zoukankan      html  css  js  c++  java
  • std::map初体验

    /*

    This exercise is in the field of bibliometric (words and text) analysis. You will be provided with a text

    file, which consists of several paragraphs of English text. Your task is to write a program which will

    analyse the text, and output a range of statistics about the text.

    Your program should do the following:

    A list of all the words that occur, in alphabetical order. You must not print the same word twice.

    Print out the 20 most common words in the text, together with the number of instances of each word,

    with the most common word at the top.

    */

    //////////////////////////////////////////////////////////////////////////

    //     ReadTxt.cpp : .

    //     by Mythma

    //     以标准的字母表形式列出文章中的单词,不能重复

    //     并把出现频率最高的20个打印出来

    //   compiler: g++

    //     vc6不能编译此程序

    //////////////////////////////////////////////////////////////////////////

    #include <iostream>

    #include <fstream.h>

    #include <string>

    #include <vector>

    #include <map>

    #include <algorithm>

    using namespace std;

     

    const string STR_INTERVAL = "/n-----------------------------------------------------------";

     

    map<string, int>     gMap;

    vector<string>              gMMStr;

     

    bool AddWordToList(string strWord)

    {

           if(strWord.empty())

                  return false;

     

           string strTemp = strWord;

          

     

           //upper to lower

           for(int i = 0; i < strTemp.size(); i++)

           {

                  strTemp[i] = tolower(strTemp[i]);

                 

           }    

          

           //remove head punctuation and number

           while(strTemp[0] < 'a' || strTemp[0] > 'z')

           {

                  if(strTemp.size() > 1)

                         strTemp = strTemp.substr(1, strTemp.size() - 1);

                  else

                         return false;

           }

     

           //remove tail punctuation and number

           while(strTemp[strTemp.size() - 1] < 'a' || strTemp[strTemp.size() - 1] > 'z')

           {

                  if(strTemp.size() > 1)

                         strTemp = strTemp.substr(0, strTemp.size() - 2);

                  else

                         return false;

           }

          

          

           map<string ,int>::iterator it = gMap.find(strTemp);

           //add to map if exist

           if(it == gMap.end())

                  gMap.insert(map<string, int>::value_type(strTemp, 1));

           //increase if not exist

           else

                  ++ (*it).second;

     

           return true;

    }

     

    void OutPutWordsList()

    {

          

          

           cout << STR_INTERVAL

                   << "/n--文件中单词的总数为: "

                   << gMap.size()

                   << " 按字母排列如下"

                   << STR_INTERVAL << endl;

     

           int n = 0;

           for(map<string, int>::iterator it = gMap.begin(); it != gMap.end(); ++it)

           {

                  ++n;

                  cout.width(15);

                  cout.flags(ios::left);

                  cout << it->first.c_str();

                  if( 5 == n)

                  {

                         cout << endl;

                         n = 0;

                  }

           }

     

           cout << STR_INTERVAL << endl;

    }

     

    bool Cmp(const pair<string,int> &p1, const pair<string,int> &p2)

    {

                  return p1.second > p2.second;

    }

     

    void OutPutCount()

    {    

          

           vector< pair<string,int> > wd(gMap.begin(), gMap.end());

           sort(wd.begin(), wd.end(), Cmp);

          

           cout << STR_INTERVAL

                << "/n--出现频率最多的几个单词是:"

                   << STR_INTERVAL;

     

           int i = 0;

          

           for(vector< pair<string, int> >::iterator it=wd.begin();

                  it != wd.end() && i < 20; ++it, ++i)

           {

                  cout.width(15);

                  cout.flags(ios::left);

                  cout << endl

                          << it->first.c_str()

                          << " ----       "

                          << it->second;

           }

           cout << STR_INTERVAL;

    }

     

     

    int main(int argc, char* argv[])

    {

           char*      strPath;

           if(argc == 2)

                  strPath = argv[1];

           else

                  strPath = "c://words.txt";

           //read file

           ifstream  inFile(strPath);

           while( !inFile.eof())

           {

                  string strWord;

                  inFile >> strWord;

                  AddWordToList(strWord);

           }

     

           OutPutWordsList();

           OutPutCount();

     

           return 0;

    }

     

     

  • 相关阅读:
    单细胞转录组CNV分析
    瘦子增肌计划 | 健身
    WashU Epigenome Browser | ChIP-seq | DNase-Seq | ATAC-seq | 表观
    羽毛球新手教学
    可变剪切 | isoform | 提取特定exon的usage | DEXSeq
    文献快读 | 单细胞测序肾癌的免疫微环境与临床疗效的关系
    內外全科醫學士課程 | MBBS | 医疗
    天龙八部 | 中国名著 | 刷剧
    当代人工智能的基石 | 数据标注
    提取基因的特定外显子exon的碱基序列 | NCBI
  • 原文地址:https://www.cnblogs.com/aiwz/p/6333285.html
Copyright © 2011-2022 走看看