| |
| |
| <!DOCTYPE html> |
| |
| |
| <html > |
| |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>pyspark.mllib.regression — PySpark 4.1.0-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/mllib/regression';</script> |
| <script> |
| DOCUMENTATION_OPTIONS.theme_switcher_json_url = 'https://spark.apache.org/static/versions.json'; |
| DOCUMENTATION_OPTIONS.theme_switcher_version_match = '4.1.0-preview2'; |
| </script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/mllib/regression.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="../../../tutorial/index.html"> |
| Tutorials |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../user_guide/index.html"> |
| User Guide |
| </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> |
| |
| <div class="nav-item dropdown"> |
| <button class="btn dropdown-toggle nav-item" type="button" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false"> |
| More |
| </button> |
| <div class="dropdown-menu"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| </div> |
| </div> |
| |
| </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"> |
| <script> |
| document.write(` |
| <div class="version-switcher__container dropdown"> |
| <button type="button" class="version-switcher__button btn btn-sm navbar-btn dropdown-toggle" data-bs-toggle="dropdown"> |
| 4.1.0-preview2 <!-- this text may get changed later by javascript --> |
| <span class="caret"></span> |
| </button> |
| <div class="version-switcher__menu dropdown-menu list-group-flush py-0"> |
| <!-- dropdown will be populated by javascript on page load --> |
| </div> |
| </div> |
| `); |
| </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="../../../tutorial/index.html"> |
| Tutorials |
| </a> |
| </li> |
| |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../user_guide/index.html"> |
| User Guide |
| </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> |
| |
| <div class="nav-item dropdown"> |
| <button class="btn dropdown-toggle nav-item" type="button" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false"> |
| More |
| </button> |
| <div class="dropdown-menu"> |
| |
| <li class="nav-item"> |
| <a class="nav-link nav-internal" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| </div> |
| </div> |
| |
| </ul> |
| </nav></div> |
| |
| </div> |
| |
| |
| |
| <div class="sidebar-header-items__end"> |
| |
| <div class="navbar-item"> |
| <script> |
| document.write(` |
| <div class="version-switcher__container dropdown"> |
| <button type="button" class="version-switcher__button btn btn-sm navbar-btn dropdown-toggle" data-bs-toggle="dropdown"> |
| 4.1.0-preview2 <!-- this text may get changed later by javascript --> |
| <span class="caret"></span> |
| </button> |
| <div class="version-switcher__menu dropdown-menu list-group-flush py-0"> |
| <!-- dropdown will be populated by javascript on page load --> |
| </div> |
| </div> |
| `); |
| </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.mllib.regression</li> |
| </ul> |
| </nav> |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| </div> |
| |
| |
| |
| |
| <div id="searchbox"></div> |
| <article class="bd-article" role="main"> |
| |
| <h1>Source code for pyspark.mllib.regression</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="kn">import</span><span class="w"> </span><span class="nn">sys</span> |
| <span class="kn">import</span><span class="w"> </span><span class="nn">warnings</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span> |
| <span class="n">Any</span><span class="p">,</span> |
| <span class="n">Callable</span><span class="p">,</span> |
| <span class="n">Iterable</span><span class="p">,</span> |
| <span class="n">Optional</span><span class="p">,</span> |
| <span class="n">Tuple</span><span class="p">,</span> |
| <span class="n">Type</span><span class="p">,</span> |
| <span class="n">TypeVar</span><span class="p">,</span> |
| <span class="n">Union</span><span class="p">,</span> |
| <span class="n">overload</span><span class="p">,</span> |
| <span class="n">TYPE_CHECKING</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="kn">import</span><span class="w"> </span><span class="nn">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span> |
| |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark</span><span class="w"> </span><span class="kn">import</span> <span class="n">RDD</span><span class="p">,</span> <span class="n">since</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.streaming.dstream</span><span class="w"> </span><span class="kn">import</span> <span class="n">DStream</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib.common</span><span class="w"> </span><span class="kn">import</span> <span class="n">callMLlibFunc</span><span class="p">,</span> <span class="n">_py2java</span><span class="p">,</span> <span class="n">_java2py</span><span class="p">,</span> <span class="n">inherit_doc</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib.linalg</span><span class="w"> </span><span class="kn">import</span> <span class="n">_convert_to_vector</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib.util</span><span class="w"> </span><span class="kn">import</span> <span class="n">Saveable</span><span class="p">,</span> <span class="n">Loader</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.core.rdd</span><span class="w"> </span><span class="kn">import</span> <span class="n">RDD</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.core.context</span><span class="w"> </span><span class="kn">import</span> <span class="n">SparkContext</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib.linalg</span><span class="w"> </span><span class="kn">import</span> <span class="n">Vector</span> |
| |
| <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib._typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">VectorLike</span> |
| |
| |
| <span class="n">LM</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"LM"</span><span class="p">)</span> |
| <span class="n">K</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"K"</span><span class="p">)</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s2">"LabeledPoint"</span><span class="p">,</span> |
| <span class="s2">"LinearModel"</span><span class="p">,</span> |
| <span class="s2">"LinearRegressionModel"</span><span class="p">,</span> |
| <span class="s2">"LinearRegressionWithSGD"</span><span class="p">,</span> |
| <span class="s2">"RidgeRegressionModel"</span><span class="p">,</span> |
| <span class="s2">"RidgeRegressionWithSGD"</span><span class="p">,</span> |
| <span class="s2">"LassoModel"</span><span class="p">,</span> |
| <span class="s2">"LassoWithSGD"</span><span class="p">,</span> |
| <span class="s2">"IsotonicRegressionModel"</span><span class="p">,</span> |
| <span class="s2">"IsotonicRegression"</span><span class="p">,</span> |
| <span class="s2">"StreamingLinearAlgorithm"</span><span class="p">,</span> |
| <span class="s2">"StreamingLinearRegressionWithSGD"</span><span class="p">,</span> |
| <span class="p">]</span> |
| |
| |
| <div class="viewcode-block" id="LabeledPoint"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LabeledPoint.html#pyspark.mllib.regression.LabeledPoint">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">LabeledPoint</span><span class="p">:</span> |
| |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Class that represents the features and labels of a data point.</span> |
| |
| <span class="sd"> .. versionadded:: 1.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> label : int</span> |
| <span class="sd"> Label for this data point.</span> |
| <span class="sd"> features : :py:class:`pyspark.mllib.linalg.Vector` or convertible</span> |
| <span class="sd"> Vector of features for this point (NumPy array, list,</span> |
| <span class="sd"> pyspark.mllib.linalg.SparseVector, or scipy.sparse column matrix).</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> 'label' and 'features' are accessible as class attributes.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">features</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">label</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">features</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">features</span><span class="p">)</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">__reduce__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Type</span><span class="p">[</span><span class="s2">"LabeledPoint"</span><span class="p">],</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="n">Vector</span><span class="p">]]:</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">LabeledPoint</span><span class="p">,</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">label</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">features</span><span class="p">))</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="fm">__str__</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">"("</span> <span class="o">+</span> <span class="s2">","</span><span class="o">.</span><span class="n">join</span><span class="p">((</span><span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">label</span><span class="p">),</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">features</span><span class="p">)))</span> <span class="o">+</span> <span class="s2">")"</span> |
