| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.pandas.resample — PySpark 3.4.2 documentation</title> |
| |
| <link rel="stylesheet" href="../../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css"> |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/open-sans_all/1.44.1/index.css"> |
| <link rel="stylesheet" |
| href="../../../_static/vendor/lato_latin-ext/1.44.1/index.css"> |
| |
| |
| <link rel="stylesheet" href="../../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/js/index.3da636dd464baa7582d2.js"> |
| |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/clipboard.min.js"></script> |
| <script src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/pandas/resample.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="en" /> |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"> |
| <div class="container-xl"> |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo" /> |
| |
| </a> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| <div id="navbar-menu" class="col-lg-9 collapse navbar-collapse"> |
| <ul id="navbar-main-elements" class="navbar-nav mr-auto"> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../index.html">Overview</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../getting_started/index.html">Getting Started</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../user_guide/index.html">User Guides</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../reference/index.html">API Reference</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../development/index.html">Development</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../migration_guide/index.html">Migration Guides</a> |
| </li> |
| |
| |
| </ul> |
| |
| |
| |
| |
| <ul class="navbar-nav"> |
| |
| |
| </ul> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| <div class="col-12 col-md-3 bd-sidebar"><form class="bd-search d-flex align-items-center" action="../../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form> |
| <nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| |
| <div class="bd-toc-item active"> |
| |
| |
| <ul class="nav bd-sidenav"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </ul> |
| |
| </nav> |
| </div> |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| |
| <nav id="bd-toc-nav"> |
| <ul class="nav section-nav flex-column"> |
| |
| </ul> |
| </nav> |
| |
| |
| |
| </div> |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <h1>Source code for pyspark.pandas.resample</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd">A wrapper for ResampledData to behave like pandas Resampler.</span> |
| <span class="sd">"""</span> |
| <span class="kn">from</span> <span class="nn">abc</span> <span class="kn">import</span> <span class="n">ABCMeta</span><span class="p">,</span> <span class="n">abstractmethod</span> |
| <span class="kn">from</span> <span class="nn">distutils.version</span> <span class="kn">import</span> <span class="n">LooseVersion</span> |
| <span class="kn">from</span> <span class="nn">functools</span> <span class="kn">import</span> <span class="n">partial</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">Any</span><span class="p">,</span> |
| <span class="n">Generic</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="p">)</span> |
| |
| <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| |
| <span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span> |
| <span class="kn">from</span> <span class="nn">pandas.tseries.frequencies</span> <span class="kn">import</span> <span class="n">to_offset</span> |
| |
| <span class="k">if</span> <span class="n">LooseVersion</span><span class="p">(</span><span class="n">pd</span><span class="o">.</span><span class="n">__version__</span><span class="p">)</span> <span class="o">>=</span> <span class="n">LooseVersion</span><span class="p">(</span><span class="s2">"1.3.0"</span><span class="p">):</span> |
| <span class="kn">from</span> <span class="nn">pandas.core.common</span> <span class="kn">import</span> <span class="n">_builtin_table</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">pandas.core.base</span> <span class="kn">import</span> <span class="n">SelectionMixin</span> |
| |
| <span class="n">_builtin_table</span> <span class="o">=</span> <span class="n">SelectionMixin</span><span class="o">.</span><span class="n">_builtin_table</span> <span class="c1"># type: ignore[attr-defined]</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</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">Column</span><span class="p">,</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">F</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">NumericType</span><span class="p">,</span> |
| <span class="n">StructField</span><span class="p">,</span> |
| <span class="n">TimestampType</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">pandas</span> <span class="k">as</span> <span class="n">ps</span> <span class="c1"># For running doctests and reference resolution in PyCharm.</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas._typing</span> <span class="kn">import</span> <span class="n">FrameLike</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.frame</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.internal</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">InternalField</span><span class="p">,</span> |
| <span class="n">InternalFrame</span><span class="p">,</span> |
| <span class="n">SPARK_DEFAULT_INDEX_NAME</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.missing.resample</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">MissingPandasLikeDataFrameResampler</span><span class="p">,</span> |
| <span class="n">MissingPandasLikeSeriesResampler</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.series</span> <span class="kn">import</span> <span class="n">Series</span><span class="p">,</span> <span class="n">first_series</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.utils</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">scol_for</span><span class="p">,</span> |
| <span class="n">verify_temp_column_name</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">Resampler</span><span class="p">(</span><span class="n">Generic</span><span class="p">[</span><span class="n">FrameLike</span><span class="p">],</span> <span class="n">metaclass</span><span class="o">=</span><span class="n">ABCMeta</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Class for resampling datetimelike data, a groupby-like operation.</span> |
| |
| <span class="sd"> It's easiest to use obj.resample(...) to use Resampler.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> psdf : DataFrame</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> a Resampler of the appropriate type</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> After resampling, see aggregate, apply, and transform functions.</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">psdf</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> |
| <span class="n">resamplekey</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Series</span><span class="p">],</span> |
| <span class="n">rule</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">closed</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">label</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">agg_columns</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">Series</span><span class="p">]</span> <span class="o">=</span> <span class="p">[],</span> |
| <span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_psdf</span> <span class="o">=</span> <span class="n">psdf</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_resamplekey</span> <span class="o">=</span> <span class="n">resamplekey</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_offset</span> <span class="o">=</span> <span class="n">to_offset</span><span class="p">(</span><span class="n">rule</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_offset</span><span class="o">.</span><span class="n">rule_code</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"A-DEC"</span><span class="p">,</span> <span class="s2">"M"</span><span class="p">,</span> <span class="s2">"D"</span><span class="p">,</span> <span class="s2">"H"</span><span class="p">,</span> <span class="s2">"T"</span><span class="p">,</span> <span class="s2">"S"</span><span class="p">]:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"rule code </span><span class="si">{}</span><span class="s2"> is not supported"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_offset</span><span class="o">.</span><span class="n">rule_code</span><span class="p">))</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_offset</span><span class="p">,</span> <span class="s2">"n"</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"rule offset must be positive"</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">closed</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">_closed</span> <span class="o">=</span> <span class="s2">"right"</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_offset</span><span class="o">.</span><span class="n">rule_code</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"A-DEC"</span><span class="p">,</span> <span class="s2">"M"</span><span class="p">]</span> <span class="k">else</span> <span class="s2">"left"</span> |
