| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.pandas.config — PySpark 3.4.2 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/_modules/pyspark/pandas/config.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="../../../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 "> |
| <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 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"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </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.config</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 "License"); 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 "AS IS" 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="sd">"""</span> |
| <span class="sd">Infrastructure of options for pandas-on-Spark.</span> |
| <span class="sd">"""</span> |
| <span class="kn">from</span> <span class="nn">contextlib</span> <span class="kn">import</span> <span class="n">contextmanager</span> |
| <span class="kn">import</span> <span class="nn">json</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Callable</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Iterator</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">Union</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark._globals</span> <span class="kn">import</span> <span class="n">_NoValue</span><span class="p">,</span> <span class="n">_NoValueType</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.utils</span> <span class="kn">import</span> <span class="n">default_session</span> |
| |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"get_option"</span><span class="p">,</span> <span class="s2">"set_option"</span><span class="p">,</span> <span class="s2">"reset_option"</span><span class="p">,</span> <span class="s2">"options"</span><span class="p">,</span> <span class="s2">"option_context"</span><span class="p">]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">Option</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Option class that defines an option with related properties.</span> |
| |
| <span class="sd"> This class holds all information relevant to the one option. Also,</span> |
| <span class="sd"> Its instance can validate if the given value is acceptable or not.</span> |
| |
| <span class="sd"> It is currently for internal usage only.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> key: str, keyword-only argument</span> |
| <span class="sd"> the option name to use.</span> |
| <span class="sd"> doc: str, keyword-only argument</span> |
| <span class="sd"> the documentation for the current option.</span> |
| <span class="sd"> default: Any, keyword-only argument</span> |
| <span class="sd"> default value for this option.</span> |
| <span class="sd"> types: Union[Tuple[type, ...], type], keyword-only argument</span> |
| <span class="sd"> default is str. It defines the expected types for this option. It is</span> |
| <span class="sd"> used with `isinstance` to validate the given value to this option.</span> |
| <span class="sd"> check_func: Tuple[Callable[[Any], bool], str], keyword-only argument</span> |
| <span class="sd"> default is a function that always returns `True` with an empty string.</span> |
| <span class="sd"> It defines:</span> |
| <span class="sd"> - a function to check the given value to this option</span> |
| <span class="sd"> - the error message to show when this check is failed</span> |
| <span class="sd"> When new value is set to this option, this function is called to check</span> |
| <span class="sd"> if the given value is valid.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> option = Option(</span> |
| <span class="sd"> ... key='option.name',</span> |
| <span class="sd"> ... doc="this is a test option",</span> |
| <span class="sd"> ... default="default",</span> |
| <span class="sd"> ... types=(float, int),</span> |
| <span class="sd"> ... check_func=(lambda v: v > 0, "should be a positive float"))</span> |
| |
| <span class="sd"> >>> option.validate('abc') # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> TypeError: The value for option 'option.name' was <class 'str'>;</span> |
| <span class="sd"> however, expected types are [(<class 'float'>, <class 'int'>)].</span> |
| |
| <span class="sd"> >>> option.validate(-1.1)</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ValueError: should be a positive float</span> |
| |
| <span class="sd"> >>> option.validate(1.1)</span> |
| <span class="sd"> """</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="o">*</span><span class="p">,</span> |
| <span class="n">key</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">doc</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">default</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> |
| <span class="n">types</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">type</span><span class="p">,</span> <span class="o">...</span><span class="p">],</span> <span class="nb">type</span><span class="p">]</span> <span class="o">=</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">check_func</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Callable</span><span class="p">[[</span><span class="n">Any</span><span class="p">],</span> <span class="nb">bool</span><span class="p">],</span> <span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span> <span class="s2">""</span><span class="p">),</span> |
| <span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">key</span> <span class="o">=</span> <span class="n">key</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">doc</span> <span class="o">=</span> <span class="n">doc</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">default</span> <span class="o">=</span> <span class="n">default</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">types</span> <span class="o">=</span> <span class="n">types</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">check_func</span> <span class="o">=</span> <span class="n">check_func</span> |
