|</span> <span class="mi">58</span> <span class="o">|</span> <span class="mi">64</span> <span class="o">|</span> <span class="mi">58</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">65</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">6</span> <span class="o">|</span> <span class="n">Charizard</span> <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> <span class="n">Flying</span> <span class="o">|</span> <span class="mi">534</span> <span class="o">|</span> <span class="mi">78</span> <span class="o">|</span> <span class="mi">84</span> <span class="o">|</span> <span class="mi">78</span> <span class="o">|</span> <span class="mi">109</span> <span class="o">|</span> <span class="mi">85</span> <span class="o">|</span> <span class="mi">100</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">6</span> <span class="o">|</span> <span class="n">CharizardMega</span> <span class="n">Charizard</span> <span class="n">X</span> <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> <span class="n">Dragon</span> <span class="o">|</span> <span class="mi">634</span> <span class="o">|</span> <span class="mi">78</span> <span class="o">|</span> <span class="mi">130</span> <span class="o">|</span> <span class="mi">111</span> <span class="o">|</span> <span class="mi">130</span> <span class="o">|</span> <span class="mi">85</span> <span class="o">|</span> <span class="mi">100</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">6</span> <span class="o">|</span> <span class="n">CharizardMega</span> <span class="n">Charizard</span> <span class="n">Y</span> <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> <span class="n">Flying</span> <span class="o">|</span> <span class="mi">634</span> <span class="o">|</span> <span class="mi">78</span> <span class="o">|</span> <span class="mi">104</span> <span class="o">|</span> <span class="mi">78</span> <span class="o">|</span> <span class="mi">159</span> <span class="o">|</span> <span class="mi">115</span> <span class="o">|</span> <span class="mi">100</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">7</span> <span class="o">|</span> <span class="n">Squirtle</span> <span class="o">|</span> <span class="n">Water</span> <span class="o">|</span> <span class="o">|</span> <span class="mi">314</span> <span class="o">|</span> <span class="mi">44</span> <span class="o">|</span> <span class="mi">48</span> <span class="o">|</span> <span class="mi">65</span> <span class="o">|</span> <span class="mi">50</span> <span class="o">|</span> <span class="mi">64</span> <span class="o">|</span> <span class="mi">43</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">8</span> <span class="o">|</span> <span class="n">Wartortle</span> <span class="o">|</span> <span class="n">Water</span> <span class="o">|</span> <span class="o">|</span> <span class="mi">405</span> <span class="o">|</span> <span class="mi">59</span> <span class="o">|</span> <span class="mi">63</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">65</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">58</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">9</span> <span class="o">|</span> <span class="n">Blastoise</span> <span class="o">|</span> <span class="n">Water</span> <span class="o">|</span> <span class="o">|</span> <span class="mi">530</span> <span class="o">|</span> <span class="mi">79</span> <span class="o">|</span> <span class="mi">83</span> <span class="o">|</span> <span class="mi">100</span> <span class="o">|</span> <span class="mi">85</span> <span class="o">|</span> <span class="mi">105</span> <span class="o">|</span> <span class="mi">78</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">9</span> <span class="o">|</span> <span class="n">BlastoiseMega</span> <span class="n">Blastoise</span> <span class="o">|</span> <span class="n">Water</span> <span class="o">|</span> <span class="o">|</span> <span class="mi">630</span> <span class="o">|</span> <span class="mi">79</span> <span class="o">|</span> <span class="mi">103</span> <span class="o">|</span> <span class="mi">120</span> <span class="o">|</span> <span class="mi">135</span> <span class="o">|</span> <span class="mi">115</span> <span class="o">|</span> <span class="mi">78</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">10</span> <span class="o">|</span> <span class="n">Caterpie</span> <span class="o">|</span> <span