Mercurial > hg > de.mpg.mpiwg.itgroup.digilib.plugin
view libs/commons-math-2.1/docs/apidocs/src-html/org/apache/commons/math/stat/ranking/NaturalRanking.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.ranking;<a name="line.18"></a> <FONT color="green">019</FONT> <a name="line.19"></a> <FONT color="green">020</FONT> import java.util.ArrayList;<a name="line.20"></a> <FONT color="green">021</FONT> import java.util.Arrays;<a name="line.21"></a> <FONT color="green">022</FONT> import java.util.Iterator;<a name="line.22"></a> <FONT color="green">023</FONT> import java.util.List;<a name="line.23"></a> <FONT color="green">024</FONT> <a name="line.24"></a> <FONT color="green">025</FONT> import org.apache.commons.math.MathRuntimeException;<a name="line.25"></a> <FONT color="green">026</FONT> import org.apache.commons.math.random.RandomData;<a name="line.26"></a> <FONT color="green">027</FONT> import org.apache.commons.math.random.RandomDataImpl;<a name="line.27"></a> <FONT color="green">028</FONT> import org.apache.commons.math.random.RandomGenerator;<a name="line.28"></a> <FONT color="green">029</FONT> <a name="line.29"></a> <FONT color="green">030</FONT> <a name="line.30"></a> <FONT color="green">031</FONT> /**<a name="line.31"></a> <FONT color="green">032</FONT> * <p> Ranking based on the natural ordering on doubles.</p><a name="line.32"></a> <FONT color="green">033</FONT> * <p>NaNs are treated according to the configured {@link NaNStrategy} and ties<a name="line.33"></a> <FONT color="green">034</FONT> * are handled using the selected {@link TiesStrategy}.<a name="line.34"></a> <FONT color="green">035</FONT> * Configuration settings are supplied in optional constructor arguments.<a name="line.35"></a> <FONT color="green">036</FONT> * Defaults are {@link NaNStrategy#MAXIMAL} and {@link TiesStrategy#AVERAGE},<a name="line.36"></a> <FONT color="green">037</FONT> * respectively. When using {@link TiesStrategy#RANDOM}, a<a name="line.37"></a> <FONT color="green">038</FONT> * {@link RandomGenerator} may be supplied as a constructor argument.</p><a name="line.38"></a> <FONT color="green">039</FONT> * <p>Examples:<a name="line.39"></a> <FONT color="green">040</FONT> * <table border="1" cellpadding="3"><a name="line.40"></a> <FONT color="green">041</FONT> * <tr><th colspan="3"><a name="line.41"></a> <FONT color="green">042</FONT> * Input data: (20, 17, 30, 42.3, 17, 50, Double.NaN, Double.NEGATIVE_INFINITY, 17)<a name="line.42"></a> <FONT color="green">043</FONT> * </th></tr><a name="line.43"></a> <FONT color="green">044</FONT> * <tr><th>NaNStrategy</th><th>TiesStrategy</th><a name="line.44"></a> <FONT color="green">045</FONT> * <th><code>rank(data)</code></th><a name="line.45"></a> <FONT color="green">046</FONT> * <tr><a name="line.46"></a> <FONT color="green">047</FONT> * <td>default (NaNs maximal)</td><a name="line.47"></a> <FONT color="green">048</FONT> * <td>default (ties averaged)</td><a name="line.48"></a> <FONT color="green">049</FONT> * <td>(5, 3, 6, 7, 3, 8, 9, 1, 3)</td></tr><a name="line.49"></a> <FONT color="green">050</FONT> * <tr><a name="line.50"></a> <FONT color="green">051</FONT> * <td>default (NaNs maximal)</td><a name="line.51"></a> <FONT color="green">052</FONT> * <td>MINIMUM</td><a name="line.52"></a> <FONT color="green">053</FONT> * <td>(5, 2, 6, 7, 2, 8, 9, 1, 2)</td></tr><a name="line.53"></a> <FONT color="green">054</FONT> * <tr><a name="line.54"></a> <FONT color="green">055</FONT> * <td>MINIMAL</td><a name="line.55"></a> <FONT color="green">056</FONT> * <td>default (ties averaged)</td><a name="line.56"></a> <FONT color="green">057</FONT> * <td>(6, 4, 7, 8, 4, 9, 1.5, 1.5, 4)</td></tr><a name="line.57"></a> <FONT color="green">058</FONT> * <tr><a name="line.58"></a> <FONT color="green">059</FONT> * <td>REMOVED</td><a name="line.59"></a> <FONT color="green">060</FONT> * <td>SEQUENTIAL</td><a name="line.60"></a> <FONT color="green">061</FONT> * <td>(5, 2, 6, 7, 3, 8, 1, 4)</td></tr><a name="line.61"></a> <FONT color="green">062</FONT> * <tr><a name="line.62"></a> <FONT color="green">063</FONT> * <td>MINIMAL</td><a name="line.63"></a> <FONT color="green">064</FONT> * <td>MAXIMUM</td><a name="line.64"></a> <FONT color="green">065</FONT> * <td>(6, 5, 7, 8, 5, 9, 2, 2, 5)</td></tr></table></p><a name="line.65"></a> <FONT color="green">066</FONT> *<a name="line.66"></a> <FONT color="green">067</FONT> * @since 2.0<a name="line.67"></a> <FONT color="green">068</FONT> * @version $Revision: 811827 $ $Date: 