blob: aa619a739ee9485d7432b0848097f0d69bbf5c70 [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>Tuple Sketch &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="Quantiles Sketches" href="../quantiles/index.html" />
<link rel="prev" title="Theta Sketch" href="theta.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="../index.html" 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 class="current">
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Distinct Counting</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="hyper_log_log.html">HyperLogLog (HLL)</a></li>
<li class="toctree-l2"><a class="reference internal" href="cpc.html">Compressed Probabilistic Counting (CPC)</a></li>
<li class="toctree-l2"><a class="reference internal" href="theta.html">Theta Sketch</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Tuple Sketch</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#datasketches.tuple_sketch"><code class="docutils literal notranslate"><span class="pre">tuple_sketch</span></code></a><ul>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.DEFAULT_SEED"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.DEFAULT_SEED</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.get_estimate"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.get_estimate</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.get_lower_bound"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.get_lower_bound</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.get_seed_hash"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.get_seed_hash</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.get_upper_bound"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.get_upper_bound</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.is_empty"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.is_empty</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.is_estimation_mode"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.is_estimation_mode</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.is_ordered"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.is_ordered</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.num_retained"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.num_retained</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.theta"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.theta</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.theta64"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.theta64</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_sketch.to_string"><code class="docutils literal notranslate"><span class="pre">tuple_sketch.to_string</span></code></a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="#datasketches.update_tuple_sketch"><code class="docutils literal notranslate"><span class="pre">update_tuple_sketch</span></code></a><ul>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.update_tuple_sketch.__init__"><code class="docutils literal notranslate"><span class="pre">update_tuple_sketch.__init__()</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.update_tuple_sketch.compact"><code class="docutils literal notranslate"><span class="pre">update_tuple_sketch.compact</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.update_tuple_sketch.filter"><code class="docutils literal notranslate"><span class="pre">update_tuple_sketch.filter</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.update_tuple_sketch.reset"><code class="docutils literal notranslate"><span class="pre">update_tuple_sketch.reset</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.update_tuple_sketch.trim"><code class="docutils literal notranslate"><span class="pre">update_tuple_sketch.trim</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.update_tuple_sketch.update"><code class="docutils literal notranslate"><span class="pre">update_tuple_sketch.update</span></code></a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="#datasketches.compact_tuple_sketch"><code class="docutils literal notranslate"><span class="pre">compact_tuple_sketch</span></code></a><ul>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.compact_tuple_sketch.deserialize"><code class="docutils literal notranslate"><span class="pre">compact_tuple_sketch.deserialize()</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.compact_tuple_sketch.__init__"><code class="docutils literal notranslate"><span class="pre">compact_tuple_sketch.__init__()</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.compact_tuple_sketch.filter"><code class="docutils literal notranslate"><span class="pre">compact_tuple_sketch.filter</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.compact_tuple_sketch.serialize"><code class="docutils literal notranslate"><span class="pre">compact_tuple_sketch.serialize</span></code></a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="#datasketches.tuple_union"><code class="docutils literal notranslate"><span class="pre">tuple_union</span></code></a><ul>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_union.__init__"><code class="docutils literal notranslate"><span class="pre">tuple_union.