输出某个英文文本文件中 26 字母出现的频率,由高到低排列,并显示字母出现的百分比,精确到小数点后面两位。
字母频率 = 这个字母出现的次数 / (所有A-Z,a-z字母出现的总数)
如果两个字母出现的频率一样,那么就按照字典序排列。
字母频率 = 这个字母出现的次数 / (所有A-Z,a-z字母出现的总数)
如果两个字母出现的频率一样,那么就按照字典序排列。
package bianli;
import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.text.NumberFormat;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.text.NumberFormat;
public class ZiMu{
public class java {
}
public static void main(String[] args) throws Exception {
BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream("D:\信1807-5郝子嘉20183684\Harry Potter and the Sorcerer's Stone.txt")));
int[] count = new int[26];
char[] c = new char[1];
int len = br.read(c);
while(len!=-1) {
if(c[0]<='Z'&&c[0]>='A') {
int number = c[0];
count[number-65]++;
// COUNT[number-65]++;
}
if(c[0]<='z'&&c[0]>='a') {
int number = c[0];
count[number-97]++;
}
len = br.read(c);
}
count=Paixu(count);
Print(count);
System.out.print(" b.txt文件读取完毕!");
br.close();
}
public static int[] Paixu(int[] count)
{
int temp;
int size=count.length;
for(int i=0;i<size-1;i++)
{
for(int j=i+1;j<size;j++)
{
if(count[i]<count[j])
{
temp=count[j];
count[j]=count[i];
count[i]=temp;
}
}
}
return count;
}
public static void Print(int[] count) {
NumberFormat numberFormat = NumberFormat.getInstance();
// 设置精确到小数点后2位
numberFormat.setMaximumFractionDigits(2);
public static void main(String[] args) throws Exception {
BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream("D:\信1807-5郝子嘉20183684\Harry Potter and the Sorcerer's Stone.txt")));
int[] count = new int[26];
char[] c = new char[1];
int len = br.read(c);
while(len!=-1) {
if(c[0]<='Z'&&c[0]>='A') {
int number = c[0];
count[number-65]++;
// COUNT[number-65]++;
}
if(c[0]<='z'&&c[0]>='a') {
int number = c[0];
count[number-97]++;
}
len = br.read(c);
}
count=Paixu(count);
Print(count);
System.out.print(" b.txt文件读取完毕!");
br.close();
}
public static int[] Paixu(int[] count)
{
int temp;
int size=count.length;
for(int i=0;i<size-1;i++)
{
for(int j=i+1;j<size;j++)
{
if(count[i]<count[j])
{
temp=count[j];
count[j]=count[i];
count[i]=temp;
}
}
}
return count;
}
public static void Print(int[] count) {
NumberFormat numberFormat = NumberFormat.getInstance();
// 设置精确到小数点后2位
numberFormat.setMaximumFractionDigits(2);
int sum=0;
for(int i=0;i<count.length;i++)
{
sum=count[i]+sum;
}
String[] a=new String[count.length];
for(int i=0;i<count.length;i++)
{
a[i] = numberFormat.format((float) count[i] / (float) sum * 100);
}
for(int i=0;i<26;i++) {
if(count[i]>0) {
char lowerCase = (char)(i+101);
System.out.println(lowerCase+"("+count[i]+")"+"("+a[i]+"%)");
}
}
}
for(int i=0;i<count.length;i++)
{
sum=count[i]+sum;
}
String[] a=new String[count.length];
for(int i=0;i<count.length;i++)
{
a[i] = numberFormat.format((float) count[i] / (float) sum * 100);
}
for(int i=0;i<26;i++) {
if(count[i]>0) {
char lowerCase = (char)(i+101);
System.out.println(lowerCase+"("+count[i]+")"+"("+a[i]+"%)");
}
}
}
}
输出单个文件中的前 N 个最常出现的英语单词。
作用:一个用于统计文本文件中的英语单词出现频率的控制台程序;
package bianli;
import java.io.*;
import java.util.*;
import java.util.Map.Entry;
public class Word
{
public static int n=0;
public static void main(String[] args) {
Scanner input=new Scanner(System.in);
String s;
int count=0;
int num=1;
String file1="D:\\信1807-5郝子嘉20183684\\Harry Potter and the Sorcerer's Stone.txt";
try
{
BufferedReader a=new BufferedReader(new FileReader(file1));
StringBuffer c=new StringBuffer();
while((s = a.readLine()) != null)
{
c.append(s);
}
String m=c.toString().toLowerCase();
String [] d=m.split("[^a-zA-Z0-9]+");
Map<String , Integer> myTreeMap=new TreeMap<String, Integer>();
for(int i = 0; i < d.length; i++) {
if(myTreeMap.containsKey(d[i])) {
count = myTreeMap.get(d[i]);
myTreeMap.put(d[i], count + 1);
}
else {
myTreeMap.put(d[i], 1);
}
}
List<Map.Entry<String, Integer>> list = new ArrayList<Map.Entry<String, Integer>>(myTreeMap.entrySet());
Collections.sort(list, new Comparator<Map.Entry<String, Integer>>() {
public int compare(Entry<String, Integer> k1, Entry<String, Integer> k2) {
return k2.getValue().compareTo(k1.getValue());
}
});
System.out.println("请输入要输出前N名的N");
n=input.nextInt();
for(Map.Entry<String, Integer> map : list) {
if(num <= n) {
System.out.println(map.getKey() + map.getValue()+"/");
num++;
}
else break;
}
a.close();
}
catch(FileNotFoundException e)
{
System.out.println("找不到指定文件");
}
catch(IOException e)
{
System.out.println("文件读取错误");
}
System.out.println("输出完成");
}
}
{
public static int n=0;
public static void main(String[] args) {
Scanner input=new Scanner(System.in);
String s;
int count=0;
int num=1;
String file1="D:\\信1807-5郝子嘉20183684\\Harry Potter and the Sorcerer's Stone.txt";
try
{
BufferedReader a=new BufferedReader(new FileReader(file1));
StringBuffer c=new StringBuffer();
while((s = a.readLine()) != null)
{
c.append(s);
}
String m=c.toString().toLowerCase();
String [] d=m.split("[^a-zA-Z0-9]+");
Map<String , Integer> myTreeMap=new TreeMap<String, Integer>();
for(int i = 0; i < d.length; i++) {
if(myTreeMap.containsKey(d[i])) {
count = myTreeMap.get(d[i]);
myTreeMap.put(d[i], count + 1);
}
else {
myTreeMap.put(d[i], 1);
}
}
List<Map.Entry<String, Integer>> list = new ArrayList<Map.Entry<String, Integer>>(myTreeMap.entrySet());
Collections.sort(list, new Comparator<Map.Entry<String, Integer>>() {
public int compare(Entry<String, Integer> k1, Entry<String, Integer> k2) {
return k2.getValue().compareTo(k1.getValue());
}
});
System.out.println("请输入要输出前N名的N");
n=input.nextInt();
for(Map.Entry<String, Integer> map : list) {
if(num <= n) {
System.out.println(map.getKey() + map.getValue()+"/");
num++;
}
else break;
}
a.close();
}
catch(FileNotFoundException e)
{
System.out.println("找不到指定文件");
}
catch(IOException e)
{
System.out.println("文件读取错误");
}
System.out.println("输出完成");
}
}