| |
| <span class="k">def</span> <span class="nf">validate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">v</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Validate the given value and throw an exception with related information such as key.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">types</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s2">"The value for option '</span><span class="si">%s</span><span class="s2">' was </span><span class="si">%s</span><span class="s2">; however, expected types are "</span> |
| <span class="s2">"[</span><span class="si">%s</span><span class="s2">]."</span> <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">key</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">v</span><span class="p">),</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">types</span><span class="p">))</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">check_func</span><span class="p">[</span><span class="mi">0</span><span class="p">](</span><span class="n">v</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">check_func</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> |
| |
| |
| <span class="c1"># Available options.</span> |
| <span class="c1">#</span> |
| <span class="c1"># NOTE: if you are fixing or adding an option here, make sure you execute `show_options()` and</span> |
| <span class="c1"># copy & paste the results into show_options</span> |
| <span class="c1"># 'docs/source/user_guide/pandas_on_spark/options.rst' as well.</span> |
| <span class="c1"># See the examples below:</span> |
| <span class="c1"># >>> from pyspark.pandas.config import show_options</span> |
| <span class="c1"># >>> show_options()</span> |
| <span class="n">_options</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">Option</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"display.max_rows"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"This sets the maximum number of rows pandas-on-Spark should output when printing out "</span> |
| <span class="s2">"various output. For example, this value determines the number of rows to be "</span> |
| <span class="s2">"shown at the repr() in a dataframe. Set `None` to unlimit the input length. "</span> |
| <span class="s2">"Default is 1000."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="p">(</span><span class="nb">int</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="kc">None</span><span class="p">)),</span> |
| <span class="n">check_func</span><span class="o">=</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">v</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">v</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">,</span> |
| <span class="s2">"'display.max_rows' should be greater than or equal to 0."</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"compute.max_rows"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"'compute.max_rows' sets the limit of the current pandas-on-Spark DataFrame. "</span> |
| <span class="s2">"Set `None` to unlimit the input length. When the limit is set, it is executed "</span> |
| <span class="s2">"by the shortcut by collecting the data into the driver, and then using the pandas "</span> |
| <span class="s2">"API. If the limit is unset, the operation is executed by PySpark. Default is 1000."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="p">(</span><span class="nb">int</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="kc">None</span><span class="p">)),</span> |
| <span class="n">check_func</span><span class="o">=</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">v</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">v</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">,</span> |
| <span class="s2">"'compute.max_rows' should be greater than or equal to 0."</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"compute.shortcut_limit"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"'compute.shortcut_limit' sets the limit for a shortcut. "</span> |
| <span class="s2">"It computes the specified number of rows and uses its schema. When the dataframe "</span> |
| <span class="s2">"length is larger than this limit, pandas-on-Spark uses PySpark to compute."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> |
| <span class="n">check_func</span><span class="o">=</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">v</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">,</span> |
| <span class="s2">"'compute.shortcut_limit' should be greater than or equal to 0."</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"compute.ops_on_diff_frames"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"This determines whether or not to operate between two different dataframes. "</span> |
| <span class="s2">"For example, 'combine_frames' function internally performs a join operation which "</span> |
| <span class="s2">"can be expensive in general. So, if `compute.ops_on_diff_frames` variable is not "</span> |
| <span class="s2">"True, that method throws an exception."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="nb">bool</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"compute.default_index_type"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span><span class="s2">"This sets the default index type: sequence, distributed and distributed-sequence."</span><span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="s2">"distributed-sequence"</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span> |
| <span class="n">check_func</span><span class="o">=</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">v</span> <span class="ow">in</span> <span class="p">(</span><span class="s2">"sequence"</span><span class="p">,</span> <span class="s2">"distributed"</span><span class="p">,</span> <span class="s2">"distributed-sequence"</span><span class="p">),</span> |
