| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.sql.readwriter — PySpark 3.5.0 documentation</title> |
| |
| <link href="../../../_static/styles/theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| <link href="../../../_static/styles/pydata-sphinx-theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| |
| |
| <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/styles/pydata-sphinx-theme.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/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"> |
| |
| <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/sql/readwriter.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="None"> |
| |
| |
| <!-- Google Analytics --> |
| |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <div class="container-fluid" id="banner"></div> |
| |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"><div class="container-xl"> |
| |
| <div id="navbar-start"> |
| |
| |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo"> |
| </a> |
| |
| |
| |
| </div> |
| |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-collapsible" aria-controls="navbar-collapsible" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| |
| <div id="navbar-collapsible" class="col-lg-9 collapse navbar-collapse"> |
| <div id="navbar-center" class="mr-auto"> |
| |
| <div class="navbar-center-item"> |
| <ul id="navbar-main-elements" class="navbar-nav"> |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| |
| </ul> |
| </div> |
| |
| </div> |
| |
| <div id="navbar-end"> |
| |
| <div class="navbar-end-item"> |
| <ul id="navbar-icon-links" class="navbar-nav" aria-label="Icon Links"> |
| </ul> |
| </div> |
| |
| </div> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| |
| <!-- Only show if we have sidebars configured, else just a small margin --> |
| <div class="col-12 col-md-3 bd-sidebar"> |
| <div class="sidebar-start-items"><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"> |
| |
| </div> |
| </nav> |
| </div> |
| <div class="sidebar-end-items"> |
| </div> |
| </div> |
| |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| </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.sql.readwriter</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="kn">import</span> <span class="nn">sys</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">cast</span><span class="p">,</span> <span class="n">overload</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">TYPE_CHECKING</span><span class="p">,</span> <span class="n">Union</span> |
| |
| <span class="kn">from</span> <span class="nn">py4j.java_gateway</span> <span class="kn">import</span> <span class="n">JavaClass</span><span class="p">,</span> <span class="n">JavaObject</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">RDD</span><span class="p">,</span> <span class="n">since</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.column</span> <span class="kn">import</span> <span class="n">_to_seq</span><span class="p">,</span> <span class="n">_to_java_column</span><span class="p">,</span> <span class="n">Column</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="n">StructType</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">utils</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.utils</span> <span class="kn">import</span> <span class="n">to_str</span> |
| <span class="kn">from</span> <span class="nn">pyspark.errors</span> <span class="kn">import</span> <span class="n">PySparkTypeError</span><span class="p">,</span> <span class="n">PySparkValueError</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.sql._typing</span> <span class="kn">import</span> <span class="n">OptionalPrimitiveType</span><span class="p">,</span> <span class="n">ColumnOrName</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.session</span> <span class="kn">import</span> <span class="n">SparkSession</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.dataframe</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.streaming</span> <span class="kn">import</span> <span class="n">StreamingQuery</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"DataFrameReader"</span><span class="p">,</span> <span class="s2">"DataFrameWriter"</span><span class="p">,</span> <span class="s2">"DataFrameWriterV2"</span><span class="p">]</span> |
| |
| <span class="n">PathOrPaths</span> <span class="o">=</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]]</span> |
| <span class="n">TupleOrListOfString</span> <span class="o">=</span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">],</span> <span class="n">Tuple</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">class</span> <span class="nc">OptionUtils</span><span class="p">:</span> |
| <span class="k">def</span> <span class="nf">_set_opts</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">schema</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="n">StructType</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="o">**</span><span class="n">options</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">,</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"> Set named options (filter out those the value is None)</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">options</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">v</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="c1"># type: ignore[attr-defined]</span> |
| |
| |
| <div class="viewcode-block" id="DataFrameReader"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.html#pyspark.sql.DataFrameReader">[docs]</a><span class="k">class</span> <span class="nc">DataFrameReader</span><span class="p">(</span><span class="n">OptionUtils</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Interface used to load a :class:`DataFrame` from external storage systems</span> |
| <span class="sd"> (e.g. file systems, key-value stores, etc). Use :attr:`SparkSession.read`</span> |
| <span class="sd"> to access this.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</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="n">spark</span><span class="p">:</span> <span class="s2">"SparkSession"</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">_jsparkSession</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span> <span class="o">=</span> <span class="n">spark</span> |
| |
| <span class="k">def</span> <span class="nf">_df</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">jdf</span><span class="p">:</span> <span class="n">JavaObject</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.dataframe</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| |
| <span class="k">return</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">jdf</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="DataFrameReader.format"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.format.html#pyspark.sql.DataFrameReader.format">[docs]</a> <span class="k">def</span> <span class="nf">format</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameReader"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Specifies the input data source format.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> source : str</span> |
| <span class="sd"> string, name of the data source, e.g. 'json', 'parquet'.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> spark.read.format('json')</span> |
| <span class="sd"> <...readwriter.DataFrameReader object ...></span> |
| |
| <span class="sd"> Write a DataFrame into a JSON file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a JSON file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.mode("overwrite").format("json").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the JSON file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.format('json').load(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">source</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.schema"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.schema.html#pyspark.sql.DataFrameReader.schema">[docs]</a> <span class="k">def</span> <span class="nf">schema</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">StructType</span><span class="p">,</span> <span class="nb">str</span><span class="p">])</span> <span class="o">-></span> <span class="s2">"DataFrameReader"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Specifies the input schema.</span> |
| |
| <span class="sd"> Some data sources (e.g. JSON) can infer the input schema automatically from data.</span> |
| <span class="sd"> By specifying the schema here, the underlying data source can skip the schema</span> |
| <span class="sd"> inference step, and thus speed up data loading.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> schema : :class:`pyspark.sql.types.StructType` or str</span> |
| <span class="sd"> a :class:`pyspark.sql.types.StructType` object or a DDL-formatted string</span> |
| <span class="sd"> (For example ``col0 INT, col1 DOUBLE``).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> spark.read.schema("col0 INT, col1 DOUBLE")</span> |
| <span class="sd"> <...readwriter.DataFrameReader object ...></span> |
| |
| <span class="sd"> Specify the schema with reading a CSV file.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... spark.read.schema("col0 INT, col1 DOUBLE").format("csv").load(d).printSchema()</span> |
| <span class="sd"> root</span> |
| <span class="sd"> |-- col0: integer (nullable = true)</span> |
| <span class="sd"> |-- col1: double (nullable = true)</span> |
| <span class="sd"> """</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span> |
| |
| <span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">_getActiveSessionOrCreate</span><span class="p">()</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">StructType</span><span class="p">):</span> |
| <span class="n">jschema</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">_jsparkSession</span><span class="o">.</span><span class="n">parseDataType</span><span class="p">(</span><span class="n">schema</span><span class="o">.</span><span class="n">json</span><span class="p">())</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">schema</span><span class="p">(</span><span class="n">jschema</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">schema</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">_jreader</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">schema</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"NOT_STR_OR_STRUCT"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_name"</span><span class="p">:</span> <span class="s2">"schema"</span><span class="p">,</span> |
| <span class="s2">"arg_type"</span><span class="p">:</span> <span class="nb">type</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.option"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.option.html#pyspark.sql.DataFrameReader.option">[docs]</a> <span class="k">def</span> <span class="nf">option</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">value</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameReader"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Adds an input option for the underlying data source.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> key : str</span> |
| <span class="sd"> The key for the option to set.</span> |
| <span class="sd"> value</span> |
| <span class="sd"> The value for the option to set.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> spark.read.option("key", "value")</span> |
| <span class="sd"> <...readwriter.DataFrameReader object ...></span> |
| |
| <span class="sd"> Specify the option 'nullValue' with reading a CSV file.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a CSV file</span> |
| <span class="sd"> ... df = spark.createDataFrame([{"age": 100, "name": "Hyukjin Kwon"}])</span> |
| <span class="sd"> ... df.write.mode("overwrite").format("csv").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the CSV file as a DataFrame with 'nullValue' option set to 'Hyukjin Kwon'.</span> |
| <span class="sd"> ... spark.read.schema(df.schema).option(</span> |
| <span class="sd"> ... "nullValue", "Hyukjin Kwon").format('csv').load(d).show()</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |age|name|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |100|NULL|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">to_str</span><span class="p">(</span><span class="n">value</span><span class="p">))</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.options"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.options.html#pyspark.sql.DataFrameReader.options">[docs]</a> <span class="k">def</span> <span class="nf">options</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameReader"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Adds input options for the underlying data source.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> **options : dict</span> |
| <span class="sd"> The dictionary of string keys and prmitive-type values.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> spark.read.option("key", "value")</span> |
| <span class="sd"> <...readwriter.DataFrameReader object ...></span> |
| |
| <span class="sd"> Specify the option 'nullValue' and 'header' with reading a CSV file.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a CSV file with a header.</span> |
| <span class="sd"> ... df = spark.createDataFrame([{"age": 100, "name": "Hyukjin Kwon"}])</span> |
| <span class="sd"> ... df.write.option("header", True).mode("overwrite").format("csv").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the CSV file as a DataFrame with 'nullValue' option set to 'Hyukjin Kwon',</span> |
| <span class="sd"> ... # and 'header' option set to `True`.</span> |
| <span class="sd"> ... spark.read.options(</span> |
| <span class="sd"> ... nullValue="Hyukjin Kwon",</span> |
| <span class="sd"> ... header=True</span> |
| <span class="sd"> ... ).format('csv').load(d).show()</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |age|name|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |100|NULL|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> """</span> |
| <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">options</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">to_str</span><span class="p">(</span><span class="n">options</span><span class="p">[</span><span class="n">k</span><span class="p">]))</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.load"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.load.html#pyspark.sql.DataFrameReader.load">[docs]</a> <span class="k">def</span> <span class="nf">load</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">path</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">PathOrPaths</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="nb">format</span><span class="p">:</span> <span class="n">Optional</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="n">schema</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="n">StructType</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="o">**</span><span class="n">options</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Loads data from a data source and returns it as a :class:`DataFrame`.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str or list, optional</span> |
| <span class="sd"> optional string or a list of string for file-system backed data sources.</span> |
| <span class="sd"> format : str, optional</span> |
| <span class="sd"> optional string for format of the data source. Default to 'parquet'.</span> |
| <span class="sd"> schema : :class:`pyspark.sql.types.StructType` or str, optional</span> |
| <span class="sd"> optional :class:`pyspark.sql.types.StructType` for the input schema</span> |
| <span class="sd"> or a DDL-formatted string (For example ``col0 INT, col1 DOUBLE``).</span> |
| <span class="sd"> **options : dict</span> |
