Java实现的一个词频统计程序

[java]  view plain  copy

 

1. import java.util.HashMap;  
2. import java.util.Iterator;  
3.   
4. public class WordCount {  
5.     public static void main(String[] args) {  
6.         String[] text=new String[]{"the weather is good ","today is good","today has good weather","good weather is good"};  
7.         HashMap<String, Integer> hashMap=new HashMap<String, Integer>();  
8.         for (int i=0;i<text.length;i++){  
9.             String temp=text[i];  
10.             String[] words=temp.split("\\s");  
11.             for(int j=0;j<words.length;j++){  
12.                 if(!hashMap.containsKey(words[j])){  
13.                     hashMap.put(words[j], new Integer(1));  
14.                 }else{  
15.                     int k=hashMap.get(words[j]).intValue()+1;  
16.                     hashMap.put(words[j], new Integer(k));  
17.                 }  
18.             }  
19.         }  
20.         Iterator iterator=hashMap.keySet().iterator();  
21.         while(iterator.hasNext()){  
22.             String word=(String) iterator.next();  
23.             System.out.println(word+":"+hashMap.get(word));  
24.         }  
25.     }  
26. }  

[java]  view plain  copy

 

1. 改进版：  

[java]  view plain  copy

 

1. <pre name="code" class="java">package jdbcExc;  
2. import java.io.BufferedReader;  
3. import java.io.FileNotFoundException;  
4. import java.io.FileReader;  
5. import java.io.IOException;  
6. import java.util.HashMap;  
7. import java.util.Iterator;  
8. import java.util.StringTokenizer;  
9.   
10. public class WordCount1 {  
11.     public static void main(String[] args) {  
12.         //用HashMap存放<单词:词频>这样一个映射关系  
13.         HashMap<String, Integer> hashMap=new HashMap<String, Integer>();  
14.         //用正则表达式来过滤字符串中的所有标点符号  
15.         String regex = "[【】、.。,\"!--;:?\'\\]]";   
16.         try {  
17.             //读取要处理的文件  
18.             BufferedReader br=new BufferedReader(new FileReader("F:\\file80.txt"));  
19.             String value;  
20.             while((value=br.readLine())!=null){  
21.                 value=value.replaceAll(regex, " ");  
22.                 //使用StringTokenizer来分词(StringTokenizer详见JDK文档)  
23.                 StringTokenizer tokenizer = new StringTokenizer(value);  
24.                 while(tokenizer.hasMoreTokens()){  
25.                     String word=tokenizer.nextToken();  
26.                     if(!hashMap.containsKey(word)){    
27.                         hashMap.put(word, new Integer(1));    
28.                     }else{    
29.                         int k=hashMap.get(word).intValue()+1;    
30.                         hashMap.put(word, new Integer(k));    
31.                     }    
32.                 }  
33.             }  
34.             //遍历HashMap,输出结果  
35.             Iterator iterator=hashMap.keySet().iterator();    
36.             while(iterator.hasNext()){    
37.                 String word=(String) iterator.next();    
38.                 System.out.println(word+":\t"+hashMap.get(word));    
39.             }    
40.         } catch (FileNotFoundException e) {  
41.             e.printStackTrace();  
42.         } catch (IOException e) {  
43.             e.printStackTrace();  
44.         }  
45.     }  
46. }