| <span class="s2">"Index type should be one of 'sequence', 'distributed', 'distributed-sequence'."</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"compute.default_index_cache"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"This sets the default storage level for temporary RDDs cached in "</span> |
| <span class="s2">"distributed-sequence indexing: 'NONE', 'DISK_ONLY', 'DISK_ONLY_2', "</span> |
| <span class="s2">"'DISK_ONLY_3', 'MEMORY_ONLY', 'MEMORY_ONLY_2', 'MEMORY_ONLY_SER', "</span> |
| <span class="s2">"'MEMORY_ONLY_SER_2', 'MEMORY_AND_DISK', 'MEMORY_AND_DISK_2', "</span> |
| <span class="s2">"'MEMORY_AND_DISK_SER', 'MEMORY_AND_DISK_SER_2', 'OFF_HEAP', "</span> |
| <span class="s2">"'LOCAL_CHECKPOINT'."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="s2">"MEMORY_AND_DISK_SER"</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span> |
| <span class="n">check_func</span><span class="o">=</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">v</span> |
| <span class="ow">in</span> <span class="p">(</span> |
| <span class="s2">"NONE"</span><span class="p">,</span> |
| <span class="s2">"DISK_ONLY"</span><span class="p">,</span> |
| <span class="s2">"DISK_ONLY_2"</span><span class="p">,</span> |
| <span class="s2">"DISK_ONLY_3"</span><span class="p">,</span> |
| <span class="s2">"MEMORY_ONLY"</span><span class="p">,</span> |
| <span class="s2">"MEMORY_ONLY_2"</span><span class="p">,</span> |
| <span class="s2">"MEMORY_ONLY_SER"</span><span class="p">,</span> |
| <span class="s2">"MEMORY_ONLY_SER_2"</span><span class="p">,</span> |
| <span class="s2">"MEMORY_AND_DISK"</span><span class="p">,</span> |
| <span class="s2">"MEMORY_AND_DISK_2"</span><span class="p">,</span> |
| <span class="s2">"MEMORY_AND_DISK_SER"</span><span class="p">,</span> |
| <span class="s2">"MEMORY_AND_DISK_SER_2"</span><span class="p">,</span> |
| <span class="s2">"OFF_HEAP"</span><span class="p">,</span> |
| <span class="s2">"LOCAL_CHECKPOINT"</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="s2">"Index type should be one of 'NONE', 'DISK_ONLY', 'DISK_ONLY_2', "</span> |
| <span class="s2">"'DISK_ONLY_3', 'MEMORY_ONLY', 'MEMORY_ONLY_2', 'MEMORY_ONLY_SER', "</span> |
| <span class="s2">"'MEMORY_ONLY_SER_2', 'MEMORY_AND_DISK', 'MEMORY_AND_DISK_2', "</span> |
| <span class="s2">"'MEMORY_AND_DISK_SER', 'MEMORY_AND_DISK_SER_2', 'OFF_HEAP', "</span> |
| <span class="s2">"'LOCAL_CHECKPOINT'."</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"compute.ordered_head"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"'compute.ordered_head' sets whether or not to operate head with natural ordering. "</span> |
| <span class="s2">"pandas-on-Spark does not guarantee the row ordering so `head` could return some "</span> |
| <span class="s2">"rows from distributed partitions. If 'compute.ordered_head' is set to True, "</span> |
| <span class="s2">"pandas-on-Spark performs natural ordering beforehand, but it will cause a "</span> |
| <span class="s2">"performance overhead."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="nb">bool</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"compute.eager_check"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"'compute.eager_check' sets whether or not to launch some Spark jobs just for the sake "</span> |
| <span class="s2">"of validation. If 'compute.eager_check' is set to True, pandas-on-Spark performs the "</span> |
| <span class="s2">"validation beforehand, but it will cause a performance overhead. Otherwise, "</span> |
| <span class="s2">"pandas-on-Spark skip the validation and will be slightly different from pandas. "</span> |
| <span class="s2">"Affected APIs: `Series.dot`, `Series.asof`, `Series.compare`, "</span> |
| <span class="s2">"`FractionalExtensionOps.astype`, `IntegralExtensionOps.astype`, "</span> |
| <span class="s2">"`FractionalOps.astype`, `DecimalOps.astype`, `skipna of statistical functions`."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="nb">bool</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"compute.isin_limit"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"'compute.isin_limit' sets the limit for filtering by 'Column.isin(list)'. "</span> |
| <span class="s2">"If the length of the ‘list’ is above the limit, broadcast join is used instead "</span> |
| <span class="s2">"for better performance."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="mi">80</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> |
| <span class="n">check_func</span><span class="o">=</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">v</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">,</span> |
| <span class="s2">"'compute.isin_limit' should be greater than or equal to 0."</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"plotting.max_rows"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"'plotting.max_rows' sets the visual limit on top-n-based plots such as `plot.bar` "</span> |
| <span class="s2">"and `plot.pie`. If it is set to 1000, the first 1000 data points will be used "</span> |
| <span class="s2">"for plotting. Default is 1000."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span> |
| <span class="n">check_func</span><span class="o">=</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">v</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">,</span> |
| <span class="s2">"'plotting.max_rows' should be greater than or equal to 0."</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"plotting.sample_ratio"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"'plotting.sample_ratio' sets the proportion of data that will be plotted for sample-"</span> |
| <span class="s2">"based plots such as `plot.line` and `plot.area`. "</span> |
