| <!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>Functions — 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="Aggregation" href="aggregations.html" /> |
| <link rel="prev" title="Joins" href="joins.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="en"> |
| |
| |
| <!-- Google Analytics --> |
| |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <div class="container-fluid" id="banner"></div> |
| |
| |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| |
| <!-- Only show if we have sidebars configured, else just a small margin --> |
| <div class="col-12 col-md-3 bd-sidebar"> |
| <div class="sidebar-start-items"> |
| <a class="navbar-brand" href="../../index.html"> |
| <img src="../../_static/images/2x_bgwhite_original.png" class="logo" alt="logo"> |
| </a> |
| |
| <form class="bd-search d-flex align-items-center" action="../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form> |
| |
| <nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| <div class="bd-toc-item active"> |
| |
| <p aria-level="2" class="caption" role="heading"> |
| <span class="caption-text"> |
| LINKS |
| </span> |
| </p> |
| <ul class="nav bd-sidenav"> |
| <li class="toctree-l1"> |
| <a class="reference external" href="https://github.com/apache/datafusion-python"> |
| Github and Issue Tracker |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference external" href="https://docs.rs/datafusion/latest/datafusion/"> |
| Rust's API Docs |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference external" href="https://github.com/apache/datafusion/blob/main/CODE_OF_CONDUCT.md"> |
| Code of conduct |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference external" href="https://github.com/apache/datafusion-python/tree/main/examples"> |
| Examples |
| </a> |
| </li> |
| </ul> |
| <p aria-level="2" class="caption" role="heading"> |
| <span class="caption-text"> |
| USER GUIDE |
| </span> |
| </p> |
| <ul class="current nav bd-sidenav"> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../introduction.html"> |
| Introduction |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../basics.html"> |
| Concepts |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../data-sources.html"> |
| Data Sources |
| </a> |
| </li> |
| <li class="toctree-l1 has-children"> |
| <a class="reference internal" href="../dataframe/index.html"> |
| DataFrames |
| </a> |
| <input class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/> |
| <label for="toctree-checkbox-1"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../dataframe/rendering.html"> |
| HTML Rendering in Jupyter |
| </a> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1 current active has-children"> |
| <a class="reference internal" href="index.html"> |
| Common Operations |
| </a> |
| <input checked="" class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/> |
| <label for="toctree-checkbox-2"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul class="current"> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="views.html"> |
| Registering Views |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="basic-info.html"> |
| Basic Operations |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="select-and-filter.html"> |
| Column Selections |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="expressions.html"> |
| Expressions |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="joins.html"> |
| Joins |
| </a> |
| </li> |
| <li class="toctree-l2 current active"> |
| <a class="current reference internal" href="#"> |
| Functions |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="aggregations.html"> |
| Aggregation |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="windows.html"> |
| Window Functions |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="udf-and-udfa.html"> |
| User-Defined Functions |
| </a> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1 has-children"> |
| <a class="reference internal" href="../io/index.html"> |
| IO |
| </a> |
| <input class="toctree-checkbox" id="toctree-checkbox-3" name="toctree-checkbox-3" type="checkbox"/> |
| <label for="toctree-checkbox-3"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/arrow.html"> |
| Arrow |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/avro.html"> |
| Avro |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/csv.html"> |
| CSV |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/json.html"> |
| JSON |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/parquet.html"> |
| Parquet |
| </a> |
| </li> |
| <li class="toctree-l2"> |
| <a class="reference internal" href="../io/table_provider.html"> |
| Custom Table Provider |
| </a> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../configuration.html"> |
| Configuration |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../sql.html"> |
| SQL |
| </a> |
| </li> |
| </ul> |
| <p aria-level="2" class="caption" role="heading"> |
| <span class="caption-text"> |