class="n">Bug</span> <span class="o">|</span> <span class="o">|</span> <span class="mi">195</span> <span class="o">|</span> <span class="mi">45</span> <span class="o">|</span> <span class="mi">30</span> <span class="o">|</span> <span class="mi">35</span> <span class="o">|</span> <span class="mi">20</span> <span class="o">|</span> <span class="mi">20</span> <span class="o">|</span> <span class="mi">45</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">11</span> <span class="o">|</span> <span class="n">Metapod</span> <span class="o">|</span> <span class="n">Bug</span> <span class="o">|</span> <span class="o">|</span> <span class="mi">205</span> <span class="o">|</span> <span class="mi">50</span> <span class="o">|</span> <span class="mi">20</span> <span class="o">|</span> <span class="mi">55</span> <span class="o">|</span> <span class="mi">25</span> <span class="o">|</span> <span class="mi">25</span> <span class="o">|</span> <span class="mi">30</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">12</span> <span class="o">|</span> <span class="n">Butterfree</span> <span class="o">|</span> <span class="n">Bug</span> <span class="o">|</span> <span class="n">Flying</span> <span class="o">|</span> <span class="mi">395</span> <span class="o">|</span> <span class="mi">60</span> <span class="o">|</span> <span class="mi">45</span> <span class="o">|</span> <span class="mi">50</span> <span class="o">|</span> <span class="mi">90</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">70</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">13</span> <span class="o">|</span> <span class="n">Weedle</span> <span class="o">|</span> <span class="n">Bug</span> <span class="o">|</span> <span class="n">Poison</span> <span class="o">|</span> <span class="mi">195</span> <span class="o">|</span> <span class="mi">40</span> <span class="o">|</span> <span class="mi">35</span> <span class="o">|</span> <span class="mi">30</span> <span class="o">|</span> <span class="mi">20</span> <span class="o">|</span> <span class="mi">20</span> <span class="o">|</span> <span class="mi">50</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">14</span> <span class="o">|</span> <span class="n">Kakuna</span> <span class="o">|</span> <span class="n">Bug</span> <span class="o">|</span> <span class="n">Poison</span> <span class="o">|</span> <span class="mi">205</span> <span class="o">|</span> <span class="mi">45</span> <span class="o">|</span> <span class="mi">25</span> <span class="o">|</span> <span class="mi">50</span> <span class="o">|</span> <span class="mi">25</span> <span class="o">|</span> <span class="mi">25</span> <span class="o">|</span> <span class="mi">35</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">15</span> <span class="o">|</span> <span class="n">Beedrill</span> <span class="o">|</span> <span class="n">Bug</span> <span class="o">|</span> <span class="n">Poison</span> <span class="o">|</span> <span class="mi">395</span> <span class="o">|</span> <span class="mi">65</span> <span class="o">|</span> <span class="mi">90</span> <span class="o">|</span> <span class="mi">40</span> <span class="o">|</span> <span class="mi">45</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">75</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">15</span> <span class="o">|</span> <span class="n">BeedrillMega</span> <span class="n">Beedrill</span> <span class="o">|</span> <span class="n">Bug</span> <span class="o">|</span> <span class="n">Poison</span> <span class="o">|</span> <span class="mi">495</span> <span class="o">|</span> <span class="mi">65</span> <span class="o">|</span> <span class="mi">150</span> <span class="o">|</span> <span class="mi">40</span> <span class="o">|</span> <span class="mi">15</span> <span class="o">|</span> <span class="mi">80</span> <span class="o">|</span> <span class="mi">145</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="n">false</span> <span class="o">|</span>
<span class="o">+----+---------------------------+--------+--------+-------+----+--------+---------+---------+---------+-------+------------+-----------+</span>
</pre></div>
</div>
</section>
<section id="create-in-memory">
<h2>Create in-memory<a class="headerlink" href="#create-in-memory" title="Link to this heading"></a></h2>
<p>Sometimes it can be convenient to create a small DataFrame from a Python list or dictionary object.