| <span class="s2">"This option defaults to 'plotting.max_rows' option."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="p">(</span><span class="nb">float</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="kc">None</span><span class="p">)),</span> |
| <span class="n">check_func</span><span class="o">=</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">v</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="mi">1</span> <span class="o">>=</span> <span class="n">v</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">,</span> |
| <span class="s2">"'plotting.sample_ratio' should be 1.0 >= value >= 0.0."</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="p">),</span> |
| <span class="n">Option</span><span class="p">(</span> |
| <span class="n">key</span><span class="o">=</span><span class="s2">"plotting.backend"</span><span class="p">,</span> |
| <span class="n">doc</span><span class="o">=</span><span class="p">(</span> |
| <span class="s2">"Backend to use for plotting. Default is plotly. "</span> |
| <span class="s2">"Supports any package that has a top-level `.plot` method. "</span> |
| <span class="s2">"Known options are: [matplotlib, plotly]."</span> |
| <span class="p">),</span> |
| <span class="n">default</span><span class="o">=</span><span class="s2">"plotly"</span><span class="p">,</span> |
| <span class="n">types</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span> |
| <span class="p">),</span> |
| <span class="p">]</span> |
| |
| <span class="n">_options_dict</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Option</span><span class="p">]</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="nb">zip</span><span class="p">((</span><span class="n">option</span><span class="o">.</span><span class="n">key</span> <span class="k">for</span> <span class="n">option</span> <span class="ow">in</span> <span class="n">_options</span><span class="p">),</span> <span class="n">_options</span><span class="p">))</span> |
| |
| <span class="n">_key_format</span> <span class="o">=</span> <span class="s2">"pandas_on_Spark.</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span> |
| |
| |
| <span class="k">class</span> <span class="nc">OptionError</span><span class="p">(</span><span class="ne">AttributeError</span><span class="p">,</span> <span class="ne">KeyError</span><span class="p">):</span> |
| <span class="k">pass</span> |
| |
| |
| <span class="k">def</span> <span class="nf">show_options</span><span class="p">()</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Make a pretty table that can be copied and pasted into public documentation.</span> |
| <span class="sd"> This is currently for an internal purpose.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> show_options() # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> ================... =======... =====================...</span> |
| <span class="sd"> Option Default Description</span> |
| <span class="sd"> ================... =======... =====================...</span> |
| <span class="sd"> display.max_rows 1000 This sets the maximum...</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ================... =======... =====================...</span> |
| <span class="sd"> """</span> |
| |
| <span class="kn">import</span> <span class="nn">textwrap</span> |
| |
| <span class="n">header</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"Option"</span><span class="p">,</span> <span class="s2">"Default"</span><span class="p">,</span> <span class="s2">"Description"</span><span class="p">]</span> |
| <span class="n">row_format</span> <span class="o">=</span> <span class="s2">"</span><span class="si">{:<31}</span><span class="s2"> </span><span class="si">{:<23}</span><span class="s2"> </span><span class="si">{:<53}</span><span class="s2">"</span> |
| |
| <span class="nb">print</span><span class="p">(</span><span class="n">row_format</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s2">"="</span> <span class="o">*</span> <span class="mi">31</span><span class="p">,</span> <span class="s2">"="</span> <span class="o">*</span> <span class="mi">23</span><span class="p">,</span> <span class="s2">"="</span> <span class="o">*</span> <span class="mi">53</span><span class="p">))</span> |
| <span class="nb">print</span><span class="p">(</span><span class="n">row_format</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">*</span><span class="n">header</span><span class="p">))</span> |
| <span class="nb">print</span><span class="p">(</span><span class="n">row_format</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s2">"="</span> <span class="o">*</span> <span class="mi">31</span><span class="p">,</span> <span class="s2">"="</span> <span class="o">*</span> <span class="mi">23</span><span class="p">,</span> <span class="s2">"="</span> <span class="o">*</span> <span class="mi">53</span><span class="p">))</span> |
| |
| <span class="k">for</span> <span class="n">option</span> <span class="ow">in</span> <span class="n">_options</span><span class="p">:</span> |
| <span class="n">doc</span> <span class="o">=</span> <span class="n">textwrap</span><span class="o">.</span><span class="n">fill</span><span class="p">(</span><span class="n">option</span><span class="o">.</span><span class="n">doc</span><span class="p">,</span> <span class="mi">53</span><span class="p">)</span> |
| <span class="n">formatted</span> <span class="o">=</span> <span class="s2">""</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">line</span> <span class="o">+</span> <span class="s2">"</span><span class="se">\n</span><span class="s2">"</span> <span class="o">+</span> <span class="p">(</span><span class="s2">" "</span> <span class="o">*</span> <span class="mi">56</span><span class="p">)</span> <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">doc</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="p">)])</span><span class="o">.</span><span class="n">rstrip</span><span class="p">()</span> |
