You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@madlib.apache.org by xt...@apache.org on 2016/09/20 18:31:38 UTC
[26/51] [partial] incubator-madlib-site git commit: Update doc for
1.9.1 release
http://git-wip-us.apache.org/repos/asf/incubator-madlib-site/blob/bed9253d/docs/v1.9.1/crf_8sql__in.html
----------------------------------------------------------------------
diff --git a/docs/v1.9.1/crf_8sql__in.html b/docs/v1.9.1/crf_8sql__in.html
new file mode 100644
index 0000000..450eb45
--- /dev/null
+++ b/docs/v1.9.1/crf_8sql__in.html
@@ -0,0 +1,527 @@
+<!-- HTML header for doxygen 1.8.4-->
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+<meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/>
+<meta http-equiv="X-UA-Compatible" content="IE=9"/>
+<meta name="generator" content="Doxygen 1.8.10"/>
+<meta name="keywords" content="madlib,postgres,greenplum,machine learning,data mining,deep learning,ensemble methods,data science,market basket analysis,affinity analysis,pca,lda,regression,elastic net,huber white,proportional hazards,k-means,latent dirichlet allocation,bayes,support vector machines,svm"/>
+<title>MADlib: crf.sql_in File Reference</title>
+<link href="tabs.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="jquery.js"></script>
+<script type="text/javascript" src="dynsections.js"></script>
+<link href="navtree.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="resize.js"></script>
+<script type="text/javascript" src="navtreedata.js"></script>
+<script type="text/javascript" src="navtree.js"></script>
+<script type="text/javascript">
+ $(document).ready(initResizable);
+ $(window).load(resizeHeight);
+</script>
+<link href="search/search.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="search/searchdata.js"></script>
+<script type="text/javascript" src="search/search.js"></script>
+<script type="text/javascript">
+ $(document).ready(function() { init_search(); });
+</script>
+<!-- hack in the navigation tree -->
+<script type="text/javascript" src="eigen_navtree_hacks.js"></script>
+<link href="doxygen.css" rel="stylesheet" type="text/css" />
+<link href="madlib_extra.css" rel="stylesheet" type="text/css"/>
+<!-- google analytics -->
+<script>
+ (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
+ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
+ m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
+ })(window,document,'script','//www.google-analytics.com/analytics.js','ga');
+ ga('create', 'UA-45382226-1', 'madlib.net');
+ ga('send', 'pageview');
+</script>
+</head>
+<body>
+<div id="top"><!-- do not remove this div, it is closed by doxygen! -->
+<div id="titlearea">
+<table cellspacing="0" cellpadding="0">
+ <tbody>
+ <tr style="height: 56px;">
+ <td id="projectlogo"><a href="http://madlib.net"><img alt="Logo" src="madlib.png" height="50" style="padding-left:0.5em;" border="0"/ ></a></td>
+ <td style="padding-left: 0.5em;">
+ <div id="projectname">
+ <span id="projectnumber">1.9.1</span>
+ </div>
+ <div id="projectbrief">User Documentation for MADlib</div>
+ </td>
+ <td> <div id="MSearchBox" class="MSearchBoxInactive">
+ <span class="left">
+ <img id="MSearchSelect" src="search/mag_sel.png"
+ onmouseover="return searchBox.OnSearchSelectShow()"
+ onmouseout="return searchBox.OnSearchSelectHide()"
+ alt=""/>
+ <input type="text" id="MSearchField" value="Search" accesskey="S"
+ onfocus="searchBox.OnSearchFieldFocus(true)"
+ onblur="searchBox.OnSearchFieldFocus(false)"
+ onkeyup="searchBox.OnSearchFieldChange(event)"/>
+ </span><span class="right">
+ <a id="MSearchClose" href="javascript:searchBox.CloseResultsWindow()"><img id="MSearchCloseImg" border="0" src="search/close.png" alt=""/></a>
+ </span>
+ </div>
+</td>
+ </tr>
+ </tbody>
+</table>
+</div>
+<!-- end header part -->
+<!-- Generated by Doxygen 1.8.10 -->
+<script type="text/javascript">
+var searchBox = new SearchBox("searchBox", "search",false,'Search');
+</script>
+</div><!-- top -->
+<div id="side-nav" class="ui-resizable side-nav-resizable">
+ <div id="nav-tree">
+ <div id="nav-tree-contents">
+ <div id="nav-sync" class="sync"></div>
+ </div>
+ </div>
+ <div id="splitbar" style="-moz-user-select:none;"
+ class="ui-resizable-handle">
+ </div>
+</div>
+<script type="text/javascript">
+$(document).ready(function(){initNavTree('crf_8sql__in.html','');});
+</script>
+<div id="doc-content">
+<!-- window showing the filter options -->
+<div id="MSearchSelectWindow"
+ onmouseover="return searchBox.OnSearchSelectShow()"
+ onmouseout="return searchBox.OnSearchSelectHide()"
+ onkeydown="return searchBox.OnSearchSelectKey(event)">
+</div>
+
+<!-- iframe showing the search results (closed by default) -->
+<div id="MSearchResultsWindow">
+<iframe src="javascript:void(0)" frameborder="0"
+ name="MSearchResults" id="MSearchResults">
+</iframe>
+</div>
+
+<div class="header">
+ <div class="summary">
+<a href="#func-members">Functions</a> </div>
+ <div class="headertitle">
+<div class="title">crf.sql_in File Reference</div> </div>
+</div><!--header-->
+<div class="contents">
+
+<p>SQL functions for conditional random field.