| CONTRIBUTOR GUIDE |
| </span> |
| </p> |
| <ul class="nav bd-sidenav"> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../../contributor-guide/introduction.html"> |
| Introduction |
| </a> |
| </li> |
| <li class="toctree-l1"> |
| <a class="reference internal" href="../../contributor-guide/ffi.html"> |
| Python Extensions |
| </a> |
| </li> |
| </ul> |
| <p aria-level="2" class="caption" role="heading"> |
| <span class="caption-text"> |
| API |
| </span> |
| </p> |
| <ul class="nav bd-sidenav"> |
| <li class="toctree-l1 has-children"> |
| <a class="reference internal" href="../../autoapi/index.html"> |
| API Reference |
| </a> |
| <input class="toctree-checkbox" id="toctree-checkbox-4" name="toctree-checkbox-4" type="checkbox"/> |
| <label for="toctree-checkbox-4"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l2 has-children"> |
| <a class="reference internal" href="../../autoapi/datafusion/index.html"> |
| datafusion |
| </a> |
| <input class="toctree-checkbox" id="toctree-checkbox-5" name="toctree-checkbox-5" type="checkbox"/> |
| <label for="toctree-checkbox-5"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/catalog/index.html"> |
| datafusion.catalog |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/context/index.html"> |
| datafusion.context |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/dataframe/index.html"> |
| datafusion.dataframe |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/dataframe_formatter/index.html"> |
| datafusion.dataframe_formatter |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/expr/index.html"> |
| datafusion.expr |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/functions/index.html"> |
| datafusion.functions |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/html_formatter/index.html"> |
| datafusion.html_formatter |
| </a> |
| </li> |
| <li class="toctree-l3 has-children"> |
| <a class="reference internal" href="../../autoapi/datafusion/input/index.html"> |
| datafusion.input |
| </a> |
| <input class="toctree-checkbox" id="toctree-checkbox-6" name="toctree-checkbox-6" type="checkbox"/> |
| <label for="toctree-checkbox-6"> |
| <i class="fas fa-chevron-down"> |
| </i> |
| </label> |
| <ul> |
| <li class="toctree-l4"> |
| <a class="reference internal" href="../../autoapi/datafusion/input/base/index.html"> |
| datafusion.input.base |
| </a> |
| </li> |
| <li class="toctree-l4"> |
| <a class="reference internal" href="../../autoapi/datafusion/input/location/index.html"> |
| datafusion.input.location |
| </a> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/io/index.html"> |
| datafusion.io |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/object_store/index.html"> |
| datafusion.object_store |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/plan/index.html"> |
| datafusion.plan |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/record_batch/index.html"> |
| datafusion.record_batch |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/substrait/index.html"> |
| datafusion.substrait |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/unparser/index.html"> |
| datafusion.unparser |
| </a> |
| </li> |
| <li class="toctree-l3"> |
| <a class="reference internal" href="../../autoapi/datafusion/user_defined/index.html"> |
| datafusion.user_defined |
| </a> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| |
| |
| </div> |
| </nav> |
| </div> |
| <div class="sidebar-end-items"> |
| </div> |
| </div> |
| |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| |
| <div class="toc-item"> |
| |
| <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-h1 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#"> |
| Functions |
| </a> |
| <ul class="visible nav section-nav flex-column"> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#mathematical"> |
| Mathematical |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#conditional"> |
| Conditional |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#temporal"> |
| Temporal |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#string"> |
| String |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#casting"> |
| Casting |
| </a> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#other"> |
| Other |
| </a> |
| </li> |
| </ul> |
| </li> |
| <li class="toc-h1 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#handling-missing-values"> |
| Handling Missing Values |
| </a> |
| <ul class="visible nav section-nav flex-column"> |
| <li class="toc-h2 nav-item toc-entry"> |
| <a class="reference internal nav-link" href="#fill-null"> |
| fill_null |
| </a> |
| </li> |
| </ul> |
| </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="functions"> |
| <h1>Functions<a class="headerlink" href="#functions" title="Link to this heading">¶</a></h1> |
| <p>DataFusion provides a large number of built-in functions for performing complex queries without requiring user-defined functions. |