| <span class="k">elif</span> <span class="n">closed</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"left"</span><span class="p">,</span> <span class="s2">"right"</span><span class="p">]:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_closed</span> <span class="o">=</span> <span class="n">closed</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"invalid closed: '</span><span class="si">{}</span><span class="s2">'"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">closed</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="n">label</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">_label</span> <span class="o">=</span> <span class="s2">"right"</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_offset</span><span class="o">.</span><span class="n">rule_code</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"A-DEC"</span><span class="p">,</span> <span class="s2">"M"</span><span class="p">]</span> <span class="k">else</span> <span class="s2">"left"</span> |
| <span class="k">elif</span> <span class="n">label</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"left"</span><span class="p">,</span> <span class="s2">"right"</span><span class="p">]:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_label</span> <span class="o">=</span> <span class="n">label</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"invalid label: '</span><span class="si">{}</span><span class="s2">'"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">label</span><span class="p">))</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_agg_columns</span> <span class="o">=</span> <span class="n">agg_columns</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">_resamplekey_scol</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_resamplekey</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_psdf</span><span class="o">.</span><span class="n">index</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">column</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">_resamplekey</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">column</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">_agg_columns_scols</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="n">Column</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">s</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">column</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_agg_columns</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="nf">_bin_time_stamp</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">origin</span><span class="p">:</span> <span class="n">pd</span><span class="o">.</span><span class="n">Timestamp</span><span class="p">,</span> <span class="n">ts_scol</span><span class="p">:</span> <span class="n">Column</span><span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="n">sql_utils</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="o">.</span><span class="n">_active_spark_context</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">PythonSQLUtils</span> |
| <span class="n">origin_scol</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="n">origin</span><span class="p">)</span> |
| <span class="p">(</span><span class="n">rule_code</span><span class="p">,</span> <span class="n">n</span><span class="p">)</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_offset</span><span class="o">.</span><span class="n">rule_code</span><span class="p">,</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_offset</span><span class="p">,</span> <span class="s2">"n"</span><span class="p">))</span> |
| <span class="n">left_closed</span><span class="p">,</span> <span class="n">right_closed</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_closed</span> <span class="o">==</span> <span class="s2">"left"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_closed</span> <span class="o">==</span> <span class="s2">"right"</span><span class="p">)</span> |
| <span class="n">left_labeled</span><span class="p">,</span> <span class="n">right_labeled</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_label</span> <span class="o">==</span> <span class="s2">"left"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_label</span> <span class="o">==</span> <span class="s2">"right"</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">rule_code</span> <span class="o">==</span> <span class="s2">"A-DEC"</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="p">(</span> |
| <span class="n">origin</span><span class="o">.</span><span class="n">month</span> <span class="o">==</span> <span class="mi">12</span> |
| <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">day</span> <span class="o">==</span> <span class="mi">31</span> |
| <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">hour</span> <span class="o">==</span> <span class="mi">0</span> |
| <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">minute</span> <span class="o">==</span> <span class="mi">0</span> |
| <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">second</span> <span class="o">==</span> <span class="mi">0</span> |
| <span class="p">)</span> |
| |
| <span class="n">diff</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">year</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">-</span> <span class="n">F</span><span class="o">.</span><span class="n">year</span><span class="p">(</span><span class="n">origin_scol</span><span class="p">)</span> |
| <span class="n">mod</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> <span class="k">if</span> <span class="n">n</span> <span class="o">==</span> <span class="mi">1</span> <span class="k">else</span> <span class="p">(</span><span class="n">diff</span> <span class="o">%</span> <span class="n">n</span><span class="p">)</span> |
| <span class="n">edge_cond</span> <span class="o">=</span> <span class="p">(</span><span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="o">&</span> <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">month</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">==</span> <span class="mi">12</span><span class="p">)</span> <span class="o">&</span> <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">dayofmonth</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">==</span> <span class="mi">31</span><span class="p">)</span> |
| |
| <span class="n">edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">year</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">left_closed</span> <span class="ow">and</span> <span class="n">right_labeled</span><span class="p">:</span> |
| <span class="n">edge_label</span> <span class="o">+=</span> <span class="n">n</span> |
| <span class="k">elif</span> <span class="n">right_closed</span> <span class="ow">and</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="n">edge_label</span> <span class="o">-=</span> <span class="n">n</span> |
| |
| <span class="k">if</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="n">non_edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">year</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">-</span> <span class="n">n</span><span class="p">)</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">year</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">-</span> <span class="n">mod</span> |
| <span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">non_edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">year</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">))</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">year</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">-</span> <span class="p">(</span><span class="n">mod</span> <span class="o">-</span> <span class="n">n</span><span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">to_timestamp</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">make_date</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">edge_cond</span><span class="p">,</span> <span class="n">edge_label</span><span class="p">)</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span><span class="n">non_edge_label</span><span class="p">),</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="mi">12</span><span class="p">),</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="mi">31</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="k">elif</span> <span class="n">rule_code</span> <span class="o">==</span> <span class="s2">"M"</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="p">(</span> |
