Evaluating on 2200 examples in 5 splits
Split 1
   number of positive examples = 36
   number of negative examples = 404
   Area under ROC curve        = 99.6 %
   Area under PRC curve        = 92.8 %
   accuracy (at threshold 0)   = 97.3 % 
Split 2
   number of positive examples = 40
   number of negative examples = 400
   Area under ROC curve        = 99.4 %
   Area under PRC curve        = 89.8 %
   accuracy (at threshold 0)   = 96.8 % 
Split 3
   number of positive examples = 51
   number of negative examples = 389
   Area under ROC curve        = 99.1 %
   Area under PRC curve        = 92.7 %
   accuracy (at threshold 0)   = 96.1 % 
Split 4
   number of positive examples = 40
   number of negative examples = 400
   Area under ROC curve        = 97.9 %
   Area under PRC curve        = 82.0 %
   accuracy (at threshold 0)   = 95.7 % 
Split 5
   number of positive examples = 33
   number of negative examples = 407
   Area under ROC curve        = 97.7 %
   Area under PRC curve        = 77.5 %
   accuracy (at threshold 0)   = 95.9 % 
Averages
   number of positive examples = 40
   number of negative examples = 400
   Area under ROC curve        = 98.8 %
   Area under PRC curve        = 86.9 %
   accuracy (at threshold 0)   = 96.4 %