clustering_kmeans

clear all;
clc;

addpath(genpath('utils'))
result = zeros(10,3);
% std=zeros(1,3);
for i=1:10
tic;
% load COIL20.mat; k = 20;
% load lung_discrete.mat; k = 7;
% load iris_uni.mat; k=3;
% load cleve_uni; k=4;
% load monk1_uni; k=2;
% load dermatology_uni; k=6;
% load glass_uni; k=6;
% load auto_uni; k=6;
% load ORL_32x32.mat; k=40;
% load cars_uni; k=3;
load umist.mat; k=20;

% fea = X;
% gnd = Y;
fea = NormalizeFea(fea,1);

%%%% Kmeans Clustering

  [predict_label, predict_center] = litekmeans(fea, k);

   %%%% Clustering Evaluation
   result(i,:) = ClusteringMeasure(gnd, predict_label);
toc;
end

average=mean(result,1)
std=std(result,0,1)