| |
| |
| <!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>HyperLogLog (HLL) — 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="Compressed Probabilistic Counting (CPC)" href="cpc.html" /> |
| <link rel="prev" title="Distinct Counting" href="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="../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 current"><a class="current reference internal" href="#">HyperLogLog (HLL)</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="#datasketches.tgt_hll_type"><code class="docutils literal notranslate"><span class="pre">tgt_hll_type</span></code></a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.tgt_hll_type.HLL_4"><code class="docutils literal notranslate"><span class="pre">tgt_hll_type.HLL_4</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.tgt_hll_type.HLL_6"><code class="docutils literal notranslate"><span class="pre">tgt_hll_type.HLL_6</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.tgt_hll_type.HLL_8"><code class="docutils literal notranslate"><span class="pre">tgt_hll_type.HLL_8</span></code></a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="#datasketches.hll_sketch"><code class="docutils literal notranslate"><span class="pre">hll_sketch</span></code></a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.deserialize"><code class="docutils literal notranslate"><span class="pre">hll_sketch.deserialize()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.get_max_updatable_serialization_bytes"><code class="docutils literal notranslate"><span class="pre">hll_sketch.get_max_updatable_serialization_bytes()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.get_rel_err"><code class="docutils literal notranslate"><span class="pre">hll_sketch.get_rel_err()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.__init__"><code class="docutils literal notranslate"><span class="pre">hll_sketch.__init__()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.get_compact_serialization_bytes"><code class="docutils literal notranslate"><span class="pre">hll_sketch.get_compact_serialization_bytes</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.get_estimate"><code class="docutils literal notranslate"><span class="pre">hll_sketch.get_estimate</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.get_lower_bound"><code class="docutils literal notranslate"><span class="pre">hll_sketch.get_lower_bound</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.get_updatable_serialization_bytes"><code class="docutils literal notranslate"><span class="pre">hll_sketch.get_updatable_serialization_bytes</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.get_upper_bound"><code class="docutils literal notranslate"><span class="pre">hll_sketch.get_upper_bound</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.is_compact"><code class="docutils literal notranslate"><span class="pre">hll_sketch.is_compact</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.is_empty"><code class="docutils literal notranslate"><span class="pre">hll_sketch.is_empty</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.lg_config_k"><code class="docutils literal notranslate"><span class="pre">hll_sketch.lg_config_k</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.reset"><code class="docutils literal notranslate"><span class="pre">hll_sketch.reset</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.serialize_compact"><code class="docutils literal notranslate"><span class="pre">hll_sketch.serialize_compact</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.serialize_updatable"><code class="docutils literal notranslate"><span class="pre">hll_sketch.serialize_updatable</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.tgt_type"><code class="docutils literal notranslate"><span class="pre">hll_sketch.tgt_type</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.to_string"><code class="docutils literal notranslate"><span class="pre">hll_sketch.to_string</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_sketch.update"><code class="docutils literal notranslate"><span class="pre">hll_sketch.update</span></code></a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="#datasketches.hll_union"><code class="docutils literal notranslate"><span class="pre">hll_union</span></code></a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.get_rel_err"><code class="docutils literal notranslate"><span class="pre">hll_union.get_rel_err()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.__init__"><code class="docutils literal notranslate"><span class="pre">hll_union.__init__()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.get_estimate"><code class="docutils literal notranslate"><span class="pre">hll_union.get_estimate</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.get_lower_bound"><code class="docutils literal notranslate"><span class="pre">hll_union.get_lower_bound</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.get_result"><code class="docutils literal notranslate"><span class="pre">hll_union.get_result</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.get_upper_bound"><code class="docutils literal notranslate"><span class="pre">hll_union.get_upper_bound</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.is_empty"><code class="docutils literal notranslate"><span class="pre">hll_union.is_empty</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.lg_config_k"><code class="docutils literal notranslate"><span class="pre">hll_union.lg_config_k</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.reset"><code class="docutils literal notranslate"><span class="pre">hll_union.reset</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#datasketches.hll_union.update"><code class="docutils literal notranslate"><span class="pre">hll_union.update</span></code></a></li> |
| </ul> |
| </li> |
| </ul> |
