def test_update_dictionary_correct_shorten_dictionary(self):
model = Multinomial()
model.train(self.sports_labels, self.sports_data)
model.update_dictionary(self.shortened_dictionary)
prediction, score = model.predict(self.a_very_close_game)
# Correct Model Parameter Updates
self.assertEqual(model.priors, self.correct_priors)
self.assertEqual(model.label_counts, self.correct_label_count)
self.assertEqual(model.empty_likelihoods,
self.correct_shortened_empty_likelihoods)
self.assertDictEqual(model.likelihoods,
self.correct_shortened_likelihoods)
# Correct Scores
self.assertIsNotNone(score)
self.assertAlmostEqual(
score[0]["sport"],
self.correct_shortened_a_very_close_game_score["sport"])
self.assertAlmostEqual(
score[0]["not sport"],
self.correct_shortened_a_very_close_game_score["not sport"])
# Correct Prediction
self.assertEqual(prediction[0], "sport")
def test_predict_prediction_and_score(self):
model = Multinomial()
model.train(self.sports_labels, self.sports_data)
prediction, score = model.predict(self.a_very_close_game)
# Correct Prediction Output
self.assertEqual(prediction[0], "sport")
# Correct Score Output
self.assertIsNotNone(score)
self.assertAlmostEqual(score[0]["sport"],
self.correct_a_very_close_game_score["sport"])
self.assertAlmostEqual(
score[0]["not sport"],
self.correct_a_very_close_game_score["not sport"])
def test_update_add_more_training_data(self):
model = Multinomial()
model.train(self.sports_labels[0:4], self.sports_data[0:4])
model.update([self.sports_labels[4]], [self.sports_data[4]])
prediction, score = model.predict(self.a_very_close_game)
# Correct Model
self.assertEqual(model.priors, self.correct_priors)
self.assertEqual(model.label_counts, self.correct_label_count)
self.assertEqual(model.empty_likelihoods,
self.correct_empty_likelihoods)
self.assertDictEqual(model.likelihoods, self.correct_likelihoods)
# Correct Score Output
self.assertIsNotNone(score)
self.assertAlmostEqual(score[0]["sport"],
self.correct_a_very_close_game_score["sport"])
self.assertAlmostEqual(
score[0]["not sport"],
self.correct_a_very_close_game_score["not sport"])
# Correct Prediction Output
self.assertEqual(prediction[0], "sport")
with open('./sample_data/nltk/wine/wine_data.pkl', 'rb') as f:
wine_data = pickle.load(f)
####################
# Dictionary Model #
####################
wine_bow_data = wine_data["bagofwords"]
raw_data_top_removed = wine_bow_data["raw_data_top_removed"]
raw_data = wine_bow_data["raw_data"]
labels = wine_bow_data["labels"]
model_dict = DictMultinomial()
model_dict.train(labels, raw_data_top_removed)
dict_predictions, dict_scores = model_dict.predict(raw_data)
matches = 0
for i in range(0, len(labels)):
if dict_predictions[i] == labels[i]:
matches += 1
print("- Dictionary")
print("Accuracy: " + str(matches / len(labels)))
################
# Vector Model #
################
wine_vector_data = wine_data["vectors"]