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)
# Correct Score Output
np.testing.assert_array_almost_equal(
score[0], self.correct_a_very_close_game_score)
def test_update_dictionary_shorten_dictionary(self):
model = Multinomial()
model.train(self.sports_labels, self.sports_data)
model.update_dictionary(self.sports_map, self.sports_map_shortened)
prediction, score = model.predict(self.a_very_close_game_short)
# Correct Model Parameter Updates
np.testing.assert_array_almost_equal(model.priors, self.correct_priors)
np.testing.assert_array_almost_equal(model.label_counts,
self.correct_label_count)
np.testing.assert_array_almost_equal(
model.empty_likelihoods, self.correct_shortened_empty_likelihoods)
np.testing.assert_array_almost_equal(
model.likelihoods, self.correct_shortened_likelihoods)
# Correct Scores
np.testing.assert_array_almost_equal(
score[0], self.correct_shortened_a_very_close_game_score)
# Correct Prediction
self.assertEqual(prediction[0], 0)
def test_update_add_more_training_data(self):
model = Multinomial()
model.train(self.sports_labels[0:4], self.sports_data[0:4])
model.update(np.array([self.sports_labels[4]]),
np.array([self.sports_data[4]]))
prediction, score = model.predict(self.a_very_close_game)
# Correct Model Parameter Updates
np.testing.assert_array_almost_equal(model.priors, self.correct_priors)
np.testing.assert_array_almost_equal(model.label_counts,
self.correct_label_count)
np.testing.assert_array_almost_equal(model.empty_likelihoods,
self.correct_empty_likelihoods)
np.testing.assert_array_almost_equal(model.likelihoods,
self.correct_likelihoods)
# Correct New Scores
np.testing.assert_array_almost_equal(
score[0], self.correct_a_very_close_game_score)
# Correct Prediction
self.assertEqual(prediction[0], 0)
print("- Dictionary")
print("Accuracy: " + str(matches / len(labels)))
################
# Vector Model #
################
wine_vector_data = wine_data["vectors"]
index_map = wine_vector_data["word_map"]
reviews_as_vector = wine_vector_data["vectors"]
labels_as_vectors = wine_vector_data["labels"]
model_vect = VectMultinomial()
model_vect.train(labels_as_vectors, reviews_as_vector)
vect_predictions, vect_scores = model_vect.predict(reviews_as_vector)
accuracy = np.sum(
vect_predictions == labels_as_vectors) / labels_as_vectors.shape[0]
print("- Vector")
print("Accuracy: " + str(accuracy))
#####################
# Spam Data Example #
#####################
print("\nSpam Data Example")
with open('./sample_data/kaggle/spam/sms_spam.pkl', 'rb') as f:
spam_data = pickle.load(f)