+<a href="#details">More...</a></p>
+<table class="memberdecls">
+<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="func-members"></a>
+Functions</h2></td></tr>
+<tr class="memitem:a2e7104fea95ca76587e7fae9bcb0d7ed"><td class="memItemLeft" align="right" valign="top">float8[] </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#a2e7104fea95ca76587e7fae9bcb0d7ed">lincrf_lbfgs_step_transition</a> (float8[], float8[], float8[], float8[], float8, float8, float8[])</td></tr>
+<tr class="separator:a2e7104fea95ca76587e7fae9bcb0d7ed"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a45f3eaf0c80cdfa99872cd071020d5c7"><td class="memItemLeft" align="right" valign="top">float8[] </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#a45f3eaf0c80cdfa99872cd071020d5c7">lincrf_lbfgs_step_merge_states</a> (float8[] state1, float8[] state2)</td></tr>
+<tr class="separator:a45f3eaf0c80cdfa99872cd071020d5c7"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a5bf4b2738003096f4eeeccd0eb5e98f0"><td class="memItemLeft" align="right" valign="top">float8[] </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#a5bf4b2738003096f4eeeccd0eb5e98f0">lincrf_lbfgs_step_final</a> (float8[] state)</td></tr>
+<tr class="separator:a5bf4b2738003096f4eeeccd0eb5e98f0"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a47ef6b30d54ac4ef89cb664a681d1067"><td class="memItemLeft" align="right" valign="top">float8 </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#a47ef6b30d54ac4ef89cb664a681d1067">internal_lincrf_lbfgs_converge</a> (float8[] state)</td></tr>
+<tr class="separator:a47ef6b30d54ac4ef89cb664a681d1067"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:aff63c9a56bebf501a2f40971271605c2"><td class="memItemLeft" align="right" valign="top">lincrf_result </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#aff63c9a56bebf501a2f40971271605c2">internal_lincrf_lbfgs_result</a> (float8[] state)</td></tr>
+<tr class="separator:aff63c9a56bebf501a2f40971271605c2"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a590cd748d8e18055d851e7d4f4a3ca00"><td class="memItemLeft" align="right" valign="top">aggregate float8[] </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#a590cd748d8e18055d851e7d4f4a3ca00">lincrf_lbfgs_step</a> (float8[], float8[], float8[], float8, float8, float8[])</td></tr>
+<tr class="separator:a590cd748d8e18055d851e7d4f4a3ca00"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a73693c959db4ca3dbfd1b9debcca2c8f"><td class="memItemLeft" align="right" valign="top">aggregate anyarray </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#a73693c959db4ca3dbfd1b9debcca2c8f">array_union</a> (anyarray)</td></tr>
+<tr class="separator:a73693c959db4ca3dbfd1b9debcca2c8f"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a20c096420d878cdd66dac6a232483737"><td class="memItemLeft" align="right" valign="top">integer </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#a20c096420d878cdd66dac6a232483737">compute_lincrf</a> (text source, text sparse_R, text dense_M, text sparse_M, text featureSize, integer tagSize, integer maxNumIterations)</td></tr>
+<tr class="separator:a20c096420d878cdd66dac6a232483737"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a336ac57ae3d07e331646d397c7651d3d"><td class="memItemLeft" align="right" valign="top">text </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#a336ac57ae3d07e331646d397c7651d3d">lincrf_train</a> (text train_feature_tbl, text train_featureset_tbl, text label_tbl, text crf_stats_tbl, text crf_weights_tbl, integer max_iterations)</td></tr>
+<tr class="memdesc:a336ac57ae3d07e331646d397c7651d3d"><td class="mdescLeft"> </td><td class="mdescRight">Compute linear-chain crf coefficients and diagnostic statistics. <a href="#a336ac57ae3d07e331646d397c7651d3d">More...</a><br /></td></tr>
+<tr class="separator:a336ac57ae3d07e331646d397c7651d3d"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a6b7059a5e22e40eae252c718217bf574"><td class="memItemLeft" align="right" valign="top">text </td><td class="memItemRight" valign="bottom"><a class="el" href="crf_8sql__in.html#a6b7059a5e22e40eae252c718217bf574">lincrf_train</a> (text train_feature_tbl, text train_featureset_tbl, text label_tbl, text crf_stats_tbl, text crf_weights_tbl)</td></tr>
+<tr class="separator:a6b7059a5e22e40eae252c718217bf574"><td class="memSeparator" colspan="2"> </td></tr>
+</table>
+<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
+<div class="textblock"><dl class="section date"><dt>Date</dt><dd>July 2012</dd></dl>
+<dl class="section see"><dt>See also</dt><dd>For a brief introduction to conditional random field, see the module description <a class="el" href="group__grp__crf.html">Conditional Random Field</a>. </dd></dl>
+</div><h2 class="groupheader">Function Documentation</h2>
+<a class="anchor" id="a73693c959db4ca3dbfd1b9debcca2c8f"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">aggregate anyarray array_union </td>
+ <td>(</td>
+ <td class="paramtype">anyarray </td>
+ <td class="paramname"></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="a20c096420d878cdd66dac6a232483737"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">integer compute_lincrf </td>
+ <td>(</td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>source</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>sparse_R</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>dense_M</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>sparse_M</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>featureSize</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">integer </td>
+ <td class="paramname"><em>tagSize</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">integer </td>
+ <td class="paramname"><em>maxNumIterations</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="a47ef6b30d54ac4ef89cb664a681d1067"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">float8 internal_lincrf_lbfgs_converge </td>
+ <td>(</td>
+ <td class="paramtype">float8[] </td>
+ <td class="paramname"><em>state</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="aff63c9a56bebf501a2f40971271605c2"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">lincrf_result internal_lincrf_lbfgs_result </td>
+ <td>(</td>
+ <td class="paramtype">float8[] </td>
+ <td class="paramname"><em>state</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="a590cd748d8e18055d851e7d4f4a3ca00"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">aggregate float8 [] lincrf_lbfgs_step </td>
+ <td>(</td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">[], </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">[], </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">[], </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">[] </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="a5bf4b2738003096f4eeeccd0eb5e98f0"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">float8 [] lincrf_lbfgs_step_final </td>
+ <td>(</td>
+ <td class="paramtype">float8[] </td>
+ <td class="paramname"><em>state</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="a45f3eaf0c80cdfa99872cd071020d5c7"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">float8 [] lincrf_lbfgs_step_merge_states </td>
+ <td>(</td>
+ <td class="paramtype">float8[] </td>
+ <td class="paramname"><em>state1</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8[] </td>
+ <td class="paramname"><em>state2</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="a2e7104fea95ca76587e7fae9bcb0d7ed"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">float8 [] lincrf_lbfgs_step_transition </td>
+ <td>(</td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">[], </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">[], </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">[], </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">[], </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8 </td>
+ <td class="paramname">[] </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="a336ac57ae3d07e331646d397c7651d3d"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">text lincrf_train </td>
+ <td>(</td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>train_feature_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>train_featureset_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>label_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>crf_stats_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>crf_weights_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">integer </td>
