| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.mllib.recommendation — PySpark 3.5.3 documentation</title> |
| |
| <link href="../../../_static/styles/theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| <link href="../../../_static/styles/pydata-sphinx-theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| |
| |
| <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/styles/pydata-sphinx-theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"> |
| |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/clipboard.min.js"></script> |
| <script src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/mllib/recommendation.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"> |
| |
| |
| <!-- Google Analytics --> |
| |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <div class="container-fluid" id="banner"></div> |
| |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"><div class="container-xl"> |
| |
| <div id="navbar-start"> |
| |
| |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo"> |
| </a> |
| |
| |
| |
| </div> |
| |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-collapsible" aria-controls="navbar-collapsible" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| |
| <div id="navbar-collapsible" class="col-lg-9 collapse navbar-collapse"> |
| <div id="navbar-center" class="mr-auto"> |
| |
| <div class="navbar-center-item"> |
| <ul id="navbar-main-elements" class="navbar-nav"> |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| |
| </ul> |
| </div> |
| |
| </div> |
| |
| <div id="navbar-end"> |
| |
| <div class="navbar-end-item"> |
| <!-- |
| Licensed to the Apache Software Foundation (ASF) under one or more |
| contributor license agreements. See the NOTICE file distributed with |
| this work for additional information regarding copyright ownership. |
| The ASF licenses this file to You under the Apache License, Version 2.0 |
| (the "License"); you may not use this file except in compliance with |
| the License. You may obtain a copy of the License at |
| |
| http://www.apache.org/licenses/LICENSE-2.0 |
| |
| Unless required by applicable law or agreed to in writing, software |
| distributed under the License is distributed on an "AS IS" BASIS, |
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| See the License for the specific language governing permissions and |
| limitations under the License. |
| --> |
| |
| <div id="version-button" class="dropdown"> |
| <button type="button" class="btn btn-secondary btn-sm navbar-btn dropdown-toggle" id="version_switcher_button" data-toggle="dropdown"> |
| 3.5.3 |
| <span class="caret"></span> |
| </button> |
| <div id="version_switcher" class="dropdown-menu list-group-flush py-0" aria-labelledby="version_switcher_button"> |
| <!-- dropdown will be populated by javascript on page load --> |
| </div> |
| </div> |
| |
| <script type="text/javascript"> |
| // Function to construct the target URL from the JSON components |
| function buildURL(entry) { |
| var template = "https://spark.apache.org/docs/{version}/api/python/index.html"; // supplied by jinja |
| template = template.replace("{version}", entry.version); |
| return template; |
| } |
| |
| // Function to check if corresponding page path exists in other version of docs |
| // and, if so, go there instead of the homepage of the other docs version |
| function checkPageExistsAndRedirect(event) { |
| const currentFilePath = "_modules/pyspark/mllib/recommendation.html", |
| otherDocsHomepage = event.target.getAttribute("href"); |
| let tryUrl = `${otherDocsHomepage}${currentFilePath}`; |
| $.ajax({ |
| type: 'HEAD', |
| url: tryUrl, |
| // if the page exists, go there |
| success: function() { |
| location.href = tryUrl; |
| } |
| }).fail(function() { |
| location.href = otherDocsHomepage; |
| }); |
| return false; |
| } |
| |
| // Function to populate the version switcher |
| (function () { |
| // get JSON config |
| $.getJSON("https://spark.apache.org/static/versions.json", function(data, textStatus, jqXHR) { |
| // create the nodes first (before AJAX calls) to ensure the order is |
| // correct (for now, links will go to doc version homepage) |
| $.each(data, function(index, entry) { |
| // if no custom name specified (e.g., "latest"), use version string |
| if (!("name" in entry)) { |
| entry.name = entry.version; |
| } |
| // construct the appropriate URL, and add it to the dropdown |
| entry.url = buildURL(entry); |
| const node = document.createElement("a"); |
| node.setAttribute("class", "list-group-item list-group-item-action py-1"); |
| node.setAttribute("href", `${entry.url}`); |
| node.textContent = `${entry.name}`; |
| node.onclick = checkPageExistsAndRedirect; |
| $("#version_switcher").append(node); |
| }); |
| }); |
| })(); |
| </script> |
| </div> |
| |
| </div> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| |
| <!-- Only show if we have sidebars configured, else just a small margin --> |
| <div class="col-12 col-md-3 bd-sidebar"> |
| <div class="sidebar-start-items"><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"> |
| |
| </div> |
| </nav> |
| </div> |
| <div class="sidebar-end-items"> |
| </div> |
| </div> |
| |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| </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.mllib.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">array</span> |
| <span class="kn">import</span> <span class="nn">sys</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">NamedTuple</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">Union</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">SparkContext</span><span class="p">,</span> <span class="n">since</span> |
