Google Git
Sign in
apache / beam-site / refs/heads/updates_release_2.15.0 / . / pydoc / 2.15.0 / _modules / apache_beam / transforms / stats.html
blob: 1b0dd98c84d2e572f61662ec6128a3f4295b584a [file] [log] [blame]
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>apache_beam.transforms.stats &mdash; Apache Beam documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="index" title="Index"
href="../../../genindex.html"/>
<link rel="search" title="Search" href="../../../search.html"/>
<link rel="top" title="Apache Beam documentation" href="../../../index.html"/>
<link rel="up" title="Module code" href="../../index.html"/>
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search">
<a href="../../../index.html" class="icon icon-home"> Apache Beam
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.internal.html">apache_beam.internal package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.io.html">apache_beam.io package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.metrics.html">apache_beam.metrics package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.testing.html">apache_beam.testing package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.tools.html">apache_beam.tools package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.utils.html">apache_beam.utils package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.version.html">apache_beam.version module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" role="navigation" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Apache Beam</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li>apache_beam.transforms.stats</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for apache_beam.transforms.stats</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 &quot;License&quot;); 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 &quot;AS IS&quot; 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">&quot;&quot;&quot;This module has all statistic related transforms.&quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">division</span>
<span class="kn">import</span> <span class="nn">heapq</span>
<span class="kn">import</span> <span class="nn">math</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">typing</span>
<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">round</span>
<span class="kn">from</span> <span class="nn">apache_beam</span> <span class="k">import</span> <span class="n">coders</span>
<span class="kn">from</span> <span class="nn">apache_beam</span> <span class="k">import</span> <span class="n">typehints</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms.core</span> <span class="k">import</span> <span class="o">*</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms.ptransform</span> <span class="k">import</span> <span class="n">PTransform</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span>
<span class="s1">&#39;ApproximateUnique&#39;</span><span class="p">,</span>
<span class="p">]</span>
<span class="c1"># Type variables</span>
<span class="n">T</span> <span class="o">=</span> <span class="n">typing</span><span class="o">.</span><span class="n">TypeVar</span><span class="p">(</span><span class="s1">&#39;T&#39;</span><span class="p">)</span>
<span class="n">K</span> <span class="o">=</span> <span class="n">typing</span><span class="o">.</span><span class="n">TypeVar</span><span class="p">(</span><span class="s1">&#39;K&#39;</span><span class="p">)</span>
<span class="n">V</span> <span class="o">=</span> <span class="n">typing</span><span class="o">.</span><span class="n">TypeVar</span><span class="p">(</span><span class="s1">&#39;V&#39;</span><span class="p">)</span>
<div class="viewcode-block" id="ApproximateUnique"><a class="viewcode-back" href="../../../apache_beam.transforms.stats.html#apache_beam.transforms.stats.ApproximateUnique">[docs]</a><span class="k">class</span> <span class="nc">ApproximateUnique</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Hashes input elements and uses those to extrapolate the size of the entire</span>
<span class="sd"> set of hash values by assuming the rest of the hash values are as densely</span>
<span class="sd"> distributed as the sample space.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_NO_VALUE_ERR_MSG</span> <span class="o">=</span> <span class="s1">&#39;Either size or error should be set. Received </span><span class="si">{}</span><span class="s1">.&#39;</span>
<span class="n">_MULTI_VALUE_ERR_MSG</span> <span class="o">=</span> <span class="s1">&#39;Either size or error should be set. &#39;</span> \
<span class="s1">&#39;Received {size = </span><span class="si">%s</span><span class="s1">, error = </span><span class="si">%s</span><span class="s1">}.&#39;</span>
<span class="n">_INPUT_SIZE_ERR_MSG</span> <span class="o">=</span> <span class="s1">&#39;ApproximateUnique needs a size &gt;= 16 for an error &#39;</span> \
<span class="s1">&#39;&lt;= 0.50. In general, the estimation error is about &#39;</span> \
<span class="s1">&#39;2 / sqrt(sample_size). Received {size = </span><span class="si">%s</span><span class="s1">}.&#39;</span>
<span class="n">_INPUT_ERROR_ERR_MSG</span> <span class="o">=</span> <span class="s1">&#39;ApproximateUnique needs an estimation error &#39;</span> \
<span class="s1">&#39;between 0.01 and 0.50. Received {error = </span><span class="si">%s</span><span class="s1">}.&#39;</span>
