| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.mllib.random — PySpark 3.5.5 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/random.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"> |
| 3.5.5 |
| <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/random.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.random</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd">Python package for random data generation.</span> |
| <span class="sd">"""</span> |
| |
| <span class="kn">import</span><span class="w"> </span><span class="nn">sys</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">functools</span><span class="w"> </span><span class="kn">import</span> <span class="n">wraps</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Callable</span><span class="p">,</span> <span class="n">Optional</span> |
| |
| <span class="kn">import</span><span class="w"> </span><span class="nn">numpy</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">np</span> |
| |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib.common</span><span class="w"> </span><span class="kn">import</span> <span class="n">callMLlibFunc</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.context</span><span class="w"> </span><span class="kn">import</span> <span class="n">SparkContext</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.rdd</span><span class="w"> </span><span class="kn">import</span> <span class="n">RDD</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.mllib.linalg</span><span class="w"> </span><span class="kn">import</span> <span class="n">Vector</span> |
| |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s2">"RandomRDDs"</span><span class="p">,</span> |
| <span class="p">]</span> |
| |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">toArray</span><span class="p">(</span><span class="n">f</span><span class="p">:</span> <span class="n">Callable</span><span class="p">[</span><span class="o">...</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="n">Vector</span><span class="p">]])</span> <span class="o">-></span> <span class="n">Callable</span><span class="p">[</span><span class="o">...</span><span class="p">,</span> <span class="n">RDD</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">]]:</span> |
| <span class="nd">@wraps</span><span class="p">(</span><span class="n">f</span><span class="p">)</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">func</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="o">*</span><span class="n">a</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="o">**</span><span class="n">kw</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">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">]:</span> |
| <span class="n">rdd</span> <span class="o">=</span> <span class="n">f</span><span class="p">(</span><span class="n">sc</span><span class="p">,</span> <span class="o">*</span><span class="n">a</span><span class="p">,</span> <span class="o">**</span><span class="n">kw</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">rdd</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">vec</span><span class="p">:</span> <span class="n">vec</span><span class="o">.</span><span class="n">toArray</span><span class="p">())</span> |
| |
| <span class="k">return</span> <span class="n">func</span> |
| |
| |
| <div class="viewcode-block" id="RandomRDDs"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs">[docs]</a><span class="k">class</span><span class="w"> </span><span class="nc">RandomRDDs</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generator methods for creating RDDs comprised of i.i.d samples from</span> |
| <span class="sd"> some distribution.</span> |
| |
| <span class="sd"> .. versionadded:: 1.1.0</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="RandomRDDs.uniformRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.uniformRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">uniformRDD</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">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">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="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of i.i.d. samples from the</span> |
| <span class="sd"> uniform distribution U(0.0, 1.0).</span> |
| |
| <span class="sd"> To transform the distribution in the generated RDD from U(0.0, 1.0)</span> |
| <span class="sd"> to U(a, b), use</span> |
| <span class="sd"> ``RandomRDDs.uniformRDD(sc, n, p, seed).map(lambda v: a + (b - a) * v)``</span> |
| |
| <span class="sd"> .. versionadded:: 1.1.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> used to create the RDD.</span> |
| <span class="sd"> size : int</span> |
| <span class="sd"> Size of the RDD.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`).</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of float comprised of i.i.d. samples ~ `U(0.0, 1.0)`.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> x = RandomRDDs.uniformRDD(sc, 100).collect()</span> |
| <span class="sd"> >>> len(x)</span> |
| <span class="sd"> 100</span> |
| <span class="sd"> >>> max(x) <= 1.0 and min(x) >= 0.0</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> RandomRDDs.uniformRDD(sc, 100, 4).getNumPartitions()</span> |
| <span class="sd"> 4</span> |
| <span class="sd"> >>> parts = RandomRDDs.uniformRDD(sc, 100, seed=4).getNumPartitions()</span> |
| <span class="sd"> >>> parts == sc.defaultParallelism</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"uniformRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.normalRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.normalRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">normalRDD</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">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">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="o">-></span> <span class="n">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of i.i.d. samples from the standard normal</span> |
