search_query_stats_positions.html 16.7 KB

Edit Raw Blame History

<!DOCTYPE html>
<!--
 | Generated by Apache Maven Doxia Site Renderer 1.7.1 at 2017-02-28
 | Rendered using Apache Maven Fluido Skin 1.5
-->
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <meta name="Date-Revision-yyyymmdd" content="20170228" />
    <meta http-equiv="Content-Language" content="en" />
    <title>Multi Tier Annotation Search &#x2013; Statistics - positions</title>
    <link rel="stylesheet" href="./css/apache-maven-fluido-1.5.min.css" />
    <link rel="stylesheet" href="./css/site.css" />
    <link rel="stylesheet" href="./css/print.css" media="print" />


    <script type="text/javascript" src="./js/apache-maven-fluido-1.5.min.js"></script>

                      </head>
        <body class="topBarDisabled">


        <div class="container-fluid">
          <div id="banner">
        <div class="pull-left">
                                <div id="bannerLeft">
                <h2>MTAS</h2>
                </div>
                      </div>
        <div class="pull-right">                  <a href="http://www.meertens.knaw.nl/" id="bannerRight">
                                                                                                <img src="images/meertens.png"  alt="Meertens Instituut" width="93" height="104"/>
                </a>
      </div>
        <div class="clear"><hr/></div>
      </div>

      <div id="breadcrumbs">
        <ul class="breadcrumb">

                  <li id="projectVersion">Version: 6.4.1
                          <span class="divider">|</span>
                    </li>
                              <li class="">
                    <a href="index.html" title="Mtas">
        Mtas</a>
                    <span class="divider">/</span>
      </li>
        <li class="active ">Statistics - positions</li>


                  <li id="publishDate" class="pull-right">Last Published: 2017-02-28</li>

                            </ul>
      </div>


      <div class="row-fluid">
        <div id="leftColumn" class="span2">
          <div class="well sidebar-nav">

                <ul class="nav nav-list">
                    <li class="nav-header">Mtas</li>

      <li>

                          <a href="index.html" title="Introduction">
          <span class="none"></span>
        Introduction</a>
            </li>

      <li>

                          <a href="features.html" title="Features">
          <span class="none"></span>
        Features</a>
            </li>

      <li>

                          <a href="installation.html" title="Getting started">
          <span class="icon-chevron-right"></span>
        Getting started</a>
                  </li>

      <li>

                          <a href="indexing.html" title="Indexing">
          <span class="icon-chevron-right"></span>
        Indexing</a>
                  </li>

      <li>

                          <a href="search.html" title="Search">
          <span class="icon-chevron-down"></span>
        Search</a>
                    <ul class="nav nav-list">

      <li>

                          <a href="search_configuration.html" title="Configuration">
          <span class="none"></span>
        Configuration</a>
            </li>

      <li>

                          <a href="search_query.html" title="Query">
          <span class="icon-chevron-down"></span>
        Query</a>
                    <ul class="nav nav-list">

      <li>

                          <a href="search_query_stats.html" title="Statistics">
          <span class="icon-chevron-down"></span>
        Statistics</a>
                    <ul class="nav nav-list">

      <li class="active">

            <a href="#"><span class="none"></span>Positions</a>
          </li>

      <li>

                          <a href="search_query_stats_tokens.html" title="Tokens">
          <span class="none"></span>
        Tokens</a>
            </li>

      <li>

                          <a href="search_query_stats_spans.html" title="Spans">
          <span class="none"></span>
        Spans</a>
            </li>
              </ul>
        </li>

      <li>

                          <a href="search_query_kwic_and_list.html" title="Kwic/List">
          <span class="none"></span>
        Kwic/List</a>
            </li>

      <li>

                          <a href="search_query_termvector.html" title="Termvector">
          <span class="none"></span>
        Termvector</a>
            </li>

      <li>

                          <a href="search_query_facet.html" title="Facet">
          <span class="none"></span>
        Facet</a>
            </li>

      <li>

                          <a href="search_query_group.html" title="Group">
          <span class="none"></span>
        Group</a>
            </li>

      <li>

                          <a href="search_query_prefix.html" title="Prefix">
          <span class="none"></span>
        Prefix</a>
            </li>
              </ul>
        </li>

      <li>

                          <a href="search_stats.html" title="Type of statistics">
          <span class="none"></span>
        Type of statistics</a>
            </li>

      <li>

                          <a href="search_functions.html" title="Functions">
          <span class="none"></span>
        Functions</a>
            </li>

      <li>

                          <a href="search_cql.html" title="CQL">
          <span class="none"></span>
        CQL</a>
            </li>

      <li>

                          <a href="search_sharding.html" title="Sharding">
          <span class="none"></span>
        Sharding</a>
            </li>
              </ul>
        </li>

      <li>

                          <a href="download.html" title="Download">
          <span class="none"></span>
        Download</a>
            </li>
                              <li class="nav-header">Project Documentation</li>