2009-09-06 11:32:50 -0400 (Sun, 06 Sep 2009) $<a name="line.68"></a> <FONT color="green">069</FONT> */<a name="line.69"></a> <FONT color="green">070</FONT> public class NaturalRanking implements RankingAlgorithm {<a name="line.70"></a> <FONT color="green">071</FONT> <a name="line.71"></a> <FONT color="green">072</FONT> /** default NaN strategy */<a name="line.72"></a> <FONT color="green">073</FONT> public static final NaNStrategy DEFAULT_NAN_STRATEGY = NaNStrategy.MAXIMAL;<a name="line.73"></a> <FONT color="green">074</FONT> <a name="line.74"></a> <FONT color="green">075</FONT> /** default ties strategy */<a name="line.75"></a> <FONT color="green">076</FONT> public static final TiesStrategy DEFAULT_TIES_STRATEGY = TiesStrategy.AVERAGE;<a name="line.76"></a> <FONT color="green">077</FONT> <a name="line.77"></a> <FONT color="green">078</FONT> /** NaN strategy - defaults to NaNs maximal */<a name="line.78"></a> <FONT color="green">079</FONT> private final NaNStrategy nanStrategy;<a name="line.79"></a> <FONT color="green">080</FONT> <a name="line.80"></a> <FONT color="green">081</FONT> /** Ties strategy - defaults to ties averaged */<a name="line.81"></a> <FONT color="green">082</FONT> private final TiesStrategy tiesStrategy;<a name="line.82"></a> <FONT color="green">083</FONT> <a name="line.83"></a> <FONT color="green">084</FONT> /** Source of random data - used only when ties strategy is RANDOM */<a name="line.84"></a> <FONT color="green">085</FONT> private final RandomData randomData;<a name="line.85"></a> <FONT color="green">086</FONT> <a name="line.86"></a> <FONT color="green">087</FONT> /**<a name="line.87"></a> <FONT color="green">088</FONT> * Create a NaturalRanking with default strategies for handling ties and NaNs.<a name="line.88"></a> <FONT color="green">089</FONT> */<a name="line.89"></a> <FONT color="green">090</FONT> public NaturalRanking() {<a name="line.90"></a> <FONT color="green">091</FONT> super();<a name="line.91"></a> <FONT color="green">092</FONT> tiesStrategy = DEFAULT_TIES_STRATEGY;<a name="line.92"></a> <FONT color="green">093</FONT> nanStrategy = DEFAULT_NAN_STRATEGY;<a name="line.93"></a> <FONT color="green">094</FONT> randomData = null;<a name="line.94"></a> <FONT color="green">095</FONT> }<a name="line.95"></a> <FONT color="green">096</FONT> <a name="line.96"></a> <FONT color="green">097</FONT> /**<a name="line.97"></a> <FONT color="green">098</FONT> * Create a NaturalRanking with the given TiesStrategy.<a name="line.98"></a> <FONT color="green">099</FONT> *<a name="line.99"></a> <FONT color="green">100</FONT> * @param tiesStrategy the TiesStrategy to use<a name="line.100"></a> <FONT color="green">101</FONT> */<a name="line.101"></a> <FONT color="green">102</FONT> public NaturalRanking(TiesStrategy tiesStrategy) {<a name="line.102"></a> <FONT color="green">103</FONT> super();<a name="line.103"></a> <FONT color="green">104</FONT> this.tiesStrategy = tiesStrategy;<a name="line.104"></a> <FONT color="green">105</FONT> nanStrategy = DEFAULT_NAN_STRATEGY;<a name="line.105"></a> <FONT color="green">106</FONT> randomData = new RandomDataImpl();<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> * Create a NaturalRanking with the given NaNStrategy.<a name="line.110"></a> <FONT color="green">111</FONT> *<a name="line.111"></a> <FONT color="green">112</FONT> * @param nanStrategy the NaNStrategy to use<a name="line.112"></a> <FONT color="green">113</FONT> */<a name="line.113"></a> <FONT color="green">114</FONT> public NaturalRanking(NaNStrategy nanStrategy) {<a name="line.114"></a> <FONT color="green">115</FONT> super();<a name="line.115"></a> <FONT color="green">116</FONT> this.nanStrategy = nanStrategy;<a name="line.116"></a> <FONT color="green">117</FONT> tiesStrategy = DEFAULT_TIES_STRATEGY;<a name="line.117"></a> <FONT color="green">118</FONT> randomData = null;<a name="line.118"></a> <FONT color="green">119</FONT> }<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> * Create a NaturalRanking with the given NaNStrategy and TiesStrategy.