| |
| |
| <!DOCTYPE html> |
| |
| |
| <html > |
| |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" /> |
| |
| <title>Testing PySpark — PySpark 4.1.0-preview1 documentation</title> |
| |
| |
| |
| <script data-cfasync="false"> |
| document.documentElement.dataset.mode = localStorage.getItem("mode") || ""; |
| document.documentElement.dataset.theme = localStorage.getItem("theme") || "light"; |
| </script> |
| |
| <!-- Loaded before other Sphinx assets --> |
| <link href="../_static/styles/theme.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link href="../_static/styles/bootstrap.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link href="../_static/styles/pydata-sphinx-theme.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| |
| |
| <link href="../_static/vendor/fontawesome/6.1.2/css/all.min.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../_static/vendor/fontawesome/6.1.2/webfonts/fa-solid-900.woff2" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../_static/vendor/fontawesome/6.1.2/webfonts/fa-brands-400.woff2" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../_static/vendor/fontawesome/6.1.2/webfonts/fa-regular-400.woff2" /> |
| |
| <link rel="stylesheet" type="text/css" href="../_static/pygments.css" /> |
| <link rel="stylesheet" type="text/css" href="../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../_static/nbsphinx-code-cells.css" /> |
| <link rel="stylesheet" type="text/css" href="../_static/css/pyspark.css" /> |
| |
| <!-- Pre-loaded scripts that we'll load fully later --> |
| <link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=e353d410970836974a52" /> |
| <link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=e353d410970836974a52" /> |
| |
| <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script> |
| <script src="../_static/jquery.js"></script> |
| <script src="../_static/underscore.js"></script> |
| <script src="../_static/doctools.js"></script> |
| <script src="../_static/clipboard.min.js"></script> |
| <script src="../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script>window.MathJax = {"tex": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true}, "options": {"ignoreHtmlClass": "tex2jax_ignore|mathjax_ignore|document", "processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script> |
| <script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script> |
| <script>DOCUMENTATION_OPTIONS.pagename = 'getting_started/testing_pyspark';</script> |
| <script> |
| DOCUMENTATION_OPTIONS.theme_switcher_json_url = 'https://spark.apache.org/static/versions.json'; |
| DOCUMENTATION_OPTIONS.theme_switcher_version_match = '4.1.0-preview1'; |
| </script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/getting_started/testing_pyspark.html" /> |
| <link rel="search" title="Search" href="../search.html" /> |
| <link rel="next" title="Tutorials" href="../tutorial/index.html" /> |
| <link rel="prev" title="Quickstart: Pandas API on Spark" href="quickstart_ps.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="None"> |
| |
| |
| <!-- Matomo --> |
| <script type="text/javascript"> |
| var _paq = window._paq = window._paq || []; |
| /* tracker methods like "setCustomDimension" should be called before "trackPageView" */ |
| _paq.push(["disableCookies"]); |
| _paq.push(['trackPageView']); |
| _paq.push(['enableLinkTracking']); |
| (function() { |
| var u="https://analytics.apache.org/"; |
| _paq.push(['setTrackerUrl', u+'matomo.php']); |
| _paq.push(['setSiteId', '40']); |
| var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0]; |
| g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s); |
| })(); |
| </script> |
| <!-- End Matomo Code --> |
| |
| </head> |
| |
| |
| <body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode=""> |
| |
| |
| |
| <a class="skip-link" href="#main-content">Skip to main content</a> |
| |
| <input type="checkbox" |
| class="sidebar-toggle" |
| name="__primary" |
| id="__primary"/> |
| <label class="overlay overlay-primary" for="__primary"></label> |
| |
| <input type="checkbox" |
| class="sidebar-toggle" |
| name="__secondary" |
| id="__secondary"/> |
| <label class="overlay overlay-secondary" for="__secondary"></label> |
| |
| <div class="search-button__wrapper"> |
| <div class="search-button__overlay"></div> |
| <div class="search-button__search-container"> |
| <form class="bd-search d-flex align-items-center" |
| action="../search.html" |
| method="get"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| <input type="search" |
| class="form-control" |
| name="q" |
| id="search-input" |
| placeholder="Search the docs ..." |
| aria-label="Search the docs ..." |
| autocomplete="off" |
| autocorrect="off" |
| autocapitalize="off" |
| spellcheck="false"/> |
| <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span> |
| </form></div> |
| </div> |
| |
| <nav class="bd-header navbar navbar-expand-lg bd-navbar"> |
| <div class="bd-header__inner bd-page-width"> |
| <label class="sidebar-toggle primary-toggle" for="__primary"> |
| <span class="fa-solid fa-bars"></span> |
| </label> |
| |
| <div class="navbar-header-items__start"> |
| |
| <div class="navbar-item"> |
| |
| |
| <a class="navbar-brand logo" href="../index.html"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <img src="https://spark.apache.org/images/spark-logo.png" class="logo__image only-light" alt="Logo image"/> |
| <script>document.write(`<img src="https://spark.apache.org/images/spark-logo-rev.svg" class="logo__image only-dark" alt="Logo image"/>`);</script> |
| |
| |
| </a></div> |
