| |
| |
| <!DOCTYPE html> |
| |
| |
| <html > |
| |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>pyspark.pandas.window — PySpark 4.0.0-preview2 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/window';</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/pandas/window.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="https://spark.apache.org/images/spark-logo.png" class="logo__image only-light" alt="Logo image"/> |
| <script>document.write(`<img src="https://spark.apache.org/images/spark-logo-rev.svg" 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-preview2 |
| <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/window.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-preview2 |
| <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/window.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.window</li> |
| </ul> |
| </nav> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| </div> |
| |
| |
| |
| |
| <div id="searchbox"></div> |
| <article class="bd-article" role="main"> |
| |
| <h1>Source code for pyspark.pandas.window</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| <span class="kn">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="n">Any</span><span class="p">,</span> <span class="n">Callable</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="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">Window</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</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.pandas.missing.window</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">MissingPandasLikeRolling</span><span class="p">,</span> |
| <span class="n">MissingPandasLikeRollingGroupby</span><span class="p">,</span> |
| <span class="n">MissingPandasLikeExpanding</span><span class="p">,</span> |
| <span class="n">MissingPandasLikeExpandingGroupby</span><span class="p">,</span> |
| <span class="n">MissingPandasLikeExponentialMoving</span><span class="p">,</span> |
| <span class="n">MissingPandasLikeExponentialMovingGroupby</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"># noqa: F401</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.groupby</span> <span class="kn">import</span> <span class="n">GroupBy</span><span class="p">,</span> <span class="n">DataFrameGroupBy</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.internal</span> <span class="kn">import</span> <span class="n">NATURAL_ORDER_COLUMN_NAME</span><span class="p">,</span> <span class="n">SPARK_INDEX_NAME_FORMAT</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.spark</span> <span class="kn">import</span> <span class="n">functions</span> <span class="k">as</span> <span class="n">SF</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.utils</span> <span class="kn">import</span> <span class="n">scol_for</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.column</span> <span class="kn">import</span> <span class="n">Column</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">DoubleType</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.window</span> <span class="kn">import</span> <span class="n">WindowSpec</span> |
| |
| |
| <span class="k">class</span> <span class="nc">RollingAndExpanding</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="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">window</span><span class="p">:</span> <span class="n">WindowSpec</span><span class="p">,</span> <span class="n">min_periods</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_window</span> <span class="o">=</span> <span class="n">window</span> |
| <span class="c1"># This unbounded Window is later used to handle 'min_periods' for now.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span> <span class="o">=</span> <span class="n">Window</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">NATURAL_ORDER_COLUMN_NAME</span><span class="p">)</span><span class="o">.</span><span class="n">rowsBetween</span><span class="p">(</span> |
| <span class="n">Window</span><span class="o">.</span><span class="n">unboundedPreceding</span><span class="p">,</span> <span class="n">Window</span><span class="o">.</span><span class="n">currentRow</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span> <span class="o">=</span> <span class="n">min_periods</span> |
| |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">_apply_as_series_or_frame</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">func</span><span class="p">:</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Column</span><span class="p">],</span> <span class="n">Column</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"> Wraps a function that handles Spark column in order</span> |
| <span class="sd"> to support it in both pandas-on-Spark Series and DataFrame.</span> |
| <span class="sd"> Note that the given `func` name should be same as the API's method name.</span> |
| <span class="sd"> """</span> |
| <span class="k">pass</span> |
| |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">count</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="k">pass</span> |
| |
| <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="k">def</span> <span class="nf">sum</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="nb">sum</span><span class="p">)</span> |
| |
| <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="k">def</span> <span class="nf">min</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</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="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="nb">min</span><span class="p">)</span> |
| |
| <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="k">def</span> <span class="nf">max</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</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="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="nb">max</span><span class="p">)</span> |
| |
| <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="k">def</span> <span class="nf">mean</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="n">mean</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">quantile</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">q</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10000</span><span class="p">)</span> <span class="o">-></span> <span class="n">FrameLike</span><span class="p">:</span> |
| <span class="k">def</span> <span class="nf">quantile</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">percentile_approx</span><span class="p">(</span><span class="n">scol</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">DoubleType</span><span class="p">()),</span> <span class="n">q</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="n">quantile</span><span class="p">)</span> |
| |
| <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="k">def</span> <span class="nf">std</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">stddev</span><span class="p">(</span><span class="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="n">std</span><span class="p">)</span> |
| |
| <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="k">def</span> <span class="nf">var</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">variance</span><span class="p">(</span><span class="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="n">var</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">skew</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="k">def</span> <span class="nf">skew</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="n">SF</span><span class="o">.</span><span class="n">skew</span><span class="p">(</span><span class="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="n">skew</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">kurt</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="k">def</span> <span class="nf">kurt</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="n">SF</span><span class="o">.</span><span class="n">kurt</span><span class="p">(</span><span class="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="n">kurt</span><span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">RollingLike</span><span class="p">(</span><span class="n">RollingAndExpanding</span><span class="p">[</span><span class="n">FrameLike</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">window</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">min_periods</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="k">if</span> <span class="n">window</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">"window must be >= 0"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">min_periods</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span><span class="n">min_periods</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">"min_periods must be >= 0"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">min_periods</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="c1"># TODO: 'min_periods' is not equivalent in pandas because it does not count NA as</span> |
| <span class="c1"># a value.</span> |
| <span class="n">min_periods</span> <span class="o">=</span> <span class="n">window</span> |
| |
| <span class="n">window_spec</span> <span class="o">=</span> <span class="n">Window</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">NATURAL_ORDER_COLUMN_NAME</span><span class="p">)</span><span class="o">.</span><span class="n">rowsBetween</span><span class="p">(</span> |
| <span class="n">Window</span><span class="o">.</span><span class="n">currentRow</span> <span class="o">-</span> <span class="p">(</span><span class="n">window</span> <span class="o">-</span> <span class="mi">1</span><span class="p">),</span> <span class="n">Window</span><span class="o">.</span><span class="n">currentRow</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">window_spec</span><span class="p">,</span> <span class="n">min_periods</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">count</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="k">def</span> <span class="nf">count</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_apply_as_series_or_frame</span><span class="p">(</span><span class="n">count</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float64"</span><span class="p">)</span> <span class="c1"># type: ignore[attr-defined]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">Rolling</span><span class="p">(</span><span class="n">RollingLike</span><span class="p">[</span><span class="n">FrameLike</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_or_psser</span><span class="p">:</span> <span class="n">FrameLike</span><span class="p">,</span> |
| <span class="n">window</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">min_periods</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.frame</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.series</span> <span class="kn">import</span> <span class="n">Series</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">window</span><span class="p">,</span> <span class="n">min_periods</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_psdf_or_psser</span> <span class="o">=</span> <span class="n">psdf_or_psser</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">psdf_or_psser</span><span class="p">,</span> <span class="p">(</span><span class="n">DataFrame</span><span class="p">,</span> <span class="n">Series</span><span class="p">)):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s2">"psdf_or_psser must be a series or dataframe; however, got: </span><span class="si">%s</span><span class="s2">"</span> |
| <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">psdf_or_psser</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">MissingPandasLikeRolling</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">MissingPandasLikeRolling</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">raise</span> <span class="ne">AttributeError</span><span class="p">(</span><span class="n">item</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_apply_as_series_or_frame</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">func</span><span class="p">:</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Column</span><span class="p">],</span> <span class="n">Column</span><span class="p">])</span> <span class="o">-></span> <span class="n">FrameLike</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_psdf_or_psser</span><span class="o">.</span><span class="n">_apply_series_op</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">psser</span><span class="p">:</span> <span class="n">psser</span><span class="o">.</span><span class="n">_with_new_scol</span><span class="p">(</span><span class="n">func</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="p">)),</span> <span class="c1"># TODO: dtype?</span> |