| <span class="sd"> distribution.</span> |
| |
| <span class="sd"> To transform the distribution in the generated RDD from standard normal</span> |
| <span class="sd"> to some other normal N(mean, sigma^2), use</span> |
| <span class="sd"> ``RandomRDDs.normal(sc, n, p, seed).map(lambda v: mean + sigma * v)``</span> |
| |
| <span class="sd"> .. versionadded:: 1.1.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> used to create the RDD.</span> |
| <span class="sd"> size : int</span> |
| <span class="sd"> Size of the RDD.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`).</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of float comprised of i.i.d. samples ~ N(0.0, 1.0).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> x = RandomRDDs.normalRDD(sc, 1000, seed=1)</span> |
| <span class="sd"> >>> stats = x.stats()</span> |
| <span class="sd"> >>> stats.count()</span> |
| <span class="sd"> 1000</span> |
| <span class="sd"> >>> abs(stats.mean() - 0.0) < 0.1</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> abs(stats.stdev() - 1.0) < 0.1</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"normalRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.logNormalRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.logNormalRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">logNormalRDD</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">mean</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">std</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of i.i.d. samples from the log normal</span> |
| <span class="sd"> distribution with the input mean and standard distribution.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> used to create the RDD.</span> |
| <span class="sd"> mean : float</span> |
| <span class="sd"> mean for the log Normal distribution</span> |
| <span class="sd"> std : float</span> |
| <span class="sd"> std for the log Normal distribution</span> |
| <span class="sd"> size : int</span> |
| <span class="sd"> Size of the RDD.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`).</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> RDD of float comprised of i.i.d. samples ~ log N(mean, std).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from math import sqrt, exp</span> |
| <span class="sd"> >>> mean = 0.0</span> |
| <span class="sd"> >>> std = 1.0</span> |
| <span class="sd"> >>> expMean = exp(mean + 0.5 * std * std)</span> |
| <span class="sd"> >>> expStd = sqrt((exp(std * std) - 1.0) * exp(2.0 * mean + std * std))</span> |
| <span class="sd"> >>> x = RandomRDDs.logNormalRDD(sc, mean, std, 1000, seed=2)</span> |
| <span class="sd"> >>> stats = x.stats()</span> |
| <span class="sd"> >>> stats.count()</span> |
| <span class="sd"> 1000</span> |
| <span class="sd"> >>> abs(stats.mean() - expMean) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> from math import sqrt</span> |
| <span class="sd"> >>> abs(stats.stdev() - expStd) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"logNormalRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">mean</span><span class="p">),</span> <span class="nb">float</span><span class="p">(</span><span class="n">std</span><span class="p">),</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span> |
| <span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.poissonRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.poissonRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">poissonRDD</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">mean</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of i.i.d. samples from the Poisson</span> |
| <span class="sd"> distribution with the input mean.</span> |
| |
| <span class="sd"> .. versionadded:: 1.1.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> SparkContext used to create the RDD.</span> |
| <span class="sd"> mean : float</span> |
| <span class="sd"> Mean, or lambda, for the Poisson distribution.</span> |
| <span class="sd"> size : int</span> |
| <span class="sd"> Size of the RDD.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`).</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of float comprised of i.i.d. samples ~ Pois(mean).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> mean = 100.0</span> |
| <span class="sd"> >>> x = RandomRDDs.poissonRDD(sc, mean, 1000, seed=2)</span> |
| <span class="sd"> >>> stats = x.stats()</span> |
| <span class="sd"> >>> stats.count()</span> |
| <span class="sd"> 1000</span> |
| <span class="sd"> >>> abs(stats.mean() - mean) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> from math import sqrt</span> |
| <span class="sd"> >>> abs(stats.stdev() - sqrt(mean)) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"poissonRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">mean</span><span class="p">),</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.exponentialRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.exponentialRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">exponentialRDD</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">mean</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of i.i.d. samples from the Exponential</span> |
| <span class="sd"> distribution with the input mean.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> SparkContext used to create the RDD.</span> |
| <span class="sd"> mean : float</span> |
| <span class="sd"> Mean, or 1 / lambda, for the Exponential distribution.</span> |
