textcategorization.java~10~

基于朴素贝叶斯算法实现的中文文本分类程序。可以对中文文本进行分类识别

/**
 * <p>Title: </p>
 * <p>Description: </p>
 * <p>Copyright: Copyright (c) 2005</p>
 * <p>Company: </p>
 * @author not attributable
 * @version 1.0
 */
import java.io.*;

public class TextCategorization {
  public static void main(String[] args) throws Exception{
                // Load the dictionary
                 Dictionary dic = new Dictionary("SDIC.txt");
                  // Construct a segmentor.
                  //FMMSegment seg = new FMMSegment(dic);

                  //String str = "分词系统演示";
                  //System.out.println(str);
                  //seg.wordSegment(str);
                  //System.out.println("----------------------------------");

                  //System.out.println("Segmention from a file ....");
                  //seg.fileSegment("sample/science.txt");
                  //System.out.println("----------------------------------");
                  System.out.println("--------------Start training-----------------");
                  Traning train=new Traning(dic);
                  train.loadVocabulary();
                  System.out.println("--------------End of training-----------------");
                  System.out.println("-------------start categorize text------------");
                  TargetText tt=new TargetText();
                  tt.init(dic);
                  tt.categorize(train.v,3,"testSample.txt");

                  //自动清空vocabulary文件
                  try{
                    BufferedWriter out=new BufferedWriter(new FileWriter("vocabulary.txt"));
                    out.write(new String(""),0,0);
                    out.flush();
                  }catch(Exception e){

                  }

          }

}