| |
| </div> |
| |
| |
| <div class="col-lg-9 navbar-header-items"> |
| |
| <div class="me-auto navbar-header-items__center"> |
| |
| <div class="navbar-item"><nav class="navbar-nav"> |
| <p class="sidebar-header-items__title" |
| role="heading" |
| aria-level="1" |
| aria-label="Site Navigation"> |
| Site Navigation |
| </p> |
| <ul class="bd-navbar-elements navbar-nav"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| |
| <li class="nav-item current active"> |
| <a class="nav-link nav-internal" href="index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../tutorial/index.html"> |
| Tutorials |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../user_guide/index.html"> |
| User Guide |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| <div class="nav-item dropdown"> |
| <button class="btn dropdown-toggle nav-item" type="button" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false"> |
| More |
| </button> |
| <div class="dropdown-menu"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| </div> |
| </div> |
| |
| </ul> |
| </nav></div> |
| |
| </div> |
| |
| |
| <div class="navbar-header-items__end"> |
| |
| <div class="navbar-item navbar-persistent--container"> |
| |
| <script> |
| document.write(` |
| <button class="btn btn-sm navbar-btn search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| </button> |
| `); |
| </script> |
| </div> |
| |
| |
| <div class="navbar-item"> |
| <script> |
| document.write(` |
| <div class="version-switcher__container dropdown"> |
| <button type="button" class="version-switcher__button btn btn-sm navbar-btn dropdown-toggle" data-bs-toggle="dropdown"> |
| 4.1.0-preview1 <!-- this text may get changed later by javascript --> |
| <span class="caret"></span> |
| </button> |
| <div class="version-switcher__menu dropdown-menu list-group-flush py-0"> |
| <!-- dropdown will be populated by javascript on page load --> |
| </div> |
| </div> |
| `); |
| </script></div> |
| |
| <div class="navbar-item"> |
| <script> |
| document.write(` |
| <button class="theme-switch-button btn btn-sm btn-outline-primary navbar-btn rounded-circle" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <span class="theme-switch" data-mode="light"><i class="fa-solid fa-sun"></i></span> |
| <span class="theme-switch" data-mode="dark"><i class="fa-solid fa-moon"></i></span> |
| <span class="theme-switch" data-mode="auto"><i class="fa-solid fa-circle-half-stroke"></i></span> |
| </button> |
| `); |
| </script></div> |
| |
| <div class="navbar-item"><ul class="navbar-icon-links navbar-nav" |
| aria-label="Icon Links"> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://github.com/apache/spark" title="GitHub" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-brands fa-github"></i></span> |
| <label class="sr-only">GitHub</label></a> |
| </li> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://pypi.org/project/pyspark" title="PyPI" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-solid fa-box"></i></span> |
| <label class="sr-only">PyPI</label></a> |
| </li> |
| </ul></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <div class="navbar-persistent--mobile"> |
| <script> |
| document.write(` |
| <button class="btn btn-sm navbar-btn search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| </button> |
| `); |
| </script> |
| </div> |
| |
| |
| |
| <label class="sidebar-toggle secondary-toggle" for="__secondary"> |
| <span class="fa-solid fa-outdent"></span> |
| </label> |
| |
| </div> |
| |
| </nav> |
| |
| <div class="bd-container"> |
| <div class="bd-container__inner bd-page-width"> |
| |
| <div class="bd-sidebar-primary bd-sidebar"> |
| |
| |
| |
| <div class="sidebar-header-items sidebar-primary__section"> |
| |
| |
| <div class="sidebar-header-items__center"> |
| |
| <div class="navbar-item"><nav class="navbar-nav"> |
| <p class="sidebar-header-items__title" |
| role="heading" |
| aria-level="1" |
| aria-label="Site Navigation"> |
| Site Navigation |
| </p> |
| <ul class="bd-navbar-elements navbar-nav"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| |
| <li class="nav-item current active"> |
| <a class="nav-link nav-internal" href="index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../tutorial/index.html"> |
| Tutorials |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../user_guide/index.html"> |
| User Guide |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| <div class="nav-item dropdown"> |
| <button class="btn dropdown-toggle nav-item" type="button" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false"> |
| More |
| </button> |
| <div class="dropdown-menu"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| </div> |
| </div> |
| |
| </ul> |
| </nav></div> |
| |
| </div> |
| |
| |
| |
| <div class="sidebar-header-items__end"> |
| |
| <div class="navbar-item"> |
| <script> |
| document.write(` |
| <div class="version-switcher__container dropdown"> |
| <button type="button" class="version-switcher__button btn btn-sm navbar-btn dropdown-toggle" data-bs-toggle="dropdown"> |
| 4.1.0-preview1 <!-- this text may get changed later by javascript --> |
| <span class="caret"></span> |
| </button> |
| <div class="version-switcher__menu dropdown-menu list-group-flush py-0"> |
| <!-- dropdown will be populated by javascript on page load --> |
| </div> |
| </div> |
| `); |
| </script></div> |
| |
| <div class="navbar-item"> |
| <script> |
| document.write(` |
| <button class="theme-switch-button btn btn-sm btn-outline-primary navbar-btn rounded-circle" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <span class="theme-switch" data-mode="light"><i class="fa-solid fa-sun"></i></span> |