| <span class="sd"> size : int</span> |
| <span class="sd"> Size of the RDD.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`).</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of float comprised of i.i.d. samples ~ Exp(mean).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> mean = 2.0</span> |
| <span class="sd"> >>> x = RandomRDDs.exponentialRDD(sc, mean, 1000, seed=2)</span> |
| <span class="sd"> >>> stats = x.stats()</span> |
| <span class="sd"> >>> stats.count()</span> |
| <span class="sd"> 1000</span> |
| <span class="sd"> >>> abs(stats.mean() - mean) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> from math import sqrt</span> |
| <span class="sd"> >>> abs(stats.stdev() - sqrt(mean)) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"exponentialRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">mean</span><span class="p">),</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.gammaRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.gammaRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">gammaRDD</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">shape</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">scale</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="nb">float</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of i.i.d. samples from the Gamma</span> |
| <span class="sd"> distribution with the input shape and scale.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> SparkContext used to create the RDD.</span> |
| <span class="sd"> shape : float</span> |
| <span class="sd"> shape (> 0) parameter for the Gamma distribution</span> |
| <span class="sd"> scale : float</span> |
| <span class="sd"> scale (> 0) parameter for the Gamma distribution</span> |
| <span class="sd"> size : int</span> |
| <span class="sd"> Size of the RDD.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`).</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of float comprised of i.i.d. samples ~ Gamma(shape, scale).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> from math import sqrt</span> |
| <span class="sd"> >>> shape = 1.0</span> |
| <span class="sd"> >>> scale = 2.0</span> |
| <span class="sd"> >>> expMean = shape * scale</span> |
| <span class="sd"> >>> expStd = sqrt(shape * scale * scale)</span> |
| <span class="sd"> >>> x = RandomRDDs.gammaRDD(sc, shape, scale, 1000, seed=2)</span> |
| <span class="sd"> >>> stats = x.stats()</span> |
| <span class="sd"> >>> stats.count()</span> |
| <span class="sd"> 1000</span> |
| <span class="sd"> >>> abs(stats.mean() - expMean) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> abs(stats.stdev() - expStd) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"gammaRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">shape</span><span class="p">),</span> <span class="nb">float</span><span class="p">(</span><span class="n">scale</span><span class="p">),</span> <span class="n">size</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span> |
| <span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.uniformVectorRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.uniformVectorRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="nd">@toArray</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">uniformVectorRDD</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">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="n">Vector</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span> |
| <span class="sd"> from the uniform distribution U(0.0, 1.0).</span> |
| |
| <span class="sd"> .. versionadded:: 1.1.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> SparkContext used to create the RDD.</span> |
| <span class="sd"> numRows : int</span> |
| <span class="sd"> Number of Vectors in the RDD.</span> |
| <span class="sd"> numCols : int</span> |
| <span class="sd"> Number of elements in each Vector.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD.</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Seed for the RNG that generates the seed for the generator in each partition.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of Vector with vectors containing i.i.d samples ~ `U(0.0, 1.0)`.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> mat = np.matrix(RandomRDDs.uniformVectorRDD(sc, 10, 10).collect())</span> |
| <span class="sd"> >>> mat.shape</span> |
| <span class="sd"> (10, 10)</span> |
| <span class="sd"> >>> mat.max() <= 1.0 and mat.min() >= 0.0</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> RandomRDDs.uniformVectorRDD(sc, 10, 10, 4).getNumPartitions()</span> |
| <span class="sd"> 4</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"uniformVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.normalVectorRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.normalVectorRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="nd">@toArray</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">normalVectorRDD</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">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="n">Vector</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span> |
| <span class="sd"> from the standard normal distribution.</span> |
| |
| <span class="sd"> .. versionadded:: 1.1.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> SparkContext used to create the RDD.</span> |
| <span class="sd"> numRows : int</span> |
| <span class="sd"> Number of Vectors in the RDD.</span> |
| <span class="sd"> numCols : int</span> |
| <span class="sd"> Number of elements in each Vector.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`).</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of Vector with vectors containing i.i.d. samples ~ `N(0.0, 1.0)`.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> mat = np.matrix(RandomRDDs.normalVectorRDD(sc, 100, 100, seed=1).collect())</span> |