To do this in DataFusion, you can use one of the three functions
<a class="reference internal" href="../autoapi/datafusion/context/index.html#datafusion.context.SessionContext.from_pydict" title="datafusion.context.SessionContext.from_pydict"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_pydict()</span></code></a>,
<a class="reference internal" href="../autoapi/datafusion/context/index.html#datafusion.context.SessionContext.from_pylist" title="datafusion.context.SessionContext.from_pylist"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_pylist()</span></code></a>, or
<a class="reference internal" href="../autoapi/datafusion/context/index.html#datafusion.context.SessionContext.create_dataframe" title="datafusion.context.SessionContext.create_dataframe"><code class="xref py py-func docutils literal notranslate"><span class="pre">create_dataframe()</span></code></a>.</p>
<p>As their names suggest, <code class="docutils literal notranslate"><span class="pre">from_pydict</span></code> and <code class="docutils literal notranslate"><span class="pre">from_pylist</span></code> will create DataFrames from Python
dictionary and list objects, respectively. <code class="docutils literal notranslate"><span class="pre">create_dataframe</span></code> assumes you will pass in a list
of list of <a class="reference external" href="https://arrow.apache.org/docs/python/generated/pyarrow.RecordBatch.html">PyArrow Record Batches</a>.</p>
<p>The following three examples all will create identical DataFrames:</p>
<div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">5</span><span class="p">]:</span> <span class="kn">import</span><span class="w"> </span><span class="nn">pyarrow</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">pa</span>
<span class="n">In</span> <span class="p">[</span><span class="mi">6</span><span class="p">]:</span> <span class="n">ctx</span><span class="o">.</span><span class="n">from_pylist</span><span class="p">([</span>
<span class="o">...</span><span class="p">:</span> <span class="p">{</span> <span class="s2">&quot;a&quot;</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">:</span> <span class="mf">10.0</span><span class="p">,</span> <span class="s2">&quot;c&quot;</span><span class="p">:</span> <span class="s2">&quot;alpha&quot;</span> <span class="p">},</span>
<span class="o">...</span><span class="p">:</span> <span class="p">{</span> <span class="s2">&quot;a&quot;</span><span class="p">:</span> <span class="mi">2</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">:</span> <span class="mf">20.0</span><span class="p">,</span> <span class="s2">&quot;c&quot;</span><span class="p">:</span> <span class="s2">&quot;beta&quot;</span> <span class="p">},</span>
<span class="o">...</span><span class="p">:</span> <span class="p">{</span> <span class="s2">&quot;a&quot;</span><span class="p">:</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">:</span> <span class="mf">30.0</span><span class="p">,</span> <span class="s2">&quot;c&quot;</span><span class="p">:</span> <span class="s2">&quot;gamma&quot;</span> <span class="p">},</span>
<span class="o">...</span><span class="p">:</span> <span class="p">])</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
<span class="o">...</span><span class="p">:</span>
<span class="n">DataFrame</span><span class="p">()</span>
<span class="o">+---+------+-------+</span>
<span class="o">|</span> <span class="n">a</span> <span class="o">|</span> <span class="n">b</span> <span class="o">|</span> <span class="n">c</span> <span class="o">|</span>
<span class="o">+---+------+-------+</span>
<span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mf">10.0</span> <span class="o">|</span> <span class="n">alpha</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">2</span> <span class="o">|</span> <span class="mf">20.0</span> <span class="o">|</span> <span class="n">beta</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">3</span> <span class="o">|</span> <span class="mf">30.0</span> <span class="o">|</span> <span class="n">gamma</span> <span class="o">|</span>
<span class="o">+---+------+-------+</span>
<span class="n">In</span> <span class="p">[</span><span class="mi">7</span><span class="p">]:</span> <span class="n">ctx</span><span class="o">.</span><span class="n">from_pydict</span><span class="p">({</span>
<span class="o">...</span><span class="p">:</span> <span class="s2">&quot;a&quot;</span><span class="p">:</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="o">...</span><span class="p">:</span> <span class="s2">&quot;b&quot;</span><span class="p">:</span> <span class="p">[</span><span class="mf">10.0</span><span class="p">,</span> <span class="mf">20.0</span><span class="p">,</span> <span class="mf">30.0</span><span class="p">],</span>