| <span class="sd"> all other string options</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Load a CSV file with format, schema and options specified.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a CSV file with a header</span> |
| <span class="sd"> ... df = spark.createDataFrame([{"age": 100, "name": "Hyukjin Kwon"}])</span> |
| <span class="sd"> ... df.write.option("header", True).mode("overwrite").format("csv").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the CSV file as a DataFrame with 'nullValue' option set to 'Hyukjin Kwon',</span> |
| <span class="sd"> ... # and 'header' option set to `True`.</span> |
| <span class="sd"> ... df = spark.read.load(</span> |
| <span class="sd"> ... d, schema=df.schema, format="csv", nullValue="Hyukjin Kwon", header=True)</span> |
| <span class="sd"> ... df.printSchema()</span> |
| <span class="sd"> ... df.show()</span> |
| <span class="sd"> root</span> |
| <span class="sd"> |-- age: long (nullable = true)</span> |
| <span class="sd"> |-- name: string (nullable = true)</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |age|name|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |100|NULL|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">format</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">format</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">schema</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="p">(</span><span class="o">**</span><span class="n">options</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">path</span><span class="p">))</span> |
| <span class="k">elif</span> <span class="n">path</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> <span class="o">!=</span> <span class="nb">list</span><span class="p">:</span> |
| <span class="n">path</span> <span class="o">=</span> <span class="p">[</span><span class="n">path</span><span class="p">]</span> <span class="c1"># type: ignore[list-item]</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">PythonUtils</span><span class="o">.</span><span class="n">toSeq</span><span class="p">(</span><span class="n">path</span><span class="p">)))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">load</span><span class="p">())</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.json"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.json.html#pyspark.sql.DataFrameReader.json">[docs]</a> <span class="k">def</span> <span class="nf">json</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">path</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">],</span> <span class="n">RDD</span><span class="p">[</span><span class="nb">str</span><span class="p">]],</span> |
| <span class="n">schema</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="n">StructType</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="n">primitivesAsString</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="nb">bool</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="n">prefersDecimal</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="nb">bool</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="n">allowComments</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="nb">bool</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="n">allowUnquotedFieldNames</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="nb">bool</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="n">allowSingleQuotes</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="nb">bool</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="n">allowNumericLeadingZero</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="nb">bool</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="n">allowBackslashEscapingAnyCharacter</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="nb">bool</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="n">mode</span><span class="p">:</span> <span class="n">Optional</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="n">columnNameOfCorruptRecord</span><span class="p">:</span> <span class="n">Optional</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="n">dateFormat</span><span class="p">:</span> <span class="n">Optional</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="n">timestampFormat</span><span class="p">:</span> <span class="n">Optional</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="n">multiLine</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="nb">bool</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="n">allowUnquotedControlChars</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="nb">bool</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="n">lineSep</span><span class="p">:</span> <span class="n">Optional</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="n">samplingRatio</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="nb">float</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="n">dropFieldIfAllNull</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="nb">bool</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="n">encoding</span><span class="p">:</span> <span class="n">Optional</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="n">locale</span><span class="p">:</span> <span class="n">Optional</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="n">pathGlobFilter</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="nb">bool</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="n">recursiveFileLookup</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="nb">bool</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="n">modifiedBefore</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="nb">bool</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="n">modifiedAfter</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="nb">bool</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="n">allowNonNumericNumbers</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="nb">bool</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="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Loads JSON files and returns the results as a :class:`DataFrame`.</span> |
| |
| <span class="sd"> `JSON Lines <http://jsonlines.org/>`_ (newline-delimited JSON) is supported by default.</span> |
| <span class="sd"> For JSON (one record per file), set the ``multiLine`` parameter to ``true``.</span> |
| |
| <span class="sd"> If the ``schema`` parameter is not specified, this function goes</span> |
| <span class="sd"> through the input once to determine the input schema.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str, list or :class:`RDD`</span> |
| <span class="sd"> string represents path to the JSON dataset, or a list of paths,</span> |
| <span class="sd"> or RDD of Strings storing JSON objects.</span> |
| <span class="sd"> schema : :class:`pyspark.sql.types.StructType` or str, optional</span> |
| <span class="sd"> an optional :class:`pyspark.sql.types.StructType` for the input schema or</span> |
| <span class="sd"> a DDL-formatted string (For example ``col0 INT, col1 DOUBLE``).</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-json.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a JSON file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a JSON file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.mode("overwrite").format("json").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the JSON file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.json(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span> |
| <span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">,</span> |
| <span class="n">primitivesAsString</span><span class="o">=</span><span class="n">primitivesAsString</span><span class="p">,</span> |
| <span class="n">prefersDecimal</span><span class="o">=</span><span class="n">prefersDecimal</span><span class="p">,</span> |
| <span class="n">allowComments</span><span class="o">=</span><span class="n">allowComments</span><span class="p">,</span> |
| <span class="n">allowUnquotedFieldNames</span><span class="o">=</span><span class="n">allowUnquotedFieldNames</span><span class="p">,</span> |
| <span class="n">allowSingleQuotes</span><span class="o">=</span><span class="n">allowSingleQuotes</span><span class="p">,</span> |
| <span class="n">allowNumericLeadingZero</span><span class="o">=</span><span class="n">allowNumericLeadingZero</span><span class="p">,</span> |
| <span class="n">allowBackslashEscapingAnyCharacter</span><span class="o">=</span><span class="n">allowBackslashEscapingAnyCharacter</span><span class="p">,</span> |
| <span class="n">mode</span><span class="o">=</span><span class="n">mode</span><span class="p">,</span> |
| <span class="n">columnNameOfCorruptRecord</span><span class="o">=</span><span class="n">columnNameOfCorruptRecord</span><span class="p">,</span> |
| <span class="n">dateFormat</span><span class="o">=</span><span class="n">dateFormat</span><span class="p">,</span> |
| <span class="n">timestampFormat</span><span class="o">=</span><span class="n">timestampFormat</span><span class="p">,</span> |
| <span class="n">multiLine</span><span class="o">=</span><span class="n">multiLine</span><span class="p">,</span> |
| <span class="n">allowUnquotedControlChars</span><span class="o">=</span><span class="n">allowUnquotedControlChars</span><span class="p">,</span> |
| <span class="n">lineSep</span><span class="o">=</span><span class="n">lineSep</span><span class="p">,</span> |
| <span class="n">samplingRatio</span><span class="o">=</span><span class="n">samplingRatio</span><span class="p">,</span> |
| <span class="n">dropFieldIfAllNull</span><span class="o">=</span><span class="n">dropFieldIfAllNull</span><span class="p">,</span> |
| <span class="n">encoding</span><span class="o">=</span><span class="n">encoding</span><span class="p">,</span> |
| <span class="n">locale</span><span class="o">=</span><span class="n">locale</span><span class="p">,</span> |
| <span class="n">pathGlobFilter</span><span class="o">=</span><span class="n">pathGlobFilter</span><span class="p">,</span> |
| <span class="n">recursiveFileLookup</span><span class="o">=</span><span class="n">recursiveFileLookup</span><span class="p">,</span> |
| <span class="n">modifiedBefore</span><span class="o">=</span><span class="n">modifiedBefore</span><span class="p">,</span> |
| <span class="n">modifiedAfter</span><span class="o">=</span><span class="n">modifiedAfter</span><span class="p">,</span> |
| <span class="n">allowNonNumericNumbers</span><span class="o">=</span><span class="n">allowNonNumericNumbers</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">path</span> <span class="o">=</span> <span class="p">[</span><span class="n">path</span><span class="p">]</span> |
| <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> <span class="o">==</span> <span class="nb">list</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">json</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">PythonUtils</span><span class="o">.</span><span class="n">toSeq</span><span class="p">(</span><span class="n">path</span><span class="p">)))</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| |
| <span class="k">def</span> <span class="nf">func</span><span class="p">(</span><span class="n">iterator</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterable</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">iterator</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s2">"utf-8"</span><span class="p">)</span> |
| <span class="k">yield</span> <span class="n">x</span> |
| |
| <span class="n">keyed</span> <span class="o">=</span> <span class="n">path</span><span class="o">.</span><span class="n">mapPartitions</span><span class="p">(</span><span class="n">func</span><span class="p">)</span> |
| <span class="n">keyed</span><span class="o">.</span><span class="n">_bypass_serializer</span> <span class="o">=</span> <span class="kc">True</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">jrdd</span> <span class="o">=</span> <span class="n">keyed</span><span class="o">.</span><span class="n">_jrdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">BytesToString</span><span class="p">())</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">json</span><span class="p">(</span><span class="n">jrdd</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"NOT_STR_OR_LIST_OF_RDD"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_name"</span><span class="p">:</span> <span class="s2">"path"</span><span class="p">,</span> |
| <span class="s2">"arg_type"</span><span class="p">:</span> <span class="nb">type</span><span class="p">(</span><span class="n">path</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.table"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.table.html#pyspark.sql.DataFrameReader.table">[docs]</a> <span class="k">def</span> <span class="nf">table</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tableName</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Returns the specified table as a :class:`DataFrame`.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> tableName : str</span> |
| <span class="sd"> string, name of the table.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> df = spark.range(10)</span> |
| <span class="sd"> >>> df.createOrReplaceTempView('tblA')</span> |
| <span class="sd"> >>> spark.read.table('tblA').show()</span> |
| <span class="sd"> +---+</span> |
| <span class="sd"> | id|</span> |
| <span class="sd"> +---+</span> |
| <span class="sd"> | 0|</span> |
| <span class="sd"> | 1|</span> |
| <span class="sd"> | 2|</span> |
| <span class="sd"> | 3|</span> |
| <span class="sd"> | 4|</span> |
| <span class="sd"> | 5|</span> |
| <span class="sd"> | 6|</span> |
| <span class="sd"> | 7|</span> |
| <span class="sd"> | 8|</span> |
| <span class="sd"> | 9|</span> |
| <span class="sd"> +---+</span> |
| <span class="sd"> >>> _ = spark.sql("DROP TABLE tblA")</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="n">tableName</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.parquet"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.parquet.html#pyspark.sql.DataFrameReader.parquet">[docs]</a> <span class="k">def</span> <span class="nf">parquet</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">paths</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Loads Parquet files, returning the result as a :class:`DataFrame`.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> paths : str</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> **options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-parquet.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a Parquet file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a Parquet file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.mode("overwrite").format("parquet").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the Parquet file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.parquet(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="n">mergeSchema</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"mergeSchema"</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">pathGlobFilter</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"pathGlobFilter"</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">modifiedBefore</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"modifiedBefore"</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">modifiedAfter</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"modifiedAfter"</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">recursiveFileLookup</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"recursiveFileLookup"</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">datetimeRebaseMode</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"datetimeRebaseMode"</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">int96RebaseMode</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"int96RebaseMode"</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span> |
