正文
K-means算法的matlab程序
提示：扫一扫查出行【扫一扫了解最新限行尾号】
复制提示
K-means算法的matlab程序
在“K-means算法的matlab程序（初步）”这篇文章中已经用matlab程序对iris数据库进行简单的实现，下面的程序最终的目的是求准确度。
作者：凯鲁嘎吉 - 博客园 http://www.cnblogs.com/kailugaji/
1.采用iris数据库iris_data.txt
5.1 3.5 1.4 0.2
4.9 1.4 0.2
4.7 3.2 1.3 0.2
4.6 3.1 1.5 0.2
3.6 1.4 0.2
5.4 3.9 1.7 0.4
4.6 3.4 1.4 0.3
3.4 1.5 0.2
4.4 2.9 1.4 0.2
4.9 3.1 1.5 0.1
5.4 3.7 1.5 0.2
4.8 3.4 1.6 0.2
4.8 1.4 0.1
4.3 1.1 0.1
5.8 1.2 0.2
5.7 4.4 1.5 0.4
5.4 3.9 1.3 0.4
5.1 3.5 1.4 0.3
5.7 3.8 1.7 0.3
5.1 3.8 1.5 0.3
5.4 3.4 1.7 0.2
5.1 3.7 1.5 0.4
4.6 3.6 0.2
5.1 3.3 1.7 0.5
4.8 3.4 1.9 0.2
1.6 0.2
3.4 1.6 0.4
5.2 3.5 1.5 0.2
5.2 3.4 1.4 0.2
4.7 3.2 1.6 0.2
4.8 3.1 1.6 0.2
5.4 3.4 1.5 0.4
5.2 4.1 1.5 0.1
5.5 4.2 1.4 0.2
4.9 3.1 1.5 0.2
3.2 1.2 0.2
5.5 3.5 1.3 0.2
4.9 3.6 1.4 0.1
4.4 1.3 0.2
5.1 3.4 1.5 0.2
3.5 1.3 0.3
4.5 2.3 1.3 0.3
4.4 3.2 1.3 0.2
3.5 1.6 0.6
5.1 3.8 1.9 0.4
4.8 1.4 0.3
5.1 3.8 1.6 0.2
4.6 3.2 1.4 0.2
5.3 3.7 1.5 0.2
3.3 1.4 0.2
3.2 4.7 1.4
6.4 3.2 4.5 1.5
6.9 3.1 4.9 1.5
5.5 2.3 1.3
6.5 2.8 4.6 1.5
5.7 2.8 4.5 1.3
6.3 3.3 4.7 1.6
4.9 2.4 3.3
6.6 2.9 4.6 1.3
5.2 2.7 3.9 1.4
3.5
5.9 4.2 1.5
2.2
6.1 2.9 4.7 1.4
5.6 2.9 3.6 1.3
6.7 3.1 4.4 1.4
5.6 4.5 1.5
5.8 2.7 4.1
6.2 2.2 4.5 1.5
5.6 2.5 3.9 1.1
5.9 3.2 4.8 1.8
6.1 2.8 1.3
6.3 2.5 4.9 1.5
6.1 2.8 4.7 1.2
6.4 2.9 4.3 1.3
6.6 4.4 1.4
6.8 2.8 4.8 1.4
6.7 1.7
2.9 4.5 1.5
5.7 2.6 3.5
5.5 2.4 3.8 1.1
5.5 2.4 3.7
5.8 2.7 3.9 1.2
2.7 5.1 1.6
5.4 4.5 1.5
3.4 4.5 1.6
6.7 3.1 4.7 1.5
6.3 2.3 4.4 1.3
5.6 4.1 1.3
5.5 2.5 1.3
5.5 2.6 4.4 1.2
6.1 4.6 1.4
5.8 2.6 1.2
2.3 3.3
5.6 2.7 4.2 1.3
5.7 4.2 1.2
5.7 2.9 4.2 1.3
6.2 2.9 4.3 1.3
5.1 2.5 1.1
5.7 2.8 4.1 1.3
6.3 3.3 2.5
5.8 2.7 5.1 1.9
7.1 5.9 2.1
6.3 2.9 5.6 1.8
6.5 5.8 2.2
7.6 6.6 2.1
4.9 2.5 4.5 1.7
7.3 2.9 6.3 1.8
6.7 2.5 5.8 1.8
7.2 3.6 6.1 2.5
6.5 3.2 5.1
6.4 2.7 5.3 1.9
6.8 5.5 2.1
5.7 2.5
5.8 2.8 5.1 2.4
6.4 3.2 5.3 2.3
6.5 5.5 1.8
7.7 3.8 6.7 2.2
7.7 2.6 6.9 2.3
2.2 1.5
6.9 3.2 5.7 2.3
5.6 2.8 4.9