| <span class="n">should_resolve</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="Rolling.count"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Rolling.count.html#pyspark.pandas.window.Rolling.count">[docs]</a> <span class="k">def</span> <span class="nf">count</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"> The rolling count of any non-NaN observations inside the window.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Return type is the same as the original object with `np.float64` dtype.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.count : Count of the full Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.count : Count of the full DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 3, float("nan"), 10])</span> |
| <span class="sd"> >>> s.rolling(1).count()</span> |
| <span class="sd"> 0 1.0</span> |
| <span class="sd"> 1 1.0</span> |
| <span class="sd"> 2 0.0</span> |
| <span class="sd"> 3 1.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.rolling(3).count()</span> |
| <span class="sd"> 0 1.0</span> |
| <span class="sd"> 1 2.0</span> |
| <span class="sd"> 2 2.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.to_frame().rolling(1).count()</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> 0 1.0</span> |
| <span class="sd"> 1 1.0</span> |
| <span class="sd"> 2 0.0</span> |
| <span class="sd"> 3 1.0</span> |
| |
| <span class="sd"> >>> s.to_frame().rolling(3).count()</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> 0 1.0</span> |
| <span class="sd"> 1 2.0</span> |
| <span class="sd"> 2 2.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">count</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Rolling.sum"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Rolling.sum.html#pyspark.pandas.window.Rolling.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"> Calculate rolling summation of given DataFrame or Series.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Same type as the input, with the same index, containing the</span> |
| <span class="sd"> rolling summation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.sum : Reducing sum for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.sum : Reducing sum for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([4, 3, 5, 2, 6])</span> |
| <span class="sd"> >>> s</span> |
| <span class="sd"> 0 4</span> |
| <span class="sd"> 1 3</span> |
| <span class="sd"> 2 5</span> |
| <span class="sd"> 3 2</span> |
| <span class="sd"> 4 6</span> |
| <span class="sd"> dtype: int64</span> |
| |
| <span class="sd"> >>> s.rolling(2).sum()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 7.0</span> |
| <span class="sd"> 2 8.0</span> |
| <span class="sd"> 3 7.0</span> |
| <span class="sd"> 4 8.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.rolling(3).sum()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 12.0</span> |
| <span class="sd"> 3 10.0</span> |
| <span class="sd"> 4 13.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling summation is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 4 16</span> |
| <span class="sd"> 1 3 9</span> |
| <span class="sd"> 2 5 25</span> |
| <span class="sd"> 3 2 4</span> |
| <span class="sd"> 4 6 36</span> |
| |
| <span class="sd"> >>> df.rolling(2).sum()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 7.0 25.0</span> |
| <span class="sd"> 2 8.0 34.0</span> |
| <span class="sd"> 3 7.0 29.0</span> |
| <span class="sd"> 4 8.0 40.0</span> |
| |
| <span class="sd"> >>> df.rolling(3).sum()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 12.0 50.0</span> |
| <span class="sd"> 3 10.0 38.0</span> |
| <span class="sd"> 4 13.0 65.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Rolling.min"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Rolling.min.html#pyspark.pandas.window.Rolling.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"> Calculate the rolling minimum.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the rolling</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with a Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with a DataFrame.</span> |
| <span class="sd"> pyspark.pandas.Series.min : Similar method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.min : Similar method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([4, 3, 5, 2, 6])</span> |
| <span class="sd"> >>> s</span> |
| <span class="sd"> 0 4</span> |
| <span class="sd"> 1 3</span> |
| <span class="sd"> 2 5</span> |
| <span class="sd"> 3 2</span> |
| <span class="sd"> 4 6</span> |
| <span class="sd"> dtype: int64</span> |
| |
| <span class="sd"> >>> s.rolling(2).min()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 3.0</span> |
| <span class="sd"> 2 3.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> 4 2.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.rolling(3).min()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 3.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> 4 2.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling minimum is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 4 16</span> |
| <span class="sd"> 1 3 9</span> |
| <span class="sd"> 2 5 25</span> |
| <span class="sd"> 3 2 4</span> |
| <span class="sd"> 4 6 36</span> |
| |
| <span class="sd"> >>> df.rolling(2).min()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 3.0 9.0</span> |
| <span class="sd"> 2 3.0 9.0</span> |
| <span class="sd"> 3 2.0 4.0</span> |
| <span class="sd"> 4 2.0 4.0</span> |
| |
| <span class="sd"> >>> df.rolling(3).min()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 3.0 9.0</span> |
| <span class="sd"> 3 2.0 4.0</span> |
| <span class="sd"> 4 2.0 4.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">min</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Rolling.max"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Rolling.max.html#pyspark.pandas.window.Rolling.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"> Calculate the rolling maximum.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Return type is determined by the caller.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Series rolling.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : DataFrame rolling.</span> |
| <span class="sd"> pyspark.pandas.Series.max : Similar method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.max : Similar method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([4, 3, 5, 2, 6])</span> |
| <span class="sd"> >>> s</span> |
| <span class="sd"> 0 4</span> |
| <span class="sd"> 1 3</span> |
| <span class="sd"> 2 5</span> |
| <span class="sd"> 3 2</span> |
| <span class="sd"> 4 6</span> |
| <span class="sd"> dtype: int64</span> |
| |
| <span class="sd"> >>> s.rolling(2).max()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 2 5.0</span> |
| <span class="sd"> 3 5.0</span> |
| <span class="sd"> 4 6.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.rolling(3).max()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 5.0</span> |
| <span class="sd"> 3 5.0</span> |
| <span class="sd"> 4 6.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling maximum is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 4 16</span> |
| <span class="sd"> 1 3 9</span> |
| <span class="sd"> 2 5 25</span> |
| <span class="sd"> 3 2 4</span> |
| <span class="sd"> 4 6 36</span> |
| |
| <span class="sd"> >>> df.rolling(2).max()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 4.0 16.0</span> |
| <span class="sd"> 2 5.0 25.0</span> |
| <span class="sd"> 3 5.0 25.0</span> |
| <span class="sd"> 4 6.0 36.0</span> |
| |
| <span class="sd"> >>> df.rolling(3).max()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 5.0 25.0</span> |
| <span class="sd"> 3 5.0 25.0</span> |
| <span class="sd"> 4 6.0 36.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">max</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Rolling.mean"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Rolling.mean.html#pyspark.pandas.window.Rolling.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"> Calculate the rolling mean of the values.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the rolling</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.mean : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.mean : Equivalent method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([4, 3, 5, 2, 6])</span> |
| <span class="sd"> >>> s</span> |
| <span class="sd"> 0 4</span> |
| <span class="sd"> 1 3</span> |
| <span class="sd"> 2 5</span> |
| <span class="sd"> 3 2</span> |
| <span class="sd"> 4 6</span> |
| <span class="sd"> dtype: int64</span> |
| |
| <span class="sd"> >>> s.rolling(2).mean()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 3.5</span> |
| <span class="sd"> 2 4.0</span> |
| <span class="sd"> 3 3.5</span> |
| <span class="sd"> 4 4.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.rolling(3).mean()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 4.000000</span> |
| <span class="sd"> 3 3.333333</span> |
| <span class="sd"> 4 4.333333</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling mean is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 4 16</span> |
| <span class="sd"> 1 3 9</span> |
| <span class="sd"> 2 5 25</span> |
| <span class="sd"> 3 2 4</span> |
| <span class="sd"> 4 6 36</span> |
| |
| <span class="sd"> >>> df.rolling(2).mean()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 3.5 12.5</span> |
| <span class="sd"> 2 4.0 17.0</span> |
| <span class="sd"> 3 3.5 14.5</span> |
| <span class="sd"> 4 4.0 20.0</span> |
| |
| <span class="sd"> >>> df.rolling(3).mean()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 4.000000 16.666667</span> |
| <span class="sd"> 3 3.333333 12.666667</span> |
| <span class="sd"> 4 4.333333 21.666667</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Rolling.quantile"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Rolling.quantile.html#pyspark.pandas.window.Rolling.quantile">[docs]</a> <span class="k">def</span> <span class="nf">quantile</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">quantile</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10000</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"> Calculate the rolling quantile of the values.</span> |
| |
| <span class="sd"> .. versionadded:: 3.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> quantile : float</span> |
| <span class="sd"> Value between 0 and 1 providing the quantile to compute.</span> |
| |
| <span class="sd"> .. deprecated:: 4.0.0</span> |
| <span class="sd"> This will be renamed to ‘q’ in a future version.</span> |
| |
| <span class="sd"> accuracy : int, optional</span> |
| <span class="sd"> Default accuracy of approximation. Larger value means better accuracy.</span> |
| <span class="sd"> The relative error can be deduced by 1.0 / accuracy.</span> |
| <span class="sd"> This is a panda-on-Spark specific parameter.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the rolling</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> `quantile` in pandas-on-Spark are using distributed percentile approximation</span> |
| <span class="sd"> algorithm unlike pandas, the result might be different with pandas, also `interpolation`</span> |
| <span class="sd"> parameter is not supported yet.</span> |
| |
| <span class="sd"> the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling rolling with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling rolling with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.quantile : Aggregating quantile for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.quantile : Aggregating quantile for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([4, 3, 5, 2, 6])</span> |
| <span class="sd"> >>> s</span> |
| <span class="sd"> 0 4</span> |
| <span class="sd"> 1 3</span> |
| <span class="sd"> 2 5</span> |
| <span class="sd"> 3 2</span> |
| <span class="sd"> 4 6</span> |
| <span class="sd"> dtype: int64</span> |
| |
| <span class="sd"> >>> s.rolling(2).quantile(0.5)</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 3.0</span> |
| <span class="sd"> 2 3.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> 4 2.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.rolling(3).quantile(0.5)</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 4.0</span> |
| <span class="sd"> 3 3.0</span> |
| <span class="sd"> 4 5.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling quantile is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 4 16</span> |
