Kmean vs CLUTO
I know that CLUTO doesn't support kmean, so i want to write a program that implements k-mean algorithm to compare with CLUTO, but i have a problem with kmean, if anyone has expertised with this problem please answer me. When i used program to cluster re0(K=13) dataset the results always show that kmean give 13 cluster with only one contain all the documents and the others don't contain any documents. How-to cope with the case that a cluster is empty? when a cluster is empty how can we update its centroid?