blob: df3fafab77369ff02887af85c4271c1af778bb25 [file] [log] [blame]
<!DOCTYPE html>
<html class="writer-html5" lang="en" data-content_root="./">
<head>
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Apache DataSketches &mdash; datasketches 0.1 documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=b86133f3" />
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=e59714d7" />
<script src="_static/jquery.js?v=5d32c60e"></script>
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
<script src="_static/documentation_options.js?v=2709fde1"></script>
<script src="_static/doctools.js?v=9bcbadda"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="_static/js/theme.js"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="Distinct Counting" href="distinct_counting/index.html" />
</head>
<body class="wy-body-for-nav">
<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="#" class="icon icon-home">
datasketches
</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" aria-label="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="Navigation menu">
<ul>
<li class="toctree-l1"><a class="reference internal" href="distinct_counting/index.html">Distinct Counting</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="quantiles/index.html">Quantiles Sketches</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="frequency/index.html">Frequency Sketches</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="vector/index.html">Vector Sketches</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="sampling/index.html">Random Sampling Sketches</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="helper/index.html">Helper Classes</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="#">datasketches</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="Page navigation">
<ul class="wy-breadcrumbs">
<li><a href="#" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item active">Apache DataSketches</li>
<li class="wy-breadcrumbs-aside">
<a href="_sources/index.rst.txt" rel="nofollow"> View page source</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<section id="apache-datasketches">
<h1>Apache DataSketches<a class="headerlink" href="#apache-datasketches" title="Link to this heading"></a></h1>
<p><strong>DataSketches</strong> are highly-efficient algorithms to analyze big data quickly.</p>
<section id="counting-distincts">
<h2>Counting Distincts<a class="headerlink" href="#counting-distincts" title="Link to this heading"></a></h2>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="distinct_counting/index.html">Distinct Counting</a><ul>
<li class="toctree-l2"><a class="reference internal" href="distinct_counting/hyper_log_log.html">HyperLogLog (HLL)</a></li>
<li class="toctree-l2"><a class="reference internal" href="distinct_counting/cpc.html">Compressed Probabilistic Counting (CPC)</a></li>
<li class="toctree-l2"><a class="reference internal" href="distinct_counting/theta.html">Theta Sketch</a></li>
<li class="toctree-l2"><a class="reference internal" href="distinct_counting/tuple.html">Tuple Sketch</a></li>
</ul>
</li>
</ul>
</div>
</section>
<section id="quantile-estimation">
<h2>Quantile Estimation<a class="headerlink" href="#quantile-estimation" title="Link to this heading"></a></h2>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="quantiles/index.html">Quantiles Sketches</a><ul>
<li class="toctree-l2"><a class="reference internal" href="quantiles/kll.html">KLL Sketch</a></li>
<li class="toctree-l2"><a class="reference internal" href="quantiles/req.html">Relative Error Quantiles (REQ) Sketch</a></li>
<li class="toctree-l2"><a class="reference internal" href="quantiles/tdigest.html">t-digest</a></li>
<li class="toctree-l2"><a class="reference internal" href="quantiles/quantiles_depr.html">Quantiles Sketch (Deprecated)</a></li>
</ul>
</li>
</ul>
</div>
</section>
<section id="frequency-sketches">
<h2>Frequency Sketches<a class="headerlink" href="#frequency-sketches" title="Link to this heading"></a></h2>
<p>This problem may also be known as <strong>heavy hitters</strong> or <strong>TopK</strong></p>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="frequency/index.html">Frequency Sketches</a><ul>
<li class="toctree-l2"><a class="reference internal" href="frequency/frequent_items.html">Frequent Items</a></li>
<li class="toctree-l2"><a class="reference internal" href="frequency/count_min_sketch.html">CountMin Sketch</a></li>
</ul>
</li>
</ul>
</div>
</section>
<section id="vector-sketches">
<h2>Vector Sketches<a class="headerlink" href="#vector-sketches" title="Link to this heading"></a></h2>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="vector/index.html">Vector Sketches</a><ul>
<li class="toctree-l2"><a class="reference internal" href="vector/density_sketch.html">Density Sketch</a></li>
</ul>
</li>
</ul>
</div>
</section>
<section id="random-sampling">
<h2>Random Sampling<a class="headerlink" href="#random-sampling" title="Link to this heading"></a></h2>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="sampling/index.html">Random Sampling Sketches</a><ul>
<li class="toctree-l2"><a class="reference internal" href="sampling/varopt.html">Variance Optimal Sampling (VarOpt)</a></li>
<li class="toctree-l2"><a class="reference internal" href="sampling/ebpps.html">Exact and Bounded, Probabilitiy Proportional to Size (EBPPS) Sampling</a></li>
</ul>
</li>
</ul>
</div>
</section>
<section id="helper-classes">
<h2>Helper Classes<a class="headerlink" href="#helper-classes" title="Link to this heading"></a></h2>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="helper/index.html">Helper Classes</a><ul>
<li class="toctree-l2"><a class="reference internal" href="helper/serde.html">Serialize/Deserialize (SerDe)</a></li>
<li class="toctree-l2"><a class="reference internal" href="helper/jaccard.html">Jaccard Similarity</a></li>
<li class="toctree-l2"><a class="reference internal" href="helper/tuple_policy.html">Tuple Policy</a></li>
<li class="toctree-l2"><a class="reference internal" href="helper/ks_test.html">Kolmogorov-Smirnov Test</a></li>
<li class="toctree-l2"><a class="reference internal" href="helper/kernel.html">Kernel Function</a></li>
</ul>
</li>
</ul>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>This project is under active development.</p>
</div>
</section>
</section>
<section id="indices-and-tables">
<h1>Indices and tables<a class="headerlink" href="#indices-and-tables" title="Link to this heading"></a></h1>
<ul class="simple">
<li><p><a class="reference internal" href="genindex.html"><span class="std std-ref">Index</span></a></p></li>
<li><p><a class="reference internal" href="py-modindex.html"><span class="std std-ref">Module Index</span></a></p></li>
<li><p><a class="reference internal" href="search.html"><span class="std std-ref">Search Page</span></a></p></li>
</ul>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="distinct_counting/index.html" class="btn btn-neutral float-right" title="Distinct Counting" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<p>&#169; Copyright 2023.</p>
</div>
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>