| <span class="sd"> 1 3 9</span> |
| <span class="sd"> 2 5 25</span> |
| <span class="sd"> 3 2 4</span> |
| <span class="sd"> 4 6 36</span> |
| |
| <span class="sd"> >>> df.rolling(2).quantile(0.5)</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 3.0 9.0</span> |
| <span class="sd"> 2 3.0 9.0</span> |
| <span class="sd"> 3 2.0 4.0</span> |
| <span class="sd"> 4 2.0 4.0</span> |
| |
| <span class="sd"> >>> df.rolling(3).quantile(0.5)</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 4.0 16.0</span> |
| <span class="sd"> 3 3.0 9.0</span> |
| <span class="sd"> 4 5.0 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">quantile</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">)</span></div> |
| |
| <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"> Calculate rolling standard deviation.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the rolling calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.std : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.std : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.std : Equivalent method for Numpy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([5, 5, 6, 7, 5, 5, 5])</span> |
| <span class="sd"> >>> s.rolling(3).std()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 0.577350</span> |
| <span class="sd"> 3 1.000000</span> |
| <span class="sd"> 4 1.000000</span> |
| <span class="sd"> 5 1.154701</span> |
| <span class="sd"> 6 0.000000</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling standard deviation is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.rolling(2).std()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 0.000000 0.000000</span> |
| <span class="sd"> 2 0.707107 7.778175</span> |
| <span class="sd"> 3 0.707107 9.192388</span> |
| <span class="sd"> 4 1.414214 16.970563</span> |
| <span class="sd"> 5 0.000000 0.000000</span> |
| <span class="sd"> 6 0.000000 0.000000</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">std</span><span class="p">()</span> |
| |
| <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"> Calculate unbiased rolling variance.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the rolling calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> Series.var : Equivalent method for Series.</span> |
| <span class="sd"> DataFrame.var : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.var : Equivalent method for Numpy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([5, 5, 6, 7, 5, 5, 5])</span> |
| <span class="sd"> >>> s.rolling(3).var()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 0.333333</span> |
| <span class="sd"> 3 1.000000</span> |
| <span class="sd"> 4 1.000000</span> |
| <span class="sd"> 5 1.333333</span> |
| <span class="sd"> 6 0.000000</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each unbiased rolling variance is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.rolling(2).var()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 0.0 0.0</span> |
| <span class="sd"> 2 0.5 60.5</span> |
| <span class="sd"> 3 0.5 84.5</span> |
| <span class="sd"> 4 2.0 288.0</span> |
| <span class="sd"> 5 0.0 0.0</span> |
| <span class="sd"> 6 0.0 0.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">var</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">skew</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"> Calculate unbiased rolling skew.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the rolling calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.std : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.std : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.std : Equivalent method for Numpy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([5, 5, 6, 7, 5, 1, 5, 9])</span> |
| <span class="sd"> >>> s.rolling(3).skew()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 1.732051</span> |
| <span class="sd"> 3 0.000000</span> |
| <span class="sd"> 4 0.000000</span> |
| <span class="sd"> 5 -0.935220</span> |
| <span class="sd"> 6 -1.732051</span> |
| <span class="sd"> 7 0.000000</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling standard deviation is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.rolling(5).skew()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 NaN NaN</span> |
| <span class="sd"> 3 NaN NaN</span> |
| <span class="sd"> 4 1.257788 1.369456</span> |
| <span class="sd"> 5 -1.492685 -0.526039</span> |
| <span class="sd"> 6 -1.492685 -0.526039</span> |
| <span class="sd"> 7 -0.551618 0.686072</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">skew</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">kurt</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"> Calculate unbiased rolling kurtosis.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the rolling calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.var : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.var : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.var : Equivalent method for Numpy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([5, 5, 6, 7, 5, 1, 5, 9])</span> |
| <span class="sd"> >>> s.rolling(4).kurt()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 NaN</span> |
| <span class="sd"> 3 -1.289256</span> |
| <span class="sd"> 4 -1.289256</span> |
| <span class="sd"> 5 2.234867</span> |
| <span class="sd"> 6 2.227147</span> |
| <span class="sd"> 7 1.500000</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each unbiased rolling variance is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.rolling(5).kurt()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 NaN NaN</span> |
| <span class="sd"> 3 NaN NaN</span> |
| <span class="sd"> 4 0.312500 0.906336</span> |
| <span class="sd"> 5 2.818047 1.016942</span> |
| <span class="sd"> 6 2.818047 1.016942</span> |
| <span class="sd"> 7 0.867769 0.389750</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">kurt</span><span class="p">()</span> |
| |
| |
| <span class="k">class</span> <span class="nc">RollingGroupby</span><span class="p">(</span><span class="n">RollingLike</span><span class="p">[</span><span class="n">FrameLike</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">groupby</span><span class="p">:</span> <span class="n">GroupBy</span><span class="p">[</span><span class="n">FrameLike</span><span class="p">],</span> |
| <span class="n">window</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">min_periods</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="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">window</span><span class="p">,</span> <span class="n">min_periods</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_groupby</span> <span class="o">=</span> <span class="n">groupby</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_window</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_window</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="o">*</span><span class="p">[</span><span class="n">ser</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">ser</span> <span class="ow">in</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</span><span class="p">])</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span> |
| <span class="o">*</span><span class="p">[</span><span class="n">ser</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">ser</span> <span class="ow">in</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</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">MissingPandasLikeRollingGroupby</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">MissingPandasLikeRollingGroupby</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">raise</span> <span class="ne">AttributeError</span><span class="p">(</span><span class="n">item</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_apply_as_series_or_frame</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">func</span><span class="p">:</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Column</span><span class="p">],</span> <span class="n">Column</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"> Wraps a function that handles Spark column in order</span> |
| <span class="sd"> to support it in both pandas-on-Spark Series and DataFrame.</span> |
| <span class="sd"> Note that the given `func` name should be same as the API's method name.</span> |
| <span class="sd"> """</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| |
| <span class="n">groupby</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_groupby</span> |
| <span class="n">psdf</span> <span class="o">=</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_psdf</span> |
| |
| <span class="c1"># Here we need to include grouped key as an index, and shift previous index.</span> |
| <span class="c1"># [index_column0, index_column1] -> [grouped key, index_column0, index_column1]</span> |
| <span class="n">new_index_scols</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">Column</span><span class="p">]</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">new_index_spark_column_names</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">new_index_names</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">new_index_fields</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">groupkey</span> <span class="ow">in</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</span><span class="p">:</span> |
| <span class="n">index_column_name</span> <span class="o">=</span> <span class="n">SPARK_INDEX_NAME_FORMAT</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">new_index_scols</span><span class="p">))</span> |
| <span class="n">new_index_scols</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">groupkey</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">column</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="n">index_column_name</span><span class="p">))</span> |
| <span class="n">new_index_spark_column_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">index_column_name</span><span class="p">)</span> |
| <span class="n">new_index_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">groupkey</span><span class="o">.</span><span class="n">_column_label</span><span class="p">)</span> |
| <span class="n">new_index_fields</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">groupkey</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">name</span><span class="o">=</span><span class="n">index_column_name</span><span class="p">))</span> |
| |
| <span class="k">for</span> <span class="n">new_index_scol</span><span class="p">,</span> <span class="n">index_name</span><span class="p">,</span> <span class="n">index_field</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span> |
| <span class="n">psdf</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">index_spark_columns</span><span class="p">,</span> |
| <span class="n">psdf</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">index_names</span><span class="p">,</span> |
| <span class="n">psdf</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">index_fields</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="n">index_column_name</span> <span class="o">=</span> <span class="n">SPARK_INDEX_NAME_FORMAT</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">new_index_scols</span><span class="p">))</span> |
| <span class="n">new_index_scols</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">new_index_scol</span><span class="o">.</span><span class="n">alias</span><span class="p">(</span><span class="n">index_column_name</span><span class="p">))</span> |
| <span class="n">new_index_spark_column_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">index_column_name</span><span class="p">)</span> |
| <span class="n">new_index_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">index_name</span><span class="p">)</span> |
| <span class="n">new_index_fields</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">index_field</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">index_column_name</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_agg_columns_selected</span><span class="p">:</span> |
| <span class="n">agg_columns</span> <span class="o">=</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_agg_columns</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># pandas doesn't keep the groupkey as a column from 1.3 for DataFrameGroupBy</span> |
| <span class="n">column_labels_to_exclude</span> <span class="o">=</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_column_labels_to_exclude</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">groupby</span><span class="p">,</span> <span class="n">DataFrameGroupBy</span><span class="p">):</span> |
