K-Means++的代码

function [L,C] = kmeanspp(X,k)
%KMEANS Cluster multivariate data using the k-means++ algorithm.
% [L,C] = kmeans_pp(X,k) produces a 1-by-size(X,2) vector L with one class
% label per column in X and a size(X,1)-by-k matrix C containing the
% centers corresponding to each class.
% Version: 2013-02-08
% Authors: Laurent Sorber (Laurent.Sorber@cs.kuleuven.be)
L = [];
L1 = 0;
while length(unique(L)) ~= k
% The k-means++ initialization.
% C就是从X中随机挑一个随机点
C = X(:,1+round(rand*(size(X,2)-1))); %size(X,2)是数据集合X的数据点的数目，C是中心点的集合
L = ones(1,size(X,2));
for i = 2:k
D = X-C(:,L); %-1，此时的C扩大了，D相当于每个X-C的集合
D = cumsum(sqrt(dot(D,D,1))); %将每个数据点与中心点的距离，依次累加，欧氏距离
if D(end) == 0, C(:,i:k) = X(:,ones(1,k-i+1)); return; end 
C(:,i) = X(:,find(rand < D/D(end),1)); %find的第二个参数表示返回的索引的数目，D/D(end)距离越远概率越大
[~,L] = max(bsxfun(@minus,2*real(C'*X),dot(C,C,1).')); %碉堡了，这句，将每个数据点进行分类。
end
% The k-means algorithm.
% any函数：检测矩阵中是否有非零元素，如果有，则返回1，否则，返回0。
while any(L ~= L1)
L1 = L;
for i = 1:k, l = L==i; C(:,i) = sum(X(:,l),2)/sum(l); end %l是各族索引
[~,L] = max(bsxfun(@minus,2*real(C'*X),dot(C,C,1).'),[],1);
end
end

 

 

clear all; close all; clc
x=[randn(3,2)*.4;randn(4,2)*.5+ones(4,1)*[4 4]];
[L, C] = kmeanspp(x',2);
L
C