| </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"><a class="reference internal" href="tuple.html">Tuple Sketch</a></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">HyperLogLog (HLL)</li> |
| <li class="wy-breadcrumbs-aside"> |
| <a href="../_sources/distinct_counting/hyper_log_log.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="hyperloglog-hll"> |
| <h1>HyperLogLog (HLL)<a class="headerlink" href="#hyperloglog-hll" title="Link to this heading"></a></h1> |
| <p>This is a high performance implementation of Phillipe Flajolet’s HLL sketch but with significantly improved error behavior.</p> |
| <p>If the ONLY use case for sketching is counting uniques and merging, the HLL sketch is a reasonable choice, although the highest performing in terms of accuracy for storage space consumed is CPC (Compressed Probabilistic Counting). For large enough counts, this HLL version (with HLL_4) can be 2 to 16 times smaller than the Theta sketch family for the same accuracy.</p> |
| <p>This implementation offers three different types of HLL sketch, each with different trade-offs with accuracy, space and performance. |
| These types are specified with the target_hll_type parameter.</p> |
| <p>In terms of accuracy, all three types, for the same lg_config_k, have the same error distribution as a function of <code class="docutils literal notranslate"><span class="pre">n</span></code>, the number of unique values fed to the sketch. |
| The configuration parameter <code class="docutils literal notranslate"><span class="pre">lg_config_k</span></code> is the log-base-2 of <code class="docutils literal notranslate"><span class="pre">k</span></code>, where <code class="docutils literal notranslate"><span class="pre">k</span></code> is the number of buckets or slots for the sketch.</p> |
| <p>During warmup, when the sketch has only received a small number of unique items (up to about 10% of <code class="docutils literal notranslate"><span class="pre">k</span></code>), this implementation leverages a new class of estimator algorithms with significantly better accuracy.</p> |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="datasketches.tgt_hll_type"> |
| <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">tgt_hll_type</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">values</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#datasketches.tgt_hll_type" title="Link to this definition"></a></dt> |
| <dd><p>Target HLL flavor</p> |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.tgt_hll_type.HLL_4"> |
| <span class="sig-name descname"><span class="pre">HLL_4</span></span><em class="property"><span class="w"> </span><span class="pre">:</span> <span class="pre">4</span> <span class="pre">bits</span> <span class="pre">per</span> <span class="pre">entry</span></em><a class="headerlink" href="#datasketches.tgt_hll_type.HLL_4" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.tgt_hll_type.HLL_6"> |
| <span class="sig-name descname"><span class="pre">HLL_6</span></span><em class="property"><span class="w"> </span><span class="pre">:</span> <span class="pre">6</span> <span class="pre">bits</span> <span class="pre">per</span> <span class="pre">entry</span></em><a class="headerlink" href="#datasketches.tgt_hll_type.HLL_6" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.tgt_hll_type.HLL_8"> |
| <span class="sig-name descname"><span class="pre">HLL_8</span></span><em class="property"><span class="w"> </span><span class="pre">:</span> <span class="pre">8</span> <span class="pre">bits</span> <span class="pre">per</span> <span class="pre">entry</span></em><a class="headerlink" href="#datasketches.tgt_hll_type.HLL_8" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="datasketches.hll_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">hll_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.hll_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.hll_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><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#datasketches.hll_sketch" title="_datasketches.hll_sketch"><span class="pre">_datasketches.hll_sketch</span></a></span></span><a class="headerlink" href="#datasketches.hll_sketch.deserialize" title="Link to this definition"></a></dt> |
| <dd><p>Reads a bytes object and returns the corresponding hll_sketch</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.get_max_updatable_serialization_bytes"> |
| <span class="sig-name descname"><span class="pre">get_max_updatable_serialization_bytes</span></span><span class="sig-paren">(</span><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></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_type</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#datasketches.tgt_hll_type" title="_datasketches.tgt_hll_type"><span class="pre">_datasketches.tgt_hll_type</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">int</span></span></span><a class="headerlink" href="#datasketches.hll_sketch.get_max_updatable_serialization_bytes" title="Link to this definition"></a></dt> |
| <dd><p>Provides a likely upper bound on serialization size for the given parameters</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.get_rel_err"> |
| <span class="sig-name descname"><span class="pre">get_rel_err</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">upper_bound</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unioned</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></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></em>, <em class="sig-param"><span class="n"><span class="pre">num_std_devs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">float</span></span></span><a class="headerlink" href="#datasketches.hll_sketch.get_rel_err" title="Link to this definition"></a></dt> |
| <dd><p>Returns the a priori relative error bound for the given parameters</p> |
| </dd></dl> |
| |