| <span class="k">for</span> <span class="n">groupkey</span> <span class="ow">in</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</span><span class="p">:</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="n">column_labels_to_exclude</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">groupkey</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">column_labels</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="n">agg_columns</span> <span class="o">=</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">label</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">label</span> <span class="ow">in</span> <span class="n">psdf</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">column_labels</span> |
| <span class="k">if</span> <span class="n">label</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">column_labels_to_exclude</span> |
| <span class="p">]</span> |
| |
| <span class="n">applied</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">agg_column</span> <span class="ow">in</span> <span class="n">agg_columns</span><span class="p">:</span> |
| <span class="n">applied</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">agg_column</span><span class="o">.</span><span class="n">_with_new_scol</span><span class="p">(</span><span class="n">func</span><span class="p">(</span><span class="n">agg_column</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">column</span><span class="p">)))</span> <span class="c1"># TODO: dtype?</span> |
| |
| <span class="c1"># Seems like pandas filters out when grouped key is NA.</span> |
| <span class="n">cond</span> <span class="o">=</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">column</span><span class="o">.</span><span class="n">isNotNull</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</span><span class="p">[</span><span class="mi">1</span><span class="p">:]:</span> |
| <span class="n">cond</span> <span class="o">=</span> <span class="n">cond</span> <span class="o">|</span> <span class="n">c</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">column</span><span class="o">.</span><span class="n">isNotNull</span><span class="p">()</span> |
| |
| <span class="n">sdf</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">filter</span><span class="p">(</span><span class="n">cond</span><span class="p">)</span><span class="o">.</span><span class="n">select</span><span class="p">(</span> |
| <span class="n">new_index_scols</span> <span class="o">+</span> <span class="p">[</span><span class="n">c</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">c</span> <span class="ow">in</span> <span class="n">applied</span><span class="p">]</span> |
| <span class="p">)</span> |
| |
| <span class="n">internal</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">copy</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">col</span><span class="p">)</span> <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">new_index_spark_column_names</span><span class="p">],</span> |
| <span class="n">index_names</span><span class="o">=</span><span class="n">new_index_names</span><span class="p">,</span> |
| <span class="n">index_fields</span><span class="o">=</span><span class="n">new_index_fields</span><span class="p">,</span> |
| <span class="n">column_labels</span><span class="o">=</span><span class="p">[</span><span class="n">c</span><span class="o">.</span><span class="n">_column_label</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">applied</span><span class="p">],</span> |
| <span class="n">data_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">c</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">c</span> <span class="ow">in</span> <span class="n">applied</span> |
| <span class="p">],</span> |
| <span class="n">data_fields</span><span class="o">=</span><span class="p">[</span><span class="n">c</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="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">applied</span><span class="p">],</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_handle_output</span><span class="p">(</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">internal</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">count</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"> The rolling count of any non-NaN observations inside the window.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the expanding</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.count : Count of the full Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.count : Count of the full DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).rolling(3).count().sort_index()</span> |
| <span class="sd"> 2 0 1.0</span> |
| <span class="sd"> 1 2.0</span> |
| <span class="sd"> 3 2 1.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 1.0</span> |
| <span class="sd"> 6 2.0</span> |
| <span class="sd"> 7 3.0</span> |
| <span class="sd"> 8 3.0</span> |
| <span class="sd"> 5 9 1.0</span> |
| <span class="sd"> 10 2.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling count is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).rolling(2).count().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 1.0</span> |
| <span class="sd"> 1 2.0</span> |
| <span class="sd"> 3 2 1.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> 4 2.0</span> |
| <span class="sd"> 4 5 1.0</span> |
| <span class="sd"> 6 2.0</span> |
| <span class="sd"> 7 2.0</span> |
| <span class="sd"> 8 2.0</span> |
| <span class="sd"> 5 9 1.0</span> |
| <span class="sd"> 10 2.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> |
| |
| <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"> The rolling summation of any non-NaN observations inside the window.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the rolling</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.sum : Sum of the full Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.sum : Sum of the full DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).rolling(3).sum().sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 12.0</span> |
| <span class="sd"> 8 12.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling summation is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).rolling(2).sum().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 8.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 18.0</span> |
| <span class="sd"> 4 18.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 32.0</span> |
| <span class="sd"> 7 32.0</span> |
| <span class="sd"> 8 32.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 50.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> |
| |
| <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"> The rolling minimum of any non-NaN observations inside the window.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the rolling</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.min : Min of the full Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.min : Min of the full DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).rolling(3).min().sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 4.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling minimum is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).rolling(2).min().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 9.0</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 16.0</span> |
| <span class="sd"> 7 16.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">min</span><span class="p">()</span> |
| |
| <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"> The rolling maximum of any non-NaN observations inside the window.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the rolling</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.max : Max of the full Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.max : Max of the full DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).rolling(3).max().sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 4.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling maximum is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).rolling(2).max().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 9.0</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 16.0</span> |
| <span class="sd"> 7 16.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">max</span><span class="p">()</span> |
| |
| <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"> The rolling mean of any non-NaN observations inside the window.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the rolling</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.mean : Mean of the full Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.mean : Mean of the full DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).rolling(3).mean().sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 4.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling mean is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).rolling(2).mean().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 9.0</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 16.0</span> |
| <span class="sd"> 7 16.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">quantile</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">quantile</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10000</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"> Calculate rolling quantile.</span> |
| |
| <span class="sd"> .. versionadded:: 3.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> quantile : float</span> |
| <span class="sd"> Value between 0 and 1 providing the quantile to compute.</span> |
| <span class="sd"> accuracy : int, optional</span> |
| <span class="sd"> Default accuracy of approximation. Larger value means better accuracy.</span> |
| <span class="sd"> The relative error can be deduced by 1.0 / accuracy.</span> |
| <span class="sd"> This is a panda-on-Spark specific parameter.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the rolling</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> `quantile` in pandas-on-Spark are using distributed percentile approximation</span> |
| <span class="sd"> algorithm unlike pandas, the result might be different with pandas, also `interpolation`</span> |
| <span class="sd"> parameter is not supported yet.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling rolling with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling rolling with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.quantile : Aggregating quantile for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.quantile : Aggregating quantile for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).rolling(3).quantile(0.5).sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 4.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each rolling quantile is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).rolling(2).quantile(0.5).sort_index()</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 9.0</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 16.0</span> |
| <span class="sd"> 7 16.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">quantile</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">)</span> |
| |
| <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"> Calculate rolling standard deviation.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the rolling calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.std : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.std : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.std : Equivalent method for Numpy array.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">std</span><span class="p">()</span> |
| |
| <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"> Calculate unbiased rolling variance.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the rolling calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.var : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.var : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.var : Equivalent method for Numpy array.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">var</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">skew</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"> Calculate unbiased rolling skew.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the rolling calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.std : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.std : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.std : Equivalent method for Numpy array.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">skew</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">kurt</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"> Calculate unbiased rolling kurtosis.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the rolling calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.rolling : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.rolling : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.var : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.var : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.var : Equivalent method for Numpy array.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">kurt</span><span class="p">()</span> |