| <span class="n">origin</span><span class="o">.</span><span class="n">is_month_end</span> |
| <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">hour</span> <span class="o">==</span> <span class="mi">0</span> |
| <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">minute</span> <span class="o">==</span> <span class="mi">0</span> |
| <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">second</span> <span class="o">==</span> <span class="mi">0</span> |
| <span class="p">)</span> |
| |
| <span class="n">diff</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">year</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">-</span> <span class="n">F</span><span class="o">.</span><span class="n">year</span><span class="p">(</span><span class="n">origin_scol</span><span class="p">))</span> <span class="o">*</span> <span class="mi">12</span> |
| <span class="o">+</span> <span class="n">F</span><span class="o">.</span><span class="n">month</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> |
| <span class="o">-</span> <span class="n">F</span><span class="o">.</span><span class="n">month</span><span class="p">(</span><span class="n">origin_scol</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="n">mod</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> <span class="k">if</span> <span class="n">n</span> <span class="o">==</span> <span class="mi">1</span> <span class="k">else</span> <span class="p">(</span><span class="n">diff</span> <span class="o">%</span> <span class="n">n</span><span class="p">)</span> |
| <span class="n">edge_cond</span> <span class="o">=</span> <span class="p">(</span><span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="o">&</span> <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">dayofmonth</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">==</span> <span class="n">F</span><span class="o">.</span><span class="n">dayofmonth</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">last_day</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)))</span> |
| |
| <span class="n">truncated_ts_scol</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">date_trunc</span><span class="p">(</span><span class="s2">"MONTH"</span><span class="p">,</span> <span class="n">ts_scol</span><span class="p">)</span> |
| <span class="n">edge_label</span> <span class="o">=</span> <span class="n">truncated_ts_scol</span> |
| <span class="k">if</span> <span class="n">left_closed</span> <span class="ow">and</span> <span class="n">right_labeled</span><span class="p">:</span> |
| <span class="n">edge_label</span> <span class="o">+=</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="s2">"MONTH"</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="n">n</span><span class="p">)</span><span class="o">.</span><span class="n">_jc</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">right_closed</span> <span class="ow">and</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="n">edge_label</span> <span class="o">-=</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="s2">"MONTH"</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="n">n</span><span class="p">)</span><span class="o">.</span><span class="n">_jc</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="n">non_edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">,</span> |
| <span class="n">truncated_ts_scol</span> <span class="o">-</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="s2">"MONTH"</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="n">n</span><span class="p">)</span><span class="o">.</span><span class="n">_jc</span><span class="p">),</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span><span class="n">truncated_ts_scol</span> <span class="o">-</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="s2">"MONTH"</span><span class="p">,</span> <span class="n">mod</span><span class="o">.</span><span class="n">_jc</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">non_edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">,</span> <span class="n">truncated_ts_scol</span><span class="p">)</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span> |
| <span class="n">truncated_ts_scol</span> <span class="o">-</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="s2">"MONTH"</span><span class="p">,</span> <span class="p">(</span><span class="n">mod</span> <span class="o">-</span> <span class="n">n</span><span class="p">)</span><span class="o">.</span><span class="n">_jc</span><span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">to_timestamp</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">last_day</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">edge_cond</span><span class="p">,</span> <span class="n">edge_label</span><span class="p">)</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span><span class="n">non_edge_label</span><span class="p">))</span> |
| <span class="p">)</span> |
| |
| <span class="k">elif</span> <span class="n">rule_code</span> <span class="o">==</span> <span class="s2">"D"</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">origin</span><span class="o">.</span><span class="n">hour</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">minute</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">second</span> <span class="o">==</span> <span class="mi">0</span> |
| |
| <span class="k">if</span> <span class="n">n</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="c1"># NOTE: the logic to process '1D' is different from the cases with n>1,</span> |
| <span class="c1"># since hour/minute/second parts are taken into account to determine edges!</span> |
| <span class="n">edge_cond</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">hour</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="o">&</span> <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">minute</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="o">&</span> <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">second</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">left_closed</span> <span class="ow">and</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">date_trunc</span><span class="p">(</span><span class="s2">"DAY"</span><span class="p">,</span> <span class="n">ts_scol</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">left_closed</span> <span class="ow">and</span> <span class="n">right_labeled</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">date_trunc</span><span class="p">(</span><span class="s2">"DAY"</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">date_add</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span> |
| <span class="k">elif</span> <span class="n">right_closed</span> <span class="ow">and</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">edge_cond</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">date_trunc</span><span class="p">(</span><span class="s2">"DAY"</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">date_sub</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">,</span> <span class="mi">1</span><span class="p">)))</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">date_trunc</span><span class="p">(</span><span class="s2">"DAY"</span><span class="p">,</span> <span class="n">ts_scol</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">edge_cond</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">date_trunc</span><span class="p">(</span><span class="s2">"DAY"</span><span class="p">,</span> <span class="n">ts_scol</span><span class="p">))</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">date_trunc</span><span class="p">(</span><span class="s2">"DAY"</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">date_add</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span> |
| <span class="p">)</span> |
| |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">diff</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">datediff</span><span class="p">(</span><span class="n">end</span><span class="o">=</span><span class="n">ts_scol</span><span class="p">,</span> <span class="n">start</span><span class="o">=</span><span class="n">origin_scol</span><span class="p">)</span> |
