统计英文单词词频

统计英文单词词频–Java

思想：首先英文文章中有很多标点符号，所以我们不妨把所有的标点或者与英文单词无关的字符变成空格，之后把所有的单词按空格切分装进数组里，然后用集合统计单词的词频，最后排序，废话不多说，直接上代码。

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashMap;
import java.util.Map;
import java.util.Map.Entry;


public class WordFrequency {
    public static String Read_File(String filename) {
        // TODO Auto-generated method stub
        String line = null;
        StringBuffer sb = new StringBuffer();
        try {
            BufferedReader br = new BufferedReader(new FileReader(filename));
            while((line = br.readLine()) != null){
                sb.append(line + "\n");
            }
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
        return sb.toString();//读文件，将文章中的所有句子变成一个字符串。

    }

    public static HashMap Char_to_Space(String article) {
        // TODO Auto-generated method stub
        String space = " ";
        article = article.replaceAll("\"",space).replaceAll(",", space).replaceAll("\\.", space);
        article = article.replaceAll(":", space).replaceAll("\\?", space);//用空格替换标点，当然这种方法很拙劣，笔者只是为了省事，最好还是用正则。
        article = article.replaceAll("\\s+", " ");//多个空格变成一个空格
        article = article.toLowerCase();//将所有单词转换为小写

        String[] wordlist = article.split(" ");//分割单词
        HashMap<String,Integer> hm = new HashMap();
        for(String word : wordlist){
            if(hm.containsKey(word)){
                Integer count = hm.get(word);
                count ++;
                hm.put(word, count);
            }
            else{
                hm.put(word, 1);
            }
        }
        //System.out.println(hm);
        //System.out.println(article);
        return hm;
    }

    //排序，这里是按照value排序。
    public static void Sort(HashMap hm) {
        // TODO Auto-generated method stub
        ArrayList <Map.Entry<String, Integer>> list = new ArrayList(hm.entrySet());
        Collections.sort(list,new Comparator<Map.Entry<String, Integer>>() {

            @Override
            public int compare(Entry<String, Integer> o1,
                    Entry<String, Integer> o2) {
                // TODO Auto-generated method stub
                return o1.getValue() - o2.getValue();
            }

        });

        System.out.println(list);
    }

    public static void main(String[] args) {
        // TODO Auto-generated method stub
        String filename = "D:\\word.txt";
        String article = Read_File(filename);
        HashMap hm = Char_to_Space(article);
        Sort(hm);
    }   

}

另外，更多HashMap排序请戳这里