Mercurial > hg > de.mpg.mpiwg.itgroup.digilib.plugin
view libs/commons-math-2.1/docs/apidocs/src-html/org/apache/commons/math/stat/correlation/SpearmansCorrelation.html @ 13:cbf34dd4d7e6
commons-math-2.1 added
author | dwinter |
---|---|
date | Tue, 04 Jan 2011 10:02:07 +0100 |
parents | |
children |
line wrap: on
line source
<HTML> <BODY BGCOLOR="white"> <PRE> <FONT color="green">001</FONT> /*<a name="line.1"></a> <FONT color="green">002</FONT> * Licensed to the Apache Software Foundation (ASF) under one or more<a name="line.2"></a> <FONT color="green">003</FONT> * contributor license agreements. See the NOTICE file distributed with<a name="line.3"></a> <FONT color="green">004</FONT> * this work for additional information regarding copyright ownership.<a name="line.4"></a> <FONT color="green">005</FONT> * The ASF licenses this file to You under the Apache License, Version 2.0<a name="line.5"></a> <FONT color="green">006</FONT> * (the "License"); you may not use this file except in compliance with<a name="line.6"></a> <FONT color="green">007</FONT> * the License. You may obtain a copy of the License at<a name="line.7"></a> <FONT color="green">008</FONT> *<a name="line.8"></a> <FONT color="green">009</FONT> * http://www.apache.org/licenses/LICENSE-2.0<a name="line.9"></a> <FONT color="green">010</FONT> *<a name="line.10"></a> <FONT color="green">011</FONT> * Unless required by applicable law or agreed to in writing, software<a name="line.11"></a> <FONT color="green">012</FONT> * distributed under the License is distributed on an "AS IS" BASIS,<a name="line.12"></a> <FONT color="green">013</FONT> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.<a name="line.13"></a> <FONT color="green">014</FONT> * See the License for the specific language governing permissions and<a name="line.14"></a> <FONT color="green">015</FONT> * limitations under the License.<a name="line.15"></a> <FONT color="green">016</FONT> */<a name="line.16"></a> <FONT color="green">017</FONT> <a name="line.17"></a> <FONT color="green">018</FONT> package org.apache.commons.math.stat.correlation;<a name="line.18"></a> <FONT color="green">019</FONT> <a name="line.19"></a> <FONT color="green">020</FONT> import org.apache.commons.math.MathRuntimeException;<a name="line.20"></a> <FONT color="green">021</FONT> import org.apache.commons.math.linear.BlockRealMatrix;<a name="line.21"></a> <FONT color="green">022</FONT> import org.apache.commons.math.linear.RealMatrix;<a name="line.22"></a> <FONT color="green">023</FONT> import org.apache.commons.math.stat.ranking.NaturalRanking;<a name="line.23"></a> <FONT color="green">024</FONT> import org.apache.commons.math.stat.ranking.RankingAlgorithm;<a name="line.24"></a> <FONT color="green">025</FONT> <a name="line.25"></a> <FONT color="green">026</FONT> /**<a name="line.26"></a> <FONT color="green">027</FONT> * <p>Spearman's rank correlation. This implementation performs a rank<a name="line.27"></a> <FONT color="green">028</FONT> * transformation on the input data and then computes {@link PearsonsCorrelation}<a name="line.28"></a> <FONT color="green">029</FONT> * on the ranked data.</p><a name="line.29"></a> <FONT color="green">030</FONT> *<a name="line.30"></a> <FONT color="green">031</FONT> * <p>By default, ranks are computed using {@link NaturalRanking} with default<a name="line.31"></a> <FONT color="green">032</FONT> * strategies for handling NaNs and ties in the data (NaNs maximal, ties averaged).<a name="line.32"></a> <FONT color="green">033</FONT> * The ranking algorithm can be set using a constructor argument.