| |
| |
| <span class="k">class</span> <span class="nc">ExpandingLike</span><span class="p">(</span><span class="n">RollingAndExpanding</span><span class="p">[</span><span class="n">FrameLike</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">min_periods</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">min_periods</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">"min_periods must be >= 0"</span><span class="p">)</span> |
| |
| <span class="n">window</span> <span class="o">=</span> <span class="n">Window</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">NATURAL_ORDER_COLUMN_NAME</span><span class="p">)</span><span class="o">.</span><span class="n">rowsBetween</span><span class="p">(</span> |
| <span class="n">Window</span><span class="o">.</span><span class="n">unboundedPreceding</span><span class="p">,</span> <span class="n">Window</span><span class="o">.</span><span class="n">currentRow</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">window</span><span class="p">,</span> <span class="n">min_periods</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">count</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="k">def</span> <span class="nf">count</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">row_number</span><span class="p">()</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="n">scol</span><span class="p">)</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="n">count</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">"float64"</span><span class="p">)</span> <span class="c1"># type: ignore[attr-defined]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">Expanding</span><span class="p">(</span><span class="n">ExpandingLike</span><span class="p">[</span><span class="n">FrameLike</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_or_psser</span><span class="p">:</span> <span class="n">FrameLike</span><span class="p">,</span> <span class="n">min_periods</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.frame</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.series</span> <span class="kn">import</span> <span class="n">Series</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">min_periods</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">psdf_or_psser</span><span class="p">,</span> <span class="p">(</span><span class="n">DataFrame</span><span class="p">,</span> <span class="n">Series</span><span class="p">)):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s2">"psdf_or_psser must be a series or dataframe; however, got: </span><span class="si">%s</span><span class="s2">"</span> |
| <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">psdf_or_psser</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_psdf_or_psser</span> <span class="o">=</span> <span class="n">psdf_or_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">MissingPandasLikeExpanding</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">MissingPandasLikeExpanding</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">raise</span> <span class="ne">AttributeError</span><span class="p">(</span><span class="n">item</span><span class="p">)</span> |
| |
| <span class="c1"># TODO: when add 'axis' parameter, should add to here too.</span> |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"Expanding [min_periods=</span><span class="si">{}</span><span class="s2">]"</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">_min_periods</span><span class="p">)</span> |
| |
| <span class="n">_apply_as_series_or_frame</span> <span class="o">=</span> <span class="n">Rolling</span><span class="o">.</span><span class="n">_apply_as_series_or_frame</span> |
| |
| <div class="viewcode-block" id="Expanding.count"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Expanding.count.html#pyspark.pandas.window.Expanding.count">[docs]</a> <span class="k">def</span> <span class="nf">count</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"> The expanding count of any non-NaN observations inside the window.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the expanding</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.count : Count of the full Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.count : Count of the full DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 3, float("nan"), 10])</span> |
| <span class="sd"> >>> s.expanding().count()</span> |
| <span class="sd"> 0 1.0</span> |
| <span class="sd"> 1 2.0</span> |
| <span class="sd"> 2 2.0</span> |
| <span class="sd"> 3 3.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.to_frame().expanding().count()</span> |
| <span class="sd"> 0</span> |
| <span class="sd"> 0 1.0</span> |
| <span class="sd"> 1 2.0</span> |
| <span class="sd"> 2 2.0</span> |
| <span class="sd"> 3 3.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">count</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Expanding.sum"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Expanding.sum.html#pyspark.pandas.window.Expanding.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"> Calculate expanding summation of given DataFrame or Series.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Same type as the input, with the same index, containing the</span> |
| <span class="sd"> expanding summation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.sum : Reducing sum for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.sum : Reducing sum for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([1, 2, 3, 4, 5])</span> |
| <span class="sd"> >>> s</span> |
| <span class="sd"> 0 1</span> |
| <span class="sd"> 1 2</span> |
| <span class="sd"> 2 3</span> |
| <span class="sd"> 3 4</span> |
| <span class="sd"> 4 5</span> |
| <span class="sd"> dtype: int64</span> |
| |
| <span class="sd"> >>> s.expanding(3).sum()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 6.0</span> |
| <span class="sd"> 3 10.0</span> |
| <span class="sd"> 4 15.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each expanding summation is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 1 1</span> |
| <span class="sd"> 1 2 4</span> |
| <span class="sd"> 2 3 9</span> |
| <span class="sd"> 3 4 16</span> |
| <span class="sd"> 4 5 25</span> |
| |
| <span class="sd"> >>> df.expanding(3).sum()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 6.0 14.0</span> |
| <span class="sd"> 3 10.0 30.0</span> |
| <span class="sd"> 4 15.0 55.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Expanding.min"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Expanding.min.html#pyspark.pandas.window.Expanding.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"> Calculate the expanding minimum.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the expanding</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with a Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with a DataFrame.</span> |
| <span class="sd"> pyspark.pandas.Series.min : Similar method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.min : Similar method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Performing a expanding minimum with a window size of 3.</span> |
| |
| <span class="sd"> >>> s = ps.Series([4, 3, 5, 2, 6])</span> |
| <span class="sd"> >>> s.expanding(3).min()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 3.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> 4 2.0</span> |
| <span class="sd"> dtype: float64</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">min</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Expanding.max"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Expanding.max.html#pyspark.pandas.window.Expanding.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"> Calculate the expanding maximum.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Return type is determined by the caller.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.max : Similar method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.max : Similar method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Performing a expanding minimum with a window size of 3.</span> |
| |
| <span class="sd"> >>> s = ps.Series([4, 3, 5, 2, 6])</span> |
| <span class="sd"> >>> s.expanding(3).max()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 5.0</span> |
| <span class="sd"> 3 5.0</span> |
| <span class="sd"> 4 6.0</span> |
| <span class="sd"> dtype: float64</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">max</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Expanding.mean"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Expanding.mean.html#pyspark.pandas.window.Expanding.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"> Calculate the expanding mean of the values.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the expanding</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.mean : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.mean : Equivalent method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> The below examples will show expanding mean calculations with window sizes of</span> |
| <span class="sd"> two and three, respectively.</span> |
| |
| <span class="sd"> >>> s = ps.Series([1, 2, 3, 4])</span> |
| <span class="sd"> >>> s.expanding(2).mean()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 1.5</span> |
| <span class="sd"> 2 2.0</span> |
| <span class="sd"> 3 2.5</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.expanding(3).mean()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 2.0</span> |
| <span class="sd"> 3 2.5</span> |
| <span class="sd"> dtype: float64</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="Expanding.quantile"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.Expanding.quantile.html#pyspark.pandas.window.Expanding.quantile">[docs]</a> <span class="k">def</span> <span class="nf">quantile</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">quantile</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10000</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"> Calculate the expanding quantile of the values.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the expanding</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> quantile : float</span> |
| <span class="sd"> Value between 0 and 1 providing the quantile to compute.</span> |
| <span class="sd"> accuracy : int, optional</span> |
| <span class="sd"> Default accuracy of approximation. Larger value means better accuracy.</span> |
| <span class="sd"> The relative error can be deduced by 1.0 / accuracy.</span> |
| <span class="sd"> This is a panda-on-Spark specific parameter.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> `quantile` in pandas-on-Spark are using distributed percentile approximation</span> |
| <span class="sd"> algorithm unlike pandas, the result might be different with pandas (the result is</span> |
| <span class="sd"> similar to the interpolation set to `lower`), also `interpolation` parameter is</span> |
| <span class="sd"> not supported yet.</span> |
| |
| <span class="sd"> the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling expanding with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling expanding with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.quantile : Aggregating quantile for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.quantile : Aggregating quantile for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> The below examples will show expanding quantile calculations with window sizes of</span> |
| <span class="sd"> two and three, respectively.</span> |
| |
| <span class="sd"> >>> s = ps.Series([1, 2, 3, 4])</span> |
| <span class="sd"> >>> s.expanding(2).quantile(0.5)</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 1.0</span> |