| <span class="n">mod</span> <span class="o">=</span> <span class="n">diff</span> <span class="o">%</span> <span class="n">n</span> |
| |
| <span class="n">edge_cond</span> <span class="o">=</span> <span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span> |
| |
| <span class="n">truncated_ts_scol</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">date_trunc</span><span class="p">(</span><span class="s2">"DAY"</span><span class="p">,</span> <span class="n">ts_scol</span><span class="p">)</span> |
| <span class="n">edge_label</span> <span class="o">=</span> <span class="n">truncated_ts_scol</span> |
| <span class="k">if</span> <span class="n">left_closed</span> <span class="ow">and</span> <span class="n">right_labeled</span><span class="p">:</span> |
| <span class="n">edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">date_add</span><span class="p">(</span><span class="n">truncated_ts_scol</span><span class="p">,</span> <span class="n">n</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">right_closed</span> <span class="ow">and</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="n">edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">date_sub</span><span class="p">(</span><span class="n">truncated_ts_scol</span><span class="p">,</span> <span class="n">n</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="n">non_edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">date_sub</span><span class="p">(</span><span class="n">truncated_ts_scol</span><span class="p">,</span> <span class="n">mod</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">non_edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">date_sub</span><span class="p">(</span><span class="n">truncated_ts_scol</span><span class="p">,</span> <span class="n">mod</span> <span class="o">-</span> <span class="n">n</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">edge_cond</span><span class="p">,</span> <span class="n">edge_label</span><span class="p">)</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span><span class="n">non_edge_label</span><span class="p">)</span> |
| |
| <span class="k">elif</span> <span class="n">rule_code</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"H"</span><span class="p">,</span> <span class="s2">"T"</span><span class="p">,</span> <span class="s2">"S"</span><span class="p">]:</span> |
| <span class="n">unit_mapping</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"H"</span><span class="p">:</span> <span class="s2">"HOUR"</span><span class="p">,</span> <span class="s2">"T"</span><span class="p">:</span> <span class="s2">"MINUTE"</span><span class="p">,</span> <span class="s2">"S"</span><span class="p">:</span> <span class="s2">"SECOND"</span><span class="p">}</span> |
| <span class="n">unit_str</span> <span class="o">=</span> <span class="n">unit_mapping</span><span class="p">[</span><span class="n">rule_code</span><span class="p">]</span> |
| |
| <span class="n">truncated_ts_scol</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">date_trunc</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="n">ts_scol</span><span class="p">)</span> |
| <span class="n">diff</span> <span class="o">=</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">timestampDiff</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="n">origin_scol</span><span class="o">.</span><span class="n">_jc</span><span class="p">,</span> <span class="n">truncated_ts_scol</span><span class="o">.</span><span class="n">_jc</span><span class="p">)</span> |
| <span class="n">mod</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> <span class="k">if</span> <span class="n">n</span> <span class="o">==</span> <span class="mi">1</span> <span class="k">else</span> <span class="p">(</span><span class="n">diff</span> <span class="o">%</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="n">n</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="n">rule_code</span> <span class="o">==</span> <span class="s2">"H"</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">origin</span><span class="o">.</span><span class="n">minute</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">origin</span><span class="o">.</span><span class="n">second</span> <span class="o">==</span> <span class="mi">0</span> |
| <span class="n">edge_cond</span> <span class="o">=</span> <span class="p">(</span><span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="o">&</span> <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">minute</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="o">&</span> <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">second</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">rule_code</span> <span class="o">==</span> <span class="s2">"T"</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">origin</span><span class="o">.</span><span class="n">second</span> <span class="o">==</span> <span class="mi">0</span> |
| <span class="n">edge_cond</span> <span class="o">=</span> <span class="p">(</span><span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="o">&</span> <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">second</span><span class="p">(</span><span class="n">ts_scol</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">edge_cond</span> <span class="o">=</span> <span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span> |
| |
| <span class="n">edge_label</span> <span class="o">=</span> <span class="n">truncated_ts_scol</span> |
| <span class="k">if</span> <span class="n">left_closed</span> <span class="ow">and</span> <span class="n">right_labeled</span><span class="p">:</span> |
| <span class="n">edge_label</span> <span class="o">+=</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="n">n</span><span class="p">)</span><span class="o">.</span><span class="n">_jc</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">right_closed</span> <span class="ow">and</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="n">edge_label</span> <span class="o">-=</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="n">n</span><span class="p">)</span><span class="o">.</span><span class="n">_jc</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">left_labeled</span><span class="p">:</span> |
| <span class="n">non_edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">,</span> <span class="n">truncated_ts_scol</span><span class="p">)</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span> |
| <span class="n">truncated_ts_scol</span> <span class="o">-</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="n">mod</span><span class="o">.</span><span class="n">_jc</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">non_edge_label</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">mod</span> <span class="o">==</span> <span class="mi">0</span><span class="p">,</span> |
| <span class="n">truncated_ts_scol</span> <span class="o">+</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="n">n</span><span class="p">)</span><span class="o">.</span><span class="n">_jc</span><span class="p">),</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span><span class="n">truncated_ts_scol</span> <span class="o">-</span> <span class="n">sql_utils</span><span class="o">.</span><span class="n">makeInterval</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="p">(</span><span class="n">mod</span> <span class="o">-</span> <span class="n">n</span><span class="p">)</span><span class="o">.</span><span class="n">_jc</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span><span class="n">edge_cond</span><span class="p">,</span> <span class="n">edge_label</span><span class="p">)</span><span class="o">.</span><span class="n">otherwise</span><span class="p">(</span><span class="n">non_edge_label</span><span class="p">)</span> |
| |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Got the unexpected unit </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">rule_code</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">_downsample</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">f</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Downsample the defined function.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> how : string / mapped function</span> |
| <span class="sd"> **kwargs : kw args passed to how function</span> |
| <span class="sd"> """</span> |
| |
| <span class="c1"># a simple example to illustrate the computation:</span> |
| <span class="c1"># dates = [</span> |
| <span class="c1"># datetime(2012, 1, 2),</span> |
| <span class="c1"># datetime(2012, 5, 3),</span> |
| <span class="c1"># datetime(2022, 5, 3),</span> |