| In here we will cover some of the more popular use cases. If you want to view all the functions go to 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">Functions</span></code></a> API Reference.</p> |
| <p>We’ll use the pokemon dataset in the following examples.</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">1</span><span class="p">]:</span> <span class="kn">from</span><span class="w"> </span><span class="nn">datafusion</span><span class="w"> </span><span class="kn">import</span> <span class="n">SessionContext</span> |
| |
| <span class="n">In</span> <span class="p">[</span><span class="mi">2</span><span class="p">]:</span> <span class="n">ctx</span> <span class="o">=</span> <span class="n">SessionContext</span><span class="p">()</span> |
| |
| <span class="n">In</span> <span class="p">[</span><span class="mi">3</span><span class="p">]:</span> <span class="n">ctx</span><span class="o">.</span><span class="n">register_csv</span><span class="p">(</span><span class="s2">"pokemon"</span><span class="p">,</span> <span class="s2">"pokemon.csv"</span><span class="p">)</span> |
| |
| <span class="n">In</span> <span class="p">[</span><span class="mi">4</span><span class="p">]:</span> <span class="n">df</span> <span class="o">=</span> <span class="n">ctx</span><span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="s2">"pokemon"</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <section id="mathematical"> |
| <h2>Mathematical<a class="headerlink" href="#mathematical" title="Link to this heading">¶</a></h2> |
| <p>DataFusion offers mathematical functions such as <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.pow" title="datafusion.functions.pow"><code class="xref py py-func docutils literal notranslate"><span class="pre">pow()</span></code></a> or <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.log" title="datafusion.functions.log"><code class="xref py py-func docutils literal notranslate"><span class="pre">log()</span></code></a></p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">5</span><span class="p">]:</span> <span class="kn">from</span><span class="w"> </span><span class="nn">datafusion</span><span class="w"> </span><span class="kn">import</span> <span class="n">col</span><span class="p">,</span> <span class="n">literal</span><span class="p">,</span> <span class="n">string_literal</span><span class="p">,</span> <span class="n">str_lit</span> |
| |
| <span class="n">In</span> <span class="p">[</span><span class="mi">6</span><span class="p">]:</span> <span class="kn">from</span><span class="w"> </span><span class="nn">datafusion</span><span class="w"> </span><span class="kn">import</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">f</span> |
| |
| <span class="n">In</span> <span class="p">[</span><span class="mi">7</span><span class="p">]:</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span> |
| <span class="o">...</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">pow</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Attack"'</span><span class="p">),</span> <span class="n">literal</span><span class="p">(</span><span class="mi">2</span><span class="p">))</span> <span class="o">-</span> <span class="n">f</span><span class="o">.</span><span class="n">pow</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Defense"'</span><span class="p">),</span> <span class="n">literal</span><span class="p">(</span><span class="mi">2</span><span class="p">))</span> |
| <span class="o">...</span><span class="p">:</span> <span class="p">)</span><span class="o">.</span><span class="n">limit</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span> |
| <span class="o">...</span><span class="p">:</span> |
| <span class="n">Out</span><span class="p">[</span><span class="mi">7</span><span class="p">]:</span> |
| <span class="n">DataFrame</span><span class="p">()</span> |
| <span class="o">+------------------------------------------------------------------+</span> |
| <span class="o">|</span> <span class="n">power</span><span class="p">(</span><span class="n">pokemon</span><span class="o">.</span><span class="n">Attack</span><span class="p">,</span><span class="n">Int64</span><span class="p">(</span><span class="mi">2</span><span class="p">))</span> <span class="o">-</span> <span class="n">power</span><span class="p">(</span><span class="n">pokemon</span><span class="o">.</span><span class="n">Defense</span><span class="p">,</span><span class="n">Int64</span><span class="p">(</span><span class="mi">2</span><span class="p">))</span> <span class="o">|</span> |
| <span class="o">+------------------------------------------------------------------+</span> |
| <span class="o">|</span> <span class="mi">0</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="o">-</span><span class="mi">125</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="o">-</span><span class="mi">165</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="o">-</span><span class="mi">5129</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">855</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">732</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">972</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">4579</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">4732</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="o">-</span><span class="mi">1921</span> <span class="o">|</span> |