| <span class="sd"> >>> mat.shape</span> |
| <span class="sd"> (100, 100)</span> |
| <span class="sd"> >>> abs(mat.mean() - 0.0) < 0.1</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> abs(mat.std() - 1.0) < 0.1</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span><span class="s2">"normalVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.logNormalVectorRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.logNormalVectorRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="nd">@toArray</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">logNormalVectorRDD</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">mean</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">std</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="n">Vector</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span> |
| <span class="sd"> from the log normal distribution.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> SparkContext used to create the RDD.</span> |
| <span class="sd"> mean : float</span> |
| <span class="sd"> Mean of the log normal distribution</span> |
| <span class="sd"> std : float</span> |
| <span class="sd"> Standard Deviation of the log normal distribution</span> |
| <span class="sd"> numRows : int</span> |
| <span class="sd"> Number of Vectors in the RDD.</span> |
| <span class="sd"> numCols : int</span> |
| <span class="sd"> Number of elements in each Vector.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`).</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of Vector with vectors containing i.i.d. samples ~ log `N(mean, std)`.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> from math import sqrt, exp</span> |
| <span class="sd"> >>> mean = 0.0</span> |
| <span class="sd"> >>> std = 1.0</span> |
| <span class="sd"> >>> expMean = exp(mean + 0.5 * std * std)</span> |
| <span class="sd"> >>> expStd = sqrt((exp(std * std) - 1.0) * exp(2.0 * mean + std * std))</span> |
| <span class="sd"> >>> m = RandomRDDs.logNormalVectorRDD(sc, mean, std, 100, 100, seed=1).collect()</span> |
| <span class="sd"> >>> mat = np.matrix(m)</span> |
| <span class="sd"> >>> mat.shape</span> |
| <span class="sd"> (100, 100)</span> |
| <span class="sd"> >>> abs(mat.mean() - expMean) < 0.1</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> abs(mat.std() - expStd) < 0.1</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"logNormalVectorRDD"</span><span class="p">,</span> |
| <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">mean</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">std</span><span class="p">),</span> |
| <span class="n">numRows</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">,</span> |
| <span class="n">seed</span><span class="p">,</span> |
| <span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.poissonVectorRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.poissonVectorRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="nd">@toArray</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">poissonVectorRDD</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">mean</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="n">Vector</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span> |
| <span class="sd"> from the Poisson distribution with the input mean.</span> |
| |
| <span class="sd"> .. versionadded:: 1.1.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> SparkContext used to create the RDD.</span> |
| <span class="sd"> mean : float</span> |
| <span class="sd"> Mean, or lambda, for the Poisson distribution.</span> |
| <span class="sd"> numRows : float</span> |
| <span class="sd"> Number of Vectors in the RDD.</span> |
| <span class="sd"> numCols : int</span> |
| <span class="sd"> Number of elements in each Vector.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`)</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of Vector with vectors containing i.i.d. samples ~ Pois(mean).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> mean = 100.0</span> |
| <span class="sd"> >>> rdd = RandomRDDs.poissonVectorRDD(sc, mean, 100, 100, seed=1)</span> |
| <span class="sd"> >>> mat = np.mat(rdd.collect())</span> |
| <span class="sd"> >>> mat.shape</span> |
| <span class="sd"> (100, 100)</span> |
| <span class="sd"> >>> abs(mat.mean() - mean) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> from math import sqrt</span> |
| <span class="sd"> >>> abs(mat.std() - sqrt(mean)) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"poissonVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">mean</span><span class="p">),</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span> |
| <span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.exponentialVectorRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.exponentialVectorRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="nd">@toArray</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">exponentialVectorRDD</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">mean</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="n">Vector</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span> |
| <span class="sd"> from the Exponential distribution with the input mean.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> SparkContext used to create the RDD.</span> |
| <span class="sd"> mean : float</span> |
| <span class="sd"> Mean, or 1 / lambda, for the Exponential distribution.</span> |
| <span class="sd"> numRows : int</span> |
| <span class="sd"> Number of Vectors in the RDD.</span> |
| <span class="sd"> numCols : int</span> |