| <span class="c1"># ]</span> |
| <span class="c1"># index = pd.DatetimeIndex(dates)</span> |
| <span class="c1"># pdf = pd.DataFrame(np.array([1,2,3]), index=index, columns=['A'])</span> |
| <span class="c1"># pdf.resample('3Y').max()</span> |
| <span class="c1"># A</span> |
| <span class="c1"># 2012-12-31 2.0</span> |
| <span class="c1"># 2015-12-31 NaN</span> |
| <span class="c1"># 2018-12-31 NaN</span> |
| <span class="c1"># 2021-12-31 NaN</span> |
| <span class="c1"># 2024-12-31 3.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># in this case:</span> |
| <span class="c1"># 1, obtain one origin point to bin all timestamps, we can get one (2009-12-31)</span> |
| <span class="c1"># from the minimum timestamp (2012-01-02);</span> |
| <span class="c1"># 2, the default intervals for 'Y' are right-closed, so intervals are:</span> |
| <span class="c1"># (2009-12-31, 2012-12-31], (2012-12-31, 2015-12-31], (2015-12-31, 2018-12-31], ...</span> |
| <span class="c1"># 3, bin all timestamps, for example, 2022-05-03 belongs to interval</span> |
| <span class="c1"># (2021-12-31, 2024-12-31], since the default label is 'right', label it with the right</span> |
| <span class="c1"># edge 2024-12-31;</span> |
| <span class="c1"># 4, some intervals maybe too large for this down sampling, so we need to pad the dataframe</span> |
| <span class="c1"># to avoid missing some results, like: 2015-12-31, 2018-12-31 and 2021-12-31;</span> |
| <span class="c1"># 5, union the binned dataframe and padded dataframe, and apply aggregation 'max' to get</span> |
| <span class="c1"># the final results;</span> |
| |
| <span class="c1"># one action to obtain the range, in the future we may cache it in the index.</span> |
| <span class="n">ts_min</span><span class="p">,</span> <span class="n">ts_max</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_psdf</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">spark_frame</span><span class="o">.</span><span class="n">select</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">min</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_resamplekey_scol</span><span class="p">),</span> <span class="n">F</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_resamplekey_scol</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="o">.</span><span class="n">toPandas</span><span class="p">()</span> |
| <span class="o">.</span><span class="n">iloc</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="p">)</span> |
| |
| <span class="c1"># the logic to obtain an origin point to bin the timestamps is too complex to follow,</span> |
| <span class="c1"># here just use Pandas' resample on a 1-length series to get it.</span> |
| <span class="n">ts_origin</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="mi">0</span><span class="p">],</span> <span class="n">index</span><span class="o">=</span><span class="p">[</span><span class="n">ts_min</span><span class="p">])</span> |
| <span class="o">.</span><span class="n">resample</span><span class="p">(</span><span class="n">rule</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_offset</span><span class="o">.</span><span class="n">freqstr</span><span class="p">,</span> <span class="n">closed</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_closed</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s2">"left"</span><span class="p">)</span> |
| <span class="o">.</span><span class="n">sum</span><span class="p">()</span> |
| <span class="o">.</span><span class="n">index</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="p">)</span> |
| <span class="k">assert</span> <span class="n">ts_origin</span> <span class="o"><=</span> <span class="n">ts_min</span> |
| |
| <span class="n">bin_col_name</span> <span class="o">=</span> <span class="s2">"__tmp_resample_bin_col__"</span> |
| <span class="n">bin_col_label</span> <span class="o">=</span> <span class="n">verify_temp_column_name</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_psdf</span><span class="p">,</span> <span class="n">bin_col_name</span><span class="p">)</span> |
| <span class="n">bin_col_field</span> <span class="o">=</span> <span class="n">InternalField</span><span class="p">(</span> |
| <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">dtype</span><span class="p">(</span><span class="s2">"datetime64[ns]"</span><span class="p">),</span> |
| <span class="n">struct_field</span><span class="o">=</span><span class="n">StructField</span><span class="p">(</span><span class="n">bin_col_name</span><span class="p">,</span> <span class="n">TimestampType</span><span class="p">(),</span> <span class="kc">True</span><span class="p">),</span> |
| <span class="p">)</span> |
| <span class="n">bin_scol</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bin_time_stamp</span><span class="p">(</span> |
| <span class="n">ts_origin</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_resamplekey_scol</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="n">agg_columns</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="n">psser</span> <span class="k">for</span> <span class="n">psser</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_agg_columns</span> <span class="k">if</span> <span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">psser</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">data_type</span><span class="p">,</span> <span class="n">NumericType</span><span class="p">))</span> |
| <span class="p">]</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">agg_columns</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span> |
| |
| <span class="c1"># in the binning side, label the timestamps according to the origin and the freq(rule)</span> |
| <span class="n">bin_sdf</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_psdf</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">spark_frame</span><span class="o">.</span><span class="n">select</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="n">SPARK_DEFAULT_INDEX_NAME</span><span class="p">),</span> |
| <span class="n">bin_scol</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="n">bin_col_name</span><span class="p">),</span> |
| <span class="o">*</span><span class="p">[</span><span class="n">psser</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">column</span> <span class="k">for</span> <span class="n">psser</span> <span class="ow">in</span> <span class="n">agg_columns</span><span class="p">],</span> |
| <span class="p">)</span> |
| |
| <span class="c1"># in the padding side, insert necessary points</span> |
| <span class="c1"># again, directly apply Pandas' resample on a 2-length series to obtain the indices</span> |
| <span class="n">pad_sdf</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">ps</span><span class="o">.</span><span class="n">from_pandas</span><span class="p">(</span> |
| <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">([</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span> <span class="n">index</span><span class="o">=</span><span class="p">[</span><span class="n">ts_min</span><span class="p">,</span> <span class="n">ts_max</span><span class="p">])</span> |
| <span class="o">.</span><span class="n">resample</span><span class="p">(</span><span class="n">rule</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_offset</span><span class="o">.</span><span class="n">freqstr</span><span class="p">,</span> <span class="n">closed</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_closed</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_label</span><span class="p">)</span> |
| <span class="o">.</span><span class="n">sum</span><span class="p">()</span> |
| <span class="o">.</span><span class="n">index</span> |
| <span class="p">)</span> |
| <span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">spark_frame</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="n">SPARK_DEFAULT_INDEX_NAME</span><span class="p">)</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="n">bin_col_name</span><span class="p">))</span> |
| <span class="o">.</span><span class="n">where</span><span class="p">((</span><span class="n">ts_min</span> <span class="o"><=</span> <span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="n">bin_col_name</span><span class="p">))</span> <span class="o">&</span> <span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="n">bin_col_name</span><span class="p">)</span> <span class="o"><=</span> <span class="n">ts_max</span><span class="p">))</span> |
| <span class="p">)</span> |
| |
| <span class="c1"># union the above two spark dataframes.</span> |
