def test_train_vocab_init(self):
vocab = set()
for words in np.r_[self.x_train, self.x_test, self.x_test]:
for word in words:
vocab.add(word)
model = polygo.Sequence(initial_vocab=vocab,
embeddings=self.embeddings)
model.fit(self.x_train, self.y_train, self.x_test, self.y_test)
def test_analyze(self):
model = polygo.Sequence()
model.fit(self.x_train, self.y_train)
res = model.analyze(self.text)
pprint(res)
self.assertIn('words', res)
self.assertIn('entities', res)
def test_save_and_load(self):
weights_file = os.path.join(SAVE_ROOT, 'weights.h5')
params_file = os.path.join(SAVE_ROOT, 'params.json')
preprocessor_file = os.path.join(SAVE_ROOT, 'preprocessor.pickle')
model = polygo.Sequence()
model.fit(self.x_train, self.y_train)
model.save(weights_file, params_file, preprocessor_file)
score1 = model.score(self.x_test, self.y_test)
self.assertTrue(weights_file)
self.assertTrue(params_file)
self.assertTrue(preprocessor_file)
model = polygo.Sequence.load(weights_file, params_file,
preprocessor_file)
score2 = model.score(self.x_test, self.y_test)
self.assertEqual(score1, score2)
def test_train_callbacks(self):
weights_file = os.path.join(SAVE_ROOT, 'weights.h5')
params_file = os.path.join(SAVE_ROOT, 'params.json')
preprocessor_file = os.path.join(SAVE_ROOT, 'preprocessor.pickle')
log_dir = os.path.join(os.path.dirname(__file__), 'logs')
file_name = '_'.join(['weights', '{epoch:02d}', '{f1:2.4f}']) + '.h5'
callback = ModelCheckpoint(os.path.join(log_dir, file_name),
monitor='f1',
save_weights_only=True)
vocab = set()
for words in np.r_[self.x_train, self.x_test, self.x_test]:
for word in words:
vocab.add(word)
model = polygo.Sequence(initial_vocab=vocab,
embeddings=self.embeddings)
model.fit(self.x_train,
self.y_train,
self.x_test,
self.y_test,
epochs=100,
callbacks=[callback])
model.save(weights_file, params_file, preprocessor_file)
def test_score(self):
model = polygo.Sequence()
model.fit(self.x_train, self.y_train)
score = model.score(self.x_test, self.y_test)
self.assertIsInstance(score, float)
def test_train_with_pretrained_embedding(self):
model = polygo.Sequence(embeddings=self.embeddings)
model.fit(self.x_train, self.y_train, self.x_test, self.y_test)