| <span class="sd"> 2 2.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> >>> s.expanding(3).quantile(0.5)</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 2.0</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> dtype: float64</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">quantile</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">)</span></div> |
| |
| <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"> Calculate expanding standard deviation.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the expanding calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.std : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.std : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.std : Equivalent method for Numpy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([5, 5, 6, 7, 5, 5, 5])</span> |
| <span class="sd"> >>> s.expanding(3).std()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 0.577350</span> |
| <span class="sd"> 3 0.957427</span> |
| <span class="sd"> 4 0.894427</span> |
| <span class="sd"> 5 0.836660</span> |
| <span class="sd"> 6 0.786796</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each expanding standard deviation variance is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.expanding(2).std()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 0.000000 0.000000</span> |
| <span class="sd"> 2 0.577350 6.350853</span> |
| <span class="sd"> 3 0.957427 11.412712</span> |
| <span class="sd"> 4 0.894427 10.630146</span> |
| <span class="sd"> 5 0.836660 9.928075</span> |
| <span class="sd"> 6 0.786796 9.327379</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">std</span><span class="p">()</span> |
| |
| <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"> Calculate unbiased expanding variance.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the expanding calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.var : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.var : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.var : Equivalent method for Numpy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([5, 5, 6, 7, 5, 5, 5])</span> |
| <span class="sd"> >>> s.expanding(3).var()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 0.333333</span> |
| <span class="sd"> 3 0.916667</span> |
| <span class="sd"> 4 0.800000</span> |
| <span class="sd"> 5 0.700000</span> |
| <span class="sd"> 6 0.619048</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each unbiased expanding variance is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.expanding(2).var()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 0.000000 0.000000</span> |
| <span class="sd"> 2 0.333333 40.333333</span> |
| <span class="sd"> 3 0.916667 130.250000</span> |
| <span class="sd"> 4 0.800000 113.000000</span> |
| <span class="sd"> 5 0.700000 98.566667</span> |
| <span class="sd"> 6 0.619048 87.000000</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">var</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">skew</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"> Calculate unbiased expanding skew.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the expanding calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.std : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.std : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.std : Equivalent method for Numpy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([5, 5, 6, 7, 5, 1, 5, 9])</span> |
| <span class="sd"> >>> s.expanding(3).skew()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 1.732051</span> |
| <span class="sd"> 3 0.854563</span> |
| <span class="sd"> 4 1.257788</span> |
| <span class="sd"> 5 -1.571593</span> |
| <span class="sd"> 6 -1.657542</span> |
| <span class="sd"> 7 -0.521760</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each expanding standard deviation variance is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.expanding(5).skew()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 NaN NaN</span> |
| <span class="sd"> 3 NaN NaN</span> |
| <span class="sd"> 4 1.257788 1.369456</span> |
| <span class="sd"> 5 -1.571593 -0.423309</span> |
| <span class="sd"> 6 -1.657542 -0.355737</span> |
| <span class="sd"> 7 -0.521760 1.116874</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">skew</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">kurt</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"> Calculate unbiased expanding kurtosis.</span> |
| |
| <span class="sd"> .. note:: the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the expanding calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.var : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.var : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.var : Equivalent method for Numpy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([5, 5, 6, 7, 5, 1, 5, 9])</span> |
| <span class="sd"> >>> s.expanding(4).kurt()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 NaN</span> |
| <span class="sd"> 3 -1.289256</span> |
| <span class="sd"> 4 0.312500</span> |
| <span class="sd"> 5 3.419520</span> |
| <span class="sd"> 6 4.028185</span> |
| <span class="sd"> 7 2.230373</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each unbiased expanding variance is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.expanding(5).kurt()</span> |
| <span class="sd"> A B</span> |
| <span class="sd"> 0 NaN NaN</span> |
| <span class="sd"> 1 NaN NaN</span> |
| <span class="sd"> 2 NaN NaN</span> |
| <span class="sd"> 3 NaN NaN</span> |
| <span class="sd"> 4 0.312500 0.906336</span> |
| <span class="sd"> 5 3.419520 1.486581</span> |
| <span class="sd"> 6 4.028185 1.936169</span> |
| <span class="sd"> 7 2.230373 2.273792</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">kurt</span><span class="p">()</span> |
| |
| |
| <span class="k">class</span> <span class="nc">ExpandingGroupby</span><span class="p">(</span><span class="n">ExpandingLike</span><span class="p">[</span><span class="n">FrameLike</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">groupby</span><span class="p">:</span> <span class="n">GroupBy</span><span class="p">[</span><span class="n">FrameLike</span><span class="p">],</span> <span class="n">min_periods</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</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">min_periods</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_groupby</span> <span class="o">=</span> <span class="n">groupby</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_window</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_window</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="o">*</span><span class="p">[</span><span class="n">ser</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">ser</span> <span class="ow">in</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</span><span class="p">])</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_window</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span> |
| <span class="o">*</span><span class="p">[</span><span class="n">ser</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">ser</span> <span class="ow">in</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</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">MissingPandasLikeExpandingGroupby</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">MissingPandasLikeExpandingGroupby</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">raise</span> <span class="ne">AttributeError</span><span class="p">(</span><span class="n">item</span><span class="p">)</span> |
| |
| <span class="n">_apply_as_series_or_frame</span> <span class="o">=</span> <span class="n">RollingGroupby</span><span class="o">.</span><span class="n">_apply_as_series_or_frame</span> |
| |
| <span class="k">def</span> <span class="nf">count</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"> The expanding count of any non-NaN observations inside the window.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the expanding</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.count : Count of the full Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.count : Count of the full DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).expanding(3).count().sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 3.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each expanding count is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).expanding(2).count().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 2.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 2.0</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 2.0</span> |
| <span class="sd"> 7 3.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 2.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> |
| |
| <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"> Calculate expanding summation of given DataFrame or Series.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Same type as the input, with the same index, containing the</span> |
| <span class="sd"> expanding summation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.sum : Reducing sum for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.sum : Reducing sum for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).expanding(3).sum().sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 12.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each expanding summation is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).expanding(2).sum().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 8.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 18.0</span> |
| <span class="sd"> 4 27.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 32.0</span> |
| <span class="sd"> 7 48.0</span> |
| <span class="sd"> 8 64.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 50.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> |
| |
| <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"> Calculate the expanding minimum.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the expanding</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with a Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with a DataFrame.</span> |
| <span class="sd"> pyspark.pandas.Series.min : Similar method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.min : Similar method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).expanding(3).min().sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 4.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each expanding minimum is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).expanding(2).min().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 9.0</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 16.0</span> |
| <span class="sd"> 7 16.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">min</span><span class="p">()</span> |
| |
| <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"> Calculate the expanding maximum.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Return type is determined by the caller.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.max : Similar method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.max : Similar method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).expanding(3).max().sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 4.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each expanding maximum is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).expanding(2).max().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 9.0</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 16.0</span> |
| <span class="sd"> 7 16.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">max</span><span class="p">()</span> |
| |
| <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"> Calculate the expanding mean of the values.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the expanding</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.mean : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.mean : Equivalent method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).expanding(3).mean().sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 4.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each expanding mean is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).expanding(2).mean().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 9.0</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 16.0</span> |
| <span class="sd"> 7 16.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">quantile</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">quantile</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10000</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"> Calculate the expanding quantile of the values.</span> |
