| |
| <!DOCTYPE html> |
| |
| |
| <html lang="en" data-content_root="../" data-theme="auto"> |
| |
| <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 — Apache DataFusion in Python documentation</title> |
| |
| |
| |
| <script data-cfasync="false"> |
| document.documentElement.dataset.mode = localStorage.getItem("mode") || "auto"; |
| document.documentElement.dataset.theme = localStorage.getItem("theme") || "auto"; |
| </script> |
| <!-- |
| this give us a css class that will be invisible only if js is disabled |
| --> |
| <noscript> |
| <style> |
| .pst-js-only { display: none !important; } |
| |
| </style> |
| </noscript> |
| |
| <!-- Loaded before other Sphinx assets --> |
| <link href="../_static/styles/theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" /> |
| <link href="../_static/styles/pydata-sphinx-theme.css?digest=8878045cc6db502f8baf" rel="stylesheet" /> |
| |
| <link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=8f2a1f02" /> |
| <link rel="stylesheet" type="text/css" href="../_static/mystnb.11b39860a7a0cbfd473a3ad8a317855267ff0bd372690045ca344a6b62be495e.css" /> |
| <link rel="stylesheet" type="text/css" href="../_static/graphviz.css?v=4ae1632d" /> |
| <link rel="stylesheet" type="text/css" href="../_static/theme_overrides.css?v=4af573bc" /> |
| |
| <!-- So that users can add custom icons --> |
| <script src="../_static/scripts/fontawesome.js?digest=8878045cc6db502f8baf"></script> |
| <!-- Pre-loaded scripts that we'll load fully later --> |
| <link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf" /> |
| <link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf" /> |
| |
| <script src="../_static/documentation_options.js?v=5929fcd5"></script> |
| <script src="../_static/doctools.js?v=9bcbadda"></script> |
| <script src="../_static/sphinx_highlight.js?v=dc90522c"></script> |
| <script>DOCUMENTATION_OPTIONS.pagename = 'user-guide/data-sources';</script> |
| <script src="../_static/toc-toggle.js?v=36375f01"></script> |
| <link rel="icon" href="../_static/favicon.svg"/> |
| <link rel="index" title="Index" href="../genindex.html" /> |
| <link rel="search" title="Search" href="../search.html" /> |
| <link rel="next" title="DataFrames" href="dataframe/index.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"/> |
| <meta name="docsearch:version" content="" /> |
| </head> |
| |
| |
| <body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="auto"> |
| |
| |
| |
| <div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div> |
| |
| <div id="pst-scroll-pixel-helper"></div> |
| |
| <button type="button" class="btn rounded-pill" id="pst-back-to-top"> |
| <i class="fa-solid fa-arrow-up"></i>Back to top</button> |
| |
| |
| <dialog id="pst-search-dialog"> |
| |
| <form class="bd-search d-flex align-items-center" |
| action="../search.html" |
| method="get"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| <input type="search" |
| class="form-control" |
| name="q" |
| placeholder="Search the docs ..." |
| aria-label="Search the docs ..." |
| autocomplete="off" |
| autocorrect="off" |
| autocapitalize="off" |
| spellcheck="false"/> |
| <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span> |
| </form> |
| </dialog> |
| |
| <div class="pst-async-banner-revealer d-none"> |
| <aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside> |
| </div> |
| |
| |
| <header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none"> |
| <div class="bd-header__inner bd-page-width"> |
| <button class="pst-navbar-icon sidebar-toggle primary-toggle" aria-label="Site navigation"> |
| <span class="fa-solid fa-bars"></span> |
| </button> |
| |
| |
| <div class="col-lg-3 navbar-header-items__start"> |
| |
| <div class="navbar-item"> |
| |
| |
| |
| |
| |
| <a class="navbar-brand logo" href="../index.html"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <img src="../_static/original.svg" class="logo__image only-light" alt="Apache DataFusion in Python"/> |
| <img src="../_static/original_dark.svg" class="logo__image only-dark pst-js-only" alt="Apache DataFusion in Python"/> |
| |
| |
| </a></div> |
| |
| </div> |
| |
| <div class="col-lg-9 navbar-header-items"> |
| |
| <div class="me-auto navbar-header-items__center"> |
| |
| <div class="navbar-item"> |
| <nav> |
| <ul class="bd-navbar-elements navbar-nav"> |
| |
| <li class="nav-item current active"> |
| <a class="nav-link nav-internal" href="index.html"> |
| User Guide |
| </a> |
| </li> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link nav-internal" href="../contributor-guide/index.html"> |
| Contributor Guide |
| </a> |
| </li> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link nav-internal" href="../autoapi/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link nav-internal" href="../links.html"> |
| Links |
| </a> |
| </li> |
| |
| </ul> |
| </nav></div> |