__init__()</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_union.get_result"><code class="docutils literal notranslate"><span class="pre">tuple_union.get_result</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_union.reset"><code class="docutils literal notranslate"><span class="pre">tuple_union.reset</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_union.update"><code class="docutils literal notranslate"><span class="pre">tuple_union.update</span></code></a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="#datasketches.tuple_intersection"><code class="docutils literal notranslate"><span class="pre">tuple_intersection</span></code></a><ul>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_intersection.__init__"><code class="docutils literal notranslate"><span class="pre">tuple_intersection.__init__()</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_intersection.get_result"><code class="docutils literal notranslate"><span class="pre">tuple_intersection.get_result</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_intersection.has_result"><code class="docutils literal notranslate"><span class="pre">tuple_intersection.has_result</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_intersection.update"><code class="docutils literal notranslate"><span class="pre">tuple_intersection.update</span></code></a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="#datasketches.tuple_a_not_b"><code class="docutils literal notranslate"><span class="pre">tuple_a_not_b</span></code></a><ul>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_a_not_b.__init__"><code class="docutils literal notranslate"><span class="pre">tuple_a_not_b.__init__()</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#datasketches.tuple_a_not_b.compute"><code class="docutils literal notranslate"><span class="pre">tuple_a_not_b.compute</span></code></a></li>
</ul>
</li>
</ul>
</li>
</ul>
</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="../index.html">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="../index.html" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item"><a href="index.html">Distinct Counting</a></li>
<li class="breadcrumb-item active">Tuple Sketch</li>
<li class="wy-breadcrumbs-aside">
<a href="../_sources/distinct_counting/tuple.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="tuple-sketch">
<h1>Tuple Sketch<a class="headerlink" href="#tuple-sketch" title="Link to this heading"></a></h1>
<p>Tuple sketches are an extension of Theta sketches, meaning they provide estimate of distinct counts, that
allow the keeping of arbitrary summaries associated with each retained key
(for example, a count for every key). The use of a <a class="reference internal" href="#datasketches.tuple_sketch" title="datasketches.tuple_sketch"><code class="xref py py-class docutils literal notranslate"><span class="pre">tuple_sketch</span></code></a> requires a <a class="reference internal" href="../helper/tuple_policy.html#datasketches.TuplePolicy" title="datasketches.TuplePolicy"><code class="xref py py-class docutils literal notranslate"><span class="pre">TuplePolicy</span></code></a> which
defines how summaries are created, updated, merged, or intersected. The library provides a few basic
examples of <a class="reference internal" href="../helper/tuple_policy.html#datasketches.TuplePolicy" title="datasketches.TuplePolicy"><code class="xref py py-class docutils literal notranslate"><span class="pre">TuplePolicy</span></code></a> implementations, but the right custom summary and policy can allow very
complicated analysis to be performed quite easily.</p>
<p>Set operations (union, intersection, A-not-B) are performed through the use of dedicated objects.</p>
<p>Several <a class="reference external" href="https://en.wikipedia.org/wiki/Jaccard_similarity">Jaccard similarity</a>
measures can be computed between theta sketches with the <a class="reference internal" href="../helper/jaccard.html#datasketches.tuple_jaccard_similarity" title="datasketches.tuple_jaccard_similarity"><code class="xref py py-class docutils literal notranslate"><span class="pre">tuple_jaccard_similarity</span></code></a> class.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Serializing and deserializing this sketch requires the use of a <a class="reference internal" href="../helper/serde.html#datasketches.PyObjectSerDe" title="datasketches.PyObjectSerDe"><code class="xref py py-class docutils literal notranslate"><span class="pre">PyObjectSerDe</span></code></a>.</p>
</div>
<dl class="py class">
<dt class="sig sig-object py" id="datasketches.tuple_sketch">
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">tuple_sketch</span></span><a class="headerlink" href="#datasketches.tuple_sketch" title="Link to this definition"></a></dt>
<dd><p>An abstract base class for tuple sketches.</p>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.DEFAULT_SEED">
<span class="sig-name descname"><span class="pre">DEFAULT_SEED</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">9001</span></em><a class="headerlink" href="#datasketches.tuple_sketch.DEFAULT_SEED" title="Link to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.get_estimate">
<span class="sig-name descname"><span class="pre">get_estimate</span></span><a class="headerlink" href="#datasketches.tuple_sketch.get_estimate" title="Link to this definition"></a></dt>
<dd><p>Estimate of the distinct count of the input stream</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.get_lower_bound">