| <p class="rubric">Non-static Methods:</p> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="datasketches.hll_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">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></em>, <em class="sig-param"><span class="n"><span class="pre">tgt_type</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#datasketches.tgt_hll_type" title="_datasketches.tgt_hll_type"><span class="pre">_datasketches.tgt_hll_type</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">tgt_hll_type.HLL_8</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_max_size</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">False</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="headerlink" href="#datasketches.hll_sketch.__init__" title="Link to this definition"></a></dt> |
| <dd><p>Constructs a new HLL 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>lg_config_k</strong> (<em>int</em>) – A full sketch can hold 2^lg_config_k rows. Must be between 7 and 21, inclusive,</p></li> |
| <li><p><strong>tgt_type</strong> (<a class="reference internal" href="#datasketches.tgt_hll_type" title="_datasketches.tgt_hll_type"><em>tgt_hll_type</em></a>) – The HLL mode to use, if/when the sketch reaches estimation mode</p></li> |
| <li><p><strong>start_full_size</strong> (<em>bool</em>) – Indicates whether to start in HLL mode, keeping memory use constant (if HLL_6 or HLL_8) at the cost of much higher initial memory use. Default (and recommended) is False.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.get_compact_serialization_bytes"> |
| <span class="sig-name descname"><span class="pre">get_compact_serialization_bytes</span></span><a class="headerlink" href="#datasketches.hll_sketch.get_compact_serialization_bytes" title="Link to this definition"></a></dt> |
| <dd><p>Returns the size of the serialized sketch when compressing the exception table if HLL_4</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.get_estimate"> |
| <span class="sig-name descname"><span class="pre">get_estimate</span></span><a class="headerlink" href="#datasketches.hll_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.hll_sketch.get_lower_bound"> |
| <span class="sig-name descname"><span class="pre">get_lower_bound</span></span><a class="headerlink" href="#datasketches.hll_sketch.get_lower_bound" title="Link to this definition"></a></dt> |
| <dd><p>Returns the approximate lower error bound given the specified number of standard deviations in {1, 2, 3}</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.get_updatable_serialization_bytes"> |
| <span class="sig-name descname"><span class="pre">get_updatable_serialization_bytes</span></span><a class="headerlink" href="#datasketches.hll_sketch.get_updatable_serialization_bytes" title="Link to this definition"></a></dt> |
| <dd><p>Returns the size of the serialized sketch</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.get_upper_bound"> |
| <span class="sig-name descname"><span class="pre">get_upper_bound</span></span><a class="headerlink" href="#datasketches.hll_sketch.get_upper_bound" title="Link to this definition"></a></dt> |
| <dd><p>Returns the approximate upper error bound given the specified number of standard deviations in {1, 2, 3}</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.is_compact"> |
| <span class="sig-name descname"><span class="pre">is_compact</span></span><a class="headerlink" href="#datasketches.hll_sketch.is_compact" title="Link to this definition"></a></dt> |
| <dd><p>True if the sketch is compact, otherwise False</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.is_empty"> |
| <span class="sig-name descname"><span class="pre">is_empty</span></span><a class="headerlink" href="#datasketches.hll_sketch.is_empty" title="Link to this definition"></a></dt> |
| <dd><p>True if the sketch is empty, otherwise False</p> |
| </dd></dl> |
| |
| <dl class="py property"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.lg_config_k"> |
| <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">lg_config_k</span></span><a class="headerlink" href="#datasketches.hll_sketch.lg_config_k" title="Link to this definition"></a></dt> |
| <dd><p>Configured lg_k value for the sketch</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.reset"> |
| <span class="sig-name descname"><span class="pre">reset</span></span><a class="headerlink" href="#datasketches.hll_sketch.reset" title="Link to this definition"></a></dt> |
| <dd><p>Resets the sketch to the empty state in coupon collection mode</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.serialize_compact"> |
| <span class="sig-name descname"><span class="pre">serialize_compact</span></span><a class="headerlink" href="#datasketches.hll_sketch.serialize_compact" title="Link to this definition"></a></dt> |
| <dd><p>Serializes the sketch into a bytes object, compressing the exception table if HLL_4</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.serialize_updatable"> |
| <span class="sig-name descname"><span class="pre">serialize_updatable</span></span><a class="headerlink" href="#datasketches.hll_sketch.serialize_updatable" title="Link to this definition"></a></dt> |
| <dd><p>Serializes the sketch into a bytes object</p> |
| </dd></dl> |
| |
| <dl class="py property"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.tgt_type"> |
| <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">tgt_type</span></span><a class="headerlink" href="#datasketches.hll_sketch.tgt_type" title="Link to this definition"></a></dt> |
| <dd><p>The HLL type (4, 6, or 8) when in estimation mode</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.to_string"> |
| <span class="sig-name descname"><span class="pre">to_string</span></span><a class="headerlink" href="#datasketches.hll_sketch.to_string" title="Link to this definition"></a></dt> |
| <dd><p>Produces a string summary of the sketch</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_sketch.update"> |
| <span class="sig-name descname"><span class="pre">update</span></span><a class="headerlink" href="#datasketches.hll_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">-></span> <span class="pre">None</span></code></p></li> |
