#include "stdafx.h"#include <iostream>#include <fstream>#include <sstream>#include <string>#include <vector>#include <set>#include <map>#include <cmath> using namespace std; //樣本特征結構體struct sample{ string type; vector<double> features;}; //讀取訓練樣本train.txt，訓練樣本格式：類型名+特征向量void readTrain(vector<sample>& train, const string& file){ ifstream fin(file.c_str()); //file是存儲希望讀寫的文件名的string對象，fin是讀的流 if(!fin) { cerr<<"Unable to open the input file: "<<file<<endl; exit(1); }  string line;  double d=0.0; while(getline(fin,line)) //fin是讀入流，getline從輸入流fin讀入一行到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的末尾添加一個值為d的元素 } train.push_back(ts); //在train的末尾添加一個值為ts的元素 } fin.close();} //讀取測試樣本test.txt，每行都是一個特征向量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();} //輸出結果，為每一個向量賦予一個類型，寫入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算法的實現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; //保存與測試樣本i距離最近的k個點  for (vector<double>::size_type j = 0; j != dm[i].size(); ++j) {  if (dts.size() < k) //把前面k個插入dts中  {  dts.insert(make_pair(dm[i][j], train[j].type)); //插入時會自動排序，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) //把當前測試樣本i到當前訓練樣本之間的歐氏距離與dts中最小距離比較，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循環主要是求出與測試樣本i最鄰近的k個樣本點中大多數屬于的類別，即將其作為測試樣本點i的類別 for (multimap<double, string>::const_iterator cit = dts.begin(); cit != dts.end(); ++cit) {  // 不考慮權重的情況，在 k 個樣例中只要出現就加 1  // ++tds[cit->second];   // 這里是考慮距離與權重的關系，距離越大權重越小  tds[cit->second] += 1.0 / cit->first;  if (tds[cit->second] > weight)  {  weight = tds[cit->second];  type = cit->second; //保存一下類別  } } test[i].type = type; }} // 計算歐氏距離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); }} /*初始化距離矩陣，該矩陣是根據訓練樣本和測試樣本而得，矩陣的行數為測試樣本的數目，列數為訓練樣本的數目，每一行為一個測試樣本到各個訓練樣本之間的歐式距離組成的數組*/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); }} //封裝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());} // 測試int main(){ xfxKnn("train.txt", "test.txt", "result.txt", 5); return 0;}