| <span class="n">sdf</span> <span class="o">=</span> <span class="n">bin_sdf</span><span class="o">.</span><span class="n">unionByName</span><span class="p">(</span><span class="n">pad_sdf</span><span class="p">,</span> <span class="n">allowMissingColumns</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span><span class="o">.</span><span class="n">where</span><span class="p">(</span> |
| <span class="o">~</span><span class="n">F</span><span class="o">.</span><span class="n">isnull</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="n">bin_col_name</span><span class="p">))</span> |
| <span class="p">)</span> |
| |
| <span class="n">internal</span> <span class="o">=</span> <span class="n">InternalFrame</span><span class="p">(</span> |
| <span class="n">spark_frame</span><span class="o">=</span><span class="n">sdf</span><span class="p">,</span> |
| <span class="n">index_spark_columns</span><span class="o">=</span><span class="p">[</span><span class="n">scol_for</span><span class="p">(</span><span class="n">sdf</span><span class="p">,</span> <span class="n">SPARK_DEFAULT_INDEX_NAME</span><span class="p">)],</span> |
| <span class="n">data_spark_columns</span><span class="o">=</span><span class="p">[</span><span class="n">F</span><span class="o">.</span><span class="n">col</span><span class="p">(</span><span class="n">bin_col_name</span><span class="p">)]</span> |
| <span class="o">+</span> <span class="p">[</span><span class="n">scol_for</span><span class="p">(</span><span class="n">sdf</span><span class="p">,</span> <span class="n">psser</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">data_spark_column_names</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="k">for</span> <span class="n">psser</span> <span class="ow">in</span> <span class="n">agg_columns</span><span class="p">],</span> |
| <span class="n">column_labels</span><span class="o">=</span><span class="p">[</span><span class="n">bin_col_label</span><span class="p">]</span> <span class="o">+</span> <span class="p">[</span><span class="n">psser</span><span class="o">.</span><span class="n">_column_label</span> <span class="k">for</span> <span class="n">psser</span> <span class="ow">in</span> <span class="n">agg_columns</span><span class="p">],</span> |
| <span class="n">data_fields</span><span class="o">=</span><span class="p">[</span><span class="n">bin_col_field</span><span class="p">]</span> |
| <span class="o">+</span> <span class="p">[</span><span class="n">psser</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">data_fields</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">nullable</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="k">for</span> <span class="n">psser</span> <span class="ow">in</span> <span class="n">agg_columns</span><span class="p">],</span> |
| <span class="n">column_label_names</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_psdf</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">column_label_names</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="n">psdf</span><span class="p">:</span> <span class="n">DataFrame</span> <span class="o">=</span> <span class="n">DataFrame</span><span class="p">(</span><span class="n">internal</span><span class="p">)</span> |
| |
| <span class="n">groupby</span> <span class="o">=</span> <span class="n">psdf</span><span class="o">.</span><span class="n">groupby</span><span class="p">(</span><span class="n">psdf</span><span class="o">.</span><span class="n">_psser_for</span><span class="p">(</span><span class="n">bin_col_label</span><span class="p">),</span> <span class="n">dropna</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> |
| <span class="n">downsampled</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">groupby</span><span class="p">,</span> <span class="n">f</span><span class="p">)()</span> |
| <span class="n">downsampled</span><span class="o">.</span><span class="n">index</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="k">return</span> <span class="n">downsampled</span> |
| |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">_handle_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">psdf</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">)</span> <span class="o">-></span> <span class="n">FrameLike</span><span class="p">:</span> |
| <span class="k">pass</span> |
| |
| <div class="viewcode-block" id="Resampler.min"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.resample.Resampler.min.html#pyspark.pandas.resample.Resampler.min">[docs]</a> <span class="k">def</span> <span class="nf">min</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">FrameLike</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute min of resampled values.</span> |
| |
| <span class="sd"> .. versionadded:: 3.4.0</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.groupby</span> |
| <span class="sd"> pyspark.pandas.DataFrame.groupby</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> from datetime import datetime</span> |
| <span class="sd"> >>> np.random.seed(22)</span> |
| <span class="sd"> >>> dates = [</span> |
| <span class="sd"> ... datetime(2022, 5, 1, 4, 5, 6),</span> |
| <span class="sd"> ... datetime(2022, 5, 3),</span> |
| <span class="sd"> ... datetime(2022, 5, 3, 23, 59, 59),</span> |
| <span class="sd"> ... datetime(2022, 5, 4),</span> |
| <span class="sd"> ... pd.NaT,</span> |
| <span class="sd"> ... datetime(2022, 5, 4, 0, 0, 1),</span> |
| <span class="sd"> ... datetime(2022, 5, 11),</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> df = ps.DataFrame(</span> |
| <span class="sd"> ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]</span> |
| <span class="sd"> ... )</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 04:05:06 0.208461 0.481681</span> |
| <span class="sd"> 2022-05-03 00:00:00 0.420538 0.859182</span> |
| <span class="sd"> 2022-05-03 23:59:59 0.171162 0.338864</span> |
| <span class="sd"> 2022-05-04 00:00:00 0.270533 0.691041</span> |
| <span class="sd"> NaT 0.220405 0.811951</span> |
| <span class="sd"> 2022-05-04 00:00:01 0.010527 0.561204</span> |
| <span class="sd"> 2022-05-11 00:00:00 0.813726 0.745100</span> |
| <span class="sd"> >>> df.resample("3D").min().sort_index()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 0.171162 0.338864</span> |
| <span class="sd"> 2022-05-04 0.010527 0.561204</span> |
| <span class="sd"> 2022-05-07 NaN NaN</span> |
| <span class="sd"> 2022-05-10 0.813726 0.745100</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_handle_output</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_downsample</span><span class="p">(</span><span class="s2">"min"</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="Resampler.max"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.resample.Resampler.max.html#pyspark.pandas.resample.Resampler.max">[docs]</a> <span class="k">def</span> <span class="nf">max</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">FrameLike</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute max of resampled values.</span> |
| |
| <span class="sd"> .. versionadded:: 3.4.0</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.groupby</span> |
| <span class="sd"> pyspark.pandas.DataFrame.groupby</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> from datetime import datetime</span> |
| <span class="sd"> >>> np.random.seed(22)</span> |
| <span class="sd"> >>> dates = [</span> |
| <span class="sd"> ... datetime(2022, 5, 1, 4, 5, 6),</span> |
| <span class="sd"> ... datetime(2022, 5, 3),</span> |
| <span class="sd"> ... datetime(2022, 5, 3, 23, 59, 59),</span> |
| <span class="sd"> ... datetime(2022, 5, 4),</span> |
| <span class="sd"> ... pd.NaT,</span> |
| <span class="sd"> ... datetime(2022, 5, 4, 0, 0, 1),</span> |
| <span class="sd"> ... datetime(2022, 5, 11),</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> df = ps.DataFrame(</span> |
| <span class="sd"> ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]</span> |
| <span class="sd"> ... )</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 04:05:06 0.208461 0.481681</span> |
| <span class="sd"> 2022-05-03 00:00:00 0.420538 0.859182</span> |
| <span class="sd"> 2022-05-03 23:59:59 0.171162 0.338864</span> |
| <span class="sd"> 2022-05-04 00:00:00 0.270533 0.691041</span> |
| <span class="sd"> NaT 0.220405 0.811951</span> |
| <span class="sd"> 2022-05-04 00:00:01 0.010527 0.561204</span> |
| <span class="sd"> 2022-05-11 00:00:00 0.813726 0.745100</span> |
| <span class="sd"> >>> df.resample("3D").max().sort_index()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 0.420538 0.859182</span> |
| <span class="sd"> 2022-05-04 0.270533 0.691041</span> |
| <span class="sd"> 2022-05-07 NaN NaN</span> |
