> - it doesn't have the final pass of in-memory clustering so it really just > gives you an indifferent quality clustering with a huge number of weighted > clusters. With the final pass, it will give you a high quality clustering > with your specified number of clusters.
I think the "huge number of weighted clusters" can be actually beneficial in certain applications. Are you going to leave this in as an option when integrating with Mahout, Ted? Still didn't have time to look at the code yet ;( Dawid
