| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.ml.recommendation — PySpark 3.2.2 documentation</title> |
| |
| <link rel="stylesheet" href="../../../_static/css/index.73d71520a4ca3b99cfee5594769eaaae.css"> |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/open-sans_all/1.44.1/index.css"> |
| <link rel="stylesheet" |
| href="../../../_static/vendor/lato_latin-ext/1.44.1/index.css"> |
| |
| |
| <link rel="stylesheet" href="../../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/js/index.3da636dd464baa7582d2.js"> |
| |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="en" /> |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"> |
| <div class="container-xl"> |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo" /> |
| |
| </a> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-menu" aria-controls="navbar-menu" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| <div id="navbar-menu" class="col-lg-9 collapse navbar-collapse"> |
| <ul id="navbar-main-elements" class="navbar-nav mr-auto"> |
| |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../getting_started/index.html">Getting Started</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../user_guide/index.html">User Guide</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../reference/index.html">API Reference</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../development/index.html">Development</a> |
| </li> |
| |
| <li class="nav-item "> |
| <a class="nav-link" href="../../../migration_guide/index.html">Migration Guide</a> |
| </li> |
| |
| |
| </ul> |
| |
| |
| |
| |
| <ul class="navbar-nav"> |
| |
| |
| </ul> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| <div class="col-12 col-md-3 bd-sidebar"><form class="bd-search d-flex align-items-center" action="../../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form> |
| <nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| |
| <div class="bd-toc-item active"> |
| |
| |
| <ul class="nav bd-sidenav"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| </ul> |
| |
| </nav> |
| </div> |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| |
| <nav id="bd-toc-nav"> |
| <ul class="nav section-nav flex-column"> |
| |
| </ul> |
| </nav> |
| |
| |
| |
| </div> |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <h1>Source code for pyspark.ml.recommendation</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="kn">import</span> <span class="nn">sys</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">since</span><span class="p">,</span> <span class="n">keyword_only</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.param.shared</span> <span class="kn">import</span> <span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasBlockSize</span><span class="p">,</span> <span class="n">HasMaxIter</span><span class="p">,</span> <span class="n">HasRegParam</span><span class="p">,</span> \ |
| <span class="n">HasCheckpointInterval</span><span class="p">,</span> <span class="n">HasSeed</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.wrapper</span> <span class="kn">import</span> <span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">JavaModel</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.common</span> <span class="kn">import</span> <span class="n">inherit_doc</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.param</span> <span class="kn">import</span> <span class="n">Params</span><span class="p">,</span> <span class="n">TypeConverters</span><span class="p">,</span> <span class="n">Param</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml.util</span> <span class="kn">import</span> <span class="n">JavaMLWritable</span><span class="p">,</span> <span class="n">JavaMLReadable</span> |
| |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'ALS'</span><span class="p">,</span> <span class="s1">'ALSModel'</span><span class="p">]</span> |
| |
| |
| <span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">_ALSModelParams</span><span class="p">(</span><span class="n">HasPredictionCol</span><span class="p">,</span> <span class="n">HasBlockSize</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Params for :py:class:`ALS` and :py:class:`ALSModel`.</span> |
| |
| <span class="sd"> .. versionadded:: 3.0.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">userCol</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"userCol"</span><span class="p">,</span> <span class="s2">"column name for user ids. Ids must be within "</span> <span class="o">+</span> |
| <span class="s2">"the integer value range."</span><span class="p">,</span> <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| <span class="n">itemCol</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"itemCol"</span><span class="p">,</span> <span class="s2">"column name for item ids. Ids must be within "</span> <span class="o">+</span> |
| <span class="s2">"the integer value range."</span><span class="p">,</span> <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| <span class="n">coldStartStrategy</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"coldStartStrategy"</span><span class="p">,</span> <span class="s2">"strategy for dealing with "</span> <span class="o">+</span> |
| <span class="s2">"unknown or new users/items at prediction time. This may be useful "</span> <span class="o">+</span> |
| <span class="s2">"in cross-validation or production scenarios, for handling "</span> <span class="o">+</span> |
| <span class="s2">"user/item ids the model has not seen in the training data. "</span> <span class="o">+</span> |
| <span class="s2">"Supported values: 'nan', 'drop'."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_ALSModelParams</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="o">*</span><span class="n">args</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">blockSize</span><span class="o">=</span><span class="mi">4096</span><span class="p">)</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="nf">getUserCol</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of userCol or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">userCol</span><span class="p">)</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="nf">getItemCol</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of itemCol or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">itemCol</span><span class="p">)</span> |