| <span class="theme-switch" data-mode="dark"><i class="fa-solid fa-moon"></i></span> |
| <span class="theme-switch" data-mode="auto"><i class="fa-solid fa-circle-half-stroke"></i></span> |
| </button> |
| `); |
| </script></div> |
| |
| <div class="navbar-item"><ul class="navbar-icon-links navbar-nav" |
| aria-label="Icon Links"> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://github.com/apache/spark" title="GitHub" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-brands fa-github"></i></span> |
| <label class="sr-only">GitHub</label></a> |
| </li> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://pypi.org/project/pyspark" title="PyPI" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-solid fa-box"></i></span> |
| <label class="sr-only">PyPI</label></a> |
| </li> |
| </ul></div> |
| |
| </div> |
| |
| </div> |
| |
| <div class="sidebar-primary-items__start sidebar-primary__section"> |
| <div class="sidebar-primary-item"><nav class="bd-docs-nav bd-links" |
| aria-label="Section Navigation"> |
| <p class="bd-links__title" role="heading" aria-level="1">Section Navigation</p> |
| <div class="bd-toc-item navbar-nav"><ul class="current nav bd-sidenav"> |
| <li class="toctree-l1"><a class="reference internal" href="install.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="quickstart_df.html">Quickstart: DataFrame</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="quickstart_connect.html">Quickstart: Spark Connect</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="quickstart_ps.html">Quickstart: Pandas API on Spark</a></li> |
| <li class="toctree-l1 current active"><a class="current reference internal" href="#">Testing PySpark</a></li> |
| </ul> |
| </div> |
| </nav></div> |
| </div> |
| |
| |
| <div class="sidebar-primary-items__end sidebar-primary__section"> |
| </div> |
| |
| <div id="rtd-footer-container"></div> |
| |
| |
| </div> |
| |
| <main id="main-content" class="bd-main"> |
| |
| |
| <div class="bd-content"> |
| <div class="bd-article-container"> |
| |
| <div class="bd-header-article"> |
| <div class="header-article-items header-article__inner"> |
| |
| <div class="header-article-items__start"> |
| |
| <div class="header-article-item"> |
| |
| |
| |
| <nav aria-label="Breadcrumbs"> |
| <ul class="bd-breadcrumbs" role="navigation" aria-label="Breadcrumb"> |
| |
| <li class="breadcrumb-item breadcrumb-home"> |
| <a href="../index.html" class="nav-link" aria-label="Home"> |
| <i class="fa-solid fa-home"></i> |
| </a> |
| </li> |
| |
| <li class="breadcrumb-item"><a href="index.html" class="nav-link">Getting Started</a></li> |
| |
| <li class="breadcrumb-item active" aria-current="page">Testing PySpark</li> |
| </ul> |
| </nav> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| </div> |
| |
| |
| |
| |
| <div id="searchbox"></div> |
| <article class="bd-article" role="main"> |
| |
| <section id="Testing-PySpark"> |
| <h1>Testing PySpark<a class="headerlink" href="#Testing-PySpark" title="Permalink to this headline">#</a></h1> |
| <p>This guide is a reference for writing robust tests for PySpark code.</p> |
| <p>To view the docs for PySpark test utils, see <a class="reference external" href="https://spark.apache.org/docs/latest/api/python/reference/pyspark.testing.html">here</a>.</p> |
| <section id="Build-a-PySpark-Application"> |
| <h2>Build a PySpark Application<a class="headerlink" href="#Build-a-PySpark-Application" title="Permalink to this headline">#</a></h2> |
| <p>Here is an example for how to start a PySpark application. Feel free to skip to the next section, “Testing your PySpark Application,” if you already have an application you’re ready to test.</p> |
| <p>First, start your Spark Session.</p> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[3]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql</span><span class="w"> </span><span class="kn">import</span> <span class="n">SparkSession</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql.functions</span><span class="w"> </span><span class="kn">import</span> <span class="n">col</span> |
| |
| <span class="c1"># Create a SparkSession</span> |
| <span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"Testing PySpark Example"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| </div> |
| <p>Next, create a DataFrame.</p> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[5]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">sample_data</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"John D."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">30</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Alice G."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">25</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Bob T."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">35</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Eve A."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">28</span><span class="p">}]</span> |
| |
| <span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">sample_data</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| </div> |
| <p>Now, let’s define and apply a transformation function to our DataFrame.</p> |
| <div class="nbinput docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[7]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql.functions</span><span class="w"> </span><span class="kn">import</span> <span class="n">col</span><span class="p">,</span> <span class="n">regexp_replace</span> |