| <span class="n">mergeSchema</span><span class="o">=</span><span class="n">mergeSchema</span><span class="p">,</span> |
| <span class="n">pathGlobFilter</span><span class="o">=</span><span class="n">pathGlobFilter</span><span class="p">,</span> |
| <span class="n">recursiveFileLookup</span><span class="o">=</span><span class="n">recursiveFileLookup</span><span class="p">,</span> |
| <span class="n">modifiedBefore</span><span class="o">=</span><span class="n">modifiedBefore</span><span class="p">,</span> |
| <span class="n">modifiedAfter</span><span class="o">=</span><span class="n">modifiedAfter</span><span class="p">,</span> |
| <span class="n">datetimeRebaseMode</span><span class="o">=</span><span class="n">datetimeRebaseMode</span><span class="p">,</span> |
| <span class="n">int96RebaseMode</span><span class="o">=</span><span class="n">int96RebaseMode</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">parquet</span><span class="p">(</span><span class="n">_to_seq</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="p">,</span> <span class="n">paths</span><span class="p">)))</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.text"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.text.html#pyspark.sql.DataFrameReader.text">[docs]</a> <span class="k">def</span> <span class="nf">text</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">paths</span><span class="p">:</span> <span class="n">PathOrPaths</span><span class="p">,</span> |
| <span class="n">wholetext</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="n">lineSep</span><span class="p">:</span> <span class="n">Optional</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="n">pathGlobFilter</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="nb">bool</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="n">recursiveFileLookup</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="nb">bool</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="n">modifiedBefore</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="nb">bool</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="n">modifiedAfter</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="nb">bool</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="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Loads text files and returns a :class:`DataFrame` whose schema starts with a</span> |
| <span class="sd"> string column named "value", and followed by partitioned columns if there</span> |
| <span class="sd"> are any.</span> |
| <span class="sd"> The text files must be encoded as UTF-8.</span> |
| |
| <span class="sd"> By default, each line in the text file is a new row in the resulting DataFrame.</span> |
| |
| <span class="sd"> .. versionadded:: 1.6.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> paths : str or list</span> |
| <span class="sd"> string, or list of strings, for input path(s).</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-text.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a text file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a text file</span> |
| <span class="sd"> ... df = spark.createDataFrame([("a",), ("b",), ("c",)], schema=["alphabets"])</span> |
| <span class="sd"> ... df.write.mode("overwrite").format("text").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the text file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.schema(df.schema).text(d).sort("alphabets").show()</span> |
| <span class="sd"> +---------+</span> |
| <span class="sd"> |alphabets|</span> |
| <span class="sd"> +---------+</span> |
| <span class="sd"> | a|</span> |
| <span class="sd"> | b|</span> |
| <span class="sd"> | c|</span> |
| <span class="sd"> +---------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span> |
| <span class="n">wholetext</span><span class="o">=</span><span class="n">wholetext</span><span class="p">,</span> |
| <span class="n">lineSep</span><span class="o">=</span><span class="n">lineSep</span><span class="p">,</span> |
| <span class="n">pathGlobFilter</span><span class="o">=</span><span class="n">pathGlobFilter</span><span class="p">,</span> |
| <span class="n">recursiveFileLookup</span><span class="o">=</span><span class="n">recursiveFileLookup</span><span class="p">,</span> |
| <span class="n">modifiedBefore</span><span class="o">=</span><span class="n">modifiedBefore</span><span class="p">,</span> |
| <span class="n">modifiedAfter</span><span class="o">=</span><span class="n">modifiedAfter</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">paths</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">paths</span> <span class="o">=</span> <span class="p">[</span><span class="n">paths</span><span class="p">]</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">text</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">PythonUtils</span><span class="o">.</span><span class="n">toSeq</span><span class="p">(</span><span class="n">paths</span><span class="p">)))</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.csv"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.csv.html#pyspark.sql.DataFrameReader.csv">[docs]</a> <span class="k">def</span> <span class="nf">csv</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">path</span><span class="p">:</span> <span class="n">PathOrPaths</span><span class="p">,</span> |
| <span class="n">schema</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="n">StructType</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="n">sep</span><span class="p">:</span> <span class="n">Optional</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="n">encoding</span><span class="p">:</span> <span class="n">Optional</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="n">quote</span><span class="p">:</span> <span class="n">Optional</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="n">escape</span><span class="p">:</span> <span class="n">Optional</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="n">comment</span><span class="p">:</span> <span class="n">Optional</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="n">header</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="nb">bool</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="n">inferSchema</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="nb">bool</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="n">ignoreLeadingWhiteSpace</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="nb">bool</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="n">ignoreTrailingWhiteSpace</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="nb">bool</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="n">nullValue</span><span class="p">:</span> <span class="n">Optional</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="n">nanValue</span><span class="p">:</span> <span class="n">Optional</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="n">positiveInf</span><span class="p">:</span> <span class="n">Optional</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="n">negativeInf</span><span class="p">:</span> <span class="n">Optional</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="n">dateFormat</span><span class="p">:</span> <span class="n">Optional</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="n">timestampFormat</span><span class="p">:</span> <span class="n">Optional</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="n">maxColumns</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="nb">int</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="n">maxCharsPerColumn</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="nb">int</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="n">maxMalformedLogPerPartition</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="nb">int</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="n">mode</span><span class="p">:</span> <span class="n">Optional</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="n">columnNameOfCorruptRecord</span><span class="p">:</span> <span class="n">Optional</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="n">multiLine</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="nb">bool</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="n">charToEscapeQuoteEscaping</span><span class="p">:</span> <span class="n">Optional</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="n">samplingRatio</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="nb">float</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="n">enforceSchema</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="nb">bool</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="n">emptyValue</span><span class="p">:</span> <span class="n">Optional</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="n">locale</span><span class="p">:</span> <span class="n">Optional</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="n">lineSep</span><span class="p">:</span> <span class="n">Optional</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="n">pathGlobFilter</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="nb">bool</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="n">recursiveFileLookup</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="nb">bool</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="n">modifiedBefore</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="nb">bool</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="n">modifiedAfter</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="nb">bool</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="n">unescapedQuoteHandling</span><span class="p">:</span> <span class="n">Optional</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="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sa">r</span><span class="sd">"""Loads a CSV file and returns the result as a :class:`DataFrame`.</span> |
| |
| <span class="sd"> This function will go through the input once to determine the input schema if</span> |
| <span class="sd"> ``inferSchema`` is enabled. To avoid going through the entire data once, disable</span> |
| <span class="sd"> ``inferSchema`` option or specify the schema explicitly using ``schema``.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str or list</span> |
| <span class="sd"> string, or list of strings, for input path(s),</span> |
| <span class="sd"> or RDD of Strings storing CSV rows.</span> |
| <span class="sd"> schema : :class:`pyspark.sql.types.StructType` or str, optional</span> |
| <span class="sd"> an optional :class:`pyspark.sql.types.StructType` for the input schema</span> |
| <span class="sd"> or a DDL-formatted string (For example ``col0 INT, col1 DOUBLE``).</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-csv.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a CSV file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a CSV file</span> |
| <span class="sd"> ... df = spark.createDataFrame([{"age": 100, "name": "Hyukjin Kwon"}])</span> |
| <span class="sd"> ... df.write.mode("overwrite").format("csv").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the CSV file as a DataFrame with 'nullValue' option set to 'Hyukjin Kwon'.</span> |
| <span class="sd"> ... spark.read.csv(d, schema=df.schema, nullValue="Hyukjin Kwon").show()</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |age|name|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |100|NULL|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span> |
| <span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">,</span> |
| <span class="n">sep</span><span class="o">=</span><span class="n">sep</span><span class="p">,</span> |
| <span class="n">encoding</span><span class="o">=</span><span class="n">encoding</span><span class="p">,</span> |
| <span class="n">quote</span><span class="o">=</span><span class="n">quote</span><span class="p">,</span> |
| <span class="n">escape</span><span class="o">=</span><span class="n">escape</span><span class="p">,</span> |
| <span class="n">comment</span><span class="o">=</span><span class="n">comment</span><span class="p">,</span> |
| <span class="n">header</span><span class="o">=</span><span class="n">header</span><span class="p">,</span> |
| <span class="n">inferSchema</span><span class="o">=</span><span class="n">inferSchema</span><span class="p">,</span> |
| <span class="n">ignoreLeadingWhiteSpace</span><span class="o">=</span><span class="n">ignoreLeadingWhiteSpace</span><span class="p">,</span> |
| <span class="n">ignoreTrailingWhiteSpace</span><span class="o">=</span><span class="n">ignoreTrailingWhiteSpace</span><span class="p">,</span> |
| <span class="n">nullValue</span><span class="o">=</span><span class="n">nullValue</span><span class="p">,</span> |
| <span class="n">nanValue</span><span class="o">=</span><span class="n">nanValue</span><span class="p">,</span> |
| <span class="n">positiveInf</span><span class="o">=</span><span class="n">positiveInf</span><span class="p">,</span> |
| <span class="n">negativeInf</span><span class="o">=</span><span class="n">negativeInf</span><span class="p">,</span> |
| <span class="n">dateFormat</span><span class="o">=</span><span class="n">dateFormat</span><span class="p">,</span> |
| <span class="n">timestampFormat</span><span class="o">=</span><span class="n">timestampFormat</span><span class="p">,</span> |
| <span class="n">maxColumns</span><span class="o">=</span><span class="n">maxColumns</span><span class="p">,</span> |
| <span class="n">maxCharsPerColumn</span><span class="o">=</span><span class="n">maxCharsPerColumn</span><span class="p">,</span> |
| <span class="n">maxMalformedLogPerPartition</span><span class="o">=</span><span class="n">maxMalformedLogPerPartition</span><span class="p">,</span> |
| <span class="n">mode</span><span class="o">=</span><span class="n">mode</span><span class="p">,</span> |
| <span class="n">columnNameOfCorruptRecord</span><span class="o">=</span><span class="n">columnNameOfCorruptRecord</span><span class="p">,</span> |
| <span class="n">multiLine</span><span class="o">=</span><span class="n">multiLine</span><span class="p">,</span> |
| <span class="n">charToEscapeQuoteEscaping</span><span class="o">=</span><span class="n">charToEscapeQuoteEscaping</span><span class="p">,</span> |
| <span class="n">samplingRatio</span><span class="o">=</span><span class="n">samplingRatio</span><span class="p">,</span> |
| <span class="n">enforceSchema</span><span class="o">=</span><span class="n">enforceSchema</span><span class="p">,</span> |
| <span class="n">emptyValue</span><span class="o">=</span><span class="n">emptyValue</span><span class="p">,</span> |
| <span class="n">locale</span><span class="o">=</span><span class="n">locale</span><span class="p">,</span> |
| <span class="n">lineSep</span><span class="o">=</span><span class="n">lineSep</span><span class="p">,</span> |
| <span class="n">pathGlobFilter</span><span class="o">=</span><span class="n">pathGlobFilter</span><span class="p">,</span> |
| <span class="n">recursiveFileLookup</span><span class="o">=</span><span class="n">recursiveFileLookup</span><span class="p">,</span> |
| <span class="n">modifiedBefore</span><span class="o">=</span><span class="n">modifiedBefore</span><span class="p">,</span> |
| <span class="n">modifiedAfter</span><span class="o">=</span><span class="n">modifiedAfter</span><span class="p">,</span> |
| <span class="n">unescapedQuoteHandling</span><span class="o">=</span><span class="n">unescapedQuoteHandling</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">path</span> <span class="o">=</span> <span class="p">[</span><span class="n">path</span><span class="p">]</span> |
| <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> <span class="o">==</span> <span class="nb">list</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">csv</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">PythonUtils</span><span class="o">.</span><span class="n">toSeq</span><span class="p">(</span><span class="n">path</span><span class="p">)))</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| |
