<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<!-- NewPage -->
<html lang="en">
<head>
<!-- Generated by javadoc (version 1.7.0_51) on Wed Sep 16 15:55:12 PDT 2015 -->
<title>LinearDataGenerator</title>
<meta name="date" content="2015-09-16">
<link rel="stylesheet" type="text/css" href="../../../../../stylesheet.css" title="Style">
</head>
<body>
<script type="text/javascript"><!--
if (location.href.indexOf('is-external=true') == -1) {
parent.document.title="LinearDataGenerator";
}
//-->
</script>
<noscript>
<div>JavaScript is disabled on your browser.</div>
</noscript>
<!-- ========= START OF TOP NAVBAR ======= -->
<div class="topNav"><a name="navbar_top">
<!-- -->
</a><a href="#skip-navbar_top" title="Skip navigation links"></a><a name="navbar_top_firstrow">
<!-- -->
</a>
<ul class="navList" title="Navigation">
<li><a href="../../../../../overview-summary.html">Overview</a></li>
<li><a href="package-summary.html">Package</a></li>
<li class="navBarCell1Rev">Class</li>
<li><a href="package-tree.html">Tree</a></li>
<li><a href="../../../../../deprecated-list.html">Deprecated</a></li>
<li><a href="../../../../../index-all.html">Index</a></li>
<li><a href="../../../../../help-doc.html">Help</a></li>
</ul>
</div>
<div class="subNav">
<ul class="navList">
<li><a href="../../../../../org/apache/spark/mllib/util/KMeansDataGenerator.html" title="class in org.apache.spark.mllib.util"><span class="strong">Prev Class</span></a></li>
<li><a href="../../../../../org/apache/spark/mllib/util/Loader.html" title="interface in org.apache.spark.mllib.util"><span class="strong">Next Class</span></a></li>
</ul>
<ul class="navList">
<li><a href="../../../../../index.html?org/apache/spark/mllib/util/LinearDataGenerator.html" target="_top">Frames</a></li>
<li><a href="LinearDataGenerator.html" target="_top">No Frames</a></li>
</ul>
<ul class="navList" id="allclasses_navbar_top">
<li><a href="../../../../../allclasses-noframe.html">All Classes</a></li>
</ul>
<div>
<script type="text/javascript"><!--
allClassesLink = document.getElementById("allclasses_navbar_top");
if(window==top) {
allClassesLink.style.display = "block";
}
else {
allClassesLink.style.display = "none";
}
//-->
</script>
</div>
<div>
<ul class="subNavList">
<li>Summary: </li>
<li>Nested | </li>
<li>Field | </li>
<li><a href="#constructor_summary">Constr</a> | </li>
<li><a href="#method_summary">Method</a></li>
</ul>
<ul class="subNavList">
<li>Detail: </li>
<li>Field | </li>
<li><a href="#constructor_detail">Constr</a> | </li>
<li><a href="#method_detail">Method</a></li>
</ul>
</div>
<a name="skip-navbar_top">
<!-- -->
</a></div>
<!-- ========= END OF TOP NAVBAR ========= -->
<!-- ======== START OF CLASS DATA ======== -->
<div class="header">
<div class="subTitle">org.apache.spark.mllib.util</div>
<h2 title="Class LinearDataGenerator" class="title">Class LinearDataGenerator</h2>
</div>
<div class="contentContainer">
<ul class="inheritance">
<li>java.lang.Object</li>
<li>
<ul class="inheritance">
<li>org.apache.spark.mllib.util.LinearDataGenerator</li>
</ul>
</li>
</ul>
<div class="description">
<ul class="blockList">
<li class="blockList">
<hr>
<br>
<pre>public class <span class="strong">LinearDataGenerator</span>
extends java.lang.Object</pre>
<div class="block">:: DeveloperApi ::
Generate sample data used for Linear Data. This class generates
uniformly random values for every feature and adds Gaussian noise with mean <code>eps</code> to the
response variable <code>Y</code>.</div>
</li>
</ul>
</div>
<div class="summary">
<ul class="blockList">
<li class="blockList">
<!-- ======== CONSTRUCTOR SUMMARY ======== -->
<ul class="blockList">
<li class="blockList"><a name="constructor_summary">
<!-- -->
</a>
<h3>Constructor Summary</h3>
<table class="overviewSummary" border="0" cellpadding="3" cellspacing="0" summary="Constructor Summary table, listing constructors, and an explanation">
<caption><span>Constructors</span><span class="tabEnd"> </span></caption>
<tr>
<th class="colOne" scope="col">Constructor and Description</th>
</tr>
<tr class="altColor">
<td class="colOne"><code><strong><a href="../../../../../org/apache/spark/mllib/util/LinearDataGenerator.html#LinearDataGenerator()">LinearDataGenerator</a></strong>()</code> </td>
</tr>
</table>
</li>
</ul>