| |
| <span class="c1"># Remove additional spaces in name</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">remove_extra_spaces</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="n">column_name</span><span class="p">):</span> |
| <span class="c1"># Remove extra spaces from the specified column</span> |
| <span class="n">df_transformed</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">withColumn</span><span class="p">(</span><span class="n">column_name</span><span class="p">,</span> <span class="n">regexp_replace</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="n">column_name</span><span class="p">),</span> <span class="s2">"</span><span class="se">\\</span><span class="s2">s+"</span><span class="p">,</span> <span class="s2">" "</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="n">df_transformed</span> |
| |
| <span class="n">transformed_df</span> <span class="o">=</span> <span class="n">remove_extra_spaces</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="s2">"name"</span><span class="p">)</span> |
| |
| <span class="n">transformed_df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| </div> |
| <div class="nboutput nblast docutils container"> |
| <div class="prompt empty docutils container"> |
| </div> |
| <div class="output_area docutils container"> |
| <div class="highlight"><pre> |
| +---+--------+ |
| |age| name| |
| +---+--------+ |
| | 30| John D.| |
| | 25|Alice G.| |
| | 35| Bob T.| |
| | 28| Eve A.| |
| +---+--------+ |
| |
| </pre></div></div> |
| </div> |
| </section> |
| <section id="Testing-your-PySpark-Application"> |
| <h2>Testing your PySpark Application<a class="headerlink" href="#Testing-your-PySpark-Application" title="Permalink to this headline">#</a></h2> |
| <p>Now let’s test our PySpark transformation function.</p> |
| <p>One option is to simply eyeball the resulting DataFrame. However, this can be impractical for large DataFrame or input sizes.</p> |
| <p>A better way is to write tests. Here are some examples of how we can test our code. The examples below apply for Spark 3.5 and above versions.</p> |
| <p>Note that these examples are not exhaustive, as there are many other test framework alternatives which you can use instead of <code class="docutils literal notranslate"><span class="pre">unittest</span></code> or <code class="docutils literal notranslate"><span class="pre">pytest</span></code>. The built-in PySpark testing util functions are standalone, meaning they can be compatible with any test framework or CI test pipeline.</p> |
| <section id="Option-1:-Using-Only-PySpark-Built-in-Test-Utility-Functions"> |
| <h3>Option 1: Using Only PySpark Built-in Test Utility Functions<a class="headerlink" href="#Option-1:-Using-Only-PySpark-Built-in-Test-Utility-Functions" title="Permalink to this headline">#</a></h3> |
| <p>For simple ad-hoc validation cases, PySpark testing utils like <code class="docutils literal notranslate"><span class="pre">assertDataFrameEqual</span></code> and <code class="docutils literal notranslate"><span class="pre">assertSchemaEqual</span></code> can be used in a standalone context. You could easily test PySpark code in a notebook session. For example, say you want to assert equality between two DataFrames:</p> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[10]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">pyspark.testing</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.testing.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">assertDataFrameEqual</span> |
| |
| <span class="c1"># Example 1</span> |
| <span class="n">df1</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="p">[(</span><span class="s2">"1"</span><span class="p">,</span> <span class="mi">1000</span><span class="p">),</span> <span class="p">(</span><span class="s2">"2"</span><span class="p">,</span> <span class="mi">3000</span><span class="p">)],</span> <span class="n">schema</span><span class="o">=</span><span class="p">[</span><span class="s2">"id"</span><span class="p">,</span> <span class="s2">"amount"</span><span class="p">])</span> |
| <span class="n">df2</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="p">[(</span><span class="s2">"1"</span><span class="p">,</span> <span class="mi">1000</span><span class="p">),</span> <span class="p">(</span><span class="s2">"2"</span><span class="p">,</span> <span class="mi">3000</span><span class="p">)],</span> <span class="n">schema</span><span class="o">=</span><span class="p">[</span><span class="s2">"id"</span><span class="p">,</span> <span class="s2">"amount"</span><span class="p">])</span> |
| <span class="n">assertDataFrameEqual</span><span class="p">(</span><span class="n">df1</span><span class="p">,</span> <span class="n">df2</span><span class="p">)</span> <span class="c1"># pass, DataFrames are identical</span> |
| </pre></div> |
| </div> |
| </div> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[11]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># Example 2</span> |
| <span class="n">df1</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="p">[(</span><span class="s2">"1"</span><span class="p">,</span> <span class="mf">0.1</span><span class="p">),</span> <span class="p">(</span><span class="s2">"2"</span><span class="p">,</span> <span class="mf">3.23</span><span class="p">)],</span> <span class="n">schema</span><span class="o">=</span><span class="p">[</span><span class="s2">"id"</span><span class="p">,</span> <span class="s2">"amount"</span><span class="p">])</span> |