| |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.2.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getColdStartStrategy</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of coldStartStrategy or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">coldStartStrategy</span><span class="p">)</span> |
| |
| |
| <span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">_ALSParams</span><span class="p">(</span><span class="n">_ALSModelParams</span><span class="p">,</span> <span class="n">HasMaxIter</span><span class="p">,</span> <span class="n">HasRegParam</span><span class="p">,</span> <span class="n">HasCheckpointInterval</span><span class="p">,</span> <span class="n">HasSeed</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Params for :py:class:`ALS`.</span> |
| |
| <span class="sd"> .. versionadded:: 3.0.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">rank</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"rank"</span><span class="p">,</span> <span class="s2">"rank of the factorization"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toInt</span><span class="p">)</span> |
| <span class="n">numUserBlocks</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"numUserBlocks"</span><span class="p">,</span> <span class="s2">"number of user blocks"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toInt</span><span class="p">)</span> |
| <span class="n">numItemBlocks</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"numItemBlocks"</span><span class="p">,</span> <span class="s2">"number of item blocks"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toInt</span><span class="p">)</span> |
| <span class="n">implicitPrefs</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"implicitPrefs"</span><span class="p">,</span> <span class="s2">"whether to use implicit preference"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toBoolean</span><span class="p">)</span> |
| <span class="n">alpha</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"alpha"</span><span class="p">,</span> <span class="s2">"alpha for implicit preference"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toFloat</span><span class="p">)</span> |
| |
| <span class="n">ratingCol</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"ratingCol"</span><span class="p">,</span> <span class="s2">"column name for ratings"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| <span class="n">nonnegative</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"nonnegative"</span><span class="p">,</span> |
| <span class="s2">"whether to use nonnegative constraint for least squares"</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toBoolean</span><span class="p">)</span> |
| <span class="n">intermediateStorageLevel</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"intermediateStorageLevel"</span><span class="p">,</span> |
| <span class="s2">"StorageLevel for intermediate datasets. Cannot be 'NONE'."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| <span class="n">finalStorageLevel</span> <span class="o">=</span> <span class="n">Param</span><span class="p">(</span><span class="n">Params</span><span class="o">.</span><span class="n">_dummy</span><span class="p">(),</span> <span class="s2">"finalStorageLevel"</span><span class="p">,</span> |
| <span class="s2">"StorageLevel for ALS model factors."</span><span class="p">,</span> |
| <span class="n">typeConverter</span><span class="o">=</span><span class="n">TypeConverters</span><span class="o">.</span><span class="n">toString</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_ALSParams</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="o">*</span><span class="n">args</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_setDefault</span><span class="p">(</span><span class="n">rank</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">numUserBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">numItemBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> |
| <span class="n">implicitPrefs</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">userCol</span><span class="o">=</span><span class="s2">"user"</span><span class="p">,</span> <span class="n">itemCol</span><span class="o">=</span><span class="s2">"item"</span><span class="p">,</span> |
| <span class="n">ratingCol</span><span class="o">=</span><span class="s2">"rating"</span><span class="p">,</span> <span class="n">nonnegative</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> |
| <span class="n">intermediateStorageLevel</span><span class="o">=</span><span class="s2">"MEMORY_AND_DISK"</span><span class="p">,</span> |
| <span class="n">finalStorageLevel</span><span class="o">=</span><span class="s2">"MEMORY_AND_DISK"</span><span class="p">,</span> <span class="n">coldStartStrategy</span><span class="o">=</span><span class="s2">"nan"</span><span class="p">)</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="nf">getRank</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of rank or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">rank</span><span class="p">)</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="nf">getNumUserBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of numUserBlocks or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numUserBlocks</span><span class="p">)</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="nf">getNumItemBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of numItemBlocks or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numItemBlocks</span><span class="p">)</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="nf">getImplicitPrefs</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of implicitPrefs or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">implicitPrefs</span><span class="p">)</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="nf">getAlpha</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of alpha or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">alpha</span><span class="p">)</span> |
| |
