用JAVA語(yǔ)言設(shè)計(jì)一個(gè)類,統(tǒng)計(jì)一篇英文文章的詞頻,并按照詞頻由高到低輸出。修改下面代碼就行了。

這題目如果能增加一個(gè)類的話會(huì)高效很多。。。如果非要在這個(gè)框框里面，代碼麻煩 效率低下呢。

創(chuàng)新互聯(lián)成立與2013年，先為留壩等服務(wù)建站，留壩等地企業(yè)，進(jìn)行企業(yè)商務(wù)咨詢服務(wù)。為留壩企業(yè)網(wǎng)站制作PC+手機(jī)+微官網(wǎng)三網(wǎng)同步一站式服務(wù)解決您的所有建站問(wèn)題。

import java.util.ArrayList;

import java.util.Collections;

import java.util.Comparator;

import java.util.Iterator;

import java.util.List;

import java.util.Set;

import java.util.TreeSet;

public class Article {

//保存文章的內(nèi)容

String content;

//保存分割后的單詞集合

String[] rawWords;

//保存統(tǒng)計(jì)后的單詞集合

String[] words;

//保存單詞對(duì)應(yīng)的詞頻

int[] wordFreqs;

//構(gòu)造函數(shù)，輸入文章內(nèi)容

//提高部分：從文件中讀取

public Article() {

content = "kolya is one of the richest films i've seen in some time . zdenek sverak plays a confirmed old bachelor ( who's likely to remain so ) , who finds his life as a czech cellist increasingly impacted by the five-year old boy that he's taking care of . though it ends rather abruptly-- and i'm whining , 'cause i wanted to spend more time with these characters-- the acting , writing , and production values are as high as , if not higher than , comparable american dramas . this father-and-son delight-- sverak also wrote the script , while his son , jan , directed-- won a golden globe for best foreign language film and , a couple days after i saw it , walked away an oscar . in czech and russian , with english subtitles . ";

}

//對(duì)文章根據(jù)分隔符進(jìn)行分詞,將結(jié)果保存到rawWords數(shù)組中

public void splitWord(){

//分詞的時(shí)候，因?yàn)闃?biāo)點(diǎn)符號(hào)不參與，所以所有的符號(hào)全部替換為空格

final char SPACE = ' ';

content = content.replace('\'', SPACE).replace(',', SPACE).replace('.', SPACE);

content = content.replace('(', SPACE).replace(')', SPACE).replace('-', SPACE);

rawWords = content.split("\\s+");//凡是空格隔開(kāi)的都算單詞，上面替換了', 所以I've 被分成2個(gè) //單詞

}

//統(tǒng)計(jì)詞，遍歷數(shù)組

public void countWordFreq() {

//將所有出現(xiàn)的字符串放入唯一的set中，不用map,是因?yàn)閙ap尋找效率太低了

SetString set = new TreeSetString();

for(String word: rawWords){

set.add(word);

}

Iterator ite = set.iterator();

ListString wordsList = new ArrayListString();

ListInteger freqList = new ArrayListInteger();

//多少個(gè)字符串未知，所以用list來(lái)保存先

while(ite.hasNext()){

String word = (String) ite.next();

int count = 0;//統(tǒng)計(jì)相同字符串的個(gè)數(shù)

for(String str: rawWords){

if(str.equals(word)){

count++;

}

}

wordsList.add(word);

freqList.add(count++);

}

//存入數(shù)組當(dāng)中

words = wordsList.toArray(new String[0]);

wordFreqs = new int[freqList.size()];

for(int i = 0; i freqList.size(); i++){

wordFreqs[i] = freqList.get(i);

}

}

//根據(jù)詞頻，將詞數(shù)組和詞頻數(shù)組進(jìn)行降序排序

public void sort() {

class Word{

private String word;

private int freq;

public Word(String word, int freq){

this.word = word;

this.freq = freq;

}

}

//注意：此處排序，1）首先按照詞頻降序排列， 2）如果詞頻相同，按照字母降序排列，

//如 'abc' 'ab' 'aa'

class WordComparator implements Comparator{

public int compare(Object o1, Object o2) {

Word word1 = (Word) o1;