| <span class="nb">print</span><span class="p">(</span><span class="n">row_format</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">option</span><span class="o">.</span><span class="n">key</span><span class="p">,</span> <span class="nb">repr</span><span class="p">(</span><span class="n">option</span><span class="o">.</span><span class="n">default</span><span class="p">),</span> <span class="n">formatted</span><span class="p">))</span> |
| |
| <span class="nb">print</span><span class="p">(</span><span class="n">row_format</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s2">"="</span> <span class="o">*</span> <span class="mi">31</span><span class="p">,</span> <span class="s2">"="</span> <span class="o">*</span> <span class="mi">23</span><span class="p">,</span> <span class="s2">"="</span> <span class="o">*</span> <span class="mi">53</span><span class="p">))</span> |
| |
| |
| <div class="viewcode-block" id="get_option"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.get_option.html#pyspark.pandas.get_option">[docs]</a><span class="k">def</span> <span class="nf">get_option</span><span class="p">(</span><span class="n">key</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">default</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">Any</span><span class="p">,</span> <span class="n">_NoValueType</span><span class="p">]</span> <span class="o">=</span> <span class="n">_NoValue</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Retrieves the value of the specified option.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> key : str</span> |
| <span class="sd"> The key which should match a single option.</span> |
| <span class="sd"> default : object</span> |
| <span class="sd"> The default value if the option is not set yet. The value should be JSON serializable.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> result : the value of the option</span> |
| |
| <span class="sd"> Raises</span> |
| <span class="sd"> ------</span> |
| <span class="sd"> OptionError : if no such option exists and the default is not provided</span> |
| <span class="sd"> """</span> |
| <span class="n">_check_option</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">default</span> <span class="ow">is</span> <span class="n">_NoValue</span><span class="p">:</span> |
| <span class="n">default</span> <span class="o">=</span> <span class="n">_options_dict</span><span class="p">[</span><span class="n">key</span><span class="p">]</span><span class="o">.</span><span class="n">default</span> |
| <span class="n">_options_dict</span><span class="p">[</span><span class="n">key</span><span class="p">]</span><span class="o">.</span><span class="n">validate</span><span class="p">(</span><span class="n">default</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">default_session</span><span class="p">()</span><span class="o">.</span><span class="n">conf</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">_key_format</span><span class="p">(</span><span class="n">key</span><span class="p">),</span> <span class="n">default</span><span class="o">=</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">default</span><span class="p">)))</span></div> |
| |
| |
| <div class="viewcode-block" id="set_option"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.set_option.html#pyspark.pandas.set_option">[docs]</a><span class="k">def</span> <span class="nf">set_option</span><span class="p">(</span><span class="n">key</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Sets the value of the specified option.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> key : str</span> |
| <span class="sd"> The key which should match a single option.</span> |
| <span class="sd"> value : object</span> |
| <span class="sd"> New value of option. The value should be JSON serializable.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> None</span> |
| <span class="sd"> """</span> |
| <span class="n">_check_option</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| <span class="n">_options_dict</span><span class="p">[</span><span class="n">key</span><span class="p">]</span><span class="o">.</span><span class="n">validate</span><span class="p">(</span><span class="n">value</span><span class="p">)</span> |
| |
| <span class="n">default_session</span><span class="p">()</span><span class="o">.</span><span class="n">conf</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">_key_format</span><span class="p">(</span><span class="n">key</span><span class="p">),</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">value</span><span class="p">))</span></div> |
| |
| |
| <div class="viewcode-block" id="reset_option"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.reset_option.html#pyspark.pandas.reset_option">[docs]</a><span class="k">def</span> <span class="nf">reset_option</span><span class="p">(</span><span class="n">key</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Reset one option to their default value.</span> |
| |
| <span class="sd"> Pass "all" as an argument to reset all options.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> key : str</span> |
| <span class="sd"> If specified only option will be reset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> None</span> |
| <span class="sd"> """</span> |
| <span class="n">_check_option</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| <span class="n">default_session</span><span class="p">()</span><span class="o">.</span><span class="n">conf</span><span class="o">.</span><span class="n">unset</span><span class="p">(</span><span class="n">_key_format</span><span class="p">(</span><span class="n">key</span><span class="p">))</span></div> |
| |
| |
| <div class="viewcode-block" id="option_context"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.option_context.html#pyspark.pandas.option_context">[docs]</a><span class="nd">@contextmanager</span> |