| |
| </div> |
| |
| |
| <div class="navbar-header-items__end"> |
| |
| <div class="navbar-item navbar-persistent--container"> |
| |
| |
| <button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| <span class="search-button__default-text">Search</span> |
| <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span> |
| </button> |
| </div> |
| |
| |
| <div class="navbar-item"><ul class="navbar-icon-links" |
| aria-label="Icon Links"> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://github.com/apache/datafusion-python" title="GitHub" class="nav-link pst-navbar-icon" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><i class="fa-brands fa-github fa-lg" aria-hidden="true"></i> |
| <span class="sr-only">GitHub</span></a> |
| </li> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://docs.rs/datafusion/latest/datafusion/" title="Rust API docs (docs.rs)" class="nav-link pst-navbar-icon" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><i class="fa-brands fa-rust fa-lg" aria-hidden="true"></i> |
| <span class="sr-only">Rust API docs (docs.rs)</span></a> |
| </li> |
| </ul></div> |
| |
| <div class="navbar-item"> |
| |
| <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i> |
| <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i> |
| <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i> |
| </button></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <div class="navbar-persistent--mobile"> |
| |
| <button class="btn search-button-field search-button__button pst-js-only" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| <span class="search-button__default-text">Search</span> |
| <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span> |
| </button> |
| </div> |
| |
| |
| |
| <button class="pst-navbar-icon sidebar-toggle secondary-toggle" aria-label="On this page"> |
| <span class="fa-solid fa-outdent"></span> |
| </button> |
| |
| </div> |
| |
| </header> |
| |
| |
| <div class="bd-container"> |
| <div class="bd-container__inner bd-page-width"> |
| |
| |
| |
| <dialog id="pst-primary-sidebar-modal"></dialog> |
| <div id="pst-primary-sidebar" class="bd-sidebar-primary bd-sidebar"> |
| |
| |
| |
| <div class="sidebar-header-items sidebar-primary__section"> |
| |
| |
| <div class="sidebar-header-items__center"> |
| |
| |
| |
| <div class="navbar-item"> |
| <nav> |
| <ul class="bd-navbar-elements navbar-nav"> |
| |
| <li class="nav-item current active"> |
| <a class="nav-link nav-internal" href="index.html"> |
| User Guide |
| </a> |
| </li> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link nav-internal" href="../contributor-guide/index.html"> |
| Contributor Guide |
| </a> |
| </li> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link nav-internal" href="../autoapi/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link nav-internal" href="../links.html"> |
| Links |
| </a> |
| </li> |
| |
| </ul> |
| </nav></div> |
| |
| |
| </div> |
| |
| |
| |
| <div class="sidebar-header-items__end"> |
| |
| <div class="navbar-item"><ul class="navbar-icon-links" |
| aria-label="Icon Links"> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://github.com/apache/datafusion-python" title="GitHub" class="nav-link pst-navbar-icon" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><i class="fa-brands fa-github fa-lg" aria-hidden="true"></i> |
| <span class="sr-only">GitHub</span></a> |
| </li> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://docs.rs/datafusion/latest/datafusion/" title="Rust API docs (docs.rs)" class="nav-link pst-navbar-icon" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><i class="fa-brands fa-rust fa-lg" aria-hidden="true"></i> |
| <span class="sr-only">Rust API docs (docs.rs)</span></a> |
| </li> |
| </ul></div> |
| |
| <div class="navbar-item"> |
| |
| <button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button pst-js-only" aria-label="Color mode" data-bs-title="Color mode" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light" title="Light"></i> |
| <i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark" title="Dark"></i> |
| <i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto" title="System Settings"></i> |
| </button></div> |
| |
| </div> |
| |
| </div> |
| |
| <div class="sidebar-primary-items__start sidebar-primary__section"> |
| <div class="sidebar-primary-item"> |
| <nav class="bd-docs-nav bd-links" aria-label="Section Navigation"> |
| <p class="bd-links__title" role="heading" aria-level="1">Section Navigation</p> |
| <div class="bd-toc-item navbar-nav"> |
| <ul class="current nav bd-sidenav"> |
| <li class="toctree-l1 current active has-children"><a class="reference internal" href="index.html">User Guide</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="introduction.html">Introduction</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="basics.html">Concepts</a></li> |