| <span class="n">df2</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="p">[(</span><span class="s2">"1"</span><span class="p">,</span> <span class="mf">0.109</span><span class="p">),</span> <span class="p">(</span><span class="s2">"2"</span><span class="p">,</span> <span class="mf">3.23</span><span class="p">)],</span> <span class="n">schema</span><span class="o">=</span><span class="p">[</span><span class="s2">"id"</span><span class="p">,</span> <span class="s2">"amount"</span><span class="p">])</span> |
| <span class="n">assertDataFrameEqual</span><span class="p">(</span><span class="n">df1</span><span class="p">,</span> <span class="n">df2</span><span class="p">,</span> <span class="n">rtol</span><span class="o">=</span><span class="mf">1e-1</span><span class="p">)</span> <span class="c1"># pass, DataFrames are approx equal by rtol</span> |
| </pre></div> |
| </div> |
| </div> |
| <p>You can also simply compare two DataFrame schemas:</p> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[13]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.testing.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">assertSchemaEqual</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql.types</span><span class="w"> </span><span class="kn">import</span> <span class="n">StructType</span><span class="p">,</span> <span class="n">StructField</span><span class="p">,</span> <span class="n">ArrayType</span><span class="p">,</span> <span class="n">DoubleType</span> |
| |
| <span class="n">s1</span> <span class="o">=</span> <span class="n">StructType</span><span class="p">([</span><span class="n">StructField</span><span class="p">(</span><span class="s2">"names"</span><span class="p">,</span> <span class="n">ArrayType</span><span class="p">(</span><span class="n">DoubleType</span><span class="p">(),</span> <span class="kc">True</span><span class="p">),</span> <span class="kc">True</span><span class="p">)])</span> |
| <span class="n">s2</span> <span class="o">=</span> <span class="n">StructType</span><span class="p">([</span><span class="n">StructField</span><span class="p">(</span><span class="s2">"names"</span><span class="p">,</span> <span class="n">ArrayType</span><span class="p">(</span><span class="n">DoubleType</span><span class="p">(),</span> <span class="kc">True</span><span class="p">),</span> <span class="kc">True</span><span class="p">)])</span> |
| |
| <span class="n">assertSchemaEqual</span><span class="p">(</span><span class="n">s1</span><span class="p">,</span> <span class="n">s2</span><span class="p">)</span> <span class="c1"># pass, schemas are identical</span> |
| </pre></div> |
| </div> |
| </div> |
| </section> |
| <section id="Option-2:-Using-Unit-Test"> |
| <h3>Option 2: Using Unit Test<a class="headerlink" href="#Option-2:-Using-Unit-Test" title="Permalink to this headline">#</a></h3> |
| <p>For more complex testing scenarios, you may want to use a testing framework.</p> |
| <p>One of the most popular testing framework options is unit tests. Let’s walk through how you can use the built-in Python <code class="docutils literal notranslate"><span class="pre">unittest</span></code> library to write PySpark tests.</p> |
| <p>First, you will need a Spark session. You can use the <code class="docutils literal notranslate"><span class="pre">@classmethod</span></code> decorator from the <code class="docutils literal notranslate"><span class="pre">unittest</span></code> package to take care of setting up and tearing down a Spark session.</p> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[15]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">unittest</span> |
| |
| <span class="k">class</span><span class="w"> </span><span class="nc">PySparkTestCase</span><span class="p">(</span><span class="n">unittest</span><span class="o">.</span><span class="n">TestCase</span><span class="p">):</span> |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">setUpClass</span><span class="p">(</span><span class="bp">cls</span><span class="p">):</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"Testing PySpark Example"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">tearDownClass</span><span class="p">(</span><span class="bp">cls</span><span class="p">):</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span> |
| </pre></div> |
| </div> |
| </div> |
| <p>Now let’s write a <code class="docutils literal notranslate"><span class="pre">unittest</span></code> class.</p> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[17]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.testing.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">assertDataFrameEqual</span> |
| |
| <span class="k">class</span><span class="w"> </span><span class="nc">TestTranformation</span><span class="p">(</span><span class="n">PySparkTestCase</span><span class="p">):</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">test_single_space</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">sample_data</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"John D."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">30</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Alice G."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">25</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Bob T."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">35</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Eve A."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">28</span><span class="p">}]</span> |
| |
| <span class="c1"># Create a Spark DataFrame</span> |
