课堂测试-统计单词个数和字母出现频率
Posted zlc364624
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了课堂测试-统计单词个数和字母出现频率相关的知识，希望对你有一定的参考价值。
testtwo.class
package classthird; import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.FileOutputStream; import java.io.IOException; import java.io.InputStreamReader; import java.io.OutputStreamWriter; import java.text.DecimalFormat; import java.util.HashMap; import java.util.Map; public class testtwo { public Map<String,Integer> map1=new HashMap<String,Integer>(); public static void main(String arg[]) { test("D:\\\\Test\\\\a.txt"); } public static void test(String path) { try { char shu[] = new char[1000];//存储单个字母内容 char zimu[] = new char[26];//存储字母‘a-z’ String h1[]=new String[1000]; //存储原文内容 String word3[]=new String[1000]; //存储单词 String word4[]=new String[1000]; //存储单词 String word5[]=new String[1000]; //存储单词 int countword[]=new int[1000]; int countwordtwo=0; double count[]=new double[26]; int j=0; String pathname=path; File filename=new File(pathname); InputStreamReader reader=new InputStreamReader(new FileInputStream(filename)); BufferedReader br=new BufferedReader(reader); String line[]=new String[100];; for(int i=0;i<line.length;i++) { line[i]=br.readLine(); } br.close(); int k=0; while(line[k]!=null) { for(int i=0;i<line[k].length();i++) { shu[j]=line[k].charAt(i); j++; } k++; } for(int i=0;i<shu.length;i++) { switch(shu[i]) { case ‘a‘:zimu[0]=‘a‘;count[0]++;break; case ‘b‘:zimu[1]=‘b‘;count[1]++;break; case ‘c‘:zimu[2]=‘c‘;count[2]++;break; case ‘d‘:zimu[3]=‘d‘;count[3]++;break; case ‘e‘:zimu[4]=‘e‘;count[4]++;break; case ‘f‘:zimu[5]=‘f‘;count[5]++;break; case ‘g‘:zimu[6]=‘g‘;count[6]++;break; case ‘h‘:zimu[7]=‘h‘;count[7]++;break; case ‘i‘:zimu[8]=‘i‘;count[8]++;break; case ‘j‘:zimu[9]=‘j‘;count[9]++;break; case ‘k‘:zimu[10]=‘k‘;count[10]++;break; case ‘l‘:zimu[11]=‘l‘;count[11]++;break; case ‘m‘:zimu[12]=‘m‘;count[12]++;break; case ‘n‘:zimu[13]=‘n‘;count[13]++;break; case ‘o‘:zimu[14]=‘o‘;count[14]++;break; case ‘p‘:zimu[15]=‘p‘;count[15]++;break; case ‘q‘:zimu[16]=‘q‘;count[16]++;break; case ‘r‘:zimu[17]=‘r‘;count[17]++;break; case ‘s‘:zimu[18]=‘s‘;count[18]++;break; case ‘t‘:zimu[19]=‘t‘;count[19]++;break; case ‘u‘:zimu[20]=‘u‘;count[20]++;break; case ‘v‘:zimu[21]=‘v‘;count[21]++;break; case ‘w‘:zimu[22]=‘w‘;count[22]++;break; case ‘x‘:zimu[23]=‘x‘;count[23]++;break; case ‘y‘:zimu[24]=‘y‘;count[24]++;break; case ‘z‘:zimu[25]=‘z‘;count[25]++;break; case ‘A‘:zimu[0]=‘a‘;count[0]++;break; case ‘B‘:zimu[1]=‘b‘;count[1]++;break; case ‘C‘:zimu[2]=‘c‘;count[2]++;break; case ‘D‘:zimu[3]=‘d‘;count[3]++;break; case ‘E‘:zimu[4]=‘e‘;count[4]++;break; case ‘F‘:zimu[5]=‘f‘;count[5]++;break; case ‘G‘:zimu[6]=‘g‘;count[6]++;break; case ‘H‘:zimu[7]=‘h‘;count[7]++;break; case ‘I‘:zimu[8]=‘i‘;count[8]++;break; case ‘J‘:zimu[9]=‘g‘;count[9]++;break; case ‘K‘:zimu[10]=‘k‘;count[10]++;break; case ‘L‘:zimu[11]=‘l‘;count[11]++;break; case ‘M‘:zimu[12]=‘m‘;count[12]++;break; case ‘N‘:zimu[13]=‘n‘;count[13]++;break; case ‘O‘:zimu[14]=‘o‘;count[14]++;break; case ‘P‘:zimu[15]=‘p‘;count[15]++;break; case ‘Q‘:zimu[16]=‘q‘;count[16]++;break; case ‘R‘:zimu[17]=‘r‘;count[17]++;break; case ‘S‘:zimu[18]=‘s‘;count[18]++;break; case ‘T‘:zimu[19]=‘t‘;count[19]++;break; case ‘U‘:zimu[20]=‘u‘;count[20]++;break; case ‘V‘:zimu[21]=‘v‘;count[24]++;break; case ‘W‘:zimu[22]=‘w‘;count[22]++;break; case ‘X‘:zimu[23]=‘x‘;count[23]++;break; case ‘Y‘:zimu[24]=‘y‘;count[24]++;break; case ‘Z‘:zimu[25]=‘z‘;count[25]++; } } int ci=0; double sum=0; double a1; double max=0; DecimalFormat df = new DecimalFormat( "0.00"); System.out.println("短文中各字母出现情况统计如下："); for(int i=0;i<26;i++) { if(count[i]!=0) { sum+=count[i]; } }///求字母总数 for (int x = 0; x < 26 - 1; x++) { for (int y = x + 1; y < 26; y++) { if (count[x] > count[y]) { double temp = count[x]; count[x] = count[y]; count[y] = temp; char temp1=zimu[x]; zimu[x] = zimu[y]; zimu[y] = temp1; } } } for(int i=0;i<26;i++) { if(count[i]!=0) { ci++; a1=count[i]/sum*100; System.out.println(ci+".