| <span class="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="nf">getRatingCol</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of ratingCol or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">ratingCol</span><span class="p">)</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="nf">getNonnegative</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of nonnegative or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">nonnegative</span><span class="p">)</span> |
| |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getIntermediateStorageLevel</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of intermediateStorageLevel or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">intermediateStorageLevel</span><span class="p">)</span> |
| |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">getFinalStorageLevel</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gets the value of finalStorageLevel or its default value.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">getOrDefault</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">finalStorageLevel</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="ALS"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">ALS</span><span class="p">(</span><span class="n">JavaEstimator</span><span class="p">,</span> <span class="n">_ALSParams</span><span class="p">,</span> <span class="n">JavaMLWritable</span><span class="p">,</span> <span class="n">JavaMLReadable</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Alternating Least Squares (ALS) matrix factorization.</span> |
| |
| <span class="sd"> ALS attempts to estimate the ratings matrix `R` as the product of</span> |
| <span class="sd"> two lower-rank matrices, `X` and `Y`, i.e. `X * Yt = R`. Typically</span> |
| <span class="sd"> these approximations are called 'factor' matrices. The general</span> |
| <span class="sd"> approach is iterative. During each iteration, one of the factor</span> |
| <span class="sd"> matrices is held constant, while the other is solved for using least</span> |
| <span class="sd"> squares. The newly-solved factor matrix is then held constant while</span> |
| <span class="sd"> solving for the other factor matrix.</span> |
| |
| <span class="sd"> This is a blocked implementation of the ALS factorization algorithm</span> |
| <span class="sd"> that groups the two sets of factors (referred to as "users" and</span> |
| <span class="sd"> "products") into blocks and reduces communication by only sending</span> |
| <span class="sd"> one copy of each user vector to each product block on each</span> |
| <span class="sd"> iteration, and only for the product blocks that need that user's</span> |
| <span class="sd"> feature vector. This is achieved by pre-computing some information</span> |
| <span class="sd"> about the ratings matrix to determine the "out-links" of each user</span> |
| <span class="sd"> (which blocks of products it will contribute to) and "in-link"</span> |
| <span class="sd"> information for each product (which of the feature vectors it</span> |
| <span class="sd"> receives from each user block it will depend on). This allows us to</span> |
| <span class="sd"> send only an array of feature vectors between each user block and</span> |
| <span class="sd"> product block, and have the product block find the users' ratings</span> |
| <span class="sd"> and update the products based on these messages.</span> |
| |
| <span class="sd"> For implicit preference data, the algorithm used is based on</span> |
| <span class="sd"> `"Collaborative Filtering for Implicit Feedback Datasets",</span> |
| <span class="sd"> <https://doi.org/10.1109/ICDM.2008.22>`_, adapted for the blocked</span> |
| <span class="sd"> approach used here.</span> |
| |
| <span class="sd"> Essentially instead of finding the low-rank approximations to the</span> |
| <span class="sd"> rating matrix `R`, this finds the approximations for a preference</span> |
| <span class="sd"> matrix `P` where the elements of `P` are 1 if r > 0 and 0 if r <= 0.</span> |
| <span class="sd"> The ratings then act as 'confidence' values related to strength of</span> |
| <span class="sd"> indicated user preferences rather than explicit ratings given to</span> |
| <span class="sd"> items.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> The input rating dataframe to the ALS implementation should be deterministic.</span> |
| <span class="sd"> Nondeterministic data can cause failure during fitting ALS model.</span> |
| <span class="sd"> For example, an order-sensitive operation like sampling after a repartition makes</span> |
| <span class="sd"> dataframe output nondeterministic, like `df.repartition(2).sample(False, 0.5, 1618)`.</span> |
| <span class="sd"> Checkpointing sampled dataframe or adding a sort before sampling can help make the</span> |
| <span class="sd"> dataframe deterministic.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> df = spark.createDataFrame(</span> |
| <span class="sd"> ... [(0, 0, 4.0), (0, 1, 2.0), (1, 1, 3.0), (1, 2, 4.0), (2, 1, 1.0), (2, 2, 5.0)],</span> |
| <span class="sd"> ... ["user", "item", "rating"])</span> |
| <span class="sd"> >>> als = ALS(rank=10, seed=0)</span> |
| <span class="sd"> >>> als.setMaxIter(5)</span> |
| <span class="sd"> ALS...</span> |
| <span class="sd"> >>> als.getMaxIter()</span> |
| <span class="sd"> 5</span> |
| <span class="sd"> >>> als.setRegParam(0.1)</span> |
| <span class="sd"> ALS...</span> |
| <span class="sd"> >>> als.getRegParam()</span> |
| <span class="sd"> 0.1</span> |
| <span class="sd"> >>> als.clear(als.regParam)</span> |
| <span class="sd"> >>> model = als.fit(df)</span> |
| <span class="sd"> >>> model.getBlockSize()</span> |
| <span class="sd"> 4096</span> |
| <span class="sd"> >>> model.getUserCol()</span> |
| <span class="sd"> 'user'</span> |
| <span class="sd"> >>> model.setUserCol("user")</span> |
| <span class="sd"> ALSModel...</span> |
| <span class="sd"> >>> model.getItemCol()</span> |
| <span class="sd"> 'item'</span> |
| <span class="sd"> >>> model.setPredictionCol("newPrediction")</span> |
| <span class="sd"> ALS...</span> |
| <span class="sd"> >>> model.rank</span> |
| <span class="sd"> 10</span> |
| <span class="sd"> >>> model.userFactors.orderBy("id").collect()</span> |
