C++编写的朴素贝叶斯分类器跟k-means聚类

#include "bayes.h" #include <iostream>////////////适合计算属性值是离散的分类 #include <fstream> #include <sstream> #include <map> using namespace std; bayes::bayes(){ TrainNum=130; TestNum=48; m=0; for(int i=0;i<3;i++) A[i]=0; } void bayes::showVector(vector<OriginalData> data) { for(int i=0;i<data.size();i++) cout<<i+1<<":"<<data[i].A1<<" "<<data[i].A2<<" "<<data[i].A3<<" "<<data[i].A4<<" "<<data[i].A5<<" "<<data[i].A6<<" "<<data[i].A7<<" "<<data[i].A8<<" "<<data[i].A9<<" "<<data[i].A10<<" "<<data[i].A11<<" "<<data[i].A12<<" "<<data[i].A13<<" "<<data[i].A14<<endl; } //从文件中读取数值 void bayes::DataRead(const char* fileName) { f.open(fileName); int num; if (fileName[1] == 'r') num = TrainNum; else num = TestNum; string line; OriginalData wine; vector<OriginalData> data; for (int i = 0; i < num; i++) { f >> line;//一行字符 while (line.find(',') > 0 && line.find(',') < line.length()) { line[line.find(',')] = ' '; } istringstream stream(line);//将stream绑定到读取的行 stream >> wine.A1 >> wine.A2 >> wine.A3 >> wine.A4 >> wine.A5 >> wine.A6 >> wine.A7 >> wine.A8 >> wine.A9 >> wine.A10 >> wine.A11 >> wine.A12 >> wine.A13 >> wine.A14;//读取数据传给wine data.push_back(wine); } if(num==TrainNum) trainData=data; else testData=data; //showVector(data); f.close(); } void bayes::do_bayes() { int count1 = 0, count2 = 0, count3 = 0; int i; //cout<<TrainNum<<endl; //showVector(trainData); for(i = 0; i < TrainNum ; i++) { if(trainData[i].A1 == 1) { count1 ++; } if(trainData[i].A1 == 2) { count2 ++; } if(trainData[i].A1 == 3) { count3 ++; }//统计三类数据,各自求和 } A[0] = (double)count1/(double)TrainNum; //求先验概率 p(c) A[1] = (double)count2/(double)TrainNum; A[2] = (double)count3/(double)TrainNum; cout<<"A:"<<A[0]<<" "<<A[1]<<" "<<A[2]<<endl; map<double, double>::iterator pipei; for(i = 0 ; i < TrainNum; i++) { if(trainData[i].A1 == 1) //求P(Xk|C1) 中Xk的个数 { int j=0; for(;j< 13 ;j++) { double temp = *(&trainData[i].A2+j); pipei = C1_map[j].find(temp); if(pipei == C1_map[j].end()) { C1_map[j].insert(map<double, double>::value_type(temp,1)); } else { double j = pipei->second; pipei->second = j + 1; } } } if(trainData[i].A1 == 2) //求P(Xk|C2) 中Xk的个数 { int j = 0; for(;j< 13 ;j++) { double temp = *(&trainData[i].A2+j); pipei = C2_map[j].find(temp); if(pipei == C2_map[j].end()) { C2_map[j].insert(map<double, double>::value_type(temp,1)); } else { double j = pipei->second; pipei->second = j + 1; } } } if(trainData[i].A1 == 3) //求P(Xk|C3) 中Xk的个数 { int j = 0; for(;j< 13 ;j++) { double temp = *(&trainData[i].A2+j); pipei = C3_map[j].find(temp); if(pipei == C3_map[j].end()) { C3_map[j].insert(map<double, double>::value_type(temp,1)); } else { double j = pipei->second; pipei->second = j + 1; } } } } //概率 累加p(x|c) for(i = 0; i < attributeNum; i++) { for(pipei=C1_map[i].begin(); pipei!=C1_map[i].end(); ++pipei) { double num = pipei->second; pipei->second = (double)num/(double)count1; //p(x|c) } for(pipei=C2_map[i].begin(); pipei!=C2_map[i].end(); ++pipei) { double num = pipei->second; pipei->second = (double)num/(double)count2; } for(pipei=C3_map[i].begin(); pipei!=C3_map[i].end(); ++pipei) { double num = pipei->second; pipei->second = (double)num/(double)count3; } } } void bayes::houyan()//计算后验分布,找出最大值 { //showVector(testData); int i,j,k; double p[3]; for(i = 0; i<TestNum; i++) { double pXC[3]={0,0,0}; for(j = 0; j < 3; j++) { map<double, double>::iterator pipei; //计算p(X|C1)=p(c1)*累加(p(x|c))/p(X),因为p(X)都一样，所以只需要比较分子的大小 for(k = 0; k < attributeNum; k++) { pipei = C1_map[k].find(*(&testData[i].A2+k)); if(pipei != C1_map[k].end()) { pXC[0] =pXC[0] + pipei->second; } } p[0] = A[0] * pXC[0]; //p(c)*累加(p(x|c)) //计算p(X|C2) for(k = 0; k < attributeNum; k++) { pipei = C2_map[k].find(*(&testData[i].A2+k)); if(pipei != C2_map[k].end()) { pXC[1] =pXC[1] + pipei->second; } } p[1] = A[1] * pXC[1]; //计算p(X|C3) for(k = 0; k < attributeNum; k++) { pipei = C3_map[k].find(*(&testData[i].A2+k)); if(pipei != C3_map[k].end()) { pXC[2] =pXC[2] + pipei->second; } } p[2] = A[2] * pXC[2]; } //找出最大值 if(p[0] > p[1] && p[0] >p[2]) { cout<<i+1<<":"<<p[0]<<"\t "<<1<<endl; cout<<"other classification's probability:"<<p[1]<<"\t\t"<<p[2]<<endl; if(testData[i].A1==1) { m++; cout<<"aaa"<<endl; } } else { if(p[1] > p[2]) { cout<<i+1<<":"<<p[1]<<"\t "<<2<<endl; cout<<"other classification's probability:"<<p[0]<<"\t\t"<<p[2]<<endl; if(testData[i].A1==2) { m++; cout<<"bbb"<<endl; } } else { cout<<i+1<<":"<<p[2]<<"\t "<<3<<endl; cout<<"other classification's probability:"<<p[0]<<"\t\t"<<p[1]<<endl; if(testData[i].A1==3) { m++; cout<<"ccc"<<endl; } } } } }