| |
| |
| <!DOCTYPE html> |
| |
| |
| <html > |
| |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>pyspark.pandas.resample — PySpark 4.0.0-preview1 documentation</title> |
| |
| |
| |
| <script data-cfasync="false"> |
| document.documentElement.dataset.mode = localStorage.getItem("mode") || ""; |
| document.documentElement.dataset.theme = localStorage.getItem("theme") || "light"; |
| </script> |
| |
| <!-- Loaded before other Sphinx assets --> |
| <link href="../../../_static/styles/theme.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link href="../../../_static/styles/bootstrap.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link href="../../../_static/styles/pydata-sphinx-theme.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| |
| |
| <link href="../../../_static/vendor/fontawesome/6.1.2/css/all.min.css?digest=e353d410970836974a52" rel="stylesheet" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-solid-900.woff2" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-brands-400.woff2" /> |
| <link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.1.2/webfonts/fa-regular-400.woff2" /> |
| |
| <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <!-- Pre-loaded scripts that we'll load fully later --> |
| <link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=e353d410970836974a52" /> |
| <link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=e353d410970836974a52" /> |
| |
| <script data-url_root="../../../" id="documentation_options" 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/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>DOCUMENTATION_OPTIONS.pagename = '_modules/pyspark/pandas/resample';</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="None"> |
| |
| |
| <!-- Matomo --> |
| <script type="text/javascript"> |
| var _paq = window._paq = window._paq || []; |
| /* tracker methods like "setCustomDimension" should be called before "trackPageView" */ |
| _paq.push(["disableCookies"]); |
| _paq.push(['trackPageView']); |
| _paq.push(['enableLinkTracking']); |
| (function() { |
| var u="https://analytics.apache.org/"; |
| _paq.push(['setTrackerUrl', u+'matomo.php']); |
| _paq.push(['setSiteId', '40']); |
| var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0]; |
| g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s); |
| })(); |
| </script> |
| <!-- End Matomo Code --> |
| |
| </head> |
| |
| |
| <body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode=""> |
| |
| |
| |
| <a class="skip-link" href="#main-content">Skip to main content</a> |
| |
| <input type="checkbox" |
| class="sidebar-toggle" |
| name="__primary" |
| id="__primary"/> |
| <label class="overlay overlay-primary" for="__primary"></label> |
| |
| <input type="checkbox" |
| class="sidebar-toggle" |
| name="__secondary" |
| id="__secondary"/> |
| <label class="overlay overlay-secondary" for="__secondary"></label> |
| |
| <div class="search-button__wrapper"> |
| <div class="search-button__overlay"></div> |
| <div class="search-button__search-container"> |
| <form class="bd-search d-flex align-items-center" |
| action="../../../search.html" |
| method="get"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| <input type="search" |
| class="form-control" |
| name="q" |
| id="search-input" |
| placeholder="Search the docs ..." |
| aria-label="Search the docs ..." |
| autocomplete="off" |
| autocorrect="off" |
| autocapitalize="off" |
| spellcheck="false"/> |
| <span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span> |
| </form></div> |
| </div> |
| |
| <nav class="bd-header navbar navbar-expand-lg bd-navbar"> |
| <div class="bd-header__inner bd-page-width"> |
| <label class="sidebar-toggle primary-toggle" for="__primary"> |
| <span class="fa-solid fa-bars"></span> |
| </label> |
| |
| <div class="navbar-header-items__start"> |
| |
| <div class="navbar-item"> |
| |
| |
| <a class="navbar-brand logo" href="../../../index.html"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <img src="../../../_static/spark-logo-light.png" class="logo__image only-light" alt="Logo image"/> |
| <script>document.write(`<img src="../../../_static/spark-logo-dark.png" class="logo__image only-dark" alt="Logo image"/>`);</script> |
| |
| |
| </a></div> |
| |
| </div> |
| |
| |
| <div class="col-lg-9 navbar-header-items"> |
| |
| <div class="me-auto navbar-header-items__center"> |
| |
| <div class="navbar-item"><nav class="navbar-nav"> |
| <p class="sidebar-header-items__title" |
| role="heading" |
| aria-level="1" |
| aria-label="Site Navigation"> |
| Site Navigation |
| </p> |
| <ul class="bd-navbar-elements navbar-nav"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| </ul> |
| </nav></div> |
| |
| </div> |
| |
| |
| <div class="navbar-header-items__end"> |
| |
| <div class="navbar-item navbar-persistent--container"> |
| |
| <script> |
| document.write(` |
| <button class="btn btn-sm navbar-btn search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| </button> |
| `); |
| </script> |
| </div> |
| |
| |
| <div class="navbar-item"><!-- |