<!-- ========== METHOD SUMMARY =========== -->
<ul class="blockList">
<li class="blockList"><a name="method_summary">
<!-- -->
</a>
<h3>Method Summary</h3>
<table class="overviewSummary" border="0" cellpadding="3" cellspacing="0" summary="Method Summary table, listing methods, and an explanation">
<caption><span>Methods</span><span class="tabEnd"> </span></caption>
<tr>
<th class="colFirst" scope="col">Modifier and Type</th>
<th class="colLast" scope="col">Method and Description</th>
</tr>
<tr class="altColor">
<td class="colFirst"><code>static scala.collection.Seq<<a href="../../../../../org/apache/spark/mllib/regression/LabeledPoint.html" title="class in org.apache.spark.mllib.regression">LabeledPoint</a>></code></td>
<td class="colLast"><code><strong><a href="../../../../../org/apache/spark/mllib/util/LinearDataGenerator.html#generateLinearInput(double, double[], double[], double[], int, int, double)">generateLinearInput</a></strong>(double intercept,
double[] weights,
double[] xMean,
double[] xVariance,
int nPoints,
int seed,
double eps)</code> </td>
</tr>
<tr class="rowColor">
<td class="colFirst"><code>static scala.collection.Seq<<a href="../../../../../org/apache/spark/mllib/regression/LabeledPoint.html" title="class in org.apache.spark.mllib.regression">LabeledPoint</a>></code></td>
<td class="colLast"><code><strong><a href="../../../../../org/apache/spark/mllib/util/LinearDataGenerator.html#generateLinearInput(double, double[], int, int, double)">generateLinearInput</a></strong>(double intercept,
double[] weights,
int nPoints,
int seed,
double eps)</code>
<div class="block">For compatibility, the generated data without specifying the mean and variance
will have zero mean and variance of (1.0/3.0) since the original output range is
[-1, 1] with uniform distribution, and the variance of uniform distribution
is (b - a)^2^ / 12 which will be (1.0/3.0)</div>
</td>
</tr>
<tr class="altColor">
<td class="colFirst"><code>static java.util.List<<a href="../../../../../org/apache/spark/mllib/regression/LabeledPoint.html" title="class in org.apache.spark.mllib.regression">LabeledPoint</a>></code></td>
<td class="colLast"><code><strong><a href="../../../../../org/apache/spark/mllib/util/LinearDataGenerator.html#generateLinearInputAsList(double, double[], int, int, double)">generateLinearInputAsList</a></strong>(double intercept,
double[] weights,
int nPoints,
int seed,
double eps)</code>
<div class="block">Return a Java List of synthetic data randomly generated according to a multi
collinear model.</div>
</td>
</tr>
<tr class="rowColor">
<td class="colFirst"><code>static <a href="../../../../../org/apache/spark/rdd/RDD.html" title="class in org.apache.spark.rdd">RDD</a><<a href="../../../../../org/apache/spark/mllib/regression/LabeledPoint.html" title="class in org.apache.spark.mllib.regression">LabeledPoint</a>></code></td>
<td class="colLast"><code><strong><a href="../../../../../org/apache/spark/mllib/util/LinearDataGenerator.html#generateLinearRDD(org.apache.spark.SparkContext, int, int, double, int, double)">generateLinearRDD</a></strong>(<a href="../../../../../org/apache/spark/SparkContext.html" title="class in org.apache.spark">SparkContext</a> sc,
int nexamples,
int nfeatures,
double eps,
int nparts,
double intercept)</code>
<div class="block">Generate an RDD containing sample data for Linear Regression models - including Ridge, Lasso,
and uregularized variants.</div>
</td>
</tr>
<tr class="altColor">
<td class="colFirst"><code>static void</code></td>
<td class="colLast"><code><strong><a href="../../../../../org/apache/spark/mllib/util/LinearDataGenerator.html#main(java.lang.String[])">main</a></strong>(java.lang.String[] args)</code> </td>
</tr>
</table>
<ul class="blockList">
<li class="blockList"><a name="methods_inherited_from_class_java.lang.Object">
<!-- -->
</a>
<h3>Methods inherited from class java.lang.Object</h3>
<code>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</code></li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
<div class="details">
<ul class="blockList">
<li class="blockList">
<!-- ========= CONSTRUCTOR DETAIL ======== -->
<ul class="blockList">
<li class="blockList"><a name="constructor_detail">
<!-- -->
</a>
<h3>Constructor Detail</h3>
<a name="LinearDataGenerator()">
<!-- -->
</a>
