| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.sql.functions.session_window — 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/pyspark.sql/api/pyspark.sql.functions.session_window.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <link rel="next" title="pyspark.sql.functions.timestamp_seconds" href="pyspark.sql.functions.timestamp_seconds.html" /> |
| <link rel="prev" title="pyspark.sql.functions.window" href="pyspark.sql.functions.window.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="active"> |
| <a href="../index.html">Spark SQL</a> |
| <ul> |
| |
| <li class=""> |
| <a href="../core_classes.html">Core Classes</a> |
| </li> |
| |
| <li class=""> |
| <a href="../spark_session.html">Spark Session</a> |
| </li> |
| |
| <li class=""> |
| <a href="../configuration.html">Configuration</a> |
| </li> |
| |
| <li class=""> |
| <a href="../io.html">Input/Output</a> |
| </li> |
| |
| <li class=""> |
| <a href="../dataframe.html">DataFrame</a> |
| </li> |
| |
| <li class=""> |
| <a href="../column.html">Column</a> |
| </li> |
| |
| <li class=""> |
| <a href="../data_types.html">Data Types</a> |
| </li> |
| |
| <li class=""> |
| <a href="../row.html">Row</a> |
| </li> |
| |
| <li class="active"> |
| <a href="../functions.html">Functions</a> |
| </li> |
| |
| <li class=""> |
| <a href="../window.html">Window</a> |
| </li> |
| |
| <li class=""> |
| <a href="../grouping.html">Grouping</a> |
| </li> |
| |
| <li class=""> |
| <a href="../catalog.html">Catalog</a> |
| </li> |
| |
| <li class=""> |
| <a href="../avro.html">Avro</a> |
| </li> |
| |
| <li class=""> |
| <a href="../observation.html">Observation</a> |
| </li> |
| |
| <li class=""> |
| <a href="../udf.html">UDF</a> |
| </li> |
| |
| <li class=""> |
| <a href="../protobuf.html">Protobuf</a> |
| </li> |
| |
| </ul> |
| </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=""> |
| <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-sql-functions-session-window"> |
| <h1>pyspark.sql.functions.session_window<a class="headerlink" href="#pyspark-sql-functions-session-window" title="Permalink to this headline">¶</a></h1> |
| <dl class="py function"> |
| <dt id="pyspark.sql.functions.session_window"> |
| <code class="sig-prename descclassname">pyspark.sql.functions.</code><code class="sig-name descname">session_window</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">timeColumn</span><span class="p">:</span> <span class="n">ColumnOrName</span></em>, <em class="sig-param"><span class="n">gapDuration</span><span class="p">:</span> <span class="n">Union<span class="p">[</span>pyspark.sql.column.Column<span class="p">, </span>str<span class="p">]</span></span></em><span class="sig-paren">)</span> → pyspark.sql.column.Column<a class="reference internal" href="../../../_modules/pyspark/sql/functions.html#session_window"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#pyspark.sql.functions.session_window" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Generates session window given a timestamp specifying column. |
| Session window is one of dynamic windows, which means the length of window is varying |
| according to the given inputs. The length of session window is defined as “the timestamp |
| of latest input of the session + gap duration”, so when the new inputs are bound to the |
| current session window, the end time of session window can be expanded according to the new |
| inputs. |
| Windows can support microsecond precision. Windows in the order of months are not supported. |
| For a streaming query, you may use the function <cite>current_timestamp</cite> to generate windows on |
| processing time. |
| gapDuration is provided as strings, e.g. ‘1 second’, ‘1 day 12 hours’, ‘2 minutes’. Valid |
| interval strings are ‘week’, ‘day’, ‘hour’, ‘minute’, ‘second’, ‘millisecond’, ‘microsecond’. |
| It could also be a Column which can be evaluated to gap duration dynamically based on the |
| input row. |
| The output column will be a struct called ‘session_window’ by default with the nested columns |
| ‘start’ and ‘end’, where ‘start’ and ‘end’ will be of <a class="reference internal" href="pyspark.sql.types.TimestampType.html#pyspark.sql.types.TimestampType" title="pyspark.sql.types.TimestampType"><code class="xref py py-class docutils literal notranslate"><span class="pre">pyspark.sql.types.TimestampType</span></code></a>.</p> |
| <div class="versionadded"> |
| <p><span class="versionmodified added">New in version 3.2.0.</span></p> |
| </div> |
| <div class="versionchanged"> |
| <p><span class="versionmodified changed">Changed in version 3.4.0: </span>Supports Spark Connect.</p> |
| </div> |
| <dl class="field-list"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><dl> |