| <span class="o">+------------------------------------------------------------------+</span> |
| </pre></div> |
| </div> |
| </section> |
| <section id="conditional"> |
| <h2>Conditional<a class="headerlink" href="#conditional" title="Link to this heading">¶</a></h2> |
| <p>There 3 conditional functions in DataFusion <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.coalesce" title="datafusion.functions.coalesce"><code class="xref py py-func docutils literal notranslate"><span class="pre">coalesce()</span></code></a>, <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.nullif" title="datafusion.functions.nullif"><code class="xref py py-func docutils literal notranslate"><span class="pre">nullif()</span></code></a> and <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.case" title="datafusion.functions.case"><code class="xref py py-func docutils literal notranslate"><span class="pre">case()</span></code></a>.</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">8</span><span class="p">]:</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span> |
| <span class="o">...</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">coalesce</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Type 1"'</span><span class="p">),</span> <span class="n">col</span><span class="p">(</span><span class="s1">'"Type 2"'</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"dominant_type"</span><span class="p">)</span> |
| <span class="o">...</span><span class="p">:</span> <span class="p">)</span><span class="o">.</span><span class="n">limit</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span> |
| <span class="o">...</span><span class="p">:</span> |
| <span class="n">Out</span><span class="p">[</span><span class="mi">8</span><span class="p">]:</span> |
| <span class="n">DataFrame</span><span class="p">()</span> |
| <span class="o">+---------------+</span> |
| <span class="o">|</span> <span class="n">dominant_type</span> <span class="o">|</span> |
| <span class="o">+---------------+</span> |
| <span class="o">|</span> <span class="n">Grass</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="n">Grass</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="n">Grass</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="n">Grass</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="n">Fire</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="n">Water</span> <span class="o">|</span> |
| <span class="o">+---------------+</span> |
| </pre></div> |
| </div> |
| </section> |
| <section id="temporal"> |
| <h2>Temporal<a class="headerlink" href="#temporal" title="Link to this heading">¶</a></h2> |
| <p>For selecting the current time use <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.now" title="datafusion.functions.now"><code class="xref py py-func docutils literal notranslate"><span class="pre">now()</span></code></a></p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">9</span><span class="p">]:</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">f</span><span class="o">.</span><span class="n">now</span><span class="p">())</span> |
| <span class="n">Out</span><span class="p">[</span><span class="mi">9</span><span class="p">]:</span> |
| <span class="n">DataFrame</span><span class="p">()</span> |
| <span class="o">+--------------------------------+</span> |
| <span class="o">|</span> <span class="n">now</span><span class="p">()</span> <span class="o">|</span> |
| <span class="o">+--------------------------------+</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">2025</span><span class="o">-</span><span class="mi">10</span><span class="o">-</span><span class="mi">16</span><span class="n">T17</span><span class="p">:</span><span class="mi">13</span><span class="p">:</span><span class="mf">48.336869762</span><span class="n">Z</span> <span class="o">|</span> |
| <span class="o">+--------------------------------+</span> |
| <span class="n">Data</span> <span class="n">truncated</span><span class="o">.</span> |
| </pre></div> |
| </div> |
| <p>Convert to timestamps using <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.to_timestamp" title="datafusion.functions.to_timestamp"><code class="xref py py-func docutils literal notranslate"><span class="pre">to_timestamp()</span></code></a></p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">10</span><span class="p">]:</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">f</span><span class="o">.</span><span class="n">to_timestamp</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Total"'</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"timestamp"</span><span class="p">))</span> |