| <span class="n">original_df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">sample_data</span><span class="p">)</span> |
| |
| <span class="c1"># Apply the transformation function from before</span> |
| <span class="n">transformed_df</span> <span class="o">=</span> <span class="n">remove_extra_spaces</span><span class="p">(</span><span class="n">original_df</span><span class="p">,</span> <span class="s2">"name"</span><span class="p">)</span> |
| |
| <span class="n">expected_data</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"John D."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">30</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Alice G."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">25</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Bob T."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">35</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Eve A."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">28</span><span class="p">}]</span> |
| |
| <span class="n">expected_df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">expected_data</span><span class="p">)</span> |
| |
| <span class="n">assertDataFrameEqual</span><span class="p">(</span><span class="n">transformed_df</span><span class="p">,</span> <span class="n">expected_df</span><span class="p">)</span> |
| <br/></pre></div> |
| </div> |
| </div> |
| <p>When run, <code class="docutils literal notranslate"><span class="pre">unittest</span></code> will pick up all functions with a name beginning with “test.”</p> |
| </section> |
| <section id="Option-3:-Using-Pytest"> |
| <h3>Option 3: Using Pytest<a class="headerlink" href="#Option-3:-Using-Pytest" title="Permalink to this headline">#</a></h3> |
| <p>We can also write our tests with <code class="docutils literal notranslate"><span class="pre">pytest</span></code>, which is one of the most popular Python testing frameworks.</p> |
| <p>Using a <code class="docutils literal notranslate"><span class="pre">pytest</span></code> fixture allows us to share a spark session across tests, tearing it down when the tests are complete.</p> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[20]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">pytest</span> |
| |
| <span class="nd">@pytest</span><span class="o">.</span><span class="n">fixture</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">spark_fixture</span><span class="p">():</span> |
| <span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"Testing PySpark Example"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="k">yield</span> <span class="n">spark</span> |
| </pre></div> |
| </div> |
| </div> |
| <p>We can then define our tests like this:</p> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[22]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">pytest</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.testing.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">assertDataFrameEqual</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">test_single_space</span><span class="p">(</span><span class="n">spark_fixture</span><span class="p">):</span> |
| <span class="n">sample_data</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"John D."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">30</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Alice G."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">25</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Bob T."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">35</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Eve A."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">28</span><span class="p">}]</span> |
| |
| <span class="c1"># Create a Spark DataFrame</span> |
| <span class="n">original_df</span> <span class="o">=</span> <span class="n">spark_fixture</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">sample_data</span><span class="p">)</span> |
| |
| <span class="c1"># Apply the transformation function from before</span> |
| <span class="n">transformed_df</span> <span class="o">=</span> <span class="n">remove_extra_spaces</span><span class="p">(</span><span class="n">original_df</span><span class="p">,</span> <span class="s2">"name"</span><span class="p">)</span> |
| |
| <span class="n">expected_data</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"John D."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">30</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Alice G."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">25</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Bob T."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">35</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Eve A."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">28</span><span class="p">}]</span> |
| |
| <span class="n">expected_df</span> <span class="o">=</span> <span class="n">spark_fixture</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">expected_data</span><span class="p">)</span> |
| |
| <span class="n">assertDataFrameEqual</span><span class="p">(</span><span class="n">transformed_df</span><span class="p">,</span> <span class="n">expected_df</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| </div> |
| <p>When you run your test file with the <code class="docutils literal notranslate"><span class="pre">pytest</span></code> command, it will pick up all functions that have their name beginning with “test.”</p> |
| </section> |
| </section> |
| <section id="Putting-It-All-Together!"> |