| <span class="kn">from</span> <span class="nn">pyspark.rdd</span> <span class="kn">import</span> <span class="n">RDD</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.common</span> <span class="kn">import</span> <span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">callMLlibFunc</span><span class="p">,</span> <span class="n">inherit_doc</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.util</span> <span class="kn">import</span> <span class="n">JavaLoader</span><span class="p">,</span> <span class="n">JavaSaveable</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"MatrixFactorizationModel"</span><span class="p">,</span> <span class="s2">"ALS"</span><span class="p">,</span> <span class="s2">"Rating"</span><span class="p">]</span> |
| |
| |
| <div class="viewcode-block" id="Rating"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.Rating.html#pyspark.mllib.recommendation.Rating">[docs]</a><span class="k">class</span> <span class="nc">Rating</span><span class="p">(</span><span class="n">NamedTuple</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Represents a (user, product, rating) tuple.</span> |
| |
| <span class="sd"> .. versionadded:: 1.2.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> r = Rating(1, 2, 5.0)</span> |
| <span class="sd"> >>> (r.user, r.product, r.rating)</span> |
| <span class="sd"> (1, 2, 5.0)</span> |
| <span class="sd"> >>> (r[0], r[1], r[2])</span> |
| <span class="sd"> (1, 2, 5.0)</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">user</span><span class="p">:</span> <span class="nb">int</span> |
| <span class="n">product</span><span class="p">:</span> <span class="nb">int</span> |
| <span class="n">rating</span><span class="p">:</span> <span class="nb">float</span> |
| |
| <span class="k">def</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">"Rating"</span><span class="p">],</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]:</span> |
| <span class="k">return</span> <span class="n">Rating</span><span class="p">,</span> <span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">user</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">product</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">rating</span><span class="p">))</span></div> |
| |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel">[docs]</a><span class="nd">@inherit_doc</span> |
| <span class="k">class</span> <span class="nc">MatrixFactorizationModel</span><span class="p">(</span> |
| <span class="n">JavaModelWrapper</span><span class="p">,</span> <span class="n">JavaSaveable</span><span class="p">,</span> <span class="n">JavaLoader</span><span class="p">[</span><span class="s2">"MatrixFactorizationModel"</span><span class="p">]</span> |
| <span class="p">):</span> |
| |
| <span class="w"> </span><span class="sd">"""A matrix factorisation model trained by regularized alternating</span> |
| <span class="sd"> least-squares.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> r1 = (1, 1, 1.0)</span> |
| <span class="sd"> >>> r2 = (1, 2, 2.0)</span> |
| <span class="sd"> >>> r3 = (2, 1, 2.0)</span> |
| <span class="sd"> >>> ratings = sc.parallelize([r1, r2, r3])</span> |
| <span class="sd"> >>> model = ALS.trainImplicit(ratings, 1, seed=10)</span> |
| <span class="sd"> >>> model.predict(2, 2)</span> |
| <span class="sd"> 0.4...</span> |
| |
| <span class="sd"> >>> testset = sc.parallelize([(1, 2), (1, 1)])</span> |
| <span class="sd"> >>> model = ALS.train(ratings, 2, seed=0)</span> |
| <span class="sd"> >>> model.predictAll(testset).collect()</span> |
| <span class="sd"> [Rating(user=1, product=1, rating=1.0...), Rating(user=1, product=2, rating=1.9...)]</span> |
| |
| <span class="sd"> >>> model = ALS.train(ratings, 4, seed=10)</span> |
| <span class="sd"> >>> model.userFeatures().collect()</span> |
| <span class="sd"> [(1, array('d', [...])), (2, array('d', [...]))]</span> |
| |
| <span class="sd"> >>> model.recommendUsers(1, 2)</span> |
| <span class="sd"> [Rating(user=2, product=1, rating=1.9...), Rating(user=1, product=1, rating=1.0...)]</span> |
| <span class="sd"> >>> model.recommendProducts(1, 2)</span> |
| <span class="sd"> [Rating(user=1, product=2, rating=1.9...), Rating(user=1, product=1, rating=1.0...)]</span> |
| <span class="sd"> >>> model.rank</span> |
| <span class="sd"> 4</span> |
| |
| <span class="sd"> >>> first_user = model.userFeatures().take(1)[0]</span> |
| <span class="sd"> >>> latents = first_user[1]</span> |
| <span class="sd"> >>> len(latents)</span> |
| <span class="sd"> 4</span> |
| |
| <span class="sd"> >>> model.productFeatures().collect()</span> |
| <span class="sd"> [(1, array('d', [...])), (2, array('d', [...]))]</span> |
| |
| <span class="sd"> >>> first_product = model.productFeatures().take(1)[0]</span> |
| <span class="sd"> >>> latents = first_product[1]</span> |
| <span class="sd"> >>> len(latents)</span> |
| <span class="sd"> 4</span> |
| |
| <span class="sd"> >>> products_for_users = model.recommendProductsForUsers(1).collect()</span> |
| <span class="sd"> >>> len(products_for_users)</span> |
| <span class="sd"> 2</span> |
| <span class="sd"> >>> products_for_users[0]</span> |
| <span class="sd"> (1, (Rating(user=1, product=2, rating=...),))</span> |
| |
| <span class="sd"> >>> users_for_products = model.recommendUsersForProducts(1).collect()</span> |
| <span class="sd"> >>> len(users_for_products)</span> |