      <li>

                          <a href="project-info.html" title="Project Information">
          <span class="icon-chevron-right"></span>
        Project Information</a>
                  </li>

      <li>

                          <a href="project-reports.html" title="Project Reports">
          <span class="icon-chevron-right"></span>
        Project Reports</a>
                  </li>
            </ul>


          <hr />

           <div id="poweredBy">
                            <div class="clear"></div>
                            <div class="clear"></div>
                            <div class="clear"></div>
                            <div class="clear"></div>
                             <a href="http://maven.apache.org/" title="Built by Maven" class="poweredBy">
        <img class="builtBy" alt="Built by Maven" src="./images/logos/maven-feather.png" />
      </a>
                  </div>
          </div>
        </div>


        <div id="bodyColumn"  class="span10" >

            <h1>Statistics - positions</h1>
<p>To get statistics on the number of positions within a set of documents, besides the parameter to enable <a href="search_query_stats.html">statistics</a>, the following parameter should be provided.</p>

<table border="0" class="table table-striped">
  <thead>

<tr class="a">

<th>Parameter </th>

<th>Value </th>

<th>Obligatory </th>
    </tr>
  </thead>
  <tbody>

<tr class="b">

<td>mtas.stats.positions </td>

<td>true </td>

<td>yes </td>
    </tr>
  </tbody>
</table>
<p>Multiple statistics on positions can be produced within the same request. To distinguish them, a unique identifier has to be provided for<br />each of the required statistics.</p>

<table border="0" class="table table-striped">
  <thead>

<tr class="a">

<th>Parameter </th>

<th>Value </th>

<th>Info </th>

<th>Obligatory </th>
    </tr>
  </thead>
  <tbody>

<tr class="b">

<td>mtas.stats.positions.&lt;identifier&gt;.key </td>

<td>&lt;string&gt; </td>

<td>key used in response </td>

<td>no </td>
    </tr>

<tr class="a">

<td>mtas.stats.positions.&lt;identifier&gt;.field </td>

<td>&lt;string&gt; </td>

<td>mtas field </td>

<td>yes </td>
    </tr>

<tr class="b">

<td>mtas.stats.positions.&lt;identifier&gt;.type </td>

<td>&lt;string&gt; </td>

<td>required <a href="search_stats.html">type of statistics</a> </td>

<td>no </td>
    </tr>

<tr class="a">

<td>mtas.stats.positions.&lt;identifier&gt;.minimum </td>

<td>&lt;double&gt; </td>

<td>minimum number of positions </td>

<td>no </td>
    </tr>

<tr class="b">

<td>mtas.stats.positions.&lt;identifier&gt;.maximum </td>

<td>&lt;double&gt; </td>

<td>maximum number of positions </td>

<td>no </td>
    </tr>
  </tbody>
</table>
<p>The <i>key</i> is added to the response and may be used to distinguish between multiple statistics on positions, and should therefore be unique. The optional <i>minimum</i> and <i>maximum</i> can be used to focus only on documents satisfying a condition on the number of positions.</p>
<hr />
<div class="section">
<h2><a name="Examples"></a>Examples</h2>

<ol style="list-style-type: decimal">

<li><a href="#basic">Basic</a> : basic statistics on the number of positions.</li>

<li><a href="#minimum-and-maximum">Minimum and maximum</a> : statistics on the number of positions with restrictions on this number.</li>

<li><a href="#subset">Subset</a> : statistics on the number of positions within a subset of documents.</li>
</ol>
<hr />
<p><a name="basic"></a> </p>
<div class="section">
<h3><a name="Basic"></a>Basic</h3>
<p><b>Example</b><br />Total and average number of positions and the number of documents.</p>
<p><b>Request and response</b><br /><tt>q=*%3A*&amp;rows=0&amp;mtas=true&amp;mtas.stats=true&amp;mtas.stats.positions=true&amp;mtas.stats.positions.0.field=text&amp;mtas.stats.positions.0.key=example - basic&amp;mtas.stats.positions.0.type=sum,mean,n&amp;wt=json&amp;indent=true</tt></p>

<div class="source">
<div class="source"><pre class="prettyprint">&quot;mtas&quot;:{
    &quot;stats&quot;:{
      &quot;positions&quot;:[{
          &quot;key&quot;:&quot;example - basic&quot;,
          &quot;mean&quot;:163.32306296759796,
          &quot;sum&quot;:337230767,
          &quot;n&quot;:2064808}]}}
</pre></div></div>
<p><a name="minimum-and-maximum"></a></p></div>
<div class="section">
<h3><a name="Minimum_and_maximum"></a>Minimum and maximum</h3>
<p><b>Example</b><br />Full statistics on positions for documents with a minimum of 100 positions, for documents with a maximum of 200 positions, and for documents with between 100 and 200 positions.</p>
<p><b>Request and response</b><br /><tt>q=*%3A*&amp;rows=0&amp;mtas=true&amp;mtas.stats=true&amp;mtas.stats.positions=true&amp;mtas.stats.positions.0.field=text&amp;mtas.stats.positions.0.key=example - minimum&amp;mtas.stats.positions.0.type=all&amp;mtas.stats.positions.0.minimum=100&amp;mtas.stats.positions.1.field=text&amp;mtas.stats.positions.1.key=example - maximum&amp;mtas.stats.positions.1.type=all&amp;mtas.stats.positions.1.maximum=200&amp;mtas.stats.positions.2.field=text&amp;mtas.stats.positions.2.key=example - minimum and maximum&amp;mtas.stats.positions.2.type=all&amp;mtas.stats.positions.2.minimum=100&amp;mtas.stats.positions.2.maximum=200&amp;wt=json&amp;indent=true</tt></p>

