| <!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>DataFrames — 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="DataFrame Rendering" href="rendering.html" /> |
| <link rel="prev" title="Data Sources" href="../data-sources.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="en"> |
| |
| |
| <!-- Google Analytics --> |
| |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <div class="container-fluid" id="banner"></div> |
| |
| |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| |
| <!-- Only show if we have sidebars configured, else just a small margin --> |
| <div class="col-12 col-md-3 bd-sidebar"> |
| <div class="sidebar-start-items"> |
| <a class="navbar-brand" href="../../index.html"> |
| <img src="../../_static/images/2x_bgwhite_original.png" class="logo" alt="logo"> |
| </a> |
| |
| <form class="bd-search d-flex align-items-center" action="../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form> |
| |
| <nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| <div class="bd-toc-item active"> |
| |
| <p aria-level="2" class="caption" role="heading"> |
| <span class="caption-text"> |
| LINKS |
| </span> |
| </p> |
| <ul class="nav bd-sidenav"> |
| <li class="toctree-l1"> |
| <a class="reference external" href="https://github.com/apache/datafusion-python"> |
| Github and Issue Tracker |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference external" href="https://docs.rs/datafusion/latest/datafusion/"> |
| Rust's API Docs |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference external" href="https://github.com/apache/datafusion/blob/main/CODE_OF_CONDUCT.md"> |
| Code of conduct |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference external" href="https://github.com/apache/datafusion-python/tree/main/examples"> |
| Examples |
| </a> |
| </li> |
| </ul> |
| <p aria-level="2" class="caption" role="heading"> |
| <span class="caption-text"> |
| USER GUIDE |
| </span> |
| </p> |
| <ul class="current nav bd-sidenav"> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../introduction.html"> |
| Introduction |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../basics.html"> |
| Concepts |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../data-sources.html"> |
| Data Sources |
| </a> |
| </li> |
| <li class="toctree-l1 current active has-children"> |
| <a class="current reference internal" href="#"> |
| DataFrames |
| </a> |
| <input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/> |
| <label for="toctree-checkbox-1"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="rendering.html"> |
| DataFrame Rendering |
| </a> |
| </li> |
| </ul> |
| </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-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="../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-3" name="toctree-checkbox-3" type="checkbox"/> |
| <label for="toctree-checkbox-3"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/arrow.html"> |
| Arrow |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/avro.html"> |
| Avro |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/csv.html"> |
| CSV |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/json.html"> |
| JSON |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/parquet.html"> |
| Parquet |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/table_provider.html"> |
| Custom Table Provider |
| </a> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../configuration.html"> |
| Configuration |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../sql.html"> |
| SQL |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../upgrade-guides.html"> |
| Upgrade Guides |
| </a> |
| </li> |
| </ul> |
| <p aria-level="2" class="caption" role="heading"> |
| <span class="caption-text"> |
| CONTRIBUTOR GUIDE |
| </span> |
| </p> |
| <ul class="nav bd-sidenav"> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../../contributor-guide/introduction.html"> |
| Introduction |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../../contributor-guide/ffi.html"> |
| Python Extensions |
| </a> |
| </li> |
| </ul> |
| <p aria-level="2" class="caption" role="heading"> |
| <span class="caption-text"> |
| API |
| </span> |
| </p> |
| <ul class="nav bd-sidenav"> |
| <li class="toctree-l1 has-children"> |
| <a class="reference internal" href="../../autoapi/index.html"> |
| API Reference |
| </a> |
| <input class="toctree-checkbox" id="toctree-checkbox-4" name="toctree-checkbox-4" type="checkbox"/> |
| <label for="toctree-checkbox-4"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l2 has-children"> |
| <a class="reference internal" href="../../autoapi/datafusion/index.html"> |
| datafusion |
| </a> |
| <input class="toctree-checkbox" id="toctree-checkbox-5" name="toctree-checkbox-5" type="checkbox"/> |
| <label for="toctree-checkbox-5"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/catalog/index.html"> |
| datafusion.catalog |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/context/index.html"> |
| datafusion.context |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/dataframe/index.html"> |