+ <td class="paramname"><em>max_iterations</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">source</td><td>Name of the source relation containing the training data </td></tr>
+ <tr><td class="paramname">sparse_R</td><td>Name of the sparse single state feature column (of type DOUBLE PRECISION[]) </td></tr>
+ <tr><td class="paramname">dense_M</td><td>Name of the dense two state feature column (of type DOUBLE PRECISION[]) </td></tr>
+ <tr><td class="paramname">sparse_M</td><td>Name of the sparse two state feature column (of type DOUBLE PRECISION[]) </td></tr>
+ <tr><td class="paramname">featureSize</td><td>Name of feature size column (of type DOUBLE PRECISION) </td></tr>
+ <tr><td class="paramname">tagSize</td><td>The number of tags in the tag set </td></tr>
+ <tr><td class="paramname">featureset</td><td>The unique feature set </td></tr>
+ <tr><td class="paramname">crf_feature</td><td>The Name of output feature table </td></tr>
+ <tr><td class="paramname">maxNumIterations</td><td>The maximum number of iterations</td></tr>
+ </table>
+ </dd>
+</dl>
+<dl class="section return"><dt>Returns</dt><dd>a composite value:<ul>
+<li><code>coef FLOAT8[]</code> - Array of coefficients, <img class="formulaInl" alt="$ \boldsymbol c $" src="form_78.png"/></li>
+<li><code>log_likelihood FLOAT8</code> - Log-likelihood <img class="formulaInl" alt="$ l(\boldsymbol c) $" src="form_79.png"/></li>
+<li><code>num_iterations INTEGER</code> - The number of iterations before the algorithm terminated <br />
+<br />
+A 'crf_feature' table is used to store all the features and corresponding weights</li>
+</ul>
+</dd></dl>
+<dl class="section note"><dt>Note</dt><dd>This function starts an iterative algorithm. It is not an aggregate function. Source and column names have to be passed as strings (due to limitations of the SQL syntax). </dd></dl>
+
+</div>
+</div>
+<a class="anchor" id="a6b7059a5e22e40eae252c718217bf574"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">text lincrf_train </td>
+ <td>(</td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>train_feature_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>train_featureset_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>label_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>crf_stats_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>crf_weights_tbl</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+</div><!-- contents -->
+</div><!-- doc-content -->
+<!-- start footer part -->
+<div id="nav-path" class="navpath"><!-- id is needed for treeview function! -->
+ <ul>
+ <li class="navelem"><a class="el" href="dir_68267d1309a1af8e8297ef4c3efbcdba.html">src</a></li><li class="navelem"><a class="el" href="dir_efbcf68973d247bbf15f9eecae7f24e3.html">ports</a></li><li class="navelem"><a class="el" href="dir_a4a48839224ef8488facbffa8a397967.html">postgres</a></li><li class="navelem"><a class="el" href="dir_dc596537ad427a4d866006d1a3e1fe29.html">modules</a></li><li class="navelem"><a class="el" href="dir_70e9abe17564e15776adcab8550c7667.html">crf</a></li><li class="navelem"><a class="el" href="crf_8sql__in.html">crf.sql_in</a></li>
+ <li class="footer">Generated on Tue Sep 20 2016 11:27:01 for MADlib by
+ <a href="http://www.doxygen.org/index.html">
+ <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.10 </li>
+ </ul>
+</div>
+</body>
+</html>
http://git-wip-us.apache.org/repos/asf/incubator-madlib-site/blob/bed9253d/docs/v1.9.1/crf__data__loader_8sql__in.html
----------------------------------------------------------------------
diff --git a/docs/v1.9.1/crf__data__loader_8sql__in.html b/docs/v1.9.1/crf__data__loader_8sql__in.html
new file mode 100644
index 0000000..a6ecdce
--- /dev/null
+++ b/docs/v1.9.1/crf__data__loader_8sql__in.html
@@ -0,0 +1,326 @@
+<!-- HTML header for doxygen 1.8.4-->
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+<meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/>
+<meta http-equiv="X-UA-Compatible" content="IE=9"/>
+<meta name="generator" content="Doxygen 1.8.10"/>
+<meta name="keywords" content="madlib,postgres,greenplum,machine learning,data mining,deep learning,ensemble methods,data science,market basket analysis,affinity analysis,pca,lda,regression,elastic net,huber white,proportional hazards,k-means,latent dirichlet allocation,bayes,support vector machines,svm"/>
+<title>MADlib: crf_data_loader.sql_in File Reference</title>
+<link href="tabs.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="jquery.js"></script>
+<script type="text/javascript" src="dynsections.js"></script>
+<link href="navtree.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="resize.js"></script>
+<script type="text/javascript" src="navtreedata.js"></script>
+<script type="text/javascript" src="navtree.js"></script>
+<script type="text/javascript">
+ $(document).ready(initResizable);
+ $(window).load(resizeHeight);
+</script>
+<link href="search/search.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="search/searchdata.js"></script>
+<script type="text/javascript" src="search/search.js"></script>
+<script type="text/javascript">
+ $(document).ready(function() { init_search(); });
+</script>
+<!-- hack in the navigation tree -->
+<script type="text/javascript" src="eigen_navtree_hacks.js"></script>
+<link href="doxygen.css" rel="stylesheet" type="text/css" />
+<link href="madlib_extra.css" rel="stylesheet" type="text/css"/>
+<!-- google analytics -->
+<script>
+ (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
+ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
+ m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
+ })(window,document,'script','//www.google-analytics.com/analytics.js','ga');
+ ga('create', 'UA-45382226-1', 'madlib.net');
+ ga('send', 'pageview');
+</script>
+</head>
+<body>
+<div id="top"><!-- do not remove this div, it is closed by doxygen! -->
+<div id="titlearea">
+<table cellspacing="0" cellpadding="0">
+ <tbody>
+ <tr style="height: 56px;">
+ <td id="projectlogo"><a href="http://madlib.net"><img alt="Logo" src="madlib.png" height="50" style="padding-left:0.5em;" border="0"/ ></a></td>
+ <td style="padding-left: 0.5em;">
+ <div id="projectname">
+ <span id="projectnumber">1.9.1</span>
+ </div>
+ <div id="projectbrief">User Documentation for MADlib</div>
+ </td>
+ <td> <div id="MSearchBox" class="MSearchBoxInactive">
+ <span class="left">
+ <img id="MSearchSelect" src="search/mag_sel.png"
+ onmouseover="return searchBox.OnSearchSelectShow()"
+ onmouseout="return searchBox.OnSearchSelectHide()"
+ alt=""/>
+ <input type="text" id="MSearchField" value="Search" accesskey="S"
+ onfocus="searchBox.OnSearchFieldFocus(true)"
+ onblur="searchBox.OnSearchFieldFocus(false)"
+ onkeyup="searchBox.OnSearchFieldChange(event)"/>
+ </span><span class="right">
+ <a id="MSearchClose" href="javascript:searchBox.CloseResultsWindow()"><img id="MSearchCloseImg" border="0" src="search/close.png" alt=""/></a>
+ </span>
+ </div>
+</td>
+ </tr>
+ </tbody>
+</table>
+</div>
+<!-- end header part -->
+<!-- Generated by Doxygen 1.8.10 -->
+<script type="text/javascript">
+var searchBox = new SearchBox("searchBox", "search",false,'Search');
+</script>
+</div><!-- top -->
+<div id="side-nav" class="ui-resizable side-nav-resizable">
+ <div id="nav-tree">
+ <div id="nav-tree-contents">
+ <div id="nav-sync" class="sync"></div>
+ </div>
+ </div>
+ <div id="splitbar" style="-moz-user-select:none;"
+ class="ui-resizable-handle">
+ </div>
+</div>
+<script type="text/javascript">
+$(document).ready(function(){initNavTree('crf__data__loader_8sql__in.html','');});
+</script>
+<div id="doc-content">
+<!-- window showing the filter options -->
+<div id="MSearchSelectWindow"
+ onmouseover="return searchBox.OnSearchSelectShow()"
+ onmouseout="return searchBox.OnSearchSelectHide()"
+ onkeydown="return searchBox.OnSearchSelectKey(event)">
+</div>
+
+<!-- iframe showing the search results (closed by default) -->
+<div id="MSearchResultsWindow">
+<iframe src="javascript:void(0)" frameborder="0"
+ name="MSearchResults" id="MSearchResults">
+</iframe>
+</div>
+
+<div class="header">
+ <div class="summary">
+<a href="#func-members">Functions</a> </div>
+ <div class="headertitle">
+<div class="title">crf_data_loader.sql_in File Reference</div> </div>
+</div><!--header-->
+<div class="contents">
+
+<p>Create database tables and import POS/NER training/testing data to the database.