<ul class="blockListLast">
<li class="blockList">
<h4>LinearDataGenerator</h4>
<pre>public LinearDataGenerator()</pre>
</li>
</ul>
</li>
</ul>
<!-- ============ METHOD DETAIL ========== -->
<ul class="blockList">
<li class="blockList"><a name="method_detail">
<!-- -->
</a>
<h3>Method Detail</h3>
<a name="generateLinearInputAsList(double, double[], int, int, double)">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>generateLinearInputAsList</h4>
<pre>public static java.util.List<<a href="../../../../../org/apache/spark/mllib/regression/LabeledPoint.html" title="class in org.apache.spark.mllib.regression">LabeledPoint</a>> generateLinearInputAsList(double intercept,
double[] weights,
int nPoints,
int seed,
double eps)</pre>
<div class="block">Return a Java List of synthetic data randomly generated according to a multi
collinear model.</div>
<dl><dt><span class="strong">Parameters:</span></dt><dd><code>intercept</code> - Data intercept</dd><dd><code>weights</code> - Weights to be applied.</dd><dd><code>nPoints</code> - Number of points in sample.</dd><dd><code>seed</code> - Random seed</dd><dd><code>eps</code> - (undocumented)</dd>
<dt><span class="strong">Returns:</span></dt><dd>Java List of input.</dd></dl>
</li>
</ul>
<a name="generateLinearInput(double, double[], int, int, double)">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>generateLinearInput</h4>
<pre>public static scala.collection.Seq<<a href="../../../../../org/apache/spark/mllib/regression/LabeledPoint.html" title="class in org.apache.spark.mllib.regression">LabeledPoint</a>> generateLinearInput(double intercept,
double[] weights,
int nPoints,
int seed,
double eps)</pre>
<div class="block">For compatibility, the generated data without specifying the mean and variance
will have zero mean and variance of (1.0/3.0) since the original output range is
[-1, 1] with uniform distribution, and the variance of uniform distribution
is (b - a)^2^ / 12 which will be (1.0/3.0)
<p></div>
<dl><dt><span class="strong">Parameters:</span></dt><dd><code>intercept</code> - Data intercept</dd><dd><code>weights</code> - Weights to be applied.</dd><dd><code>nPoints</code> - Number of points in sample.</dd><dd><code>seed</code> - Random seed</dd><dd><code>eps</code> - Epsilon scaling factor.</dd>
<dt><span class="strong">Returns:</span></dt><dd>Seq of input.</dd></dl>
</li>
</ul>
<a name="generateLinearInput(double, double[], double[], double[], int, int, double)">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>generateLinearInput</h4>
<pre>public static scala.collection.Seq<<a href="../../../../../org/apache/spark/mllib/regression/LabeledPoint.html" title="class in org.apache.spark.mllib.regression">LabeledPoint</a>> generateLinearInput(double intercept,
double[] weights,
double[] xMean,
double[] xVariance,
int nPoints,
int seed,
double eps)</pre>
<dl><dt><span class="strong">Parameters:</span></dt><dd><code>intercept</code> - Data intercept</dd><dd><code>weights</code> - Weights to be applied.</dd><dd><code>xMean</code> - the mean of the generated features. Lots of time, if the features are not properly
standardized, the algorithm with poor implementation will have difficulty
to converge.</dd><dd><code>xVariance</code> - the variance of the generated features.</dd><dd><code>nPoints</code> - Number of points in sample.</dd><dd><code>seed</code> - Random seed</dd><dd><code>eps</code> - Epsilon scaling factor.</dd>
<dt><span class="strong">Returns:</span></dt><dd>Seq of input.</dd></dl>
</li>
</ul>
<a name="generateLinearRDD(org.apache.spark.SparkContext, int, int, double, int, double)">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>generateLinearRDD</h4>
<pre>public static <a href="../../../../../org/apache/spark/rdd/RDD.html" title="class in org.apache.spark.rdd">RDD</a><<a href="../../../../../org/apache/spark/mllib/regression/LabeledPoint.html" title="class in org.apache.spark.mllib.regression">LabeledPoint</a>> generateLinearRDD(<a href="../../../../../org/apache/spark/SparkContext.html" title="class in org.apache.spark">SparkContext</a> sc,
int nexamples,
int nfeatures,
double eps,
int nparts,
double intercept)</pre>
<div class="block">Generate an RDD containing sample data for Linear Regression models - including Ridge, Lasso,
and uregularized variants.