7.7 2.8 6.7
6.3 2.7 4.9 1.8
6.7 3.3 5.7 2.1
7.2 3.2 1.8
6.2 2.8 4.8 1.8
6.1 4.9 1.8
6.4 2.8 5.6 2.1
7.2 5.8 1.6
7.4 2.8 6.1 1.9
7.9 3.8 6.4
6.4 2.8 5.6 2.2
6.3 2.8 5.1 1.5
6.1 2.6 5.6 1.4
7.7 6.1 2.3
6.3 3.4 5.6 2.4
6.4 3.1 5.5 1.8
4.8 1.8
6.9 3.1 5.4 2.1
6.7 3.1 5.6 2.4
6.9 3.1 5.1 2.3
5.8 2.7 5.1 1.9
6.8 3.2 5.9 2.3
6.7 3.3 5.7 2.5
6.7 5.2 2.3
6.3 2.5 1.9
6.5 5.2
6.2 3.4 5.4 2.3
5.9 5.1 1.8
iris_id.txt
2.matlab源程序：My_Kmeans.m
function label_1=My_Kmeans(K)
%输入K：聚类数
%输出：label_1:聚的类, para_miu_new:聚类中心μ
format long
eps=1e-5; %定义迭代终止条件的eps
data=dlmread('E:\www.cnblogs.comkailugaji\data\iris\iris_data.txt');
%----------------------------------------------------------------------------------------------------
%对data做最大-最小归一化处理
[data_num,~]=size(data);
X=(data-ones(data_num,1)*min(data))./(ones(data_num,1)*(max(data)-min(data)));
[X_num,~]=size(X);
%----------------------------------------------------------------------------------------------------
%随机初始化K个聚类中心
rand_array=randperm(X_num); %产生1~X_num之间整数的随机排列
para_miu_new=X(rand_array(1:K),:); %随机排列取前K个数，在X矩阵中取这K行作为初始聚类中心
responsivity=zeros(X_num,K);
%----------------------------------------------------------------------------------------------------
%K-means算法
while true
para_miu=para_miu_new; %上一步的聚类中心
%欧氏距离，计算（X-para_miu）^2=X^2+para_miu^2-2*X*para_miu'，矩阵大小为X_num*K
distant=repmat(sum(X.*X,2),1,K)+repmat(sum(para_miu.*para_miu,2)',X_num,1)-2*X*para_miu';
%返回distant每行最小值所在的下标
[~,label_1]=min(distant,[],2);
%构建隶属度矩阵X_num*K
for i=1:X_num
for j=1:K
responsivity(i,j)=isequal(j,label_1(i));
end
end
R_k=sum(responsivity,1); %分母,第k类的个数,1*k的矩阵
para_miu_new=diag(1./R_k)*responsivity'*X; %更新参数miu(聚类中心)
if norm(para_miu_new-para_miu)<=eps
break;
end
end
Eg_Kmeans.m
function ave_acc_kmeans=Eg_Kmeans(K,max_iter)
%输入K:聚的类，max_iter是最大迭代次数
%输出ave_acc_kmeans：迭代max_iter次之后的平均准确度
s=0;
for i=1:max_iter
label_1=My_Kmeans(K);
accuracy=succeed(K,label_1);
s=s+accuracy;
end
ave_acc_kmeans=s/max_iter;