Word word2 = (Word) o2;

if(word1.freq word2.freq){

return 1;

}else if(word1.freq word2.freq){

return -1;

}else{

int len1 = word1.word.trim().length();

int len2 = word2.word.trim().length();

String min = len1 len2? word2.word: word1.word;

String max = len1 len2? word1.word: word2.word;

for(int i = 0; i min.length(); i++){

if(min.charAt(i) max.charAt(i)){

return 1;

}

}

return 1;

}

}

}

List wordList = new ArrayListWord();

for(int i = 0; i words.length; i++){

wordList.add(new Word(words[i], wordFreqs[i]));

}

Collections.sort(wordList, new WordComparator());

for(int i = 0; i wordList.size(); i++){

Word wor = (Word) wordList.get(i);

words[i] = wor.word;

wordFreqs[i] = wor.freq;

}

}

//將排序結(jié)果輸出

public void printResult() {

System.out.println("Total " + words.length + " different words in the content!");

for(int i = 0; i words.length; i++){

System.out.println(wordFreqs[i] + " " + words[i]);

}

}

//測(cè)試類的功能

public static void main(String[] args) {

Article a = new Article();

a.splitWord();

a.countWordFreq();

a.sort();

a.printResult();

}

}

-----------------------

Total 99 different words in the content!

5 and

4 the

4 i

4 a

3 as

2 with

2 who

2 to

2 time

2 sverak

2 son

2 s

2 old

2 of

2 it

2 in

2 his

2 czech

1 zdenek

1 year

1 wrote

1 writing

1 won

1 whining

1 while

1 wanted

1 walked

1 ve

1 values

1 though

1 this

1 these

1 that

1 than

1 taking

1 subtitles

1 spend

1 some

1 so

1 seen

1 script

1 saw

1 russian

1 richest

1 remain

1 rather

1 production

1 plays

1 oscar

1 one

1 not

1 more

1 m

1 likely

1 life

1 language

1 kolya

1 jan

1 is

1 increasingly

1 impacted

1 if

1 higher

1 high

1 he

1 golden

1 globe

1 foreign

1 for

1 five

1 finds

1 films

1 film

1 father

1 english

1 ends

1 dramas

1 directed

1 delight

1 days

1 couple

1 confirmed

1 comparable

1 characters

1 cellist

1 cause

1 care

1 by

1 boy

1 best

1 bachelor

1 away

1 are

1 an

1 american

1 also

1 after

1 acting

1 abruptly

java 程序編程出現(xiàn)警告

1.告警是你使用Map時(shí)沒(méi)有指定具體類型,你可以為其指定相應(yīng)的類型MapString,Integermap = new HashMapString,Integer();

2.第一句是獲取Map的Entry集合,你可以查看JDK幫助文檔看看Entry的數(shù)據(jù)結(jié)構(gòu).

第二句是獲取Set的迭代器,后面的代碼是通過(guò)迭代器,迭代出每個(gè)Entry對(duì)象.

3.自己寫個(gè)冒泡算法,把Map中的記錄排序下.

java計(jì)算一篇英文文檔詞頻 并按出現(xiàn)次數(shù)從高到低輸出（以下基礎(chǔ)上補(bǔ)充）謝謝！

String result = sb.toString();

String[] Str = result.split("[^A-Za-z0-9]"); //quanbu

for(String string:Str){

singleSet.add(string);

if("".equals(string)){ //這里是我加的，去除空格次數(shù)的處理

singleSet.remove("");

}

}

MapString, Integer map=new HashMapString, Integer();

for (String childString : singleSet){

int count=0;

for(String fatherString : Str){

if(fatherString.equals(childString)){

count++;

}

}

map.put(childString, count); //存儲(chǔ)在hashmap中

}

ArrayListEntryString,Integer l = new ArrayListEntryString,Integer(map.entrySet());