| datafusion.dataframe |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/dataframe_formatter/index.html"> |
| datafusion.dataframe_formatter |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/expr/index.html"> |
| datafusion.expr |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/functions/index.html"> |
| datafusion.functions |
| </a> |
| </li> |
| <li class="toctree-l3 has-children"> |
| <a class="reference internal" href="../../autoapi/datafusion/input/index.html"> |
| datafusion.input |
| </a> |
| <input class="toctree-checkbox" id="toctree-checkbox-6" name="toctree-checkbox-6" type="checkbox"/> |
| <label for="toctree-checkbox-6"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l4"> |
| <a class="reference internal" href="../../autoapi/datafusion/input/base/index.html"> |
| datafusion.input.base |
| </a> |
| </li> |
| <li class="toctree-l4"> |
| <a class="reference internal" href="../../autoapi/datafusion/input/location/index.html"> |
| datafusion.input.location |
| </a> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/io/index.html"> |
| datafusion.io |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/object_store/index.html"> |
| datafusion.object_store |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/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> |
| </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="#overview"> |
| Overview |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#creating-dataframes"> |
| Creating DataFrames |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#common-dataframe-operations"> |
| Common DataFrame Operations |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#column-names-as-function-arguments"> |
| Column Names as Function Arguments |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#terminal-operations"> |
| Terminal Operations |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#zero-copy-streaming-to-arrow-based-python-libraries"> |
| Zero-copy streaming to Arrow-based Python libraries |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#pyarrow"> |
| PyArrow |
| </a> |
| <ul class="visible nav section-nav flex-column"> |
| <li class="toc-h3 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#execute-as-stream"> |
| Execute as Stream |
| </a> |
| </li> |
| </ul> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#html-rendering"> |
| HTML Rendering |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#core-classes"> |
| Core Classes |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#expression-classes"> |
| Expression Classes |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#built-in-functions"> |
| Built-in Functions |
| </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="dataframes"> |
| <h1>DataFrames<a class="headerlink" href="#dataframes" title="Link to this heading">¶</a></h1> |
| <section id="overview"> |
| <h2>Overview<a class="headerlink" href="#overview" title="Link to this heading">¶</a></h2> |
| <p>The <code class="docutils literal notranslate"><span class="pre">DataFrame</span></code> class is the core abstraction in DataFusion that represents tabular data and operations |
| on that data. DataFrames provide a flexible API for transforming data through various operations such as |
| filtering, projection, aggregation, joining, and more.</p> |
| <p>A DataFrame represents a logical plan that is lazily evaluated. The actual execution occurs only when |
| terminal operations like <code class="docutils literal notranslate"><span class="pre">collect()</span></code>, <code class="docutils literal notranslate"><span class="pre">show()</span></code>, or <code class="docutils literal notranslate"><span class="pre">to_pandas()</span></code> are called.</p> |
| </section> |
| <section id="creating-dataframes"> |
| <h2>Creating DataFrames<a class="headerlink" href="#creating-dataframes" title="Link to this heading">¶</a></h2> |
| <p>DataFrames can be created in several ways:</p> |
| <ul> |
| <li><p>From SQL queries via a <code class="docutils literal notranslate"><span class="pre">SessionContext</span></code>:</p> |
| <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="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">sql</span><span class="p">(</span><span class="s2">"SELECT * FROM your_table"</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| </li> |
| <li><p>From registered tables:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></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">"your_table"</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| </li> |
| <li><p>From various data sources:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># From CSV files (see :ref:`io_csv` for detailed options)</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">"path/to/data.csv"</span><span class="p">)</span> |
| |
| <span class="c1"># From Parquet files (see :ref:`io_parquet` for detailed options)</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">read_parquet</span><span class="p">(</span><span class="s2">"path/to/data.parquet"</span><span class="p">)</span> |