| <span class="sd"> 2</span> |
| <span class="sd"> >>> users_for_products[0]</span> |
| <span class="sd"> (1, (Rating(user=2, product=1, rating=...),))</span> |
| |
| <span class="sd"> >>> model = ALS.train(ratings, 1, nonnegative=True, seed=123456789)</span> |
| <span class="sd"> >>> model.predict(2, 2)</span> |
| <span class="sd"> 3.73...</span> |
| |
| <span class="sd"> >>> df = sqlContext.createDataFrame([Rating(1, 1, 1.0), Rating(1, 2, 2.0), Rating(2, 1, 2.0)])</span> |
| <span class="sd"> >>> model = ALS.train(df, 1, nonnegative=True, seed=123456789)</span> |
| <span class="sd"> >>> model.predict(2, 2)</span> |
| <span class="sd"> 3.73...</span> |
| |
| <span class="sd"> >>> model = ALS.trainImplicit(ratings, 1, nonnegative=True, seed=123456789)</span> |
| <span class="sd"> >>> model.predict(2, 2)</span> |
| <span class="sd"> 0.4...</span> |
| |
| <span class="sd"> >>> import os, tempfile</span> |
| <span class="sd"> >>> path = tempfile.mkdtemp()</span> |
| <span class="sd"> >>> model.save(sc, path)</span> |
| <span class="sd"> >>> sameModel = MatrixFactorizationModel.load(sc, path)</span> |
| <span class="sd"> >>> sameModel.predict(2, 2)</span> |
| <span class="sd"> 0.4...</span> |
| <span class="sd"> >>> sameModel.predictAll(testset).collect()</span> |
| <span class="sd"> [Rating(...</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> |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel.predict"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel.predict">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"0.9.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">user</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">product</span><span class="p">:</span> <span class="nb">int</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">"""</span> |
| <span class="sd"> Predicts rating for the given user and product.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_java_model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">user</span><span class="p">),</span> <span class="nb">int</span><span class="p">(</span><span class="n">product</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel.predictAll"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel.predictAll">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"0.9.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">predictAll</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">user_product</span><span class="p">:</span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">]])</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">Rating</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns a list of predicted ratings for input user and product</span> |
| <span class="sd"> pairs.</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">user_product</span><span class="p">,</span> <span class="n">RDD</span><span class="p">),</span> <span class="s2">"user_product should be RDD of (user, product)"</span> |
| <span class="n">first</span> <span class="o">=</span> <span class="n">user_product</span><span class="o">.</span><span class="n">first</span><span class="p">()</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">first</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">,</span> <span class="s2">"user_product should be RDD of (user, product)"</span> |
| <span class="n">user_product</span> <span class="o">=</span> <span class="n">user_product</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">u_p</span><span class="p">:</span> <span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">u_p</span><span class="p">[</span><span class="mi">0</span><span class="p">]),</span> <span class="nb">int</span><span class="p">(</span><span class="n">u_p</span><span class="p">[</span><span class="mi">1</span><span class="p">])))</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"predict"</span><span class="p">,</span> <span class="n">user_product</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel.userFeatures"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel.userFeatures">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.2.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">userFeatures</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">array</span><span class="o">.</span><span class="n">array</span><span class="p">]]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns a paired RDD, where the first element is the user and the</span> |
| <span class="sd"> second is an array of features corresponding to that user.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"getUserFeatures"</span><span class="p">)</span><span class="o">.</span><span class="n">mapValues</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">array</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="s2">"d"</span><span class="p">,</span> <span class="n">v</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel.productFeatures"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel.productFeatures">[docs]</a> <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.2.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">productFeatures</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">array</span><span class="o">.</span><span class="n">array</span><span class="p">]]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns a paired RDD, where the first element is the product and the</span> |
