k_means.m

this code is a faster kmeans clustering implementation

function [gIdx,c]=k_means(X,k)
% Check input and output number of arguments
error(nargchk(2,2,nargin));
error(nargoutchk(0,2,nargout));
[n,m]=size(X);
% Check if second input is centroids else generate the centers randomly
if ~isscalar(k)
    c=k;
    k=size(c,1);
else
    c=X(ceil(rand(k,1)*n),:);
end
% allocating variables
g0=ones(n,1);
gIdx=zeros(n,1);
D=zeros(n,k);
% Main loop converge if previous partition is the same as current
while any(g0~=gIdx)
%     disp(sum(g0~=gIdx))
    g0=gIdx;
    % Loop for each centroid
    for t=1:k
        d=zeros(n,1);
        % Loop for each dimension
        for s=1:m
            d=d+(X(:,s)-c(t,s)).^2;
        end
        D(:,t)=d;
    end
    % Partition data to closest centroids
    [z,gIdx]=min(D,[],2);
    % Update centroids using means of partitions
    for t=1:k
        c(t,:)=mean(X(gIdx==t,:));
    end
%     for t=1:m
%         c(:,t)=accumarray(gIdx,X(:,t),[],@mean);
%     end
end