NTU-Coursera機器學習:HomeWork 2 Q16-20

NTU-Coursera機器學習:HomeWork 2 Q16-20

QUESTION 16~18

vcHLxMe49me6r8r9oaM8L3A+PHA+PC9wPjxwcmUgY2xhc3M9"brush:java;">#include #include #include #include using namespace std; #define SAMPLE_SIZE 20 //樣本量 struct Hypothesis{ int coef; double threshold; }; //求數字的符號 int sign(double x) { if(x<0) return -1; else if(x>0) return 1; else return -1; } //反轉數字的符號 int flipSign(int num) { return num * (-1); } //計算樣本錯誤率 double calErrInSample(vector& inputVec, vector& outputVec, Hypothesis & hypo) { int errCount = 0; for(int i=0;i& inputVec) { for(int i=0;i& inputVec, vector& outputVec) { int output; double randNum; for(int i=0;i& inputVec, vector& outputVec, Hypothesis & hypo, double & bestThres ) { double minErrIn = 1.0; double curErrIn; for(int i=0;i& inputVec, vector& outputVec, Hypothesis & hypo ) { double minErrInPositive = 1.0; double minErrInNegtive = 1.0; double minErrIn; double bestThresPositive; double bestThresNegtive; hypo.coef = 1; minErrInPositive = getMinErrIn(inputVec,outputVec,hypo,bestThresPositive); hypo.coef = -1; minErrInNegtive = getMinErrIn(inputVec,outputVec,hypo,bestThresNegtive); if(minErrInPositive inputVec; vector outputVec; Hypothesis hypo; getTrainingData(inputVec); calOutput(inputVec,outputVec); errInTotal += decisionStump(inputVec,outputVec,hypo); errOutTotal += calErrOutSample(hypo); cout<<"-----------------第"<輸出結果

QUESTION 19~20

這一題把16題中的 decision stump 拓展到多維，要求找出E-in最小的那一維並在測試數據上計算對應維度的E-out:

#include 
#include 
#include 
#include 
#include 
 
using namespace std;
 
#define DEMENSION 9           //數據維度
 
char *file = "training.txt";
char *file_test = "testing.txt";
 
struct record {
    double input[DEMENSION];  
    int output;                       
};
 
struct singleDemensionRecord {
    double input;
    int output;
};
 
struct Hypothesis{
    int coef;
    double threshold; 
};
 
//求數字的符號
int sign(double x)
{
    if(x<0)       return -1;
    else if(x>0) return 1;
    else         return -1;
}
 
//從文件讀取數據
void getData(ifstream & dataFile, vector &data)
{
    while(!dataFile.eof()){
        record curRecord;   
        for(int i=0;i>curRecord.input[i]; }
        dataFile>>curRecord.output;
        data.push_back(curRecord);
    }
    dataFile.close();  
}
 
//計算指定維度的樣本錯誤率
double calErr(vector& singleDemensionVec, vector& hypo, int demension)
{
    int errCount = 0;
    int length = singleDemensionVec.size();
 
    for(int i=0;i& dataSet, vector& singleDemensionVec, int demension)
{
    int recordSize = dataSet.size(); 
    singleDemensionRecord curRec;
 
    for(int i=0;i & singleDemensionVec, vector& hypo, int demension, double & bestThres)
{
    double minErrIn = 1.0;
    double curErrIn;
    int recordSize = singleDemensionVec.size();
 
    for(int i=0;i& trainingSet, vector& testSet, vector& hypo)
{
    int recordSize = trainingSet.size();
    int minErrInDem;
    double minErrIn = 1.1;  
 
    for(int dem=0;dem singleDemensionVec; 
        double curMinErrIn;
        double bestThresPositive;
        double bestThresNegtive;
        double minErrInPositive;
        double minErrInNegtive;
 
        getInputByDemension(trainingSet,singleDemensionVec,dem+1);
 
        hypo[dem].coef = 1;
        minErrInPositive = getMinErrIn(singleDemensionVec,hypo,dem+1,bestThresPositive);
     
        hypo[dem].coef = -1;
        minErrInNegtive = getMinErrIn(singleDemensionVec,hypo,dem+1,bestThresNegtive);
 
        if(minErrInPositivecurMinErrIn){
            minErrIn = curMinErrIn;
            minErrInDem = dem+1;
        }
    }
 
    cout<<"The demension with min error is : "< 文件打開失敗"<輸出結果:


關於Machine Learning更多討論與交流，敬請關注本博客和新浪微博songzi_tea.