<div class="viewcode-block" id="ApproximateUnique.parse_input_params"><a class="viewcode-back" href="../../../apache_beam.transforms.stats.html#apache_beam.transforms.stats.ApproximateUnique.parse_input_params">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">parse_input_params</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">error</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Check if input params are valid and return sample size.</span>
<span class="sd"> :param size: an int not smaller than 16, which we would use to estimate</span>
<span class="sd"> number of unique values.</span>
<span class="sd"> :param error: max estimation error, which is a float between 0.01 and 0.50.</span>
<span class="sd"> If error is given, sample size will be calculated from error with</span>
<span class="sd"> _get_sample_size_from_est_error function.</span>
<span class="sd"> :return: sample size</span>
<span class="sd"> :raises:</span>
<span class="sd"> ValueError: If both size and error are given, or neither is given, or</span>
<span class="sd"> values are out of range.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="kc">None</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="n">error</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="n">ApproximateUnique</span><span class="o">.</span><span class="n">_MULTI_VALUE_ERR_MSG</span> <span class="o">%</span> <span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="n">error</span><span class="p">))</span>
<span class="k">elif</span> <span class="n">size</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">error</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="n">ApproximateUnique</span><span class="o">.</span><span class="n">_NO_VALUE_ERR_MSG</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">size</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="nb">int</span><span class="p">)</span> <span class="ow">or</span> <span class="n">size</span> <span class="o">&lt;</span> <span class="mi">16</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="n">ApproximateUnique</span><span class="o">.</span><span class="n">_INPUT_SIZE_ERR_MSG</span> <span class="o">%</span> <span class="p">(</span><span class="n">size</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">size</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">error</span> <span class="o">&lt;</span> <span class="mf">0.01</span> <span class="ow">or</span> <span class="n">error</span> <span class="o">&gt;</span> <span class="mf">0.5</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="n">ApproximateUnique</span><span class="o">.</span><span class="n">_INPUT_ERROR_ERR_MSG</span> <span class="o">%</span> <span class="p">(</span><span class="n">error</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">ApproximateUnique</span><span class="o">.</span><span class="n">_get_sample_size_from_est_error</span><span class="p">(</span><span class="n">error</span><span class="p">)</span></div>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">_get_sample_size_from_est_error</span><span class="p">(</span><span class="n">est_err</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> :return: sample size</span>
<span class="sd"> Calculate sample size from estimation error</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1">#math.ceil in python2.7 returns a float, while it returns an int in python3.</span>
<span class="k">return</span> <span class="nb">int</span><span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">ceil</span><span class="p">(</span><span class="mf">4.0</span> <span class="o">/</span> <span class="n">math</span><span class="o">.</span><span class="n">pow</span><span class="p">(</span><span class="n">est_err</span><span class="p">,</span> <span class="mf">2.0</span><span class="p">)))</span>
<div class="viewcode-block" id="ApproximateUnique.Globally"><a class="viewcode-back" href="../../../apache_beam.transforms.stats.html#apache_beam.transforms.stats.ApproximateUnique.Globally">[docs]</a> <span class="nd">@typehints</span><span class="o">.</span><span class="n">with_input_types</span><span class="p">(</span><span class="n">T</span><span class="p">)</span>
<span class="nd">@typehints</span><span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">Globally</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot; Approximate.Globally approximate number of unique values&quot;&quot;&quot;</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">error</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span> <span class="o">=</span> <span class="n">ApproximateUnique</span><span class="o">.</span><span class="n">parse_input_params</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="n">error</span><span class="p">)</span>
<div class="viewcode-block" id="ApproximateUnique.Globally.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.stats.html#apache_beam.transforms.stats.ApproximateUnique.Globally.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span>
<span class="n">coder</span> <span class="o">=</span> <span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">get_coder</span><span class="p">(</span><span class="n">pcoll</span><span class="p">)</span>
<span class="k">return</span> <span class="n">pcoll</span> \
<span class="o">|</span> <span class="s1">&#39;CountGlobalUniqueValues&#39;</span> \
