clear all;
close all;
clc;
train=csvread('Training.csv');%输入训练数据
test=csvread('Testing-label.csv'); %输入测试数据
test_attr = test(:,2:4);
test_label=test(:,5);%真实特征值
train_attr=train(:,2:4);%训练数据
train_label=train(:,5);%训练特征列
classification = knnclassify(test_attr,train_attr,train_label);
c=[test,classification];
m=1000;
figure;
hold on;
for i=1:m
if c(i,5)==0
plot3(c(i,2),c(i,3),c(i,4),'.','color','r','markersize',10);
elseif c(i,5)==1
plot3(c(i,2),c(i,3),c(i,4),'.','color','g','markersize',10);
else
plot3(c(i,2),c(i,3),c(i,4),'.','color','b','markersize',10);
end
end
count=0;
for i=1:m
if classification(i)==test_label(i)
count=count+1;
end
end
accuracy=count/m