| </ol> |
| <p>Updates the sketch with the given integral 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">-></span> <span class="pre">None</span></code></p></li> |
| </ol> |
| <p>Updates the sketch with the given floating point 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">-></span> <span class="pre">None</span></code></p></li> |
| </ol> |
| <p>Updates the sketch with the given string value</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="datasketches.hll_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">hll_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.hll_union" 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.hll_union.get_rel_err"> |
| <span class="sig-name descname"><span class="pre">get_rel_err</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">upper_bound</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unioned</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></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></em>, <em class="sig-param"><span class="n"><span class="pre">num_std_devs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">float</span></span></span><a class="headerlink" href="#datasketches.hll_union.get_rel_err" title="Link to this definition"></a></dt> |
| <dd><p>Returns the a priori relative error bound for the given parameters</p> |
| </dd></dl> |
| |
| <p class="rubric">Non-static Methods:</p> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="datasketches.hll_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">lg_max_k</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">None</span></span></span><a class="headerlink" href="#datasketches.hll_union.__init__" title="Link to this definition"></a></dt> |
| <dd><p>Construct an hll_union object if the given size.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>lg_max_k</strong> (<em>int</em>) – The maximum size, in log2, of k. Must be between 7 and 21, inclusive.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_union.get_estimate"> |
| <span class="sig-name descname"><span class="pre">get_estimate</span></span><a class="headerlink" href="#datasketches.hll_union.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.hll_union.get_lower_bound"> |
| <span class="sig-name descname"><span class="pre">get_lower_bound</span></span><a class="headerlink" href="#datasketches.hll_union.get_lower_bound" title="Link to this definition"></a></dt> |
| <dd><p>Returns the approximate lower error bound given the specified number of standard deviations in {1, 2, 3}</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_union.get_result"> |
| <span class="sig-name descname"><span class="pre">get_result</span></span><a class="headerlink" href="#datasketches.hll_union.get_result" title="Link to this definition"></a></dt> |
| <dd><p>Returns a sketch of the target type representing the current union state</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_union.get_upper_bound"> |
| <span class="sig-name descname"><span class="pre">get_upper_bound</span></span><a class="headerlink" href="#datasketches.hll_union.get_upper_bound" title="Link to this definition"></a></dt> |
| <dd><p>Returns the approximate upper error bound given the specified number of standard deviations in {1, 2, 3}</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_union.is_empty"> |
| <span class="sig-name descname"><span class="pre">is_empty</span></span><a class="headerlink" href="#datasketches.hll_union.is_empty" title="Link to this definition"></a></dt> |
| <dd><p>True if the union is empty, otherwise False</p> |
| </dd></dl> |
| |
| <dl class="py property"> |
| <dt class="sig sig-object py" id="datasketches.hll_union.lg_config_k"> |
| <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">lg_config_k</span></span><a class="headerlink" href="#datasketches.hll_union.lg_config_k" title="Link to this definition"></a></dt> |
| <dd><p>Configured lg_k value for the union</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_union.reset"> |
| <span class="sig-name descname"><span class="pre">reset</span></span><a class="headerlink" href="#datasketches.hll_union.reset" title="Link to this definition"></a></dt> |
| <dd><p>Resets the union to the empty state</p> |
| </dd></dl> |
| |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="datasketches.hll_union.update"> |
| <span class="sig-name descname"><span class="pre">update</span></span><a class="headerlink" href="#datasketches.hll_union.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">sketch:</span> <span class="pre">_datasketches.hll_sketch)</span> <span class="pre">-></span> <span class="pre">None</span></code></p></li> |
| </ol> |
| <p>Updates the union with the given HLL sketch</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">int)</span> <span class="pre">-></span> <span class="pre">None</span></code></p></li> |
| </ol> |
| <p>Updates the union with the given integral 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">float)</span> <span class="pre">-></span> <span class="pre">None</span></code></p></li> |
| </ol> |
| <p>Updates the union with the given floating point value</p> |
| <ol class="arabic simple" start="4"> |
| <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">-></span> <span class="pre">None</span></code></p></li> |
| </ol> |
| <p>Updates the union with the given string value</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| </section> |
| |
| |
| </div> |
| </div> |
| <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer"> |
| <a href="index.html" class="btn btn-neutral float-left" title="Distinct Counting" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a> |
| <a href="cpc.html" class="btn btn-neutral float-right" title="Compressed Probabilistic Counting (CPC)" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a> |
| </div> |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p>© 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> |