| |
| <span class="k">def</span><span class="w"> </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">"LabeledPoint(</span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2">)"</span> <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">label</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">features</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="LinearModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LinearModel.html#pyspark.mllib.regression.LinearModel">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">LinearModel</span><span class="p">:</span> |
| |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> A linear model that has a vector of coefficients and an intercept.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> weights : :py:class:`pyspark.mllib.linalg.Vector`</span> |
| <span class="sd"> Weights computed for every feature.</span> |
| <span class="sd"> intercept : float</span> |
| <span class="sd"> Intercept computed for this model.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">weights</span><span class="p">:</span> <span class="n">Vector</span><span class="p">,</span> <span class="n">intercept</span><span class="p">:</span> <span class="nb">float</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">weights</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_intercept</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">intercept</span><span class="p">)</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.0.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">weights</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Vector</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Weights computed for every feature."""</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.0.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">intercept</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="w"> </span><span class="sd">"""Intercept computed for this model."""</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_intercept</span> |
| |
| <span class="k">def</span><span class="w"> </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">"(weights=</span><span class="si">%s</span><span class="s2">, intercept=</span><span class="si">%r</span><span class="s2">)"</span> <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_intercept</span><span class="p">)</span></div> |
| |
| |
| <span class="nd">@inherit_doc</span> |
| <span class="k">class</span><span class="w"> </span><span class="nc">LinearRegressionModelBase</span><span class="p">(</span><span class="n">LinearModel</span><span class="p">):</span> |
| |
| <span class="w"> </span><span class="sd">"""A linear regression model.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import SparseVector</span> |
| <span class="sd"> >>> lrmb = LinearRegressionModelBase(np.array([1.0, 2.0]), 0.1)</span> |
| <span class="sd"> >>> bool(abs(lrmb.predict(np.array([-1.03, 7.777])) - 14.624) < 1e-6)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrmb.predict(SparseVector(2, {0: -1.03, 1: 7.777})) - 14.624) < 1e-6)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="s2">"VectorLike"</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">])</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span> |
| <span class="o">...</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]])</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">]]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Predict the value of the dependent variable given a vector or</span> |
| <span class="sd"> an RDD of vectors containing values for the independent variables.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">predict</span><span class="p">)</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">weights</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</span> <span class="c1"># type: ignore[attr-defined]</span> |
| |
| |
| <div class="viewcode-block" id="LinearRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LinearRegressionModel.html#pyspark.mllib.regression.LinearRegressionModel">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span><span class="w"> </span><span class="nc">LinearRegressionModel</span><span class="p">(</span><span class="n">LinearRegressionModelBase</span><span class="p">):</span> |
| |
| <span class="w"> </span><span class="sd">"""A linear regression model derived from a least-squares fit.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import SparseVector</span> |
| <span class="sd"> >>> from pyspark.mllib.regression import LabeledPoint</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, [0.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [1.0]),</span> |
| <span class="sd"> ... LabeledPoint(3.0, [2.0]),</span> |
| <span class="sd"> ... LabeledPoint(2.0, [3.0])</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10,</span> |
| <span class="sd"> ... initialWeights=np.array([1.0]))</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([1.0])) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(sc.parallelize([[1.0]])).collect()[0] - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> import os, tempfile</span> |
| <span class="sd"> >>> path = tempfile.mkdtemp()</span> |
| <span class="sd"> >>> lrm.save(sc, path)</span> |
| <span class="sd"> >>> sameModel = LinearRegressionModel.load(sc, path)</span> |
| <span class="sd"> >>> bool(abs(sameModel.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(sameModel.predict(np.array([1.0])) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(sameModel.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> from shutil import rmtree</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... rmtree(path)</span> |
| <span class="sd"> ... except BaseException:</span> |
| <span class="sd"> ... pass</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(1, {0: 0.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, SparseVector(1, {0: 1.0})),</span> |
| <span class="sd"> ... LabeledPoint(3.0, SparseVector(1, {0: 2.0})),</span> |
| <span class="sd"> ... LabeledPoint(2.0, SparseVector(1, {0: 3.0}))</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10,</span> |
| <span class="sd"> ... initialWeights=np.array([1.0]))</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10, step=1.0,</span> |
| <span class="sd"> ... miniBatchFraction=1.0, initialWeights=np.array([1.0]), regParam=0.1, regType="l2",</span> |
| <span class="sd"> ... intercept=True, validateData=True)</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="LinearRegressionModel.save"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LinearRegressionModel.html#pyspark.mllib.regression.LinearRegressionModel.save">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Save a LinearRegressionModel."""</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">regression</span><span class="o">.</span><span class="n">LinearRegressionModel</span><span class="p">(</span> |
| <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</span> |
| <span class="p">)</span> |
| <span class="n">java_model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="LinearRegressionModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LinearRegressionModel.html#pyspark.mllib.regression.LinearRegressionModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">load</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"LinearRegressionModel"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Load a LinearRegressionModel."""</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">regression</span><span class="o">.</span><span class="n">LinearRegressionModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span> |
| <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span> |
| <span class="p">)</span> |
| <span class="n">weights</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">weights</span><span class="p">())</span> |
| <span class="n">intercept</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">intercept</span><span class="p">()</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">LinearRegressionModel</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">model</span></div></div> |
| |
| |
| <span class="c1"># train_func should take two parameters, namely data and initial_weights, and</span> |
| <span class="c1"># return the result of a call to the appropriate JVM stub.</span> |
| <span class="c1"># _regression_train_wrapper is responsible for setup and error checking.</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">_regression_train_wrapper</span><span class="p">(</span> |