+<a href="#details">More...</a></p>
+<table class="memberdecls">
+<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="func-members"></a>
+Functions</h2></td></tr>
+<tr class="memitem:aaa609ec1d1d4cff0f335fa358091d5c3"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="crf__data__loader_8sql__in.html#aaa609ec1d1d4cff0f335fa358091d5c3">crf_train_data</a> (text datapath)</td></tr>
+<tr class="separator:aaa609ec1d1d4cff0f335fa358091d5c3"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:abf2a39a0b84a5e7ae215db28b3a87f81"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="crf__data__loader_8sql__in.html#abf2a39a0b84a5e7ae215db28b3a87f81">crf_test_data</a> (text datapath)</td></tr>
+<tr class="separator:abf2a39a0b84a5e7ae215db28b3a87f81"><td class="memSeparator" colspan="2"> </td></tr>
+</table>
+<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
+<div class="textblock"><dl class="section date"><dt>Date</dt><dd>Feb. 2012 </dd></dl>
+</div><h2 class="groupheader">Function Documentation</h2>
+<a class="anchor" id="abf2a39a0b84a5e7ae215db28b3a87f81"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void crf_test_data </td>
+ <td>(</td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>datapath</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+<dl class="section user"><dt>Input</dt><dd></dd></dl>
+<ol type="1">
+<li>Prepare an input test data segment table, e.g.:</li>
+</ol>
+<ul>
+<li>CREATE TABLE test_segmenttbl (start_pos integer,doc_id integer,seg_text text, max_pos integer) <pre class="fragment">sql> select * from test_segmenttbl order by doc_id, start_pos;
+start_pos | doc_id | seg_text | max_pos
+----------+---------+--------------+-------------
+ 0 | 1 | the | 26
+ 1 | 1 | madlib | 26
+ 2 | 1 | mission | 26
+ 3 | 1 | : | 26
+ 4 | 1 | to | 26
+ 5 | 1 | foster | 26
+ 6 | 1 | widespread | 26
+ 7 | 1 | development | 26
+ 8 | 1 | of | 26
+ 9 | 1 | scalable | 26
+ 10 | 1 | analytic | 26
+ 11 | 1 | skills | 26
+ 12 | 1 | , | 26
+ 13 | 1 | by | 26
+ ...
+ 24 | 1 | open-source | 26
+ 25 | 1 | development | 26
+ 26 | 1 | . | 26
+</pre></li>
+</ul>
+<dl class="section user"><dt>Usage</dt><dd><ul>
+<li>create tables and import data to the database SELECT madlib.crf_test_data('/path/to/modeldata') </li>
+</ul>
+</dd></dl>
+
+</div>
+</div>
+<a class="anchor" id="aaa609ec1d1d4cff0f335fa358091d5c3"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void crf_train_data </td>
+ <td>(</td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>datapath</em></td><td>)</td>
+ <td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+<dl class="section user"><dt>Input</dt><dd></dd></dl>
+<ol type="1">
+<li>Prepare an input train data segment table, e.g.:</li>
+</ol>
+<ul>
+<li>CREATE TABLE train_segmenttbl (start_pos integer,doc_id integer,seg_text text, max_pos integer) <pre class="fragment">sql> select * from train_segmenttbl order by doc_id, start_pos;
+start_pos | doc_id | seg_text | max_pos
+----------+---------+--------------+-------------
+ 0 | 1 | madlib | 9
+ 1 | 1 | is | 9
+ 2 | 1 | an | 9
+ 3 | 1 | open-source | 9
+ 4 | 1 | library | 9
+ 5 | 1 | for | 9
+ 6 | 1 | scalable | 9
+ 7 | 1 | in-database | 9
+ 8 | 1 | analytics | 9
+ 9 | 1 | . | 9
+ 0 | 2 | it | 16
+ 1 | 2 | provides | 16
+ 2 | 2 |data-parallel | 16
+ 3 | 2 |implementations| 16
+ ...
+ 14 | 2 | unstructured | 16
+ 15 | 2 | data | 16
+ 16 | 2 | . | 16
+</pre></li>
+</ul>
+<ol type="1">
+<li>Prepare an input dictionary table, e.g.,:</li>
+</ol>
+<ul>
+<li>CREATE TABLE crf_dictionary (token text,token_id integer,label text,count integer,total integer) <pre class="fragment">sql> select * from crf_dictionary;
+token | label | count | total
+------------+--------+--------------
+ freefall | 11 | 1 | 1
+ policy | 11 | 2 | 2
+ measures | 12 | 1 | 1
+ commitment | 11 | 1 | 1
+ new | 6 | 1 | 1
+ speech | 11 | 1 | 1
+ 's | 16 | 2 | 2
+ reckon | 30 | 1 | 1
+ underlying | 28 | 1 | 1
+ ...
+</pre></li>
+</ul>
+<ol type="1">
+<li>Prepare an input label table, e.g.,:</li>
+</ol>
+<ul>
+<li>CREATE TABLE labeltbl (id integer,label character varying) <pre class="fragment">sql> select * from labeltbl order by id;
+id | label
+------------+--------
+ 0 | CC
+ 1 | CD
+ 2 | DT
+ 3 | EX
+ 4 | FW
+ 5 | IN
+ 6 | JJ
+...
+ 42 | ,
+ 43 | .
+ 44 | :
+</pre></li>
+</ul>
+<ol type="1">
+<li>Prepare an input regex table, e.g.,:</li>
+</ol>
+<ul>
+<li>CREATE TABLE crf_regex (pattern text,name text) <pre class="fragment">sql> select * from crf_regex;
+pattern | name
+------------- +---------------
+^[A-Z][a-z]+$ | InitCapital%
+ ^[A-Z]+$ | isAllCapital%
+ ^.*[0-9]+.*$ | containsDigit%
+ ^.+[.]$ | endsWithDot%
+ ^.+[,]$ | endsWithComma%
+ ^.+er$ | endsWithER%
+ ^.+est$ | endsWithEst%
+ ^.+ed$ | endsWithED%
+...
+</pre></li>
+</ul>
+<ol type="1">
+<li>Prepare an input feature table, e.g.,:</li>
+</ol>
+<ul>
+<li>CREATE TABLE featuretbl (id integer,name text,prev_label_id integer,label_id integer,weight float) <pre class="fragment">sql> select * from featuretbl order by id;
+id | name | prev_label_id | label_id | weight
+-------------------------------------------------------
+1 | W_chancellor | -1 | 13 | 2.2322
+2 | E.13 | 13 | 5 | 2.3995
+3 | U | -1 | 5 | 1.2164
+4 | W_of | -1 | 5 | 2.8744
+5 | E.5 | 5 | 2 | 3.7716
+6 | W_the | -1 | 2 | 4.1790
+7 | E.2 | 2 | 13 | 0.8957
+...
+</pre></li>
+</ul>
+<ol type="1">
+<li>Prepare an crf feature set table, e.g.,:</li>
+</ol>
+<ul>
+<li>CREATE TABLE madlib.crf_feature_dic(f_index integer, f_name text, feature integer[]) <pre class="fragment">sql> select * from crf_feature_dic order by id;
+f_index| f_name | feature
+--------------------------------
+0 | W_chancellor | -1
+1 | E.13 | 13
+2 | U | -1
+3 | W_of | -1
+4 | E.5 | 5
+5 | W_the | -1
+...