<span class="o">...</span><span class="p">:</span> <span class="s2">&quot;c&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;alpha&quot;</span><span class="p">,</span> <span class="s2">&quot;beta&quot;</span><span class="p">,</span> <span class="s2">&quot;gamma&quot;</span><span class="p">],</span>
<span class="o">...</span><span class="p">:</span> <span class="p">})</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
<span class="o">...</span><span class="p">:</span>
<span class="n">DataFrame</span><span class="p">()</span>
<span class="o">+---+------+-------+</span>
<span class="o">|</span> <span class="n">a</span> <span class="o">|</span> <span class="n">b</span> <span class="o">|</span> <span class="n">c</span> <span class="o">|</span>
<span class="o">+---+------+-------+</span>
<span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mf">10.0</span> <span class="o">|</span> <span class="n">alpha</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">2</span> <span class="o">|</span> <span class="mf">20.0</span> <span class="o">|</span> <span class="n">beta</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">3</span> <span class="o">|</span> <span class="mf">30.0</span> <span class="o">|</span> <span class="n">gamma</span> <span class="o">|</span>
<span class="o">+---+------+-------+</span>
<span class="n">In</span> <span class="p">[</span><span class="mi">8</span><span class="p">]:</span> <span class="n">batch</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">RecordBatch</span><span class="o">.</span><span class="n">from_arrays</span><span class="p">(</span>
<span class="o">...</span><span class="p">:</span> <span class="p">[</span>
<span class="o">...</span><span class="p">:</span> <span class="n">pa</span><span class="o">.</span><span class="n">array</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="o">...</span><span class="p">:</span> <span class="n">pa</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">10.0</span><span class="p">,</span> <span class="mf">20.0</span><span class="p">,</span> <span class="mf">30.0</span><span class="p">]),</span>
<span class="o">...</span><span class="p">:</span> <span class="n">pa</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="s2">&quot;alpha&quot;</span><span class="p">,</span> <span class="s2">&quot;beta&quot;</span><span class="p">,</span> <span class="s2">&quot;gamma&quot;</span><span class="p">]),</span>
<span class="o">...</span><span class="p">:</span> <span class="p">],</span>
<span class="o">...</span><span class="p">:</span> <span class="n">names</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;a&quot;</span><span class="p">,</span> <span class="s2">&quot;b&quot;</span><span class="p">,</span> <span class="s2">&quot;c&quot;</span><span class="p">],</span>
<span class="o">...</span><span class="p">:</span> <span class="p">)</span>
<span class="o">...</span><span class="p">:</span>
<span class="n">In</span> <span class="p">[</span><span class="mi">9</span><span class="p">]:</span> <span class="n">ctx</span><span class="o">.</span><span class="n">create_dataframe</span><span class="p">([[</span><span class="n">batch</span><span class="p">]])</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
<span class="n">DataFrame</span><span class="p">()</span>
<span class="o">+---+------+-------+</span>
<span class="o">|</span> <span class="n">a</span> <span class="o">|</span> <span class="n">b</span> <span class="o">|</span> <span class="n">c</span> <span class="o">|</span>
<span class="o">+---+------+-------+</span>
<span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mf">10.0</span> <span class="o">|</span> <span class="n">alpha</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">2</span> <span class="o">|</span> <span class="mf">20.0</span> <span class="o">|</span> <span class="n">beta</span> <span class="o">|</span>
<span class="o">|</span> <span class="mi">3</span> <span class="o">|</span> <span class="mf">30.0</span> <span class="o">|</span> <span class="n">gamma</span> <span class="o">|</span>
<span class="o">+---+------+-------+</span>
</pre></div>
</div>
</section>
<section id="object-store">
<h2>Object Store<a class="headerlink" href="#object-store" title="Link to this heading"></a></h2>
<p>DataFusion has support for multiple storage options in addition to local files.