| <span class="n">Out</span><span class="p">[</span><span class="mi">10</span><span class="p">]:</span> |
| <span class="n">DataFrame</span><span class="p">()</span> |
| <span class="o">+---------------------+</span> |
| <span class="o">|</span> <span class="n">timestamp</span> <span class="o">|</span> |
| <span class="o">+---------------------+</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">05</span><span class="p">:</span><span class="mi">18</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">06</span><span class="p">:</span><span class="mi">45</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">08</span><span class="p">:</span><span class="mi">45</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">10</span><span class="p">:</span><span class="mi">25</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">05</span><span class="p">:</span><span class="mi">09</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">06</span><span class="p">:</span><span class="mi">45</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">08</span><span class="p">:</span><span class="mi">54</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">10</span><span class="p">:</span><span class="mi">34</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">10</span><span class="p">:</span><span class="mi">34</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1970</span><span class="o">-</span><span class="mi">01</span><span class="o">-</span><span class="mi">01</span><span class="n">T00</span><span class="p">:</span><span class="mi">05</span><span class="p">:</span><span class="mi">14</span> <span class="o">|</span> |
| <span class="o">+---------------------+</span> |
| <span class="n">Data</span> <span class="n">truncated</span><span class="o">.</span> |
| </pre></div> |
| </div> |
| <p>Extracting parts of a date using <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.date_part" title="datafusion.functions.date_part"><code class="xref py py-func docutils literal notranslate"><span class="pre">date_part()</span></code></a> (alias <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.extract" title="datafusion.functions.extract"><code class="xref py py-func docutils literal notranslate"><span class="pre">extract()</span></code></a>)</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">11</span><span class="p">]:</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">date_part</span><span class="p">(</span><span class="n">literal</span><span class="p">(</span><span class="s2">"month"</span><span class="p">),</span> <span class="n">f</span><span class="o">.</span><span class="n">to_timestamp</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Total"'</span><span class="p">)))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"month"</span><span class="p">),</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">extract</span><span class="p">(</span><span class="n">literal</span><span class="p">(</span><span class="s2">"day"</span><span class="p">),</span> <span class="n">f</span><span class="o">.</span><span class="n">to_timestamp</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Total"'</span><span class="p">)))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"day"</span><span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> <span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> |
| <span class="n">Out</span><span class="p">[</span><span class="mi">11</span><span class="p">]:</span> |
| <span class="n">DataFrame</span><span class="p">()</span> |
| <span class="o">+-------+-----+</span> |
| <span class="o">|</span> <span class="n">month</span> <span class="o">|</span> <span class="n">day</span> <span class="o">|</span> |
| <span class="o">+-------+-----+</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> <span class="mi">1</span> <span class="o">|</span> |
| <span class="o">+-------+-----+</span> |
| <span class="n">Data</span> <span class="n">truncated</span><span class="o">.</span> |
| </pre></div> |
| </div> |
| </section> |
| <section id="string"> |
| <h2>String<a class="headerlink" href="#string" title="Link to this heading">¶</a></h2> |
| <p>In the field of data science, working with textual data is a common task. To make string manipulation easier, |
| DataFusion offers a range of helpful options.</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">12</span><span class="p">]:</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">char_length</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Name"'</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"len"</span><span class="p">),</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">lower</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Name"'</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"lower"</span><span class="p">),</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">left</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Name"'</span><span class="p">),</span> <span class="n">literal</span><span class="p">(</span><span class="mi">4</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"code"</span><span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> <span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> |