| <li class="toctree-l2 current active"><a class="current reference internal" href="#">Data Sources</a></li> |
| |
| <li class="toctree-l2 has-children"><a class="reference internal" href="dataframe/index.html">DataFrames</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul> |
| <li class="toctree-l3"><a class="reference internal" href="dataframe/rendering.html">DataFrame Rendering</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="dataframe/execution-metrics.html">Execution Metrics</a></li> |
| </ul> |
| </details></li> |
| <li class="toctree-l2 has-children"><a class="reference internal" href="common-operations/index.html">Common Operations</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul> |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/views.html">Registering Views</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/basic-info.html">Basic Operations</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/select-and-filter.html">Column Selections</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/expressions.html">Expressions</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/joins.html">Joins</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/functions.html">Functions</a></li> |
| |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/spark-functions.html">Spark-Compatible Functions</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/aggregations.html">Aggregation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/windows.html">Window Functions</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="common-operations/udf-and-udfa.html">User-Defined Functions</a></li> |
| </ul> |
| </details></li> |
| <li class="toctree-l2 has-children"><a class="reference internal" href="io/index.html">IO</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul> |
| <li class="toctree-l3"><a class="reference internal" href="io/arrow.html">Arrow</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="io/avro.html">Avro</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="io/csv.html">CSV</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="io/json.html">JSON</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="io/parquet.html">Parquet</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="io/table_provider.html">Custom Table Provider</a></li> |
| </ul> |
| </details></li> |
| <li class="toctree-l2"><a class="reference internal" href="configuration.html">Configuration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="distributing-work.html">Distributing work</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="sql.html">SQL</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="upgrade-guides.html">Upgrade Guides</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="ai-coding-assistants.html">Using AI Coding Assistants</a></li> |
| </ul> |
| </details></li> |
| <li class="toctree-l1 has-children"><a class="reference internal" href="../contributor-guide/index.html">Contributor Guide</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul> |
| <li class="toctree-l2"><a class="reference internal" href="../contributor-guide/introduction.html">Introduction</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../contributor-guide/ffi.html">Python Extensions</a></li> |
| </ul> |
| </details></li> |
| <li class="toctree-l1 has-children"><a class="reference internal" href="../autoapi/index.html">API Reference</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul> |
| <li class="toctree-l2 has-children"><a class="reference internal" href="../autoapi/datafusion/index.html">datafusion</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><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 has-children"><a class="reference internal" href="../autoapi/datafusion/functions/index.html">datafusion.functions</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../autoapi/datafusion/functions/spark/index.html">datafusion.functions.spark</a></li> |
| </ul> |
| </details></li> |
| <li class="toctree-l3 has-children"><a class="reference internal" href="../autoapi/datafusion/input/index.html">datafusion.input</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><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> |
| </details></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/ipc/index.html">datafusion.ipc</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/options/index.html">datafusion.options</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> |
| </details></li> |
| </ul> |
| </details></li> |
| <li class="toctree-l1 has-children"><a class="reference internal" href="../links.html">Links</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul> |
| <li class="toctree-l2"><a class="reference external" href="https://github.com/apache/datafusion-python">GitHub and Issue Tracker</a></li> |
