def main():
path_pfx = ''
max_len = 37
dm = DataManager()
dm.add_data('test', os.path.join(sys.argv[1]), False, True)
print(len(dm.data['test'][0]))
dm.preprocessing()
dm.load_word2vec(os.path.join(path_pfx, 'model/word2vec'))
#dm.load_tokenizer(os.path.join(path_pfx, 'token.pkl'))
dm.to_sequence(max_len, use_pretrain=True)
result = predict(dm.data['test'][0], path_pfx)
write(sys.argv[2], result)
print('finished')
def main():
voc_size = None
max_len = 39
path_pfx = ''
dm = DataManager()
dm.add_data('train', sys.argv[1])
#dm.add_data('semi', os.path.join(path_pfx, 'training_nolabel.txt'), False)
#dm.add_data('test', os.path.join(path_pfx, 'testing_data.txt'), False, True)
dm.preprocessing()
dm.load_word2vec(os.path.join(path_pfx, 'model/word2vec'))
#dm.load_embedding_matrix(os.path.join(path_pfx, 'word2vec.wv.vectors.npy'))
dm.to_sequence(max_len, use_pretrain=True)
#dm.to_bow()
print(max_len)
#emb_mat = dm.get_embedding_matrix()
emb_mat = None
train(dm, voc_size=voc_size, max_len=max_len, emb_mat=emb_mat)