| <span class="n">Out</span><span class="p">[</span><span class="mi">12</span><span class="p">]:</span> |
| <span class="n">DataFrame</span><span class="p">()</span> |
| <span class="o">+-----+---------------------------+------+</span> |
| <span class="o">|</span> <span class="nb">len</span> <span class="o">|</span> <span class="n">lower</span> <span class="o">|</span> <span class="n">code</span> <span class="o">|</span> |
| <span class="o">+-----+---------------------------+------+</span> |
| <span class="o">|</span> <span class="mi">9</span> <span class="o">|</span> <span class="n">bulbasaur</span> <span class="o">|</span> <span class="n">Bulb</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">7</span> <span class="o">|</span> <span class="n">ivysaur</span> <span class="o">|</span> <span class="n">Ivys</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">8</span> <span class="o">|</span> <span class="n">venusaur</span> <span class="o">|</span> <span class="n">Venu</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">21</span> <span class="o">|</span> <span class="n">venusaurmega</span> <span class="n">venusaur</span> <span class="o">|</span> <span class="n">Venu</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">10</span> <span class="o">|</span> <span class="n">charmander</span> <span class="o">|</span> <span class="n">Char</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">10</span> <span class="o">|</span> <span class="n">charmeleon</span> <span class="o">|</span> <span class="n">Char</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">9</span> <span class="o">|</span> <span class="n">charizard</span> <span class="o">|</span> <span class="n">Char</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">25</span> <span class="o">|</span> <span class="n">charizardmega</span> <span class="n">charizard</span> <span class="n">x</span> <span class="o">|</span> <span class="n">Char</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">25</span> <span class="o">|</span> <span class="n">charizardmega</span> <span class="n">charizard</span> <span class="n">y</span> <span class="o">|</span> <span class="n">Char</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mi">8</span> <span class="o">|</span> <span class="n">squirtle</span> <span class="o">|</span> <span class="n">Squi</span> <span class="o">|</span> |
| <span class="o">+-----+---------------------------+------+</span> |
| <span class="n">Data</span> <span class="n">truncated</span><span class="o">.</span> |
| </pre></div> |
| </div> |
| <p>This also includes the functions for regular expressions like <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.regexp_replace" title="datafusion.functions.regexp_replace"><code class="xref py py-func docutils literal notranslate"><span class="pre">regexp_replace()</span></code></a> and <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.regexp_match" title="datafusion.functions.regexp_match"><code class="xref py py-func docutils literal notranslate"><span class="pre">regexp_match()</span></code></a></p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">13</span><span class="p">]:</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">regexp_match</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Name"'</span><span class="p">),</span> <span class="n">literal</span><span class="p">(</span><span class="s2">"Char"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"dragons"</span><span class="p">),</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">regexp_replace</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Name"'</span><span class="p">),</span> <span class="n">literal</span><span class="p">(</span><span class="s2">"saur"</span><span class="p">),</span> <span class="n">literal</span><span class="p">(</span><span class="s2">"fleur"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"flowers"</span><span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> <span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> |
| <span class="n">Out</span><span class="p">[</span><span class="mi">13</span><span class="p">]:</span> |
| <span class="n">DataFrame</span><span class="p">()</span> |
| <span class="o">+---------+---------------------------+</span> |
| <span class="o">|</span> <span class="n">dragons</span> <span class="o">|</span> <span class="n">flowers</span> <span class="o">|</span> |
| <span class="o">+---------+---------------------------+</span> |