| Licensed to the Apache Software Foundation (ASF) under one or more |
| contributor license agreements. See the NOTICE file distributed with |
| this work for additional information regarding copyright ownership. |
| The ASF licenses this file to You under the Apache License, Version 2.0 |
| (the "License"); you may not use this file except in compliance with |
| the License. You may obtain a copy of the License at |
| |
| http://www.apache.org/licenses/LICENSE-2.0 |
| |
| Unless required by applicable law or agreed to in writing, software |
| distributed under the License is distributed on an "AS IS" BASIS, |
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| See the License for the specific language governing permissions and |
| limitations under the License. |
| --> |
| |
| <div id="version-button" class="dropdown"> |
| <button type="button" class="btn btn-secondary btn-sm navbar-btn dropdown-toggle" id="version_switcher_button" data-toggle="dropdown"> |
| 4.0.0-preview1 |
| <span class="caret"></span> |
| </button> |
| <div id="version_switcher" class="dropdown-menu list-group-flush py-0" aria-labelledby="version_switcher_button"> |
| <!-- dropdown will be populated by javascript on page load --> |
| </div> |
| </div> |
| |
| <script type="text/javascript"> |
| // Function to construct the target URL from the JSON components |
| function buildURL(entry) { |
| var template = "https://spark.apache.org/docs/{version}/api/python/index.html"; // supplied by jinja |
| template = template.replace("{version}", entry.version); |
| return template; |
| } |
| |
| // Function to check if corresponding page path exists in other version of docs |
| // and, if so, go there instead of the homepage of the other docs version |
| function checkPageExistsAndRedirect(event) { |
| const currentFilePath = "_modules/pyspark/pandas/resample.html", |
| otherDocsHomepage = event.target.getAttribute("href"); |
| let tryUrl = `${otherDocsHomepage}${currentFilePath}`; |
| $.ajax({ |
| type: 'HEAD', |
| url: tryUrl, |
| // if the page exists, go there |
| success: function() { |
| location.href = tryUrl; |
| } |
| }).fail(function() { |
| location.href = otherDocsHomepage; |
| }); |
| return false; |
| } |
| |
| // Function to populate the version switcher |
| (function () { |
| // get JSON config |
| $.getJSON("https://spark.apache.org/static/versions.json", function(data, textStatus, jqXHR) { |
| // create the nodes first (before AJAX calls) to ensure the order is |
| // correct (for now, links will go to doc version homepage) |
| $.each(data, function(index, entry) { |
| // if no custom name specified (e.g., "latest"), use version string |
| if (!("name" in entry)) { |
| entry.name = entry.version; |
| } |
| // construct the appropriate URL, and add it to the dropdown |
| entry.url = buildURL(entry); |
| const node = document.createElement("a"); |
| node.setAttribute("class", "list-group-item list-group-item-action py-1"); |
| node.setAttribute("href", `${entry.url}`); |
| node.textContent = `${entry.name}`; |
| node.onclick = checkPageExistsAndRedirect; |
| $("#version_switcher").append(node); |
| }); |
| }); |
| })(); |
| </script></div> |
| |
| <div class="navbar-item"> |
| <script> |
| document.write(` |
| <button class="theme-switch-button btn btn-sm btn-outline-primary navbar-btn rounded-circle" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <span class="theme-switch" data-mode="light"><i class="fa-solid fa-sun"></i></span> |
| <span class="theme-switch" data-mode="dark"><i class="fa-solid fa-moon"></i></span> |
| <span class="theme-switch" data-mode="auto"><i class="fa-solid fa-circle-half-stroke"></i></span> |
| </button> |
| `); |
| </script></div> |
| |
| <div class="navbar-item"><ul class="navbar-icon-links navbar-nav" |
| aria-label="Icon Links"> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://github.com/apache/spark" title="GitHub" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-brands fa-github"></i></span> |
| <label class="sr-only">GitHub</label></a> |
| </li> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://pypi.org/project/pyspark" title="PyPI" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-solid fa-box"></i></span> |
| <label class="sr-only">PyPI</label></a> |
| </li> |
| </ul></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <div class="navbar-persistent--mobile"> |
| <script> |
| document.write(` |
| <button class="btn btn-sm navbar-btn search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <i class="fa-solid fa-magnifying-glass"></i> |
| </button> |
| `); |
| </script> |
| </div> |
| |
| |
| |
| </div> |
| |
| </nav> |
| |
| <div class="bd-container"> |
| <div class="bd-container__inner bd-page-width"> |
| |
| <div class="bd-sidebar-primary bd-sidebar hide-on-wide"> |
| |
| |
| |
| <div class="sidebar-header-items sidebar-primary__section"> |
| |
| |
| <div class="sidebar-header-items__center"> |
| |
| <div class="navbar-item"><nav class="navbar-nav"> |
| <p class="sidebar-header-items__title" |
| role="heading" |
