聚类分析—Kmeans and Kmedoids聚类 ppt课件

??按下式重新计算k个聚类中心；????重复步骤2和步骤3，直到达到最大迭代次数为止。Р2020/10/15РРMatlab程序实现Рfunction [M, j, e] = kmeans(X, K, Max_Its)?[N,D]=size(X);?I=randperm(N);?M=X(I(1:K),:);?Mo = M;?for n=1:Max_Its? for k=1:K? Dist(:,k) = sum((X - repmat(M(k,:),N,1)).^2,2)';? end? [i, j]=min(Dist, [], 2);? for k=1:K? if size(find(j==k))>0? M(k, :) = mean(X(find(j==k), :));? end? endР2020/10/15РРMatlab程序实现（续）РZ = zeros(N,K);? for m=1:N? Z(m,j(m)) = 1;? end? e = sum(sum(Z.*Dist)./N);? fprintf('%d Error = %f\n', n, e);? Mo = M;?endР2020/10/15РРk-平均聚类算法(续)Р例Р0Р1Р2Р3Р4Р5Р6Р7Р8Р9Р10Р0Р1Р2Р3Р4Р5Р6Р7Р8Р9Р10Р0Р1Р2Р3Р4Р5Р6Р7Р8Р9Р10Р0Р1Р2Р3Р4Р5Р6Р7Р8Р9Р10РK=2?任意选择 K个对象作为初始聚类中心Р将每个对象赋给最类似的中心Р更新簇的平均值Р重新赋值Р更新簇的平均值Р重新赋值Р2020/10/15