| <li class="toctree-l2"><a class="reference external" href="https://docs.rs/datafusion/latest/datafusion/">Rust API Docs</a></li> |
| <li class="toctree-l2"><a class="reference external" href="https://github.com/apache/datafusion/blob/main/CODE_OF_CONDUCT.md">Code of Conduct</a></li> |
| <li class="toctree-l2"><a class="reference external" href="https://github.com/apache/datafusion-python/tree/main/examples">Examples</a></li> |
| </ul> |
| </details></li> |
| </ul> |
| </div> |
| </nav></div> |
| </div> |
| |
| |
| <div class="sidebar-primary-items__end sidebar-primary__section"> |
| <div class="sidebar-primary-item"> |
| <div id="ethical-ad-placement" |
| class="flat" |
| data-ea-publisher="readthedocs" |
| data-ea-type="readthedocs-sidebar" |
| data-ea-manual="true"> |
| </div></div> |
| </div> |
| |
| |
| </div> |
| |
| <main id="main-content" class="bd-main" role="main"> |
| |
| |
| <div class="bd-content"> |
| <div class="bd-article-container"> |
| |
| <div class="bd-header-article d-print-none"> |
| <div class="header-article-items header-article__inner"> |
| |
| <div class="header-article-items__start"> |
| |
| <div class="header-article-item"> |
| |
| <nav aria-label="Breadcrumb" class="d-print-none"> |
| <ul class="bd-breadcrumbs"> |
| |
| <li class="breadcrumb-item breadcrumb-home"> |
| <a href="../index.html" class="nav-link" aria-label="Home"> |
| <i class="fa-solid fa-home"></i> |
| </a> |
| </li> |
| |
| <li class="breadcrumb-item"><a href="index.html" class="nav-link">User Guide</a></li> |
| |
| <li class="breadcrumb-item active" aria-current="page"><span class="ellipsis">Data Sources</span></li> |
| </ul> |
| </nav> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| </div> |
| |
| |
| |
| |
| <div id="searchbox"></div> |
| <article class="bd-article"> |
| |
| <!--- |
| Licensed to the Apache Software Foundation (ASF) under one |
| or more contributor license agreements. See the NOTICE file |
| distributed with this work for additional information |
| regarding copyright ownership. The ASF licenses this file |
| to you under the Apache License, Version 2.0 (the |
| "License"); you may not use this file except in compliance |
| with the License. You may obtain a copy of the License at |
| |
| http://www.apache.org/licenses/LICENSE-2.0 |
| |
| Unless required by applicable law or agreed to in writing, |
| software distributed under the License is distributed on an |
| "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| KIND, either express or implied. See the License for the |
| specific language governing permissions and limitations |
| under the License. |
| --> |
| <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 ability 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="cell docutils container"> |
| <div class="cell_input docutils container"> |
| <div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></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">ctx</span> <span class="o">=</span> <span class="n">SessionContext</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">"pokemon.csv"</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> |
| </div> |
| <div class="cell_output docutils container"> |
| <div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>DataFrame() |
| +----+---------------------------+--------+--------+-------+----+--------+---------+---------+---------+-------+------------+-----------+ |
| | # | Name | Type 1 | Type 2 | Total | HP | Attack | Defense | Sp. Atk | Sp. Def | Speed | Generation | Legendary | |
| +----+---------------------------+--------+--------+-------+----+--------+---------+---------+---------+-------+------------+-----------+ |
| | 1 | Bulbasaur | Grass | Poison | 318 | 45 | 49 | 49 | 65 | 65 | 45 | 1 | false | |
| | 2 | Ivysaur | Grass | Poison | 405 | 60 | 62 | 63 | 80 | 80 | 60 | 1 | false | |
| | 3 | Venusaur | Grass | Poison | 525 | 80 | 82 | 83 | 100 | 100 | 80 | 1 | false | |
| | 3 | VenusaurMega Venusaur | Grass | Poison | 625 | 80 | 100 | 123 | 122 | 120 | 80 | 1 | false | |
| | 4 | Charmander | Fire | | 309 | 39 | 52 | 43 | 60 | 50 | 65 | 1 | false | |
| | 5 | Charmeleon | Fire | | 405 | 58 | 64 | 58 | 80 | 65 | 80 | 1 | false | |
| | 6 | Charizard | Fire | Flying | 534 | 78 | 84 | 78 | 109 | 85 | 100 | 1 | false | |
| | 6 | CharizardMega Charizard X | Fire | Dragon | 634 | 78 | 130 | 111 | 130 | 85 | 100 | 1 | false | |
| | 6 | CharizardMega Charizard Y | Fire | Flying | 634 | 78 | 104 | 78 | 159 | 115 | 100 | 1 | false | |
| | 7 | Squirtle | Water | | 314 | 44 | 48 | 65 | 50 | 64 | 43 | 1 | false | |
| | 8 | Wartortle | Water | | 405 | 59 | 63 | 80 | 65 | 80 | 58 | 1 | false | |
| | 9 | Blastoise | Water | | 530 | 79 | 83 | 100 | 85 | 105 | 78 | 1 | false | |
| | 9 | BlastoiseMega Blastoise | Water | | 630 | 79 | 103 | 120 | 135 | 115 | 78 | 1 | false | |
| | 10 | Caterpie | Bug | | 195 | 45 | 30 | 35 | 20 | 20 | 45 | 1 | false | |
| | 11 | Metapod | Bug | | 205 | 50 | 20 | 55 | 25 | 25 | 30 | 1 | false | |
| | 12 | Butterfree | Bug | Flying | 395 | 60 | 45 | 50 | 90 | 80 | 70 | 1 | false | |
| | 13 | Weedle | Bug | Poison | 195 | 40 | 35 | 30 | 20 | 20 | 50 | 1 | false | |
| | 14 | Kakuna | Bug | Poison | 205 | 45 | 25 | 50 | 25 | 25 | 35 | 1 | false | |
| | 15 | Beedrill | Bug | Poison | 395 | 65 | 90 | 40 | 45 | 80 | 75 | 1 | false | |
| | 15 | BeedrillMega Beedrill | Bug | Poison | 495 | 65 | 150 | 40 | 15 | 80 | 145 | 1 | false | |
| +----+---------------------------+--------+--------+-------+----+--------+---------+---------+---------+-------+------------+-----------+ |
| </pre></div> |
| </div> |
| </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="cell docutils container"> |
| <div class="cell_input docutils container"> |
| <div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></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">ctx</span><span class="o">.</span><span class="n">from_pylist</span><span class="p">([</span> |
| <span class="p">{</span> <span class="s2">"a"</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"b"</span><span class="p">:</span> <span class="mf">10.0</span><span class="p">,</span> <span class="s2">"c"</span><span class="p">:</span> <span class="s2">"alpha"</span> <span class="p">},</span> |
| <span class="p">{</span> <span class="s2">"a"</span><span class="p">:</span> <span class="mi">2</span><span class="p">,</span> <span class="s2">"b"</span><span class="p">:</span> <span class="mf">20.0</span><span class="p">,</span> <span class="s2">"c"</span><span class="p">:</span> <span class="s2">"beta"</span> <span class="p">},</span> |
| <span class="p">{</span> <span class="s2">"a"</span><span class="p">:</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">"b"</span><span class="p">:</span> <span class="mf">30.0</span><span class="p">,</span> <span class="s2">"c"</span><span class="p">:</span> <span class="s2">"gamma"</span> <span class="p">},</span> |
| <span class="p">])</span><span class="o">.</span><span class="n">show</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="s2">"a"</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">"b"</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">"c"</span><span class="p">:</span> <span class="p">[</span><span class="s2">"alpha"</span><span class="p">,</span> <span class="s2">"beta"</span><span class="p">,</span> <span class="s2">"gamma"</span><span class="p">],</span> |
| <span class="p">})</span><span class="o">.</span><span class="n">show</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="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="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="n">pa</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="s2">"alpha"</span><span class="p">,</span> <span class="s2">"beta"</span><span class="p">,</span> <span class="s2">"gamma"</span><span class="p">]),</span> |
| <span class="p">],</span> |
| <span class="n">names</span><span class="o">=</span><span class="p">[</span><span class="s2">"a"</span><span class="p">,</span> <span class="s2">"b"</span><span class="p">,</span> <span class="s2">"c"</span><span class="p">],</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> |
| </pre></div> |
| </div> |
| </div> |
| <div class="cell_output docutils container"> |
| <div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>DataFrame() |
| +---+------+-------+ |
| | a | b | c | |
| +---+------+-------+ |
| | 1 | 10.0 | alpha | |
| | 2 | 20.0 | beta | |
| | 3 | 30.0 | gamma | |
| +---+------+-------+ |
| DataFrame() |
| +---+------+-------+ |
| | a | b | c | |
| +---+------+-------+ |
| | 1 | 10.0 | alpha | |
| | 2 | 20.0 | beta | |
| | 3 | 30.0 | gamma | |
| +---+------+-------+ |
| DataFrame() |
| +---+------+-------+ |
| | a | b | c | |
| +---+------+-------+ |
| | 1 | 10.0 | alpha | |
| | 2 | 20.0 | beta | |
| | 3 | 30.0 | gamma | |
| +---+------+-------+ |
| </pre></div> |
| </div> |
| </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">"us-east-1"</span> |
| <span class="n">bucket_name</span> <span class="o">=</span> <span class="s2">"yellow-trips"</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">"AWS_ACCESS_KEY_ID"</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">"AWS_SECRET_ACCESS_KEY"</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">"s3://</span><span class="si">{</span><span class="n">bucket_name</span><span class="si">}</span><span class="s2">/"</span> |
| <span class="n">ctx</span><span class="o">.</span><span class="n">register_object_store</span><span class="p">(</span><span class="s2">"s3://"</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">"trips"</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">"trips"</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 versions 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">"a"</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">"b"</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">"c"</span><span class="p">:</span> <span class="p">[</span><span class="s2">"alpha"</span><span class="p">,</span> <span class="s2">"beta"</span><span class="p">,</span> <span class="s2">"gamma"</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">"path_to_table"</span><span class="p">)</span> |
| <span class="n">ctx</span><span class="o">.</span><span class="n">register_table</span><span class="p">(</span><span class="s2">"my_delta_table"</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">"my_delta_table"</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">"path_to_table"</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">"my_delta_table"</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">"my_delta_table"</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="apache-iceberg"> |
| <h2>Apache Iceberg<a class="headerlink" href="#apache-iceberg" title="Link to this heading">#</a></h2> |
| <p>DataFusion 45.0.0 and later support the ability to register Apache Iceberg tables as table providers through the Custom Table Provider interface.</p> |
| <p>This requires either the <a class="reference external" href="https://pypi.org/project/pyiceberg/">pyiceberg</a> library (>=0.10.0) or the <a class="reference external" href="https://pypi.org/project/pyiceberg-core/">pyiceberg-core</a> library (>=0.5.0).</p> |
| <ul class="simple"> |
| <li><p>The <code class="docutils literal notranslate"><span class="pre">pyiceberg-core</span></code> library exposes Iceberg Rust’s implementation of the Custom Table Provider interface as python bindings.</p></li> |
| <li><p>The <code class="docutils literal notranslate"><span class="pre">pyiceberg</span></code> library utilizes the <code class="docutils literal notranslate"><span class="pre">pyiceberg-core</span></code> python bindings under the hood and provides a native way for Python users to interact with the DataFusion.</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</span><span class="w"> </span><span class="kn">import</span> <span class="n">SessionContext</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyiceberg.catalog</span><span class="w"> </span><span class="kn">import</span> <span class="n">load_catalog</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="c1"># Load catalog and create/load a table</span> |
| <span class="n">catalog</span> <span class="o">=</span> <span class="n">load_catalog</span><span class="p">(</span><span class="s2">"catalog"</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="s2">"in-memory"</span><span class="p">)</span> |
| <span class="n">catalog</span><span class="o">.</span><span class="n">create_namespace_if_not_exists</span><span class="p">(</span><span class="s2">"default"</span><span class="p">)</span> |
| |
| <span class="c1"># Create some sample data</span> |
| <span class="n">data</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">table</span><span class="p">({</span><span class="s2">"x"</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">"y"</span><span class="p">:</span> <span class="p">[</span><span class="mi">4</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">6</span><span class="p">]})</span> |
| <span class="n">iceberg_table</span> <span class="o">=</span> <span class="n">catalog</span><span class="o">.</span><span class="n">create_table</span><span class="p">(</span><span class="s2">"default.test"</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">data</span><span class="o">.</span><span class="n">schema</span><span class="p">)</span> |
| <span class="n">iceberg_table</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> |
| |
| <span class="c1"># Register the table with DataFusion</span> |
| <span class="n">ctx</span> <span class="o">=</span> <span class="n">SessionContext</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">"test"</span><span class="p">,</span> <span class="n">iceberg_table</span><span class="p">)</span> |
| |
| <span class="c1"># Query the table using DataFusion</span> |
| <span class="n">ctx</span><span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="s2">"test"</span><span class="p">)</span><span class="o">.</span><span class="n">show</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| <p>Note that the Datafusion integration rely on features from the <a class="reference external" href="https://github.com/apache/iceberg-rust/">Iceberg Rust</a> implementation instead of the <a class="reference external" href="https://github.com/apache/iceberg-python/">PyIceberg</a> implementation. |