| |
| <span class="c1"># From JSON files (see :ref:`io_json` for detailed options)</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">read_json</span><span class="p">(</span><span class="s2">"path/to/data.json"</span><span class="p">)</span> |
| |
| <span class="c1"># From Avro files (see :ref:`io_avro` for detailed options)</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">read_avro</span><span class="p">(</span><span class="s2">"path/to/data.avro"</span><span class="p">)</span> |
| |
| <span class="c1"># From Pandas DataFrame</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">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="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="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">df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">from_pandas</span><span class="p">(</span><span class="n">pandas_df</span><span class="p">)</span> |
| |
| <span class="c1"># From Arrow data</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">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="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">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="p">)</span> |
| <span class="n">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">batch</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| </li> |
| </ul> |
| <p>For detailed information about reading from different data sources, see the <a class="reference internal" href="../io/index.html"><span class="doc">I/O Guide</span></a>. |
| For custom data sources, see <a class="reference internal" href="../io/table_provider.html#io-custom-table-provider"><span class="std std-ref">Custom Table Provider</span></a>.</p> |
| </section> |
| <section id="common-dataframe-operations"> |
| <h2>Common DataFrame Operations<a class="headerlink" href="#common-dataframe-operations" title="Link to this heading">¶</a></h2> |
| <p>DataFusion’s DataFrame API offers a wide range of operations:</p> |
| <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">column</span><span class="p">,</span> <span class="n">literal</span> |
| |
| <span class="c1"># Select specific columns</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="s2">"col1"</span><span class="p">,</span> <span class="s2">"col2"</span><span class="p">)</span> |
| |
| <span class="c1"># Select with expressions</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">column</span><span class="p">(</span><span class="s2">"a"</span><span class="p">)</span> <span class="o">+</span> <span class="n">column</span><span class="p">(</span><span class="s2">"b"</span><span class="p">),</span> <span class="n">column</span><span class="p">(</span><span class="s2">"a"</span><span class="p">)</span> <span class="o">-</span> <span class="n">column</span><span class="p">(</span><span class="s2">"b"</span><span class="p">))</span> |
| |
| <span class="c1"># Filter rows (expressions or SQL strings)</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">column</span><span class="p">(</span><span class="s2">"age"</span><span class="p">)</span> <span class="o">></span> <span class="n">literal</span><span class="p">(</span><span class="mi">25</span><span class="p">))</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="s2">"age > 25"</span><span class="p">)</span> |
| |
| <span class="c1"># Add computed columns</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">with_column</span><span class="p">(</span><span class="s2">"full_name"</span><span class="p">,</span> <span class="n">column</span><span class="p">(</span><span class="s2">"first_name"</span><span class="p">)</span> <span class="o">+</span> <span class="n">literal</span><span class="p">(</span><span class="s2">" "</span><span class="p">)</span> <span class="o">+</span> <span class="n">column</span><span class="p">(</span><span class="s2">"last_name"</span><span class="p">))</span> |
| |
| <span class="c1"># Multiple column additions</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">with_columns</span><span class="p">(</span> |
| <span class="p">(</span><span class="n">column</span><span class="p">(</span><span class="s2">"a"</span><span class="p">)</span> <span class="o">+</span> <span class="n">column</span><span class="p">(</span><span class="s2">"b"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"sum"</span><span class="p">),</span> |
| <span class="p">(</span><span class="n">column</span><span class="p">(</span><span class="s2">"a"</span><span class="p">)</span> <span class="o">*</span> <span class="n">column</span><span class="p">(</span><span class="s2">"b"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"product"</span><span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="c1"># Sort data</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">column</span><span class="p">(</span><span class="s2">"age"</span><span class="p">)</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">ascending</span><span class="o">=</span><span class="kc">False</span><span class="p">))</span> |
| |