| <h2>Putting It All Together!<a class="headerlink" href="#Putting-It-All-Together!" title="Permalink to this headline">#</a></h2> |
| <p>Let’s see all the steps together, in a Unit Test example.</p> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[25]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># pkg/etl.py</span> |
| <span class="kn">import</span><span class="w"> </span><span class="nn">unittest</span> |
| |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql</span><span class="w"> </span><span class="kn">import</span> <span class="n">SparkSession</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql.functions</span><span class="w"> </span><span class="kn">import</span> <span class="n">col</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql.functions</span><span class="w"> </span><span class="kn">import</span> <span class="n">regexp_replace</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.testing.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">assertDataFrameEqual</span> |
| |
| <span class="c1"># Create a SparkSession</span> |
| <span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"Sample PySpark ETL"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| |
| <span class="n">sample_data</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"John D."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">30</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Alice G."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">25</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Bob T."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">35</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Eve A."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">28</span><span class="p">}]</span> |
| |
| <span class="n">df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">sample_data</span><span class="p">)</span> |
| |
| <span class="c1"># Define DataFrame transformation function</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">remove_extra_spaces</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="n">column_name</span><span class="p">):</span> |
| <span class="c1"># Remove extra spaces from the specified column using regexp_replace</span> |
| <span class="n">df_transformed</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">withColumn</span><span class="p">(</span><span class="n">column_name</span><span class="p">,</span> <span class="n">regexp_replace</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="n">column_name</span><span class="p">),</span> <span class="s2">"</span><span class="se">\\</span><span class="s2">s+"</span><span class="p">,</span> <span class="s2">" "</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="n">df_transformed</span> |
| </pre></div> |
| </div> |
| </div> |
| <div class="nbinput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[26]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># pkg/test_etl.py</span> |
| <span class="kn">import</span><span class="w"> </span><span class="nn">unittest</span> |
| |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql</span><span class="w"> </span><span class="kn">import</span> <span class="n">SparkSession</span> |
| |
| <span class="c1"># Define unit test base class</span> |
| <span class="k">class</span><span class="w"> </span><span class="nc">PySparkTestCase</span><span class="p">(</span><span class="n">unittest</span><span class="o">.</span><span class="n">TestCase</span><span class="p">):</span> |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">setUpClass</span><span class="p">(</span><span class="bp">cls</span><span class="p">):</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"Sample PySpark ETL"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">tearDownClass</span><span class="p">(</span><span class="bp">cls</span><span class="p">):</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span> |
| |
| <span class="c1"># Define unit test</span> |
| <span class="k">class</span><span class="w"> </span><span class="nc">TestTranformation</span><span class="p">(</span><span class="n">PySparkTestCase</span><span class="p">):</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">test_single_space</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">sample_data</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"John D."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">30</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Alice G."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">25</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Bob T."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">35</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Eve A."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">28</span><span class="p">}]</span> |
| |
| <span class="c1"># Create a Spark DataFrame</span> |
| <span class="n">original_df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">sample_data</span><span class="p">)</span> |
| |
| <span class="c1"># Apply the transformation function from before</span> |
| <span class="n">transformed_df</span> <span class="o">=</span> <span class="n">remove_extra_spaces</span><span class="p">(</span><span class="n">original_df</span><span class="p">,</span> <span class="s2">"name"</span><span class="p">)</span> |
| |
| <span class="n">expected_data</span> <span class="o">=</span> <span class="p">[{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"John D."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">30</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Alice G."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">25</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Bob T."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">35</span><span class="p">},</span> |
