词向量的kmeans词聚类实现

package com.alg.qid.kmeans;

import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.List;

import com.alg.qid.word2vec.VectorModel;

public class Kmeans {
    
    private int K;
    static int vecsize=300;//向量长度
    
    public static void main(String[] args) throws IOException{
        if(args.length < 1){
            System.err.println("parameter missing");
        }
        Kmeans kmclass = new Kmeans();
        HashSet<String> title2word = new HashSet<String>();
        int k=1000;
        HashMap<String, float[]> title2vec = new HashMap<String, float[]>();
        VectorModel vm = VectorModel.loadFromFile(args[1]);
        System.out.println(vm.getVectorSize());
        BufferedReader br = new BufferedReader(new InputStreamReader(
                new FileInputStream(args[2]), "utf-8"));
        PrintWriter pw = new PrintWriter(new OutputStreamWriter(
                new FileOutputStream(args[2] + ".kmeans"), "utf-8"), true);
        String line = null; 
        int count = 0;
        while ((line = br.readLine()) != null){
            count +=1;
            System.out.println(count);
            String[] words=line.split("\t");
            if (!vm.getWordM