| <span class="o">|</span> <span class="o">|</span> <span class="n">Bulbafleur</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="o">|</span> <span class="n">Ivyfleur</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="o">|</span> <span class="n">Venufleur</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="o">|</span> <span class="n">VenufleurMega</span> <span class="n">Venusaur</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="p">[</span><span class="n">Char</span><span class="p">]</span> <span class="o">|</span> <span class="n">Charmander</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="p">[</span><span class="n">Char</span><span class="p">]</span> <span class="o">|</span> <span class="n">Charmeleon</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="p">[</span><span class="n">Char</span><span class="p">]</span> <span class="o">|</span> <span class="n">Charizard</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="p">[</span><span class="n">Char</span><span class="p">]</span> <span class="o">|</span> <span class="n">CharizardMega</span> <span class="n">Charizard</span> <span class="n">X</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="p">[</span><span class="n">Char</span><span class="p">]</span> <span class="o">|</span> <span class="n">CharizardMega</span> <span class="n">Charizard</span> <span class="n">Y</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="o">|</span> <span class="n">Squirtle</span> <span class="o">|</span> |
| <span class="o">+---------+---------------------------+</span> |
| <span class="n">Data</span> <span class="n">truncated</span><span class="o">.</span> |
| </pre></div> |
| </div> |
| </section> |
| <section id="casting"> |
| <h2>Casting<a class="headerlink" href="#casting" title="Link to this heading">¶</a></h2> |
| <p>Casting expressions to different data types using <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.arrow_cast" title="datafusion.functions.arrow_cast"><code class="xref py py-func docutils literal notranslate"><span class="pre">arrow_cast()</span></code></a></p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">14</span><span class="p">]:</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">arrow_cast</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Total"'</span><span class="p">),</span> <span class="n">string_literal</span><span class="p">(</span><span class="s2">"Float64"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"total_as_float"</span><span class="p">),</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">f</span><span class="o">.</span><span class="n">arrow_cast</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Total"'</span><span class="p">),</span> <span class="n">str_lit</span><span class="p">(</span><span class="s2">"Int32"</span><span class="p">))</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"total_as_int"</span><span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> <span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> |
| <span class="n">Out</span><span class="p">[</span><span class="mi">14</span><span class="p">]:</span> |
| <span class="n">DataFrame</span><span class="p">()</span> |
| <span class="o">+----------------+--------------+</span> |
| <span class="o">|</span> <span class="n">total_as_float</span> <span class="o">|</span> <span class="n">total_as_int</span> <span class="o">|</span> |
| <span class="o">+----------------+--------------+</span> |
| <span class="o">|</span> <span class="mf">318.0</span> <span class="o">|</span> <span class="mi">318</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mf">405.0</span> <span class="o">|</span> <span class="mi">405</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mf">525.0</span> <span class="o">|</span> <span class="mi">525</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mf">625.0</span> <span class="o">|</span> <span class="mi">625</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mf">309.0</span> <span class="o">|</span> <span class="mi">309</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mf">405.0</span> <span class="o">|</span> <span class="mi">405</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mf">534.0</span> <span class="o">|</span> <span class="mi">534</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mf">634.0</span> <span class="o">|</span> <span class="mi">634</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mf">634.0</span> <span class="o">|</span> <span class="mi">634</span> <span class="o">|</span> |
| <span class="o">|</span> <span class="mf">314.0</span> <span class="o">|</span> <span class="mi">314</span> <span class="o">|</span> |
| <span class="o">+----------------+--------------+</span> |
| <span class="n">Data</span> <span class="n">truncated</span><span class="o">.</span> |
| </pre></div> |
| </div> |
| </section> |
| <section id="other"> |
| <h2>Other<a class="headerlink" href="#other" title="Link to this heading">¶</a></h2> |