| <span class="n">train_func</span><span class="p">:</span> <span class="n">Callable</span><span class="p">[[</span><span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> <span class="n">Vector</span><span class="p">],</span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Any</span><span class="p">]],</span> |
| <span class="n">modelClass</span><span class="p">:</span> <span class="n">Type</span><span class="p">[</span><span class="n">LM</span><span class="p">],</span> |
| <span class="n">data</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> |
| <span class="n">initial_weights</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">],</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">LM</span><span class="p">:</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib.classification</span><span class="w"> </span><span class="kn">import</span> <span class="n">LogisticRegressionModel</span> |
| |
| <span class="n">first</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">first</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">first</span><span class="p">,</span> <span class="n">LabeledPoint</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"data should be an RDD of LabeledPoint, but 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">first</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">initial_weights</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">initial_weights</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.0</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">first</span><span class="p">()</span><span class="o">.</span><span class="n">features</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">modelClass</span> <span class="o">==</span> <span class="n">LogisticRegressionModel</span><span class="p">:</span> |
| <span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">,</span> <span class="n">numFeatures</span><span class="p">,</span> <span class="n">numClasses</span> <span class="o">=</span> <span class="n">train_func</span><span class="p">(</span> |
| <span class="n">data</span><span class="p">,</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">initial_weights</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="n">modelClass</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">,</span> <span class="n">numFeatures</span><span class="p">,</span> <span class="n">numClasses</span><span class="p">)</span> <span class="c1"># type: ignore[call-arg]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span> <span class="o">=</span> <span class="n">train_func</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">initial_weights</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">modelClass</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span> <span class="c1"># type: ignore[call-arg]</span> |
| |
| |
| <div class="viewcode-block" id="LinearRegressionWithSGD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LinearRegressionWithSGD.html#pyspark.mllib.regression.LinearRegressionWithSGD">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">LinearRegressionWithSGD</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train a linear regression model with no regularization using Stochastic Gradient Descent.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> .. deprecated:: 2.0.0</span> |
| <span class="sd"> Use :py:class:`pyspark.ml.regression.LinearRegression`.</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="LinearRegressionWithSGD.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LinearRegressionWithSGD.html#pyspark.mllib.regression.LinearRegressionWithSGD.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">train</span><span class="p">(</span> |
| <span class="bp">cls</span><span class="p">,</span> |
| <span class="n">data</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> |
| <span class="n">iterations</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span> |
| <span class="n">step</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">miniBatchFraction</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">initialWeights</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span> |
| <span class="n">regType</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">intercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="n">validateData</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> |
| <span class="n">convergenceTol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.001</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">LinearRegressionModel</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train a linear regression model using Stochastic Gradient</span> |
| <span class="sd"> Descent (SGD). This solves the least squares regression</span> |
| <span class="sd"> formulation</span> |
| |
| <span class="sd"> f(weights) = 1/(2n) ||A weights - y||^2</span> |
| |
| <span class="sd"> which is the mean squared error. Here the data matrix has n rows,</span> |
| <span class="sd"> and the input RDD holds the set of rows of A, each with its</span> |
| <span class="sd"> corresponding right hand side label y.</span> |
| <span class="sd"> See also the documentation for the precise formulation.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> The training data, an RDD of LabeledPoint.</span> |
| <span class="sd"> iterations : int, optional</span> |
| <span class="sd"> The number of iterations.</span> |
| <span class="sd"> (default: 100)</span> |
| <span class="sd"> step : float, optional</span> |
| <span class="sd"> The step parameter used in SGD.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> miniBatchFraction : float, optional</span> |
| <span class="sd"> Fraction of data to be used for each SGD iteration.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> initialWeights : :py:class:`pyspark.mllib.linalg.Vector` or convertible, optional</span> |
| <span class="sd"> The initial weights.</span> |
| <span class="sd"> (default: None)</span> |
| <span class="sd"> regParam : float, optional</span> |
| <span class="sd"> The regularizer parameter.</span> |
| <span class="sd"> (default: 0.0)</span> |
| <span class="sd"> regType : str, optional</span> |
| <span class="sd"> The type of regularizer used for training our model.</span> |
| <span class="sd"> Supported values:</span> |
| |
| <span class="sd"> - "l1" for using L1 regularization</span> |
| <span class="sd"> - "l2" for using L2 regularization</span> |
| <span class="sd"> - None for no regularization (default)</span> |
| |
| <span class="sd"> intercept : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates the use or not of the</span> |
| <span class="sd"> augmented representation for training data (i.e., whether bias</span> |
| <span class="sd"> features are activated or not).</span> |
| <span class="sd"> (default: False)</span> |
| <span class="sd"> validateData : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates if the algorithm should</span> |
| <span class="sd"> validate data before training.</span> |
| <span class="sd"> (default: True)</span> |
| <span class="sd"> convergenceTol : float, optional</span> |
| <span class="sd"> A condition which decides iteration termination.</span> |
| <span class="sd"> (default: 0.001)</span> |
| <span class="sd"> """</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s2">"Deprecated in 2.0.0. Use ml.regression.LinearRegression."</span><span class="p">,</span> <span class="ne">FutureWarning</span><span class="p">)</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> <span class="n">i</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Any</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainLinearRegressionModelWithSGD"</span><span class="p">,</span> |
| <span class="n">rdd</span><span class="p">,</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">iterations</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">step</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">miniBatchFraction</span><span class="p">),</span> |
| <span class="n">i</span><span class="p">,</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">regParam</span><span class="p">),</span> |
| <span class="n">regType</span><span class="p">,</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">validateData</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">convergenceTol</span><span class="p">),</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">_regression_train_wrapper</span><span class="p">(</span><span class="n">train</span><span class="p">,</span> <span class="n">LinearRegressionModel</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="LassoModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LassoModel.html#pyspark.mllib.regression.LassoModel">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span><span class="w"> </span><span class="nc">LassoModel</span><span class="p">(</span><span class="n">LinearRegressionModelBase</span><span class="p">):</span> |