</p><a name="line.33"></a> <FONT color="green">034</FONT> *<a name="line.34"></a> <FONT color="green">035</FONT> * @since 2.0<a name="line.35"></a> <FONT color="green">036</FONT> * @version $Revision: 811685 $ $Date: 2009-09-05 13:36:48 -0400 (Sat, 05 Sep 2009) $<a name="line.36"></a> <FONT color="green">037</FONT> */<a name="line.37"></a> <FONT color="green">038</FONT> <a name="line.38"></a> <FONT color="green">039</FONT> public class SpearmansCorrelation {<a name="line.39"></a> <FONT color="green">040</FONT> <a name="line.40"></a> <FONT color="green">041</FONT> /** Input data */<a name="line.41"></a> <FONT color="green">042</FONT> private final RealMatrix data;<a name="line.42"></a> <FONT color="green">043</FONT> <a name="line.43"></a> <FONT color="green">044</FONT> /** Ranking algorithm */<a name="line.44"></a> <FONT color="green">045</FONT> private final RankingAlgorithm rankingAlgorithm;<a name="line.45"></a> <FONT color="green">046</FONT> <a name="line.46"></a> <FONT color="green">047</FONT> /** Rank correlation */<a name="line.47"></a> <FONT color="green">048</FONT> private final PearsonsCorrelation rankCorrelation;<a name="line.48"></a> <FONT color="green">049</FONT> <a name="line.49"></a> <FONT color="green">050</FONT> /**<a name="line.50"></a> <FONT color="green">051</FONT> * Create a SpearmansCorrelation with the given input data matrix<a name="line.51"></a> <FONT color="green">052</FONT> * and ranking algorithm.<a name="line.52"></a> <FONT color="green">053</FONT> *<a name="line.53"></a> <FONT color="green">054</FONT> * @param dataMatrix matrix of data with columns representing<a name="line.54"></a> <FONT color="green">055</FONT> * variables to correlate<a name="line.55"></a> <FONT color="green">056</FONT> * @param rankingAlgorithm ranking algorithm<a name="line.56"></a> <FONT color="green">057</FONT> */<a name="line.57"></a> <FONT color="green">058</FONT> public SpearmansCorrelation(final RealMatrix dataMatrix, final RankingAlgorithm rankingAlgorithm) {<a name="line.58"></a> <FONT color="green">059</FONT> this.data = dataMatrix.copy();<a name="line.59"></a> <FONT color="green">060</FONT> this.rankingAlgorithm = rankingAlgorithm;<a name="line.60"></a> <FONT color="green">061</FONT> rankTransform(data);<a name="line.61"></a> <FONT color="green">062</FONT> rankCorrelation = new PearsonsCorrelation(data);<a name="line.62"></a> <FONT color="green">063</FONT> }<a name="line.63"></a> <FONT color="green">064</FONT> <a name="line.64"></a> <FONT color="green">065</FONT> /**<a name="line.65"></a> <FONT color="green">066</FONT> * Create a SpearmansCorrelation from the given data matrix.<a name="line.66"></a> <FONT color="green">067</FONT> *<a name="line.67"></a> <FONT color="green">068</FONT> * @param dataMatrix matrix of data with columns representing<a name="line.68"></a> <FONT color="green">069</FONT> * variables to correlate<a name="line.69"></a> <FONT color="green">070</FONT> */<a name="line.70"></a> <FONT color="green">071</FONT> public SpearmansCorrelation(final RealMatrix dataMatrix) {<a name="line.71"></a> <FONT color="green">072</FONT> this(dataMatrix, new NaturalRanking());<a name="line.72"></a> <FONT color="green">073</FONT> }<a name="line.73"></a> <FONT color="green">074</FONT> <a name="line.74"></a> <FONT color="green">075</FONT> /**<a name="line.75"></a> <FONT color="green">076</FONT> * Create a SpearmansCorrelation without data.<a name="line.76"></a> <FONT color="green">077</FONT> */<a name="line.77"></a> <FONT color="green">078</FONT> public SpearmansCorrelation() {<a name="line.78"></a> <FONT color="green">079</FONT> data = null;<a name="line.79"></a> <FONT color="green">080</FONT> this.rankingAlgorithm = new NaturalRanking();<a name="line.80"></a> <FONT color="green">081</FONT> rankCorrelation = null;<a name="line.81"></a> <FONT color="green">082</FONT> }<a name="line.82"></a> <FONT color="green">083</FONT> <a name="line.83"></a> <FONT color="green">084</FONT> /**<a name="line.84"></a> <FONT color="green">085</FONT> * Calculate the Spearman Rank Correlation Matrix.