#include <iostream>
#include <vector>
#include <cstddef>
#include <string>
#include <sstream>
#include <fstream>
#include <algorithm>
#include <cmath>
#include <set>
#include <limits>
#include <functional>
#include <numeric> template <class DataType>
void ReadMatFromFile(std::string &filename, std::vector<std::vector<DataType> > &lines_feat) {
std::ifstream vm_info(filename.c_str());
std::string lines;
DataType var;
std::vector<DataType> row; lines_feat.clear(); while(!vm_info.eof()) {
getline(vm_info, lines);
if(lines.empty())
break;
std::stringstream stringin(lines);
row.clear(); while(stringin >> var) {
row.push_back(var);
}
lines_feat.push_back(row);
}
} void ReadStringFromFile(std::string &filename, std::vector<std::string> &in_string) {
std::ifstream vm_info(filename.c_str());
std::string lines, var; while(!vm_info.eof()) {
getline(vm_info, lines);
if(lines.empty())
break;
std::stringstream stringin(lines); while(stringin >> var) {
in_string.push_back(var);
}
}
} std::string lowerCase(const std::string& s) {
std::string lower(s);
for(size_t i=;i<s.length();++i) {
lower[i]=tolower(lower[i]);
}
return lower;
} std::string letters(const std::string& s) {
std::string letter;
for(size_t i=;i<s.length();++i) {
char ch=s.at(i);
bool flag=false;
if((ch>= && ch<=)) {
ch=ch+;
flag=true;
}
else if((ch>= && ch<=) || (ch>= && ch<=)) {
flag=true;
}
else {
;
}
if(flag) {
letter.push_back(ch);
}
}
letter.push_back('\0');
return letter;
} template <class T1, class T2>
int MatMultiply(const std::vector<std::vector<T1> > &Mata, const std::vector<std::vector<T2> > &Matb, std::vector<std::vector<T1> > &MatOut) {
if(Mata.at().size() != Matb.size()) {
std::cout<<"not match!\n";
return -;
}
for(size_t i=; i<Mata.size(); ++i) {
for(size_t j=; j<Matb.at().size(); ++j) {
std::vector<T2> col;
col.clear();
for(size_t k=; k<Matb.size(); ++k) {
col.push_back(Matb.at(k).at(j));
}
MatOut.at(i).at(j)=inner_product(Mata.at(i).begin(), Mata.at(i).end(), col.begin(), );
}
}
return ;
} template <class T1, class T2, class T3>
void outer_product(const std::vector<T1> &inst1, const std::vector<T2> &inst2, std::vector<std::vector<T3> > &out) {
std::vector<T3> temp_row(inst2.size()); for(typename::std::vector<T1>::const_iterator it=inst1.begin();it!=inst1.end();++it) {
transform(inst2.begin(), inst2.end(), temp_row.begin(), bind2nd(std::multiplies<T1>(), *it));
out.push_back(temp_row);
}
} void ReadDataFromFile(std::string &filename, std::vector<std::string> &lines_feat) {
std::ifstream vm_info(filename.c_str());
std::string lines; lines_feat.clear(); while(!vm_info.eof()) {
getline(vm_info, lines);
if(lines.empty())
break; lines_feat.push_back(lines);
}
} std::vector<std::string> split(const std::string& s, char delimiter) {
std::vector<std::string> tokens;
std::string token;
std::istringstream tokenStream(s); while(std::getline(tokenStream, token, delimiter)) {
tokens.push_back(token);
}
return tokens;
} int stringtoint(const std::string& s) {
std::istringstream iss(s);
int num;
return iss>>num?num:;
} void printip(const std::string& s) {
std::vector<std::string> temp, ip_segment; temp=split(s, '-');
ip_segment=split(temp.front(), '.'); std::string ip_start=ip_segment.back(), ip_end=temp.back();
int start, end;
start=stringtoint(ip_start);
end=stringtoint(ip_end); for(size_t i=start;i<=end;++i) {
std::cout<<ip_segment[]<<"."<<ip_segment[]<<"."<<ip_segment[]<<"."<<i<<"\n";
}
} template <class T>
void Display2DVector(std::vector<std::vector<T> > &vv) {
for(size_t i=;i<vv.size();++i) {
for(typename::std::vector<T>::const_iterator it=vv.at(i).begin();it!=vv.at(i).end();++it) {
std::cout<<*it<<" ";
}
std::cout<<"\n";
}
std::cout<<"--------the total of the 2DVector is "<<vv.size()<<std::endl;
} int main() {
std::string filename("data");
std::vector<std::string> v_string;
std::string words;
std::set<std::string> s_string; ReadStringFromFile(filename, v_string); for(std::vector<std::string>::const_iterator it=v_string.begin(); it!=v_string.end(); ++it) {
std::cout<<*it<<" ";
words=letters(*it);
s_string.insert(words);
}
std::cout<<std::endl;
for(std::set<std::string>::const_iterator it=s_string.begin(); it!=s_string.end(); ++it) {
std::cout<<*it<<" ";
}
std::cout<<std::endl;
return ;
}

The bag of words model ignores grammar and order of words.