| Features that are available in PyIceberg but not yet in Iceberg Rust will not be available when using DataFusion.</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/datafusion-ffi-example">user example</a> |
| is provided in the DataFusion repository.</p> |
| </section> |
| </section> |
| <section id="catalog"> |
| <h1>Catalog<a class="headerlink" href="#catalog" title="Link to this heading">#</a></h1> |
| <p>A common technique for organizing tables is using a three level hierarchical approach. DataFusion |
| supports this form of organizing using the <a class="reference internal" href="../autoapi/datafusion/catalog/index.html#datafusion.catalog.Catalog" title="datafusion.catalog.Catalog"><code class="xref py py-class docutils literal notranslate"><span class="pre">Catalog</span></code></a>, |
| <a class="reference internal" href="../autoapi/datafusion/catalog/index.html#datafusion.catalog.Schema" title="datafusion.catalog.Schema"><code class="xref py py-class docutils literal notranslate"><span class="pre">Schema</span></code></a>, and <a class="reference internal" href="../autoapi/datafusion/catalog/index.html#datafusion.catalog.Table" title="datafusion.catalog.Table"><code class="xref py py-class docutils literal notranslate"><span class="pre">Table</span></code></a>. By default, |
| a <a class="reference internal" href="../autoapi/datafusion/context/index.html#datafusion.context.SessionContext" title="datafusion.context.SessionContext"><code class="xref py py-class docutils literal notranslate"><span class="pre">SessionContext</span></code></a> comes with a single Catalog and a single Schema |
| with the names <code class="docutils literal notranslate"><span class="pre">datafusion</span></code> and <code class="docutils literal notranslate"><span class="pre">public</span></code>, respectively.</p> |
| <p>The default implementation uses an in-memory approach to the catalog and schema. We have support |
| for adding additional in-memory catalogs and schemas. You can access tables registered in a schema |
| either through the Dataframe API or via sql commands. This can be done like in the following |
| example:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></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="kn">from</span><span class="w"> </span><span class="nn">datafusion.catalog</span><span class="w"> </span><span class="kn">import</span> <span class="n">Catalog</span><span class="p">,</span> <span class="n">Schema</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">ctx</span> <span class="o">=</span> <span class="n">SessionContext</span><span class="p">()</span> |
| |
| <span class="n">my_catalog</span> <span class="o">=</span> <span class="n">Catalog</span><span class="o">.</span><span class="n">memory_catalog</span><span class="p">()</span> |
| <span class="n">my_schema</span> <span class="o">=</span> <span class="n">Schema</span><span class="o">.</span><span class="n">memory_schema</span><span class="p">()</span> |
| <span class="n">my_catalog</span><span class="o">.</span><span class="n">register_schema</span><span class="p">(</span><span class="s1">'my_schema_name'</span><span class="p">,</span> <span class="n">my_schema</span><span class="p">)</span> |
| <span class="n">ctx</span><span class="o">.</span><span class="n">register_catalog_provider</span><span class="p">(</span><span class="s1">'my_catalog_name'</span><span class="p">,</span> <span class="n">my_catalog</span><span class="p">)</span> |
| |
| <span class="c1"># Create an in-memory table</span> |
| <span class="n">table</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">table</span><span class="p">({</span> |
| <span class="s1">'name'</span><span class="p">:</span> <span class="p">[</span><span class="s1">'Bulbasaur'</span><span class="p">,</span> <span class="s1">'Charmander'</span><span class="p">,</span> <span class="s1">'Squirtle'</span><span class="p">],</span> |
| <span class="s1">'type'</span><span class="p">:</span> <span class="p">[</span><span class="s1">'Grass'</span><span class="p">,</span> <span class="s1">'Fire'</span><span class="p">,</span> <span class="s1">'Water'</span><span class="p">],</span> |
| <span class="s1">'hp'</span><span class="p">:</span> <span class="p">[</span><span class="mi">45</span><span class="p">,</span> <span class="mi">39</span><span class="p">,</span> <span class="mi">44</span><span class="p">],</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">create_dataframe</span><span class="p">([</span><span class="n">table</span><span class="o">.</span><span class="n">to_batches</span><span class="p">()],</span> <span class="n">name</span><span class="o">=</span><span class="s1">'pokemon'</span><span class="p">)</span> |
| |