<a name="line.122"></a> <FONT color="green">123</FONT> *<a name="line.123"></a> <FONT color="green">124</FONT> * @param nanStrategy NaNStrategy to use<a name="line.124"></a> <FONT color="green">125</FONT> * @param tiesStrategy TiesStrategy to use<a name="line.125"></a> <FONT color="green">126</FONT> */<a name="line.126"></a> <FONT color="green">127</FONT> public NaturalRanking(NaNStrategy nanStrategy, TiesStrategy tiesStrategy) {<a name="line.127"></a> <FONT color="green">128</FONT> super();<a name="line.128"></a> <FONT color="green">129</FONT> this.nanStrategy = nanStrategy;<a name="line.129"></a> <FONT color="green">130</FONT> this.tiesStrategy = tiesStrategy;<a name="line.130"></a> <FONT color="green">131</FONT> randomData = new RandomDataImpl();<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> * Create a NaturalRanking with TiesStrategy.RANDOM and the given<a name="line.135"></a> <FONT color="green">136</FONT> * RandomGenerator as the source of random data.<a name="line.136"></a> <FONT color="green">137</FONT> *<a name="line.137"></a> <FONT color="green">138</FONT> * @param randomGenerator source of random data<a name="line.138"></a> <FONT color="green">139</FONT> */<a name="line.139"></a> <FONT color="green">140</FONT> public NaturalRanking(RandomGenerator randomGenerator) {<a name="line.140"></a> <FONT color="green">141</FONT> super();<a name="line.141"></a> <FONT color="green">142</FONT> this.tiesStrategy = TiesStrategy.RANDOM;<a name="line.142"></a> <FONT color="green">143</FONT> nanStrategy = DEFAULT_NAN_STRATEGY;<a name="line.143"></a> <FONT color="green">144</FONT> randomData = new RandomDataImpl(randomGenerator);<a name="line.144"></a> <FONT color="green">145</FONT> }<a name="line.145"></a> <FONT color="green">146</FONT> <a name="line.146"></a> <FONT color="green">147</FONT> <a name="line.147"></a> <FONT color="green">148</FONT> /**<a name="line.148"></a> <FONT color="green">149</FONT> * Create a NaturalRanking with the given NaNStrategy, TiesStrategy.RANDOM<a name="line.149"></a> <FONT color="green">150</FONT> * and the given source of random data.<a name="line.150"></a> <FONT color="green">151</FONT> *<a name="line.151"></a> <FONT color="green">152</FONT> * @param nanStrategy NaNStrategy to use<a name="line.152"></a> <FONT color="green">153</FONT> * @param randomGenerator source of random data<a name="line.153"></a> <FONT color="green">154</FONT> */<a name="line.154"></a> <FONT color="green">155</FONT> public NaturalRanking(NaNStrategy nanStrategy,<a name="line.155"></a> <FONT color="green">156</FONT> RandomGenerator randomGenerator) {<a name="line.156"></a> <FONT color="green">157</FONT> super();<a name="line.157"></a> <FONT color="green">158</FONT> this.nanStrategy = nanStrategy;<a name="line.158"></a> <FONT color="green">159</FONT> this.tiesStrategy = TiesStrategy.RANDOM;<a name="line.159"></a> <FONT color="green">160</FONT> randomData = new RandomDataImpl(randomGenerator);<a name="line.160"></a> <FONT color="green">161</FONT> }<a name="line.161"></a> <FONT color="green">162</FONT> <a name="line.162"></a> <FONT color="green">163</FONT> /**<a name="line.163"></a> <FONT color="green">164</FONT> * Return the NaNStrategy<a name="line.164"></a> <FONT color="green">165</FONT> *<a name="line.165"></a> <FONT color="green">166</FONT> * @return returns the NaNStrategy<a name="line.166"></a> <FONT color="green">167</FONT> */<a name="line.167"></a> <FONT color="green">168</FONT> public NaNStrategy getNanStrategy() {<a name="line.168"></a> <FONT color="green">169</FONT> return nanStrategy;<a name="line.169"></a> <FONT color="green">170</FONT> }<a name="line.170"></a> <FONT color="green">171</FONT> <a name="line.171"></a> <FONT color="green">172</FONT> /**<a name="line.172"></a> <FONT color="green">173</FONT> * Return the TiesStrategy<a name="line.173"></a> <FONT color="green">174</FONT> *<a name="line.174"></a> <FONT color="green">175</FONT> * @return the TiesStrategy<a name="line.175"></a> <FONT color="green">176</FONT> */<a name="line.176"></a> <FONT color="green">177</FONT> public TiesStrategy getTiesStrategy() {<a name="line.177"></a> <FONT color="green">178</FONT> return tiesStrategy;<a name="line.178"></a> <FONT color="green">179</FONT> }<a name="line.179"></a> <FONT color="green">180</FONT> <a name="line.180"></a> <FONT color="green">181</FONT> /**<a name="line.181"></a> <FONT color="green">182</FONT> * Rank <code>data</code> using the natural ordering on Doubles, with<a name="line.182"></a> <FONT color="green">183</FONT> * NaN values handled according to <code>nanStrategy</code> and ties<a name="line.183"></a> <FONT color="green">184</FONT> * resolved using <code>tiesStrategy.