| |
| <span class="w"> </span><span class="sd">"""A linear regression model derived from a least-squares fit with</span> |
| <span class="sd"> an l_1 penalty term.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import SparseVector</span> |
| <span class="sd"> >>> from pyspark.mllib.regression import LabeledPoint</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, [0.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [1.0]),</span> |
| <span class="sd"> ... LabeledPoint(3.0, [2.0]),</span> |
| <span class="sd"> ... LabeledPoint(2.0, [3.0])</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> lrm = LassoWithSGD.train(</span> |
| <span class="sd"> ... sc.parallelize(data), iterations=10, initialWeights=np.array([1.0]))</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([1.0])) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(sc.parallelize([[1.0]])).collect()[0] - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> import os, tempfile</span> |
| <span class="sd"> >>> path = tempfile.mkdtemp()</span> |
| <span class="sd"> >>> lrm.save(sc, path)</span> |
| <span class="sd"> >>> sameModel = LassoModel.load(sc, path)</span> |
| <span class="sd"> >>> bool(abs(sameModel.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(sameModel.predict(np.array([1.0])) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(sameModel.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> from shutil import rmtree</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... rmtree(path)</span> |
| <span class="sd"> ... except BaseException:</span> |
| <span class="sd"> ... pass</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(1, {0: 0.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, SparseVector(1, {0: 1.0})),</span> |
| <span class="sd"> ... LabeledPoint(3.0, SparseVector(1, {0: 2.0})),</span> |
| <span class="sd"> ... LabeledPoint(2.0, SparseVector(1, {0: 3.0}))</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10,</span> |
| <span class="sd"> ... initialWeights=np.array([1.0]))</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> lrm = LassoWithSGD.train(sc.parallelize(data), iterations=10, step=1.0,</span> |
| <span class="sd"> ... regParam=0.01, miniBatchFraction=1.0, initialWeights=np.array([1.0]), intercept=True,</span> |
| <span class="sd"> ... validateData=True)</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="LassoModel.save"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LassoModel.html#pyspark.mllib.regression.LassoModel.save">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Save a LassoModel."""</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">regression</span><span class="o">.</span><span class="n">LassoModel</span><span class="p">(</span> |
| <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</span> |
| <span class="p">)</span> |
| <span class="n">java_model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="LassoModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LassoModel.html#pyspark.mllib.regression.LassoModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">load</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"LassoModel"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Load a LassoModel."""</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">regression</span><span class="o">.</span><span class="n">LassoModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span> |
| <span class="n">weights</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">weights</span><span class="p">())</span> |
| <span class="n">intercept</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">intercept</span><span class="p">()</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">LassoModel</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">model</span></div></div> |
| |
| |
| <div class="viewcode-block" id="LassoWithSGD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LassoWithSGD.html#pyspark.mllib.regression.LassoWithSGD">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">LassoWithSGD</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train a regression model with L1-regularization using Stochastic Gradient Descent.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> .. deprecated:: 2.0.0</span> |
| <span class="sd"> Use :py:class:`pyspark.ml.regression.LinearRegression` with elasticNetParam = 1.0.</span> |
| <span class="sd"> Note the default regParam is 0.01 for LassoWithSGD, but is 0.0 for LinearRegression.</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="LassoWithSGD.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.LassoWithSGD.html#pyspark.mllib.regression.LassoWithSGD.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">train</span><span class="p">(</span> |
| <span class="bp">cls</span><span class="p">,</span> |
| <span class="n">data</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> |
| <span class="n">iterations</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span> |
| <span class="n">step</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.01</span><span class="p">,</span> |
| <span class="n">miniBatchFraction</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">initialWeights</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">intercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="n">validateData</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> |
| <span class="n">convergenceTol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.001</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">LassoModel</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train a regression model with L1-regularization using Stochastic</span> |
| <span class="sd"> Gradient Descent. This solves the l1-regularized least squares</span> |
| <span class="sd"> regression formulation</span> |
| |
| <span class="sd"> f(weights) = 1/(2n) ||A weights - y||^2 + regParam ||weights||_1</span> |
| |
| <span class="sd"> Here the data matrix has n rows, and the input RDD holds the set</span> |
| <span class="sd"> of rows of A, each with its corresponding right hand side label y.</span> |
| <span class="sd"> See also the documentation for the precise formulation.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> The training data, an RDD of LabeledPoint.</span> |
| <span class="sd"> iterations : int, optional</span> |
| <span class="sd"> The number of iterations.</span> |
| <span class="sd"> (default: 100)</span> |
| <span class="sd"> step : float, optional</span> |
| <span class="sd"> The step parameter used in SGD.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> regParam : float, optional</span> |
| <span class="sd"> The regularizer parameter.</span> |
| <span class="sd"> (default: 0.01)</span> |
| <span class="sd"> miniBatchFraction : float, optional</span> |
| <span class="sd"> Fraction of data to be used for each SGD iteration.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> initialWeights : :py:class:`pyspark.mllib.linalg.Vector` or convertible, optional</span> |
| <span class="sd"> The initial weights.</span> |
| <span class="sd"> (default: None)</span> |
| <span class="sd"> intercept : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates the use or not of the</span> |
| <span class="sd"> augmented representation for training data (i.e. whether bias</span> |
| <span class="sd"> features are activated or not).</span> |
| <span class="sd"> (default: False)</span> |
| <span class="sd"> validateData : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates if the algorithm should</span> |
| <span class="sd"> validate data before training.</span> |
| <span class="sd"> (default: True)</span> |
| <span class="sd"> convergenceTol : float, optional</span> |
| <span class="sd"> A condition which decides iteration termination.</span> |
| <span class="sd"> (default: 0.001)</span> |
| <span class="sd"> """</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span> |
| <span class="s2">"Deprecated in 2.0.0. Use ml.regression.LinearRegression with elasticNetParam = 1.0. "</span> |
| <span class="s2">"Note the default regParam is 0.01 for LassoWithSGD, but is 0.0 for LinearRegression."</span><span class="p">,</span> |
| <span class="ne">FutureWarning</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> <span class="n">i</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Any</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainLassoModelWithSGD"</span><span class="p">,</span> |
| <span class="n">rdd</span><span class="p">,</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">iterations</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">step</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">regParam</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">miniBatchFraction</span><span class="p">),</span> |