| <span class="sd"> [Row(id=0, features=[...]), Row(id=1, ...), Row(id=2, ...)]</span> |
| <span class="sd"> >>> test = spark.createDataFrame([(0, 2), (1, 0), (2, 0)], ["user", "item"])</span> |
| <span class="sd"> >>> predictions = sorted(model.transform(test).collect(), key=lambda r: r[0])</span> |
| <span class="sd"> >>> predictions[0]</span> |
| <span class="sd"> Row(user=0, item=2, newPrediction=0.69291...)</span> |
| <span class="sd"> >>> predictions[1]</span> |
| <span class="sd"> Row(user=1, item=0, newPrediction=3.47356...)</span> |
| <span class="sd"> >>> predictions[2]</span> |
| <span class="sd"> Row(user=2, item=0, newPrediction=-0.899198...)</span> |
| <span class="sd"> >>> user_recs = model.recommendForAllUsers(3)</span> |
| <span class="sd"> >>> user_recs.where(user_recs.user == 0)\</span> |
| <span class="sd"> .select("recommendations.item", "recommendations.rating").collect()</span> |
| <span class="sd"> [Row(item=[0, 1, 2], rating=[3.910..., 1.997..., 0.692...])]</span> |
| <span class="sd"> >>> item_recs = model.recommendForAllItems(3)</span> |
| <span class="sd"> >>> item_recs.where(item_recs.item == 2)\</span> |
| <span class="sd"> .select("recommendations.user", "recommendations.rating").collect()</span> |
| <span class="sd"> [Row(user=[2, 1, 0], rating=[4.892..., 3.991..., 0.692...])]</span> |
| <span class="sd"> >>> user_subset = df.where(df.user == 2)</span> |
| <span class="sd"> >>> user_subset_recs = model.recommendForUserSubset(user_subset, 3)</span> |
| <span class="sd"> >>> user_subset_recs.select("recommendations.item", "recommendations.rating").first()</span> |
| <span class="sd"> Row(item=[2, 1, 0], rating=[4.892..., 1.076..., -0.899...])</span> |
| <span class="sd"> >>> item_subset = df.where(df.item == 0)</span> |
| <span class="sd"> >>> item_subset_recs = model.recommendForItemSubset(item_subset, 3)</span> |
| <span class="sd"> >>> item_subset_recs.select("recommendations.user", "recommendations.rating").first()</span> |
| <span class="sd"> Row(user=[0, 1, 2], rating=[3.910..., 3.473..., -0.899...])</span> |
| <span class="sd"> >>> als_path = temp_path + "/als"</span> |
| <span class="sd"> >>> als.save(als_path)</span> |
| <span class="sd"> >>> als2 = ALS.load(als_path)</span> |
| <span class="sd"> >>> als.getMaxIter()</span> |
| <span class="sd"> 5</span> |
| <span class="sd"> >>> model_path = temp_path + "/als_model"</span> |
| <span class="sd"> >>> model.save(model_path)</span> |
| <span class="sd"> >>> model2 = ALSModel.load(model_path)</span> |
| <span class="sd"> >>> model.rank == model2.rank</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> sorted(model.userFactors.collect()) == sorted(model2.userFactors.collect())</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> sorted(model.itemFactors.collect()) == sorted(model2.itemFactors.collect())</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> model.transform(test).take(1) == model2.transform(test).take(1)</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@keyword_only</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">rank</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">numUserBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> |
| <span class="n">numItemBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">implicitPrefs</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">userCol</span><span class="o">=</span><span class="s2">"user"</span><span class="p">,</span> <span class="n">itemCol</span><span class="o">=</span><span class="s2">"item"</span><span class="p">,</span> |
| <span class="n">seed</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">ratingCol</span><span class="o">=</span><span class="s2">"rating"</span><span class="p">,</span> <span class="n">nonnegative</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> |
| <span class="n">intermediateStorageLevel</span><span class="o">=</span><span class="s2">"MEMORY_AND_DISK"</span><span class="p">,</span> |
| <span class="n">finalStorageLevel</span><span class="o">=</span><span class="s2">"MEMORY_AND_DISK"</span><span class="p">,</span> <span class="n">coldStartStrategy</span><span class="o">=</span><span class="s2">"nan"</span><span class="p">,</span> <span class="n">blockSize</span><span class="o">=</span><span class="mi">4096</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> __init__(self, \\*, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10,</span> |
| <span class="sd"> numItemBlocks=10, implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", \</span> |
| <span class="sd"> seed=None, ratingCol="rating", nonnegative=False, checkpointInterval=10, \</span> |
| <span class="sd"> intermediateStorageLevel="MEMORY_AND_DISK", \</span> |
| <span class="sd"> finalStorageLevel="MEMORY_AND_DISK", coldStartStrategy="nan", blockSize=4096)</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">ALS</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="bp">self</span><span class="o">.</span><span class="n">_java_obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_new_java_obj</span><span class="p">(</span><span class="s2">"org.apache.spark.ml.recommendation.ALS"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">uid</span><span class="p">)</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">setParams</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ALS.setParams"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setParams">[docs]</a> <span class="nd">@keyword_only</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="nf">setParams</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">rank</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">maxIter</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">regParam</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">numUserBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> |
| <span class="n">numItemBlocks</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">implicitPrefs</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">userCol</span><span class="o">=</span><span class="s2">"user"</span><span class="p">,</span> <span class="n">itemCol</span><span class="o">=</span><span class="s2">"item"</span><span class="p">,</span> |