| <span class="c1"># Join DataFrames</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df1</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">df2</span><span class="p">,</span> <span class="n">on</span><span class="o">=</span><span class="s2">"user_id"</span><span class="p">,</span> <span class="n">how</span><span class="o">=</span><span class="s2">"inner"</span><span class="p">)</span> |
| |
| <span class="c1"># Aggregate data</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">functions</span> <span class="k">as</span> <span class="n">f</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">aggregate</span><span class="p">(</span> |
| <span class="p">[],</span> <span class="c1"># Group by columns (empty for global aggregation)</span> |
| <span class="p">[</span><span class="n">f</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">column</span><span class="p">(</span><span class="s2">"amount"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"total_amount"</span><span class="p">)]</span> |
| <span class="p">)</span> |
| |
| <span class="c1"># Limit rows</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">limit</span><span class="p">(</span><span class="mi">100</span><span class="p">)</span> |
| |
| <span class="c1"># Drop columns</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">drop</span><span class="p">(</span><span class="s2">"temporary_column"</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| </section> |
| <section id="column-names-as-function-arguments"> |
| <h2>Column Names as Function Arguments<a class="headerlink" href="#column-names-as-function-arguments" title="Link to this heading">¶</a></h2> |
| <p>Some <code class="docutils literal notranslate"><span class="pre">DataFrame</span></code> methods accept column names when an argument refers to an |
| existing column. These include:</p> |
| <ul class="simple"> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">select()</span></code></p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">sort()</span></code></p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">drop()</span></code></p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">join()</span></code> (<code class="docutils literal notranslate"><span class="pre">on</span></code> argument)</p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">aggregate()</span></code> (grouping columns)</p></li> |
| </ul> |
| <p>See the full function documentation for details on any specific function.</p> |
| <p>Note that <code class="xref py py-meth docutils literal notranslate"><span class="pre">join_on()</span></code> expects <code class="docutils literal notranslate"><span class="pre">col()</span></code>/<code class="docutils literal notranslate"><span class="pre">column()</span></code> expressions rather than plain strings.</p> |
| <p>For such methods, you can pass column names directly:</p> |
| <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">col</span><span class="p">,</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">f</span> |
| |
| <span class="n">df</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="s1">'id'</span><span class="p">)</span> |
| <span class="n">df</span><span class="o">.</span><span class="n">aggregate</span><span class="p">(</span><span class="s1">'id'</span><span class="p">,</span> <span class="p">[</span><span class="n">f</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'value'</span><span class="p">))])</span> |
| </pre></div> |
| </div> |
| <p>The same operation can also be written with explicit column expressions, using either <code class="docutils literal notranslate"><span class="pre">col()</span></code> or <code class="docutils literal notranslate"><span class="pre">column()</span></code>:</p> |
| <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">col</span><span class="p">,</span> <span class="n">column</span><span class="p">,</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">f</span> |
| |
| <span class="n">df</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'id'</span><span class="p">))</span> |
| <span class="n">df</span><span class="o">.</span><span class="n">aggregate</span><span class="p">(</span><span class="n">column</span><span class="p">(</span><span class="s1">'id'</span><span class="p">),</span> <span class="p">[</span><span class="n">f</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'value'</span><span class="p">))])</span> |
| </pre></div> |
| </div> |
| <p>Note that <code class="docutils literal notranslate"><span class="pre">column()</span></code> is an alias of <code class="docutils literal notranslate"><span class="pre">col()</span></code>, so you can use either name; the example above shows both in action.</p> |
| <p>Whenever an argument represents an expression—such as in |
| <code class="xref py py-meth docutils literal notranslate"><span class="pre">filter()</span></code> or |
| <code class="xref py py-meth docutils literal notranslate"><span class="pre">with_column()</span></code>—use <code class="docutils literal notranslate"><span class="pre">col()</span></code> to reference |