| aria-level="1" |
| aria-label="Site Navigation"> |
| Site Navigation |
| </p> |
| <ul class="bd-navbar-elements navbar-nav"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| </ul> |
| </nav></div> |
| |
| </div> |
| |
| |
| |
| <div class="sidebar-header-items__end"> |
| |
| <div class="navbar-item"><!-- |
| Licensed to the Apache Software Foundation (ASF) under one or more |
| contributor license agreements. See the NOTICE file distributed with |
| this work for additional information regarding copyright ownership. |
| The ASF licenses this file to You under the Apache License, Version 2.0 |
| (the "License"); you may not use this file except in compliance with |
| the License. You may obtain a copy of the License at |
| |
| http://www.apache.org/licenses/LICENSE-2.0 |
| |
| Unless required by applicable law or agreed to in writing, software |
| distributed under the License is distributed on an "AS IS" BASIS, |
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| See the License for the specific language governing permissions and |
| limitations under the License. |
| --> |
| |
| <div id="version-button" class="dropdown"> |
| <button type="button" class="btn btn-secondary btn-sm navbar-btn dropdown-toggle" id="version_switcher_button" data-toggle="dropdown"> |
| 4.0.0-preview1 |
| <span class="caret"></span> |
| </button> |
| <div id="version_switcher" class="dropdown-menu list-group-flush py-0" aria-labelledby="version_switcher_button"> |
| <!-- dropdown will be populated by javascript on page load --> |
| </div> |
| </div> |
| |
| <script type="text/javascript"> |
| // Function to construct the target URL from the JSON components |
| function buildURL(entry) { |
| var template = "https://spark.apache.org/docs/{version}/api/python/index.html"; // supplied by jinja |
| template = template.replace("{version}", entry.version); |
| return template; |
| } |
| |
| // Function to check if corresponding page path exists in other version of docs |
| // and, if so, go there instead of the homepage of the other docs version |
| function checkPageExistsAndRedirect(event) { |
| const currentFilePath = "_modules/pyspark/pandas/resample.html", |
| otherDocsHomepage = event.target.getAttribute("href"); |
| let tryUrl = `${otherDocsHomepage}${currentFilePath}`; |
| $.ajax({ |
| type: 'HEAD', |
| url: tryUrl, |
| // if the page exists, go there |
| success: function() { |
| location.href = tryUrl; |
| } |
| }).fail(function() { |
| location.href = otherDocsHomepage; |
| }); |
| return false; |
| } |
| |
| // Function to populate the version switcher |
| (function () { |
| // get JSON config |
| $.getJSON("https://spark.apache.org/static/versions.json", function(data, textStatus, jqXHR) { |
| // create the nodes first (before AJAX calls) to ensure the order is |
| // correct (for now, links will go to doc version homepage) |
| $.each(data, function(index, entry) { |
| // if no custom name specified (e.g., "latest"), use version string |
| if (!("name" in entry)) { |
| entry.name = entry.version; |
| } |
| // construct the appropriate URL, and add it to the dropdown |
| entry.url = buildURL(entry); |
| const node = document.createElement("a"); |
| node.setAttribute("class", "list-group-item list-group-item-action py-1"); |
| node.setAttribute("href", `${entry.url}`); |
| node.textContent = `${entry.name}`; |
| node.onclick = checkPageExistsAndRedirect; |
| $("#version_switcher").append(node); |
| }); |
| }); |
| })(); |
| </script></div> |
| |
| <div class="navbar-item"> |
| <script> |
| document.write(` |
| <button class="theme-switch-button btn btn-sm btn-outline-primary navbar-btn rounded-circle" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip"> |
| <span class="theme-switch" data-mode="light"><i class="fa-solid fa-sun"></i></span> |
| <span class="theme-switch" data-mode="dark"><i class="fa-solid fa-moon"></i></span> |
| <span class="theme-switch" data-mode="auto"><i class="fa-solid fa-circle-half-stroke"></i></span> |
| </button> |
| `); |
| </script></div> |
| |
| <div class="navbar-item"><ul class="navbar-icon-links navbar-nav" |
| aria-label="Icon Links"> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://github.com/apache/spark" title="GitHub" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-brands fa-github"></i></span> |
| <label class="sr-only">GitHub</label></a> |
| </li> |
| <li class="nav-item"> |
| |
| |
| |
| |
| |
| |
| |
| |
| <a href="https://pypi.org/project/pyspark" title="PyPI" class="nav-link" rel="noopener" target="_blank" data-bs-toggle="tooltip" data-bs-placement="bottom"><span><i class="fa-solid fa-box"></i></span> |
| <label class="sr-only">PyPI</label></a> |
| </li> |
| </ul></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <div class="sidebar-primary-items__end sidebar-primary__section"> |
| </div> |
| |
| <div id="rtd-footer-container"></div> |
| |
| |
| </div> |
| |
| <main id="main-content" class="bd-main"> |
| |
| |
| <div class="bd-content"> |
| <div class="bd-article-container"> |
| |