运行结果如下,第一行为原始数据,第二行为提取后的数据:

bag of words in c++的更多相关文章

  1. 【ros】.bag文件

    Bags are typically created by a tool like rosbag They store the serialized message data in a file as ...

  2. MATLAB 图像分类 Image Category Classification Using Bag of Features

    使用MATLAB实现图像的识别,这是MATLAB官网上面的例子,学习一下. http://cn.mathworks.com/help/vision/examples/image-category-cl ...

  3. Bag标签之中的一个行代码实行中文分词实例2

    例1: 分词(返回以逗号隔开每一个词带上引號的词组.gap=",",quotes="'"或quotes='"') 单引號 <bag id=pPa ...

  4. Bag Problem

    Bag Problem Time Limit: 10000/5000 MS (Java/Others) Memory Limit: 32768/131072 K (Java/Others) Total ...

  5. Bag of mice(CodeForces 148D )

    D. Bag of mice time limit per test 2 seconds memory limit per test 256 megabytes input standard inpu ...

  6. Hibernate的集合映射(Set、List、Array、Map、Bag)

    POJOs如下: Customer类------>customer表   Order类对应---------->orders表  customer(1)<-------------- ...

  7. Bag of Words/Bag of Features的Matlab源码发布

    2010年11月19日 ⁄ 技术, 科研 ⁄ 共 1296字 ⁄ 评论数 26 ⁄ 被围观 4,150 阅读+ 由于自己以前发过一篇文章讲bow特征的matlab代码的优化的<Bag-Of-Wo ...

  8. Bag of Words(BOW)模型

    原文来自:http://www.yuanyong.org/blog/cv/bow-mode 重复造轮子并不是完全没有意义的. 这几天忙里偷闲看了一些关于BOW模型的知识,虽然自己做图像检索到目前为止并 ...

  9. Hibernate 多表关联映射- Hibernate中使用的集合类型(set,list,array,bag,map)

    Set类型的使用: <hibernate-mapping package="cn.model"> <class name="Department&quo ...

  10. CF 148D. Bag of mice (可能性DP)

    D. Bag of mice time limit per test 2 seconds memory limit per test 256 megabytes input standard inpu ...

随机推荐

  1. Java笔记——String、StringBuffer和StringBuilder类

    String类是不可变类,即一旦一个String对象被创建以后,包含在这个对象中的字符串序列是不可改变的,直至这个对象被销毁.   StringBuffer对象则代表一个字符序列可变的字符串,当一个S ...

  2. The APR based Apache Tomcat Native library which allows optimal performance in production environments was not found on the java.library.path: [C:\Program Files\Java\jdk1.8.0_60\bin;C:\Windows\Sun\Jav

    启动项目自动结束,查看日志发现 [ost-startStop-1] o.a.catalina.core.AprLifecycleListener   : The APR based Apache To ...

  3. libevent reference Mannual I

    FYI:http://www.wangafu.net/~nickm/libevent-book/ This lib is a integral of asynchronous IO. we shoul ...

  4. Centos7安装MySQL5.7(yum)

    本人尝试过使用源码安装方式,那叫一个头疼,各种问题,于是采用yum方式安装,没想到如此简单: 此服务器是刚买的,所以以前没有安装过mysql,如果以前安装过mysql的,好像要卸载干净再安装(其实我也 ...

  5. JSP内置对象说明

    JSP内置对象说明 制作人:全心全意 request对象:request对象封装了由客户端生成的HTTP请求的所有细节,主要包括HTTP头信息.系统信息.请求方式和请求参数等.通过request对象提 ...

  6. js之获取html标签的值

    <!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8&quo ...

  7. hdu 1754 I Hate It(线段树水题)

    >>点击进入原题测试<< 思路:线段树水题,可以手敲 #include<string> #include<iostream> #include<a ...

  8. i2c中start和restart的区别

    有的硬件芯片提供了一个个寄存器,供我们很好的操作i2c,但是,在用的时候,我们是不知道他到地是怎么操作的,下边,我就探讨下i2c中的start和restart的区别. start是在scl是高电平的时 ...

  9. Ubuntu 16.04安装Synaptic Package Manager图形化APT管理工具

    安装: sudo apt-get install synaptic 启动:

  10. Angularjs中添加HighCharts

    一. 添加基本配置 1. 添加指令 angular.module('newApp') .directive('dpHighchart', ['$rootScope', function($rootSc ...