+</pre></li>
+</ul>
+<dl class="section user"><dt>Usage</dt><dd><ul>
+<li>create tables and import data to the database SELECT madlib.crf_train_data('/path/to/modeldata') </li>
+</ul>
+</dd></dl>
+
+</div>
+</div>
+</div><!-- contents -->
+</div><!-- doc-content -->
+<!-- start footer part -->
+<div id="nav-path" class="navpath"><!-- id is needed for treeview function! -->
+ <ul>
+ <li class="navelem"><a class="el" href="dir_68267d1309a1af8e8297ef4c3efbcdba.html">src</a></li><li class="navelem"><a class="el" href="dir_efbcf68973d247bbf15f9eecae7f24e3.html">ports</a></li><li class="navelem"><a class="el" href="dir_a4a48839224ef8488facbffa8a397967.html">postgres</a></li><li class="navelem"><a class="el" href="dir_dc596537ad427a4d866006d1a3e1fe29.html">modules</a></li><li class="navelem"><a class="el" href="dir_70e9abe17564e15776adcab8550c7667.html">crf</a></li><li class="navelem"><a class="el" href="crf__data__loader_8sql__in.html">crf_data_loader.sql_in</a></li>
+ <li class="footer">Generated on Tue Sep 20 2016 11:27:01 for MADlib by
+ <a href="http://www.doxygen.org/index.html">
+ <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.10 </li>
+ </ul>
+</div>
+</body>
+</html>
http://git-wip-us.apache.org/repos/asf/incubator-madlib-site/blob/bed9253d/docs/v1.9.1/crf__feature__gen_8sql__in.html
----------------------------------------------------------------------
diff --git a/docs/v1.9.1/crf__feature__gen_8sql__in.html b/docs/v1.9.1/crf__feature__gen_8sql__in.html
new file mode 100644
index 0000000..49ff13c
--- /dev/null
+++ b/docs/v1.9.1/crf__feature__gen_8sql__in.html
@@ -0,0 +1,289 @@
+<!-- HTML header for doxygen 1.8.4-->
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+<meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/>
+<meta http-equiv="X-UA-Compatible" content="IE=9"/>
+<meta name="generator" content="Doxygen 1.8.10"/>
+<meta name="keywords" content="madlib,postgres,greenplum,machine learning,data mining,deep learning,ensemble methods,data science,market basket analysis,affinity analysis,pca,lda,regression,elastic net,huber white,proportional hazards,k-means,latent dirichlet allocation,bayes,support vector machines,svm"/>
+<title>MADlib: crf_feature_gen.sql_in File Reference</title>
+<link href="tabs.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="jquery.js"></script>
+<script type="text/javascript" src="dynsections.js"></script>
+<link href="navtree.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="resize.js"></script>
+<script type="text/javascript" src="navtreedata.js"></script>
+<script type="text/javascript" src="navtree.js"></script>
+<script type="text/javascript">
+ $(document).ready(initResizable);
+ $(window).load(resizeHeight);
+</script>
+<link href="search/search.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="search/searchdata.js"></script>
+<script type="text/javascript" src="search/search.js"></script>
+<script type="text/javascript">
+ $(document).ready(function() { init_search(); });
+</script>
+<!-- hack in the navigation tree -->
+<script type="text/javascript" src="eigen_navtree_hacks.js"></script>
+<link href="doxygen.css" rel="stylesheet" type="text/css" />
+<link href="madlib_extra.css" rel="stylesheet" type="text/css"/>
+<!-- google analytics -->
+<script>
+ (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
+ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
+ m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
+ })(window,document,'script','//www.google-analytics.com/analytics.js','ga');
+ ga('create', 'UA-45382226-1', 'madlib.net');
+ ga('send', 'pageview');
+</script>
+</head>
+<body>
+<div id="top"><!-- do not remove this div, it is closed by doxygen! -->
+<div id="titlearea">
+<table cellspacing="0" cellpadding="0">
+ <tbody>
+ <tr style="height: 56px;">
+ <td id="projectlogo"><a href="http://madlib.net"><img alt="Logo" src="madlib.png" height="50" style="padding-left:0.5em;" border="0"/ ></a></td>
+ <td style="padding-left: 0.5em;">
+ <div id="projectname">
+ <span id="projectnumber">1.9.1</span>
+ </div>
+ <div id="projectbrief">User Documentation for MADlib</div>
+ </td>
+ <td> <div id="MSearchBox" class="MSearchBoxInactive">
+ <span class="left">
+ <img id="MSearchSelect" src="search/mag_sel.png"
+ onmouseover="return searchBox.OnSearchSelectShow()"
+ onmouseout="return searchBox.OnSearchSelectHide()"
+ alt=""/>
+ <input type="text" id="MSearchField" value="Search" accesskey="S"
+ onfocus="searchBox.OnSearchFieldFocus(true)"
+ onblur="searchBox.OnSearchFieldFocus(false)"
+ onkeyup="searchBox.OnSearchFieldChange(event)"/>
+ </span><span class="right">
+ <a id="MSearchClose" href="javascript:searchBox.CloseResultsWindow()"><img id="MSearchCloseImg" border="0" src="search/close.png" alt=""/></a>
+ </span>
+ </div>
+</td>
+ </tr>
+ </tbody>
+</table>
+</div>
+<!-- end header part -->
+<!-- Generated by Doxygen 1.8.10 -->
+<script type="text/javascript">
+var searchBox = new SearchBox("searchBox", "search",false,'Search');
+</script>
+</div><!-- top -->
+<div id="side-nav" class="ui-resizable side-nav-resizable">
+ <div id="nav-tree">
+ <div id="nav-tree-contents">
+ <div id="nav-sync" class="sync"></div>
+ </div>
+ </div>
+ <div id="splitbar" style="-moz-user-select:none;"
+ class="ui-resizable-handle">
+ </div>
+</div>
+<script type="text/javascript">
+$(document).ready(function(){initNavTree('crf__feature__gen_8sql__in.html','');});
+</script>
+<div id="doc-content">
+<!-- window showing the filter options -->
+<div id="MSearchSelectWindow"
+ onmouseover="return searchBox.OnSearchSelectShow()"
+ onmouseout="return searchBox.OnSearchSelectHide()"
+ onkeydown="return searchBox.OnSearchSelectKey(event)">
+</div>
+
+<!-- iframe showing the search results (closed by default) -->
+<div id="MSearchResultsWindow">
+<iframe src="javascript:void(0)" frameborder="0"
+ name="MSearchResults" id="MSearchResults">
+</iframe>
+</div>
+
+<div class="header">
+ <div class="summary">
+<a href="#func-members">Functions</a> </div>
+ <div class="headertitle">
+<div class="title">crf_feature_gen.sql_in File Reference</div> </div>
+</div><!--header-->
+<div class="contents">
+
+<p>SQL function for POS/NER feature extraction.