| <span class="n">seed</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">ratingCol</span><span class="o">=</span><span class="s2">"rating"</span><span class="p">,</span> <span class="n">nonnegative</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">checkpointInterval</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> |
| <span class="n">intermediateStorageLevel</span><span class="o">=</span><span class="s2">"MEMORY_AND_DISK"</span><span class="p">,</span> |
| <span class="n">finalStorageLevel</span><span class="o">=</span><span class="s2">"MEMORY_AND_DISK"</span><span class="p">,</span> <span class="n">coldStartStrategy</span><span class="o">=</span><span class="s2">"nan"</span><span class="p">,</span> <span class="n">blockSize</span><span class="o">=</span><span class="mi">4096</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> setParams(self, \\*, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, \</span> |
| <span class="sd"> numItemBlocks=10, implicitPrefs=False, alpha=1.0, userCol="user", itemCol="item", \</span> |
| <span class="sd"> seed=None, ratingCol="rating", nonnegative=False, checkpointInterval=10, \</span> |
| <span class="sd"> intermediateStorageLevel="MEMORY_AND_DISK", \</span> |
| <span class="sd"> finalStorageLevel="MEMORY_AND_DISK", coldStartStrategy="nan", blockSize=4096)</span> |
| <span class="sd"> Sets params for ALS.</span> |
| <span class="sd"> """</span> |
| <span class="n">kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_kwargs</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_create_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">java_model</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">ALSModel</span><span class="p">(</span><span class="n">java_model</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ALS.setRank"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setRank">[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="nf">setRank</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`rank`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">rank</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setNumUserBlocks"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setNumUserBlocks">[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="nf">setNumUserBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`numUserBlocks`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">numUserBlocks</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setNumItemBlocks"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setNumItemBlocks">[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="nf">setNumItemBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`numItemBlocks`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">numItemBlocks</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setNumBlocks"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setNumBlocks">[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="nf">setNumBlocks</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets both :py:attr:`numUserBlocks` and :py:attr:`numItemBlocks` to the specific value.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">numUserBlocks</span><span class="o">=</span><span class="n">value</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">numItemBlocks</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setImplicitPrefs"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setImplicitPrefs">[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="nf">setImplicitPrefs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`implicitPrefs`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">implicitPrefs</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setAlpha"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setAlpha">[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="nf">setAlpha</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`alpha`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">alpha</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setUserCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setUserCol">[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="nf">setUserCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`userCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">userCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setItemCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setItemCol">[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="nf">setItemCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`itemCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">itemCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setRatingCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setRatingCol">[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="nf">setRatingCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`ratingCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">ratingCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setNonnegative"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setNonnegative">[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="nf">setNonnegative</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`nonnegative`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">nonnegative</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setIntermediateStorageLevel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setIntermediateStorageLevel">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setIntermediateStorageLevel</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`intermediateStorageLevel`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">intermediateStorageLevel</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setFinalStorageLevel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setFinalStorageLevel">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setFinalStorageLevel</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`finalStorageLevel`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">finalStorageLevel</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setColdStartStrategy"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setColdStartStrategy">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.2.