def testProb(self):
c = Classifier(getwords)
# training
c.incc("Good")
c.incf("hello", "Good")
c.incc("Good")
c.incf("world", "Good")
c.incc("Good")
c.incf("world", "Good")
c.incc("Bad")
c.incf("world", "Bad")
# classify new document
item = "world world wurst Wurst wurst world"
self.assertEqual(c.prob(item, "Good"), 0.234375)
print "----------------------------------------------------------------"
print "----------------------------------------------------------------"
print "----------------------------------------------------------------"
print 'Number of used trainings samples in categorie tech',countnews['tech']
print 'Number of used trainings samples in categorie notech',countnews['nontech']
print 'Number of used test samples',countnews['test']
print '--'*30
rss_classifier = Classifier()
for tech in train_data["good"]:
rss_classifier.train(tech, "good")
for nontech in train_data["bad"]:
rss_classifier.train(nontech, "bad")
print "---- training finished ---------------------"
for test in data:
g_pb = rss_classifier.prob(test, "good")
b_pb = rss_classifier.prob(test, "bad")
# Normalisierung der Wahrscheinlichkeiten
g_pb_n = g_pb /(g_pb + b_pb)
b_pb_n = b_pb /(g_pb + b_pb)
print test
print "good: ", g_pb_n, " bad: ", b_pb_n
rss_classifier.save("trainData")