+<a href="#details">More...</a></p>
+<table class="memberdecls">
+<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="func-members"></a>
+Functions</h2></td></tr>
+<tr class="memitem:a3548bd640c2af456f3755cb24b913ebd"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="crf__feature__gen_8sql__in.html#a3548bd640c2af456f3755cb24b913ebd">crf_train_fgen</a> (text train_segment_tbl, text regex_tbl, text label_tbl, text dictionary_tbl, text train_feature_tbl, text train_featureset_tbl)</td></tr>
+<tr class="memdesc:a3548bd640c2af456f3755cb24b913ebd"><td class="mdescLeft"> </td><td class="mdescRight">This function extracts POS/NER features from the training data. <a href="#a3548bd640c2af456f3755cb24b913ebd">More...</a><br /></td></tr>
+<tr class="separator:a3548bd640c2af456f3755cb24b913ebd"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ad9af2c3d1a4f1c937795634ca297dede"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="crf__feature__gen_8sql__in.html#ad9af2c3d1a4f1c937795634ca297dede">crf_test_fgen</a> (text test_segment_tbl, text dictionary_tbl, text label_tbl, text regex_tbl, text crf_weights_tbl, text viterbi_mtbl, text viterbi_rtbl)</td></tr>
+<tr class="memdesc:ad9af2c3d1a4f1c937795634ca297dede"><td class="mdescLeft"> </td><td class="mdescRight">This function extracts POS/NER features from the testing data. <a href="#ad9af2c3d1a4f1c937795634ca297dede">More...</a><br /></td></tr>
+<tr class="separator:ad9af2c3d1a4f1c937795634ca297dede"><td class="memSeparator" colspan="2"> </td></tr>
+</table>
+<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
+<div class="textblock"><dl class="section date"><dt>Date</dt><dd>February 2012</dd></dl>
+<dl class="section see"><dt>See also</dt><dd>For an introduction to POS/NER feature extraction, see the module description <a class="el" href="group__grp__crf.html">Conditional Random Field</a> </dd></dl>
+</div><h2 class="groupheader">Function Documentation</h2>
+<a class="anchor" id="ad9af2c3d1a4f1c937795634ca297dede"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void crf_test_fgen </td>
+ <td>(</td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>test_segment_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>dictionary_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>label_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>regex_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>crf_weights_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>viterbi_mtbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>viterbi_rtbl</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+<p>This feature extraction function will produce two factor tables, "m table" (<em>viterbi_mtbl</em>) and "r table" (<em>viterbi_rtbl</em>). The <em>viterbi_mtbl</em> table and <em>viterbi_rtbl</em> table are used to calculate the best label sequence for each sentence.</p>
+<ul>
+<li><em>viterbi_mtbl</em> table encodes the edge features which are solely dependent on upon current label and previous y value. The m table has three columns which are prev_label, label, and value respectively. If the number of labels in <img class="formulaInl" alt="$ n $" src="form_10.png"/>, then the m factor table will <img class="formulaInl" alt="$ n^2 $" src="form_80.png"/> rows. Each row encodes the transition feature weight value from the previous label to the current label.</li>
+</ul>
+<p><em>startFeature</em> is considered as a special edge feature which is from the beginning to the first token. Likewise, <em>endFeature</em> can be considered as a special edge feature which is from the last token to the very end. So m table encodes the edgeFeature, startFeature, and endFeature. If the total number of labels in the label space is 45 from 0 to 44, then the m factor array is as follows: </p><pre>
+ 0 1 2 3 4 5...44
+startFeature -1 a a a a a a...a
+edgeFeature 0 a a a a a a...a
+edgeFeature 1 a a a a a a...a
+...
+edgeFeature 44 a a a a a a...a
+endFeature 45 a a a a a a...a</pre><ul>
+<li>viterbi_r table is related to specific tokens. It encodes the single state features, e.g., wordFeature, RegexFeature for all tokens. The r table is represented in the following way. <pre>
+ 0 1 2 3 4...44
+token1 a a a a a...a
+token2 a a a a a...a</pre></li>
+</ul>
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">test_segment_tbl</td><td>Name of table containing all the tokenized testing sentences. </td></tr>
+ <tr><td class="paramname">dictionary_tbl</td><td>Name of table containing the dictionary_tbl. </td></tr>
+ <tr><td class="paramname">label_tbl</td><td>Name of table containing the the label space used in POS or other NLP tasks. </td></tr>
+ <tr><td class="paramname">regex_tbl</td><td>Name of table containing all the regular expressions to capture regex features. </td></tr>
+ <tr><td class="paramname">crf_weights_tbl</td><td>Name of the table containing featureset weights. </td></tr>
+ <tr><td class="paramname">viterbi_mtbl</td><td>Name of table to store the m factors. </td></tr>
+ <tr><td class="paramname">viterbi_rtbl</td><td>Name of table to store the r factors. </td></tr>
+ </table>
+ </dd>
+</dl>
+
+</div>
+</div>
+<a class="anchor" id="a3548bd640c2af456f3755cb24b913ebd"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void crf_train_fgen </td>
+ <td>(</td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>train_segment_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>regex_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>label_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>dictionary_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>train_feature_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">text </td>
+ <td class="paramname"><em>train_featureset_tbl</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">train_segment_tbl</td><td>Name of table containing all the tokenized training sentences. </td></tr>
+ <tr><td class="paramname">regex_tbl</td><td>Name of table containing all the regular expressions to capture regex features. </td></tr>
+ <tr><td class="paramname">label_tbl</td><td>Name of the label table containing unique ids and label names. </td></tr>
+ <tr><td class="paramname">dictionary_tbl</td><td>Name of table containing the dictionary_tbl. </td></tr>
+ <tr><td class="paramname">train_feature_tbl</td><td>features generated from the traning dataset </td></tr>
+ <tr><td class="paramname">train_featureset_tbl</td><td>unique feature set generated from the training dataset </td></tr>
+ </table>
+ </dd>
+</dl>
+
+</div>
+</div>
+</div><!-- contents -->
+</div><!-- doc-content -->
+<!-- start footer part -->
+<div id="nav-path" class="navpath"><!-- id is needed for treeview function! -->
+ <ul>
+ <li class="navelem"><a class="el" href="dir_68267d1309a1af8e8297ef4c3efbcdba.html">src</a></li><li class="navelem"><a class="el" href="dir_efbcf68973d247bbf15f9eecae7f24e3.html">ports</a></li><li class="navelem"><a class="el" href="dir_a4a48839224ef8488facbffa8a397967.html">postgres</a></li><li class="navelem"><a class="el" href="dir_dc596537ad427a4d866006d1a3e1fe29.html">modules</a></li><li class="navelem"><a class="el" href="dir_70e9abe17564e15776adcab8550c7667.html">crf</a></li><li class="navelem"><a class="el" href="crf__feature__gen_8sql__in.html">crf_feature_gen.sql_in</a></li>
+ <li class="footer">Generated on Tue Sep 20 2016 11:27:01 for MADlib by
+ <a href="http://www.doxygen.org/index.html">
+ <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.10 </li>
+ </ul>
+</div>
+</body>
+</html>
http://git-wip-us.apache.org/repos/asf/incubator-madlib-site/blob/bed9253d/docs/v1.9.1/cross__validation_8sql__in.html
----------------------------------------------------------------------
diff --git a/docs/v1.9.1/cross__validation_8sql__in.html b/docs/v1.9.1/cross__validation_8sql__in.html
new file mode 100644
index 0000000..0a05399
--- /dev/null
+++ b/docs/v1.9.1/cross__validation_8sql__in.html
@@ -0,0 +1,687 @@
+<!-- HTML header for doxygen 1.8.4-->
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+<meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/>
+<meta http-equiv="X-UA-Compatible" content="IE=9"/>
+<meta name="generator" content="Doxygen 1.8.10"/>
+<meta name="keywords" content="madlib,postgres,greenplum,machine learning,data mining,deep learning,ensemble methods,data science,market basket analysis,affinity analysis,pca,lda,regression,elastic net,huber white,proportional hazards,k-means,latent dirichlet allocation,bayes,support vector machines,svm"/>
+<title>MADlib: cross_validation.sql_in File Reference</title>
+<link href="tabs.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="jquery.js"></script>
+<script type="text/javascript" src="dynsections.js"></script>
+<link href="navtree.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="resize.js"></script>
+<script type="text/javascript" src="navtreedata.js"></script>
+<script type="text/javascript" src="navtree.js"></script>
+<script type="text/javascript">