| <span class="sd"> 2022-05-10 0.813726 0.745100</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_handle_output</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_downsample</span><span class="p">(</span><span class="s2">"max"</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="Resampler.sum"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.resample.Resampler.sum.html#pyspark.pandas.resample.Resampler.sum">[docs]</a> <span class="k">def</span> <span class="nf">sum</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">FrameLike</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute sum of resampled values.</span> |
| |
| <span class="sd"> .. versionadded:: 3.4.0</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.groupby</span> |
| <span class="sd"> pyspark.pandas.DataFrame.groupby</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> from datetime import datetime</span> |
| <span class="sd"> >>> np.random.seed(22)</span> |
| <span class="sd"> >>> dates = [</span> |
| <span class="sd"> ... datetime(2022, 5, 1, 4, 5, 6),</span> |
| <span class="sd"> ... datetime(2022, 5, 3),</span> |
| <span class="sd"> ... datetime(2022, 5, 3, 23, 59, 59),</span> |
| <span class="sd"> ... datetime(2022, 5, 4),</span> |
| <span class="sd"> ... pd.NaT,</span> |
| <span class="sd"> ... datetime(2022, 5, 4, 0, 0, 1),</span> |
| <span class="sd"> ... datetime(2022, 5, 11),</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> df = ps.DataFrame(</span> |
| <span class="sd"> ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]</span> |
| <span class="sd"> ... )</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 04:05:06 0.208461 0.481681</span> |
| <span class="sd"> 2022-05-03 00:00:00 0.420538 0.859182</span> |
| <span class="sd"> 2022-05-03 23:59:59 0.171162 0.338864</span> |
| <span class="sd"> 2022-05-04 00:00:00 0.270533 0.691041</span> |
| <span class="sd"> NaT 0.220405 0.811951</span> |
| <span class="sd"> 2022-05-04 00:00:01 0.010527 0.561204</span> |
| <span class="sd"> 2022-05-11 00:00:00 0.813726 0.745100</span> |
| <span class="sd"> >>> df.resample("3D").sum().sort_index()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 0.800160 1.679727</span> |
| <span class="sd"> 2022-05-04 0.281060 1.252245</span> |
| <span class="sd"> 2022-05-07 0.000000 0.000000</span> |
| <span class="sd"> 2022-05-10 0.813726 0.745100</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_handle_output</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_downsample</span><span class="p">(</span><span class="s2">"sum"</span><span class="p">)</span><span class="o">.</span><span class="n">fillna</span><span class="p">(</span><span class="mf">0.0</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="Resampler.mean"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.resample.Resampler.mean.html#pyspark.pandas.resample.Resampler.mean">[docs]</a> <span class="k">def</span> <span class="nf">mean</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">FrameLike</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute mean of resampled values.</span> |
| |
| <span class="sd"> .. versionadded:: 3.4.0</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.groupby</span> |
| <span class="sd"> pyspark.pandas.DataFrame.groupby</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> from datetime import datetime</span> |
| <span class="sd"> >>> np.random.seed(22)</span> |
| <span class="sd"> >>> dates = [</span> |
| <span class="sd"> ... datetime(2022, 5, 1, 4, 5, 6),</span> |
| <span class="sd"> ... datetime(2022, 5, 3),</span> |
| <span class="sd"> ... datetime(2022, 5, 3, 23, 59, 59),</span> |
| <span class="sd"> ... datetime(2022, 5, 4),</span> |
| <span class="sd"> ... pd.NaT,</span> |
| <span class="sd"> ... datetime(2022, 5, 4, 0, 0, 1),</span> |
| <span class="sd"> ... datetime(2022, 5, 11),</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> df = ps.DataFrame(</span> |
| <span class="sd"> ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]</span> |
| <span class="sd"> ... )</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 04:05:06 0.208461 0.481681</span> |
| <span class="sd"> 2022-05-03 00:00:00 0.420538 0.859182</span> |
| <span class="sd"> 2022-05-03 23:59:59 0.171162 0.338864</span> |
| <span class="sd"> 2022-05-04 00:00:00 0.270533 0.691041</span> |
| <span class="sd"> NaT 0.220405 0.811951</span> |
| <span class="sd"> 2022-05-04 00:00:01 0.010527 0.561204</span> |
| <span class="sd"> 2022-05-11 00:00:00 0.813726 0.745100</span> |
| <span class="sd"> >>> df.resample("3D").mean().sort_index()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 0.266720 0.559909</span> |
| <span class="sd"> 2022-05-04 0.140530 0.626123</span> |
| <span class="sd"> 2022-05-07 NaN NaN</span> |
| <span class="sd"> 2022-05-10 0.813726 0.745100</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_handle_output</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_downsample</span><span class="p">(</span><span class="s2">"mean"</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="Resampler.std"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.resample.Resampler.std.html#pyspark.pandas.resample.Resampler.std">[docs]</a> <span class="k">def</span> <span class="nf">std</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">FrameLike</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute std of resampled values.</span> |
| |
| <span class="sd"> .. versionadded:: 3.4.0</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.groupby</span> |
| <span class="sd"> pyspark.pandas.DataFrame.groupby</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> from datetime import datetime</span> |
| <span class="sd"> >>> np.random.seed(22)</span> |
| <span class="sd"> >>> dates = [</span> |
| <span class="sd"> ... datetime(2022, 5, 1, 4, 5, 6),</span> |
| <span class="sd"> ... datetime(2022, 5, 3),</span> |
| <span class="sd"> ... datetime(2022, 5, 3, 23, 59, 59),</span> |
| <span class="sd"> ... datetime(2022, 5, 4),</span> |
| <span class="sd"> ... pd.NaT,</span> |
| <span class="sd"> ... datetime(2022, 5, 4, 0, 0, 1),</span> |
| <span class="sd"> ... datetime(2022, 5, 11),</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> df = ps.DataFrame(</span> |
| <span class="sd"> ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]</span> |
| <span class="sd"> ... )</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 04:05:06 0.208461 0.481681</span> |
| <span class="sd"> 2022-05-03 00:00:00 0.420538 0.859182</span> |
| <span class="sd"> 2022-05-03 23:59:59 0.171162 0.338864</span> |
| <span class="sd"> 2022-05-04 00:00:00 0.270533 0.691041</span> |
| <span class="sd"> NaT 0.220405 0.811951</span> |
| <span class="sd"> 2022-05-04 00:00:01 0.010527 0.561204</span> |
| <span class="sd"> 2022-05-11 00:00:00 0.813726 0.745100</span> |
| <span class="sd"> >>> df.resample("3D").std().sort_index()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 0.134509 0.268835</span> |
| <span class="sd"> 2022-05-04 0.183852 0.091809</span> |
| <span class="sd"> 2022-05-07 NaN NaN</span> |
| <span class="sd"> 2022-05-10 NaN NaN</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_handle_output</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_downsample</span><span class="p">(</span><span class="s2">"std"</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="Resampler.var"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.resample.Resampler.var.html#pyspark.pandas.resample.Resampler.var">[docs]</a> <span class="k">def</span> <span class="nf">var</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">FrameLike</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute var of resampled values.</span> |
| |
| <span class="sd"> .. versionadded:: 3.4.0</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.groupby</span> |
| <span class="sd"> pyspark.pandas.DataFrame.groupby</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> from datetime import datetime</span> |
| <span class="sd"> >>> np.random.seed(22)</span> |
| <span class="sd"> >>> dates = [</span> |
| <span class="sd"> ... datetime(2022, 5, 1, 4, 5, 6),</span> |
| <span class="sd"> ... datetime(2022, 5, 3),</span> |
| <span class="sd"> ... datetime(2022, 5, 3, 23, 59, 59),</span> |
| <span class="sd"> ... datetime(2022, 5, 4),</span> |
| <span class="sd"> ... pd.NaT,</span> |
| <span class="sd"> ... datetime(2022, 5, 4, 0, 0, 1),</span> |
| <span class="sd"> ... datetime(2022, 5, 11),</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> df = ps.DataFrame(</span> |
| <span class="sd"> ... np.random.rand(len(dates), 2), index=pd.DatetimeIndex(dates), columns=["A", "B"]</span> |