| <span class="n">i</span><span class="p">,</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">validateData</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">convergenceTol</span><span class="p">),</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">_regression_train_wrapper</span><span class="p">(</span><span class="n">train</span><span class="p">,</span> <span class="n">LassoModel</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="RidgeRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.RidgeRegressionModel.html#pyspark.mllib.regression.RidgeRegressionModel">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span><span class="w"> </span><span class="nc">RidgeRegressionModel</span><span class="p">(</span><span class="n">LinearRegressionModelBase</span><span class="p">):</span> |
| |
| <span class="w"> </span><span class="sd">"""A linear regression model derived from a least-squares fit with</span> |
| <span class="sd"> an l_2 penalty term.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from pyspark.mllib.linalg import SparseVector</span> |
| <span class="sd"> >>> from pyspark.mllib.regression import LabeledPoint</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, [0.0]),</span> |
| <span class="sd"> ... LabeledPoint(1.0, [1.0]),</span> |
| <span class="sd"> ... LabeledPoint(3.0, [2.0]),</span> |
| <span class="sd"> ... LabeledPoint(2.0, [3.0])</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> lrm = RidgeRegressionWithSGD.train(sc.parallelize(data), iterations=10,</span> |
| <span class="sd"> ... initialWeights=np.array([1.0]))</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([1.0])) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(sc.parallelize([[1.0]])).collect()[0] - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> import os, tempfile</span> |
| <span class="sd"> >>> path = tempfile.mkdtemp()</span> |
| <span class="sd"> >>> lrm.save(sc, path)</span> |
| <span class="sd"> >>> sameModel = RidgeRegressionModel.load(sc, path)</span> |
| <span class="sd"> >>> bool(abs(sameModel.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(sameModel.predict(np.array([1.0])) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(sameModel.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> from shutil import rmtree</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... rmtree(path)</span> |
| <span class="sd"> ... except BaseException:</span> |
| <span class="sd"> ... pass</span> |
| <span class="sd"> >>> data = [</span> |
| <span class="sd"> ... LabeledPoint(0.0, SparseVector(1, {0: 0.0})),</span> |
| <span class="sd"> ... LabeledPoint(1.0, SparseVector(1, {0: 1.0})),</span> |
| <span class="sd"> ... LabeledPoint(3.0, SparseVector(1, {0: 2.0})),</span> |
| <span class="sd"> ... LabeledPoint(2.0, SparseVector(1, {0: 3.0}))</span> |
| <span class="sd"> ... ]</span> |
| <span class="sd"> >>> lrm = LinearRegressionWithSGD.train(sc.parallelize(data), iterations=10,</span> |
| <span class="sd"> ... initialWeights=np.array([1.0]))</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> lrm = RidgeRegressionWithSGD.train(sc.parallelize(data), iterations=10, step=1.0,</span> |
| <span class="sd"> ... regParam=0.01, miniBatchFraction=1.0, initialWeights=np.array([1.0]), intercept=True,</span> |
| <span class="sd"> ... validateData=True)</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(np.array([0.0])) - 0) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> bool(abs(lrm.predict(SparseVector(1, {0: 1.0})) - 1) < 0.5)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="RidgeRegressionModel.save"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.RidgeRegressionModel.html#pyspark.mllib.regression.RidgeRegressionModel.save">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Save a RidgeRegressionMode."""</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">regression</span><span class="o">.</span><span class="n">RidgeRegressionModel</span><span class="p">(</span> |
| <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coeff</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">intercept</span> |
| <span class="p">)</span> |
| <span class="n">java_model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RidgeRegressionModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.RidgeRegressionModel.html#pyspark.mllib.regression.RidgeRegressionModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">load</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"RidgeRegressionModel"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Load a RidgeRegressionMode."""</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">regression</span><span class="o">.</span><span class="n">RidgeRegressionModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span> |
| <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span> |
| <span class="p">)</span> |
| <span class="n">weights</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">weights</span><span class="p">())</span> |
| <span class="n">intercept</span> <span class="o">=</span> <span class="n">java_model</span><span class="o">.</span><span class="n">intercept</span><span class="p">()</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">RidgeRegressionModel</span><span class="p">(</span><span class="n">weights</span><span class="p">,</span> <span class="n">intercept</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">model</span></div></div> |
| |
| |
| <div class="viewcode-block" id="RidgeRegressionWithSGD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.RidgeRegressionWithSGD.html#pyspark.mllib.regression.RidgeRegressionWithSGD">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">RidgeRegressionWithSGD</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train a regression model with L2-regularization using Stochastic Gradient Descent.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> .. deprecated:: 2.0.0</span> |
| <span class="sd"> Use :py:class:`pyspark.ml.regression.LinearRegression` with elasticNetParam = 0.0.</span> |
| <span class="sd"> Note the default regParam is 0.01 for RidgeRegressionWithSGD, but is 0.0 for</span> |
| <span class="sd"> LinearRegression.</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="RidgeRegressionWithSGD.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.RidgeRegressionWithSGD.html#pyspark.mllib.regression.RidgeRegressionWithSGD.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">train</span><span class="p">(</span> |
| <span class="bp">cls</span><span class="p">,</span> |
| <span class="n">data</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> |
| <span class="n">iterations</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</span><span class="p">,</span> |
| <span class="n">step</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">regParam</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.01</span><span class="p">,</span> |
| <span class="n">miniBatchFraction</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">initialWeights</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">intercept</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="n">validateData</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> |
| <span class="n">convergenceTol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.001</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">RidgeRegressionModel</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train a regression model with L2-regularization using Stochastic</span> |
| <span class="sd"> Gradient Descent. This solves the l2-regularized least squares</span> |
| <span class="sd"> regression formulation</span> |
| |
| <span class="sd"> f(weights) = 1/(2n) ||A weights - y||^2 + regParam/2 ||weights||^2</span> |
| |
| <span class="sd"> Here the data matrix has n rows, and the input RDD holds the set</span> |
| <span class="sd"> of rows of A, each with its corresponding right hand side label y.</span> |
| <span class="sd"> See also the documentation for the precise formulation.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> The training data, an RDD of LabeledPoint.</span> |
| <span class="sd"> iterations : int, optional</span> |
| <span class="sd"> The number of iterations.</span> |
| <span class="sd"> (default: 100)</span> |
| <span class="sd"> step : float, optional</span> |
| <span class="sd"> The step parameter used in SGD.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> regParam : float, optional</span> |
| <span class="sd"> The regularizer parameter.</span> |
| <span class="sd"> (default: 0.01)</span> |
| <span class="sd"> miniBatchFraction : float, optional</span> |
| <span class="sd"> Fraction of data to be used for each SGD iteration.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> initialWeights : :py:class:`pyspark.mllib.linalg.Vector` or convertible, optional</span> |