| <span class="sd"> second is an array of features corresponding to that product.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"getProductFeatures"</span><span class="p">)</span><span class="o">.</span><span class="n">mapValues</span><span class="p">(</span><span class="k">lambda</span> <span class="n">v</span><span class="p">:</span> <span class="n">array</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="s2">"d"</span><span class="p">,</span> <span class="n">v</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel.recommendUsers"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel.recommendUsers">[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">recommendUsers</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">product</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">num</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="n">Rating</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Recommends the top "num" number of users for a given product and</span> |
| <span class="sd"> returns a list of Rating objects sorted by the predicted rating in</span> |
| <span class="sd"> descending order.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"recommendUsers"</span><span class="p">,</span> <span class="n">product</span><span class="p">,</span> <span class="n">num</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel.recommendProducts"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel.recommendProducts">[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">recommendProducts</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">user</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">num</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="n">Rating</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Recommends the top "num" number of products for a given user and</span> |
| <span class="sd"> returns a list of Rating objects sorted by the predicted rating in</span> |
| <span class="sd"> descending order.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"recommendProducts"</span><span class="p">,</span> <span class="n">user</span><span class="p">,</span> <span class="n">num</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel.recommendProductsForUsers"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel.recommendProductsForUsers">[docs]</a> <span class="k">def</span> <span class="nf">recommendProductsForUsers</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">num</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Rating</span><span class="p">,</span> <span class="o">...</span><span class="p">]]]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Recommends the top "num" number of products for all users. The</span> |
| <span class="sd"> number of recommendations returned per user may be less than "num".</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"wrappedRecommendProductsForUsers"</span><span class="p">,</span> <span class="n">num</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel.recommendUsersForProducts"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel.recommendUsersForProducts">[docs]</a> <span class="k">def</span> <span class="nf">recommendUsersForProducts</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">num</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Rating</span><span class="p">,</span> <span class="o">...</span><span class="p">]]]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Recommends the top "num" number of users for all products. The</span> |
| <span class="sd"> number of recommendations returned per product may be less than</span> |
| <span class="sd"> "num".</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"wrappedRecommendUsersForProducts"</span><span class="p">,</span> <span class="n">num</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="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Rank for the features in this model"""</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">call</span><span class="p">(</span><span class="s2">"rank"</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="MatrixFactorizationModel.load"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.MatrixFactorizationModel.html#pyspark.mllib.recommendation.MatrixFactorizationModel.load">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"1.3.1"</span><span class="p">)</span> |
| <span class="k">def</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">"MatrixFactorizationModel"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Load a model from the given path"""</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_load_java</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="n">path</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">wrapper</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">api</span><span class="o">.</span><span class="n">python</span><span class="o">.</span><span class="n">MatrixFactorizationModelWrapper</span><span class="p">(</span><span class="n">model</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">MatrixFactorizationModel</span><span class="p">(</span><span class="n">wrapper</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ALS"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.ALS.html#pyspark.mllib.recommendation.ALS">[docs]</a><span class="k">class</span> <span class="nc">ALS</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Alternating Least Squares matrix factorization</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">_prepare</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">ratings</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="n">Rating</span><span class="p">]:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">ratings</span><span class="p">,</span> <span class="n">RDD</span><span class="p">):</span> |
