| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.pandas.Series.apply — PySpark 3.3.4 documentation</title> |
| |
| <link rel="stylesheet" href="../../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css"> |
| |
| |
| <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" |
| href="../../../_static/vendor/open-sans_all/1.44.1/index.css"> |
| <link rel="stylesheet" |
| href="../../../_static/vendor/lato_latin-ext/1.44.1/index.css"> |
| |
| |
| <link rel="stylesheet" href="../../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/js/index.3da636dd464baa7582d2.js"> |
| |
| <script id="documentation_options" data-url_root="../../../" 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/language_data.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 async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/reference/pyspark.pandas/api/pyspark.pandas.Series.apply.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <link rel="next" title="pyspark.pandas.Series.agg" href="pyspark.pandas.Series.agg.html" /> |
| <link rel="prev" title="pyspark.pandas.Series.dot" href="pyspark.pandas.Series.dot.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="en" /> |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"> |
| <div class="container-xl"> |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo" /> |
| |
| </a> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| <div id="navbar-menu" class="col-lg-9 collapse navbar-collapse"> |
| <ul id="navbar-main-elements" class="navbar-nav mr-auto"> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../getting_started/index.html">Getting Started</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../user_guide/index.html">User Guide</a> |
| </li> |
| |
| <li class="nav-item active"> |
| <a class="nav-link" href="../../index.html">API Reference</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../development/index.html">Development</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../migration_guide/index.html">Migration Guide</a> |
| </li> |
| |
| |
| </ul> |
| |
| |
| |
| |
| <ul class="navbar-nav"> |
| |
| |
| </ul> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| <div class="col-12 col-md-3 bd-sidebar"><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"> |
| |
| |
| <ul class="nav bd-sidenav"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <li class=""> |
| <a href="../../pyspark.sql/index.html">Spark SQL</a> |
| </li> |
| |
| |
| |
| |
| <li class="active"> |
| <a href="../index.html">Pandas API on Spark</a> |
| <ul> |
| |
| <li class=""> |
| <a href="../io.html">Input/Output</a> |
| </li> |
| |
| <li class=""> |
| <a href="../general_functions.html">General functions</a> |
| </li> |
| |
| <li class="active"> |
| <a href="../series.html">Series</a> |
| </li> |
| |
| <li class=""> |
| <a href="../frame.html">DataFrame</a> |
| </li> |
| |
| <li class=""> |
| <a href="../indexing.html">Index objects</a> |
| </li> |
| |
| <li class=""> |
| <a href="../window.html">Window</a> |
| </li> |
| |
| <li class=""> |
| <a href="../groupby.html">GroupBy</a> |
| </li> |
| |
| <li class=""> |
| <a href="../ml.html">Machine Learning utilities</a> |
| </li> |
| |
| <li class=""> |
| <a href="../extensions.html">Extensions</a> |
| </li> |
| |
| </ul> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../../pyspark.ss/index.html">Structured Streaming</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../../pyspark.ml.html">MLlib (DataFrame-based)</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../../pyspark.streaming.html">Spark Streaming</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../../pyspark.mllib.html">MLlib (RDD-based)</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../../pyspark.html">Spark Core</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../../pyspark.resource.html">Resource Management</a> |
| </li> |
| |
| |
| |
| |
| |
| |
| |
| |
| </ul> |
| |
| </nav> |
| </div> |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| |
| <nav id="bd-toc-nav"> |
| <ul class="nav section-nav flex-column"> |
| |
| </ul> |
| </nav> |
| |
| |
| |
| </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> |
| |
| <div class="section" id="pyspark-pandas-series-apply"> |
| <h1>pyspark.pandas.Series.apply<a class="headerlink" href="#pyspark-pandas-series-apply" title="Permalink to this headline">¶</a></h1> |
| <dl class="py method"> |
| <dt id="pyspark.pandas.Series.apply"> |
| <code class="sig-prename descclassname">Series.</code><code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">func</span><span class="p">:</span> <span class="n">Callable</span></em>, <em class="sig-param"><span class="n">args</span><span class="p">:</span> <span class="n">Sequence<span class="p">[</span>Any<span class="p">]</span></span> <span class="o">=</span> <span class="default_value">()</span></em>, <em class="sig-param"><span class="o">**</span><span class="n">kwds</span><span class="p">:</span> <span class="n">Any</span></em><span class="sig-paren">)</span> → pyspark.pandas.series.Series<a class="reference internal" href="../../../_modules/pyspark/pandas/series.html#Series.apply"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.pandas.Series.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Invoke function on values of Series.</p> |
| <p>Can be a Python function that only works on the Series.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>this API executes the function once to infer the type which is |
| potentially expensive, for instance, when the dataset is created after |
| aggregations or sorting.</p> |
| <p>To avoid this, specify return type in <code class="docutils literal notranslate"><span class="pre">func</span></code>, for instance, as below:</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">def</span> <span class="nf">square</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">x</span> <span class="o">**</span> <span class="mi">2</span> |
| </pre></div> |
| </div> |
| <p>pandas-on-Spark uses return type hint and does not try to infer the type.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl class="simple"> |
| <dt><strong>func</strong><span class="classifier">function</span></dt><dd><p>Python function to apply. Note that type hint for return type is required.</p> |
| </dd> |
| <dt><strong>args</strong><span class="classifier">tuple</span></dt><dd><p>Positional arguments passed to func after the series value.</p> |
| </dd> |
| <dt><strong>**kwds</strong></dt><dd><p>Additional keyword arguments passed to func.</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt>Series</dt><dd></dd> |
| </dl> |
| </dd> |
| </dl> |
| <div class="admonition seealso"> |