| <span class="sd"> The initial weights.</span> |
| <span class="sd"> (default: None)</span> |
| <span class="sd"> intercept : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates the use or not of the</span> |
| <span class="sd"> augmented representation for training data (i.e. whether bias</span> |
| <span class="sd"> features are activated or not).</span> |
| <span class="sd"> (default: False)</span> |
| <span class="sd"> validateData : bool, optional</span> |
| <span class="sd"> Boolean parameter which indicates if the algorithm should</span> |
| <span class="sd"> validate data before training.</span> |
| <span class="sd"> (default: True)</span> |
| <span class="sd"> convergenceTol : float, optional</span> |
| <span class="sd"> A condition which decides iteration termination.</span> |
| <span class="sd"> (default: 0.001)</span> |
| <span class="sd"> """</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span> |
| <span class="s2">"Deprecated in 2.0.0. Use ml.regression.LinearRegression with elasticNetParam = 0.0. "</span> |
| <span class="s2">"Note the default regParam is 0.01 for RidgeRegressionWithSGD, but is 0.0 for "</span> |
| <span class="s2">"LinearRegression."</span><span class="p">,</span> |
| <span class="ne">FutureWarning</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">train</span><span class="p">(</span><span class="n">rdd</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">],</span> <span class="n">i</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-></span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Any</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainRidgeModelWithSGD"</span><span class="p">,</span> |
| <span class="n">rdd</span><span class="p">,</span> |
| <span class="nb">int</span><span class="p">(</span><span class="n">iterations</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">step</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">regParam</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">miniBatchFraction</span><span class="p">),</span> |
| <span class="n">i</span><span class="p">,</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">intercept</span><span class="p">),</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">validateData</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">convergenceTol</span><span class="p">),</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">_regression_train_wrapper</span><span class="p">(</span><span class="n">train</span><span class="p">,</span> <span class="n">RidgeRegressionModel</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="IsotonicRegressionModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.IsotonicRegressionModel.html#pyspark.mllib.regression.IsotonicRegressionModel">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">IsotonicRegressionModel</span><span class="p">(</span><span class="n">Saveable</span><span class="p">,</span> <span class="n">Loader</span><span class="p">[</span><span class="s2">"IsotonicRegressionModel"</span><span class="p">]):</span> |
| |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Regression model for isotonic regression.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> boundaries : ndarray</span> |
| <span class="sd"> Array of boundaries for which predictions are known. Boundaries</span> |
| <span class="sd"> must be sorted in increasing order.</span> |
| <span class="sd"> predictions : ndarray</span> |
| <span class="sd"> Array of predictions associated to the boundaries at the same</span> |
| <span class="sd"> index. Results of isotonic regression and therefore monotone.</span> |
| <span class="sd"> isotonic : true</span> |
| <span class="sd"> Indicates whether this is isotonic or antitonic.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> data = [(1, 0, 1), (2, 1, 1), (3, 2, 1), (1, 3, 1), (6, 4, 1), (17, 5, 1), (16, 6, 1)]</span> |
| <span class="sd"> >>> irm = IsotonicRegression.train(sc.parallelize(data))</span> |
| <span class="sd"> >>> float(irm.predict(3))</span> |
| <span class="sd"> 2.0</span> |
| <span class="sd"> >>> float(irm.predict(5))</span> |
| <span class="sd"> 16.5</span> |
| <span class="sd"> >>> list(map(float, irm.predict(sc.parallelize([3, 5])).collect()))</span> |
| <span class="sd"> [2.0, 16.5]</span> |
| <span class="sd"> >>> import os, tempfile</span> |
| <span class="sd"> >>> path = tempfile.mkdtemp()</span> |
| <span class="sd"> >>> irm.save(sc, path)</span> |
| <span class="sd"> >>> sameModel = IsotonicRegressionModel.load(sc, path)</span> |
| <span class="sd"> >>> float(sameModel.predict(3))</span> |
| <span class="sd"> 2.0</span> |
| <span class="sd"> >>> float(sameModel.predict(5))</span> |
| <span class="sd"> 16.5</span> |
| <span class="sd"> >>> from shutil import rmtree</span> |
| <span class="sd"> >>> try:</span> |
| <span class="sd"> ... rmtree(path)</span> |
| <span class="sd"> ... except OSError:</span> |
| <span class="sd"> ... pass</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">boundaries</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span> <span class="n">predictions</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span> <span class="n">isotonic</span><span class="p">:</span> <span class="nb">bool</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">boundaries</span> <span class="o">=</span> <span class="n">boundaries</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">predictions</span> <span class="o">=</span> <span class="n">predictions</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">isotonic</span> <span class="o">=</span> <span class="n">isotonic</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="s2">"VectorLike"</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">]:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">])</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">]:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="IsotonicRegressionModel.predict"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.IsotonicRegressionModel.html#pyspark.mllib.regression.IsotonicRegressionModel.predict">[docs]</a> <span class="k">def</span><span class="w"> </span><span class="nf">predict</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="s2">"VectorLike"</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">]]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">],</span> <span class="n">RDD</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">]]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Predict labels for provided features.</span> |
| <span class="sd"> Using a piecewise linear function.</span> |
| <span class="sd"> 1) If x exactly matches a boundary then associated prediction</span> |
| <span class="sd"> is returned. In case there are multiple predictions with the</span> |
| <span class="sd"> same boundary then one of them is returned. Which one is</span> |
| <span class="sd"> undefined (same as java.util.Arrays.binarySearch).</span> |
| <span class="sd"> 2) If x is lower or higher than all boundaries then first or</span> |
| <span class="sd"> last prediction is returned respectively. In case there are</span> |
| <span class="sd"> multiple predictions with the same boundary then the lowest</span> |
| <span class="sd"> or highest is returned respectively.</span> |
| <span class="sd"> 3) If x falls between two values in boundary array then</span> |
| <span class="sd"> prediction is treated as piecewise linear function and</span> |
| <span class="sd"> interpolated value is returned. In case there are multiple</span> |
| <span class="sd"> values with the same boundary then the same rules as in 2)</span> |
| <span class="sd"> are used.</span> |
| |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> x : :py:class:`pyspark.mllib.linalg.Vector` or :py:class:`pyspark.RDD`</span> |
| <span class="sd"> Feature or RDD of Features to be labeled.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">v</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">interp</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">boundaries</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">predictions</span><span class="p">)</span> <span class="c1"># type: ignore[arg-type]</span></div> |
| |
| <div class="viewcode-block" id="IsotonicRegressionModel.save"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.IsotonicRegressionModel.html#pyspark.mllib.regression.IsotonicRegressionModel.save">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Save an IsotonicRegressionModel."""</span> |
| <span class="n">java_boundaries</span> <span class="o">=</span> <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">boundaries</span><span class="o">.</span><span class="n">tolist</span><span class="p">())</span> |
