blob: fadcbceb7dc0fe4cd023c0486904a06882dc19c4 [file] [log] [blame]
<!-- 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 1.8.13"/>
<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: Train-Test Split</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);
</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>
<script type="text/x-mathjax-config">
MathJax.Hub.Config({
extensions: ["tex2jax.js", "TeX/AMSmath.js", "TeX/AMSsymbols.js"],
jax: ["input/TeX","output/HTML-CSS"],
});
</script><script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></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.apache.org');
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.apache.org"><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">1.21.0</span>
</div>
<div id="projectbrief">User Documentation for Apache 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 1.8.13 -->
<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('group__grp__train__test__split.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="headertitle">
<div class="title">Train-Test Split<div class="ingroups"><a class="el" href="group__grp__mdl.html">Model Selection</a></div></div> </div>
</div><!--header-->
<div class="contents">
<div class="toc"><b>Contents</b> <ul>
<li>
<a href="#strs">Train-Test Split</a> </li>
<li>
<a href="#examples">Examples</a> </li>
</ul>
</div><p>Train-test split is a utility to create training and testing sets from a single data set.</p>
<p><a class="anchor" id="strs"></a></p><dl class="section user"><dt>Train-Test Split</dt><dd></dd></dl>
<pre class="syntax">
train_test_split( source_table,
output_table,
train_proportion,
test_proportion,
grouping_cols,
target_cols,
with_replacement,
separate_output_tables
)
</pre><p><b>Arguments</b> </p><dl class="arglist">
<dt>source_table </dt>
<dd><p class="startdd">TEXT. Name of the table containing the input data.</p>
<p class="enddd"></p>
</dd>
<dt>output_table </dt>
<dd><p class="startdd">Name of output table. A new INTEGER column on the right called 'split' will identify 1 for train set and 0 for test set, unless the 'separate_output_tables' parameter below is TRUE, in which case two output tables will be created using the 'output_table' name with the suffixes '_train' and '_test'. The output table contains all the columns present in the source table unless otherwise specified in the 'target_cols' parameter below. </p>
<p class="enddd"></p>
</dd>
<dt>train_proportion </dt>
<dd><p class="startdd">FLOAT8 in the range (0,1). Proportion of the dataset to include in the train split. If the 'grouping_col' parameter is specified below, each group will be sampled independently using the train proportion, i.e., in a stratified fashion.</p>
<p class="enddd"></p>
</dd>
<dt>test_proportion (optional) </dt>
<dd><p class="startdd">FLOAT8 in the range (0,1). Proportion of the dataset to include in the test split. Default is the complement to the train proportion (1-'train_proportion'). If the 'grouping_col' parameter is specified below, each group will be sampled independently using the train proportion, i.e., in a stratified fashion.</p>
<p class="enddd"></p>
</dd>
<dt>grouping_cols (optional) </dt>
<dd><p class="startdd">TEXT, default: NULL. A single column or a list of comma-separated columns that defines how to stratify. When this parameter is NULL, the train-test split is not stratified.</p>
<p class="enddd"></p>
</dd>
<dt>target_cols (optional) </dt>
<dd><p class="startdd">TEXT, default NULL. A comma-separated list of columns to appear in the 'output_table'. If NULL or '*', all columns from the 'source_table' will appear in the 'output_table'.</p>
<p class="enddd"><a class="anchor" id="note"></a></p><dl class="section note"><dt>Note</dt><dd>Do not include 'grouping_cols' in the parameter 'target_cols', because they are always included in the 'output_table'.</dd></dl>