<span class="sig-name descname"><span class="pre">get_lower_bound</span></span><a class="headerlink" href="#datasketches.tuple_sketch.get_lower_bound" title="Link to this definition"></a></dt>
<dd><p>Returns an approximate lower bound on the estimate at standard deviations in {1, 2, 3}</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.get_seed_hash">
<span class="sig-name descname"><span class="pre">get_seed_hash</span></span><a class="headerlink" href="#datasketches.tuple_sketch.get_seed_hash" title="Link to this definition"></a></dt>
<dd><p>Returns a hash of the seed used in the sketch</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.get_upper_bound">
<span class="sig-name descname"><span class="pre">get_upper_bound</span></span><a class="headerlink" href="#datasketches.tuple_sketch.get_upper_bound" title="Link to this definition"></a></dt>
<dd><p>Returns an approximate upper bound on the estimate at standard deviations in {1, 2, 3}</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.is_empty">
<span class="sig-name descname"><span class="pre">is_empty</span></span><a class="headerlink" href="#datasketches.tuple_sketch.is_empty" title="Link to this definition"></a></dt>
<dd><p>Returns True if the sketch is empty, otherwise False</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.is_estimation_mode">
<span class="sig-name descname"><span class="pre">is_estimation_mode</span></span><a class="headerlink" href="#datasketches.tuple_sketch.is_estimation_mode" title="Link to this definition"></a></dt>
<dd><p>Returns True if sketch is in estimation mode, otherwise False</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.is_ordered">
<span class="sig-name descname"><span class="pre">is_ordered</span></span><a class="headerlink" href="#datasketches.tuple_sketch.is_ordered" title="Link to this definition"></a></dt>
<dd><p>Returns True if the sketch entries are sorted, otherwise False</p>
</dd></dl>
<dl class="py property">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.num_retained">
<em class="property"><span class="k"><span class="pre">property</span></span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">num_retained</span></span><a class="headerlink" href="#datasketches.tuple_sketch.num_retained" title="Link to this definition"></a></dt>
<dd><p>The number of items currently in the sketch</p>
</dd></dl>
<dl class="py property">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.theta">
<em class="property"><span class="k"><span class="pre">property</span></span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">theta</span></span><a class="headerlink" href="#datasketches.tuple_sketch.theta" title="Link to this definition"></a></dt>
<dd><p>Theta (effective sampling rate) as a fraction from 0 to 1</p>
</dd></dl>
<dl class="py property">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.theta64">
<em class="property"><span class="k"><span class="pre">property</span></span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">theta64</span></span><a class="headerlink" href="#datasketches.tuple_sketch.theta64" title="Link to this definition"></a></dt>
<dd><p>Theta as 64-bit value</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_sketch.to_string">
<span class="sig-name descname"><span class="pre">to_string</span></span><a class="headerlink" href="#datasketches.tuple_sketch.to_string" title="Link to this definition"></a></dt>
<dd><p>Produces a string summary of the sketch</p>
</dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="datasketches.update_tuple_sketch">
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">update_tuple_sketch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#datasketches.update_tuple_sketch" title="Link to this definition"></a></dt>
<dd><dl class="py method">
<dt class="sig sig-object py" id="datasketches.update_tuple_sketch.__init__">
<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">self</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">policy</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../helper/tuple_policy.html#datasketches.TuplePolicy" title="_datasketches.TuplePolicy"><span class="pre">_datasketches.TuplePolicy</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">lg_k</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">float</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">9001</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="headerlink" href="#datasketches.update_tuple_sketch.__init__" title="Link to this definition"></a></dt>
<dd><p>Creates an update_tuple_sketch using the provided parameters</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>policy</strong> (<a class="reference internal" href="../helper/tuple_policy.html#datasketches.TuplePolicy" title="datasketches.TuplePolicy"><em>TuplePolicy</em></a>) – a policy to use when updating</p></li>
<li><p><strong>lg_k</strong> (<em>int</em><em>, </em><em>optional</em>) – base 2 logarithm of the maximum size of the sketch. Default 12.</p></li>
<li><p><strong>p</strong> (<em>float</em><em>, </em><em>optional</em>) – an initial sampling rate to use. Default 1.0</p></li>
<li><p><strong>seed</strong> (<em>int</em><em>, </em><em>optional</em>) – the seed to use when hashing values</p></li>
</ul>
</dd>
</dl>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.update_tuple_sketch.compact">