| <p>The function <a class="reference internal" href="../../autoapi/datafusion/functions/index.html#datafusion.functions.in_list" title="datafusion.functions.in_list"><code class="xref py py-func docutils literal notranslate"><span class="pre">in_list()</span></code></a> allows to check a column for the presence of multiple values:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="n">In</span> <span class="p">[</span><span class="mi">15</span><span class="p">]:</span> <span class="n">types</span> <span class="o">=</span> <span class="p">[</span><span class="n">literal</span><span class="p">(</span><span class="s2">"Grass"</span><span class="p">),</span> <span class="n">literal</span><span class="p">(</span><span class="s2">"Fire"</span><span class="p">),</span> <span class="n">literal</span><span class="p">(</span><span class="s2">"Water"</span><span class="p">)]</span> |
| |
| <span class="n">In</span> <span class="p">[</span><span class="mi">16</span><span class="p">]:</span> <span class="p">(</span> |
| <span class="o">....</span><span class="p">:</span> <span class="n">df</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">f</span><span class="o">.</span><span class="n">in_list</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s1">'"Type 1"'</span><span class="p">),</span> <span class="n">types</span><span class="p">,</span> <span class="n">negated</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"basic_types"</span><span class="p">))</span> |
| <span class="o">....</span><span class="p">:</span> <span class="o">.</span><span class="n">limit</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> <span class="o">.</span><span class="n">to_pandas</span><span class="p">()</span> |
| <span class="o">....</span><span class="p">:</span> <span class="p">)</span> |
| <span class="o">....</span><span class="p">:</span> |
| <span class="n">Out</span><span class="p">[</span><span class="mi">16</span><span class="p">]:</span> |
| <span class="n">basic_types</span> |
| <span class="mi">0</span> <span class="kc">True</span> |
| <span class="mi">1</span> <span class="kc">True</span> |
| <span class="mi">2</span> <span class="kc">True</span> |
| <span class="mi">3</span> <span class="kc">True</span> |
| <span class="mi">4</span> <span class="kc">True</span> |
| <span class="mi">5</span> <span class="kc">True</span> |
| <span class="mi">6</span> <span class="kc">True</span> |
| <span class="mi">7</span> <span class="kc">True</span> |
| <span class="mi">8</span> <span class="kc">True</span> |
| <span class="mi">9</span> <span class="kc">True</span> |
| <span class="mi">10</span> <span class="kc">True</span> |
| <span class="mi">11</span> <span class="kc">True</span> |
| <span class="mi">12</span> <span class="kc">True</span> |
| <span class="mi">13</span> <span class="kc">False</span> |
| <span class="mi">14</span> <span class="kc">False</span> |
| <span class="mi">15</span> <span class="kc">False</span> |
| <span class="mi">16</span> <span class="kc">False</span> |
| <span class="mi">17</span> <span class="kc">False</span> |
| <span class="mi">18</span> <span class="kc">False</span> |
| <span class="mi">19</span> <span class="kc">False</span> |
| </pre></div> |
| </div> |
| </section> |
| </section> |
| <section id="handling-missing-values"> |
| <h1>Handling Missing Values<a class="headerlink" href="#handling-missing-values" title="Link to this heading">¶</a></h1> |
| <p>DataFusion provides methods to handle missing values in DataFrames:</p> |
| <section id="fill-null"> |
| <h2>fill_null<a class="headerlink" href="#fill-null" title="Link to this heading">¶</a></h2> |
| <p>The <code class="docutils literal notranslate"><span class="pre">fill_null()</span></code> method replaces NULL values in specified columns with a provided value:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Fill all NULL values with 0 where possible</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">fill_null</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> |
| |
| <span class="c1"># Fill NULL values only in specific string columns</span> |
| <span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">fill_null</span><span class="p">(</span><span class="s2">"missing"</span><span class="p">,</span> <span class="n">subset</span><span class="o">=</span><span class="p">[</span><span class="s2">"name"</span><span class="p">,</span> <span class="s2">"category"</span><span class="p">])</span> |
| </pre></div> |
| </div> |
| <p>The fill value will be cast to match each column’s type. If casting fails for a column, that column remains unchanged.</p> |
| </section> |
| </section> |
| |
| |
| </div> |
| |
| |
| <!-- Previous / next buttons --> |
| <div class='prev-next-area'> |
| <a class='left-prev' id="prev-link" href="joins.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">Joins</p> |
| </div> |
| </a> |
| <a class='right-next' id="next-link" href="aggregations.html" title="next page"> |
| <div class="prev-next-info"> |
| <p class="prev-next-subtitle">next</p> |
| <p class="prev-next-title">Aggregation</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> |
