Calculate euclidean distances

Fri Apr 01, 2011 10:13 pm

Calculate euclidean distances between samples .
usage :

Code:: function D = mydistfunc(X, C, dist, iter) %DISTFUN Calculate point to cluster centroid distances. [n,p] = size(X); D = zeros(n,size(C,1)); nclusts = size(C,1); switch dist case 'sqeuclidean' for i = 1:nclusts D(:,i) = (X(:,1) - C(i,1)).^2; for j = 2:p D(:,i) = D(:,i) + (X(:,j) - C(i,j)).^2; end % D(:,i) = sum((X - C(repmat(i,n,1),:)).^2, 2); end case 'cityblock' for i = 1:nclusts D(:,i) = abs(X(:,1) - C(i,1)); for j = 2:p D(:,i) = D(:,i) + abs(X(:,j) - C(i,j)); end % D(:,i) = sum(abs(X - C(repmat(i,n,1),:)), 2); end case {'cosine','correlation'} % The points are normalized, centroids are not, so normalize them normC = sqrt(sum(C.^2, 2)); if any(normC < eps(class(normC))) % small relative to unit-length data points error('stats:kmeans:ZeroCentroid', ... 'Zero cluster centroid created at iteration %d.',iter); end for i = 1:nclusts D(:,i) = max(1 - X * (C(i,:)./normC(i))', 0); end case 'hamming' for i = 1:nclusts D(:,i) = abs(X(:,1) - C(i,1)); for j = 2:p D(:,i) = D(:,i) + abs(X(:,j) - C(i,j)); end D(:,i) = D(:,i) / p; % D(:,i) = sum(abs(X - C(repmat(i,n,1),:)), 2) / p; end end end % function