| <span class="k">def</span> <span class="nf">option_context</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterator</span><span class="p">[</span><span class="kc">None</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Context manager to temporarily set options in the `with` statement context.</span> |
| |
| <span class="sd"> You need to invoke ``option_context(pat, val, [(pat, val), ...])``.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> with option_context('display.max_rows', 10, 'compute.max_rows', 5):</span> |
| <span class="sd"> ... print(get_option('display.max_rows'), get_option('compute.max_rows'))</span> |
| <span class="sd"> 10 5</span> |
| <span class="sd"> >>> print(get_option('display.max_rows'), get_option('compute.max_rows'))</span> |
| <span class="sd"> 1000 1000</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">args</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">or</span> <span class="nb">len</span><span class="p">(</span><span class="n">args</span><span class="p">)</span> <span class="o">%</span> <span class="mi">2</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Need to invoke as option_context(pat, val, [(pat, val), ...])."</span><span class="p">)</span> |
| <span class="n">opts</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="n">args</span><span class="p">[::</span><span class="mi">2</span><span class="p">],</span> <span class="n">args</span><span class="p">[</span><span class="mi">1</span><span class="p">::</span><span class="mi">2</span><span class="p">]))</span> |
| <span class="n">orig_opts</span> <span class="o">=</span> <span class="p">{</span><span class="n">key</span><span class="p">:</span> <span class="n">get_option</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">opts</span><span class="p">}</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">opts</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">set_option</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span> |
| <span class="k">yield</span> |
| <span class="k">finally</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">orig_opts</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">set_option</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_check_option</span><span class="p">(</span><span class="n">key</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">key</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">_options_dict</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">OptionError</span><span class="p">(</span> |
| <span class="s2">"No such option: '</span><span class="si">{}</span><span class="s2">'. Available options are [</span><span class="si">{}</span><span class="s2">]"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="n">key</span><span class="p">,</span> <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">_options_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">()))</span> |
| <span class="p">)</span> |
| <span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">DictWrapper</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""provide attribute-style access to a nested dict"""</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">d</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Option</span><span class="p">],</span> <span class="n">prefix</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">""</span><span class="p">):</span> |
| <span class="nb">object</span><span class="o">.</span><span class="fm">__setattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"d"</span><span class="p">,</span> <span class="n">d</span><span class="p">)</span> |
| <span class="nb">object</span><span class="o">.</span><span class="fm">__setattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"prefix"</span><span class="p">,</span> <span class="n">prefix</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__setattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">val</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">prefix</span> <span class="o">=</span> <span class="nb">object</span><span class="o">.</span><span class="fm">__getattribute__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"prefix"</span><span class="p">)</span> |
| <span class="n">d</span> <span class="o">=</span> <span class="nb">object</span><span class="o">.</span><span class="fm">__getattribute__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"d"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">prefix</span><span class="p">:</span> |
| <span class="n">prefix</span> <span class="o">+=</span> <span class="s2">"."</span> |
| <span class="n">canonical_key</span> <span class="o">=</span> <span class="n">prefix</span> <span class="o">+</span> <span class="n">key</span> |
| |
| <span class="n">candidates</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="n">k</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">d</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span> <span class="k">if</span> <span class="nb">all</span><span class="p">(</span><span class="n">x</span> <span class="ow">in</span> <span class="n">k</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"."</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">canonical_key</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"."</span><span class="p">))</span> |
| <span class="p">]</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">candidates</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="n">candidates</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="n">canonical_key</span><span class="p">:</span> |
| <span class="n">set_option</span><span class="p">(</span><span class="n">canonical_key</span><span class="p">,</span> <span class="n">val</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">OptionError</span><span class="p">(</span> |