| |
| <span class="sd"> .. versionadded:: 3.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> quantile : float</span> |
| <span class="sd"> Value between 0 and 1 providing the quantile to compute.</span> |
| <span class="sd"> accuracy : int, optional</span> |
| <span class="sd"> Default accuracy of approximation. Larger value means better accuracy.</span> |
| <span class="sd"> The relative error can be deduced by 1.0 / accuracy.</span> |
| <span class="sd"> This is a panda-on-Spark specific parameter.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the expanding</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> `quantile` in pandas-on-Spark are using distributed percentile approximation</span> |
| <span class="sd"> algorithm unlike pandas, the result might be different with pandas, also `interpolation`</span> |
| <span class="sd"> parameter is not supported yet.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling expanding with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling expanding with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.quantile : Aggregating quantile for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.quantile : Aggregating quantile for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).expanding(3).quantile(0.5).sort_index()</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 NaN</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 NaN</span> |
| <span class="sd"> 7 4.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 NaN</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each expanding quantile is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).expanding(2).quantile(0.5).sort_index()</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 NaN</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 3 2 NaN</span> |
| <span class="sd"> 3 9.0</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 NaN</span> |
| <span class="sd"> 6 16.0</span> |
| <span class="sd"> 7 16.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 NaN</span> |
| <span class="sd"> 10 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">quantile</span><span class="p">(</span><span class="n">quantile</span><span class="p">,</span> <span class="n">accuracy</span><span class="p">)</span> |
| |
| <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"> Calculate expanding standard deviation.</span> |
| |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the expanding calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding: Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.std : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.std : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.std : Equivalent method for Numpy array.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">std</span><span class="p">()</span> |
| |
| <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"> Calculate unbiased expanding variance.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the expanding calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.var : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.var : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.var : Equivalent method for Numpy array.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">var</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">skew</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"> Calculate expanding standard skew.</span> |
| |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the expanding calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding: Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.std : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.std : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.std : Equivalent method for Numpy array.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">skew</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">kurt</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"> Calculate unbiased expanding kurtosis.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returns the same object type as the caller of the expanding calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.var : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.var : Equivalent method for DataFrame.</span> |
| <span class="sd"> numpy.var : Equivalent method for Numpy array.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">kurt</span><span class="p">()</span> |
| |
| |
| <span class="k">class</span> <span class="nc">ExponentialMovingLike</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="k">def</span> <span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">window</span><span class="p">:</span> <span class="n">WindowSpec</span><span class="p">,</span> |
| <span class="n">com</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">span</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">halflife</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">alpha</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">min_periods</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">ignore_na</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">min_periods</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span><span class="n">min_periods</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">"min_periods must be >= 0"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">min_periods</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">min_periods</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span> <span class="o">=</span> <span class="n">min_periods</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_ignore_na</span> <span class="o">=</span> <span class="n">ignore_na</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_window</span> <span class="o">=</span> <span class="n">window</span> |
| <span class="c1"># This unbounded Window is later used to handle 'min_periods' for now.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span> <span class="o">=</span> <span class="n">Window</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">NATURAL_ORDER_COLUMN_NAME</span><span class="p">)</span><span class="o">.</span><span class="n">rowsBetween</span><span class="p">(</span> |
| <span class="n">Window</span><span class="o">.</span><span class="n">unboundedPreceding</span><span class="p">,</span> <span class="n">Window</span><span class="o">.</span><span class="n">currentRow</span> |
| <span class="p">)</span> |
| |
| <span class="k">if</span> <span class="p">(</span><span class="n">com</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span><span class="ow">not</span> <span class="n">com</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">"com must be >= 0"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_com</span> <span class="o">=</span> <span class="n">com</span> |
| |
| <span class="k">if</span> <span class="p">(</span><span class="n">span</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span><span class="ow">not</span> <span class="n">span</span> <span class="o">>=</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"span must be >= 1"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_span</span> <span class="o">=</span> <span class="n">span</span> |
| |
| <span class="k">if</span> <span class="p">(</span><span class="n">halflife</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span><span class="ow">not</span> <span class="n">halflife</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">"halflife must be > 0"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_halflife</span> <span class="o">=</span> <span class="n">halflife</span> |
| |
| <span class="k">if</span> <span class="p">(</span><span class="n">alpha</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span><span class="ow">not</span> <span class="mi">0</span> <span class="o"><</span> <span class="n">alpha</span> <span class="o"><=</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"alpha must be in (0, 1]"</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_alpha</span> <span class="o">=</span> <span class="n">alpha</span> |
| |
| <span class="k">def</span> <span class="nf">_compute_unified_alpha</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="n">unified_alpha</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">nan</span> |
| <span class="n">opt_count</span> <span class="o">=</span> <span class="mi">0</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_com</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">unified_alpha</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_com</span><span class="p">)</span> |
| <span class="n">opt_count</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_span</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">unified_alpha</span> <span class="o">=</span> <span class="mf">2.0</span> <span class="o">/</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_span</span><span class="p">)</span> |
| <span class="n">opt_count</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_halflife</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">unified_alpha</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="n">np</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_halflife</span><span class="p">)</span> |
| <span class="n">opt_count</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_alpha</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">unified_alpha</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_alpha</span> |
| <span class="n">opt_count</span> <span class="o">+=</span> <span class="mi">1</span> |
| |
| <span class="k">if</span> <span class="n">opt_count</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">"Must pass one of com, span, halflife, or alpha"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">opt_count</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"com, span, halflife, and alpha are mutually exclusive"</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">unified_alpha</span> |
| |
| <span class="nd">@abstractmethod</span> |
| <span class="k">def</span> <span class="nf">_apply_as_series_or_frame</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">func</span><span class="p">:</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">Column</span><span class="p">],</span> <span class="n">Column</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"> Wraps a function that handles Spark column in order</span> |
| <span class="sd"> to support it in both pandas-on-Spark Series and DataFrame.</span> |
| <span class="sd"> Note that the given `func` name should be same as the API's method name.</span> |
| <span class="sd"> """</span> |
| <span class="k">pass</span> |
| |
| <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="n">unified_alpha</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compute_unified_alpha</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">mean</span><span class="p">(</span><span class="n">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">col_ewm</span> <span class="o">=</span> <span class="n">SF</span><span class="o">.</span><span class="n">ewm</span><span class="p">(</span><span class="n">scol</span><span class="p">,</span> <span class="n">unified_alpha</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ignore_na</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">when</span><span class="p">(</span> |
| <span class="n">F</span><span class="o">.</span><span class="n">count</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="o">~</span><span class="n">scol</span><span class="o">.</span><span class="n">isNull</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="kc">None</span><span class="p">))</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="p">)</span> |
| <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="n">col_ewm</span><span class="o">.</span><span class="n">over</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_window</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">F</span><span class="o">.</span><span class="n">lit</span><span class="p">(</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">_apply_as_series_or_frame</span><span class="p">(</span><span class="n">mean</span><span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">ExponentialMoving</span><span class="p">(</span><span class="n">ExponentialMovingLike</span><span class="p">[</span><span class="n">FrameLike</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_or_psser</span><span class="p">:</span> <span class="n">FrameLike</span><span class="p">,</span> |