<span class="o">&gt;&gt;</span> <span class="p">(</span><span class="n">CombineGlobally</span><span class="p">(</span><span class="n">ApproximateUniqueCombineFn</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span><span class="p">,</span>
<span class="n">coder</span><span class="p">)))</span></div></div>
<div class="viewcode-block" id="ApproximateUnique.PerKey"><a class="viewcode-back" href="../../../apache_beam.transforms.stats.html#apache_beam.transforms.stats.ApproximateUnique.PerKey">[docs]</a> <span class="nd">@typehints</span><span class="o">.</span><span class="n">with_input_types</span><span class="p">(</span><span class="n">typing</span><span class="o">.</span><span class="n">Tuple</span><span class="p">[</span><span class="n">K</span><span class="p">,</span> <span class="n">V</span><span class="p">])</span>
<span class="nd">@typehints</span><span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="n">typing</span><span class="o">.</span><span class="n">Tuple</span><span class="p">[</span><span class="n">K</span><span class="p">,</span> <span class="nb">int</span><span class="p">])</span>
<span class="k">class</span> <span class="nc">PerKey</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot; Approximate.PerKey approximate number of unique values per key&quot;&quot;&quot;</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">error</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span> <span class="o">=</span> <span class="n">ApproximateUnique</span><span class="o">.</span><span class="n">parse_input_params</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="n">error</span><span class="p">)</span>
<div class="viewcode-block" id="ApproximateUnique.PerKey.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.stats.html#apache_beam.transforms.stats.ApproximateUnique.PerKey.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span>
<span class="n">coder</span> <span class="o">=</span> <span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">get_coder</span><span class="p">(</span><span class="n">pcoll</span><span class="p">)</span>
<span class="k">return</span> <span class="n">pcoll</span> \
<span class="o">|</span> <span class="s1">&#39;CountPerKeyUniqueValues&#39;</span> \
<span class="o">&gt;&gt;</span> <span class="p">(</span><span class="n">CombinePerKey</span><span class="p">(</span><span class="n">ApproximateUniqueCombineFn</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span><span class="p">,</span>
<span class="n">coder</span><span class="p">)))</span></div></div></div>
<span class="k">class</span> <span class="nc">_LargestUnique</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> An object to keep samples and calculate sample hash space. It is an</span>
<span class="sd"> accumulator of a combine function.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_HASH_SPACE_SIZE</span> <span class="o">=</span> <span class="mf">2.0</span> <span class="o">*</span> <span class="n">sys</span><span class="o">.</span><span class="n">maxsize</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sample_size</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span> <span class="o">=</span> <span class="n">sample_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_min_hash</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">maxsize</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sample_heap</span> <span class="o">=</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sample_set</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">add</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> :param an element from pcoll.</span>
<span class="sd"> :return: boolean type whether the value is in the heap</span>
<span class="sd"> Adds a value to the heap, returning whether the value is (large enough to</span>
<span class="sd"> be) in the heap.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_heap</span><span class="p">)</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span> <span class="ow">and</span> <span class="n">element</span> <span class="o">&lt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_hash</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">if</span> <span class="n">element</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample_set</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sample_set</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">element</span><span class="p">)</span>
<span class="n">heapq</span><span class="o">.</span><span class="n">heappush</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_heap</span><span class="p">,</span> <span class="n">element</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_heap</span><span class="p">)</span> <span class="o">&gt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span><span class="p">:</span>
<span class="n">temp</span> <span class="o">=</span> <span class="n">heapq</span><span class="o">.</span><span class="n">heappop</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_heap</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sample_set</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">temp</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_min_hash</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample_heap</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">elif</span> <span class="n">element</span> <span class="o">&lt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_hash</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_min_hash</span> <span class="o">=</span> <span class="n">element</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">def</span> <span class="nf">get_estimate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> :return: estimation count of unique values</span>