</code><a name="line.184"></a> <FONT color="green">185</FONT> *<a name="line.185"></a> <FONT color="green">186</FONT> * @param data array to be ranked<a name="line.186"></a> <FONT color="green">187</FONT> * @return array of ranks<a name="line.187"></a> <FONT color="green">188</FONT> */<a name="line.188"></a> <FONT color="green">189</FONT> public double[] rank(double[] data) {<a name="line.189"></a> <FONT color="green">190</FONT> <a name="line.190"></a> <FONT color="green">191</FONT> // Array recording initial positions of data to be ranked<a name="line.191"></a> <FONT color="green">192</FONT> IntDoublePair[] ranks = new IntDoublePair[data.length];<a name="line.192"></a> <FONT color="green">193</FONT> for (int i = 0; i < data.length; i++) {<a name="line.193"></a> <FONT color="green">194</FONT> ranks[i] = new IntDoublePair(data[i], i);<a name="line.194"></a> <FONT color="green">195</FONT> }<a name="line.195"></a> <FONT color="green">196</FONT> <a name="line.196"></a> <FONT color="green">197</FONT> // Recode, remove or record positions of NaNs<a name="line.197"></a> <FONT color="green">198</FONT> List<Integer> nanPositions = null;<a name="line.198"></a> <FONT color="green">199</FONT> switch (nanStrategy) {<a name="line.199"></a> <FONT color="green">200</FONT> case MAXIMAL: // Replace NaNs with +INFs<a name="line.200"></a> <FONT color="green">201</FONT> recodeNaNs(ranks, Double.POSITIVE_INFINITY);<a name="line.201"></a> <FONT color="green">202</FONT> break;<a name="line.202"></a> <FONT color="green">203</FONT> case MINIMAL: // Replace NaNs with -INFs<a name="line.203"></a> <FONT color="green">204</FONT> recodeNaNs(ranks, Double.NEGATIVE_INFINITY);<a name="line.204"></a> <FONT color="green">205</FONT> break;<a name="line.205"></a> <FONT color="green">206</FONT> case REMOVED: // Drop NaNs from data<a name="line.206"></a> <FONT color="green">207</FONT> ranks = removeNaNs(ranks);<a name="line.207"></a> <FONT color="green">208</FONT> break;<a name="line.208"></a> <FONT color="green">209</FONT> case FIXED: // Record positions of NaNs<a name="line.209"></a> <FONT color="green">210</FONT> nanPositions = getNanPositions(ranks);<a name="line.210"></a> <FONT color="green">211</FONT> break;<a name="line.211"></a> <FONT color="green">212</FONT> default: // this should not happen unless NaNStrategy enum is changed<a name="line.212"></a> <FONT color="green">213</FONT> throw MathRuntimeException.createInternalError(null);<a name="line.213"></a> <FONT color="green">214</FONT> }<a name="line.214"></a> <FONT color="green">215</FONT> <a name="line.215"></a> <FONT color="green">216</FONT> // Sort the IntDoublePairs<a name="line.216"></a> <FONT color="green">217</FONT> Arrays.sort(ranks);<a name="line.217"></a> <FONT color="green">218</FONT> <a name="line.218"></a> <FONT color="green">219</FONT> // Walk the sorted array, filling output array using sorted positions,<a name="line.219"></a> <FONT color="green">220</FONT> // resolving ties as we go<a name="line.220"></a> <FONT color="green">221</FONT> double[] out = new double[ranks.length];<a name="line.221"></a> <FONT color="green">222</FONT> int pos = 1; // position in sorted array<a name="line.222"></a> <FONT color="green">223</FONT> out[ranks[0].getPosition()] = pos;<a name="line.223"></a> <FONT color="green">224</FONT> List<Integer> tiesTrace = new ArrayList<Integer>();<a name="line.224"></a> <FONT color="green">225</FONT> tiesTrace.add(ranks[0].getPosition());<a name="line.225"></a> <FONT color="green">226</FONT> for (int i = 1; i < ranks.length; i++) {<a name="line.226"></a> <FONT color="green">227</FONT> if (Double.compare(ranks[i].getValue(), ranks[i - 1].getValue()) > 0) {<a name="line.227"></a> <FONT color="green">228</FONT> // tie sequence has ended (or had length 1)<a name="line.228"></a> <FONT color="green">229</FONT> pos = i + 1;<a name="line.229"></a> <FONT color="green">230</FONT> if (tiesTrace.size() > 1) { // if seq is nontrivial, resolve<a name="line.230"></a> <FONT color="green">231</FONT> resolveTie(out, tiesTrace);<a name="line.231"></a> <FONT color="green">232</FONT> }<a name="line.232"></a> <FONT color="green">233</FONT> tiesTrace = new ArrayList<Integer>();<a name="line.233"></a> <FONT color="green">234</FONT> tiesTrace.add(ranks[i].getPosition());<a name="line.234"></a> <FONT color="green">235</FONT> } else {<a name="line.235"></a> <FONT color="green">236</FONT> // tie sequence continues<a name="line.236"></a> <FONT color="green">237</FONT> tiesTrace.add(ranks[i].getPosition());<a name="line.237"></a> <FONT color="green">238</FONT> }<a name="line.238"></a> <FONT color="green">239</FONT> out[ranks[i].getPosition()] = pos;<a name="line.239"></a> <FONT color="green">240</FONT> }<a name="line.240"></a> <FONT color="green">241</FONT> if (tiesTrace.size() > 