| <span class="n">com</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">span</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">halflife</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">alpha</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">min_periods</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">ignore_na</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.frame</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.series</span> <span class="kn">import</span> <span class="n">Series</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">psdf_or_psser</span><span class="p">,</span> <span class="p">(</span><span class="n">DataFrame</span><span class="p">,</span> <span class="n">Series</span><span class="p">)):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s2">"psdf_or_psser must be a series or dataframe; however, got: </span><span class="si">%s</span><span class="s2">"</span> |
| <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">psdf_or_psser</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_psdf_or_psser</span> <span class="o">=</span> <span class="n">psdf_or_psser</span> |
| |
| <span class="n">window_spec</span> <span class="o">=</span> <span class="n">Window</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">NATURAL_ORDER_COLUMN_NAME</span><span class="p">)</span><span class="o">.</span><span class="n">rowsBetween</span><span class="p">(</span> |
| <span class="n">Window</span><span class="o">.</span><span class="n">unboundedPreceding</span><span class="p">,</span> <span class="n">Window</span><span class="o">.</span><span class="n">currentRow</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">window_spec</span><span class="p">,</span> <span class="n">com</span><span class="p">,</span> <span class="n">span</span><span class="p">,</span> <span class="n">halflife</span><span class="p">,</span> <span class="n">alpha</span><span class="p">,</span> <span class="n">min_periods</span><span class="p">,</span> <span class="n">ignore_na</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">MissingPandasLikeExponentialMoving</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">MissingPandasLikeExponentialMoving</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">raise</span> <span class="ne">AttributeError</span><span class="p">(</span><span class="n">item</span><span class="p">)</span> |
| |
| <span class="n">_apply_as_series_or_frame</span> <span class="o">=</span> <span class="n">Rolling</span><span class="o">.</span><span class="n">_apply_as_series_or_frame</span> |
| |
| <div class="viewcode-block" id="ExponentialMoving.mean"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.window.ExponentialMoving.mean.html#pyspark.pandas.window.ExponentialMoving.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"> Calculate an online exponentially weighted mean.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> There are behavior differences between pandas-on-Spark and pandas.</span> |
| |
| <span class="sd"> * the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the exponentially</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.mean : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.mean : Equivalent method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> The below examples will show computing exponentially weighted moving average.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({'s1': [.2, .0, .6, .2, .4, .5, .6], 's2': [2, 1, 3, 1, 0, 0, 0]})</span> |
| <span class="sd"> >>> df.ewm(com=0.1).mean()</span> |
| <span class="sd"> s1 s2</span> |
| <span class="sd"> 0 0.200000 2.000000</span> |
| <span class="sd"> 1 0.016667 1.083333</span> |
| <span class="sd"> 2 0.547368 2.827068</span> |
| <span class="sd"> 3 0.231557 1.165984</span> |
| <span class="sd"> 4 0.384688 0.105992</span> |
| <span class="sd"> 5 0.489517 0.009636</span> |
| <span class="sd"> 6 0.589956 0.000876</span> |
| |
| <span class="sd"> >>> df.s2.ewm(halflife=1.5, min_periods=3).mean()</span> |
| <span class="sd"> 0 NaN</span> |
| <span class="sd"> 1 NaN</span> |
| <span class="sd"> 2 2.182572</span> |
| <span class="sd"> 3 1.663174</span> |
| <span class="sd"> 4 0.979949</span> |
| <span class="sd"> 5 0.593155</span> |
| <span class="sd"> 6 0.364668</span> |
| <span class="sd"> Name: s2, dtype: float64</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span></div> |
| |
| <span class="c1"># TODO: when add 'adjust' parameter, should add to here too.</span> |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="s2">"ExponentialMoving [com=</span><span class="si">{}</span><span class="s2">, span=</span><span class="si">{}</span><span class="s2">, halflife=</span><span class="si">{}</span><span class="s2">, alpha=</span><span class="si">{}</span><span class="s2">, "</span> |
| <span class="s2">"min_periods=</span><span class="si">{}</span><span class="s2">, ignore_na=</span><span class="si">{}</span><span class="s2">]"</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">_com</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_span</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_halflife</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_alpha</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_ignore_na</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">ExponentialMovingGroupby</span><span class="p">(</span><span class="n">ExponentialMovingLike</span><span class="p">[</span><span class="n">FrameLike</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">groupby</span><span class="p">:</span> <span class="n">GroupBy</span><span class="p">[</span><span class="n">FrameLike</span><span class="p">],</span> |
| <span class="n">com</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">span</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">halflife</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">alpha</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">float</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">min_periods</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">ignore_na</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="n">window_spec</span> <span class="o">=</span> <span class="n">Window</span><span class="o">.</span><span class="n">orderBy</span><span class="p">(</span><span class="n">NATURAL_ORDER_COLUMN_NAME</span><span class="p">)</span><span class="o">.</span><span class="n">rowsBetween</span><span class="p">(</span> |
| <span class="n">Window</span><span class="o">.</span><span class="n">unboundedPreceding</span><span class="p">,</span> <span class="n">Window</span><span class="o">.</span><span class="n">currentRow</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">window_spec</span><span class="p">,</span> <span class="n">com</span><span class="p">,</span> <span class="n">span</span><span class="p">,</span> <span class="n">halflife</span><span class="p">,</span> <span class="n">alpha</span><span class="p">,</span> <span class="n">min_periods</span><span class="p">,</span> <span class="n">ignore_na</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_groupby</span> <span class="o">=</span> <span class="n">groupby</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_window</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_window</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span><span class="o">*</span><span class="p">[</span><span class="n">ser</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">ser</span> <span class="ow">in</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</span><span class="p">])</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_unbounded_window</span><span class="o">.</span><span class="n">partitionBy</span><span class="p">(</span> |
| <span class="o">*</span><span class="p">[</span><span class="n">ser</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">ser</span> <span class="ow">in</span> <span class="n">groupby</span><span class="o">.</span><span class="n">_groupkeys</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">MissingPandasLikeExponentialMovingGroupby</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">MissingPandasLikeExponentialMovingGroupby</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">raise</span> <span class="ne">AttributeError</span><span class="p">(</span><span class="n">item</span><span class="p">)</span> |
| |
| <span class="n">_apply_as_series_or_frame</span> <span class="o">=</span> <span class="n">RollingGroupby</span><span class="o">.</span><span class="n">_apply_as_series_or_frame</span> |
| |
| <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"> Calculate an online exponentially weighted mean.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> There are behavior differences between pandas-on-Spark and pandas.</span> |
| |
| <span class="sd"> * the current implementation of this API uses Spark's Window without</span> |
| <span class="sd"> specifying partition specification. This leads to move all data into</span> |
| <span class="sd"> single partition in single machine and could cause serious</span> |
| <span class="sd"> performance degradation. Avoid this method against very large dataset.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> Series or DataFrame</span> |
| <span class="sd"> Returned object type is determined by the caller of the exponentially</span> |
| <span class="sd"> calculation.</span> |
| |
| <span class="sd"> See Also</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> pyspark.pandas.Series.expanding : Calling object with Series data.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.expanding : Calling object with DataFrames.</span> |
| <span class="sd"> pyspark.pandas.Series.mean : Equivalent method for Series.</span> |
| <span class="sd"> pyspark.pandas.DataFrame.mean : Equivalent method for DataFrame.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> s = ps.Series([2, 2, 3, 3, 3, 4, 4, 4, 4, 5, 5])</span> |
| <span class="sd"> >>> s.groupby(s).ewm(alpha=0.5).mean().sort_index()</span> |
| <span class="sd"> 2 0 2.0</span> |
| <span class="sd"> 1 2.0</span> |
| <span class="sd"> 3 2 3.0</span> |
| <span class="sd"> 3 3.0</span> |
| <span class="sd"> 4 3.0</span> |
| <span class="sd"> 4 5 4.0</span> |
| <span class="sd"> 6 4.0</span> |
| <span class="sd"> 7 4.0</span> |
| <span class="sd"> 8 4.0</span> |
| <span class="sd"> 5 9 5.0</span> |
| <span class="sd"> 10 5.0</span> |
| <span class="sd"> dtype: float64</span> |
| |
| <span class="sd"> For DataFrame, each ewm mean is computed column-wise.</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"A": s.to_numpy(), "B": s.to_numpy() ** 2})</span> |
| <span class="sd"> >>> df.groupby(df.A).ewm(alpha=0.5).mean().sort_index() # doctest: +NORMALIZE_WHITESPACE</span> |
| <span class="sd"> B</span> |
| <span class="sd"> A</span> |
| <span class="sd"> 2 0 4.0</span> |
| <span class="sd"> 1 4.0</span> |
| <span class="sd"> 3 2 9.0</span> |
| <span class="sd"> 3 9.0</span> |
| <span class="sd"> 4 9.0</span> |
| <span class="sd"> 4 5 16.0</span> |
| <span class="sd"> 6 16.0</span> |
| <span class="sd"> 7 16.0</span> |
| <span class="sd"> 8 16.0</span> |
| <span class="sd"> 5 9 25.0</span> |
| <span class="sd"> 10 25.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span> |
| |
| <span class="c1"># TODO: when add 'adjust' parameter, should add to here too.</span> |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="s2">"ExponentialMovingGroupby [com=</span><span class="si">{}</span><span class="s2">, span=</span><span class="si">{}</span><span class="s2">, halflife=</span><span class="si">{}</span><span class="s2">, alpha=</span><span class="si">{}</span><span class="s2">, "</span> |
| <span class="s2">"min_periods=</span><span class="si">{}</span><span class="s2">, ignore_na=</span><span class="si">{}</span><span class="s2">]"</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">_com</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_span</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_halflife</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_alpha</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_min_periods</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_ignore_na</span><span class="p">,</span> |
| <span class="p">)</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.window</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">window</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.window 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">window</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> |
