正文之前

因为数据差距实在太大，从10-10000都有，要是全搞决策树我估计我是啥都不用搞了，看着电脑卡死就ok！所以特地将连续的数据转化为连续的数据！看看是不是会生成新的、更好地决策树！

正文

废话不多说！直接丢代码！不然真是难受的一批！写了好一会儿才搞定的！

#include<iostream>
#include<string>
#include<fstream>
using namespace std;

int main()
{
    int count=0;
    float attr[34];
    ifstream in("/Users/zhangzhaobo/Documents/Graduation-Design/Mydata.txt");
    ofstream out("/Users/zhangzhaobo/Documents/Graduation-Design/Data/New_Data.txt");
    string line[34];
    for (int i = 0; i < 34; ++i)
    {
        in>>line[i];
    }
    out<<"Diff_X"<<"\t"<<"Diff_Y"<<"\t";
    for (int i = 4; i < 8; ++i)
    {
        out<<line[i]<<"\t";
    }
    out<<"Diff_Luminosity\t";
    out<<line[10]<<"\t";
    out<<"TypeouOfSteel\t";
    for (int i = 13; i < 27; ++i)
    {
        out<<line[i]<<"\t";
    }
    out<<"Fault";
    out<<endl;
    float maxX,MaxY,MaxL;
    while(count<1941)
    {
        for (int i = 0; i < 34; ++i)
        {
            in>>attr[i];
        }
        float X_dis=attr[1]-attr[0];
        float Y_dis=attr[3]-attr[2];
        float Luminosity_dis=attr[9]-attr[8];
        float TypeOfSteel=attr[11];
        out<<X_dis<<"\t"<<Y_dis<<"\t";
        for (int i = 4; i < 8; ++i)
        {
            out<<attr[i]<<"\t";
        }
        out<<Luminosity_dis<<"\t";
        out<<attr[10]<<"\t";
        out<<TypeOfSteel<<"\t";
        for (int i = 13; i < 27; ++i)
        {
            out<<attr[i]<<"\t";
        }
        int Fault=0;
        for (int i = 0; i < 7; ++i)
        {
            Fault=(Fault+attr[i+27])*2;
        }
        out<<Fault<<endl;
        count++;
    }
    in.close();
    return 0;
}
复制代码

正文

改善之后的属性为：

Diff_X	Diff_Y	Pixels_Areas	X_Perimeter	Y_Perimeter	Sum_of_Luminosity	Diff_Luminosity	Length_of_Conveyer	TypeouOfSteel	Steel_Plate_Thickness	Edges_Index	Empty_Index	Square_Index	Outside_X_Index	Edges_X_Index	Edges_Y_Index	Outside_Global_Index	LogOfAreas	Log_X_Index	Log_Y_Index	Orientation_Index	Luminosity_Index	SigmoidOfAreas	Fault
8	44	267	17	44	24220	32	1687	1	80	0.0498	0.2415	0.1818	0.0047	0.4706	1	1	2.4265	0.9031	1.6435	0.8182	-0.2913	0.5822	128
6	29	108	10	30	11397	39	1687	1	80	0.7647	0.3793	0.2069	0.0036	0.6	0.9667	1	2.0334	0.7782	1.4624	0.7931	-0.1756	0.2984	128
复制代码

为此还特地写了个C++的程序来观察！

#include<iostream>
#include<string>
#include<fstream>
using namespace std;

int main()
{
    string line[72];
    int count=0;
    for (int i = 0; i < 72; ++i)
    {
        cin>>line[i];
    }
    for (int i = 0; i < 24; ++i)
    {
        cout<<"[->"<<i<<": "<<line[i]<<" --> "<<line[i+24]<<" --> "<<line[i+48]<<endl;
        /* code */
    }
}
复制代码

最后整出来还蛮好看！?

[->0: Diff_X --> 8 --> 6
[->1: Diff_Y --> 44 --> 29
[->2: Pixels_Areas --> 267 --> 108
[->3: X_Perimeter --> 17 --> 10
[->4: Y_Perimeter --> 44 --> 30
[->5: Sum_of_Luminosity --> 24220 --> 11397
[->6: Diff_Luminosity --> 32 --> 39
[->7: Length_of_Conveyer --> 1687 --> 1687
[->8: TypeouOfSteel --> 1 --> 1
[->9: Steel_Plate_Thickness --> 80 --> 80
[->10: Edges_Index --> 0.0498 --> 0.7647
[->11: Empty_Index --> 0.2415 --> 0.3793
[->12: Square_Index --> 0.1818 --> 0.2069
[->13: Outside_X_Index --> 0.0047 --> 0.0036
[->14: Edges_X_Index --> 0.4706 --> 0.6
[->15: Edges_Y_Index --> 1 --> 0.9667
[->16: Outside_Global_Index --> 1 --> 1
[->17: LogOfAreas --> 2.4265 --> 2.0334
[->18: Log_X_Index --> 0.9031 --> 0.7782
[->19: Log_Y_Index --> 1.6435 --> 1.4624
[->20: Orientation_Index --> 0.8182 --> 0.7931
[->21: Luminosity_Index --> -0.2913 --> -0.1756
[->22: SigmoidOfAreas --> 0.5822 --> 0.2984
[->23: Fault --> 128 --> 128
复制代码