java topn_java实现文件单词频率统计 topN top K

java 实现单词计数.top N

思路

先统计每个单词出现的个数

利用 TreeSet 的自动排序的功能

上代码

wordcount

public void wordCount() {

String route = "青岛路 青岛路 济阳路口东 济南路 宴坡路 ";

Map<String, Integer> map = new HashMap<String, Integer>();

StringTokenizer st = new StringTokenizer(route, " ");

while (st.hasMoreTokens()) {

String letter = st.nextToken();

int count;

if (map.get(letter) == null) {

count = 1;

} else {

count = map.get(letter).intValue() + 1;

}

map.put(letter, count);

}

Set<StationEntity> set = new TreeSet<StationEntity>();

for (String word : map.keySet()) {

set.add(new StationEntity(word, map.get(word)));

System.out.println("word" + word + ":" + map.get(word));

}

System.out.println(" 输出形式 --");

for (Iterator<StationEntity> it = set.iterator(); it.hasNext(); ) {

StationEntity station = it.next();

System.out.println(station.getName() + "=" + station.getCount());

System.out.println("station"+station+":");

}

}

2.StationEntity

package com.dk.route;

/**

* Created by zzy on 15/11/28.

*/

public class StationEntity implements Comparable<StationEntity>{

private String name ;

public int getCount() {

return count;

}

public void setCount(int count) {

this.count = count;

}

public String getName() {

return name;

}

public void setName(String name) {

this.name = name;

}

private int count;

public StationEntity(String name,int count){

this.name = name;

this.count = count;

}

public int compareTo(StationEntity o) {

int cmp = count - o.count;

StationEntity s = (StationEntity)o ;

return cmp ==0 ?name.compareTo(o.name):-cmp;

}

}

3.运行结果