1) { // handle tie sequence at end<a name="line.241"></a> <FONT color="green">242</FONT> resolveTie(out, tiesTrace);<a name="line.242"></a> <FONT color="green">243</FONT> }<a name="line.243"></a> <FONT color="green">244</FONT> if (nanStrategy == NaNStrategy.FIXED) {<a name="line.244"></a> <FONT color="green">245</FONT> restoreNaNs(out, nanPositions);<a name="line.245"></a> <FONT color="green">246</FONT> }<a name="line.246"></a> <FONT color="green">247</FONT> return out;<a name="line.247"></a> <FONT color="green">248</FONT> }<a name="line.248"></a> <FONT color="green">249</FONT> <a name="line.249"></a> <FONT color="green">250</FONT> /**<a name="line.250"></a> <FONT color="green">251</FONT> * Returns an array that is a copy of the input array with IntDoublePairs<a name="line.251"></a> <FONT color="green">252</FONT> * having NaN values removed.<a name="line.252"></a> <FONT color="green">253</FONT> *<a name="line.253"></a> <FONT color="green">254</FONT> * @param ranks input array<a name="line.254"></a> <FONT color="green">255</FONT> * @return array with NaN-valued entries removed<a name="line.255"></a> <FONT color="green">256</FONT> */<a name="line.256"></a> <FONT color="green">257</FONT> private IntDoublePair[] removeNaNs(IntDoublePair[] ranks) {<a name="line.257"></a> <FONT color="green">258</FONT> if (!containsNaNs(ranks)) {<a name="line.258"></a> <FONT color="green">259</FONT> return ranks;<a name="line.259"></a> <FONT color="green">260</FONT> }<a name="line.260"></a> <FONT color="green">261</FONT> IntDoublePair[] outRanks = new IntDoublePair[ranks.length];<a name="line.261"></a> <FONT color="green">262</FONT> int j = 0;<a name="line.262"></a> <FONT color="green">263</FONT> for (int i = 0; i < ranks.length; i++) {<a name="line.263"></a> <FONT color="green">264</FONT> if (Double.isNaN(ranks[i].getValue())) {<a name="line.264"></a> <FONT color="green">265</FONT> // drop, but adjust original ranks of later elements<a name="line.265"></a> <FONT color="green">266</FONT> for (int k = i + 1; k < ranks.length; k++) {<a name="line.266"></a> <FONT color="green">267</FONT> ranks[k] = new IntDoublePair(<a name="line.267"></a> <FONT color="green">268</FONT> ranks[k].getValue(), ranks[k].getPosition() - 1);<a name="line.268"></a> <FONT color="green">269</FONT> }<a name="line.269"></a> <FONT color="green">270</FONT> } else {<a name="line.270"></a> <FONT color="green">271</FONT> outRanks[j] = new IntDoublePair(<a name="line.271"></a> <FONT color="green">272</FONT> ranks[i].getValue(), ranks[i].getPosition());<a name="line.272"></a> <FONT color="green">273</FONT> j++;<a name="line.273"></a> <FONT color="green">274</FONT> }<a name="line.274"></a> <FONT color="green">275</FONT> }<a name="line.275"></a> <FONT color="green">276</FONT> IntDoublePair[] returnRanks = new IntDoublePair[j];<a name="line.276"></a> <FONT color="green">277</FONT> System.arraycopy(outRanks, 0, returnRanks, 0, j);<a name="line.277"></a> <FONT color="green">278</FONT> return returnRanks;<a name="line.278"></a> <FONT color="green">279</FONT> }<a name="line.279"></a> <FONT color="green">280</FONT> <a name="line.280"></a> <FONT color="green">281</FONT> /**<a name="line.281"></a> <FONT color="green">282</FONT> * Recodes NaN values to the given value.<a name="line.282"></a> <FONT color="green">283</FONT> *<a name="line.283"></a> <FONT color="green">284</FONT> * @param ranks array to recode<a name="line.284"></a> <FONT color="green">285</FONT> * @param value the value to replace NaNs with<a name="line.285"></a> <FONT color="green">286</FONT> */<a name="line.286"></a> <FONT color="green">287</FONT> private void recodeNaNs(IntDoublePair[] ranks, double value) {<a name="line.287"></a> <FONT color="green">288</FONT> for (int i = 0; i < ranks.length; i++) {<a name="line.288"></a> <FONT color="green">289</FONT> if (Double.isNaN(ranks[i].getValue())) {<a name="line.289"></a> <FONT color="green">290</FONT> ranks[i] = new IntDoublePair(<a name="line.290"></a> <FONT color="green">291</FONT> value, ranks[i].getPosition());<a name="line.291"></a> <FONT color="green">292</FONT> }<a name="line.292"></a> <FONT color="green">293</FONT> }<a name="line.293"></a> <FONT color="green">294</FONT> }<a name="line.294"></a> <FONT color="green">295</FONT> <a name="line.295"></a> <FONT color="green">296</FONT> /**<a name="line.296"></a> <FONT color="green">297</FONT> * Checks for presence of NaNs in <code>ranks.