| columns. The comparison and arithmetic operators on <code class="docutils literal notranslate"><span class="pre">Expr</span></code> will automatically |
| convert any non-<code class="docutils literal notranslate"><span class="pre">Expr</span></code> value into a literal expression, so writing</p> |
| <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">col</span> |
| <span class="n">df</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s2">"age"</span><span class="p">)</span> <span class="o">></span> <span class="mi">21</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>is equivalent to using <code class="docutils literal notranslate"><span class="pre">lit(21)</span></code> explicitly. Use <code class="docutils literal notranslate"><span class="pre">lit()</span></code> (also available |
| as <code class="docutils literal notranslate"><span class="pre">literal()</span></code>) when you need to construct a literal expression directly.</p> |
| </section> |
| <section id="terminal-operations"> |
| <h2>Terminal Operations<a class="headerlink" href="#terminal-operations" title="Link to this heading">¶</a></h2> |
| <p>To materialize the results of your DataFrame operations:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Collect all data as PyArrow RecordBatches</span> |
| <span class="n">result_batches</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span> |
| |
| <span class="c1"># Convert to various formats</span> |
| <span class="n">pandas_df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">to_pandas</span><span class="p">()</span> <span class="c1"># Pandas DataFrame</span> |
| <span class="n">polars_df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">to_polars</span><span class="p">()</span> <span class="c1"># Polars DataFrame</span> |
| <span class="n">arrow_table</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">to_arrow_table</span><span class="p">()</span> <span class="c1"># PyArrow Table</span> |
| <span class="n">py_dict</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">to_pydict</span><span class="p">()</span> <span class="c1"># Python dictionary</span> |
| <span class="n">py_list</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">to_pylist</span><span class="p">()</span> <span class="c1"># Python list of dictionaries</span> |
| |
| <span class="c1"># Display results</span> |
| <span class="n">df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span> <span class="c1"># Print tabular format to console</span> |
| |
| <span class="c1"># Count rows</span> |
| <span class="n">count</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> |
| |
| <span class="c1"># Collect a single column of data as a PyArrow Array</span> |
| <span class="n">arr</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">collect_column</span><span class="p">(</span><span class="s2">"age"</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| </section> |
| <section id="zero-copy-streaming-to-arrow-based-python-libraries"> |
| <h2>Zero-copy streaming to Arrow-based Python libraries<a class="headerlink" href="#zero-copy-streaming-to-arrow-based-python-libraries" title="Link to this heading">¶</a></h2> |
| <p>DataFusion DataFrames implement the <code class="docutils literal notranslate"><span class="pre">__arrow_c_stream__</span></code> protocol, enabling |
| zero-copy, lazy streaming into Arrow-based Python libraries. With the streaming |
| protocol, batches are produced on demand.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>The protocol is implementation-agnostic and works with any Python library |
| that understands the Arrow C streaming interface (for example, PyArrow |
| or other Arrow-compatible implementations). The sections below provide a |
| short PyArrow-specific example and general guidance for other |
| implementations.</p> |
| </div> |
| </section> |
| <section id="pyarrow"> |
| <h2>PyArrow<a class="headerlink" href="#pyarrow" title="Link to this heading">¶</a></h2> |
| <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="c1"># Create a PyArrow RecordBatchReader without materializing all batches</span> |
| <span class="n">reader</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">RecordBatchReader</span><span class="o">.</span><span class="n">from_stream</span><span class="p">(</span><span class="n">df</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">reader</span><span class="p">:</span> |
| <span class="o">...</span> <span class="c1"># process each batch as it is produced</span> |
| </pre></div> |
| </div> |
| <p>DataFrames are also iterable, yielding <a class="reference internal" href="../../autoapi/datafusion/index.html#datafusion.RecordBatch" title="datafusion.RecordBatch"><code class="xref py py-class docutils literal notranslate"><span class="pre">datafusion.RecordBatch</span></code></a> |
| objects lazily so you can loop over results directly without importing |
| PyArrow:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">df</span><span class="p">:</span> |
| <span class="o">...</span> <span class="c1"># each batch is a ``datafusion.RecordBatch``</span> |