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setColdStartStrategy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`coldStartStrategy`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">coldStartStrategy</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setMaxIter"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setMaxIter">[docs]</a> <span class="k">def</span> <span class="nf">setMaxIter</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`maxIter`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">maxIter</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setRegParam"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setRegParam">[docs]</a> <span class="k">def</span> <span class="nf">setRegParam</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`regParam`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">regParam</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setPredictionCol">[docs]</a> <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setCheckpointInterval"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setCheckpointInterval">[docs]</a> <span class="k">def</span> <span class="nf">setCheckpointInterval</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`checkpointInterval`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">checkpointInterval</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setSeed"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setSeed">[docs]</a> <span class="k">def</span> <span class="nf">setSeed</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`seed`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">seed</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.setBlockSize"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALS.html#pyspark.ml.recommendation.ALS.setBlockSize">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setBlockSize</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`blockSize`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">blockSize</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ALSModel"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel">[docs]</a><span class="k">class</span> <span class="nc">ALSModel</span><span class="p">(</span><span class="n">JavaModel</span><span class="p">,</span> <span class="n">_ALSModelParams</span><span class="p">,</span> <span class="n">JavaMLWritable</span><span class="p">,</span> <span class="n">JavaMLReadable</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Model fitted by ALS.</span> |
| |
| <span class="sd"> .. versionadded:: 1.4.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="ALSModel.setUserCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel.setUserCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setUserCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`userCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">userCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALSModel.setItemCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel.setItemCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setItemCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`itemCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">itemCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALSModel.setColdStartStrategy"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel.setColdStartStrategy">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setColdStartStrategy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`coldStartStrategy`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">coldStartStrategy</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALSModel.setPredictionCol"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel.setPredictionCol">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setPredictionCol</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`predictionCol`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">predictionCol</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALSModel.setBlockSize"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel.setBlockSize">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"3.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">setBlockSize</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Sets the value of :py:attr:`blockSize`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_set</span><span class="p">(</span><span class="n">blockSize</span><span class="o">=</span><span class="n">value</span><span class="p">)</span></div> |
| |
| <span class="nd">@property</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="nf">rank</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""rank of the matrix factorization model"""</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">"rank"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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="nf">userFactors</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> a DataFrame that stores user factors in two columns: `id` and</span> |
| <span class="sd"> `features`</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">"userFactors"</span><span class="p">)</span> |
| |
| <span class="nd">@property</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="nf">itemFactors</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> a DataFrame that stores item factors in two columns: `id` and</span> |
| <span class="sd"> `features`</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">"itemFactors"</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ALSModel.recommendForAllUsers"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel.recommendForAllUsers">[docs]</a> <span class="k">def</span> <span class="nf">recommendForAllUsers</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numItems</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns top `numItems` items recommended for each user, for all users.</span> |
| |
| <span class="sd"> .. versionadded:: 2.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> numItems : int</span> |
| <span class="sd"> max number of recommendations for each user</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> a DataFrame of (userCol, recommendations), where recommendations are</span> |
