def test_train(self):
model_config = ModelConfig()
training_config = TrainingConfig()
train_path = os.path.join(DATA_ROOT, 'train.txt')
valid_path = os.path.join(DATA_ROOT, 'valid.txt')
x_train, y_train = load_data_and_labels(train_path)
x_valid, y_valid = load_data_and_labels(valid_path)
p = prepare_preprocessor(x_train, y_train)
p.save(os.path.join(SAVE_ROOT, 'preprocessor.pkl'))
embeddings = load_word_embeddings(p.vocab_word, EMBEDDING_PATH,
model_config.word_embedding_size)
model_config.char_vocab_size = len(p.vocab_char)
model = SeqLabeling(model_config, embeddings, len(p.vocab_tag))
trainer = anago.Trainer(model,
training_config,
checkpoint_path=LOG_ROOT,
save_path=SAVE_ROOT,
preprocessor=p,
embeddings=embeddings)
trainer.train(x_train, y_train, x_valid, y_valid)
model.save(os.path.join(SAVE_ROOT, 'model_weights.h5'))
def test_train(self):
DATA_ROOT = os.path.join(os.path.dirname(__file__),
'../data/conll2003/en/tagging')
SAVE_ROOT = os.path.join(os.path.dirname(__file__),
'../models') # trained model
LOG_ROOT = os.path.join(os.path.dirname(__file__),
'../logs') # checkpoint, tensorboard
embedding_path = os.path.join(os.path.dirname(__file__),
'../data/glove.6B/glove.6B.100d.txt')
model_config = ModelConfig()
training_config = TrainingConfig()
train_path = os.path.join(DATA_ROOT, 'train.txt')
valid_path = os.path.join(DATA_ROOT, 'valid.txt')
test_path = os.path.join(DATA_ROOT, 'test.txt')
x_train, y_train = load_data_and_labels(train_path)
x_valid, y_valid = load_data_and_labels(valid_path)
x_test, y_test = load_data_and_labels(test_path)
p = prepare_preprocessor(np.r_[x_train, x_valid, x_test],
y_train) # np.r_ is for vocabulary expansion.
p.save(os.path.join(SAVE_ROOT, 'preprocessor.pkl'))
embeddings = load_word_embeddings(p.vocab_word, embedding_path,
model_config.word_embedding_size)
model_config.char_vocab_size = len(p.vocab_char)
trainer = anago.Trainer(model_config,
training_config,
checkpoint_path=LOG_ROOT,
save_path=SAVE_ROOT,
preprocessor=p,
embeddings=embeddings)
trainer.train(x_train, y_train, x_test, y_test)
def test_predict(self):
X, y = load_data_and_labels(self.filename)
X, y = X[:100], y[:100]
p = prepare_preprocessor(X, y)
self.model_config.char_vocab_size = len(p.vocab_char)
model = SeqLabeling(self.model_config, self.embeddings, ntags=len(p.vocab_tag))
model.predict(p.transform(X))
def test_batch_iter(self):
sents, labels = load_data_and_labels(self.filename)
batch_size = 32
p = prepare_preprocessor(sents, labels)
steps, batches = batch_iter(list(zip(sents, labels)), batch_size, preprocessor=p)
self.assertEqual(len([_ for _ in batches]), steps) # Todo: infinite loop