| </pre></div> |
| </div> |
| <p>Each batch exposes <code class="docutils literal notranslate"><span class="pre">to_pyarrow()</span></code>, allowing conversion to a PyArrow |
| table. <code class="docutils literal notranslate"><span class="pre">pa.table(df)</span></code> collects the entire DataFrame eagerly into a |
| PyArrow table:</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="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="n">df</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>Asynchronous iteration is supported as well, allowing integration with |
| <code class="docutils literal notranslate"><span class="pre">asyncio</span></code> event loops:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">async</span> <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">df</span><span class="p">:</span> |
| <span class="o">...</span> <span class="c1"># process each batch as it is produced</span> |
| </pre></div> |
| </div> |
| <p>To work with the stream directly, use <code class="docutils literal notranslate"><span class="pre">execute_stream()</span></code>, which returns a |
| <a class="reference internal" href="../../autoapi/datafusion/index.html#datafusion.RecordBatchStream" title="datafusion.RecordBatchStream"><code class="xref py py-class docutils literal notranslate"><span class="pre">RecordBatchStream</span></code></a>.</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">stream</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">execute_stream</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">stream</span><span class="p">:</span> |
| <span class="o">...</span> |
| </pre></div> |
| </div> |
| <section id="execute-as-stream"> |
| <h3>Execute as Stream<a class="headerlink" href="#execute-as-stream" title="Link to this heading">¶</a></h3> |
| <p>For finer control over streaming execution, use |
| <code class="xref py py-meth docutils literal notranslate"><span class="pre">execute_stream()</span></code> to obtain a |
| <a class="reference internal" href="../../autoapi/datafusion/index.html#datafusion.RecordBatchStream" title="datafusion.RecordBatchStream"><code class="xref py py-class docutils literal notranslate"><span class="pre">datafusion.RecordBatchStream</span></code></a>:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">stream</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">execute_stream</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">stream</span><span class="p">:</span> |
| <span class="o">...</span> <span class="c1"># process each batch as it is produced</span> |
| </pre></div> |
| </div> |
| <div class="admonition tip"> |
| <p class="admonition-title">Tip</p> |
| <p>To get a PyArrow reader instead, call</p> |
| <p><code class="docutils literal notranslate"><span class="pre">pa.RecordBatchReader.from_stream(df)</span></code>.</p> |
| </div> |
| <p>When partition boundaries are important, |
| <code class="xref py py-meth docutils literal notranslate"><span class="pre">execute_stream_partitioned()</span></code> |
| returns an iterable of <a class="reference internal" href="../../autoapi/datafusion/index.html#datafusion.RecordBatchStream" title="datafusion.RecordBatchStream"><code class="xref py py-class docutils literal notranslate"><span class="pre">datafusion.RecordBatchStream</span></code></a> objects, one per |
| partition:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">for</span> <span class="n">stream</span> <span class="ow">in</span> <span class="n">df</span><span class="o">.</span><span class="n">execute_stream_partitioned</span><span class="p">():</span> |
| <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">stream</span><span class="p">:</span> |
| <span class="o">...</span> <span class="c1"># each stream yields RecordBatches</span> |
| </pre></div> |
| </div> |
| <p>To process partitions concurrently, first collect the streams into a list |
| and then poll each one in a separate <code class="docutils literal notranslate"><span class="pre">asyncio</span></code> task:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">asyncio</span> |
| |
| <span class="k">async</span> <span class="k">def</span><span class="w"> </span><span class="nf">consume</span><span class="p">(</span><span class="n">stream</span><span class="p">):</span> |
| <span class="k">async</span> <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">stream</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="n">streams</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">execute_stream_partitioned</span><span class="p">())</span> |
| <span class="k">await</span> <span class="n">asyncio</span><span class="o">.</span><span class="n">gather</span><span class="p">(</span><span class="o">*</span><span class="p">(</span><span class="n">consume</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">streams</span><span class="p">))</span> |
| </pre></div> |
| </div> |
| <p>See <a class="reference internal" href="../io/arrow.html"><span class="doc">Arrow</span></a> for additional details on the Arrow interface.</p> |
| </section> |