| <span class="sd"> stored as an array of (itemCol, rating) Rows.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">"recommendForAllUsers"</span><span class="p">,</span> <span class="n">numItems</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALSModel.recommendForAllItems"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel.recommendForAllItems">[docs]</a> <span class="k">def</span> <span class="nf">recommendForAllItems</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numUsers</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns top `numUsers` users recommended for each item, for all items.</span> |
| |
| <span class="sd"> .. versionadded:: 2.2.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> numUsers : int</span> |
| <span class="sd"> max number of recommendations for each item</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> a DataFrame of (itemCol, recommendations), where recommendations are</span> |
| <span class="sd"> stored as an array of (userCol, rating) Rows.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">"recommendForAllItems"</span><span class="p">,</span> <span class="n">numUsers</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALSModel.recommendForUserSubset"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel.recommendForUserSubset">[docs]</a> <span class="k">def</span> <span class="nf">recommendForUserSubset</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">numItems</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns top `numItems` items recommended for each user id in the input data set. Note that</span> |
| <span class="sd"> if there are duplicate ids in the input dataset, only one set of recommendations per unique</span> |
| <span class="sd"> id will be returned.</span> |
| |
| <span class="sd"> .. versionadded:: 2.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> a DataFrame containing a column of user ids. The column name must match `userCol`.</span> |
| <span class="sd"> numItems : int</span> |
| <span class="sd"> max number of recommendations for each user</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> a DataFrame of (userCol, recommendations), where recommendations are</span> |
| <span class="sd"> stored as an array of (itemCol, rating) Rows.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">"recommendForUserSubset"</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">numItems</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALSModel.recommendForItemSubset"><a class="viewcode-back" href="../../../reference/api/pyspark.ml.recommendation.ALSModel.html#pyspark.ml.recommendation.ALSModel.recommendForItemSubset">[docs]</a> <span class="k">def</span> <span class="nf">recommendForItemSubset</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">numUsers</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns top `numUsers` users recommended for each item id in the input data set. Note that</span> |
| <span class="sd"> if there are duplicate ids in the input dataset, only one set of recommendations per unique</span> |
| <span class="sd"> id will be returned.</span> |
| |
| <span class="sd"> .. versionadded:: 2.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> dataset : :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> a DataFrame containing a column of item ids. The column name must match `itemCol`.</span> |
| <span class="sd"> numUsers : int</span> |
| <span class="sd"> max number of recommendations for each item</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.sql.DataFrame`</span> |
| <span class="sd"> a DataFrame of (itemCol, recommendations), where recommendations are</span> |
| <span class="sd"> stored as an array of (userCol, rating) Rows.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_call_java</span><span class="p">(</span><span class="s2">"recommendForItemSubset"</span><span class="p">,</span> <span class="n">dataset</span><span class="p">,</span> <span class="n">numUsers</span><span class="p">)</span></div></div> |
| |
| |
| <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="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">import</span> <span class="nn">pyspark.ml.recommendation</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span> |
| <span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">ml</span><span class="o">.</span><span class="n">recommendation</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="c1"># The small batch size here ensures that we see multiple batches,</span> |
| <span class="c1"># even in these small test examples:</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">"ml.recommendation tests"</span><span class="p">)</span>\ |
| <span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="n">sc</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s1">'sc'</span><span class="p">]</span> <span class="o">=</span> <span class="n">sc</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s1">'spark'</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span> |
| <span class="kn">import</span> <span class="nn">tempfile</span> |
| <span class="n">temp_path</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">mkdtemp</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s1">'temp_path'</span><span class="p">]</span> <span class="o">=</span> <span class="n">temp_path</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">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">finally</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">shutil</span> <span class="kn">import</span> <span class="n">rmtree</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">rmtree</span><span class="p">(</span><span class="n">temp_path</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">OSError</span><span class="p">:</span> |
| <span class="k">pass</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> |
| </pre></div> |
| |
| </div> |
| |
| |
| <div class='prev-next-bottom'> |
| |
| |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| |
| <script src="../../../_static/js/index.3da636dd464baa7582d2.js"></script> |
| |
| |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| <p> |
| © Copyright .<br/> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br/> |
| </p> |
| </div> |
| </footer> |
| </body> |
| </html> |