+ $(document).ready(initResizable);
+ $(window).load(resizeHeight);
+</script>
+<link href="search/search.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="search/searchdata.js"></script>
+<script type="text/javascript" src="search/search.js"></script>
+<script type="text/javascript">
+ $(document).ready(function() { init_search(); });
+</script>
+<!-- hack in the navigation tree -->
+<script type="text/javascript" src="eigen_navtree_hacks.js"></script>
+<link href="doxygen.css" rel="stylesheet" type="text/css" />
+<link href="madlib_extra.css" rel="stylesheet" type="text/css"/>
+<!-- google analytics -->
+<script>
+ (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
+ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
+ m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
+ })(window,document,'script','//www.google-analytics.com/analytics.js','ga');
+ ga('create', 'UA-45382226-1', 'madlib.net');
+ ga('send', 'pageview');
+</script>
+</head>
+<body>
+<div id="top"><!-- do not remove this div, it is closed by doxygen! -->
+<div id="titlearea">
+<table cellspacing="0" cellpadding="0">
+ <tbody>
+ <tr style="height: 56px;">
+ <td id="projectlogo"><a href="http://madlib.net"><img alt="Logo" src="madlib.png" height="50" style="padding-left:0.5em;" border="0"/ ></a></td>
+ <td style="padding-left: 0.5em;">
+ <div id="projectname">
+ <span id="projectnumber">1.9.1</span>
+ </div>
+ <div id="projectbrief">User Documentation for MADlib</div>
+ </td>
+ <td> <div id="MSearchBox" class="MSearchBoxInactive">
+ <span class="left">
+ <img id="MSearchSelect" src="search/mag_sel.png"
+ onmouseover="return searchBox.OnSearchSelectShow()"
+ onmouseout="return searchBox.OnSearchSelectHide()"
+ alt=""/>
+ <input type="text" id="MSearchField" value="Search" accesskey="S"
+ onfocus="searchBox.OnSearchFieldFocus(true)"
+ onblur="searchBox.OnSearchFieldFocus(false)"
+ onkeyup="searchBox.OnSearchFieldChange(event)"/>
+ </span><span class="right">
+ <a id="MSearchClose" href="javascript:searchBox.CloseResultsWindow()"><img id="MSearchCloseImg" border="0" src="search/close.png" alt=""/></a>
+ </span>
+ </div>
+</td>
+ </tr>
+ </tbody>
+</table>
+</div>
+<!-- end header part -->
+<!-- Generated by Doxygen 1.8.10 -->
+<script type="text/javascript">
+var searchBox = new SearchBox("searchBox", "search",false,'Search');
+</script>
+</div><!-- top -->
+<div id="side-nav" class="ui-resizable side-nav-resizable">
+ <div id="nav-tree">
+ <div id="nav-tree-contents">
+ <div id="nav-sync" class="sync"></div>
+ </div>
+ </div>
+ <div id="splitbar" style="-moz-user-select:none;"
+ class="ui-resizable-handle">
+ </div>
+</div>
+<script type="text/javascript">
+$(document).ready(function(){initNavTree('cross__validation_8sql__in.html','');});
+</script>
+<div id="doc-content">
+<!-- window showing the filter options -->
+<div id="MSearchSelectWindow"
+ onmouseover="return searchBox.OnSearchSelectShow()"
+ onmouseout="return searchBox.OnSearchSelectHide()"
+ onkeydown="return searchBox.OnSearchSelectKey(event)">
+</div>
+
+<!-- iframe showing the search results (closed by default) -->
+<div id="MSearchResultsWindow">
+<iframe src="javascript:void(0)" frameborder="0"
+ name="MSearchResults" id="MSearchResults">
+</iframe>
+</div>
+
+<div class="header">
+ <div class="summary">
+<a href="#func-members">Functions</a> </div>
+ <div class="headertitle">
+<div class="title">cross_validation.sql_in File Reference</div> </div>
+</div><!--header-->
+<div class="contents">
+
+<p>SQL functions for cross validation.
+<a href="#details">More...</a></p>
+<table class="memberdecls">
+<tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="func-members"></a>
+Functions</h2></td></tr>
+<tr class="memitem:a2a7791b05f51e8748ab7b6ccf328a7e2"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="cross__validation_8sql__in.html#a2a7791b05f51e8748ab7b6ccf328a7e2">cross_validation_general</a> (varchar modelling_func, varchar[] modelling_params, varchar[] modelling_params_type, varchar param_explored, varchar[] explore_values, varchar predict_func, varchar[] predict_params, varchar[] predict_params_type, varchar metric_func, varchar[] metric_params, varchar[] metric_params_type, varchar data_tbl, varchar data_id, boolean id_is_random, varchar validation_result, varchar[] data_cols, integer n_folds)</td></tr>
+<tr class="separator:a2a7791b05f51e8748ab7b6ccf328a7e2"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a5efbb27898e99f7685816d9d5dfd082c"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="cross__validation_8sql__in.html#a5efbb27898e99f7685816d9d5dfd082c">cross_validation_general</a> (varchar modelling_func, varchar[] modelling_params, varchar[] modelling_params_type, varchar param_explored, varchar[] explore_values, varchar predict_func, varchar[] predict_params, varchar[] predict_params_type, varchar metric_func, varchar[] metric_params, varchar[] metric_params_type, varchar data_tbl, varchar data_id, boolean id_is_random, varchar validation_result, varchar[] data_cols)</td></tr>
+<tr class="separator:a5efbb27898e99f7685816d9d5dfd082c"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:aa151eb3fa9acc7f4cc33236e22ad4362"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="cross__validation_8sql__in.html#aa151eb3fa9acc7f4cc33236e22ad4362">cv_linregr_train</a> (varchar tbl_source, varchar col_ind_var, varchar col_dep_var, varchar tbl_result)</td></tr>
+<tr class="memdesc:aa151eb3fa9acc7f4cc33236e22ad4362"><td class="mdescLeft"> </td><td class="mdescRight">A wrapper for linear regression. <a href="#aa151eb3fa9acc7f4cc33236e22ad4362">More...</a><br /></td></tr>
+<tr class="separator:aa151eb3fa9acc7f4cc33236e22ad4362"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:aa572f1f57c0dd106b30948928161d8cc"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="cross__validation_8sql__in.html#aa572f1f57c0dd106b30948928161d8cc">cv_linregr_predict</a> (varchar tbl_model, varchar tbl_newdata, varchar col_ind_var, varchar col_id, varchar tbl_predict)</td></tr>
+<tr class="memdesc:aa572f1f57c0dd106b30948928161d8cc"><td class="mdescLeft"> </td><td class="mdescRight">A wrapper for linear regression prediction. <a href="#aa572f1f57c0dd106b30948928161d8cc">More...</a><br /></td></tr>
+<tr class="separator:aa572f1f57c0dd106b30948928161d8cc"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a2cd71e756f90b0c4fa46f508a1ca261e"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="cross__validation_8sql__in.html#a2cd71e756f90b0c4fa46f508a1ca261e">mse_error</a> (varchar tbl_prediction, varchar tbl_actual, varchar id_actual, varchar values_actual, varchar tbl_error)</td></tr>
+<tr class="separator:a2cd71e756f90b0c4fa46f508a1ca261e"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ad01cd1c97ae1be0ac7cd6c42abb75bb2"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="cross__validation_8sql__in.html#ad01cd1c97ae1be0ac7cd6c42abb75bb2">misclassification_avg</a> (varchar tbl_prediction, varchar tbl_actual, varchar id_actual, varchar values_actual, varchar tbl_error)</td></tr>
+<tr class="separator:ad01cd1c97ae1be0ac7cd6c42abb75bb2"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ac7dbc115f0c4624ccbf62b2d5494388d"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="cross__validation_8sql__in.html#ac7dbc115f0c4624ccbf62b2d5494388d">cv_logregr_predict</a> (varchar tbl_model, varchar tbl_newdata, varchar col_ind_var, varchar col_id, varchar tbl_predict)</td></tr>
+<tr class="memdesc:ac7dbc115f0c4624ccbf62b2d5494388d"><td class="mdescLeft"> </td><td class="mdescRight">A prediction function for logistic regression The result is stored in the table of tbl_predict. <a href="#ac7dbc115f0c4624ccbf62b2d5494388d">More...</a><br /></td></tr>
+<tr class="separator:ac7dbc115f0c4624ccbf62b2d5494388d"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a2d1571ffa794176a5dfed9d35e70fed7"><td class="memItemLeft" align="right" valign="top">integer </td><td class="memItemRight" valign="bottom"><a class="el" href="cross__validation_8sql__in.html#a2d1571ffa794176a5dfed9d35e70fed7">logregr_accuracy</a> (float8[] coef, float8[] col_ind, boolean col_dep)</td></tr>
+<tr class="memdesc:a2d1571ffa794176a5dfed9d35e70fed7"><td class="mdescLeft"> </td><td class="mdescRight">Metric function for logistic regression. <a href="#a2d1571ffa794176a5dfed9d35e70fed7">More...</a><br /></td></tr>
+<tr class="separator:a2d1571ffa794176a5dfed9d35e70fed7"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ac1b5c57473ff672af45191c8d53f46ed"><td class="memItemLeft" align="right" valign="top">void </td><td class="memItemRight" valign="bottom"><a class="el" href="cross__validation_8sql__in.html#ac1b5c57473ff672af45191c8d53f46ed">cv_logregr_accuracy</a> (varchar tbl_predict, varchar tbl_source, varchar col_id, varchar col_dep_var, varchar tbl_accuracy)</td></tr>
+<tr class="memdesc:ac1b5c57473ff672af45191c8d53f46ed"><td class="mdescLeft"> </td><td class="mdescRight">Metric function for logistic regression. <a href="#ac1b5c57473ff672af45191c8d53f46ed">More...</a><br /></td></tr>
