yes, but the other centroid should be close to all the samples in the bigger blog, isn't it?
________________________________________ From: Andy [[email protected]] Sent: Wednesday, November 05, 2014 4:18 PM To: [email protected] Subject: Re: [Scikit-learn-general] k-means with unbalanced clusters On 11/05/2014 03:15 PM, Pagliari, Roberto wrote: > I agree with you. However, for clarification purposes, do you know why in > this extreme case, false positive rate (where class 0 is much bigger than > class 1) might be pretty high if not 1? If you have two overlapping blobs and one has way more samples than the other, than the ratio of samples around the small blob approaches 1, right? (This is what would happen with fixed known centers). ------------------------------------------------------------------------------ _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general ------------------------------------------------------------------------------ _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
