Java编写的k-means文本聚类算法

Java编写的k-means文本聚类算法，lib文件中有IK-analysis的jar包，需要自己先导入到工程中，准确率能达到90%多，用于学习机器学习，可以运行

package algrithm.kmeans.text.byProduct;
import java.util.Comparator;
import java.util.Map;
import java.util.TreeMap;


public class ByValueComparator implements Comparator {
	 Map base;  
	    public ByValueComparator（Map base） {  
	        this.base = base;  
	    }  
	  
	    // Note: this comparator imposes orderings that are inconsistent with equals.      
	    public int compare（String a String b） {  
	        if （base.get（a） >= base.get（b）） {  
	            return -1;  
	        } else {  
	            return 1;  
	        } // returning 0 would merge keys  
	    }  
}

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件       1096  2015-07-21 09:33  DataStructTest\.classpath

     文件        390  2015-07-21 09:33  DataStructTest\.project

     文件         57  2015-07-21 09:33  DataStructTest\.settings\org.eclipse.core.resources.prefs

     文件         52  2015-07-21 09:33  DataStructTest\.settings\org.eclipse.core.runtime.prefs

     文件        598  2015-07-21 09:33  DataStructTest\.settings\org.eclipse.jdt.core.prefs

     文件        106  2015-07-21 09:33  DataStructTest\.settings\org.eclipse.ltk.core.refactoring.prefs

     文件        415  2015-07-21 09:33  DataStructTest\bin\algrithm\bayes\auxiliary\Classifier.class

     文件       2901  2015-07-21 09:33  DataStructTest\bin\algrithm\bayes\auxiliary\DataSet.class

     文件       4684  2015-07-21 09:33  DataStructTest\bin\algrithm\bayes\auxiliary\Evaluation.class

     文件       4531  2015-07-21 09:33  DataStructTest\bin\algrithm\bayes\auxiliary\NaiveBayes$CountProbility.class

     文件       3574  2015-07-21 09:33  DataStructTest\bin\algrithm\bayes\auxiliary\NaiveBayes.class

     文件       1476  2015-07-21 09:33  DataStructTest\bin\algrithm\bayes\dm13\TestAss3.class

     文件       4714  2015-07-21 09:33  DataStructTest\bin\algrithm\bayes2\bayes\Bayes.class

     文件       4223  2015-07-21 09:33  DataStructTest\bin\algrithm\bayes2\bayes\OriginalData.class

     文件        614  2015-07-21 09:33  DataStructTest\bin\algrithm\bayes2\bayes\Test.class

     文件       7748  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\figure\Kmeans.class

     文件       4225  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\figure\OriginalData.class

     文件       1208  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\figure\Test.class

     文件       1197  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byField\ByValueComparator.class

     文件      10408  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byField\Calculate.class

     文件       1987  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byField\Field.class

     文件       1529  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byField\Item.class

     文件       5479  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byField\Kmeans.class

     文件       1865  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byField\Similarity.class

     文件       3664  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byField\Test.class

     文件       1201  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byProduct\ByValueComparator.class

     文件      10931  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byProduct\Calculater.class

     文件       5223  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byProduct\Kmeans.class

     文件       3337  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byProduct\Product.class

     文件       1869  2015-07-21 09:33  DataStructTest\bin\algrithm\kmeans\text\byProduct\Similarity.class

............此处省略106个文件信息