統計一TXT文件中單詞出現頻率,輸出頻率最高的10個單詞
實驗過程
主要思路就是首先將標點符號,常用冠詞等替換掉,然後利用雜湊表和陣列原理排序,輸出最高頻率的前十個陣列
程式碼如下
import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Map.Entry;
public class test {
public static void main(String[] args) throws IOException {
long start = System.currentTimeMillis(); // 程式開始時間
File file = new File("E:/TEST.txt");
BufferedReader br = new BufferedReader(new FileReader(file));
StringBuilder sb = new StringBuilder();
String line = null;
while ((line = br.readLine()) != null) {
sb.append(line);
}
br.close(); // 關閉流
String words = sb.toString(); // 全部的單詞字串
String targetString = words.replaceAll("[.,\"\\?!:;\\(\\)]", ""); // 將標點替換為空
// 分詞並且定義英文中不代表實際意義的一些單詞,如介詞、代詞、情態動詞等
String[] singleWord = targetString.split(" ");
String[] keys = { "you", "i", "he", "she", "me", "him", "her", "it",
"they", "them", "we", "us", "your", "your", "our", "his",
"her", "its", "my", "in", "into", "on", "for", "out", "up",
"down", "at", "to","too", "with", "by", "about", "among", "between",
"over", "from", "be", "been", "am", "is", "are", "was", "were",
"whthout", "the", "of", "and", "a", "an", "that", "this", "be",
"or", "as", "will", "would", "can", "could", "may", "might",
"shall", "should", "must", "has", "have", "had", "than" };
// 將一部分常見的無意義的英語單詞替換為字元 '#' 以便後面輸出單詞出現次數時的判斷
for (int i = 0; i < singleWord.length; i++) {
for (String str : keys) {
if (singleWord[i].equals(str))
singleWord[i] = "#";
}
}
// 將單詞以及其出現的次數關聯起來
for (int i = 0; i < singleWord.length; i++) {
count++; // 計算單詞個數
if ((wordMap.get(singleWord[i]) != null)) {
int value = ((Integer) wordMap.get(singleWord[i])).intValue();
value++;
wordMap.put(singleWord[i].toLowerCase(), new Integer(value)); // 將單詞轉換為小寫存放以統一格式
} else {
wordMap.put(singleWord[i].toLowerCase(), new Integer(1));
}
}
System.out.println("\t\t--檔案資訊--");
System.out.println(" 名稱: " + file.getName() + " 大小: "
+ file.length()/ 1024 + "KB");
System.out.println("\t\t--檔案資訊--");
System.out.println();
System.out.println("■■■■ " + count + " 個單詞中出現頻率最高的 10 個單詞如下■■■■");
// 比較器, 按值排序
System.setProperty("java.util.Arrays.useLegacyMergeSort", "true");
List<Entry<String, Integer>> list = new ArrayList<Entry<String, Integer>>(
wordMap.entrySet());
Collections.sort(list, new Comparator<Entry<String, Integer>>() {
public int compare(Entry<String, Integer> e1,
Entry<String, Integer> e2) {
if (e2.getValue() != null && e1.getValue() != null
&& e2.getValue().compareTo(e1.getValue()) > 0) {
return 1;
} else {
return -1;
}
}
});
int wordCount = 1; // 記錄已經輸出單詞的個數
for (Map.Entry<String, Integer> entry : list) {
if (entry.getKey().equals("#")) // 相當於過濾作用,不輸出介詞、代詞、情態動詞等無意義單詞
continue;
System.out.printf("\t%2d、 %8s \t %4d次\n", wordCount,
entry.getKey(), entry.getValue());
if (wordCount++ == 10) { // 表示只輸出10個
long end = System.currentTimeMillis(); // 程式結束時間
System.out.println("■■■■■■■■■■■■■■■ 耗時 " + (end - start)
+ " ms" + " ■■■■■■■■■■■■■■■■");
return;
}
}
}
private static HashMap<String, Integer> wordMap = new HashMap<String, Integer>();
private static int count = 0;
}
執行結果如圖
、
並且用JDK自帶的visualVM測試工具進行測試,測試見截圖如下