| <span class="k">pass</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">ratings</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span> |
| <span class="n">ratings</span> <span class="o">=</span> <span class="n">ratings</span><span class="o">.</span><span class="n">rdd</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s2">"Ratings should be represented by either an RDD or a DataFrame, "</span> |
| <span class="s2">"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">ratings</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="n">first</span> <span class="o">=</span> <span class="n">ratings</span><span class="o">.</span><span class="n">first</span><span class="p">()</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">first</span><span class="p">,</span> <span class="n">Rating</span><span class="p">):</span> |
| <span class="k">pass</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">first</span><span class="p">,</span> <span class="p">(</span><span class="nb">tuple</span><span class="p">,</span> <span class="nb">list</span><span class="p">)):</span> |
| <span class="n">ratings</span> <span class="o">=</span> <span class="n">ratings</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="n">Rating</span><span class="p">(</span><span class="o">*</span><span class="n">x</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Expect a Rating or a tuple/list, 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">return</span> <span class="n">ratings</span> |
| |
| <div class="viewcode-block" id="ALS.train"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.ALS.html#pyspark.mllib.recommendation.ALS.train">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">train</span><span class="p">(</span> |
| <span class="bp">cls</span><span class="p">,</span> |
| <span class="n">ratings</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">RDD</span><span class="p">[</span><span class="n">Rating</span><span class="p">],</span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]],</span> |
| <span class="n">rank</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">int</span> <span class="o">=</span> <span class="mi">5</span><span class="p">,</span> |
| <span class="n">lambda_</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">blocks</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> |
| <span class="n">nonnegative</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">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">MatrixFactorizationModel</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train a matrix factorization model given an RDD of ratings by users</span> |
| <span class="sd"> for a subset of products. The ratings matrix is approximated as the</span> |
| <span class="sd"> product of two lower-rank matrices of a given rank (number of</span> |
| <span class="sd"> features). To solve for these features, ALS is run iteratively with</span> |
| <span class="sd"> a configurable level of parallelism.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> ratings : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of `Rating` or (userID, productID, rating) tuple.</span> |
| <span class="sd"> rank : int</span> |
| <span class="sd"> Number of features to use (also referred to as the number of latent factors).</span> |
| <span class="sd"> iterations : int, optional</span> |
| <span class="sd"> Number of iterations of ALS.</span> |
| <span class="sd"> (default: 5)</span> |
| <span class="sd"> lambda\\_ : float, optional</span> |
| <span class="sd"> Regularization parameter.</span> |
| <span class="sd"> (default: 0.01)</span> |
| <span class="sd"> blocks : int, optional</span> |
| <span class="sd"> Number of blocks used to parallelize the computation. A value</span> |
| <span class="sd"> of -1 will use an auto-configured number of blocks.</span> |
| <span class="sd"> (default: -1)</span> |
| <span class="sd"> nonnegative : bool, optional</span> |
| <span class="sd"> A value of True will solve least-squares with nonnegativity</span> |
| <span class="sd"> constraints.</span> |
| <span class="sd"> (default: False)</span> |
| <span class="sd"> seed : bool, optional</span> |
| <span class="sd"> Random seed for initial matrix factorization model. A value</span> |
| <span class="sd"> of None will use system time as the seed.</span> |
| <span class="sd"> (default: None)</span> |
| <span class="sd"> """</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainALSModel"</span><span class="p">,</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">_prepare</span><span class="p">(</span><span class="n">ratings</span><span class="p">),</span> |
| <span class="n">rank</span><span class="p">,</span> |
| <span class="n">iterations</span><span class="p">,</span> |
| <span class="n">lambda_</span><span class="p">,</span> |
| <span class="n">blocks</span><span class="p">,</span> |
| <span class="n">nonnegative</span><span class="p">,</span> |
| <span class="n">seed</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="n">MatrixFactorizationModel</span><span class="p">(</span><span class="n">model</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ALS.trainImplicit"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.recommendation.ALS.html#pyspark.mllib.recommendation.ALS.trainImplicit">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">trainImplicit</span><span class="p">(</span> |