| <span class="sd"> ... )</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 04:05:06 0.208461 0.481681</span> |
| <span class="sd"> 2022-05-03 00:00:00 0.420538 0.859182</span> |
| <span class="sd"> 2022-05-03 23:59:59 0.171162 0.338864</span> |
| <span class="sd"> 2022-05-04 00:00:00 0.270533 0.691041</span> |
| <span class="sd"> NaT 0.220405 0.811951</span> |
| <span class="sd"> 2022-05-04 00:00:01 0.010527 0.561204</span> |
| <span class="sd"> 2022-05-11 00:00:00 0.813726 0.745100</span> |
| <span class="sd"> >>> df.resample("3D").var().sort_index()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 2022-05-01 0.018093 0.072272</span> |
| <span class="sd"> 2022-05-04 0.033802 0.008429</span> |
| <span class="sd"> 2022-05-07 NaN NaN</span> |
| <span class="sd"> 2022-05-10 NaN NaN</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_handle_output</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_downsample</span><span class="p">(</span><span class="s2">"var"</span><span class="p">))</span></div> |
| |
| |
| <span class="k">class</span> <span class="nc">DataFrameResampler</span><span class="p">(</span><span class="n">Resampler</span><span class="p">[</span><span class="n">DataFrame</span><span class="p">]):</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">psdf</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">,</span> |
| <span class="n">resamplekey</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Series</span><span class="p">],</span> |
| <span class="n">rule</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">closed</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">label</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">agg_columns</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">Series</span><span class="p">]</span> <span class="o">=</span> <span class="p">[],</span> |
| <span class="p">):</span> |
| <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">psdf</span><span class="o">=</span><span class="n">psdf</span><span class="p">,</span> |
| <span class="n">resamplekey</span><span class="o">=</span><span class="n">resamplekey</span><span class="p">,</span> |
| <span class="n">rule</span><span class="o">=</span><span class="n">rule</span><span class="p">,</span> |
| <span class="n">closed</span><span class="o">=</span><span class="n">closed</span><span class="p">,</span> |
| <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span> |
| <span class="n">agg_columns</span><span class="o">=</span><span class="n">agg_columns</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__getattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">item</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">MissingPandasLikeDataFrameResampler</span><span class="p">,</span> <span class="n">item</span><span class="p">):</span> |
| <span class="n">property_or_func</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">MissingPandasLikeDataFrameResampler</span><span class="p">,</span> <span class="n">item</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">property_or_func</span><span class="p">,</span> <span class="nb">property</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">property_or_func</span><span class="o">.</span><span class="n">fget</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">partial</span><span class="p">(</span><span class="n">property_or_func</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_handle_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">psdf</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataFrame</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">psdf</span> |
| |
| |
| <span class="k">class</span> <span class="nc">SeriesResampler</span><span class="p">(</span><span class="n">Resampler</span><span class="p">[</span><span class="n">Series</span><span class="p">]):</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">psser</span><span class="p">:</span> <span class="n">Series</span><span class="p">,</span> |
| <span class="n">resamplekey</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Series</span><span class="p">],</span> |
| <span class="n">rule</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">closed</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">label</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">agg_columns</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">Series</span><span class="p">]</span> <span class="o">=</span> <span class="p">[],</span> |
| <span class="p">):</span> |
| <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">psdf</span><span class="o">=</span><span class="n">psser</span><span class="o">.</span><span class="n">_psdf</span><span class="p">,</span> |
| <span class="n">resamplekey</span><span class="o">=</span><span class="n">resamplekey</span><span class="p">,</span> |
| <span class="n">rule</span><span class="o">=</span><span class="n">rule</span><span class="p">,</span> |
| <span class="n">closed</span><span class="o">=</span><span class="n">closed</span><span class="p">,</span> |
| <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span> |
| <span class="n">agg_columns</span><span class="o">=</span><span class="n">agg_columns</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_psser</span> <span class="o">=</span> <span class="n">psser</span> |
| |
| <span class="k">def</span> <span class="fm">__getattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">item</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">MissingPandasLikeSeriesResampler</span><span class="p">,</span> <span class="n">item</span><span class="p">):</span> |
| <span class="n">property_or_func</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">MissingPandasLikeSeriesResampler</span><span class="p">,</span> <span class="n">item</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">property_or_func</span><span class="p">,</span> <span class="nb">property</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">property_or_func</span><span class="o">.</span><span class="n">fget</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">partial</span><span class="p">(</span><span class="n">property_or_func</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_handle_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">psdf</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">)</span> <span class="o">-></span> <span class="n">Series</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">first_series</span><span class="p">(</span><span class="n">psdf</span><span class="p">)</span><span class="o">.</span><span class="n">rename</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_psser</span><span class="o">.</span><span class="n">name</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_test</span><span class="p">()</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">import</span> <span class="nn">sys</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span> |
| <span class="kn">import</span> <span class="nn">pyspark.pandas.resample</span> |
| |
| <span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s2">"SPARK_HOME"</span><span class="p">])</span> |
| |
| <span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">pandas</span><span class="o">.</span><span class="n">resample</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"ps"</span><span class="p">]</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">pandas</span> |
| <span class="n">spark</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">"local[4]"</span><span class="p">)</span> |
| <span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"pyspark.pandas.resample tests"</span><span class="p">)</span> |
| <span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="p">)</span> |
| <span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span> |
| <span class="n">pyspark</span><span class="o">.</span><span class="n">pandas</span><span class="o">.</span><span class="n">resample</span><span class="p">,</span> |
| <span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span> |
| <span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span> <span class="o">|</span> <span class="n">doctest</span><span class="o">.</span><span class="n">NORMALIZE_WHITESPACE</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
| <span class="n">_test</span><span class="p">()</span> |
| </pre></div> |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| |
| <script src="../../../_static/js/index.3da636dd464baa7582d2.js"></script> |
| |
| |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| <p> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
