Google Git
Sign in
apache / spark-website / 77b22e9b52e4b9406f14096c2c09f6c602f0987b / . / site / docs / 3.3.3 / api / python / _modules / pyspark / pandas / extensions.html
blob: 133f598f9bc801dc2114a08b7b07f4e526ca914b [file] [log] [blame]
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<title>pyspark.pandas.extensions &#8212; PySpark 3.3.3 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/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/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/_modules/pyspark/pandas/extensions.html" />
<link rel="search" title="Search" href="../../../search.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 ">
<a class="nav-link" href="../../../reference/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">
</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>
<h1>Source code for pyspark.pandas.extensions</h1><div class="highlight"><pre>
<span></span><span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c1"># contributor license agreements. See the NOTICE file distributed with</span>
<span class="c1"># this work for additional information regarding copyright ownership.</span>
<span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c1"># (the &quot;License&quot;); you may not use this file except in compliance with</span>
<span class="c1"># the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Callable</span><span class="p">,</span> <span class="n">Generic</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Type</span><span class="p">,</span> <span class="n">Union</span><span class="p">,</span> <span class="n">TYPE_CHECKING</span>
<span class="kn">import</span> <span class="nn">warnings</span>
<span class="kn">from</span> <span class="nn">pyspark.pandas._typing</span> <span class="kn">import</span> <span class="n">T</span>
<span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">pyspark.pandas.frame</span> <span class="kn">import</span> <span class="n">DataFrame</span>
<span class="kn">from</span> <span class="nn">pyspark.pandas.indexes</span> <span class="kn">import</span> <span class="n">Index</span>
<span class="kn">from</span> <span class="nn">pyspark.pandas.series</span> <span class="kn">import</span> <span class="n">Series</span>
<span class="k">class</span> <span class="nc">CachedAccessor</span><span class="p">(</span><span class="n">Generic</span><span class="p">[</span><span class="n">T</span><span class="p">]):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Custom property-like object.</span>
<span class="sd"> A descriptor for caching accessors:</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> name : str</span>
<span class="sd"> Namespace that accessor&#39;s methods, properties, etc will be accessed under, e.g. &quot;foo&quot; for a</span>
<span class="sd"> dataframe accessor yields the accessor ``df.foo``</span>
<span class="sd"> accessor: cls</span>
<span class="sd"> Class with the extension methods.</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> For accessor, the class&#39;s __init__ method assumes that you are registering an accessor for one</span>
<span class="sd"> of ``Series``, ``DataFrame``, or ``Index``.</span>
<span class="sd"> This object is not meant to be instantiated directly. Instead, use register_dataframe_accessor,</span>
<span class="sd"> register_series_accessor, or register_index_accessor.</span>
<span class="sd"> The pandas-on-Spark accessor is modified based on pandas.core.accessor.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">accessor</span><span class="p">:</span> <span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_name</span> <span class="o">=</span> <span class="n">name</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_accessor</span> <span class="o">=</span> <span class="n">accessor</span>
<span class="k">def</span> <span class="fm">__get__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span> <span class="n">obj</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Union</span><span class="p">[</span><span class="s2">&quot;DataFrame&quot;</span><span class="p">,</span> <span class="s2">&quot;Series&quot;</span><span class="p">,</span> <span class="s2">&quot;Index&quot;</span><span class="p">]],</span> <span class="bp">cls</span><span class="p">:</span> <span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Union</span><span class="p">[</span><span class="n">T</span><span class="p">,</span> <span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]]:</span>
<span class="k">if</span> <span class="n">obj</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_accessor</span>