<p></div>
<dl><dt><span class="strong">Parameters:</span></dt><dd><code>sc</code> - SparkContext to be used for generating the RDD.</dd><dd><code>nexamples</code> - Number of examples that will be contained in the RDD.</dd><dd><code>nfeatures</code> - Number of features to generate for each example.</dd><dd><code>eps</code> - Epsilon factor by which examples are scaled.</dd><dd><code>nparts</code> - Number of partitions in the RDD. Default value is 2.
<p></dd><dd><code>intercept</code> - (undocumented)</dd>
<dt><span class="strong">Returns:</span></dt><dd>RDD of LabeledPoint containing sample data.</dd></dl>
</li>
</ul>
<a name="main(java.lang.String[])">
<!-- -->
</a>
<ul class="blockListLast">
<li class="blockList">
<h4>main</h4>
<pre>public static void main(java.lang.String[] args)</pre>
</li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
</div>
<!-- ========= END OF CLASS DATA ========= -->
<!-- ======= START OF BOTTOM NAVBAR ====== -->
<div class="bottomNav"><a name="navbar_bottom">
<!-- -->
</a><a href="#skip-navbar_bottom" title="Skip navigation links"></a><a name="navbar_bottom_firstrow">
<!-- -->
</a>
<ul class="navList" title="Navigation">
<li><a href="../../../../../overview-summary.html">Overview</a></li>
<li><a href="package-summary.html">Package</a></li>
<li class="navBarCell1Rev">Class</li>
<li><a href="package-tree.html">Tree</a></li>
<li><a href="../../../../../deprecated-list.html">Deprecated</a></li>
<li><a href="../../../../../index-all.html">Index</a></li>
<li><a href="../../../../../help-doc.html">Help</a></li>
</ul>
</div>
<div class="subNav">
<ul class="navList">
<li><a href="../../../../../org/apache/spark/mllib/util/KMeansDataGenerator.html" title="class in org.apache.spark.mllib.util"><span class="strong">Prev Class</span></a></li>
<li><a href="../../../../../org/apache/spark/mllib/util/Loader.html" title="interface in org.apache.spark.mllib.util"><span class="strong">Next Class</span></a></li>
</ul>
<ul class="navList">
<li><a href="../../../../../index.html?org/apache/spark/mllib/util/LinearDataGenerator.html" target="_top">Frames</a></li>
<li><a href="LinearDataGenerator.html" target="_top">No Frames</a></li>
</ul>
<ul class="navList" id="allclasses_navbar_bottom">
<li><a href="../../../../../allclasses-noframe.html">All Classes</a></li>
</ul>
<div>
<script type="text/javascript"><!--
allClassesLink = document.getElementById("allclasses_navbar_bottom");
if(window==top) {
allClassesLink.style.display = "block";
}
else {
allClassesLink.style.display = "none";
}
//-->
</script>
</div>
<div>
<ul class="subNavList">
<li>Summary: </li>
<li>Nested | </li>
<li>Field | </li>
<li><a href="#constructor_summary">Constr</a> | </li>
<li><a href="#method_summary">Method</a></li>
</ul>
<ul class="subNavList">
<li>Detail: </li>
<li>Field | </li>
<li><a href="#constructor_detail">Constr</a> | </li>
<li><a href="#method_detail">Method</a></li>
</ul>
</div>
<a name="skip-navbar_bottom">
<!-- -->
</a></div>
<!-- ======== END OF BOTTOM NAVBAR ======= -->
<script defer="defer" type="text/javascript" src="../../../../../lib/jquery.js"></script><script defer="defer" type="text/javascript" src="../../../../../lib/api-javadocs.js"></script></body>
</html>