weka：SimpleKMeans实现Class to clusters evaluation验证

最新推荐文章于 2020-11-06 13:33:54 发布

薄荷微光少年梦

最新推荐文章于 2020-11-06 13:33:54 发布

阅读量5.8k

点赞数

分类专栏： Data mining and Machine Learni

本文链接：https://blog.csdn.net/daliaojie/article/details/49230815

版权

Data mining and Machine Learni 专栏收录该内容

9 篇文章 0 订阅

订阅专栏

今天利用weka实现聚类的时候遇到如何使用java实现Class to clusters evaluation的问题，下面是核心代码。

package WekaProcess;


import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;

import weka.clusterers.ClusterEvaluation;
import weka.clusterers.EM;
import weka.clusterers.SimpleKMeans;
import weka.core.DistanceFunction;
import weka.core.EuclideanDistance;
import weka.core.Instances;
import weka.core.converters.ArffLoader;
import weka.filters.Filter;

public class StrongCluster {
	
	public static void Kmeans(String ArffFile)
	{
		 Instances ins = null;
	       Instances tempIns = null;
	      
	       SimpleKMeans KM = null;
	       DistanceFunction disFun = null;
	       try{
	           /*
	            * 1.读入样本
	            */
 
	
	          
	           Instances data = new Instances(new BufferedReader(new 
	        		   FileReader(ArffFile))); 
	        		   data.setClassIndex(data.numAttributes() - 1); 
	        		   //l 产生无类别的数据，并用下面代码训练 
	        		   weka .filters.unsupervised.attribute.Remove filter = new weka.filters.unsupervised.attribute.Remove(); 
	        		   filter.setAttributeIndices("" + (data.classIndex() + 1)); 
	        		   filter.setInputFormat(data); 
	        		   Instances dataClusterer = Filter.useFilter(data,filter); 
	        		 //  l 学习一个clusterer，比如EM 
	        		  /// EM clusterer = new EM(); 
	        		   // set further options for EM if necessary... 
	        		   KM = new SimpleKMeans();       
	    	           //设置聚类要得到的类别数量
	    	           KM.setNumClusters(2);
	    	           KM.setSeed(10);
	    	         /*
	    	            * 3.使用聚类算法对样本进行聚类
	    	            */
	    	           //KM.buildClusterer(ins);
	        		   KM.buildClusterer(dataClusterer); 
	        		 //  l 用仍然包含类别属性的数据集评价这个clusterer 
	        		   ClusterEvaluation evals = new ClusterEvaluation(); 
	        		   evals.setClusterer(KM); 
	        		   evals.evaluateClusterer(data);
	        		  // l 输出评价结果 
	        		   System.out.println(evals.clusterResultsToString()); 
	           
	           
	 
	       }catch(Exception e){
	           e.printStackTrace();
	       }
		
	}
	
	public static void DoCluster(String CSVfile)
	{
        System.out.println("Strong Cluster IS STARTED!!");
		
		//String CSVfile="D://fre21.csv";
		String InputArff=InputCSV.CSV2Arff(CSVfile);
		Kmeans(InputArff);
		
	}
	public static void main(String[] args) {

		System.out.println("Strong Cluster IS STARTED!!");
		
		String CSVfile="D://fre21.csv";
		String InputArff=InputCSV.CSV2Arff(CSVfile);
		Kmeans(InputArff);
		//Kmeans();
		
		
	}

}