<span class="n">accessor_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_accessor</span><span class="p">(</span><span class="n">obj</span><span class="p">)</span> <span class="c1"># type: ignore[call-arg]</span>
<span class="nb">object</span><span class="o">.</span><span class="fm">__setattr__</span><span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">,</span> <span class="n">accessor_obj</span><span class="p">)</span>
<span class="k">return</span> <span class="n">accessor_obj</span>
<span class="k">def</span> <span class="nf">_register_accessor</span><span class="p">(</span>
<span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="bp">cls</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">Type</span><span class="p">[</span><span class="s2">&quot;DataFrame&quot;</span><span class="p">],</span> <span class="n">Type</span><span class="p">[</span><span class="s2">&quot;Series&quot;</span><span class="p">],</span> <span class="n">Type</span><span class="p">[</span><span class="s2">&quot;Index&quot;</span><span class="p">]]</span>
<span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]],</span> <span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Register a custom accessor on {klass} objects.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> name : str</span>
<span class="sd"> Name under which the accessor should be registered. A warning is issued if this name</span>
<span class="sd"> conflicts with a preexisting attribute.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> callable</span>
<span class="sd"> A class decorator.</span>
<span class="sd"> See Also</span>
<span class="sd"> --------</span>
<span class="sd"> register_dataframe_accessor: Register a custom accessor on DataFrame objects</span>
<span class="sd"> register_series_accessor: Register a custom accessor on Series objects</span>
<span class="sd"> register_index_accessor: Register a custom accessor on Index objects</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> When accessed, your accessor will be initialiazed with the pandas-on-Spark object the user</span>
<span class="sd"> is interacting with. The code signature must be:</span>
<span class="sd"> .. code-block:: python</span>
<span class="sd"> def __init__(self, pandas_on_spark_obj):</span>
<span class="sd"> # constructor logic</span>
<span class="sd"> ...</span>
<span class="sd"> In the pandas API, if data passed to your accessor has an incorrect dtype, it&#39;s recommended to</span>
<span class="sd"> raise an ``AttributeError`` for consistency purposes. In pandas-on-Spark, ``ValueError`` is more</span>
<span class="sd"> frequently used to annotate when a value&#39;s datatype is unexpected for a given method/function.</span>
<span class="sd"> Ultimately, you can structure this however you like, but pandas-on-Spark would likely do</span>
<span class="sd"> something like this:</span>
<span class="sd"> &gt;&gt;&gt; ps.Series([&#39;a&#39;, &#39;b&#39;]).dt</span>
<span class="sd"> ...</span>
<span class="sd"> Traceback (most recent call last):</span>
<span class="sd"> ...</span>
<span class="sd"> ValueError: Cannot call DatetimeMethods on type StringType()</span>
<span class="sd"> Note: This function is not meant to be used directly - instead, use register_dataframe_accessor,</span>
<span class="sd"> register_series_accessor, or register_index_accessor.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="nf">decorator</span><span class="p">(</span><span class="n">accessor</span><span class="p">:</span> <span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]:</span>
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
<span class="n">msg</span> <span class="o">=</span> <span class="p">(</span>
<span class="s2">&quot;registration of accessor </span><span class="si">{0}</span><span class="s2"> under name &#39;</span><span class="si">{1}</span><span class="s2">&#39; for type </span><span class="si">{2}</span><span class="s2"> is overriding &quot;</span>
<span class="s2">&quot;a preexisting attribute with the same name.&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">accessor</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)</span>
<span class="p">)</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
<span class="n">msg</span><span class="p">,</span>
<span class="ne">UserWarning</span><span class="p">,</span>
<span class="n">stacklevel</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span>
<span class="p">)</span>