</code><a name="line.297"></a> <FONT color="green">298</FONT> *<a name="line.298"></a> <FONT color="green">299</FONT> * @param ranks array to be searched for NaNs<a name="line.299"></a> <FONT color="green">300</FONT> * @return true iff ranks contains one or more NaNs<a name="line.300"></a> <FONT color="green">301</FONT> */<a name="line.301"></a> <FONT color="green">302</FONT> private boolean containsNaNs(IntDoublePair[] ranks) {<a name="line.302"></a> <FONT color="green">303</FONT> for (int i = 0; i < ranks.length; i++) {<a name="line.303"></a> <FONT color="green">304</FONT> if (Double.isNaN(ranks[i].getValue())) {<a name="line.304"></a> <FONT color="green">305</FONT> return true;<a name="line.305"></a> <FONT color="green">306</FONT> }<a name="line.306"></a> <FONT color="green">307</FONT> }<a name="line.307"></a> <FONT color="green">308</FONT> return false;<a name="line.308"></a> <FONT color="green">309</FONT> }<a name="line.309"></a> <FONT color="green">310</FONT> <a name="line.310"></a> <FONT color="green">311</FONT> /**<a name="line.311"></a> <FONT color="green">312</FONT> * Resolve a sequence of ties, using the configured {@link TiesStrategy}.<a name="line.312"></a> <FONT color="green">313</FONT> * The input <code>ranks</code> array is expected to take the same value<a name="line.313"></a> <FONT color="green">314</FONT> * for all indices in <code>tiesTrace</code>. The common value is recoded<a name="line.314"></a> <FONT color="green">315</FONT> * according to the tiesStrategy. For example, if ranks = <5,8,2,6,2,7,1,2>,<a name="line.315"></a> <FONT color="green">316</FONT> * tiesTrace = <2,4,7> and tiesStrategy is MINIMUM, ranks will be unchanged.<a name="line.316"></a> <FONT color="green">317</FONT> * The same array and trace with tiesStrategy AVERAGE will come out<a name="line.317"></a> <FONT color="green">318</FONT> * <5,8,3,6,3,7,1,3>.<a name="line.318"></a> <FONT color="green">319</FONT> *<a name="line.319"></a> <FONT color="green">320</FONT> * @param ranks array of ranks<a name="line.320"></a> <FONT color="green">321</FONT> * @param tiesTrace list of indices where <code>ranks</code> is constant<a name="line.321"></a> <FONT color="green">322</FONT> * -- that is, for any i and j in TiesTrace, <code> ranks[i] == ranks[j]<a name="line.322"></a> <FONT color="green">323</FONT> * </code><a name="line.323"></a> <FONT color="green">324</FONT> */<a name="line.324"></a> <FONT color="green">325</FONT> private void resolveTie(double[] ranks, List<Integer> tiesTrace) {<a name="line.325"></a> <FONT color="green">326</FONT> <a name="line.326"></a> <FONT color="green">327</FONT> // constant value of ranks over tiesTrace<a name="line.327"></a> <FONT color="green">328</FONT> final double c = ranks[tiesTrace.get(0)];<a name="line.328"></a> <FONT color="green">329</FONT> <a name="line.329"></a> <FONT color="green">330</FONT> // length of sequence of tied ranks<a name="line.330"></a> <FONT color="green">331</FONT> final int length = tiesTrace.size();<a name="line.331"></a> <FONT color="green">332</FONT> <a name="line.332"></a> <FONT color="green">333</FONT> switch (tiesStrategy) {<a name="line.333"></a> <FONT color="green">334</FONT> case AVERAGE: // Replace ranks with average<a name="line.334"></a> <FONT color="green">335</FONT> fill(ranks, tiesTrace, (2 * c + length - 1) / 2d);<a name="line.335"></a> <FONT color="green">336</FONT> break;<a name="line.336"></a> <FONT color="green">337</FONT> case MAXIMUM: // Replace ranks with maximum values<a name="line.337"></a> <FONT color="green">338</FONT> fill(ranks, tiesTrace, c + length - 1);<a name="line.338"></a> <FONT color="green">339</FONT> break;<a name="line.339"></a> <FONT color="green">340</FONT> case MINIMUM: // Replace ties with minimum<a name="line.340"></a> <FONT color="green">341</FONT> fill(ranks, tiesTrace, c);<a name="line.341"></a> <FONT color="green">342</FONT> break;<a name="line.342"></a> <FONT color="green">343</FONT> case RANDOM: // Fill with random integral values in [c, c + length - 1]<a name="line.343"></a> <FONT color="green">344</FONT> Iterator<Integer> iterator = tiesTrace.iterator();<a name="line.344"></a> <FONT color="green">345</FONT> long f = Math.round(c);<a name="line.345"></a> <FONT color="green">346</FONT> while (iterator.hasNext()) {<a name="line.346"></a> <FONT color="green">347</FONT> ranks[iterator.next()] =<a name="line.347"></a> <FONT color="green">348</FONT> randomData.nextLong(f, f + length - 1);<a name="line.348"></a> <FONT color="green">349</FONT> }<a name="line.349"></a> <FONT color="green">350</FONT> break;<a