| <div class="bd-header-article"> |
| <div class="header-article-items header-article__inner"> |
| |
| <div class="header-article-items__start"> |
| |
| <div class="header-article-item"> |
| |
| |
| |
| <nav aria-label="Breadcrumbs"> |
| <ul class="bd-breadcrumbs" role="navigation" aria-label="Breadcrumb"> |
| |
| <li class="breadcrumb-item breadcrumb-home"> |
| <a href="../../../index.html" class="nav-link" aria-label="Home"> |
| <i class="fa-solid fa-home"></i> |
| </a> |
| </li> |
| |
| <li class="breadcrumb-item"><a href="../../index.html" class="nav-link">Module code</a></li> |
| |
| <li class="breadcrumb-item active" aria-current="page">pyspark.pandas.resample</li> |
| </ul> |
| </nav> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| </div> |
| |
| |
| |
| |
| <div id="searchbox"></div> |
| <article class="bd-article" role="main"> |
| |
| <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">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="n">Union</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="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">TimestampNTZType</span><span class="p">,</span> |
| <span class="n">DataType</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">"ME"</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">"h"</span><span class="p">,</span> <span class="s2">"T"</span><span class="p">,</span> <span class="s2">"min"</span><span class="p">,</span> <span class="s2">"S"</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="s2">"ME"</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="s2">"ME"</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">_resamplekey_type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataType</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">data_type</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">data_type</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">get_make_interval</span><span class="p">(</span> <span class="c1"># type: ignore[return]</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">unit</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">col</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">Column</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Column</span><span class="p">:</span> |
| <span class="n">col</span> <span class="o">=</span> <span class="n">col</span> <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="p">(</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">))</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</span><span class="n">col</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">unit</span> <span class="o">==</span> <span class="s2">"MONTH"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">make_interval</span><span class="p">(</span><span class="n">months</span><span class="o">=</span><span class="n">col</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">unit</span> <span class="o">==</span> <span class="s2">"HOUR"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">make_interval</span><span class="p">(</span><span class="n">hours</span><span class="o">=</span><span class="n">col</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">unit</span> <span class="o">==</span> <span class="s2">"MINUTE"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">make_interval</span><span class="p">(</span><span class="n">mins</span><span class="o">=</span><span class="n">col</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">unit</span> <span class="o">==</span> <span class="s2">"SECOND"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">make_interval</span><span class="p">(</span><span class="n">secs</span><span class="o">=</span><span class="n">col</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_bin_timestamp</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">key_type</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_resamplekey_type</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="n">ret</span> <span class="o">=</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="ow">in</span> <span class="p">[</span><span class="s2">"ME"</span><span class="p">,</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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</span><span class="p">(</span><span class="s2">"MONTH"</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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</span><span class="p">(</span><span class="s2">"MONTH"</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">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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</span><span class="p">(</span><span class="s2">"MONTH"</span><span class="p">,</span> <span class="n">n</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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</span><span class="p">(</span><span class="s2">"MONTH"</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">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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</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">n</span><span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="n">ret</span> <span