<span class="nb">setattr</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">CachedAccessor</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">accessor</span><span class="p">))</span>
<span class="k">return</span> <span class="n">accessor</span>
<span class="k">return</span> <span class="n">decorator</span>
<div class="viewcode-block" id="register_dataframe_accessor"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.extensions.register_dataframe_accessor.html#pyspark.pandas.extensions.register_dataframe_accessor">[docs]</a><span class="k">def</span> <span class="nf">register_dataframe_accessor</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]],</span> <span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Register a custom accessor with a DataFrame</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> name : str</span>
<span class="sd"> name used when calling the accessor after its registered</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> callable</span>
<span class="sd"> A class decorator.</span>
<span class="sd"> See Also</span>
<span class="sd"> --------</span>
<span class="sd"> register_series_accessor: Register a custom accessor on Series objects</span>
<span class="sd"> register_index_accessor: Register a custom accessor on Index objects</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> When accessed, your accessor will be initialiazed with the pandas-on-Spark object the user</span>
<span class="sd"> is interacting with. The accessor&#39;s init method should always ingest the object being accessed.</span>
<span class="sd"> See the examples for the init signature.</span>
<span class="sd"> In the pandas API, if data passed to your accessor has an incorrect dtype, it&#39;s recommended to</span>
<span class="sd"> raise an ``AttributeError`` for consistency purposes. In pandas-on-Spark, ``ValueError`` is more</span>
<span class="sd"> frequently used to annotate when a value&#39;s datatype is unexpected for a given method/function.</span>
<span class="sd"> Ultimately, you can structure this however you like, but pandas-on-Spark would likely do</span>
<span class="sd"> something like this:</span>
<span class="sd"> &gt;&gt;&gt; ps.Series([&#39;a&#39;, &#39;b&#39;]).dt</span>
<span class="sd"> ...</span>
<span class="sd"> Traceback (most recent call last):</span>
<span class="sd"> ...</span>
<span class="sd"> ValueError: Cannot call DatetimeMethods on type StringType()</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> In your library code::</span>
<span class="sd"> from pyspark.pandas.extensions import register_dataframe_accessor</span>
<span class="sd"> @register_dataframe_accessor(&quot;geo&quot;)</span>
<span class="sd"> class GeoAccessor:</span>
<span class="sd"> def __init__(self, pandas_on_spark_obj):</span>
<span class="sd"> self._obj = pandas_on_spark_obj</span>
<span class="sd"> # other constructor logic</span>
<span class="sd"> @property</span>
<span class="sd"> def center(self):</span>
<span class="sd"> # return the geographic center point of this DataFrame</span>
<span class="sd"> lat = self._obj.latitude</span>
<span class="sd"> lon = self._obj.longitude</span>
<span class="sd"> return (float(lon.mean()), float(lat.mean()))</span>
<span class="sd"> def plot(self):</span>
<span class="sd"> # plot this array&#39;s data on a map</span>
<span class="sd"> pass</span>
<span class="sd"> Then, in an ipython session::</span>
<span class="sd"> &gt;&gt;&gt; ## Import if the accessor is in the other file.</span>
<span class="sd"> &gt;&gt;&gt; # from my_ext_lib import GeoAccessor</span>
<span class="sd"> &gt;&gt;&gt; psdf = ps.DataFrame({&quot;longitude&quot;: np.linspace(0,10),</span>
<span class="sd"> ... &quot;latitude&quot;: np.linspace(0, 20)})</span>
<span class="sd"> &gt;&gt;&gt; psdf.geo.center # doctest: +SKIP</span>
<span class="sd"> (5.0, 10.0)</span>
<span class="sd"> &gt;&gt;&gt; psdf.geo.plot() # doctest: +SKIP</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">pyspark.pandas</span> <span class="kn">import</span> <span class="n">DataFrame</span>
<span class="k">return</span> <span class="n">_register_accessor</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">)</span></div>
<div class="viewcode-block" id="register_series_accessor"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.extensions.register_series_accessor.html#pyspark.pandas.extensions.register_series_accessor">[docs]</a><span class="k">def</span> <span class="nf">register_series_accessor</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]],</span> <span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Register a custom accessor with a Series object</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> name : str</span>
