I found using J48 with laplace smoothing that it
always, only checked a sample) returned distributions that summed to
greater than 1. Is this a known bug that's fixed?
I could confirm that in the developer version as well. We're looking
Peter Reutemann, Dept. of Computer Science, University of Waikato, NZ
+64 (7) 838-4466 Ext. 5174