<a name="line.85"></a> <FONT color="green">086</FONT> *<a name="line.86"></a> <FONT color="green">087</FONT> * @return Spearman Rank Correlation Matrix<a name="line.87"></a> <FONT color="green">088</FONT> */<a name="line.88"></a> <FONT color="green">089</FONT> public RealMatrix getCorrelationMatrix() {<a name="line.89"></a> <FONT color="green">090</FONT> return rankCorrelation.getCorrelationMatrix();<a name="line.90"></a> <FONT color="green">091</FONT> }<a name="line.91"></a> <FONT color="green">092</FONT> <a name="line.92"></a> <FONT color="green">093</FONT> /**<a name="line.93"></a> <FONT color="green">094</FONT> * Returns a {@link PearsonsCorrelation} instance constructed from the<a name="line.94"></a> <FONT color="green">095</FONT> * ranked input data. That is,<a name="line.95"></a> <FONT color="green">096</FONT> * <code>new SpearmansCorrelation(matrix).getRankCorrelation()</code><a name="line.96"></a> <FONT color="green">097</FONT> * is equivalent to<a name="line.97"></a> <FONT color="green">098</FONT> * <code>new PearsonsCorrelation(rankTransform(matrix))</code> where<a name="line.98"></a> <FONT color="green">099</FONT> * <code>rankTransform(matrix)</code> is the result of applying the<a name="line.99"></a> <FONT color="green">100</FONT> * configured <code>RankingAlgorithm</code> to each of the columns of<a name="line.100"></a> <FONT color="green">101</FONT> * <code>matrix.</code><a name="line.101"></a> <FONT color="green">102</FONT> *<a name="line.102"></a> <FONT color="green">103</FONT> * @return PearsonsCorrelation among ranked column data<a name="line.103"></a> <FONT color="green">104</FONT> */<a name="line.104"></a> <FONT color="green">105</FONT> public PearsonsCorrelation getRankCorrelation() {<a name="line.105"></a> <FONT color="green">106</FONT> return rankCorrelation;<a name="line.106"></a> <FONT color="green">107</FONT> }<a name="line.107"></a> <FONT color="green">108</FONT> <a name="line.108"></a> <FONT color="green">109</FONT> /**<a name="line.109"></a> <FONT color="green">110</FONT> * Computes the Spearman's rank correlation matrix for the columns of the<a name="line.110"></a> <FONT color="green">111</FONT> * input matrix.<a name="line.111"></a> <FONT color="green">112</FONT> *<a name="line.112"></a> <FONT color="green">113</FONT> * @param matrix matrix with columns representing variables to correlate<a name="line.113"></a> <FONT color="green">114</FONT> * @return correlation matrix<a name="line.114"></a> <FONT color="green">115</FONT> */<a name="line.115"></a> <FONT color="green">116</FONT> public RealMatrix computeCorrelationMatrix(RealMatrix matrix) {<a name="line.116"></a> <FONT color="green">117</FONT> RealMatrix matrixCopy = matrix.copy();<a name="line.117"></a> <FONT color="green">118</FONT> rankTransform(matrixCopy);<a name="line.118"></a> <FONT color="green">119</FONT> return new PearsonsCorrelation().computeCorrelationMatrix(matrixCopy);<a name="line.119"></a> <FONT color="green">120</FONT> }<a name="line.120"></a> <FONT color="green">121</FONT> <a name="line.121"></a> <FONT color="green">122</FONT> /**<a name="line.122"></a> <FONT color="green">123</FONT> * Computes the Spearman's rank correlation matrix for the columns of the<a name="line.123"></a> <FONT color="green">124</FONT> * input rectangular array. The columns of the array represent values<a name="line.124"></a> <FONT color="green">125</FONT> * of variables to be correlated.