<span class="sd"> name used when calling the accessor after its registered</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> callable</span>
<span class="sd"> A class decorator.</span>
<span class="sd"> See Also</span>
<span class="sd"> --------</span>
<span class="sd"> register_dataframe_accessor: Register a custom accessor on DataFrame objects</span>
<span class="sd"> register_index_accessor: Register a custom accessor on Index objects</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> When accessed, your accessor will be initialiazed with the pandas-on-Spark object the user is</span>
<span class="sd"> interacting with. The code signature must be::</span>
<span class="sd"> def __init__(self, pandas_on_spark_obj):</span>
<span class="sd"> # constructor logic</span>
<span class="sd"> ...</span>
<span class="sd"> In the pandas API, if data passed to your accessor has an incorrect dtype, it&#39;s recommended to</span>
<span class="sd"> raise an ``AttributeError`` for consistency purposes. In pandas-on-Spark, ``ValueError`` is more</span>
<span class="sd"> frequently used to annotate when a value&#39;s datatype is unexpected for a given method/function.</span>
<span class="sd"> Ultimately, you can structure this however you like, but pandas-on-Spark would likely do</span>
<span class="sd"> something like this:</span>
<span class="sd"> &gt;&gt;&gt; ps.Series([&#39;a&#39;, &#39;b&#39;]).dt</span>
<span class="sd"> ...</span>
<span class="sd"> Traceback (most recent call last):</span>
<span class="sd"> ...</span>
<span class="sd"> ValueError: Cannot call DatetimeMethods on type StringType()</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> In your library code::</span>
<span class="sd"> from pyspark.pandas.extensions import register_series_accessor</span>
<span class="sd"> @register_series_accessor(&quot;geo&quot;)</span>
<span class="sd"> class GeoAccessor:</span>
<span class="sd"> def __init__(self, pandas_on_spark_obj):</span>
<span class="sd"> self._obj = pandas_on_spark_obj</span>
<span class="sd"> @property</span>
<span class="sd"> def is_valid(self):</span>
<span class="sd"> # boolean check to see if series contains valid geometry</span>
<span class="sd"> return True</span>
<span class="sd"> Then, in an ipython session::</span>
<span class="sd"> &gt;&gt;&gt; ## Import if the accessor is in the other file.</span>
<span class="sd"> &gt;&gt;&gt; # from my_ext_lib import GeoAccessor</span>
<span class="sd"> &gt;&gt;&gt; psdf = ps.DataFrame({&quot;longitude&quot;: np.linspace(0,10),</span>
<span class="sd"> ... &quot;latitude&quot;: np.linspace(0, 20)})</span>
<span class="sd"> &gt;&gt;&gt; psdf.longitude.geo.is_valid # doctest: +SKIP</span>
<span class="sd"> True</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">pyspark.pandas</span> <span class="kn">import</span> <span class="n">Series</span>
<span class="k">return</span> <span class="n">_register_accessor</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">Series</span><span class="p">)</span></div>
<div class="viewcode-block" id="register_index_accessor"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.extensions.register_index_accessor.html#pyspark.pandas.extensions.register_index_accessor">[docs]</a><span class="k">def</span> <span class="nf">register_index_accessor</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]],</span> <span class="n">Type</span><span class="p">[</span><span class="n">T</span><span class="p">]]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Register a custom accessor with an Index</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> name : str</span>
<span class="sd"> name used when calling the accessor after its registered</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> callable</span>
<span class="sd"> A class decorator.</span>
<span class="sd"> See Also</span>
<span class="sd"> --------</span>
<span class="sd"> register_dataframe_accessor: Register a custom accessor on DataFrame objects</span>
<span class="sd"> register_series_accessor: Register a custom accessor on Series objects</span>
<span class="sd"> Notes</span>
<span class="sd"> -----</span>
<span class="sd"> When accessed, your accessor will be initialiazed with the pandas-on-Spark object the user is</span>
<span class="sd"> interacting with. The code signature must be::</span>
<span class="sd"> def __init__(self, pandas_on_spark_obj):</span>
<span class="sd"> # constructor logic</span>
