Decision Tree的matlab实现及原理

clear all;
clc;
[S1,S2,S3,S4,S5,S6,S7,S8,classity]=textread('Pima-training-set.txt','%f %f %f %f %f %f %f %f %s');%Pima-training-set.txt
D=[S1 S2 S3 S4 S5 S6 S7 S8];
AttributName={ 'preg','plas','pres','skin','insu','mass','pedi','age'};
t=classregtree(D,classity,'names',AttributName);
t=prune(t,'level',1);% j减掉最后5层
view(t);
yfit1=eval(t,D,1);
count1=0;
for i=1:length(yfit1)
    if(strcmp(classity(i,1),yfit1(i,1)))
           count1=count1+1;
    end
end
fprintf('Accuracy of training is:%d \n',count1/length(yfit1));

costsum=zeros(10,1);   %10_1,9_2...
for k=1:10
cost=test(t,'cross',D,classity);
costsum=costsum+cost;
end
costsum=costsum/10;
i=1:10;
plot(i,costsum,'-o');xlabel('交叉次数');ylabel('错误率');
title('