<span class="sig-name descname"><span class="pre">compact</span></span><a class="headerlink" href="#datasketches.update_tuple_sketch.compact" title="Link to this definition"></a></dt>
<dd><p>Returns a compacted form of the sketch, optionally sorting it</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.update_tuple_sketch.filter">
<span class="sig-name descname"><span class="pre">filter</span></span><a class="headerlink" href="#datasketches.update_tuple_sketch.filter" title="Link to this definition"></a></dt>
<dd><p>Produces a compact_tuple_sketch from the given sketch by applying a predicate to the summary in each entry.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><p><strong>predicate</strong> – A function returning true or value evaluated on each tuple summary</p>
</dd>
<dt class="field-even">Returns<span class="colon">:</span></dt>
<dd class="field-even"><p>A compact_tuple_sketch with the selected entries</p>
</dd>
<dt class="field-odd">Return type<span class="colon">:</span></dt>
<dd class="field-odd"><p><a class="reference internal" href="#datasketches.compact_tuple_sketch" title="datasketches.compact_tuple_sketch"><code class="xref py py-class docutils literal notranslate"><span class="pre">compact_tuple_sketch</span></code></a></p>
</dd>
</dl>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.update_tuple_sketch.reset">
<span class="sig-name descname"><span class="pre">reset</span></span><a class="headerlink" href="#datasketches.update_tuple_sketch.reset" title="Link to this definition"></a></dt>
<dd><p>Resets the sketch to the initial empty state</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.update_tuple_sketch.trim">
<span class="sig-name descname"><span class="pre">trim</span></span><a class="headerlink" href="#datasketches.update_tuple_sketch.trim" title="Link to this definition"></a></dt>
<dd><p>Removes retained entries in excess of the nominal size k (if any)</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.update_tuple_sketch.update">
<span class="sig-name descname"><span class="pre">update</span></span><a class="headerlink" href="#datasketches.update_tuple_sketch.update" title="Link to this definition"></a></dt>
<dd><p>Overloaded function.</p>
<ol class="arabic simple">
<li><p><code class="docutils literal notranslate"><span class="pre">update(self,</span> <span class="pre">datum:</span> <span class="pre">int,</span> <span class="pre">value:</span> <span class="pre">object)</span> <span class="pre">-&gt;</span> <span class="pre">None</span></code></p></li>
</ol>
<p>Updates the sketch with the given integral item and summary value</p>
<ol class="arabic simple" start="2">
<li><p><code class="docutils literal notranslate"><span class="pre">update(self,</span> <span class="pre">datum:</span> <span class="pre">float,</span> <span class="pre">value:</span> <span class="pre">object)</span> <span class="pre">-&gt;</span> <span class="pre">None</span></code></p></li>
</ol>
<p>Updates the sketch with the given floating point item and summary value</p>
<ol class="arabic simple" start="3">
<li><p><code class="docutils literal notranslate"><span class="pre">update(self,</span> <span class="pre">datum:</span> <span class="pre">str,</span> <span class="pre">value:</span> <span class="pre">object)</span> <span class="pre">-&gt;</span> <span class="pre">None</span></code></p></li>
</ol>
<p>Updates the sketch with the given string item and summary value</p>
</dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="datasketches.compact_tuple_sketch">
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">compact_tuple_sketch</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#datasketches.compact_tuple_sketch" title="Link to this definition"></a></dt>
<dd><p class="rubric">Static Methods:</p>
<dl class="py method">
<dt class="sig sig-object py" id="datasketches.compact_tuple_sketch.deserialize">
<span class="sig-name descname"><span class="pre">deserialize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">bytes</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bytes</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">serde</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../helper/serde.html#datasketches.PyObjectSerDe" title="_datasketches.PyObjectSerDe"><span class="pre">_datasketches.PyObjectSerDe</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">9001</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="#datasketches.compact_tuple_sketch" title="_datasketches.compact_tuple_sketch"><span class="pre">_datasketches.compact_tuple_sketch</span></a></span></span><a class="headerlink" href="#datasketches.compact_tuple_sketch.deserialize" title="Link to this definition"></a></dt>
<dd><p>Reads a bytes object and returns the corresponding compact_tuple_sketch</p>
</dd></dl>
<p class="rubric">Non-static Methods:</p>
<dl class="py method">
<dt class="sig sig-object py" id="datasketches.compact_tuple_sketch.__init__">
<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">self</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">other</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#datasketches.tuple_sketch" title="_datasketches.tuple_sketch"><span class="pre">_datasketches.tuple_sketch</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">ordered</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="headerlink" href="#datasketches.compact_tuple_sketch.__init__" title="Link to this definition"></a></dt>
