原文:http://blog.csdn.net/anqiang1984/article/details/4048177
package com.csdn;
import java.io.File;
import weka.attributeSelection.InfoGainAttributeEval;
import weka.attributeSelection.Ranker;
import weka.classifiers.Classifier;
import weka.core.Instances;
import weka.core.converters.ArffLoader;
public class SimpleAttributeSelection {
public static void main(String[] args) {
Instances trainIns = null;
try{
File file= new File("C://Program Files//Weka-3-6//data//segment-challenge.arff");
ArffLoader loader = new ArffLoader();
loader.setFile(file);
trainIns = loader.getDataSet();
//在使用样本之前一定要首先设置instances的classIndex,否则在使用instances对象是会抛出异常
trainIns.setClassIndex(trainIns.numAttributes()-1);
Ranker rank = new Ranker();
InfoGainAttributeEval eval = new InfoGainAttributeEval();
eval.buildEvaluator(trainIns);
//System.out.println(rank.search(eval, trainIns));
int[] attrIndex = rank.search(eval, trainIns);
StringBuffer attrIndexInfo = new StringBuffer();
StringBuffer attrInfoGainInfo = new StringBuffer();
attrIndexInfo.append("Selected attributes:");
attrInfoGainInfo.append("Ranked attributes:/n");
for(int i = 0; i < attrIndex.length; i ++){
attrIndexInfo.append(attrIndex[i]);
attrIndexInfo.append(",");
attrInfoGainInfo.append(eval.evaluateAttribute(attrIndex[i]));
attrInfoGainInfo.append("/t");
attrInfoGainInfo.append((trainIns.attribute(attrIndex[i]).name()));
attrInfoGainInfo.append("/n");
}
System.out.println(attrIndexInfo.toString());
System.out.println(attrInfoGainInfo.toString());
}catch(Exception e){
e.printStackTrace();
}
}
}
在这个实例中,我用了InfoGain的属性选择类来进行特征选择。InfoGainAttributeEval主要是计算出各个属性的InfoGain信息。同时在weka中为属性选择方法配备的有搜索算法(seacher method),在这里我们用最简单的Ranker类。它对属性进行了简单的排序。在Weka中我们还可以对搜索算法设置一些其它的属性,例如设置搜索的属性集,阈值等等,如果有需求大家可以进行详细的设置。
在最后我们打印了一些结果信息,打印了各个属性的InfoGain的信息。