| <span class="bp">cls</span><span class="p">,</span> |
| <span class="n">ratings</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">RDD</span><span class="p">[</span><span class="n">Rating</span><span class="p">],</span> <span class="n">RDD</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]],</span> |
| <span class="n">rank</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">int</span> <span class="o">=</span> <span class="mi">5</span><span class="p">,</span> |
| <span class="n">lambda_</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">blocks</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> |
| <span class="n">alpha</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">nonnegative</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">seed</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">MatrixFactorizationModel</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Train a matrix factorization model given an RDD of 'implicit</span> |
| <span class="sd"> preferences' of users for a subset of products. The ratings matrix</span> |
| <span class="sd"> is approximated as the product of two lower-rank matrices of a</span> |
| <span class="sd"> given rank (number of features). To solve for these features, ALS</span> |
| <span class="sd"> is run iteratively with a configurable level of parallelism.</span> |
| |
| <span class="sd"> .. versionadded:: 0.9.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> ratings : :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of `Rating` or (userID, productID, rating) tuple.</span> |
| <span class="sd"> rank : int</span> |
| <span class="sd"> Number of features to use (also referred to as the number of latent factors).</span> |
| <span class="sd"> iterations : int, optional</span> |
| <span class="sd"> Number of iterations of ALS.</span> |
| <span class="sd"> (default: 5)</span> |
| <span class="sd"> lambda\\_ : float, optional</span> |
| <span class="sd"> Regularization parameter.</span> |
| <span class="sd"> (default: 0.01)</span> |
| <span class="sd"> blocks : int, optional</span> |
| <span class="sd"> Number of blocks used to parallelize the computation. A value</span> |
| <span class="sd"> of -1 will use an auto-configured number of blocks.</span> |
| <span class="sd"> (default: -1)</span> |
| <span class="sd"> alpha : float, optional</span> |
| <span class="sd"> A constant used in computing confidence.</span> |
| <span class="sd"> (default: 0.01)</span> |
| <span class="sd"> nonnegative : bool, optional</span> |
| <span class="sd"> A value of True will solve least-squares with nonnegativity</span> |
| <span class="sd"> constraints.</span> |
| <span class="sd"> (default: False)</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed for initial matrix factorization model. A value</span> |
| <span class="sd"> of None will use system time as the seed.</span> |
| <span class="sd"> (default: None)</span> |
| <span class="sd"> """</span> |
| <span class="n">model</span> <span class="o">=</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"trainImplicitALSModel"</span><span class="p">,</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">_prepare</span><span class="p">(</span><span class="n">ratings</span><span class="p">),</span> |
| <span class="n">rank</span><span class="p">,</span> |
| <span class="n">iterations</span><span class="p">,</span> |
| <span class="n">lambda_</span><span class="p">,</span> |
| <span class="n">blocks</span><span class="p">,</span> |
| <span class="n">alpha</span><span class="p">,</span> |
| <span class="n">nonnegative</span><span class="p">,</span> |
| <span class="n">seed</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="n">MatrixFactorizationModel</span><span class="p">(</span><span class="n">model</span><span class="p">)</span></div></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_test</span><span class="p">()</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">import</span> <span class="nn">pyspark.mllib.recommendation</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SQLContext</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">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="n">sc</span> <span class="o">=</span> <span class="n">SparkContext</span><span class="p">(</span><span class="s2">"local[4]"</span><span class="p">,</span> <span class="s2">"PythonTest"</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">sc</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"sqlContext"</span><span class="p">]</span> <span class="o">=</span> <span class="n">SQLContext</span><span class="p">(</span><span class="n">sc</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">globs</span><span class="p">[</span><span class="s2">"sc"</span><span class="p">]</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
| <span class="n">_test</span><span class="p">()</span> |
| </pre></div> |
| |
| </div> |
| |
| |
| <!-- Previous / next buttons --> |
| <div class='prev-next-area'> |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| <script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"></script> |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| |
| <div class="footer-item"> |
| <p class="copyright"> |
| © Copyright .<br> |
| </p> |
| </div> |
| |
| <div class="footer-item"> |
| <p class="sphinx-version"> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br> |
| </p> |
| </div> |
| |
| </div> |
| </footer> |
| </body> |
| </html> |