| <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="s2">"Eve A."</span><span class="p">,</span> <span class="s2">"age"</span><span class="p">:</span> <span class="mi">28</span><span class="p">}]</span> |
| |
| <span class="n">expected_df</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">expected_data</span><span class="p">)</span> |
| |
| <span class="n">assertDataFrameEqual</span><span class="p">(</span><span class="n">transformed_df</span><span class="p">,</span> <span class="n">expected_df</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| </div> |
| <div class="nbinput docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[27]: |
| </pre></div> |
| </div> |
| <div class="input_area highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">unittest</span><span class="o">.</span><span class="n">main</span><span class="p">(</span><span class="n">argv</span><span class="o">=</span><span class="p">[</span><span class="s1">''</span><span class="p">],</span> <span class="n">verbosity</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">exit</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| </div> |
| <div class="nboutput docutils container"> |
| <div class="prompt empty docutils container"> |
| </div> |
| <div class="output_area docutils container"> |
| <div class="highlight"><pre> |
| Ran 1 test in 1.734s |
| |
| OK |
| </pre></div></div> |
| </div> |
| <div class="nboutput nblast docutils container"> |
| <div class="prompt highlight-none notranslate"><div class="highlight"><pre><span></span>[27]: |
| </pre></div> |
| </div> |
| <div class="output_area docutils container"> |
| <div class="highlight"><pre> |
| <unittest.main.TestProgram at 0x174539db0> |
| </pre></div></div> |
| </div> |
| </section> |
| </section> |
| |
| |
| </article> |
| |
| |
| |
| <footer class="bd-footer-article"> |
| |
| <div class="footer-article-items footer-article__inner"> |
| |
| <div class="footer-article-item"><!-- Previous / next buttons --> |
| <div class="prev-next-area"> |
| <a class="left-prev" |
| href="quickstart_ps.html" |
| title="previous page"> |
| <i class="fa-solid fa-angle-left"></i> |
| <div class="prev-next-info"> |
| <p class="prev-next-subtitle">previous</p> |
| <p class="prev-next-title">Quickstart: Pandas API on Spark</p> |
| </div> |
| </a> |
| <a class="right-next" |
| href="../tutorial/index.html" |
| title="next page"> |
| <div class="prev-next-info"> |
| <p class="prev-next-subtitle">next</p> |
| <p class="prev-next-title">Tutorials</p> |
| </div> |
| <i class="fa-solid fa-angle-right"></i> |
| </a> |
| </div></div> |
| |
| </div> |
| |
| </footer> |
| |
| </div> |
| |
| |
| |
| <div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner"> |
| |
| <div class="sidebar-secondary-item"> |
| <div class="page-toc tocsection onthispage"> |
| <i class="fa-solid fa-list"></i> On this page |
| </div> |
| <nav class="bd-toc-nav page-toc"> |
| <ul class="visible nav section-nav flex-column"> |
| <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#Build-a-PySpark-Application">Build a PySpark Application</a></li> |
| <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#Testing-your-PySpark-Application">Testing your PySpark Application</a><ul class="nav section-nav flex-column"> |
| <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#Option-1:-Using-Only-PySpark-Built-in-Test-Utility-Functions">Option 1: Using Only PySpark Built-in Test Utility Functions</a></li> |
| <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#Option-2:-Using-Unit-Test">Option 2: Using Unit Test</a></li> |
| <li class="toc-h3 nav-item toc-entry"><a class="reference internal nav-link" href="#Option-3:-Using-Pytest">Option 3: Using Pytest</a></li> |
| </ul> |
| </li> |
| <li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#Putting-It-All-Together!">Putting It All Together!</a></li> |
| </ul> |
| </nav></div> |
| |
| <div class="sidebar-secondary-item"> |
| <div class="tocsection sourcelink"> |
| <a href="../_sources/getting_started/testing_pyspark.ipynb.txt"> |
| <i class="fa-solid fa-file-lines"></i> Show Source |
| </a> |
| </div> |
| </div> |
| |
| </div></div> |
| |
| |
| </div> |
| <footer class="bd-footer-content"> |
| |
| </footer> |
| |
| </main> |
| </div> |
| </div> |
| |
| <!-- Scripts loaded after <body> so the DOM is not blocked --> |
| <script src="../_static/scripts/bootstrap.js?digest=e353d410970836974a52"></script> |
| <script src="../_static/scripts/pydata-sphinx-theme.js?digest=e353d410970836974a52"></script> |
| |
| <footer class="bd-footer"> |
| <div class="bd-footer__inner bd-page-width"> |
| |
| <div class="footer-items__start"> |
| |
| <div class="footer-item"><p class="copyright"> |
| Copyright @ 2025 The Apache Software Foundation, Licensed under the <a href="https://www.apache.org/licenses/LICENSE-2.0">Apache License, Version 2.0</a>. |
| </p></div> |
| |
| <div class="footer-item"> |
| <p class="sphinx-version"> |
| Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 4.5.0. |
| <br/> |
| </p> |
| </div> |
| |
| </div> |
| |
| |
| <div class="footer-items__end"> |
| |
| <div class="footer-item"><p class="theme-version"> |
| Built with the <a href="https://pydata-sphinx-theme.readthedocs.io/en/stable/index.html">PyData Sphinx Theme</a> 0.13.3. |
| </p></div> |
| |
| </div> |
| |
| </div> |
| |
| </footer> |
| </body> |
| </html> |