| <p class="admonition-title">See also</p> |
| <dl class="simple"> |
| <dt><a class="reference internal" href="pyspark.pandas.Series.aggregate.html#pyspark.pandas.Series.aggregate" title="pyspark.pandas.Series.aggregate"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Series.aggregate</span></code></a></dt><dd><p>Only perform aggregating type operations.</p> |
| </dd> |
| <dt><a class="reference internal" href="pyspark.pandas.Series.transform.html#pyspark.pandas.Series.transform" title="pyspark.pandas.Series.transform"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Series.transform</span></code></a></dt><dd><p>Only perform transforming type operations.</p> |
| </dd> |
| <dt><a class="reference internal" href="pyspark.pandas.DataFrame.apply.html#pyspark.pandas.DataFrame.apply" title="pyspark.pandas.DataFrame.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">DataFrame.apply</span></code></a></dt><dd><p>The equivalent function for DataFrame.</p> |
| </dd> |
| </dl> |
| </div> |
| <p class="rubric">Examples</p> |
| <p>Create a Series with typical summer temperatures for each city.</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">s</span> <span class="o">=</span> <span class="n">ps</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="mi">20</span><span class="p">,</span> <span class="mi">21</span><span class="p">,</span> <span class="mi">12</span><span class="p">],</span> |
| <span class="gp">... </span> <span class="n">index</span><span class="o">=</span><span class="p">[</span><span class="s1">'London'</span><span class="p">,</span> <span class="s1">'New York'</span><span class="p">,</span> <span class="s1">'Helsinki'</span><span class="p">])</span> |
| <span class="gp">>>> </span><span class="n">s</span> |
| <span class="go">London 20</span> |
| <span class="go">New York 21</span> |
| <span class="go">Helsinki 12</span> |
| <span class="go">dtype: int64</span> |
| </pre></div> |
| </div> |
| <p>Square the values by defining a function and passing it as an |
| argument to <code class="docutils literal notranslate"><span class="pre">apply()</span></code>.</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">def</span> <span class="nf">square</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">int64</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">x</span> <span class="o">**</span> <span class="mi">2</span> |
| <span class="gp">>>> </span><span class="n">s</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">square</span><span class="p">)</span> |
| <span class="go">London 400</span> |
| <span class="go">New York 441</span> |
| <span class="go">Helsinki 144</span> |
| <span class="go">dtype: int64</span> |
| </pre></div> |
| </div> |
| <p>Define a custom function that needs additional positional |
| arguments and pass these additional arguments using the |
| <code class="docutils literal notranslate"><span class="pre">args</span></code> keyword</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">def</span> <span class="nf">subtract_custom_value</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">custom_value</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">int64</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">x</span> <span class="o">-</span> <span class="n">custom_value</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">s</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">subtract_custom_value</span><span class="p">,</span> <span class="n">args</span><span class="o">=</span><span class="p">(</span><span class="mi">5</span><span class="p">,))</span> |
| <span class="go">London 15</span> |
| <span class="go">New York 16</span> |
| <span class="go">Helsinki 7</span> |
| <span class="go">dtype: int64</span> |
| </pre></div> |
| </div> |
| <p>Define a custom function that takes keyword arguments |
| and pass these arguments to <code class="docutils literal notranslate"><span class="pre">apply</span></code></p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">def</span> <span class="nf">add_custom_values</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">int64</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">for</span> <span class="n">month</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="n">x</span> <span class="o">+=</span> <span class="n">kwargs</span><span class="p">[</span><span class="n">month</span><span class="p">]</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">x</span> |
| </pre></div> |
| </div> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">s</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">add_custom_values</span><span class="p">,</span> <span class="n">june</span><span class="o">=</span><span class="mi">30</span><span class="p">,</span> <span class="n">july</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="n">august</span><span class="o">=</span><span class="mi">25</span><span class="p">)</span> |
| <span class="go">London 95</span> |
| <span class="go">New York 96</span> |
| <span class="go">Helsinki 87</span> |
| <span class="go">dtype: int64</span> |
| </pre></div> |
| </div> |
| <p>Use a function from the Numpy library</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">def</span> <span class="nf">numpy_log</span><span class="p">(</span><span class="n">col</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="n">col</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">s</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">numpy_log</span><span class="p">)</span> |
| <span class="go">London 2.995732</span> |
| <span class="go">New York 3.044522</span> |
| <span class="go">Helsinki 2.484907</span> |
| <span class="go">dtype: float64</span> |
| </pre></div> |
| </div> |
| <p>You can omit the type hint and let pandas-on-Spark infer its type.</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">s</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">log</span><span class="p">)</span> |
| <span class="go">London 2.995732</span> |
| <span class="go">New York 3.044522</span> |
| <span class="go">Helsinki 2.484907</span> |
| <span class="go">dtype: float64</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| <a class='left-prev' id="prev-link" href="pyspark.pandas.Series.dot.html" title="previous page">pyspark.pandas.Series.dot</a> |
| <a class='right-next' id="next-link" href="pyspark.pandas.Series.agg.html" title="next page">pyspark.pandas.Series.agg</a> |
| |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| |
| <script src="../../../_static/js/index.3da636dd464baa7582d2.js"></script> |
| |
| |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| <p> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
