| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.RDD.combineByKey — PySpark 3.4.3 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/api/pyspark.RDD.combineByKey.html" /> |
| <link rel="search" title="Search" href="../../search.html" /> |
| <link rel="next" title="pyspark.RDD.context" href="pyspark.RDD.context.html" /> |
| <link rel="prev" title="pyspark.RDD.collectWithJobGroup" href="pyspark.RDD.collectWithJobGroup.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="../../index.html">Overview</a> |
| </li> |
| |
| <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 Guides</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 Guides</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=""> |
| <a href="../pyspark.pandas/index.html">Pandas API on Spark</a> |
| </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 (Legacy)</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.mllib.html">MLlib (RDD-based)</a> |
| </li> |
| |
| |
| |
| <li class="active"> |
| <a href="../pyspark.html">Spark Core</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.resource.html">Resource Management</a> |
| </li> |
| |
| |
| |
| <li class=""> |
| <a href="../pyspark.errors.html">Errors</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-rdd-combinebykey"> |
| <h1>pyspark.RDD.combineByKey<a class="headerlink" href="#pyspark-rdd-combinebykey" title="Permalink to this headline">¶</a></h1> |
| <dl class="py method"> |
| <dt id="pyspark.RDD.combineByKey"> |
| <code class="sig-prename descclassname">RDD.</code><code class="sig-name descname">combineByKey</code><span class="sig-paren">(</span><em class="sig-param">createCombiner: Callable[[V], U], mergeValue: Callable[[U, V], U], mergeCombiners: Callable[[U, U], U], numPartitions: Optional[int] = None, partitionFunc: Callable[[K], int] = <function portable_hash></em><span class="sig-paren">)</span> → pyspark.rdd.RDD<span class="p">[</span>Tuple<span class="p">[</span>K<span class="p">, </span>U<span class="p">]</span><span class="p">]</span><a class="reference internal" href="../../_modules/pyspark/rdd.html#RDD.combineByKey"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.RDD.combineByKey" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Generic function to combine the elements for each key using a custom |
| set of aggregation functions.</p> |
| <p>Turns an RDD[(K, V)] into a result of type RDD[(K, C)], for a “combined |
| type” C.</p> |
| <p>To avoid memory allocation, both mergeValue and mergeCombiners are allowed to |
| modify and return their first argument instead of creating a new C.</p> |
| <p>In addition, users can control the partitioning of the output RDD.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 0.7.0.</span></p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>createCombiner</strong><span class="classifier">function</span></dt><dd><p>a function to turns a V into a C</p> |
| </dd> |
| <dt><strong>mergeValue</strong><span class="classifier">function</span></dt><dd><p>a function to merge a V into a C</p> |
| </dd> |
| <dt><strong>mergeCombiners</strong><span class="classifier">function</span></dt><dd><p>a function to combine two C’s into a single one</p> |
| </dd> |
| <dt><strong>numPartitions</strong><span class="classifier">int, optional</span></dt><dd><p>the number of partitions in new <a class="reference internal" href="pyspark.RDD.html#pyspark.RDD" title="pyspark.RDD"><code class="xref py py-class docutils literal notranslate"><span class="pre">RDD</span></code></a></p> |
| </dd> |
| <dt><strong>partitionFunc</strong><span class="classifier">function, optional, default <cite>portable_hash</cite></span></dt><dd><p>function to compute the partition index</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><a class="reference internal" href="pyspark.RDD.html#pyspark.RDD" title="pyspark.RDD"><code class="xref py py-class docutils literal notranslate"><span class="pre">RDD</span></code></a></dt><dd><p>a <a class="reference internal" href="pyspark.RDD.html#pyspark.RDD" title="pyspark.RDD"><code class="xref py py-class docutils literal notranslate"><span class="pre">RDD</span></code></a> containing the keys and the aggregated result for each key</p> |
| </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.RDD.reduceByKey.html#pyspark.RDD.reduceByKey" title="pyspark.RDD.reduceByKey"><code class="xref py py-meth docutils literal notranslate"><span class="pre">RDD.reduceByKey()</span></code></a></dt><dd></dd> |
| <dt><a class="reference internal" href="pyspark.RDD.aggregateByKey.html#pyspark.RDD.aggregateByKey" title="pyspark.RDD.aggregateByKey"><code class="xref py py-meth docutils literal notranslate"><span class="pre">RDD.aggregateByKey()</span></code></a></dt><dd></dd> |
| <dt><a class="reference internal" href="pyspark.RDD.foldByKey.html#pyspark.RDD.foldByKey" title="pyspark.RDD.foldByKey"><code class="xref py py-meth docutils literal notranslate"><span class="pre">RDD.foldByKey()</span></code></a></dt><dd></dd> |
| <dt><a class="reference internal" href="pyspark.RDD.groupByKey.html#pyspark.RDD.groupByKey" title="pyspark.RDD.groupByKey"><code class="xref py py-meth docutils literal notranslate"><span class="pre">RDD.groupByKey()</span></code></a></dt><dd></dd> |
| </dl> |
| </div> |
| <p class="rubric">Notes</p> |
| <dl class="simple"> |
| <dt>V and C can be different – for example, one might group an RDD of type</dt><dd><p>(Int, Int) into an RDD of type (Int, List[Int]).</p> |
| </dd> |
| </dl> |
| <p class="rubric">Examples</p> |
| <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">rdd</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">([(</span><span class="s2">"a"</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="p">(</span><span class="s2">"b"</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="p">(</span><span class="s2">"a"</span><span class="p">,</span> <span class="mi">2</span><span class="p">)])</span> |
| <span class="gp">>>> </span><span class="k">def</span> <span class="nf">to_list</span><span class="p">(</span><span class="n">a</span><span class="p">):</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="p">[</span><span class="n">a</span><span class="p">]</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="k">def</span> <span class="nf">append</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">):</span> |
| <span class="gp">... </span> <span class="n">a</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">b</span><span class="p">)</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">a</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="k">def</span> <span class="nf">extend</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">):</span> |
| <span class="gp">... </span> <span class="n">a</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">b</span><span class="p">)</span> |
| <span class="gp">... </span> <span class="k">return</span> <span class="n">a</span> |
| <span class="gp">...</span> |
| <span class="gp">>>> </span><span class="nb">sorted</span><span class="p">(</span><span class="n">rdd</span><span class="o">.</span><span class="n">combineByKey</span><span class="p">(</span><span class="n">to_list</span><span class="p">,</span> <span class="n">append</span><span class="p">,</span> <span class="n">extend</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">())</span> |
| <span class="go">[('a', [1, 2]), ('b', [1])]</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| <a class='left-prev' id="prev-link" href="pyspark.RDD.collectWithJobGroup.html" title="previous page">pyspark.RDD.collectWithJobGroup</a> |
| <a class='right-next' id="next-link" href="pyspark.RDD.context.html" title="next page">pyspark.RDD.context</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> |