| <dt><strong>timeColumn</strong><span class="classifier"><a class="reference internal" href="pyspark.sql.Column.html#pyspark.sql.Column" title="pyspark.sql.Column"><code class="xref py py-class docutils literal notranslate"><span class="pre">Column</span></code></a> or str</span></dt><dd><p>The column name or column to use as the timestamp for windowing by time. |
| The time column must be of TimestampType or TimestampNTZType.</p> |
| </dd> |
| <dt><strong>gapDuration</strong><span class="classifier"><a class="reference internal" href="pyspark.sql.Column.html#pyspark.sql.Column" title="pyspark.sql.Column"><code class="xref py py-class docutils literal notranslate"><span class="pre">Column</span></code></a> or str</span></dt><dd><p>A Python string literal or column specifying the timeout of the session. It could be |
| static value, e.g. <cite>10 minutes</cite>, <cite>1 second</cite>, or an expression/UDF that specifies gap |
| duration dynamically based on the input row.</p> |
| </dd> |
| </dl> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><dl class="simple"> |
| <dt><a class="reference internal" href="pyspark.sql.Column.html#pyspark.sql.Column" title="pyspark.sql.Column"><code class="xref py py-class docutils literal notranslate"><span class="pre">Column</span></code></a></dt><dd><p>the column for computed results.</p> |
| </dd> |
| </dl> |
| </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">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="s2">"2016-03-11 09:00:07"</span><span class="p">,</span> <span class="mi">1</span><span class="p">)])</span><span class="o">.</span><span class="n">toDF</span><span class="p">(</span><span class="s2">"date"</span><span class="p">,</span> <span class="s2">"val"</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">w</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="n">session_window</span><span class="p">(</span><span class="s2">"date"</span><span class="p">,</span> <span class="s2">"5 seconds"</span><span class="p">))</span><span class="o">.</span><span class="n">agg</span><span class="p">(</span><span class="nb">sum</span><span class="p">(</span><span class="s2">"val"</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"sum"</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="n">w</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">w</span><span class="o">.</span><span class="n">session_window</span><span class="o">.</span><span class="n">start</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="s2">"string"</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"start"</span><span class="p">),</span> |
| <span class="gp">... </span> <span class="n">w</span><span class="o">.</span><span class="n">session_window</span><span class="o">.</span><span class="n">end</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="s2">"string"</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"end"</span><span class="p">),</span> <span class="s2">"sum"</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span> |
| <span class="go">[Row(start='2016-03-11 09:00:07', end='2016-03-11 09:00:12', sum=1)]</span> |
| <span class="gp">>>> </span><span class="n">w</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">groupBy</span><span class="p">(</span><span class="n">session_window</span><span class="p">(</span><span class="s2">"date"</span><span class="p">,</span> <span class="n">lit</span><span class="p">(</span><span class="s2">"5 seconds"</span><span class="p">)))</span><span class="o">.</span><span class="n">agg</span><span class="p">(</span><span class="nb">sum</span><span class="p">(</span><span class="s2">"val"</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"sum"</span><span class="p">))</span> |
| <span class="gp">>>> </span><span class="n">w</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">w</span><span class="o">.</span><span class="n">session_window</span><span class="o">.</span><span class="n">start</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="s2">"string"</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"start"</span><span class="p">),</span> |
| <span class="gp">... </span> <span class="n">w</span><span class="o">.</span><span class="n">session_window</span><span class="o">.</span><span class="n">end</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="s2">"string"</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="s2">"end"</span><span class="p">),</span> <span class="s2">"sum"</span><span class="p">)</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span> |
| <span class="go">[Row(start='2016-03-11 09:00:07', end='2016-03-11 09:00:12', sum=1)]</span> |
| </pre></div> |
| </div> |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| <a class='left-prev' id="prev-link" href="pyspark.sql.functions.window.html" title="previous page">pyspark.sql.functions.window</a> |
| <a class='right-next' id="next-link" href="pyspark.sql.functions.timestamp_seconds.html" title="next page">pyspark.sql.functions.timestamp_seconds</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> |