Created
February 27, 2017 06:23
-
-
Save taras-sereda/d11078a555c93c048b92e6c93d86815a to your computer and use it in GitHub Desktop.
word frequency tool
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// compile with g++ --std=c++11 | |
// g++ --std=c++11 freqs.cpp -o freqs | |
#include <iostream> | |
#include <sstream> | |
#include <fstream> | |
#include <regex> | |
#include <algorithm> | |
#include <map> | |
#include <vector> | |
using namespace std; | |
int main(int argc, char *argv[]) { | |
locale::global(locale("")); | |
regex word_pattern("[[:alpha:]]+"); | |
map<string, int> frequency_map; | |
ifstream input_file (argv[1]); | |
ofstream out_file (argv[2]); | |
string line; | |
if (input_file.is_open()) | |
{ | |
while (getline(input_file, line)) { | |
//remove punctuation; | |
line.erase(remove_if(line.begin(), line.end(), ::ispunct), line.end()); | |
istringstream iss(line); | |
while(iss) | |
{ | |
string sub_str; | |
iss >> sub_str; | |
if (regex_match(sub_str, word_pattern)) | |
{ | |
//convert word to lower case; | |
transform(sub_str.begin(), sub_str.end(), sub_str.begin(), ::tolower); | |
map<string, int>::iterator it = frequency_map.find(sub_str); | |
if (it != frequency_map.end()) { | |
frequency_map[sub_str] += 1; | |
} | |
else { | |
frequency_map[sub_str] = 1; | |
} | |
} | |
} | |
} | |
input_file.close(); | |
} | |
else { | |
cout << "Unable to open input file" << endl; | |
} | |
map<string, int>::iterator it; | |
vector<pair<int, string>> frequency_list; | |
//build list of pairs | |
for (it = frequency_map.begin(); it != frequency_map.end(); it++) { | |
frequency_list.push_back(make_pair(-it -> second, it -> first)); | |
} | |
//sort pairs | |
sort(frequency_list.begin(), frequency_list.end()); | |
if (out_file.is_open()) { | |
for (auto &item: frequency_list) { | |
out_file << abs(item.first) << " " << item.second << endl; | |
} | |
} else { | |
cout << "Unable to open out file" << endl; | |
} | |
out_file.close(); | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment