请帮我用matlab编写一段kmeans算法中计算MSE结果的迭代函数

以下是一个简单的MATLAB代码，用于计算K均值聚类的MSE：

function [centroid, cluster] = kmeans(data, k)
% initializations
num_points = size(data,1);
dim = size(data,2);
cluster = zeros(num_points,1);
centroid = data(randperm(num_points,k),:);
old_centroid = zeros(size(centroid));

while sum(sum(abs(centroid - old_centroid))) > 0
old_centroid = centroid;
% assign each point to the nearest centroid
for i = 1:num_points
min_dist = inf;
for j = 1:k
dist = norm(data(i,:) - centroid(j,:));
if dist < min_dist
cluster(i) = j;
min_dist = dist;
end
end
end
% recompute centroids
for j = 1:k
centroid(j,:) = mean(data(cluster==j,:),1);
end
end

% compute MSE
mse = 0;
for i = 1:num_points
mse = mse + norm(data(i,:) - centroid(cluster(i),:))^2;
end
mse = mse/num_points;

end

您可以将数据和k作为输入参数传递给此函数。它将返回聚类中心和每个数据点所属的簇。此外，它还将计算并返回MSE值。