<span class="sd"> ...</span>
<span class="sd"> In the pandas API, if data passed to your accessor has an incorrect dtype, it&#39;s recommended to</span>
<span class="sd"> raise an ``AttributeError`` for consistency purposes. In pandas-on-Spark, ``ValueError`` is more</span>
<span class="sd"> frequently used to annotate when a value&#39;s datatype is unexpected for a given method/function.</span>
<span class="sd"> Ultimately, you can structure this however you like, but pandas-on-Spark would likely do</span>
<span class="sd"> something like this:</span>
<span class="sd"> &gt;&gt;&gt; ps.Series([&#39;a&#39;, &#39;b&#39;]).dt</span>
<span class="sd"> ...</span>
<span class="sd"> Traceback (most recent call last):</span>
<span class="sd"> ...</span>
<span class="sd"> ValueError: Cannot call DatetimeMethods on type StringType()</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> In your library code::</span>
<span class="sd"> from pyspark.pandas.extensions import register_index_accessor</span>
<span class="sd"> @register_index_accessor(&quot;foo&quot;)</span>
<span class="sd"> class CustomAccessor:</span>
<span class="sd"> def __init__(self, pandas_on_spark_obj):</span>
<span class="sd"> self._obj = pandas_on_spark_obj</span>
<span class="sd"> self.item = &quot;baz&quot;</span>
<span class="sd"> @property</span>
<span class="sd"> def bar(self):</span>
<span class="sd"> # return item value</span>
<span class="sd"> return self.item</span>
<span class="sd"> Then, in an ipython session::</span>
<span class="sd"> &gt;&gt;&gt; ## Import if the accessor is in the other file.</span>
<span class="sd"> &gt;&gt;&gt; # from my_ext_lib import CustomAccessor</span>
<span class="sd"> &gt;&gt;&gt; psdf = ps.DataFrame({&quot;longitude&quot;: np.linspace(0,10),</span>
<span class="sd"> ... &quot;latitude&quot;: np.linspace(0, 20)})</span>
<span class="sd"> &gt;&gt;&gt; psdf.index.foo.bar # doctest: +SKIP</span>
<span class="sd"> &#39;baz&#39;</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">pyspark.pandas</span> <span class="kn">import</span> <span class="n">Index</span>
<span class="k">return</span> <span class="n">_register_accessor</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">Index</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_test</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">doctest</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">numpy</span>
<span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span>
<span class="kn">import</span> <span class="nn">pyspark.pandas.extensions</span>
<span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s2">&quot;SPARK_HOME&quot;</span><span class="p">])</span>
<span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">pandas</span><span class="o">.</span><span class="n">extensions</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">globs</span><span class="p">[</span><span class="s2">&quot;np&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">numpy</span>
<span class="n">globs</span><span class="p">[</span><span class="s2">&quot;ps&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">pandas</span>
<span class="n">spark</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">&quot;local[4]&quot;</span><span class="p">)</span>
<span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">&quot;pyspark.pandas.extensions tests&quot;</span><span class="p">)</span>
<span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span>
<span class="p">)</span>
<span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span>
<span class="n">pyspark</span><span class="o">.</span><span class="n">pandas</span><span class="o">.</span><span class="n">extensions</span><span class="p">,</span>
<span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span>
<span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span> <span class="o">|</span> <span class="n">doctest</span><span class="o">.</span><span class="n">NORMALIZE_WHITESPACE</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span>
<span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span>
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</span><span class="p">:</span>
<span class="n">_test</span><span class="p">()</span>
</pre></div>
</div>
<div class='prev-next-bottom'>
</div>
</main>
</div>
</div>
<script src="../../../_static/js/index.3da636dd464baa7582d2.js"></script>
<footer class="footer mt-5 mt-md-0">
<div class="container">
<p>
&copy; Copyright .<br/>
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/>
</p>
</div>
</footer>
</body>
</html>