def save_label(train_files, label_file, task=2, firstline=True):
datasets = Tokenizer.load_file(train_files, firstline=firstline, task=task)
# data = []
label_set = set()
for dataset in datasets:
for nl, label in dataset:
# data.append(d)
label_set.update(set(label.split()))
# label_set.update([NULL])
TXT.write(label_set, label_file)
def build_data(args):
if not args.tl:
if not os.path.exists(args.model_dir):
os.mkdir(args.model_dir)
if args.timestamped_subdir:
sub_folder = datetime.now().isoformat(sep='-', timespec='minutes').replace(":", "-").replace("-", "_")
else:
sub_folder = ''
if not os.path.exists(os.path.join(args.model_dir, sub_folder)):
os.mkdir(os.path.join(args.model_dir, sub_folder))
args.model_dir = os.path.join(args.model_dir, sub_folder)
args.log_file = os.path.join(args.model_dir, args.log_file)
if args.tokenize_type != "bpe":
s_paras = [args.wl_th, args.wcutoff]
t_paras = [args.wl_th, args.wcutoff]
print("INFO: - Build vocabulary...")
tokenizer = Tokenizer(s_paras, t_paras)
files = [args.train_file]
if args.train_file != args.dev_file:
files.append(args.dev_file)
# Load datasets to build vocabulary
data = Tokenizer.load_file(files, task=2)
tokenizer.build(datasets=data)
sw2i = tokenizer.sw2i
tw2i = tokenizer.tw2i
print("INFO: - Save vocabulary...")
Tokenizer.save(tokenizer, os.path.join(args.model_dir, "tokenizer.vocab"))
else:
print("INFO: - Load vocabulary...")
tokenizer = BPE.load(args.vocab_file)
tokenizer.add_tokens(sys_tokens)
sw2i = tokenizer.get_vocab()
tw2i = tokenizer.get_vocab()
# args.tokenizer = tokenizer
# Source language
args.swd_pretrained = None
args.twd_pretrained = None
if len(args.swd_embfile) != 0:
scale = np.sqrt(3.0 / args.swd_dim)
emb_reader = Embeddings(args.swd_embfile)
args.swd_pretrained = emb_reader.get_W(args.swd_dim, sw2i, scale)
if args.twd_embfile == args.swd_embfile:
scale = np.sqrt(3.0 / args.twd_dim)
args.twd_pretrained = emb_reader.get_W(args.twd_dim, tw2i, scale)
# Target language
if len(args.twd_embfile) != 0:
scale = np.sqrt(3.0 / args.twd_dim)
if args.twd_pretrained is None:
emb_reader = Embeddings(args.swd_embfile)
args.twd_pretrained = emb_reader.get_W(args.twd_dim, tw2i, scale)
# directly integrate transfer learning if no updating new words
SaveloadHP.save(args, os.path.join(args.model_dir, args.model_args))
return args
else:
print("INFO: - Use transfer learning technique")
assert os.path.exists(args.tlargs), print("\t - There is no pre-trained argument file")
# load pre-trained argument file from a previous training folder
margs = SaveloadHP.load(args.tlargs)
# margs.tl = args.tl
# margs.log_file = args.log_file
# TODO update new vocab and all other new arguments used for new training
# 0. Read vocab
# 1. Update schema
# 2. Update vocab
# args.tokenizer = margs.tokenizer
# 3. Use all model file directory of previous train
args.model_dir = margs.model_dir
args.seq2seq_file = margs.seq2seq_file
# 4. Keep the remaining current arguments
# add a constraint at the loading time that if fail to load any model, just skip it
args.swd_pretrained = margs.swd_pretrained
args.twd_pretrained = margs.twd_pretrained
return args
Data2tensor.set_randseed(12345)
device = torch.device("cpu")
dtype = torch.long
use_cuda = False
filename = "/media/data/classification/datasets/yelp_review_full_csv/train.csv"
label_file = "/media/data/classification/datasets/yelp_review_full_csv/labels.txt"
labels_list = TXT.read(label_file, firstline=False)
lb2id_dict = Tokenizer.list2dict(sys_tokens + labels_list)
id2lb_dict = Tokenizer.reversed_dict(lb2id_dict)
lb2ids = Tokenizer.lst2idx(tokenizer=Tokenizer.process_target, vocab_words=lb2id_dict,
unk_words=False, sos=False, eos=False)
tokenize_type = "bpe"
if tokenize_type != "bpe":
# Load datasets to build vocabulary
data = Tokenizer.load_file([filename], task=1)
s_paras = [-1, 1]
t_paras = [-1, 1]
tokenizer = Tokenizer(s_paras, t_paras)
tokenizer.build(data)
nl2ids = Tokenizer.lst2idx(tokenizer=Tokenizer.process_nl, vocab_words=tokenizer.sw2i,
unk_words=True, sos=False, eos=False)
tokenizer.tw2i = lb2id_dict
tokenizer.i2tw = id2lb_dict
tg2ids = Tokenizer.lst2idx(tokenizer=Tokenizer.process_target, vocab_words=tokenizer.tw2i,
unk_words=False, sos=False, eos=False)
pad_id = tokenizer.sw2i.get(PAD, 0)
sw_size = len(tokenizer.sw2i)
tw_size = len(tokenizer.tw2i)
collate_fn = Tokenizer.collate_fn(pad_id, True)
else: