226
edits
Changes
Jump to navigation
Jump to search
Parallel Enclosing Circle Algorithm (view source)
Revision as of 15:18, 27 November 2017
, 15:18, 27 November 2017→Progress on the bug
=== Progress on the bug ===
# Removing duplicate points from the data actually removes all of the errors, but this doesn't give you the solution with the smallest area.
# I tried removing duplicates but keeping track of a "count,." though this reintroduces errors.## % error before change (n=997 sample, A-Carlsbad):## % error after change (n=997 sample):
# I narrowed down the bug to the constrained_kmeans method in ckmeans.py [https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/tr-2000-65.pdf (paper here)]
## For some reason, this returns clusters with smaller numbers of points than n