<span class="sd"> If heap size is smaller than sample size, just return heap size.</span>
<span class="sd"> Otherwise, takes into account the possibility of hash collisions,</span>
<span class="sd"> which become more likely than not for 2^32 distinct elements.</span>
<span class="sd"> Note that log(1+x) ~ x for small x, so for sampleSize &lt;&lt; maxHash</span>
<span class="sd"> log(1 - sample_size/sample_space) / log(1 - 1/sample_space) ~ sample_size</span>
<span class="sd"> and hence estimate ~ sample_size * hash_space / sample_space</span>
<span class="sd"> as one would expect.</span>
<span class="sd"> Given sample_size / sample_space = est / hash_space</span>
<span class="sd"> est = sample_size * hash_space / sample_space</span>
<span class="sd"> Given above sample_size approximate,</span>
<span class="sd"> est = log1p(-sample_size/sample_space) / log1p(-1/sample_space)</span>
<span class="sd"> * hash_space / sample_space</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_heap</span><span class="p">)</span> <span class="o">&lt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_heap</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">sample_space_size</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">maxsize</span> <span class="o">-</span> <span class="mf">1.0</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_min_hash</span>
<span class="n">est</span> <span class="o">=</span> <span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">log1p</span><span class="p">(</span><span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span> <span class="o">/</span> <span class="n">sample_space_size</span><span class="p">)</span>
<span class="o">/</span> <span class="n">math</span><span class="o">.</span><span class="n">log1p</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span> <span class="o">/</span> <span class="n">sample_space_size</span><span class="p">)</span>
<span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_HASH_SPACE_SIZE</span>
<span class="o">/</span> <span class="n">sample_space_size</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">round</span><span class="p">(</span><span class="n">est</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">ApproximateUniqueCombineFn</span><span class="p">(</span><span class="n">CombineFn</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> ApproximateUniqueCombineFn computes an estimate of the number of</span>
<span class="sd"> unique values that were combined.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sample_size</span><span class="p">,</span> <span class="n">coder</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span> <span class="o">=</span> <span class="n">sample_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_coder</span> <span class="o">=</span> <span class="n">coder</span>
<span class="k">def</span> <span class="nf">create_accumulator</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="k">return</span> <span class="n">_LargestUnique</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">accumulator</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="nb">hash</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_coder</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">element</span><span class="p">)))</span>
<span class="k">return</span> <span class="n">accumulator</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">&quot;Runtime exception: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="c1"># created an issue https://issues.apache.org/jira/browse/BEAM-7285 to speep up</span>
<span class="c1"># merge process.</span>
<span class="k">def</span> <span class="nf">merge_accumulators</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulators</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="n">merged_accumulator</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">create_accumulator</span><span class="p">()</span>
<span class="k">for</span> <span class="n">accumulator</span> <span class="ow">in</span> <span class="n">accumulators</span><span class="p">:</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">accumulator</span><span class="o">.</span><span class="n">_sample_heap</span><span class="p">:</span>
<span class="n">merged_accumulator</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
<span class="k">return</span> <span class="n">merged_accumulator</span>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">extract_output</span><span class="p">(</span><span class="n">accumulator</span><span class="p">):</span>
<span class="k">return</span> <span class="n">accumulator</span><span class="o">.</span><span class="n">get_estimate</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="p">{</span><span class="s1">&#39;sample_size&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span><span class="p">}</span>
</pre></div>
</div>
<div class="articleComments">
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright .
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt'
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.StickyNav.enable();
});
</script>
</body>
</html>