| <span class="k">def</span> <span class="nf">func</span><span class="p">(</span><span class="n">iterator</span><span class="p">):</span> |
| <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">iterator</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s2">"utf-8"</span><span class="p">)</span> |
| <span class="k">yield</span> <span class="n">x</span> |
| |
| <span class="n">keyed</span> <span class="o">=</span> <span class="n">path</span><span class="o">.</span><span class="n">mapPartitions</span><span class="p">(</span><span class="n">func</span><span class="p">)</span> |
| <span class="n">keyed</span><span class="o">.</span><span class="n">_bypass_serializer</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="n">jrdd</span> <span class="o">=</span> <span class="n">keyed</span><span class="o">.</span><span class="n">_jrdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">BytesToString</span><span class="p">())</span> |
| <span class="c1"># see SPARK-22112</span> |
| <span class="c1"># There aren't any jvm api for creating a dataframe from rdd storing csv.</span> |
| <span class="c1"># We can do it through creating a jvm dataset firstly and using the jvm api</span> |
| <span class="c1"># for creating a dataframe from dataset storing csv.</span> |
| <span class="n">jdataset</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_jsparkSession</span><span class="o">.</span><span class="n">createDataset</span><span class="p">(</span> |
| <span class="n">jrdd</span><span class="o">.</span><span class="n">rdd</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">Encoders</span><span class="o">.</span><span class="n">STRING</span><span class="p">()</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">csv</span><span class="p">(</span><span class="n">jdataset</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"NOT_STR_OR_LIST_OF_RDD"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_name"</span><span class="p">:</span> <span class="s2">"path"</span><span class="p">,</span> |
| <span class="s2">"arg_type"</span><span class="p">:</span> <span class="nb">type</span><span class="p">(</span><span class="n">path</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameReader.orc"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.orc.html#pyspark.sql.DataFrameReader.orc">[docs]</a> <span class="k">def</span> <span class="nf">orc</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">path</span><span class="p">:</span> <span class="n">PathOrPaths</span><span class="p">,</span> |
| <span class="n">mergeSchema</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">pathGlobFilter</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="nb">bool</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="n">recursiveFileLookup</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="nb">bool</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="n">modifiedBefore</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="nb">bool</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="n">modifiedAfter</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="nb">bool</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="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Loads ORC files, returning the result as a :class:`DataFrame`.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str or list</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-orc.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a ORC file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a ORC file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.mode("overwrite").format("orc").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the Parquet file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.orc(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span> |
| <span class="n">mergeSchema</span><span class="o">=</span><span class="n">mergeSchema</span><span class="p">,</span> |
| <span class="n">pathGlobFilter</span><span class="o">=</span><span class="n">pathGlobFilter</span><span class="p">,</span> |
| <span class="n">modifiedBefore</span><span class="o">=</span><span class="n">modifiedBefore</span><span class="p">,</span> |
| <span class="n">modifiedAfter</span><span class="o">=</span><span class="n">modifiedAfter</span><span class="p">,</span> |
| <span class="n">recursiveFileLookup</span><span class="o">=</span><span class="n">recursiveFileLookup</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">path</span> <span class="o">=</span> <span class="p">[</span><span class="n">path</span><span class="p">]</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">orc</span><span class="p">(</span><span class="n">_to_seq</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="p">,</span> <span class="n">path</span><span class="p">)))</span></div> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">jdbc</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">url</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">table</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">properties</span><span class="p">:</span> <span class="n">Optional</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="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">jdbc</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">url</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">table</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">column</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">lowerBound</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">str</span><span class="p">],</span> |
| <span class="n">upperBound</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">str</span><span class="p">],</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="o">*</span><span class="p">,</span> |
| <span class="n">properties</span><span class="p">:</span> <span class="n">Optional</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="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">jdbc</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">url</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">table</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="o">*</span><span class="p">,</span> |
| <span class="n">predicates</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">],</span> |
| <span class="n">properties</span><span class="p">:</span> <span class="n">Optional</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="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="DataFrameReader.jdbc"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameReader.jdbc.html#pyspark.sql.DataFrameReader.jdbc">[docs]</a> <span class="k">def</span> <span class="nf">jdbc</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">url</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">table</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">column</span><span class="p">:</span> <span class="n">Optional</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="n">lowerBound</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="nb">int</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="n">upperBound</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="nb">int</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="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">predicates</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">List</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="n">properties</span><span class="p">:</span> <span class="n">Optional</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="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrame"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Construct a :class:`DataFrame` representing the database table named ``table``</span> |
| <span class="sd"> accessible via JDBC URL ``url`` and connection ``properties``.</span> |
| |
| <span class="sd"> Partitions of the table will be retrieved in parallel if either ``column`` or</span> |
| <span class="sd"> ``predicates`` is specified. ``lowerBound``, ``upperBound`` and ``numPartitions``</span> |
| <span class="sd"> is needed when ``column`` is specified.</span> |
| |
| <span class="sd"> If both ``column`` and ``predicates`` are specified, ``column`` will be used.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> table : str</span> |
| <span class="sd"> the name of the table</span> |
| <span class="sd"> column : str, optional</span> |
| <span class="sd"> alias of ``partitionColumn`` option. Refer to ``partitionColumn`` in</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-jdbc.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| <span class="sd"> predicates : list, optional</span> |
| <span class="sd"> a list of expressions suitable for inclusion in WHERE clauses;</span> |
| <span class="sd"> each one defines one partition of the :class:`DataFrame`</span> |
| <span class="sd"> properties : dict, optional</span> |
| <span class="sd"> a dictionary of JDBC database connection arguments. Normally at</span> |
| <span class="sd"> least properties "user" and "password" with their corresponding values.</span> |
| <span class="sd"> For example { 'user' : 'SYSTEM', 'password' : 'mypassword' }</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-jdbc.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Don't create too many partitions in parallel on a large cluster;</span> |
| <span class="sd"> otherwise Spark might crash your external database systems.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :class:`DataFrame`</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">properties</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">properties</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_gateway</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">jprop</span> <span class="o">=</span> <span class="n">JavaClass</span><span class="p">(</span> |
| <span class="s2">"java.util.Properties"</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_gateway</span><span class="o">.</span><span class="n">_gateway_client</span><span class="p">,</span> |
| <span class="p">)()</span> |
| <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">properties</span><span class="p">:</span> |
| <span class="n">jprop</span><span class="o">.</span><span class="n">setProperty</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">properties</span><span class="p">[</span><span class="n">k</span><span class="p">])</span> |
| <span class="k">if</span> <span class="n">column</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">lowerBound</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> <span class="s2">"lowerBound can not be None when ``column`` is specified"</span> |
| <span class="k">assert</span> <span class="n">upperBound</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> <span class="s2">"upperBound can not be None when ``column`` is specified"</span> |
| <span class="k">assert</span> <span class="p">(</span> |
| <span class="n">numPartitions</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="p">),</span> <span class="s2">"numPartitions can not be None when ``column`` is specified"</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">jdbc</span><span class="p">(</span> |
| <span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">column</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">lowerBound</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">upperBound</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">numPartitions</span><span class="p">),</span> <span class="n">jprop</span> |
| <span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="n">predicates</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">gateway</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_gateway</span> |
| <span class="k">assert</span> <span class="n">gateway</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">jpredicates</span> <span class="o">=</span> <span class="n">utils</span><span class="o">.</span><span class="n">toJArray</span><span class="p">(</span><span class="n">gateway</span><span class="p">,</span> <span class="n">gateway</span><span class="o">.</span><span class="n">jvm</span><span class="o">.</span><span class="n">java</span><span class="o">.</span><span class="n">lang</span><span class="o">.</span><span class="n">String</span><span class="p">,</span> <span class="n">predicates</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">jdbc</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">jpredicates</span><span class="p">,</span> <span class="n">jprop</span><span class="p">))</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_df</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jreader</span><span class="o">.</span><span class="n">jdbc</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">jprop</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataFrameWriter"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.html#pyspark.sql.DataFrameWriter">[docs]</a><span class="k">class</span> <span class="nc">DataFrameWriter</span><span class="p">(</span><span class="n">OptionUtils</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Interface used to write a :class:`DataFrame` to external storage systems</span> |
| <span class="sd"> (e.g. file systems, key-value stores, etc). Use :attr:`DataFrame.write`</span> |
| <span class="sd"> to access this.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</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="n">df</span><span class="p">:</span> <span class="s2">"DataFrame"</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_df</span> <span class="o">=</span> <span class="n">df</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">sparkSession</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="o">.</span><span class="n">write</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">_sq</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">jsq</span><span class="p">:</span> <span class="n">JavaObject</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"StreamingQuery"</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.streaming</span> <span class="kn">import</span> <span class="n">StreamingQuery</span> |
| |
| <span class="k">return</span> <span class="n">StreamingQuery</span><span class="p">(</span><span class="n">jsq</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="DataFrameWriter.mode"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.mode.html#pyspark.sql.DataFrameWriter.mode">[docs]</a> <span class="k">def</span> <span class="nf">mode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">saveMode</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">])</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Specifies the behavior when data or table already exists.</span> |
| |
| <span class="sd"> Options include:</span> |
| |
| <span class="sd"> * `append`: Append contents of this :class:`DataFrame` to existing data.</span> |
| <span class="sd"> * `overwrite`: Overwrite existing data.</span> |
| <span class="sd"> * `error` or `errorifexists`: Throw an exception if data already exists.</span> |
| <span class="sd"> * `ignore`: Silently ignore this operation if data already exists.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Raise an error when writing to an existing path.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 80, "name": "Xinrong Meng"}]</span> |
| <span class="sd"> ... ).write.mode("error").format("parquet").save(d) # doctest: +SKIP</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ...AnalysisException: ...</span> |
| |
| <span class="sd"> Write a Parquet file back with various options, and read it back.</span> |