<div class="source">
<div class="source"><pre class="prettyprint">&quot;mtas&quot;:{
    &quot;stats&quot;:{
      &quot;positions&quot;:[{
          &quot;key&quot;:&quot;example - minimum&quot;,
          &quot;sumsq&quot;:3.217738942941E12,
          &quot;populationvariance&quot;:4429860.598303376,
          &quot;max&quot;:419252.0,
          &quot;sum&quot;:3.03356085E8,
          &quot;kurtosis&quot;:7475.629984106579,
          &quot;standarddeviation&quot;:2104.724912671482,
          &quot;n&quot;:696551,
          &quot;quadraticmean&quot;:2149.309425767974,
          &quot;min&quot;:100.0,
          &quot;median&quot;:232.0,
          &quot;variance&quot;:4429866.9580199765,
          &quot;mean&quot;:435.5116638982477,
          &quot;geometricmean&quot;:269.08829791186866,
          &quot;sumoflogs&quot;:3897230.408057158,
          &quot;skewness&quot;:69.96996634727896},
        {
          &quot;key&quot;:&quot;example - maximum&quot;,
          &quot;sumsq&quot;:8.387258635E9,
          &quot;populationvariance&quot;:2952.9318413516844,
          &quot;max&quot;:200.0,
          &quot;sum&quot;:7.6021711E7,
          &quot;kurtosis&quot;:0.06752103336188053,
          &quot;standarddeviation&quot;:54.34090186412456,
          &quot;n&quot;:1664511,
          &quot;quadraticmean&quot;:70.98501573316724,
          &quot;min&quot;:0.0,
          &quot;median&quot;:25.0,
          &quot;variance&quot;:2952.9336154064163,
          &quot;mean&quot;:45.672098892754136,
          &quot;geometricmean&quot;:0.0,
          &quot;sumoflogs&quot;:&quot;-Infinity&quot;,
          &quot;skewness&quot;:1.055453308387049},
        {
          &quot;key&quot;:&quot;example - minimum and maximum&quot;,
          &quot;sumsq&quot;:6.242915333E9,
          &quot;populationvariance&quot;:833.0814348912809,
          &quot;max&quot;:200.0,
          &quot;sum&quot;:4.2147029E7,
          &quot;kurtosis&quot;:-1.089851452153094,
          &quot;standarddeviation&quot;:28.86319883436408,
          &quot;n&quot;:296254,
          &quot;quadraticmean&quot;:145.16489726459713,
          &quot;min&quot;:100.0,
          &quot;median&quot;:139.0,
          &quot;variance&quot;:833.084246952036,
          &quot;mean&quot;:142.2665314223605,
          &quot;geometricmean&quot;:139.38264759454245,
          &quot;sumoflogs&quot;:1462672.066002271,
          &quot;skewness&quot;:0.30992716799338843}]}}
</pre></div></div>
<p><a name="subset"></a> </p></div>
<div class="section">
<h3><a name="Subset"></a>Subset</h3>
<p><b>Example</b><br />Total and average number of positions and the number of documents for a subset of documents.</p>
<p><b>Request and response</b><br /><tt>q=text:koe&amp;rows=0&amp;mtas=true&amp;mtas.stats=true&amp;mtas.stats.positions=true&amp;mtas.stats.positions.0.field=text&amp;mtas.stats.positions.0.key=example - subset&amp;mtas.stats.positions.0.type=sum,mean,n&amp;wt=json&amp;indent=true</tt></p>

<div class="source">
<div class="source"><pre class="prettyprint">&quot;mtas&quot;:{
    &quot;stats&quot;:{
      &quot;positions&quot;:[{
          &quot;key&quot;:&quot;example - subset&quot;,
          &quot;mean&quot;:3578.5040620384048,
          &quot;sum&quot;:9690589,
          &quot;n&quot;:2708}]}}
</pre></div></div></div></div>
                  </div>
            </div>
          </div>

    <hr/>

    <footer>
            <div class="container-fluid">
                      <div class="row-fluid">
                                      <p >Copyright &copy;                    2017
                        <a href="http://www.meertens.knaw.nl/">Meertens Institute</a>.
            All rights reserved.
      </p>
                </div>


                </div>
    </footer>
        </body>
</html>