| <span class="s2">"No such option: '</span><span class="si">{}</span><span class="s2">'. Available options are [</span><span class="si">{}</span><span class="s2">]"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="n">key</span><span class="p">,</span> <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">_options_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">()))</span> |
| <span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__getattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="s2">"DictWrapper"</span><span class="p">,</span> <span class="n">Any</span><span class="p">]:</span> |
| <span class="n">prefix</span> <span class="o">=</span> <span class="nb">object</span><span class="o">.</span><span class="fm">__getattribute__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"prefix"</span><span class="p">)</span> |
| <span class="n">d</span> <span class="o">=</span> <span class="nb">object</span><span class="o">.</span><span class="fm">__getattribute__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"d"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">prefix</span><span class="p">:</span> |
| <span class="n">prefix</span> <span class="o">+=</span> <span class="s2">"."</span> |
| <span class="n">canonical_key</span> <span class="o">=</span> <span class="n">prefix</span> <span class="o">+</span> <span class="n">key</span> |
| |
| <span class="n">candidates</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="n">k</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">d</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span> <span class="k">if</span> <span class="nb">all</span><span class="p">(</span><span class="n">x</span> <span class="ow">in</span> <span class="n">k</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"."</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">canonical_key</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"."</span><span class="p">))</span> |
| <span class="p">]</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">candidates</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="n">candidates</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="n">canonical_key</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">get_option</span><span class="p">(</span><span class="n">canonical_key</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">candidates</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">OptionError</span><span class="p">(</span> |
| <span class="s2">"No such option: '</span><span class="si">{}</span><span class="s2">'. Available options are [</span><span class="si">{}</span><span class="s2">]"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="n">key</span><span class="p">,</span> <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">_options_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">()))</span> |
| <span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">DictWrapper</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">canonical_key</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__dir__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span> |
| <span class="n">prefix</span> <span class="o">=</span> <span class="nb">object</span><span class="o">.</span><span class="fm">__getattribute__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"prefix"</span><span class="p">)</span> |
| <span class="n">d</span> <span class="o">=</span> <span class="nb">object</span><span class="o">.</span><span class="fm">__getattribute__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s2">"d"</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">prefix</span> <span class="o">==</span> <span class="s2">""</span><span class="p">:</span> |
| <span class="n">candidates</span> <span class="o">=</span> <span class="n">d</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span> |
| <span class="n">offset</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">candidates</span> <span class="o">=</span> <span class="p">[</span><span class="n">k</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">d</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span> <span class="k">if</span> <span class="nb">all</span><span class="p">(</span><span class="n">x</span> <span class="ow">in</span> <span class="n">k</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"."</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">prefix</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"."</span><span class="p">))]</span> |
| <span class="n">offset</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">prefix</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span> <span class="c1"># prefix (e.g. "compute.") to trim.</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="p">[</span><span class="n">offset</span><span class="p">:]</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">candidates</span><span class="p">]</span> |
| |
| |
| <span class="n">options</span> <span class="o">=</span> <span class="n">DictWrapper</span><span class="p">(</span><span class="n">_options_dict</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_test</span><span class="p">()</span> <span class="o">-></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">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.config</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">"SPARK_HOME"</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">config</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">"ps"</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">"local[4]"</span><span class="p">)</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"pyspark.pandas.config tests"</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">config</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">"__main__"</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> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
