from data import Data
from naivebayes import NaiveBayes
filename = "datasets/weatherNominal.td"
## filename = "datasets/titanic.td"
## filename = "datasets/cmc.td"
d = Data(filename)
d.report()
pr = NaiveBayes(d)
pr.train()
pr.show()
for (v, c_true) in d.test_set:
c_pred = pr.predict(v)[0]
print(v, ":")
print(" ", c_pred, "( true class:", c_true, ")")
## print(pr.predict(("Class:1st","Sex:Female","Age:Child")))
## print(pr.predict(("Class:Crew","Sex:Female","Age:Child")))
#pos_class = "Survived:No"
# datafile = "cmcTr.txt"
# pos_class = "contraceptive-method:none"
d = Data(datafile)
prnb = NaiveBayes(d)
prnb.train()
r = Roc(prnb, pos_class)
r.do_curve()
print "Predicting", pos_class, "for data file", datafile,
print "with", int(r.curve[2]), "positive instances and", int(
r.curve[3]), "negative instances"
if print_numbers:
prnb.show()
print "Scores for predicting", pos_class, ":"
for e in sorted(r.preds):
print e
print "==="
print "Curve coordinates:"
for e in zip(r.curve[0], r.curve[1]):
print e
r.draw_curve()