| |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Overwrite the path with a new Parquet file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.mode("overwrite").format("parquet").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Append another DataFrame into the Parquet file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 120, "name": "Takuya Ueshin"}]</span> |
| <span class="sd"> ... ).write.mode("append").format("parquet").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Append another DataFrame into the Parquet file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 140, "name": "Haejoon Lee"}]</span> |
| <span class="sd"> ... ).write.mode("ignore").format("parquet").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the Parquet file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.parquet(d).show()</span> |
| <span class="sd"> +---+-------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+-------------+</span> |
| <span class="sd"> |120|Takuya Ueshin|</span> |
| <span class="sd"> |100| Hyukjin Kwon|</span> |
| <span class="sd"> +---+-------------+</span> |
| <span class="sd"> """</span> |
| <span class="c1"># At the JVM side, the default value of mode is already set to "error".</span> |
| <span class="c1"># So, if the given saveMode is None, we will not call JVM-side's mode method.</span> |
| <span class="k">if</span> <span class="n">saveMode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">saveMode</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.format"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.format.html#pyspark.sql.DataFrameWriter.format">[docs]</a> <span class="k">def</span> <span class="nf">format</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Specifies the underlying output data source.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> source : str</span> |
| <span class="sd"> string, name of the data source, e.g. 'json', 'parquet'.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> spark.range(1).write.format('parquet')</span> |
| <span class="sd"> <...readwriter.DataFrameWriter object ...></span> |
| |
| <span class="sd"> Write a DataFrame into a Parquet file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a Parquet file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.mode("overwrite").format("parquet").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the Parquet file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.format('parquet').load(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">source</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.option"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.option.html#pyspark.sql.DataFrameWriter.option">[docs]</a> <span class="k">def</span> <span class="nf">option</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">value</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Adds an output option for the underlying data source.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> key : str</span> |
| <span class="sd"> The key for the option to set.</span> |
| <span class="sd"> value</span> |
| <span class="sd"> The value for the option to set.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> spark.range(1).write.option("key", "value")</span> |
| <span class="sd"> <...readwriter.DataFrameWriter object ...></span> |
| |
| <span class="sd"> Specify the option 'nullValue' with writing a CSV file.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a CSV file with 'nullValue' option set to 'Hyukjin Kwon'.</span> |
| <span class="sd"> ... df = spark.createDataFrame([(100, None)], "age INT, name STRING")</span> |
| <span class="sd"> ... df.write.option("nullValue", "Hyukjin Kwon").mode("overwrite").format("csv").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the CSV file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.schema(df.schema).format('csv').load(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">to_str</span><span class="p">(</span><span class="n">value</span><span class="p">))</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.options"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.options.html#pyspark.sql.DataFrameWriter.options">[docs]</a> <span class="k">def</span> <span class="nf">options</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Adds output options for the underlying data source.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> **options : dict</span> |
| <span class="sd"> The dictionary of string keys and primitive-type values.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> spark.range(1).write.option("key", "value")</span> |
| <span class="sd"> <...readwriter.DataFrameWriter object ...></span> |
| |
| <span class="sd"> Specify the option 'nullValue' and 'header' with writing a CSV file.</span> |
| |
| <span class="sd"> >>> from pyspark.sql.types import StructType,StructField, StringType, IntegerType</span> |
| <span class="sd"> >>> schema = StructType([</span> |
| <span class="sd"> ... StructField("age",IntegerType(),True),</span> |
| <span class="sd"> ... StructField("name",StringType(),True),</span> |
| <span class="sd"> ... ])</span> |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a CSV file with 'nullValue' option set to 'Hyukjin Kwon',</span> |
| <span class="sd"> ... # and 'header' option set to `True`.</span> |
| <span class="sd"> ... df = spark.createDataFrame([(100, None)], schema=schema)</span> |
| <span class="sd"> ... df.write.options(nullValue="Hyukjin Kwon", header=True).mode(</span> |
| <span class="sd"> ... "overwrite").format("csv").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the CSV file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.option("header", True).format('csv').load(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">options</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">to_str</span><span class="p">(</span><span class="n">options</span><span class="p">[</span><span class="n">k</span><span class="p">]))</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">partitionBy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">partitionBy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">])</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="DataFrameWriter.partitionBy"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.partitionBy.html#pyspark.sql.DataFrameWriter.partitionBy">[docs]</a> <span class="k">def</span> <span class="nf">partitionBy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]])</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Partitions the output by the given columns on the file system.</span> |
| |
| <span class="sd"> If specified, the output is laid out on the file system similar</span> |
| <span class="sd"> to Hive's partitioning scheme.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> cols : str or list</span> |
| <span class="sd"> name of columns</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a Parquet file in a partitioned manner, and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> import os</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a Parquet file in a partitioned manner.</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}, {"age": 120, "name": "Ruifeng Zheng"}]</span> |
| <span class="sd"> ... ).write.partitionBy("name").mode("overwrite").format("parquet").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the Parquet file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.parquet(d).sort("age").show()</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read one partition as a DataFrame.</span> |
| <span class="sd"> ... spark.read.parquet(f"{d}{os.path.sep}name=Hyukjin Kwon").show()</span> |
| <span class="sd"> +---+-------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+-------------+</span> |
| <span class="sd"> |100| Hyukjin Kwon|</span> |
| <span class="sd"> |120|Ruifeng Zheng|</span> |
| <span class="sd"> +---+-------------+</span> |
| <span class="sd"> +---+</span> |
| <span class="sd"> |age|</span> |
| <span class="sd"> +---+</span> |
| <span class="sd"> |100|</span> |
| <span class="sd"> +---+</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">cols</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">cols</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span> |
| <span class="n">cols</span> <span class="o">=</span> <span class="n">cols</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="c1"># type: ignore[assignment]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span> |
| <span class="n">_to_seq</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="p">,</span> <span class="n">cast</span><span class="p">(</span><span class="n">Iterable</span><span class="p">[</span><span class="s2">"ColumnOrName"</span><span class="p">],</span> <span class="n">cols</span><span class="p">))</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">bucketBy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numBuckets</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">col</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">bucketBy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numBuckets</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">col</span><span class="p">:</span> <span class="n">TupleOrListOfString</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="DataFrameWriter.bucketBy"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.bucketBy.html#pyspark.sql.DataFrameWriter.bucketBy">[docs]</a> <span class="k">def</span> <span class="nf">bucketBy</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">numBuckets</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">col</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">TupleOrListOfString</span><span class="p">],</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Buckets the output by the given columns. If specified,</span> |
| <span class="sd"> the output is laid out on the file system similar to Hive's bucketing scheme,</span> |
| <span class="sd"> but with a different bucket hash function and is not compatible with Hive's bucketing.</span> |
| |
| <span class="sd"> .. versionadded:: 2.3.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> numBuckets : int</span> |
| <span class="sd"> the number of buckets to save</span> |
| <span class="sd"> col : str, list or tuple</span> |
| <span class="sd"> a name of a column, or a list of names.</span> |
| <span class="sd"> cols : str</span> |
| <span class="sd"> additional names (optional). If `col` is a list it should be empty.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Applicable for file-based data sources in combination with</span> |
| <span class="sd"> :py:meth:`DataFrameWriter.saveAsTable`.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a Parquet file in a buckted manner, and read it back.</span> |
| |
| <span class="sd"> >>> from pyspark.sql.functions import input_file_name</span> |
| <span class="sd"> >>> # Write a DataFrame into a Parquet file in a bucketed manner.</span> |
| <span class="sd"> ... _ = spark.sql("DROP TABLE IF EXISTS bucketed_table")</span> |
| <span class="sd"> >>> spark.createDataFrame([</span> |
| <span class="sd"> ... (100, "Hyukjin Kwon"), (120, "Hyukjin Kwon"), (140, "Haejoon Lee")],</span> |
| <span class="sd"> ... schema=["age", "name"]</span> |
| <span class="sd"> ... ).write.bucketBy(2, "name").mode("overwrite").saveAsTable("bucketed_table")</span> |
| <span class="sd"> >>> # Read the Parquet file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.table("bucketed_table").sort("age").show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> |120|Hyukjin Kwon|</span> |
| <span class="sd"> |140| Haejoon Lee|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> >>> _ = spark.sql("DROP TABLE bucketed_table")</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">numBuckets</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"NOT_INT"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_name"</span><span class="p">:</span> <span class="s2">"numBuckets"</span><span class="p">,</span> |
| <span class="s2">"arg_type"</span><span class="p">:</span> <span class="nb">type</span><span class="p">(</span><span class="n">numBuckets</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span> |
| <span class="k">if</span> <span class="n">cols</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">PySparkValueError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"CANNOT_SET_TOGETHER"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_list"</span><span class="p">:</span> <span class="sa">f</span><span class="s2">"`col` of type </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">col</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s2"> and `cols`"</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span> |
| |
| <span class="n">col</span><span class="p">,</span> <span class="n">cols</span> <span class="o">=</span> <span class="n">col</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">col</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span> <span class="c1"># type: ignore[assignment]</span> |
| |
| <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">cols</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">c</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"NOT_LIST_OF_STR"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_name"</span><span class="p">:</span> <span class="s2">"cols"</span><span class="p">,</span> |
| <span class="s2">"arg_type"</span><span class="p">:</span> <span class="nb">type</span><span class="p">(</span><span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"NOT_LIST_OF_STR"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_name"</span><span class="p">:</span> <span class="s2">"col"</span><span class="p">,</span> |
| <span class="s2">"arg_type"</span><span class="p">:</span> <span class="nb">type</span><span class="p">(</span><span class="n">col</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">bucketBy</span><span class="p">(</span> |
| <span class="n">numBuckets</span><span class="p">,</span> <span class="n">col</span><span class="p">,</span> <span class="n">_to_seq</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="p">,</span> <span class="n">cast</span><span class="p">(</span><span class="n">Iterable</span><span class="p">[</span><span class="s2">"ColumnOrName"</span><span class="p">],</span> <span class="n">cols</span><span class="p">))</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">sortBy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">col</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">sortBy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">col</span><span class="p">:</span> <span class="n">TupleOrListOfString</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="DataFrameWriter.sortBy"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.sortBy.html#pyspark.sql.DataFrameWriter.sortBy">[docs]</a> <span class="k">def</span> <span class="nf">sortBy</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">col</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">TupleOrListOfString</span><span class="p">],</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriter"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Sorts the output in each bucket by the given columns on the file system.</span> |
| |
| <span class="sd"> .. versionadded:: 2.3.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> col : str, tuple or list</span> |
| <span class="sd"> a name of a column, or a list of names.</span> |
| <span class="sd"> cols : str</span> |
| <span class="sd"> additional names (optional). If `col` is a list it should be empty.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a Parquet file in a sorted-buckted manner, and read it back.</span> |
| |
| <span class="sd"> >>> from pyspark.sql.functions import input_file_name</span> |
| <span class="sd"> >>> # Write a DataFrame into a Parquet file in a sorted-bucketed manner.</span> |