name="line.350"></a> <FONT color="green">351</FONT> case SEQUENTIAL: // Fill sequentially from c to c + length - 1<a name="line.351"></a> <FONT color="green">352</FONT> // walk and fill<a name="line.352"></a> <FONT color="green">353</FONT> iterator = tiesTrace.iterator();<a name="line.353"></a> <FONT color="green">354</FONT> f = Math.round(c);<a name="line.354"></a> <FONT color="green">355</FONT> int i = 0;<a name="line.355"></a> <FONT color="green">356</FONT> while (iterator.hasNext()) {<a name="line.356"></a> <FONT color="green">357</FONT> ranks[iterator.next()] = f + i++;<a name="line.357"></a> <FONT color="green">358</FONT> }<a name="line.358"></a> <FONT color="green">359</FONT> break;<a name="line.359"></a> <FONT color="green">360</FONT> default: // this should not happen unless TiesStrategy enum is changed<a name="line.360"></a> <FONT color="green">361</FONT> throw MathRuntimeException.createInternalError(null);<a name="line.361"></a> <FONT color="green">362</FONT> }<a name="line.362"></a> <FONT color="green">363</FONT> }<a name="line.363"></a> <FONT color="green">364</FONT> <a name="line.364"></a> <FONT color="green">365</FONT> /**<a name="line.365"></a> <FONT color="green">366</FONT> * Sets<code>data[i] = value</code> for each i in <code>tiesTrace.</code><a name="line.366"></a> <FONT color="green">367</FONT> *<a name="line.367"></a> <FONT color="green">368</FONT> * @param data array to modify<a name="line.368"></a> <FONT color="green">369</FONT> * @param tiesTrace list of index values to set<a name="line.369"></a> <FONT color="green">370</FONT> * @param value value to set<a name="line.370"></a> <FONT color="green">371</FONT> */<a name="line.371"></a> <FONT color="green">372</FONT> private void fill(double[] data, List<Integer> tiesTrace, double value) {<a name="line.372"></a> <FONT color="green">373</FONT> Iterator<Integer> iterator = tiesTrace.iterator();<a name="line.373"></a> <FONT color="green">374</FONT> while (iterator.hasNext()) {<a name="line.374"></a> <FONT color="green">375</FONT> data[iterator.next()] = value;<a name="line.375"></a> <FONT color="green">376</FONT> }<a name="line.376"></a> <FONT color="green">377</FONT> }<a name="line.377"></a> <FONT color="green">378</FONT> <a name="line.378"></a> <FONT color="green">379</FONT> /**<a name="line.379"></a> <FONT color="green">380</FONT> * Set <code>ranks[i] = Double.NaN</code> for each i in <code>nanPositions.</code><a name="line.380"></a> <FONT color="green">381</FONT> *<a name="line.381"></a> <FONT color="green">382</FONT> * @param ranks array to modify<a name="line.382"></a> <FONT color="green">383</FONT> * @param nanPositions list of index values to set to <code>Double.NaN</code><a name="line.383"></a> <FONT color="green">384</FONT> */<a name="line.384"></a> <FONT color="green">385</FONT> private void restoreNaNs(double[] ranks, List<Integer> nanPositions) {<a name="line.385"></a> <FONT color="green">386</FONT> if (nanPositions.size() == 0) {<a name="line.386"></a> <FONT color="green">387</FONT> return;<a name="line.387"></a> <FONT color="green">388</FONT> }<a name="line.388"></a> <FONT color="green">389</FONT> Iterator<Integer> iterator = nanPositions.iterator();<a name="line.389"></a> <FONT color="green">390</FONT> while (iterator.hasNext()) {<a name="line.390"></a> <FONT color="green">391</FONT> ranks[iterator.next().intValue()] = Double.NaN;<a name="line.391"></a> <FONT color="green">392</FONT> }<a name="line.392"></a> <FONT color="green">393</FONT> <a name="line.393"></a> <FONT color="green">394</FONT> }<a name="line.394"></a> <FONT color="green">395</FONT> <a name="line.395"></a> <FONT color="green">396</FONT> /**<a name="line.396"></a> <FONT color="green">397</FONT> * Returns a list of indexes where <code>ranks</code> is <code>NaN.</code><a name="line.397"></a> <FONT color="green">398</FONT> *<a name="line.398"></a> <FONT color="green">399</FONT> * @param ranks array to search for <code>NaNs</code><a name="line.399"></a> <FONT color="green">400</FONT> * @return list of indexes i such that <code>ranks[i] = NaN</code><a name="line.400"></a> <FONT color="green">401</FONT> */<a name="line.401"></a> <FONT color="green">402</FONT> private List<Integer> getNanPositions(IntDoublePair[] ranks) {<a name="line.402"></a> <FONT color="green">403</FONT> ArrayList<Integer> out = new ArrayList<Integer>();<a name="line.403"></a> <FONT color="green">404</FONT> for (int i = 0; i < ranks.length; i++) {<a name="line.404"></a> <FONT color="green">405</FONT> if (Double.isNaN(ranks[i].getValue())) {<a name="line.405"></a> <FONT color="green">406</FONT> out.add(Integer.valueOf(i));<a name="line.406"></a> <FONT color="green">407</FONT> }<a name="line.407"></a> <FONT color="green">408</FONT> }<a name="line.408"></a> <FONT color="green">409</FONT> return out;<a name="line.409"></a> <FONT color="green">410</FONT> }<a name="line.410"></a> <FONT color="green">411</FONT> <a name="line.411"></a> <FONT color="green">412</FONT> /**<a name="line.412"></a> <FONT color="green">413</FONT> * Represents the position of a double value in an ordering.