<a name="line.125"></a> <FONT color="green">126</FONT> *<a name="line.126"></a> <FONT color="green">127</FONT> * @param matrix matrix with columns representing variables to correlate<a name="line.127"></a> <FONT color="green">128</FONT> * @return correlation matrix<a name="line.128"></a> <FONT color="green">129</FONT> */<a name="line.129"></a> <FONT color="green">130</FONT> public RealMatrix computeCorrelationMatrix(double[][] matrix) {<a name="line.130"></a> <FONT color="green">131</FONT> return computeCorrelationMatrix(new BlockRealMatrix(matrix));<a name="line.131"></a> <FONT color="green">132</FONT> }<a name="line.132"></a> <FONT color="green">133</FONT> <a name="line.133"></a> <FONT color="green">134</FONT> /**<a name="line.134"></a> <FONT color="green">135</FONT> * Computes the Spearman's rank correlation coefficient between the two arrays.<a name="line.135"></a> <FONT color="green">136</FONT> *<a name="line.136"></a> <FONT color="green">137</FONT> * </p>Throws IllegalArgumentException if the arrays do not have the same length<a name="line.137"></a> <FONT color="green">138</FONT> * or their common length is less than 2</p><a name="line.138"></a> <FONT color="green">139</FONT> *<a name="line.139"></a> <FONT color="green">140</FONT> * @param xArray first data array<a name="line.140"></a> <FONT color="green">141</FONT> * @param yArray second data array<a name="line.141"></a> <FONT color="green">142</FONT> * @return Returns Spearman's rank correlation coefficient for the two arrays<a name="line.142"></a> <FONT color="green">143</FONT> * @throws IllegalArgumentException if the arrays lengths do not match or<a name="line.143"></a> <FONT color="green">144</FONT> * there is insufficient data<a name="line.144"></a> <FONT color="green">145</FONT> */<a name="line.145"></a> <FONT color="green">146</FONT> public double correlation(final double[] xArray, final double[] yArray)<a name="line.146"></a> <FONT color="green">147</FONT> throws IllegalArgumentException {<a name="line.147"></a> <FONT color="green">148</FONT> if (xArray.length == yArray.length && xArray.length > 1) {<a name="line.148"></a> <FONT color="green">149</FONT> return new PearsonsCorrelation().correlation(rankingAlgorithm.rank(xArray),<a name="line.149"></a> <FONT color="green">150</FONT> rankingAlgorithm.rank(yArray));<a name="line.150"></a> <FONT color="green">151</FONT> }<a name="line.151"></a> <FONT color="green">152</FONT> else {<a name="line.152"></a> <FONT color="green">153</FONT> throw MathRuntimeException.createIllegalArgumentException(<a name="line.153"></a> <FONT color="green">154</FONT> "invalid array dimensions. xArray has size {0}; yArray has {1} elements",<a name="line.154"></a> <FONT color="green">155</FONT> xArray.length, yArray.length);<a name="line.155"></a> <FONT color="green">156</FONT> }<a name="line.156"></a> <FONT color="green">157</FONT> }<a name="line.157"></a> <FONT color="green">158</FONT> <a name="line.158"></a> <FONT color="green">159</FONT> /**<a name="line.159"></a> <FONT color="green">160</FONT> * Applies rank transform to each of the columns of <code>matrix</code><a name="line.160"></a> <FONT color="green">161</FONT> * using the current <code>rankingAlgorithm</code><a name="line.161"></a> <FONT color="green">162</FONT> *<a name="line.162"></a> <FONT color="green">163</FONT> * @param matrix matrix to transform<a name="line.163"></a> <FONT color="green">164</FONT> */<a name="line.164"></a> <FONT color="green">165</FONT> private void rankTransform(RealMatrix matrix) {<a name="line.165"></a> <FONT color="green">166</FONT> for (int i = 0; i < matrix.getColumnDimension(); i++) {<a name="line.166"></a> <FONT color="green">167</FONT> matrix.setColumn(i, rankingAlgorithm.rank(matrix.getColumn(i)));<a name="line.167"></a> <FONT color="green">168</FONT> }<a name="line.168"></a> <FONT color="green">169</FONT> }<a name="line.169"></a> <FONT color="green">170</FONT> }<a name="line.170"></a> </PRE> </BODY> </HTML>