[Biopython-dev] [Bug 2268] Cluster unit test suite runs indefinitely

bugzilla-daemon at portal.open-bio.org bugzilla-daemon at portal.open-bio.org
Tue May 1 12:01:49 UTC 2007


http://bugzilla.open-bio.org/show_bug.cgi?id=2268





------- Comment #8 from mdehoon at ims.u-tokyo.ac.jp  2007-05-01 08:01 EST -------
Chris,

I was not able to replicate this bug on any of the platforms I've tried so far
(Windows 32-bits, Mac OS X, Unix, Linux). However, since it does occur on your
system, I still feel that this is a true bug that should be fixed. Would you be
willing to compile and run some test cases on your platform to find the source
of this problem?

One possibility is that the k-means algorithm gets stuck in an infinite
(periodic) loop in which genes are assigned back and forth between clusters. I
thought that with the current implementation, that was no longer possible, but
maybe there is some case that I overlooked. Since the k-means algorithm starts
from a random initial state, maybe on your platform starts from some funny
initial state that doesn't appear on the other platforms, causing this bug to
appear on your platform only.


-- 
Configure bugmail: http://bugzilla.open-bio.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.



More information about the Biopython-dev mailing list