On 11/26/2013 10:26 PM, Walrus theCat wrote:
Ok, I definitely agree that my data size should be higher, but even a zero count doesn't necessitate an NPE. This could be tested via some data set (ala UCIhttp://archive.ics.uci.edu/ml/), as to whether there exists some threshold where the cross validator doesn't throw NPEs, and that information included in the documentation:-D. I think we can all see where I'm going with this... haha.
Yes, please send us patches to fix the exceptions and a patch for our documentation :)
Jörn