<dt class="sig sig-object py">
<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">self</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">other</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="theta.html#datasketches.theta_sketch" title="_datasketches.theta_sketch"><span class="pre">_datasketches.theta_sketch</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">summary</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">object</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span></dt>
<dd><p>Overloaded function.</p>
<ol class="arabic simple">
<li><p><code class="docutils literal notranslate"><span class="pre">__init__(self,</span> <span class="pre">other:</span> <span class="pre">_datasketches.tuple_sketch,</span> <span class="pre">ordered:</span> <span class="pre">bool</span> <span class="pre">=</span> <span class="pre">True)</span> <span class="pre">-&gt;</span> <span class="pre">None</span></code></p></li>
</ol>
<p>Creates a compact_tuple_sketch from an existing tuple_sketch.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>other</strong> (<a class="reference internal" href="#datasketches.tuple_sketch" title="datasketches.tuple_sketch"><em>tuple_sketch</em></a>) – a sourch tuple_sketch</p></li>
<li><p><strong>ordered</strong> (<em>bool</em><em>, </em><em>optional</em>) – whether the incoming sketch entries are sorted. Default True</p></li>
</ul>
</dd>
</dl>
<ol class="arabic simple" start="2">
<li><p><code class="docutils literal notranslate"><span class="pre">__init__(self,</span> <span class="pre">other:</span> <span class="pre">_datasketches.theta_sketch,</span> <span class="pre">summary:</span> <span class="pre">object)</span> <span class="pre">-&gt;</span> <span class="pre">None</span></code></p></li>
</ol>
<p>Creates a compact_tuple_sketch from a theta_sketch using a fixed summary value.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>other</strong> (<a class="reference internal" href="theta.html#datasketches.theta_sketch" title="datasketches.theta_sketch"><em>theta_sketch</em></a>) – a source theta sketch</p></li>
<li><p><strong>summary</strong> (<em>object</em>) – a summary to use for every sketch entry</p></li>
</ul>
</dd>
</dl>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.compact_tuple_sketch.filter">
<span class="sig-name descname"><span class="pre">filter</span></span><a class="headerlink" href="#datasketches.compact_tuple_sketch.filter" title="Link to this definition"></a></dt>
<dd><p>Produces a compact_tuple_sketch from the given sketch by applying a predicate to the summary in each entry.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><p><strong>predicate</strong> – A function returning true or value evaluated on each tuple summary</p>
</dd>
<dt class="field-even">Returns<span class="colon">:</span></dt>
<dd class="field-even"><p>A compact_tuple_sketch with the selected entries</p>
</dd>
<dt class="field-odd">Return type<span class="colon">:</span></dt>
<dd class="field-odd"><p><a class="reference internal" href="#datasketches.compact_tuple_sketch" title="datasketches.compact_tuple_sketch"><code class="xref py py-class docutils literal notranslate"><span class="pre">compact_tuple_sketch</span></code></a></p>
</dd>
</dl>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.compact_tuple_sketch.serialize">
<span class="sig-name descname"><span class="pre">serialize</span></span><a class="headerlink" href="#datasketches.compact_tuple_sketch.serialize" title="Link to this definition"></a></dt>
<dd><p>Serializes the sketch into a bytes object</p>
</dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="datasketches.tuple_union">
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">tuple_union</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#datasketches.tuple_union" title="Link to this definition"></a></dt>
<dd><dl class="py method">
<dt class="sig sig-object py" id="datasketches.tuple_union.__init__">
<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">self</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">policy</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../helper/tuple_policy.html#datasketches.TuplePolicy" title="_datasketches.TuplePolicy"><span class="pre">_datasketches.TuplePolicy</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">lg_k</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">12</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">p</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">float</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">9001</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="headerlink" href="#datasketches.tuple_union.__init__" title="Link to this definition"></a></dt>
<dd><p>Creates a tuple_union using the provided parameters</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>policy</strong> (<a class="reference internal" href="../helper/tuple_policy.html#datasketches.TuplePolicy" title="datasketches.TuplePolicy"><em>TuplePolicy</em></a>) – a policy to use when unioning entries</p></li>
<li><p><strong>lg_k</strong> (<em>int</em><em>, </em><em>optional</em>) – base 2 logarithm of the maximum size of the union. Default 12.</p></li>
<li><p><strong>p</strong> (<em>float</em><em>, </em><em>optional</em>) – an initial sampling rate to use. Default 1.0</p></li>