| <span class="n">java_predictions</span> <span class="o">=</span> <span class="n">_py2java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">predictions</span><span class="o">.</span><span class="n">tolist</span><span class="p">())</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">regression</span><span class="o">.</span><span class="n">IsotonicRegressionModel</span><span class="p">(</span> |
| <span class="n">java_boundaries</span><span class="p">,</span> <span class="n">java_predictions</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">isotonic</span> |
| <span class="p">)</span> |
| <span class="n">java_model</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="IsotonicRegressionModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.IsotonicRegressionModel.html#pyspark.mllib.regression.IsotonicRegressionModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.4.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">load</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">sc</span><span class="p">:</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"IsotonicRegressionModel"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Load an IsotonicRegressionModel."""</span> |
| <span class="k">assert</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| |
| <span class="n">java_model</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jvm</span><span class="o">.</span><span class="n">org</span><span class="o">.</span><span class="n">apache</span><span class="o">.</span><span class="n">spark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">regression</span><span class="o">.</span><span class="n">IsotonicRegressionModel</span><span class="o">.</span><span class="n">load</span><span class="p">(</span> |
| <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="o">.</span><span class="n">sc</span><span class="p">(),</span> <span class="n">path</span> |
| <span class="p">)</span> |
| <span class="n">py_boundaries</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">boundaryVector</span><span class="p">())</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span> |
| <span class="n">py_predictions</span> <span class="o">=</span> <span class="n">_java2py</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">predictionVector</span><span class="p">())</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">IsotonicRegressionModel</span><span class="p">(</span><span class="n">py_boundaries</span><span class="p">,</span> <span class="n">py_predictions</span><span class="p">,</span> <span class="n">java_model</span><span class="o">.</span><span class="n">isotonic</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="IsotonicRegression"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.IsotonicRegression.html#pyspark.mllib.regression.IsotonicRegression">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">IsotonicRegression</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Isotonic regression.</span> |
| <span class="sd"> Currently implemented using parallelized pool adjacent violators</span> |
| <span class="sd"> algorithm. Only univariate (single feature) algorithm supported.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Sequential PAV implementation based on</span> |
| <span class="sd"> Tibshirani, Ryan J., Holger Hoefling, and Robert Tibshirani (2011) [1]_</span> |
| |
| <span class="sd"> Sequential PAV parallelization based on</span> |
| <span class="sd"> Kearsley, Anthony J., Richard A. Tapia, and Michael W. Trosset (1996) [2]_</span> |
| |
| <span class="sd"> See also</span> |
| <span class="sd"> `Isotonic regression (Wikipedia) <http://en.wikipedia.org/wiki/Isotonic_regression>`_.</span> |
| |
| <span class="sd"> .. [1] Tibshirani, Ryan J., Holger Hoefling, and Robert Tibshirani.</span> |
| <span class="sd"> "Nearly-isotonic regression." Technometrics 53.1 (2011): 54-61.</span> |
| <span class="sd"> Available from http://www.stat.cmu.edu/~ryantibs/papers/neariso.pdf</span> |
| <span class="sd"> .. [2] Kearsley, Anthony J., Richard A. Tapia, and Michael W. Trosset</span> |
| <span class="sd"> "An approach to parallelizing isotonic regression."</span> |
| <span class="sd"> Applied Mathematics and Parallel Computing. Physica-Verlag HD, 1996. 141-147.</span> |
| <span class="sd"> Available from http://softlib.rice.edu/pub/CRPC-TRs/reports/CRPC-TR96640.pdf</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="IsotonicRegression.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.IsotonicRegression.html#pyspark.mllib.regression.IsotonicRegression.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">train</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">data</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">],</span> <span class="n">isotonic</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="n">IsotonicRegressionModel</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train an isotonic regression model on the given data.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> data : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of (label, feature, weight) tuples.</span> |
| <span class="sd"> isotonic : bool, optional</span> |
| <span class="sd"> Whether this is isotonic (which is default) or antitonic.</span> |
| <span class="sd"> (default: True)</span> |
| <span class="sd"> """</span> |
| <span class="n">boundaries</span><span class="p">,</span> <span class="n">predictions</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainIsotonicRegressionModel"</span><span class="p">,</span> <span class="n">data</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">),</span> <span class="nb">bool</span><span class="p">(</span><span class="n">isotonic</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="n">IsotonicRegressionModel</span><span class="p">(</span><span class="n">boundaries</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">predictions</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">isotonic</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="StreamingLinearAlgorithm"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.StreamingLinearAlgorithm.html#pyspark.mllib.regression.StreamingLinearAlgorithm">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">StreamingLinearAlgorithm</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Base class that has to be inherited by any StreamingLinearAlgorithm.</span> |
| |
| <span class="sd"> Prevents reimplementation of methods predictOn and predictOnValues.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">model</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">LinearModel</span><span class="p">]):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="n">model</span> |
| |
| <div class="viewcode-block" id="StreamingLinearAlgorithm.latestModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.StreamingLinearAlgorithm.html#pyspark.mllib.regression.StreamingLinearAlgorithm.latestModel">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.5.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">latestModel</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Optional</span><span class="p">[</span><span class="n">LinearModel</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the latest model.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span></div> |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">_validate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dstream</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dstream</span><span class="p">,</span> <span class="n">DStream</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"dstream should be a DStream object, 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">dstream</span><span class="p">))</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Model must be initialized using setInitialWeights"</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="StreamingLinearAlgorithm.predictOn"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.StreamingLinearAlgorithm.html#pyspark.mllib.regression.StreamingLinearAlgorithm.predictOn">[docs]</a> <span class="k">def</span><span class="w"> </span><span class="nf">predictOn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dstream</span><span class="p">:</span> <span class="s2">"DStream[VectorLike]"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DStream[float]"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Use the model to make predictions on batches of data from a</span> |
| <span class="sd"> DStream.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.streaming.DStream`</span> |
| <span class="sd"> DStream containing predictions.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_validate</span><span class="p">(</span><span class="n">dstream</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">dstream</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">x</span><span class="p">))</span> <span class="c1"># type: ignore[union-attr]</span></div> |