</dd>
<dt>with_replacement (optional) </dt>
<dd><p class="startdd">BOOLEAN, default FALSE. Determines whether to sample with replacement or without replacement (default). With replacement means that it is possible that the same row may appear in the sample set more than once. Without replacement means a given row can be selected only once.</p>
<p class="enddd"></p>
</dd>
<dt>separate_output_tables (optional) </dt>
<dd>BOOLEAN, default FALSE. If TRUE, two output tables will be created using the 'output_table' name with the suffixes '_train' and '_test'. </dd>
</dl>
<p><a class="anchor" id="examples"></a></p><dl class="section user"><dt>Examples</dt><dd></dd></dl>
<p>Please note that due to the random nature of sampling, your results may look different from those below.</p>
<ol type="1">
<li>Create an input table: <pre class="syntax">
DROP TABLE IF EXISTS test;
CREATE TABLE test(
id1 INTEGER,
id2 INTEGER,
gr1 INTEGER,
gr2 INTEGER
);
INSERT INTO test VALUES
(1,0,1,1),
(2,0,1,1),
(3,0,1,1),
(4,0,1,1),
(5,0,1,1),
(6,0,1,1),
(7,0,1,1),
(8,0,1,1),
(9,0,1,1),
(9,0,1,1),
(9,0,1,1),
(9,0,1,1),
(0,1,1,2),
(0,2,1,2),
(0,3,1,2),
(0,4,1,2),
(0,5,1,2),
(0,6,1,2),
(10,10,2,2),
(20,20,2,2),
(30,30,2,2),
(40,40,2,2),
(50,50,2,2),
(60,60,2,2),
(70,70,2,2);
</pre></li>
<li>Sample without replacement: <pre class="syntax">
DROP TABLE IF EXISTS out;
SELECT madlib.train_test_split(
'test', -- Source table
'out', -- Output table
0.5, -- Sample proportion
0.5, -- Sample proportion
'gr1,gr2', -- Strata definition
'id1,id2', -- Columns to output
FALSE, -- Sample without replacement
FALSE); -- Do not separate output tables
SELECT * FROM out ORDER BY split,gr1,gr2,id1,id2;
</pre> <pre class="result">
gr1 | gr2 | id1 | id2 | split
-----+-----+-----+-----+-------
1 | 1 | 1 | 0 | 0
1 | 1 | 4 | 0 | 0
1 | 1 | 6 | 0 | 0
1 | 1 | 9 | 0 | 0
1 | 1 | 9 | 0 | 0
1 | 1 | 9 | 0 | 0
1 | 2 | 0 | 3 | 0
1 | 2 | 0 | 4 | 0
1 | 2 | 0 | 5 | 0
2 | 2 | 10 | 10 | 0
2 | 2 | 30 | 30 | 0
2 | 2 | 40 | 40 | 0
2 | 2 | 60 | 60 | 0
1 | 1 | 2 | 0 | 1
1 | 1 | 3 | 0 | 1
1 | 1 | 5 | 0 | 1
1 | 1 | 7 | 0 | 1
1 | 1 | 8 | 0 | 1
1 | 1 | 9 | 0 | 1
1 | 2 | 0 | 1 | 1
1 | 2 | 0 | 2 | 1
1 | 2 | 0 | 6 | 1
2 | 2 | 20 | 20 | 1
2 | 2 | 50 | 50 | 1
2 | 2 | 70 | 70 | 1
(25 rows)
</pre></li>
<li>Sample with replacement and create separate train and test tables: <pre class="syntax">
DROP TABLE IF EXISTS out, out_train, out_test;
SELECT madlib.train_test_split(
'test', -- Source table
'out', -- Output table
0.5, -- train_proportion
NULL, -- Default = 1 - train_proportion = 0.5
'gr1,gr2', -- Strata definition
'id1,id2', -- Columns to output
TRUE, -- Sample with replacement
TRUE); -- Separate output tables
SELECT * FROM out_train ORDER BY gr1,gr2,id1,id2;
</pre> <pre class="result">
gr1 | gr2 | id1 | id2
-----+-----+-----+-----
1 | 1 | 1 | 0
1 | 1 | 2 | 0
1 | 1 | 4 | 0
1 | 1 | 7 | 0
1 | 1 | 8 | 0
1 | 1 | 9 | 0
1 | 2 | 0 | 4
1 | 2 | 0 | 5
1 | 2 | 0 | 6
2 | 2 | 40 | 40
2 | 2 | 50 | 50
2 | 2 | 50 | 50
(12 rows)
</pre> <pre class="syntax">
SELECT * FROM out_test ORDER BY gr1,gr2,id1,id2;
</pre> <pre class="result">
gr1 | gr2 | id1 | id2
----&mdash;+----&mdash;+----&mdash;+---&mdash;
1 | 1 | 1 | 0
1 | 1 | 1 | 0
1 | 1 | 3 | 0
1 | 1 | 4 | 0
1 | 1 | 5 | 0
1 | 1 | 9 | 0
1 | 2 | 0 | 1
1 | 2 | 0 | 5
1 | 2 | 0 | 6
2 | 2 | 20 | 20
2 | 2 | 20 | 20
2 | 2 | 20 | 20
2 | 2 | 70 | 70
(13 rows)
</pre> </li>
</ol>
</div><!-- contents -->
</div><!-- doc-content -->
<!-- start footer part -->
<div id="nav-path" class="navpath"><!-- id is needed for treeview function! -->
<ul>
<li class="footer">Generated on Thu Feb 23 2023 19:26:40 for MADlib by
<a href="http://www.doxygen.org/index.html">
<img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.13 </li>
</ul>
</div>
</body>
</html>