Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
print("Training complete")
elif option == 1:
print("Training a Gensim FastText model")
model = FastText(sentences=sentences, size = embed_dim, workers = workers, window = window)
print("Training complete")
elif option == 2:
print("Training a Fasttext model from Facebook Research")
y_train = ["__label__positive" if i==1 else "__label__negative" for i in y_train]
with open("imdb_train.txt","w") as text_file:
for i in range(len(sentences)):
print(sentences[i],y_train[i],file = text_file)
model = fasttext.skipgram("imdb_train.txt","model_ft_2018_imdb",dim = embed_dim)
print("Training complete")
return model
"""
if model_filename is None:
if model_type == 'skipgram':
model_filename = FAST_TEXT_SKIPGRAM_MODEL_FILENAME
elif model_type == 'cbow':
model_filename = FAST_TEXT_CBOW_MODEL_FILENAME
full_model_filename = self.full_filename(model_filename)
full_input_filename = self.full_filename(input_filename)
if model_type == 'skipgram':
self.logger.info(
'Training fasttext skipgram model on {} to {}'.format(
full_input_filename, full_model_filename))
self.model = fasttext.skipgram(
full_input_filename, full_model_filename)
elif model_type == 'cbow':
self.logger.info(
'Training fasttext cbow model on {} to {}'.format(
full_input_filename, full_model_filename))
self.model = fasttext.cbow(
full_input_filename, full_model_filename)
else:
raise ValueError('Wrong argument to model_type')
# Invalidate computed normalized matrix
self._normalized_matrix = None
def train(self):
# silent设为False, 训练过程会打印日志信息
return fasttext.skipgram(self.train_file, self.model_path, silent=False)
def train(inp = "wiki.he.text",out_model = "wiki.he.fasttext.model",
alg = "CBOW"):
start = time.time()
if alg == "skipgram":
# Skipgram model
model = fasttext.skipgram(inp, out_model)
print(model.words) # list of words in dictionary
else:
# CBOW model
model = fasttext.cbow(inp, out_model)
print(model.words) # list of words in dictionary
print(time.time()-start)
model.save(out_model)