| <span class="sd"> ... _ = spark.sql("DROP TABLE IF EXISTS sorted_bucketed_table")</span> |
| <span class="sd"> >>> spark.createDataFrame([</span> |
| <span class="sd"> ... (100, "Hyukjin Kwon"), (120, "Hyukjin Kwon"), (140, "Haejoon Lee")],</span> |
| <span class="sd"> ... schema=["age", "name"]</span> |
| <span class="sd"> ... ).write.bucketBy(1, "name").sortBy("age").mode(</span> |
| <span class="sd"> ... "overwrite").saveAsTable("sorted_bucketed_table")</span> |
| <span class="sd"> >>> # Read the Parquet file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.table("sorted_bucketed_table").sort("age").show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> |120|Hyukjin Kwon|</span> |
| <span class="sd"> |140| Haejoon Lee|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> >>> _ = spark.sql("DROP TABLE sorted_bucketed_table")</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span> |
| <span class="k">if</span> <span class="n">cols</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">PySparkValueError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"CANNOT_SET_TOGETHER"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_list"</span><span class="p">:</span> <span class="sa">f</span><span class="s2">"`col` of type </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">col</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s2"> and `cols`"</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span> |
| |
| <span class="n">col</span><span class="p">,</span> <span class="n">cols</span> <span class="o">=</span> <span class="n">col</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">col</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span> <span class="c1"># type: ignore[assignment]</span> |
| |
| <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">cols</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">c</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"NOT_LIST_OF_STR"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_name"</span><span class="p">:</span> <span class="s2">"cols"</span><span class="p">,</span> |
| <span class="s2">"arg_type"</span><span class="p">:</span> <span class="nb">type</span><span class="p">(</span><span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="n">PySparkTypeError</span><span class="p">(</span> |
| <span class="n">error_class</span><span class="o">=</span><span class="s2">"NOT_LIST_OF_STR"</span><span class="p">,</span> |
| <span class="n">message_parameters</span><span class="o">=</span><span class="p">{</span> |
| <span class="s2">"arg_name"</span><span class="p">:</span> <span class="s2">"col"</span><span class="p">,</span> |
| <span class="s2">"arg_type"</span><span class="p">:</span> <span class="nb">type</span><span class="p">(</span><span class="n">col</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">sortBy</span><span class="p">(</span> |
| <span class="n">col</span><span class="p">,</span> <span class="n">_to_seq</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="p">,</span> <span class="n">cast</span><span class="p">(</span><span class="n">Iterable</span><span class="p">[</span><span class="s2">"ColumnOrName"</span><span class="p">],</span> <span class="n">cols</span><span class="p">))</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.save"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.save.html#pyspark.sql.DataFrameWriter.save">[docs]</a> <span class="k">def</span> <span class="nf">save</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">path</span><span class="p">:</span> <span class="n">Optional</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="nb">format</span><span class="p">:</span> <span class="n">Optional</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="n">mode</span><span class="p">:</span> <span class="n">Optional</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="n">partitionBy</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="nb">str</span><span class="p">,</span> <span class="n">List</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="o">**</span><span class="n">options</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">,</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">"""Saves the contents of the :class:`DataFrame` to a data source.</span> |
| |
| <span class="sd"> The data source is specified by the ``format`` and a set of ``options``.</span> |
| <span class="sd"> If ``format`` is not specified, the default data source configured by</span> |
| <span class="sd"> ``spark.sql.sources.default`` will be used.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str, optional</span> |
| <span class="sd"> the path in a Hadoop supported file system</span> |
| <span class="sd"> format : str, optional</span> |
| <span class="sd"> the format used to save</span> |
| <span class="sd"> mode : str, optional</span> |
| <span class="sd"> specifies the behavior of the save operation when data already exists.</span> |
| |
| <span class="sd"> * ``append``: Append contents of this :class:`DataFrame` to existing data.</span> |
| <span class="sd"> * ``overwrite``: Overwrite existing data.</span> |
| <span class="sd"> * ``ignore``: Silently ignore this operation if data already exists.</span> |
| <span class="sd"> * ``error`` or ``errorifexists`` (default case): Throw an exception if data already \</span> |
| <span class="sd"> exists.</span> |
| <span class="sd"> partitionBy : list, optional</span> |
| <span class="sd"> names of partitioning columns</span> |
| <span class="sd"> **options : dict</span> |
| <span class="sd"> all other string options</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a JSON file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a JSON file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.mode("overwrite").format("json").save(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the JSON file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.format('json').load(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span><span class="o">.</span><span class="n">options</span><span class="p">(</span><span class="o">**</span><span class="n">options</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">partitionBy</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="n">partitionBy</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">format</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">format</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">path</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">save</span><span class="p">()</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.insertInto"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.insertInto.html#pyspark.sql.DataFrameWriter.insertInto">[docs]</a> <span class="k">def</span> <span class="nf">insertInto</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tableName</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">overwrite</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</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">"""Inserts the content of the :class:`DataFrame` to the specified table.</span> |
| |
| <span class="sd"> It requires that the schema of the :class:`DataFrame` is the same as the</span> |
| <span class="sd"> schema of the table.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> overwrite : bool, optional</span> |
| <span class="sd"> If true, overwrites existing data. Disabled by default</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Unlike :meth:`DataFrameWriter.saveAsTable`, :meth:`DataFrameWriter.insertInto` ignores</span> |
| <span class="sd"> the column names and just uses position-based resolution.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> _ = spark.sql("DROP TABLE IF EXISTS tblA")</span> |
| <span class="sd"> >>> df = spark.createDataFrame([</span> |
| <span class="sd"> ... (100, "Hyukjin Kwon"), (120, "Hyukjin Kwon"), (140, "Haejoon Lee")],</span> |
| <span class="sd"> ... schema=["age", "name"]</span> |
| <span class="sd"> ... )</span> |
| <span class="sd"> >>> df.write.saveAsTable("tblA")</span> |
| |
| <span class="sd"> Insert the data into 'tblA' table but with different column names.</span> |
| |
| <span class="sd"> >>> df.selectExpr("age AS col1", "name AS col2").write.insertInto("tblA")</span> |
| <span class="sd"> >>> spark.read.table("tblA").sort("age").show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> |120|Hyukjin Kwon|</span> |
| <span class="sd"> |120|Hyukjin Kwon|</span> |
| <span class="sd"> |140| Haejoon Lee|</span> |
| <span class="sd"> |140| Haejoon Lee|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> >>> _ = spark.sql("DROP TABLE tblA")</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">overwrite</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="s2">"overwrite"</span> <span class="k">if</span> <span class="n">overwrite</span> <span class="k">else</span> <span class="s2">"append"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">insertInto</span><span class="p">(</span><span class="n">tableName</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.saveAsTable"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.saveAsTable.html#pyspark.sql.DataFrameWriter.saveAsTable">[docs]</a> <span class="k">def</span> <span class="nf">saveAsTable</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="nb">format</span><span class="p">:</span> <span class="n">Optional</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="n">mode</span><span class="p">:</span> <span class="n">Optional</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="n">partitionBy</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="nb">str</span><span class="p">,</span> <span class="n">List</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="o">**</span><span class="n">options</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">,</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">"""Saves the content of the :class:`DataFrame` as the specified table.</span> |
| |
| <span class="sd"> In the case the table already exists, behavior of this function depends on the</span> |
| <span class="sd"> save mode, specified by the `mode` function (default to throwing an exception).</span> |
| <span class="sd"> When `mode` is `Overwrite`, the schema of the :class:`DataFrame` does not need to be</span> |
| <span class="sd"> the same as that of the existing table.</span> |
| |
| <span class="sd"> * `append`: Append contents of this :class:`DataFrame` to existing data.</span> |
| <span class="sd"> * `overwrite`: Overwrite existing data.</span> |
| <span class="sd"> * `error` or `errorifexists`: Throw an exception if data already exists.</span> |
| <span class="sd"> * `ignore`: Silently ignore this operation if data already exists.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> When `mode` is `Append`, if there is an existing table, we will use the format and</span> |
| <span class="sd"> options of the existing table. The column order in the schema of the :class:`DataFrame`</span> |
| <span class="sd"> doesn't need to be the same as that of the existing table. Unlike</span> |
| <span class="sd"> :meth:`DataFrameWriter.insertInto`, :meth:`DataFrameWriter.saveAsTable` will use the</span> |
| <span class="sd"> column names to find the correct column positions.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> name : str</span> |
| <span class="sd"> the table name</span> |
| <span class="sd"> format : str, optional</span> |
| <span class="sd"> the format used to save</span> |
| <span class="sd"> mode : str, optional</span> |
| <span class="sd"> one of `append`, `overwrite`, `error`, `errorifexists`, `ignore` \</span> |
| <span class="sd"> (default: error)</span> |
| <span class="sd"> partitionBy : str or list</span> |
| <span class="sd"> names of partitioning columns</span> |
| <span class="sd"> **options : dict</span> |
| <span class="sd"> all other string options</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Creates a table from a DataFrame, and read it back.</span> |
| |
| <span class="sd"> >>> _ = spark.sql("DROP TABLE IF EXISTS tblA")</span> |
| <span class="sd"> >>> spark.createDataFrame([</span> |
| <span class="sd"> ... (100, "Hyukjin Kwon"), (120, "Hyukjin Kwon"), (140, "Haejoon Lee")],</span> |
| <span class="sd"> ... schema=["age", "name"]</span> |
| <span class="sd"> ... ).write.saveAsTable("tblA")</span> |
| <span class="sd"> >>> spark.read.table("tblA").sort("age").show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> |120|Hyukjin Kwon|</span> |
| <span class="sd"> |140| Haejoon Lee|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> >>> _ = spark.sql("DROP TABLE tblA")</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span><span class="o">.</span><span class="n">options</span><span class="p">(</span><span class="o">**</span><span class="n">options</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">partitionBy</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="n">partitionBy</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">format</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">format</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">saveAsTable</span><span class="p">(</span><span class="n">name</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.json"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.json.html#pyspark.sql.DataFrameWriter.json">[docs]</a> <span class="k">def</span> <span class="nf">json</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">mode</span><span class="p">:</span> <span class="n">Optional</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="n">compression</span><span class="p">:</span> <span class="n">Optional</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="n">dateFormat</span><span class="p">:</span> <span class="n">Optional</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="n">timestampFormat</span><span class="p">:</span> <span class="n">Optional</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="n">lineSep</span><span class="p">:</span> <span class="n">Optional</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="n">encoding</span><span class="p">:</span> <span class="n">Optional</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="n">ignoreNullFields</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="nb">bool</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="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Saves the content of the :class:`DataFrame` in JSON format</span> |
| <span class="sd"> (`JSON Lines text format or newline-delimited JSON <http://jsonlines.org/>`_) at the</span> |
| <span class="sd"> specified path.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str</span> |
| <span class="sd"> the path in any Hadoop supported file system</span> |
| <span class="sd"> mode : str, optional</span> |
| <span class="sd"> specifies the behavior of the save operation when data already exists.</span> |
| |
| <span class="sd"> * ``append``: Append contents of this :class:`DataFrame` to existing data.</span> |
| <span class="sd"> * ``overwrite``: Overwrite existing data.</span> |
| <span class="sd"> * ``ignore``: Silently ignore this operation if data already exists.</span> |
| <span class="sd"> * ``error`` or ``errorifexists`` (default case): Throw an exception if data already \</span> |
| <span class="sd"> exists.</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-json.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a JSON file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a JSON file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.json(d, mode="overwrite")</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the JSON file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.format("json").load(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span> |
| <span class="n">compression</span><span class="o">=</span><span class="n">compression</span><span class="p">,</span> |
