def test_bag_of_words_2_vec_mn(self):
documents, classifications = bayes.load_documents() # pylint: disable=unused-variable
vocabulary = bayes.create_vocabulary(documents)
features = bayes.bag_of_words_2_vec_mn(vocabulary, documents[0])
expected = [
0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0,
0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1
]
self.assertEqual(features, expected)
def test_train_nbo(self):
documents, classifications = bayes.load_documents()
vocabulary = bayes.create_vocabulary(documents)
trainmat = [] # list of lists, e.g., [[...], ..., [...]]
for document in documents:
trainmat.append(bayes.set_of_words_2_vec(vocabulary, document))
# this is interesting as the names sent to the funtion imply
# different types than the names received by the function.
# Compare sending trainCategory to receiving classifications.
# There isn't even a hint of meaning between those two names
# at the program (self-referentiall) perspective.
# p0Vect, p1Vect, pAbusive = trainNBO(trainMatrix, trainCategory)
p0_vec, p1_vec, p_abusive = bayes.train_nbo(trainmat, classifications)
# print p0V, p1V, pAb
self.assertAlmostEqual(p_abusive, 0.5)