class="o">=</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="n">ret</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="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="n">ret</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">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="n">ret</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">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="n">ret</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">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="n">ret</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">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">"min"</span><span class="p">,</span> <span class="s2">"s"</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">"min"</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="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="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="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">key_type</span><span class="p">,</span> <span class="n">TimestampNTZType</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">to_timestamp_ntz</span><span class="p">(</span><span class="n">truncated_ts_scol</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">timestamp_diff</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="n">origin_scol</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">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="ow">in</span> <span class="p">[</span><span class="s2">"h"</span><span class="p">,</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="ow">in</span> <span class="p">[</span><span class="s2">"min"</span><span class="p">,</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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</span><span class="p">(</span><span class="n">unit_str</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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</span><span class="p">(</span><span class="n">unit_str</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">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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="n">mod</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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</span><span class="p">(</span><span class="n">unit_str</span><span class="p">,</span> <span class="n">n</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="bp">self</span><span class="o">.</span><span class="n">get_make_interval</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">n</span><span class="p">))</span> |
| |
| <span class="n">ret</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">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">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">key_type</span><span class="p">,</span> <span class="n">TimestampNTZType</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">to_timestamp_ntz</span><span class="p">(</span><span class="n">ret</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">ret</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="bp">self</span><span class="o">.</span><span class="n">_resamplekey_type</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_timestamp</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="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> |
| |
| </article> |
| |
| |
| |
| <footer class="bd-footer-article"> |
| |
| <div class="footer-article-items footer-article__inner"> |
| |
| <div class="footer-article-item"><!-- Previous / next buttons --> |
| <div class="prev-next-area"> |
| </div></div> |
| |
| </div> |
| |
| </footer> |
| |
| </div> |
| |
| |
| |
| |
| </div> |
| <footer class="bd-footer-content"> |
| |
| </footer> |
| |
| </main> |
| </div> |
| </div> |
| |
| <!-- Scripts loaded after <body> so the DOM is not blocked --> |
| <script src="../../../_static/scripts/bootstrap.js?digest=e353d410970836974a52"></script> |
| <script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=e353d410970836974a52"></script> |
| |
| <footer class="bd-footer"> |
| <div class="bd-footer__inner bd-page-width"> |
| |
| <div class="footer-items__start"> |
| |
| <div class="footer-item"><p class="copyright"> |
| Copyright @ 2024 The Apache Software Foundation, Licensed under the <a href="https://www.apache.org/licenses/LICENSE-2.0">Apache License, Version 2.0</a>. |
| </p></div> |
| |
| <div class="footer-item"> |
| <p class="sphinx-version"> |
| Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 4.5.0. |
| <br/> |
| </p> |
| </div> |
| |
| </div> |
| |
| |
| <div class="footer-items__end"> |
| |
| <div class="footer-item"><p class="theme-version"> |
| Built with the <a href="https://pydata-sphinx-theme.readthedocs.io/en/stable/index.html">PyData Sphinx Theme</a> 0.13.3. |
| </p></div> |
| |
| </div> |
| |
| </div> |
| |
| </footer> |
| </body> |
| </html> |