| <span class="n">dateFormat</span><span class="o">=</span><span class="n">dateFormat</span><span class="p">,</span> |
| <span class="n">timestampFormat</span><span class="o">=</span><span class="n">timestampFormat</span><span class="p">,</span> |
| <span class="n">lineSep</span><span class="o">=</span><span class="n">lineSep</span><span class="p">,</span> |
| <span class="n">encoding</span><span class="o">=</span><span class="n">encoding</span><span class="p">,</span> |
| <span class="n">ignoreNullFields</span><span class="o">=</span><span class="n">ignoreNullFields</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">json</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.parquet"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.parquet.html#pyspark.sql.DataFrameWriter.parquet">[docs]</a> <span class="k">def</span> <span class="nf">parquet</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">mode</span><span class="p">:</span> <span class="n">Optional</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="n">partitionBy</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="nb">str</span><span class="p">,</span> <span class="n">List</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="n">compression</span><span class="p">:</span> <span class="n">Optional</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="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Saves the content of the :class:`DataFrame` in Parquet format at the specified path.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str</span> |
| <span class="sd"> the path in any Hadoop supported file system</span> |
| <span class="sd"> mode : str, optional</span> |
| <span class="sd"> specifies the behavior of the save operation when data already exists.</span> |
| |
| <span class="sd"> * ``append``: Append contents of this :class:`DataFrame` to existing data.</span> |
| <span class="sd"> * ``overwrite``: Overwrite existing data.</span> |
| <span class="sd"> * ``ignore``: Silently ignore this operation if data already exists.</span> |
| <span class="sd"> * ``error`` or ``errorifexists`` (default case): Throw an exception if data already \</span> |
| <span class="sd"> exists.</span> |
| <span class="sd"> partitionBy : str or list, optional</span> |
| <span class="sd"> names of partitioning columns</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-parquet.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a Parquet file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a Parquet file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.parquet(d, mode="overwrite")</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the Parquet file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.format("parquet").load(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">partitionBy</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="n">partitionBy</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span><span class="n">compression</span><span class="o">=</span><span class="n">compression</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">parquet</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.text"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.text.html#pyspark.sql.DataFrameWriter.text">[docs]</a> <span class="k">def</span> <span class="nf">text</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">compression</span><span class="p">:</span> <span class="n">Optional</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="n">lineSep</span><span class="p">:</span> <span class="n">Optional</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="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Saves the content of the DataFrame in a text file at the specified path.</span> |
| <span class="sd"> The text files will be encoded as UTF-8.</span> |
| |
| <span class="sd"> .. versionadded:: 1.6.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str</span> |
| <span class="sd"> the path in any Hadoop supported file system</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-text.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> The DataFrame must have only one column that is of string type.</span> |
| <span class="sd"> Each row becomes a new line in the output file.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a text file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a text file</span> |
| <span class="sd"> ... df = spark.createDataFrame([("a",), ("b",), ("c",)], schema=["alphabets"])</span> |
| <span class="sd"> ... df.write.mode("overwrite").text(d)</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the text file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.schema(df.schema).format("text").load(d).sort("alphabets").show()</span> |
| <span class="sd"> +---------+</span> |
| <span class="sd"> |alphabets|</span> |
| <span class="sd"> +---------+</span> |
| <span class="sd"> | a|</span> |
| <span class="sd"> | b|</span> |
| <span class="sd"> | c|</span> |
| <span class="sd"> +---------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span><span class="n">compression</span><span class="o">=</span><span class="n">compression</span><span class="p">,</span> <span class="n">lineSep</span><span class="o">=</span><span class="n">lineSep</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">text</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.csv"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.csv.html#pyspark.sql.DataFrameWriter.csv">[docs]</a> <span class="k">def</span> <span class="nf">csv</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">mode</span><span class="p">:</span> <span class="n">Optional</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="n">compression</span><span class="p">:</span> <span class="n">Optional</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="n">sep</span><span class="p">:</span> <span class="n">Optional</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="n">quote</span><span class="p">:</span> <span class="n">Optional</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="n">escape</span><span class="p">:</span> <span class="n">Optional</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="n">header</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="nb">bool</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="n">nullValue</span><span class="p">:</span> <span class="n">Optional</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="n">escapeQuotes</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="nb">bool</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="n">quoteAll</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="nb">bool</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="n">dateFormat</span><span class="p">:</span> <span class="n">Optional</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="n">timestampFormat</span><span class="p">:</span> <span class="n">Optional</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="n">ignoreLeadingWhiteSpace</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="nb">bool</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="n">ignoreTrailingWhiteSpace</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="nb">bool</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="n">charToEscapeQuoteEscaping</span><span class="p">:</span> <span class="n">Optional</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="n">encoding</span><span class="p">:</span> <span class="n">Optional</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="n">emptyValue</span><span class="p">:</span> <span class="n">Optional</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="n">lineSep</span><span class="p">:</span> <span class="n">Optional</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="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sa">r</span><span class="sd">"""Saves the content of the :class:`DataFrame` in CSV format at the specified path.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str</span> |
| <span class="sd"> the path in any Hadoop supported file system</span> |
| <span class="sd"> mode : str, optional</span> |
| <span class="sd"> specifies the behavior of the save operation when data already exists.</span> |
| |
| <span class="sd"> * ``append``: Append contents of this :class:`DataFrame` to existing data.</span> |
| <span class="sd"> * ``overwrite``: Overwrite existing data.</span> |
| <span class="sd"> * ``ignore``: Silently ignore this operation if data already exists.</span> |
| <span class="sd"> * ``error`` or ``errorifexists`` (default case): Throw an exception if data already \</span> |
| <span class="sd"> exists.</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-csv.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a CSV file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a CSV file</span> |
| <span class="sd"> ... df = spark.createDataFrame([{"age": 100, "name": "Hyukjin Kwon"}])</span> |
| <span class="sd"> ... df.write.csv(d, mode="overwrite")</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the CSV file as a DataFrame with 'nullValue' option set to 'Hyukjin Kwon'.</span> |
| <span class="sd"> ... spark.read.schema(df.schema).format("csv").option(</span> |
| <span class="sd"> ... "nullValue", "Hyukjin Kwon").load(d).show()</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |age|name|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> |100|NULL|</span> |
| <span class="sd"> +---+----+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span> |
| <span class="n">compression</span><span class="o">=</span><span class="n">compression</span><span class="p">,</span> |
| <span class="n">sep</span><span class="o">=</span><span class="n">sep</span><span class="p">,</span> |
| <span class="n">quote</span><span class="o">=</span><span class="n">quote</span><span class="p">,</span> |
| <span class="n">escape</span><span class="o">=</span><span class="n">escape</span><span class="p">,</span> |
| <span class="n">header</span><span class="o">=</span><span class="n">header</span><span class="p">,</span> |
| <span class="n">nullValue</span><span class="o">=</span><span class="n">nullValue</span><span class="p">,</span> |
| <span class="n">escapeQuotes</span><span class="o">=</span><span class="n">escapeQuotes</span><span class="p">,</span> |
| <span class="n">quoteAll</span><span class="o">=</span><span class="n">quoteAll</span><span class="p">,</span> |
| <span class="n">dateFormat</span><span class="o">=</span><span class="n">dateFormat</span><span class="p">,</span> |
| <span class="n">timestampFormat</span><span class="o">=</span><span class="n">timestampFormat</span><span class="p">,</span> |
| <span class="n">ignoreLeadingWhiteSpace</span><span class="o">=</span><span class="n">ignoreLeadingWhiteSpace</span><span class="p">,</span> |
| <span class="n">ignoreTrailingWhiteSpace</span><span class="o">=</span><span class="n">ignoreTrailingWhiteSpace</span><span class="p">,</span> |
| <span class="n">charToEscapeQuoteEscaping</span><span class="o">=</span><span class="n">charToEscapeQuoteEscaping</span><span class="p">,</span> |
| <span class="n">encoding</span><span class="o">=</span><span class="n">encoding</span><span class="p">,</span> |
| <span class="n">emptyValue</span><span class="o">=</span><span class="n">emptyValue</span><span class="p">,</span> |
| <span class="n">lineSep</span><span class="o">=</span><span class="n">lineSep</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">csv</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.orc"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.orc.html#pyspark.sql.DataFrameWriter.orc">[docs]</a> <span class="k">def</span> <span class="nf">orc</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">mode</span><span class="p">:</span> <span class="n">Optional</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="n">partitionBy</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="nb">str</span><span class="p">,</span> <span class="n">List</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="n">compression</span><span class="p">:</span> <span class="n">Optional</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="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Saves the content of the :class:`DataFrame` in ORC format at the specified path.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> path : str</span> |
| <span class="sd"> the path in any Hadoop supported file system</span> |
| <span class="sd"> mode : str, optional</span> |
| <span class="sd"> specifies the behavior of the save operation when data already exists.</span> |
| |
| <span class="sd"> * ``append``: Append contents of this :class:`DataFrame` to existing data.</span> |
| <span class="sd"> * ``overwrite``: Overwrite existing data.</span> |
| <span class="sd"> * ``ignore``: Silently ignore this operation if data already exists.</span> |
| <span class="sd"> * ``error`` or ``errorifexists`` (default case): Throw an exception if data already \</span> |
| <span class="sd"> exists.</span> |
| <span class="sd"> partitionBy : str or list, optional</span> |
| <span class="sd"> names of partitioning columns</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-orc.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Write a DataFrame into a ORC file and read it back.</span> |
| |
| <span class="sd"> >>> import tempfile</span> |
| <span class="sd"> >>> with tempfile.TemporaryDirectory() as d:</span> |
| <span class="sd"> ... # Write a DataFrame into a ORC file</span> |
| <span class="sd"> ... spark.createDataFrame(</span> |
| <span class="sd"> ... [{"age": 100, "name": "Hyukjin Kwon"}]</span> |
| <span class="sd"> ... ).write.orc(d, mode="overwrite")</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ... # Read the Parquet file as a DataFrame.</span> |
| <span class="sd"> ... spark.read.format("orc").load(d).show()</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |age| name|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> |100|Hyukjin Kwon|</span> |
| <span class="sd"> +---+------------+</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">partitionBy</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="n">partitionBy</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set_opts</span><span class="p">(</span><span class="n">compression</span><span class="o">=</span><span class="n">compression</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">orc</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriter.jdbc"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriter.jdbc.html#pyspark.sql.DataFrameWriter.jdbc">[docs]</a> <span class="k">def</span> <span class="nf">jdbc</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">url</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">table</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">mode</span><span class="p">:</span> <span class="n">Optional</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="n">properties</span><span class="p">:</span> <span class="n">Optional</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="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</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">"""Saves the content of the :class:`DataFrame` to an external database table via JDBC.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> table : str</span> |
| <span class="sd"> Name of the table in the external database.</span> |
| <span class="sd"> mode : str, optional</span> |
| <span class="sd"> specifies the behavior of the save operation when data already exists.</span> |
| |
| <span class="sd"> * ``append``: Append contents of this :class:`DataFrame` to existing data.</span> |
| <span class="sd"> * ``overwrite``: Overwrite existing data.</span> |
| <span class="sd"> * ``ignore``: Silently ignore this operation if data already exists.</span> |