| <span class="sd"> Number of elements in each Vector.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`)</span> |
| <span class="sd"> seed : int, optional</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of Vector with vectors containing i.i.d. samples ~ Exp(mean).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> mean = 0.5</span> |
| <span class="sd"> >>> rdd = RandomRDDs.exponentialVectorRDD(sc, mean, 100, 100, seed=1)</span> |
| <span class="sd"> >>> mat = np.mat(rdd.collect())</span> |
| <span class="sd"> >>> mat.shape</span> |
| <span class="sd"> (100, 100)</span> |
| <span class="sd"> >>> abs(mat.mean() - mean) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> from math import sqrt</span> |
| <span class="sd"> >>> abs(mat.std() - sqrt(mean)) < 0.5</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"exponentialVectorRDD"</span><span class="p">,</span> <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="n">mean</span><span class="p">),</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">numPartitions</span><span class="p">,</span> <span class="n">seed</span> |
| <span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="RandomRDDs.gammaVectorRDD"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.random.RandomRDDs.html#pyspark.mllib.random.RandomRDDs.gammaVectorRDD">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="nd">@toArray</span> |
| <span class="k">def</span><span class="w"> </span><span class="nf">gammaVectorRDD</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">shape</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">scale</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> |
| <span class="n">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">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">RDD</span><span class="p">[</span><span class="n">Vector</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Generates an RDD comprised of vectors containing i.i.d. samples drawn</span> |
| <span class="sd"> from the Gamma distribution.</span> |
| |
| <span class="sd"> .. versionadded:: 1.3.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sc : :py:class:`pyspark.SparkContext`</span> |
| <span class="sd"> SparkContext used to create the RDD.</span> |
| <span class="sd"> shape : float</span> |
| <span class="sd"> Shape (> 0) of the Gamma distribution</span> |
| <span class="sd"> scale : float</span> |
| <span class="sd"> Scale (> 0) of the Gamma distribution</span> |
| <span class="sd"> numRows : int</span> |
| <span class="sd"> Number of Vectors in the RDD.</span> |
| <span class="sd"> numCols : int</span> |
| <span class="sd"> Number of elements in each Vector.</span> |
| <span class="sd"> numPartitions : int, optional</span> |
| <span class="sd"> Number of partitions in the RDD (default: `sc.defaultParallelism`).</span> |
| <span class="sd"> seed : int, optional,</span> |
| <span class="sd"> Random seed (default: a random long integer).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.RDD`</span> |
| <span class="sd"> RDD of Vector with vectors containing i.i.d. samples ~ Gamma(shape, scale).</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> import numpy as np</span> |
| <span class="sd"> >>> from math import sqrt</span> |
| <span class="sd"> >>> shape = 1.0</span> |
| <span class="sd"> >>> scale = 2.0</span> |
| <span class="sd"> >>> expMean = shape * scale</span> |
| <span class="sd"> >>> expStd = sqrt(shape * scale * scale)</span> |
| <span class="sd"> >>> mat = np.matrix(RandomRDDs.gammaVectorRDD(sc, shape, scale, 100, 100, seed=1).collect())</span> |
| <span class="sd"> >>> mat.shape</span> |
| <span class="sd"> (100, 100)</span> |
| <span class="sd"> >>> abs(mat.mean() - expMean) < 0.1</span> |
| <span class="sd"> True</span> |
| <span class="sd"> >>> abs(mat.std() - expStd) < 0.1</span> |
| <span class="sd"> True</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">callMLlibFunc</span><span class="p">(</span> |
| <span class="s2">"gammaVectorRDD"</span><span class="p">,</span> |
| <span class="n">sc</span><span class="o">.</span><span class="n">_jsc</span><span class="p">,</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">shape</span><span class="p">),</span> |
| <span class="nb">float</span><span class="p">(</span><span class="n">scale</span><span class="p">),</span> |
| <span class="n">numRows</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">,</span> |
| <span class="n">numPartitions</span><span class="p">,</span> |
| <span class="n">seed</span><span class="p">,</span> |
| <span class="p">)</span></div></div> |
| |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">_test</span><span class="p">()</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="kn">import</span><span class="w"> </span><span class="nn">doctest</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">pyspark.sql</span><span class="w"> </span><span class="kn">import</span> <span class="n">SparkSession</span> |
| |
| <span class="n">globs</span> <span class="o">=</span> <span class="nb">globals</span><span class="p">()</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">"mllib.random tests"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"sc"</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark</span><span class="o">.</span><span class="n">sparkContext</span> |
| <span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span> <span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span><span class="p">)</span> |
| <span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
| <span class="n">_test</span><span class="p">()</span> |
| </pre></div> |
| |
| </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> |