+<tr class="separator:ac1b5c57473ff672af45191c8d53f46ed"><td class="memSeparator" colspan="2"> </td></tr>
+</table>
+<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
+<div class="textblock"><dl class="section date"><dt>Date</dt><dd>January 2011</dd></dl>
+<dl class="section see"><dt>See also</dt><dd>For a brief introduction to the usage of cross validation, see the module description <a class="el" href="group__grp__validation.html">Cross Validation</a>. </dd></dl>
+</div><h2 class="groupheader">Function Documentation</h2>
+<a class="anchor" id="a2a7791b05f51e8748ab7b6ccf328a7e2"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void cross_validation_general </td>
+ <td>(</td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>modelling_func</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>modelling_params</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>modelling_params_type</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>param_explored</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>explore_values</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>predict_func</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>predict_params</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>predict_params_type</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>metric_func</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>metric_params</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>metric_params_type</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>data_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>data_id</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">boolean </td>
+ <td class="paramname"><em>id_is_random</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>validation_result</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>data_cols</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">integer </td>
+ <td class="paramname"><em>n_folds</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="a5efbb27898e99f7685816d9d5dfd082c"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void cross_validation_general </td>
+ <td>(</td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>modelling_func</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>modelling_params</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>modelling_params_type</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>param_explored</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>explore_values</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>predict_func</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>predict_params</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>predict_params_type</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>metric_func</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>metric_params</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>metric_params_type</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>data_tbl</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>data_id</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">boolean </td>
+ <td class="paramname"><em>id_is_random</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>validation_result</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar[] </td>
+ <td class="paramname"><em>data_cols</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="aa572f1f57c0dd106b30948928161d8cc"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void cv_linregr_predict </td>
+ <td>(</td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_model</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_newdata</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>col_ind_var</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>col_id</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_predict</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="aa151eb3fa9acc7f4cc33236e22ad4362"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void cv_linregr_train </td>
+ <td>(</td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_source</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>col_ind_var</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>col_dep_var</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_result</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="ac1b5c57473ff672af45191c8d53f46ed"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void cv_logregr_accuracy </td>
+ <td>(</td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_predict</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_source</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>col_id</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>col_dep_var</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_accuracy</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+<p>It computes the percentage of correct predictions. The result is stored in the table of tbl_accuracy </p>
+
+</div>
+</div>
+<a class="anchor" id="ac7dbc115f0c4624ccbf62b2d5494388d"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void cv_logregr_predict </td>
+ <td>(</td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_model</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_newdata</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>col_ind_var</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>col_id</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_predict</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+<p>This function can be used together with cross-validation </p>
+
+</div>
+</div>
+<a class="anchor" id="a2d1571ffa794176a5dfed9d35e70fed7"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">integer logregr_accuracy </td>
+ <td>(</td>
+ <td class="paramtype">float8[] </td>
+ <td class="paramname"><em>coef</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">float8[] </td>
+ <td class="paramname"><em>col_ind</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">boolean </td>
+ <td class="paramname"><em>col_dep</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+<dl class="params"><dt>Parameters</dt><dd>
+ <table class="params">
+ <tr><td class="paramname">coef</td><td>Logistic fitting coefficients. Note: MADlib logregr_train function, unlike elastic_net, does not produce a separate intercept term. </td></tr>
+ <tr><td class="paramname">col_ind</td><td>Independent variable, an array </td></tr>
+ <tr><td class="paramname">col_dep</td><td>Dependent variable</td></tr>
+ </table>
+ </dd>
+</dl>
+<p>returns 1 if the prediction is the same as col_dep, otherwise 0 </p>
+
+</div>
+</div>
+<a class="anchor" id="ad01cd1c97ae1be0ac7cd6c42abb75bb2"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void misclassification_avg </td>
+ <td>(</td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_prediction</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_actual</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>id_actual</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>values_actual</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_error</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+<a class="anchor" id="a2cd71e756f90b0c4fa46f508a1ca261e"></a>
+<div class="memitem">
+<div class="memproto">
+ <table class="memname">
+ <tr>
+ <td class="memname">void mse_error </td>
+ <td>(</td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_prediction</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_actual</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>id_actual</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>values_actual</em>, </td>
+ </tr>
+ <tr>
+ <td class="paramkey"></td>
+ <td></td>
+ <td class="paramtype">varchar </td>
+ <td class="paramname"><em>tbl_error</em> </td>
+ </tr>
+ <tr>
+ <td></td>
+ <td>)</td>
+ <td></td><td></td>
+ </tr>
+ </table>
+</div><div class="memdoc">
+
+</div>
+</div>
+</div><!-- contents -->
+</div><!-- doc-content -->
+<!-- start footer part -->
+<div id="nav-path" class="navpath"><!-- id is needed for treeview function! -->
+ <ul>
+ <li class="navelem"><a class="el" href="dir_68267d1309a1af8e8297ef4c3efbcdba.html">src</a></li><li class="navelem"><a class="el" href="dir_efbcf68973d247bbf15f9eecae7f24e3.html">ports</a></li><li class="navelem"><a class="el" href="dir_a4a48839224ef8488facbffa8a397967.html">postgres</a></li><li class="navelem"><a class="el" href="dir_dc596537ad427a4d866006d1a3e1fe29.html">modules</a></li><li class="navelem"><a class="el" href="dir_9f5e6edf0db58b0627c46b41dbbbb27f.html">validation</a></li><li class="navelem"><a class="el" href="cross__validation_8sql__in.html">cross_validation.sql_in</a></li>
+ <li class="footer">Generated on Tue Sep 20 2016 11:27:01 for MADlib by
+ <a href="http://www.doxygen.org/index.html">
+ <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.10 </li>
+ </ul>
+</div>
+</body>
+</html>