def test_classify_nb(self): # pylint: disable=missing-docstring
documents = [
['stupid'],
['smart']
]
classifications = [1, 0]
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))
print "trainmat: ", trainmat, "\n"
self.assertEqual(trainmat, [[1, 0], [0, 1]])
p0_vec, p1_vec, p_abusive = bayes.train_nbo(trainmat, classifications)
# print p0_vec, p1_vec, p_abusive
this_doc = array(bayes.set_of_words_2_vec(vocabulary, ['smart']))
print "this_doc: ", this_doc, "\n"
result = bayes.classify_nb(this_doc, p0_vec, p1_vec, p_abusive)
print "result: ", result, "\n"
self.assertEqual(result, 0)
this_doc = array(bayes.set_of_words_2_vec(vocabulary, ['stupid']))
print "this_doc: ", this_doc, "\n"
result = bayes.classify_nb(this_doc, p0_vec, p1_vec, p_abusive)
print "result: ", result, "\n"
self.assertEqual(result, 1)
this_doc = array(bayes.set_of_words_2_vec(vocabulary, ['intelligent']))
print "this_doc: ", this_doc, "\n"
result = bayes.classify_nb(this_doc, p0_vec, p1_vec, p_abusive)
print "result: ", result, "\n"
self.assertEqual(result, 0)
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)