| <span class="n">my_schema</span><span class="o">.</span><span class="n">register_table</span><span class="p">(</span><span class="s1">'pokemon'</span><span class="p">,</span> <span class="n">df</span><span class="p">)</span> |
| |
| <span class="n">ctx</span><span class="o">.</span><span class="n">sql</span><span class="p">(</span><span class="s1">'SELECT * FROM my_catalog_name.my_schema_name.pokemon'</span><span class="p">)</span><span class="o">.</span><span class="n">show</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| <section id="user-defined-catalog-and-schema"> |
| <h2>User Defined Catalog and Schema<a class="headerlink" href="#user-defined-catalog-and-schema" title="Link to this heading">#</a></h2> |
| <p>If the in-memory catalogs are insufficient for your uses, there are two approaches you can take |
| to implementing a custom catalog and/or schema. In the below discussion, we describe how to |
| implement these for a Catalog, but the approach to implementing for a Schema is nearly |
| identical.</p> |
| <p>DataFusion supports Catalogs written in either Rust or Python. If you write a Catalog in Rust, |
| you will need to export it as a Python library via PyO3. There is a complete example of a |
| catalog implemented this way in the |
| <a class="reference external" href="https://github.com/apache/datafusion-python/tree/main/examples/">examples folder</a> |
| of our repository. Writing catalog providers in Rust provides typically can lead to significant |
| performance improvements over the Python based approach.</p> |
| <p>To implement a Catalog in Python, you will need to inherit from the abstract base class |
| <a class="reference internal" href="../autoapi/datafusion/catalog/index.html#datafusion.catalog.CatalogProvider" title="datafusion.catalog.CatalogProvider"><code class="xref py py-class docutils literal notranslate"><span class="pre">CatalogProvider</span></code></a>. There are examples in the |
| <a class="reference external" href="https://github.com/apache/datafusion-python/tree/main/python/tests">unit tests</a> of |
| implementing a basic Catalog in Python where we simply keep a dictionary of the |
| registered Schemas.</p> |
| <p>One important note for developers is that when we have a Catalog defined in Python, we have |
| two different ways of accessing this Catalog. First, we register the catalog with a Rust |
| wrapper. This allows for any rust based code to call the Python functions as necessary. |
| Second, if the user access the Catalog via the Python API, we identify this and return back |
| the original Python object that implements the Catalog. This is an important distinction |
| for developers because we do <em>not</em> return a Python wrapper around the Rust wrapper of the |
| original Python object.</p> |
| </section> |
| </section> |
| |
| |
| </article> |
| |
| |
| |
| |
| |
| <footer class="prev-next-footer d-print-none"> |
| |
| <div class="prev-next-area"> |
| <a class="left-prev" |
| href="basics.html" |
| title="previous page"> |
| <i class="fa-solid 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" |
| href="dataframe/index.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="fa-solid fa-angle-right"></i> |
| </a> |
| </div> |
| </footer> |
| |
| </div> |
| |
| |
| |
| <dialog id="pst-secondary-sidebar-modal"></dialog> |
| <div id="pst-secondary-sidebar" class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner"> |
| |
| |
| <div class="sidebar-secondary-item"> |
| <div |
| id="pst-page-navigation-heading-2" |
| class="page-toc tocsection onthispage"> |
| <i class="fa-solid fa-list"></i> On this page |
| </div> |
| <nav class="bd-toc-nav page-toc" aria-labelledby="pst-page-navigation-heading-2"> |
| <ul class="visible nav section-nav flex-column"> |
| <li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#">Data Sources</a><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="#apache-iceberg">Apache 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> |
| </li> |
| <li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#catalog">Catalog</a><ul class="visible nav section-nav flex-column"> |
| <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#user-defined-catalog-and-schema">User Defined Catalog and Schema</a></li> |
| </ul> |
| </li> |
| </ul> |
| |
| </nav></div> |
| |
| </div></div> |
| |
| |
| </div> |
| <footer class="bd-footer-content"> |
| |
| </footer> |
| |
| </main> |
| </div> |
| </div> |
| |
| <!-- Scripts loaded after <body> so the DOM is not blocked --> |
| <script defer src="../_static/scripts/bootstrap.js?digest=8878045cc6db502f8baf"></script> |
| <script defer src="../_static/scripts/pydata-sphinx-theme.js?digest=8878045cc6db502f8baf"></script> |
| |
| <!-- Based on pydata_sphinx_theme/footer.html --> |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| |
| <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> |
