# Save the particular model
model_dbow.save("/share/pi/rubin/jiaming/models/{}.model".format(model_name))
model_dbow.delete_temporary_training_data(keep_doctags_vectors=True, keep_inference=True)
elif args.model == 'fasttext':
model_name = "fasttext_v{}_a{}_e{}_t{}_w{}_s{}_ns{}".format(args.size, args.alpha,
args.epochs, args.alg,
args.window, args.sample,
args.ns_exponent)
if model_name + ".model" in trained_models:
print (model_name + "already trained. Passing.")
continue
print("Training model: " + model_name)
model = FastText(min_count=10, negative=5,
size=args.size, sg = args.alg,
alpha=args.alpha, min_alpha=args.alpha,
window=args.window, sample=args.sample,
ns_exponent=args.ns_exponent, workers=10)
model.build_vocab(sentences=[word_tokenize(line.strip()) for line in note_sentences])
for epoch in range(args.epochs):
model.train(sentences=utils.shuffle([x for x in tqdm(note_sentences)]),
total_examples=len(note_sentences), epochs=1)
model.alpha -= 0.002
model.min_alpha = model.alpha
# Save the particular model
model.save("/share/pi/rubin/jiaming/models/{}.model".format(model_name))