3.结果>> ave_acc_kmeans=Eg_Kmeans(3,50)
ave_acc_kmeans =
0.842533333333333
5.1 3.5 1.4 0.2
4.9 1.4 0.2
4.7 3.2 1.3 0.2
4.6 3.1 1.5 0.2
3.6 1.4 0.2
5.4 3.9 1.7 0.4
4.6 3.4 1.4 0.3
3.4 1.5 0.2
4.4 2.9 1.4 0.2
4.9 3.1 1.5 0.1
5.4 3.7 1.5 0.2
4.8 3.4 1.6 0.2
4.8 1.4 0.1
4.3 1.1 0.1
5.8 1.2 0.2
5.7 4.4 1.5 0.4
5.4 3.9 1.3 0.4
5.1 3.5 1.4 0.3
5.7 3.8 1.7 0.3
5.1 3.8 1.5 0.3
5.4 3.4 1.7 0.2
5.1 3.7 1.5 0.4
4.6 3.6 0.2
5.1 3.3 1.7 0.5
4.8 3.4 1.9 0.2
1.6 0.2
3.4 1.6 0.4
5.2 3.5 1.5 0.2
5.2 3.4 1.4 0.2
4.7 3.2 1.6 0.2
4.8 3.1 1.6 0.2
5.4 3.4 1.5 0.4
5.2 4.1 1.5 0.1
5.5 4.2 1.4 0.2
4.9 3.1 1.5 0.2
3.2 1.2 0.2
5.5 3.5 1.3 0.2
4.9 3.6 1.4 0.1
4.4 1.3 0.2
5.1 3.4 1.5 0.2
3.5 1.3 0.3
4.5 2.3 1.3 0.3
4.4 3.2 1.3 0.2
3.5 1.6 0.6
5.1 3.8 1.9 0.4
4.8 1.4 0.3
5.1 3.8 1.6 0.2
4.6 3.2 1.4 0.2
5.3 3.7 1.5 0.2
3.3 1.4 0.2
3.2 4.7 1.4
6.4 3.2 4.5 1.5
6.9 3.1 4.9 1.5
5.5 2.3 1.3
6.5 2.8 4.6 1.5
5.7 2.8 4.5 1.3
6.3 3.3 4.7 1.6
4.9 2.4 3.3
6.6 2.9 4.6 1.3
5.2 2.7 3.9 1.4
3.5
5.9 4.2 1.5
2.2
6.1 2.9 4.7 1.4
5.6 2.9 3.6 1.3
6.7 3.1 4.4 1.4
5.6 4.5 1.5
5.8 2.7 4.1
6.2 2.2 4.5 1.5
5.6 2.5 3.9 1.1
5.9 3.2 4.8 1.8
6.1 2.8 1.3
6.3 2.5 4.9 1.5
6.1 2.8 4.7 1.2
6.4 2.9 4.3 1.3
6.6 4.4 1.4
6.8 2.8 4.8 1.4
6.7 1.7
2.9 4.5 1.5
5.7 2.6 3.5
5.5 2.4 3.8 1.1
5.5 2.4 3.7
5.8 2.7 3.9 1.2
2.7 5.1 1.6
5.4 4.5 1.5
3.4 4.5 1.6
6.7 3.1 4.7 1.5
6.3 2.3 4.4 1.3
5.6 4.1 1.3
5.5 2.5 1.3
5.5 2.6 4.4 1.2
6.1 4.6 1.4
5.8 2.6 1.2
2.3 3.3
5.6 2.7 4.2 1.3
5.7 4.2 1.2
5.7 2.9 4.2 1.3
6.2 2.9 4.3 1.3
5.1 2.5 1.1
5.7 2.8 4.1 1.3
6.3 3.3 2.5
5.8 2.7 5.1 1.9
7.1 5.9 2.1
6.3 2.9 5.6 1.8
6.5 5.8 2.2
7.6 6.6 2.1
4.9 2.5 4.5 1.7
7.3 2.9 6.3 1.8
6.7 2.5 5.8 1.8
7.2 3.6 6.1 2.5
6.5 3.2 5.1
6.4 2.7 5.3 1.9
6.8 5.5 2.1
5.7 2.5
5.8 2.8 5.1 2.4
6.4 3.2 5.3 2.3
6.5 5.5 1.8
7.7 3.8 6.7 2.2
7.7 2.6 6.9 2.3
2.2 1.5
6.9 3.2 5.7 2.3
5.6 2.8 4.9
7.7 2.8 6.7
6.3 2.7 4.9 1.8
6.7 3.3 5.7 2.1
7.2 3.2 1.8
6.2 2.8 4.8 1.8
6.1 4.9 1.8
6.4 2.8 5.6 2.1
7.2 5.8 1.6
7.4 2.8 6.1 1.9