<li><p><strong>seed</strong> (<em>int</em><em>, </em><em>optional</em>) – the seed to use when hashing values. Must match any sketch seeds.</p></li>
</ul>
</dd>
</dl>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_union.get_result">
<span class="sig-name descname"><span class="pre">get_result</span></span><a class="headerlink" href="#datasketches.tuple_union.get_result" title="Link to this definition"></a></dt>
<dd><p>Returns the sketch corresponding to the union result</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_union.reset">
<span class="sig-name descname"><span class="pre">reset</span></span><a class="headerlink" href="#datasketches.tuple_union.reset" title="Link to this definition"></a></dt>
<dd><p>Resets the sketch to the initial empty</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_union.update">
<span class="sig-name descname"><span class="pre">update</span></span><a class="headerlink" href="#datasketches.tuple_union.update" title="Link to this definition"></a></dt>
<dd><p>Updates the union with the given sketch</p>
</dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="datasketches.tuple_intersection">
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">tuple_intersection</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#datasketches.tuple_intersection" title="Link to this definition"></a></dt>
<dd><dl class="py method">
<dt class="sig sig-object py" id="datasketches.tuple_intersection.__init__">
<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">self</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">policy</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="../helper/tuple_policy.html#datasketches.TuplePolicy" title="_datasketches.TuplePolicy"><span class="pre">_datasketches.TuplePolicy</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">9001</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="headerlink" href="#datasketches.tuple_intersection.__init__" title="Link to this definition"></a></dt>
<dd><p>Creates a tuple_intersection using the provided parameters</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>policy</strong> (<a class="reference internal" href="../helper/tuple_policy.html#datasketches.TuplePolicy" title="datasketches.TuplePolicy"><em>TuplePolicy</em></a>) – a policy to use when intersecting entries</p></li>
<li><p><strong>seed</strong> (<em>int</em><em>, </em><em>optional</em>) – the seed to use when hashing values. Must match any sketch seeds</p></li>
</ul>
</dd>
</dl>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_intersection.get_result">
<span class="sig-name descname"><span class="pre">get_result</span></span><a class="headerlink" href="#datasketches.tuple_intersection.get_result" title="Link to this definition"></a></dt>
<dd><p>Returns the sketch corresponding to the intersection result</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_intersection.has_result">
<span class="sig-name descname"><span class="pre">has_result</span></span><a class="headerlink" href="#datasketches.tuple_intersection.has_result" title="Link to this definition"></a></dt>
<dd><p>Returns True if the intersection has a valid result, otherwise False</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_intersection.update">
<span class="sig-name descname"><span class="pre">update</span></span><a class="headerlink" href="#datasketches.tuple_intersection.update" title="Link to this definition"></a></dt>
<dd><p>Intersects the provided sketch with the current intersection state</p>
</dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="datasketches.tuple_a_not_b">
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">tuple_a_not_b</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#datasketches.tuple_a_not_b" title="Link to this definition"></a></dt>
<dd><dl class="py method">
<dt class="sig sig-object py" id="datasketches.tuple_a_not_b.__init__">
<span class="sig-name descname"><span class="pre">__init__</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">self</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">seed</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">9001</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="headerlink" href="#datasketches.tuple_a_not_b.__init__" title="Link to this definition"></a></dt>
<dd><p>Creates a tuple_a_not_b object</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters<span class="colon">:</span></dt>
<dd class="field-odd"><p><strong>seed</strong> (<em>int</em><em>, </em><em>optional</em>) – the seed to use when hashing values. Must match any sketch seeds.</p>
</dd>
</dl>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="datasketches.tuple_a_not_b.compute">
<span class="sig-name descname"><span class="pre">compute</span></span><a class="headerlink" href="#datasketches.tuple_a_not_b.compute" title="Link to this definition"></a></dt>
<dd><p>Returns a sketch with the result of applying the A-not-B operation on the given inputs</p>
</dd></dl>
</dd></dl>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="theta.html" class="btn btn-neutral float-left" title="Theta Sketch" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="../quantiles/index.html" class="btn btn-neutral float-right" title="Quantiles Sketches" 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>