zoukankan      html  css  js  c++  java
  • 词频统计

    请编写程序,对一段英文文本,统计其中所有不同单词的个数,以及词频最大的前10%的单词。

    所谓“单词”,是指由不超过80个单词字符组成的连续字符串,但长度超过15的单词将只截取保留前15个单词字符。而合法的“单词字符”为大小写字母、数字和下划线,其它字符均认为是单词分隔符。

    输入格式:

    输入给出一段非空文本,最后以符号#结尾。输入保证存在至少10个不同的单词。

    输出格式:

    在第一行中输出文本中所有不同单词的个数。注意“单词”不区分英文大小写,例如“PAT”和“pat”被认为是同一个单词。

    随后按照词频递减的顺序,按照词频:单词的格式输出词频最大的前10%的单词。若有并列,则按递增字典序输出。

    输入样例:

    This is a test.
    
    The word "this" is the word with the highest frequency.
    
    Longlonglonglongword should be cut off, so is considered as the same as longlonglonglonee.  But this_8 is different than this, and this, and this...#
    this line should be ignored.
    

    输出样例:(注意:虽然单词the也出现了4次,但因为我们只要输出前10%(即23个单词中的前2个)单词,而按照字母序,the排第3位,所以不输出。)

    23
    5:this
    4:is
    

    map映射到数组,统计并排序。
    #include <iostream>
    #include <algorithm>
    #include <map>
    #include <cstring>
    using namespace std;
    struct str
    {
        char s[16];
        int num;
    }ans[10000];
    int no = 1;
    bool cmp(str a,str b)
    {
        if(a.num == b.num)return strcmp(a.s,b.s) < 0;
        return a.num > b.num;
    }
    int main()
    {
        char ch,s[16];
        int c = 0;
        map<string,int> p;
        while((ch = cin.get()) != '#')
        {
            if(ch == '_')
            {
                if(c < 15)s[c ++] = ch;
            }
            else if(isdigit(ch))
            {
                if(c < 15)s[c ++] = ch;
            }
            else if(isalpha(ch))
            {
                if(c < 15)s[c ++] = tolower(ch);
            }
            else
            {
                if(c)
                {
                    s[c] = '';
                    c = 0;
                    if(!p[s])
                    {
                        strcpy(ans[no].s,s);
                        ans[no].num = 1;
                        p[s] = no ++;
                    }
                    else
                    {
                        ans[p[s]].num ++;
                    }
                }
            }
        }
        sort(ans + 1,ans + no,cmp);
        cout<<no - 1<<endl;
        for(int i = 1;i <= no / 10;i ++)
        {
            cout<<ans[i].num<<':'<<ans[i].s<<endl;
        }
    }

     2019重做:

    #include <iostream>
    #include <cstdlib>
    #include <map>
    #include <algorithm>
    #include <sstream>
    #include <vector>
    using namespace std;
    map<string,int> mp;
    vector<string> vec;
    bool cmp(string a,string b) {
        if(mp[a] == mp[b]) return a < b;
        return mp[a] > mp[b];
    }
    void check(string t) {
        int s = 0;
        for(int i = 0;i <= t.size();i ++) {
            if(!isalnum(t[i]) && t[i] != '_') {
                string temp = "";
                if(i - s > 15) temp = t.substr(s,15);
                else if(i != s) temp = t.substr(s,i - s);
                s = i + 1;
                if(temp == "") continue;
                if(!mp[temp] ++) vec.push_back(temp);
            }
            else t[i] = tolower(t[i]);
        }
    }
    int main() {
        string s;
        while(getline(cin,s)) {
            istringstream in(s);
            string t;
            while(in>>t) {
                check(t);
            }
            if(s.size() && s[s.size() - 1] == '#') break;
        }
        sort(vec.begin(),vec.end(),cmp);
        cout<<vec.size()<<endl;
        for(int i = 0;(i + 1) * 10 <= vec.size();i ++) {
            cout<<mp[vec[i]]<<':'<<vec[i]<<endl;
        }
    }

     2020:

    import sys
    dict = {}
    flag = 0
    for line in sys.stdin:
        if(flag == 1):
            line = ""
        for i in line.split(' '):
            s = 0
            i = i + " "
            for j in range(len(i)):
                if(not i[j].isalnum() and i[j] != "_"):
                    if(i[j] == "#"):
                        flag = 1
                    temp = ""
                    if(j - s > 15):
                        temp = i[s:s + 15]
                    elif(j != s):
                        temp = i[s:j]
                    s = j + 1
                    if(temp != ""):
                        temp = temp.lower()
                        if(dict.get(temp) == None):
                            dict[temp] = 1
                        else:
                            dict[temp] += 1
    dict = sorted(dict.items(),key=lambda d:(d[0]),reverse=False)
    dict = sorted(dict,key=lambda d:(d[1]),reverse=True)
    len = len(dict)
    print(len)
    for i in range(int(len / 10)):
        print("%d:%s" % (dict[i][1],dict[i][0]))
  • 相关阅读:
    Help document of CAD Build
    NSTableView 中 NSTextField无法输入
    NSScrollView 内容显示不正常问题
    Mac 中 NSTrackingArea 鼠标移动事件捕获
    java定时任务调度框架
    uboot: initramfs image to roofs, and rootfs to initramfs image
    jfrog CLI(command line interface)
    git submodule list/clone/update
    python run javascript in ubuntu
    git blame
  • 原文地址:https://www.cnblogs.com/8023spz/p/8444257.html
Copyright © 2011-2022 走看看