| |
| <div class="viewcode-block" id="StreamingLinearAlgorithm.predictOnValues"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.StreamingLinearAlgorithm.html#pyspark.mllib.regression.StreamingLinearAlgorithm.predictOnValues">[docs]</a> <span class="k">def</span><span class="w"> </span><span class="nf">predictOnValues</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">dstream</span><span class="p">:</span> <span class="s2">"DStream[Tuple[K, VectorLike]]"</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"DStream[Tuple[K, float]]"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Use the model to make predictions on the values of a DStream and</span> |
| <span class="sd"> carry over its keys.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.streaming.DStream`</span> |
| <span class="sd"> DStream containing predictions.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_validate</span><span class="p">(</span><span class="n">dstream</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">dstream</span><span class="o">.</span><span class="n">mapValues</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">x</span><span class="p">))</span> <span class="c1"># type: ignore[union-attr]</span></div></div> |
| |
| |
| <div class="viewcode-block" id="StreamingLinearRegressionWithSGD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.StreamingLinearRegressionWithSGD.html#pyspark.mllib.regression.StreamingLinearRegressionWithSGD">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span><span class="w"> </span><span class="nc">StreamingLinearRegressionWithSGD</span><span class="p">(</span><span class="n">StreamingLinearAlgorithm</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train or predict a linear regression model on streaming data.</span> |
| <span class="sd"> Training uses Stochastic Gradient Descent to update the model</span> |
| <span class="sd"> based on each new batch of incoming data from a DStream</span> |
| <span class="sd"> (see `LinearRegressionWithSGD` for model equation).</span> |
| |
| <span class="sd"> Each batch of data is assumed to be an RDD of LabeledPoints.</span> |
| <span class="sd"> The number of data points per batch can vary, but the number</span> |
| <span class="sd"> of features must be constant. An initial weight vector must</span> |
| <span class="sd"> be provided.</span> |
| |
| <span class="sd"> .. versionadded:: 1.5.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> stepSize : float, optional</span> |
| <span class="sd"> Step size for each iteration of gradient descent.</span> |
| <span class="sd"> (default: 0.1)</span> |
| <span class="sd"> numIterations : int, optional</span> |
| <span class="sd"> Number of iterations run for each batch of data.</span> |
| <span class="sd"> (default: 50)</span> |
| <span class="sd"> miniBatchFraction : float, optional</span> |
| <span class="sd"> Fraction of each batch of data to use for updates.</span> |
| <span class="sd"> (default: 1.0)</span> |
| <span class="sd"> convergenceTol : float, optional</span> |
| <span class="sd"> Value used to determine when to terminate iterations.</span> |
| <span class="sd"> (default: 0.001)</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">stepSize</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.1</span><span class="p">,</span> |
| <span class="n">numIterations</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">50</span><span class="p">,</span> |
| <span class="n">miniBatchFraction</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> |
| <span class="n">convergenceTol</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.001</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">stepSize</span> <span class="o">=</span> <span class="n">stepSize</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numIterations</span> <span class="o">=</span> <span class="n">numIterations</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">miniBatchFraction</span> <span class="o">=</span> <span class="n">miniBatchFraction</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">convergenceTol</span> <span class="o">=</span> <span class="n">convergenceTol</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">LinearModel</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">StreamingLinearRegressionWithSGD</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">model</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="StreamingLinearRegressionWithSGD.setInitialWeights"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.StreamingLinearRegressionWithSGD.html#pyspark.mllib.regression.StreamingLinearRegressionWithSGD.setInitialWeights">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.5.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">setInitialWeights</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">initialWeights</span><span class="p">:</span> <span class="s2">"VectorLike"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"StreamingLinearRegressionWithSGD"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Set the initial value of weights.</span> |
| |
| <span class="sd"> This must be set before running trainOn and predictOn</span> |
| <span class="sd"> """</span> |
| <span class="n">initialWeights</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">initialWeights</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="n">LinearRegressionModel</span><span class="p">(</span><span class="n">initialWeights</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="StreamingLinearRegressionWithSGD.trainOn"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.regression.StreamingLinearRegressionWithSGD.html#pyspark.mllib.regression.StreamingLinearRegressionWithSGD.trainOn">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.5.0"</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">trainOn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dstream</span><span class="p">:</span> <span class="s2">"DStream[LabeledPoint]"</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Train the model on the incoming dstream."""</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_validate</span><span class="p">(</span><span class="n">dstream</span><span class="p">)</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">update</span><span class="p">(</span><span class="n">rdd</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">LabeledPoint</span><span class="p">])</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="c1"># LinearRegressionWithSGD.train raises an error for an empty RDD.</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">rdd</span><span class="o">.</span><span class="n">isEmpty</span><span class="p">():</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="n">LinearRegressionWithSGD</span><span class="o">.</span><span class="n">train</span><span class="p">(</span> |
| <span class="n">rdd</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numIterations</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">stepSize</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">miniBatchFraction</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="o">.</span><span class="n">weights</span><span class="p">,</span> |
| <span class="n">intercept</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="o">.</span><span class="n">intercept</span><span class="p">,</span> <span class="c1"># type: ignore[arg-type]</span> |
| <span class="n">convergenceTol</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">convergenceTol</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="n">dstream</span><span class="o">.</span><span class="n">foreachRDD</span><span class="p">(</span><span class="n">update</span><span class="p">)</span></div></div> |
| |
| |
| <span class="k">def</span><span class="w"> </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="w"> </span><span class="nn">doctest</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql</span><span class="w"> </span><span class="kn">import</span> <span class="n">SparkSession</span> |
| <span class="kn">import</span><span class="w"> </span><span class="nn">pyspark.mllib.regression</span> |
| |
| <span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">mllib</span><span class="o">.</span><span class="n">regression</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">spark</span> <span class="o">=</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[2]"</span><span class="p">)</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"mllib.regression tests"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"sc"</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</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">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="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 @ 2025 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> |