| </section> |
| <section id="html-rendering"> |
| <h2>HTML Rendering<a class="headerlink" href="#html-rendering" title="Link to this heading">¶</a></h2> |
| <p>When working in Jupyter notebooks or other environments that support HTML rendering, DataFrames will |
| automatically display as formatted HTML tables. For detailed information about customizing HTML |
| rendering, formatting options, and advanced styling, see <a class="reference internal" href="rendering.html"><span class="doc">DataFrame Rendering</span></a>.</p> |
| </section> |
| <section id="core-classes"> |
| <h2>Core Classes<a class="headerlink" href="#core-classes" title="Link to this heading">¶</a></h2> |
| <dl> |
| <dt><strong>DataFrame</strong></dt><dd><p>The main DataFrame class for building and executing queries.</p> |
| <p>See: <code class="xref py py-class docutils literal notranslate"><span class="pre">datafusion.DataFrame</span></code></p> |
| </dd> |
| <dt><strong>SessionContext</strong></dt><dd><p>The primary entry point for creating DataFrames from various data sources.</p> |
| <p>Key methods for DataFrame creation:</p> |
| <ul class="simple"> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">read_csv()</span></code> - Read CSV files</p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">read_parquet()</span></code> - Read Parquet files</p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">read_json()</span></code> - Read JSON files</p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">read_avro()</span></code> - Read Avro files</p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">table()</span></code> - Access registered tables</p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">sql()</span></code> - Execute SQL queries</p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">from_pandas()</span></code> - Create from Pandas DataFrame</p></li> |
| <li><p><code class="xref py py-meth docutils literal notranslate"><span class="pre">from_arrow()</span></code> - Create from Arrow data</p></li> |
| </ul> |
| <p>See: <code class="xref py py-class docutils literal notranslate"><span class="pre">datafusion.SessionContext</span></code></p> |
| </dd> |
| </dl> |
| </section> |
| <section id="expression-classes"> |
| <h2>Expression Classes<a class="headerlink" href="#expression-classes" title="Link to this heading">¶</a></h2> |
| <dl> |
| <dt><strong>Expr</strong></dt><dd><p>Represents expressions that can be used in DataFrame operations.</p> |
| <p>See: <a class="reference internal" href="../../autoapi/datafusion/index.html#datafusion.Expr" title="datafusion.Expr"><code class="xref py py-class docutils literal notranslate"><span class="pre">datafusion.Expr</span></code></a></p> |
| </dd> |
| </dl> |
| <p><strong>Functions for creating expressions:</strong></p> |
| <ul class="simple"> |
| <li><p><a class="reference internal" href="../../autoapi/datafusion/index.html#datafusion.column" title="datafusion.column"><code class="xref py py-func docutils literal notranslate"><span class="pre">datafusion.column()</span></code></a> - Reference a column by name</p></li> |
| <li><p><a class="reference internal" href="../../autoapi/datafusion/index.html#datafusion.literal" title="datafusion.literal"><code class="xref py py-func docutils literal notranslate"><span class="pre">datafusion.literal()</span></code></a> - Create a literal value expression</p></li> |
| </ul> |
| </section> |
| <section id="built-in-functions"> |
| <h2>Built-in Functions<a class="headerlink" href="#built-in-functions" title="Link to this heading">¶</a></h2> |
| <p>DataFusion provides many built-in functions for data manipulation:</p> |
| <ul class="simple"> |
| <li><p><a class="reference internal" href="../../autoapi/datafusion/functions/index.html#module-datafusion.functions" title="datafusion.functions"><code class="xref py py-mod docutils literal notranslate"><span class="pre">datafusion.functions</span></code></a> - Mathematical, string, date/time, and aggregation functions</p></li> |
| </ul> |
| <p>For a complete list of available functions, see the <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#module-datafusion.functions" title="datafusion.functions"><code class="xref py py-mod docutils literal notranslate"><span class="pre">datafusion.functions</span></code></a> module documentation.</p> |
| <div class="toctree-wrapper compound"> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="rendering.html">DataFrame Rendering</a></li> |
| </ul> |
| </div> |
| </section> |
| </section> |
| |
| |
| </div> |
| |
| |
| <!-- Previous / next buttons --> |
| <div class='prev-next-area'> |
| <a class='left-prev' id="prev-link" href="../data-sources.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">Data Sources</p> |
| </div> |
| </a> |
| <a class='right-next' id="next-link" href="rendering.html" title="next page"> |
| <div class="prev-next-info"> |
| <p class="prev-next-subtitle">next</p> |
| <p class="prev-next-title">DataFrame Rendering</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"> |
| © 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> |
