C++基于特征向量的KNN分类算法

#include "stdafx.h"#include <iostream>#include <fstream>#include <sstream>#include <string>#include <vector>#include <set>#include <map>#include <cmath> using namespace std; //样本特征结构体struct sample{ string type; vector<double> features;}; //读取训练样本train.txt，训练样本格式：类型名+特征向量void readTrain(vector<sample>& train, const string& file){ ifstream fin(file.c_str()); //file是存储希望读写的文件名的string对象，fin是读的流 if(!fin) { cerr<<"Unable to open the input file: "<<file<<endl; exit(1); }  string line;  double d=0.0; while(getline(fin,line)) //fin是读入流，getline从输入流fin读入一行到line { istringstream stream(line); //bind to stream to the line we read sample ts; stream>>ts.type; while(stream>>d) //read a word from line {  ts.features.push_back(d); //在trains.features的末尾添加一个值为d的元素 } train.push_back(ts); //在train的末尾添加一个值为ts的元素 } fin.close();} //读取测试样本test.txt，每行都是一个特征向量void readTest(vector<sample>& test, const string& file){ ifstream fin(file.c_str()); if(!fin) { cerr<<"Unable to open the input file: "<<file<<endl; exit(1); }  string line; double d=0.0; while(getline(fin,line)) { istringstream stream(line); //bind to stream to the line we read sample ts; while(stream>>d) {  ts.features.push_back(d); } test.push_back(ts); } fin.close();} //输出结果，为每一个向量赋予一个类型，写入result.txt中void writeResult(const vector<sample>& test, const string& file){ ofstream fout(file.c_str()); if(!fout) { cerr<<"Unable to write the input file: "<<endl; exit(1); }  for(vector<sample>::size_type i=0;i!=test.size();++i) { fout << test[i].type << '/t'; for(vector<double>::size_type j=0;j!=test[j].features.size();++j) {  fout<<test[i].features[j]<<' '; } fout<<endl; }} //KNN算法的实现void knnProcess(vector<sample>& test, const vector<sample>& train, const vector<vector<double> >& dm, unsigned int k){ for (vector<sample>::size_type i = 0; i != test.size(); ++i) { multimap<double, string> dts; //保存与测试样本i距离最近的k个点  for (vector<double>::size_type j = 0; j != dm[i].size(); ++j) {  if (dts.size() < k) //把前面k个插入dts中  {  dts.insert(make_pair(dm[i][j], train[j].type)); //插入时会自动排序，按dts中的double排序，最小的排在最后  }  else  {  multimap<double, string>::iterator it = dts.end();  --it;   if (dm[i][j] < it->first) //把当前测试样本i到当前训练样本之间的欧氏距离与dts中最小距离比较，若更小就更新dts  {   dts.erase(it);   dts.insert(make_pair(dm[i][j], train[j].type));  }  } } map<string, double> tds; string type = ""; double weight = 0.0; //下面for循环主要是求出与测试样本i最邻近的k个样本点中大多数属于的类别，即将其作为测试样本点i的类别 for (multimap<double, string>::const_iterator cit = dts.begin(); cit != dts.end(); ++cit) {  // 不考虑权重的情况，在 k 个样例中只要出现就加 1  // ++tds[cit->second];   // 这里是考虑距离与权重的关系，距离越大权重越小  tds[cit->second] += 1.0 / cit->first;  if (tds[cit->second] > weight)  {  weight = tds[cit->second];  type = cit->second; //保存一下类别  } } test[i].type = type; }} // 计算欧氏距离double euclideanDistance(const vector<double>& v1, const vector<double>& v2){ if(v1.size() != v2.size()) { cerr<<"Unable to get a distance! "<<endl; }  else { double distance = 0.0;  for (vector<double>::size_type i = 0; i != v1.size(); ++i) {  distance += (v1[i] - v2[i]) * (v1[i] - v2[i]); } return sqrt(distance); }} /*初始化距离矩阵，该矩阵是根据训练样本和测试样本而得，矩阵的行数为测试样本的数目，列数为训练样本的数目，每一行为一个测试样本到各个训练样本之间的欧式距离组成的数组*/void initDistanceMatrix(vector<vector<double> >& dm, const vector<sample>& train, const vector<sample>& test){ for (vector<sample>::size_type i = 0; i != test.size(); ++i) { vector<double> vd; for (vector<sample>::size_type j = 0; j != train.size(); ++j) {  vd.push_back(euclideanDistance(test[i].features, train[j].features)); } dm.push_back(vd); }} //封装void xfxKnn(const string& file1, const string& file2, const string& file3, int k){ vector<sample> train,test; readTrain(train, file1.c_str()); readTest(test, file2.c_str()); vector< vector<double> > dm; initDistanceMatrix(dm, train, test); knnProcess(test, train, dm, k); writeResult(test, file3.c_str());} // 测试int main(){ xfxKnn("train.txt", "test.txt", "result.txt", 5); return 0;}