7.9 3.8 6.4
6.4 2.8 5.6 2.2
6.3 2.8 5.1 1.5
6.1 2.6 5.6 1.4
7.7 6.1 2.3
6.3 3.4 5.6 2.4
6.4 3.1 5.5 1.8
4.8 1.8
6.9 3.1 5.4 2.1
6.7 3.1 5.6 2.4
6.9 3.1 5.1 2.3
5.8 2.7 5.1 1.9
6.8 3.2 5.9 2.3
6.7 3.3 5.7 2.5
6.7 5.2 2.3
6.3 2.5 1.9
6.5 5.2
6.2 3.4 5.4 2.3
5.9 5.1 1.8
My_Kmeans.m
function label_1=My_Kmeans(K)
%输入K：聚类数
%输出：label_1:聚的类, para_miu_new:聚类中心μ
format long
eps=1e-5; %定义迭代终止条件的eps
data=dlmread('E:\www.cnblogs.comkailugaji\data\iris\iris_data.txt');
%----------------------------------------------------------------------------------------------------
%对data做最大-最小归一化处理
[data_num,~]=size(data);
X=(data-ones(data_num,1)*min(data))./(ones(data_num,1)*(max(data)-min(data)));
[X_num,~]=size(X);
%----------------------------------------------------------------------------------------------------
%随机初始化K个聚类中心
rand_array=randperm(X_num); %产生1~X_num之间整数的随机排列
para_miu_new=X(rand_array(1:K),:); %随机排列取前K个数，在X矩阵中取这K行作为初始聚类中心
responsivity=zeros(X_num,K);
%----------------------------------------------------------------------------------------------------
%K-means算法
while true
para_miu=para_miu_new; %上一步的聚类中心
%欧氏距离，计算（X-para_miu）^2=X^2+para_miu^2-2*X*para_miu'，矩阵大小为X_num*K
distant=repmat(sum(X.*X,2),1,K)+repmat(sum(para_miu.*para_miu,2)',X_num,1)-2*X*para_miu';
%返回distant每行最小值所在的下标
[~,label_1]=min(distant,[],2);
%构建隶属度矩阵X_num*K
for i=1:X_num
for j=1:K
responsivity(i,j)=isequal(j,label_1(i));
end
end
R_k=sum(responsivity,1); %分母,第k类的个数,1*k的矩阵
para_miu_new=diag(1./R_k)*responsivity'*X; %更新参数miu(聚类中心)
if norm(para_miu_new-para_miu)<=eps
break;
end
end
Eg_Kmeans.m
function ave_acc_kmeans=Eg_Kmeans(K,max_iter)
%输入K:聚的类，max_iter是最大迭代次数
%输出ave_acc_kmeans：迭代max_iter次之后的平均准确度
s=0;
for i=1:max_iter
label_1=My_Kmeans(K);
accuracy=succeed(K,label_1);
s=s+accuracy;
end
ave_acc_kmeans=s/max_iter;
3.结果>> ave_acc_kmeans=Eg_Kmeans(3,50)
ave_acc_kmeans =
0.842533333333333
>> ave_acc_kmeans=Eg_Kmeans(3,50)
ave_acc_kmeans =
0.842533333333333