字母"+zimu[i]+"的出现频率是:"+df.format(a1)+"%"); } } System.out.println("字母共计："+sum+"个"); for(int i=0;i<shu.length;i++) { h1[i] = String.valueOf(shu[i]); } int msg1=0; int count1=0; //判断单词个数 String word2 =""; for(int i=0;i<shu.length;i++) { if((shu[i]>=‘a‘&&shu[i]<=‘z‘)||(shu[i]>=‘A‘&&shu[i]<=‘Z‘)) { word2+=h1[i]; }else { msg1=1; } if(word3[i]==" ") { //考虑标点加空格的情况 msg1=0; //msg1初始化 word3[i]=""; continue; //跳出循环 } if(msg1==1) { //如果中间出现非字母 word3[i]=word2; //word2存入数组 word2=""; //word2初始化 msg1=0; //msg1初始化 } if(word3[i]==null) { //判断为空，防止空指针 msg1=0; //msg1初始化 word3[i]="空"; continue; //跳出循环 } if(word3[i]=="") { //判断为空，防止空指针 msg1=0; //msg1初始化 word3[i]="空"; continue; //跳出循环 } if(word3[i].length()==1) { //若长度为一，是单字母不为单词 msg1=0; //msg1初始化 word3[i]=""; continue; //跳出循环 } //System.out.println(word3[i]); word4[count1]=word3[i]; count1++; if(word3[i]==""&&word3[i-1]=="") { break; } } for(int i=0;i<word4.length;i++) { if(word4[i]!=null) { //System.out.println(word4[i]); }else { break; } } int thought_a=0; for(int i=0;i<word4.length;i++) { word5[thought_a]=word4[i]; } }catch (Exception e) { e.printStackTrace(); } } public void daoru(String path) throws IOException { File a=new File(path); FileInputStream b = new FileInputStream(a); InputStreamReader c=new InputStreamReader(b,"UTF-8"); String string2=new String(); while(c.ready()) { char string1=(char) c.read(); if(!isWord(string1)) { if(map1.containsKey(string2)) { Integer num1=map1.get(string2)+1; map1.put(string2,num1); } else { Integer num1=1; map1.put(string2,num1); } string2=""; } else { string2+=string1; } } if(!string2.isEmpty()) { if(map1.containsKey(string2)) { Integer num1=map1.get(string2)+1; map1.put(string2,num1); } else { Integer num1=1; map1.put(string2,num1); } string2=""; } c.close(); b.close(); } public void testthird(String path) { String sz[]; Integer num[]; final int MAXNUM=10; //统计的单词出现最多的前n个的个数 sz=new String[MAXNUM+1]; num=new Integer[MAXNUM+1]; testtwo tt=new testtwo(); int account =1; //Vector<String> ve1=new Vector<String>(); try { tt.daoru(path); } catch (IOException e) { // TODO 自动生成的 catch 块 e.printStackTrace(); } System.out.println("英文单词的出现情况如下:"); int g_run=0; for(g_run=0;g_run<MAXNUM+1;g_run++) { account=1; for(Map.Entry<String,Integer> it : tt.map1.entrySet()) { if(account==1) { sz[g_run]=it.getKey(); num[g_run]=it.getValue(); account=2; } if(account==0) { account=1; continue; } if(num[g_run]<it.getValue()) { sz[g_run]=it.getKey(); num[g_run]=it.getValue(); } //System.out.println("英文单词: "+it.getKey()+" 该英文单词出现次数: "+it.getValue()); } tt.map1.remove(sz[g_run]); } int g_count=1; String tx1=new String(); for(int i=0;i<g_run;i++) { if(sz[i]==null) continue; if(sz[i].equals("")) continue; tx1+="出现次数第"+(g_count)+"多的单词为:"+sz[i]+"\\t\\t\\t出现次数: "+num[i]+"\\r\\n"; System.out.println("出现次数第"+(g_count)+"多的单词为:"+sz[i]+"\\t\\t\\t出现次数: "+num[i]); g_count++; } try { tt.daochu(tx1); } catch (IOException e) { // TODO 自动生成的 catch 块 e.printStackTrace(); } } public void daochu(String txt) throws IOException { File fi=new File("tongji.txt"); FileOutputStream fop=new FileOutputStream(fi); OutputStreamWriter ops=new OutputStreamWriter(fop,"UTF-8"); ops.append(txt); ops.close(); fop.close(); } public boolean isWord(char a) { if(a<=‘z‘&&a>=‘a‘||a<=‘Z‘&&a>=‘A‘) return true; return false; } public void testthird1(String name) { // TODO Auto-generated method stub } }
testthird.class
package classthird; import java.io.File; import java.io.IOException; import classthird.testtwo; public class TestThird { public static void main(String[] args) throws IOException { testtwo tt=new testtwo(); File file = new File("D:\\\\Test"); String strArray[] = file.list(); for (String s : strArray) { System.out.println("文件名：" + s); } System.out.println("-----------------------------"); File fileArray[] = file.listFiles(); for (File f : fileArray) { //System.out.println("文件名：" + f.getName()); String thought_a; thought_a=f.getCanonicalPath(); tt.test(thought_a); tt.testthird(thought_a); } } }
以上是关于课堂测试-统计单词个数和字母出现频率的主要内容，如果未能解决你的问题，请参考以下文章
统计一段文章的单词频率，取出频率最高的5个单词和个数(python)