Collections.sort(l, new ComparatorObject(){

public int compare(Object e1, Object e2){

int v1 = Integer.parseInt(((EntryString,Integer)e1).getValue().toString());

int v2 = Integer.parseInt(((Entry)e2).getValue().toString());

return v2-v1; //改為v1-v2就是從小到大了

}

});

for (EntryString, Integer e: l){

System.out.println(e.getKey()+" "+e.getValue());

}

代碼僅供參考！希望對(duì)你有用

java程序：統(tǒng)計(jì)單詞詞頻，

不多說(shuō)，先看代碼：

import java.util.*;

import java.io.*;

public class wordsRate {

public static void main(String[] args) throws Exception {

BufferedReader infile = new BufferedReader(new FileReader("article.txt"));

String string;

String file = null;

while ((string = infile.readLine()) != null) {

file += string;

}

file = file.toLowerCase();

file = file.replaceAll("[^A-Za-z]", " ");

file = file.replaceAll("\\s+", " ");

String words[];

words = file.split("\\s+");

MapString, Integer hashMap = new HashMapString, Integer();

for (int i = 0; i words.length; i++) {

String key = words[i];

if (hashMap.get(key) != null) {

int value = ((Integer) hashMap.get(key)).intValue();

value++;

hashMap.put(key, new Integer(value));

} else {

hashMap.put(key, new Integer(1));

}

}

MapString, Object treeMap = new TreeMapString, Object(hashMap);

MapString, Object treeMap1 = new TreeMapString, Object(hashMap);

BufferedWriter bw = new BufferedWriter(new FileWriter("result.txt"));

//下面是我改動(dòng)的你的代碼：

Iterator iter = treeMap.entrySet().iterator();

//定義兩個(gè)新的數(shù)組ss1和ss2，數(shù)組長(zhǎng)度就是hashMap的長(zhǎng)度，里面放分別是hashMap的value和key

String ss1[]=new String[treeMap.size()];;

int ss2[]=new int[treeMap.size()];

int i=0;

while (iter.hasNext()) {

Map.Entry entry = (Map.Entry) iter.next();

int val = (Integer)entry.getValue();

String key =(String) entry.getKey();

ss1[i]=key;

ss2[i]=val;

i++;

}

//下面將ss1數(shù)組進(jìn)行排序,并將其與ss2數(shù)組的內(nèi)容相對(duì)應(yīng)起來(lái)

int sValue=0;

String sKey="";

for(int j=0;jss2.length;j++){

for(int k=0;ki;k++){

if(ss2[j]ss2[k]){

sValue=ss2[j];

sKey=ss1[j];

ss2[j]=ss2[k];

ss1[j]=ss1[k];

ss2[k]=sValue;

ss1[k]=sKey;

}

}

}

for(int j=0;jss2.length;j++){

System.out.println(ss1[j]+"="+ss2[j]);

bw.write(ss1[j]+"="+ss2[j]);

bw.newLine();

bw.flush();

}

}

}

代碼是本人自己寫的，也經(jīng)過(guò)了自己的驗(yàn)證，肯定沒(méi)問(wèn)題，希望采納。

功能實(shí)現(xiàn)了，我是將其key和value值放在了數(shù)組之中，然后進(jìn)行排序，將其輸出到了txt文件里

排序方式不一樣，實(shí)現(xiàn)的方式也不一樣，所謂仁者見(jiàn)仁智者見(jiàn)智。

當(dāng)前名稱：java漢字查詞頻源代碼 java怎么查api字典
文章起源：http://chinadenli.net/article38/dojgcpp.html

成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián)，為您提供云服務(wù)器、網(wǎng)站排名、移動(dòng)網(wǎng)站建設(shè)、建站公司、動(dòng)態(tài)網(wǎng)站、網(wǎng)頁(yè)設(shè)計(jì)公司

廣告

聲明：本網(wǎng)站發(fā)布的內(nèi)容（圖片、視頻和文字）以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主，如果涉及侵權(quán)請(qǐng)盡快告知，我們將會(huì)在第一時(shí)間刪除。文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng)，如需處理請(qǐng)聯(lián)系客服。電話：028-86922220；郵箱：631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載，或轉(zhuǎn)載時(shí)需注明來(lái)源： 創(chuàng)新互聯(lián)