The example below requires an appropriate S3 account with access credentials.</p>
<p>Supported Object Stores are</p>
<ul class="simple">
<li><p><a class="reference internal" href="../autoapi/datafusion/object_store/index.html#datafusion.object_store.AmazonS3" title="datafusion.object_store.AmazonS3"><code class="xref py py-class docutils literal notranslate"><span class="pre">AmazonS3</span></code></a></p></li>
<li><p><a class="reference internal" href="../autoapi/datafusion/object_store/index.html#datafusion.object_store.GoogleCloud" title="datafusion.object_store.GoogleCloud"><code class="xref py py-class docutils literal notranslate"><span class="pre">GoogleCloud</span></code></a></p></li>
<li><p><a class="reference internal" href="../autoapi/datafusion/object_store/index.html#datafusion.object_store.Http" title="datafusion.object_store.Http"><code class="xref py py-class docutils literal notranslate"><span class="pre">Http</span></code></a></p></li>
<li><p><a class="reference internal" href="../autoapi/datafusion/object_store/index.html#datafusion.object_store.LocalFileSystem" title="datafusion.object_store.LocalFileSystem"><code class="xref py py-class docutils literal notranslate"><span class="pre">LocalFileSystem</span></code></a></p></li>
<li><p><a class="reference internal" href="../autoapi/datafusion/object_store/index.html#datafusion.object_store.MicrosoftAzure" title="datafusion.object_store.MicrosoftAzure"><code class="xref py py-class docutils literal notranslate"><span class="pre">MicrosoftAzure</span></code></a></p></li>
</ul>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">datafusion.object_store</span><span class="w"> </span><span class="kn">import</span> <span class="n">AmazonS3</span>
<span class="n">region</span> <span class="o">=</span> <span class="s2">&quot;us-east-1&quot;</span>
<span class="n">bucket_name</span> <span class="o">=</span> <span class="s2">&quot;yellow-trips&quot;</span>
<span class="n">s3</span> <span class="o">=</span> <span class="n">AmazonS3</span><span class="p">(</span>
<span class="n">bucket_name</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span>
<span class="n">region</span><span class="o">=</span><span class="n">region</span><span class="p">,</span>
<span class="n">access_key_id</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span><span class="s2">&quot;AWS_ACCESS_KEY_ID&quot;</span><span class="p">),</span>
<span class="n">secret_access_key</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span><span class="s2">&quot;AWS_SECRET_ACCESS_KEY&quot;</span><span class="p">),</span>
<span class="p">)</span>
<span class="n">path</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;s3://</span><span class="si">{</span><span class="n">bucket_name</span><span class="si">}</span><span class="s2">/&quot;</span>
<span class="n">ctx</span><span class="o">.</span><span class="n">register_object_store</span><span class="p">(</span><span class="s2">&quot;s3://&quot;</span><span class="p">,</span> <span class="n">s3</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
<span class="n">ctx</span><span class="o">.</span><span class="n">register_parquet</span><span class="p">(</span><span class="s2">&quot;trips&quot;</span><span class="p">,</span> <span class="n">path</span><span class="p">)</span>
<span class="n">ctx</span><span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="s2">&quot;trips&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
</section>
<section id="other-dataframe-libraries">
<h2>Other DataFrame Libraries<a class="headerlink" href="#other-dataframe-libraries" title="Link to this heading"></a></h2>
<p>DataFusion can import DataFrames directly from other libraries, such as
<a class="reference external" href="https://pola.rs/">Polars</a> and <a class="reference external" href="https://pandas.pydata.org/">Pandas</a>.