| <span class="sd"> * ``error`` or ``errorifexists`` (default case): Throw an exception if data already \</span> |
| <span class="sd"> exists.</span> |
| <span class="sd"> properties : dict</span> |
| <span class="sd"> a dictionary of JDBC database connection arguments. Normally at</span> |
| <span class="sd"> least properties "user" and "password" with their corresponding values.</span> |
| <span class="sd"> For example { 'user' : 'SYSTEM', 'password' : 'mypassword' }</span> |
| |
| <span class="sd"> Other Parameters</span> |
| <span class="sd"> ----------------</span> |
| <span class="sd"> Extra options</span> |
| <span class="sd"> For the extra options, refer to</span> |
| <span class="sd"> `Data Source Option <https://spark.apache.org/docs/latest/sql-data-sources-jdbc.html#data-source-option>`_</span> |
| <span class="sd"> for the version you use.</span> |
| |
| <span class="sd"> .. # noqa</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Don't create too many partitions in parallel on a large cluster;</span> |
| <span class="sd"> otherwise Spark might crash your external database systems.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">properties</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">properties</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span> |
| |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_gateway</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="n">jprop</span> <span class="o">=</span> <span class="n">JavaClass</span><span class="p">(</span> |
| <span class="s2">"java.util.Properties"</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="o">.</span><span class="n">_gateway</span><span class="o">.</span><span class="n">_gateway_client</span><span class="p">,</span> |
| <span class="p">)()</span> |
| <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">properties</span><span class="p">:</span> |
| <span class="n">jprop</span><span class="o">.</span><span class="n">setProperty</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">properties</span><span class="p">[</span><span class="n">k</span><span class="p">])</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">(</span><span class="n">mode</span><span class="p">)</span><span class="o">.</span><span class="n">_jwrite</span><span class="o">.</span><span class="n">jdbc</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">jprop</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataFrameWriterV2"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.html#pyspark.sql.DataFrameWriterV2">[docs]</a><span class="k">class</span> <span class="nc">DataFrameWriterV2</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Interface used to write a class:`pyspark.sql.dataframe.DataFrame`</span> |
| <span class="sd"> to external storage using the v2 API.</span> |
| |
| <span class="sd"> .. versionadded:: 3.1.0</span> |
| |
| <span class="sd"> .. versionchanged:: 3.4.0</span> |
| <span class="sd"> Supports Spark Connect.</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="n">df</span><span class="p">:</span> <span class="s2">"DataFrame"</span><span class="p">,</span> <span class="n">table</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">_df</span> <span class="o">=</span> <span class="n">df</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_spark</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">sparkSession</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">_jdf</span><span class="o">.</span><span class="n">writeTo</span><span class="p">(</span><span class="n">table</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.using"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.using.html#pyspark.sql.DataFrameWriterV2.using">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">using</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">provider</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriterV2"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Specifies a provider for the underlying output data source.</span> |
| <span class="sd"> Spark's default catalog supports "parquet", "json", etc.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">using</span><span class="p">(</span><span class="n">provider</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.option"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.option.html#pyspark.sql.DataFrameWriterV2.option">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">option</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">value</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriterV2"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Add a write option.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">option</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">to_str</span><span class="p">(</span><span class="n">value</span><span class="p">))</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.options"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.options.html#pyspark.sql.DataFrameWriterV2.options">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">options</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">options</span><span class="p">:</span> <span class="s2">"OptionalPrimitiveType"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriterV2"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Add write options.</span> |
| <span class="sd"> """</span> |
| <span class="n">options</span> <span class="o">=</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">to_str</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">options</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">options</span><span class="p">(</span><span class="n">options</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.tableProperty"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.tableProperty.html#pyspark.sql.DataFrameWriterV2.tableProperty">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">tableProperty</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="nb">property</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="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriterV2"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Add table property.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">tableProperty</span><span class="p">(</span><span class="nb">property</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.partitionedBy"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.partitionedBy.html#pyspark.sql.DataFrameWriterV2.partitionedBy">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">partitionedBy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">col</span><span class="p">:</span> <span class="n">Column</span><span class="p">,</span> <span class="o">*</span><span class="n">cols</span><span class="p">:</span> <span class="n">Column</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DataFrameWriterV2"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Partition the output table created by `create`, `createOrReplace`, or `replace` using</span> |
| <span class="sd"> the given columns or transforms.</span> |
| |
| <span class="sd"> When specified, the table data will be stored by these values for efficient reads.</span> |
| |
| <span class="sd"> For example, when a table is partitioned by day, it may be stored</span> |
| <span class="sd"> in a directory layout like:</span> |
| |
| <span class="sd"> * `table/day=2019-06-01/`</span> |
| <span class="sd"> * `table/day=2019-06-02/`</span> |
| |
| <span class="sd"> Partitioning is one of the most widely used techniques to optimize physical data layout.</span> |
| <span class="sd"> It provides a coarse-grained index for skipping unnecessary data reads when queries have</span> |
| <span class="sd"> predicates on the partitioned columns. In order for partitioning to work well, the number</span> |
| <span class="sd"> of distinct values in each column should typically be less than tens of thousands.</span> |
| |
| <span class="sd"> `col` and `cols` support only the following functions:</span> |
| |
| <span class="sd"> * :py:func:`pyspark.sql.functions.years`</span> |
| <span class="sd"> * :py:func:`pyspark.sql.functions.months`</span> |
| <span class="sd"> * :py:func:`pyspark.sql.functions.days`</span> |
| <span class="sd"> * :py:func:`pyspark.sql.functions.hours`</span> |
| <span class="sd"> * :py:func:`pyspark.sql.functions.bucket`</span> |
| |
| <span class="sd"> """</span> |
| <span class="n">col</span> <span class="o">=</span> <span class="n">_to_java_column</span><span class="p">(</span><span class="n">col</span><span class="p">)</span> |
| <span class="n">cols</span> <span class="o">=</span> <span class="n">_to_seq</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_spark</span><span class="o">.</span><span class="n">_sc</span><span class="p">,</span> <span class="p">[</span><span class="n">_to_java_column</span><span class="p">(</span><span class="n">c</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">cols</span><span class="p">])</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">partitionedBy</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">cols</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.create"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.create.html#pyspark.sql.DataFrameWriterV2.create">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">create</span><span class="p">(</span><span class="bp">self</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"> Create a new table from the contents of the data frame.</span> |
| |
| <span class="sd"> The new table's schema, partition layout, properties, and other configuration will be</span> |
| <span class="sd"> based on the configuration set on this writer.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">create</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.replace"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.replace.html#pyspark.sql.DataFrameWriterV2.replace">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">replace</span><span class="p">(</span><span class="bp">self</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"> Replace an existing table with the contents of the data frame.</span> |
| |
| <span class="sd"> The existing table's schema, partition layout, properties, and other configuration will be</span> |
| <span class="sd"> replaced with the contents of the data frame and the configuration set on this writer.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">replace</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.createOrReplace"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.createOrReplace.html#pyspark.sql.DataFrameWriterV2.createOrReplace">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">createOrReplace</span><span class="p">(</span><span class="bp">self</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"> Create a new table or replace an existing table with the contents of the data frame.</span> |
| |
| <span class="sd"> The output table's schema, partition layout, properties,</span> |
| <span class="sd"> and other configuration will be based on the contents of the data frame</span> |
| <span class="sd"> and the configuration set on this writer.</span> |
| <span class="sd"> If the table exists, its configuration and data will be replaced.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">createOrReplace</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.append"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.append.html#pyspark.sql.DataFrameWriterV2.append">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">append</span><span class="p">(</span><span class="bp">self</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"> Append the contents of the data frame to the output table.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">append</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.overwrite"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.overwrite.html#pyspark.sql.DataFrameWriterV2.overwrite">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">overwrite</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">condition</span><span class="p">:</span> <span class="n">Column</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"> Overwrite rows matching the given filter condition with the contents of the data frame in</span> |
| <span class="sd"> the output table.</span> |
| <span class="sd"> """</span> |
| <span class="n">condition</span> <span class="o">=</span> <span class="n">_to_java_column</span><span class="p">(</span><span class="n">condition</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">overwrite</span><span class="p">(</span><span class="n">condition</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DataFrameWriterV2.overwritePartitions"><a class="viewcode-back" href="../../../reference/pyspark.sql/api/pyspark.sql.DataFrameWriterV2.overwritePartitions.html#pyspark.sql.DataFrameWriterV2.overwritePartitions">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="mf">3.1</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">overwritePartitions</span><span class="p">(</span><span class="bp">self</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"> Overwrite all partition for which the data frame contains at least one row with the contents</span> |
| <span class="sd"> of the data frame in the output table.</span> |
| |
| <span class="sd"> This operation is equivalent to Hive's `INSERT OVERWRITE ... PARTITION`, which replaces</span> |
| <span class="sd"> partitions dynamically depending on the contents of the data frame.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_jwriter</span><span class="o">.</span><span class="n">overwritePartitions</span><span class="p">()</span></div></div> |
| |
| |
| <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">doctest</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">py4j</span> |
| <span class="kn">from</span> <span class="nn">pyspark.context</span> <span class="kn">import</span> <span class="n">SparkContext</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.sql.readwriter</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">sql</span><span class="o">.</span><span class="n">readwriter</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">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s2">"local[4]"</span><span class="p">,</span> <span class="s2">"PythonTest"</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="o">.</span><span class="n">_getActiveSessionOrCreate</span><span class="p">()</span> |
| <span class="k">except</span> <span class="n">py4j</span><span class="o">.</span><span class="n">protocol</span><span class="o">.</span><span class="n">Py4JError</span><span class="p">:</span> |
| <span class="n">spark</span> <span class="o">=</span> <span class="n">SparkSession</span><span class="p">(</span><span class="n">sc</span><span class="p">)</span> |
| |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"spark"</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</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">sql</span><span class="o">.</span><span class="n">readwriter</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="o">|</span> <span class="n">doctest</span><span class="o">.</span><span class="n">REPORT_NDIFF</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> |
| |
| |
| <!-- Previous / next buttons --> |
| <div class='prev-next-area'> |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| <script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"></script> |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| |
| <div class="footer-item"> |
| <p class="copyright"> |
| © Copyright .<br> |
| </p> |
| </div> |
| |
| <div class="footer-item"> |
| <p class="sphinx-version"> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br> |
| </p> |
| </div> |
| |
| </div> |
| </footer> |
| </body> |
| </html> |