<a name="line.413"></a> <FONT color="green">414</FONT> * Comparable interface is implemented so Arrays.sort can be used<a name="line.414"></a> <FONT color="green">415</FONT> * to sort an array of IntDoublePairs by value. Note that the<a name="line.415"></a> <FONT color="green">416</FONT> * implicitly defined natural ordering is NOT consistent with equals.<a name="line.416"></a> <FONT color="green">417</FONT> */<a name="line.417"></a> <FONT color="green">418</FONT> private static class IntDoublePair implements Comparable<IntDoublePair> {<a name="line.418"></a> <FONT color="green">419</FONT> <a name="line.419"></a> <FONT color="green">420</FONT> /** Value of the pair */<a name="line.420"></a> <FONT color="green">421</FONT> private final double value;<a name="line.421"></a> <FONT color="green">422</FONT> <a name="line.422"></a> <FONT color="green">423</FONT> /** Original position of the pair */<a name="line.423"></a> <FONT color="green">424</FONT> private final int position;<a name="line.424"></a> <FONT color="green">425</FONT> <a name="line.425"></a> <FONT color="green">426</FONT> /**<a name="line.426"></a> <FONT color="green">427</FONT> * Construct an IntDoublePair with the given value and position.<a name="line.427"></a> <FONT color="green">428</FONT> * @param value the value of the pair<a name="line.428"></a> <FONT color="green">429</FONT> * @param position the original position<a name="line.429"></a> <FONT color="green">430</FONT> */<a name="line.430"></a> <FONT color="green">431</FONT> public IntDoublePair(double value, int position) {<a name="line.431"></a> <FONT color="green">432</FONT> this.value = value;<a name="line.432"></a> <FONT color="green">433</FONT> this.position = position;<a name="line.433"></a> <FONT color="green">434</FONT> }<a name="line.434"></a> <FONT color="green">435</FONT> <a name="line.435"></a> <FONT color="green">436</FONT> /**<a name="line.436"></a> <FONT color="green">437</FONT> * Compare this IntDoublePair to another pair.<a name="line.437"></a> <FONT color="green">438</FONT> * Only the <strong>values</strong> are compared.<a name="line.438"></a> <FONT color="green">439</FONT> *<a name="line.439"></a> <FONT color="green">440</FONT> * @param other the other pair to compare this to<a name="line.440"></a> <FONT color="green">441</FONT> * @return result of <code>Double.compare(value, other.value)</code><a name="line.441"></a> <FONT color="green">442</FONT> */<a name="line.442"></a> <FONT color="green">443</FONT> public int compareTo(IntDoublePair other) {<a name="line.443"></a> <FONT color="green">444</FONT> return Double.compare(value, other.value);<a name="line.444"></a> <FONT color="green">445</FONT> }<a name="line.445"></a> <FONT color="green">446</FONT> <a name="line.446"></a> <FONT color="green">447</FONT> /**<a name="line.447"></a> <FONT color="green">448</FONT> * Returns the value of the pair.<a name="line.448"></a> <FONT color="green">449</FONT> * @return value<a name="line.449"></a> <FONT color="green">450</FONT> */<a name="line.450"></a> <FONT color="green">451</FONT> public double getValue() {<a name="line.451"></a> <FONT color="green">452</FONT> return value;<a name="line.452"></a> <FONT color="green">453</FONT> }<a name="line.453"></a> <FONT color="green">454</FONT> <a name="line.454"></a> <FONT color="green">455</FONT> /**<a name="line.455"></a> <FONT color="green">456</FONT> * Returns the original position of the pair.<a name="line.456"></a> <FONT color="green">457</FONT> * @return position<a name="line.457"></a> <FONT color="green">458</FONT> */<a name="line.458"></a> <FONT color="green">459</FONT> public int getPosition() {<a name="line.459"></a> <FONT color="green">460</FONT> return position;<a name="line.460"></a> <FONT color="green">461</FONT> }<a name="line.461"></a> <FONT color="green">462</FONT> }<a name="line.462"></a> <FONT color="green">463</FONT> }<a name="line.463"></a> </PRE> </BODY> </HTML>