Since DataFusion version 42.0.0, any DataFrame library that supports the Arrow FFI PyCapsule
interface can be imported to DataFusion using the
<a class="reference internal" href="../autoapi/datafusion/context/index.html#datafusion.context.SessionContext.from_arrow" title="datafusion.context.SessionContext.from_arrow"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_arrow()</span></code></a> function. Older verions of Polars may
not support the arrow interface. In those cases, you can still import via the
<a class="reference internal" href="../autoapi/datafusion/context/index.html#datafusion.context.SessionContext.from_polars" title="datafusion.context.SessionContext.from_polars"><code class="xref py py-func docutils literal notranslate"><span class="pre">from_polars()</span></code></a> function.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">pandas</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">pd</span>
<span class="n">data</span> <span class="o">=</span> <span class="p">{</span> <span class="s2">&quot;a&quot;</span><span class="p">:</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="s2">&quot;b&quot;</span><span class="p">:</span> <span class="p">[</span><span class="mf">10.0</span><span class="p">,</span> <span class="mf">20.0</span><span class="p">,</span> <span class="mf">30.0</span><span class="p">],</span> <span class="s2">&quot;c&quot;</span><span class="p">:</span> <span class="p">[</span><span class="s2">&quot;alpha&quot;</span><span class="p">,</span> <span class="s2">&quot;beta&quot;</span><span class="p">,</span> <span class="s2">&quot;gamma&quot;</span><span class="p">]</span> <span class="p">}</span>
<span class="n">pandas_df</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="n">data</span><span class="p">)</span>
<span class="n">datafusion_df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">from_arrow</span><span class="p">(</span><span class="n">pandas_df</span><span class="p">)</span>
<span class="n">datafusion_df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">polars</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">pl</span>
<span class="n">polars_df</span> <span class="o">=</span> <span class="n">pl</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="n">datafusion_df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">from_arrow</span><span class="p">(</span><span class="n">polars_df</span><span class="p">)</span>
<span class="n">datafusion_df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
</section>
<section id="delta-lake">
<h2>Delta Lake<a class="headerlink" href="#delta-lake" title="Link to this heading"></a></h2>
<p>DataFusion 43.0.0 and later support the ability to register table providers from sources such
as Delta Lake. This will require a recent version of
<a class="reference external" href="https://delta-io.github.io/delta-rs/">deltalake</a> to provide the required interfaces.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">deltalake</span><span class="w"> </span><span class="kn">import</span> <span class="n">DeltaTable</span>
<span class="n">delta_table</span> <span class="o">=</span> <span class="n">DeltaTable</span><span class="p">(</span><span class="s2">&quot;path_to_table&quot;</span><span class="p">)</span>
<span class="n">ctx</span><span class="o">.</span><span class="n">register_table_provider</span><span class="p">(</span><span class="s2">&quot;my_delta_table&quot;</span><span class="p">,</span> <span class="n">delta_table</span><span class="p">)</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="s2">&quot;my_delta_table&quot;</span><span class="p">)</span>
<span class="n">df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
<p>On older versions of <code class="docutils literal notranslate"><span class="pre">deltalake</span></code> (prior to 0.22) you can use the
<a class="reference external" href="https://arrow.apache.org/docs/python/generated/pyarrow.dataset.Dataset.html">Arrow DataSet</a>
interface to import to DataFusion, but this does not support features such as filter push down
which can lead to a significant performance difference.</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">deltalake</span><span class="w"> </span><span class="kn">import</span> <span class="n">DeltaTable</span>
<span class="n">delta_table</span> <span class="o">=</span> <span class="n">DeltaTable</span><span class="p">(</span><span class="s2">&quot;path_to_table&quot;</span><span class="p">)</span>
<span class="n">ctx</span><span class="o">.</span><span class="n">register_dataset</span><span class="p">(</span><span class="s2">&quot;my_delta_table&quot;</span><span class="p">,</span> <span class="n">delta_table</span><span class="o">.</span><span class="n">to_pyarrow_dataset</span><span class="p">())</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="s2">&quot;my_delta_table&quot;</span><span class="p">)</span>
<span class="n">df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
</section>
<section id="iceberg">
<h2>Iceberg<a class="headerlink" href="#iceberg" title="Link to this heading"></a></h2>
<p>Coming soon!</p>
</section>
<section id="custom-table-provider">
<h2>Custom Table Provider<a class="headerlink" href="#custom-table-provider" title="Link to this heading"></a></h2>
<p>You can implement a custom Data Provider in Rust and expose it to DataFusion through the
the interface as describe in the <a class="reference internal" href="io/table_provider.html#io-custom-table-provider"><span class="std std-ref">Custom Table Provider</span></a>
section. This is an advanced topic, but a
<a class="reference external" href="https://github.com/apache/datafusion-python/tree/main/examples/ffi-table-provider">user example</a>
is provided in the DataFusion repository.</p>
</section>
</section>
</div>
<!-- Previous / next buttons -->
<div class='prev-next-area'>
<a class='left-prev' id="prev-link" href="basics.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">Concepts</p>
</div>
</a>
<a class='right-next' id="next-link" href="dataframe.html" title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">DataFrames</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>