def main():
args = set_args()
global logger
start_time = time.time()
logger = create_logger(__name__, to_disk=True,
log_file=args.log_file) # ./san.log
v2_on = args.v2_on
version = 'v1'
if v2_on:
msg = '~Processing SQuAD v2.0 dataset~'
train_path = 'train-v2.0.json'
dev_path = 'dev-v2.0.json'
version = 'v2'
else:
msg = '~Processing SQuAD dataset~'
train_path = 'train-v1.1.json'
dev_path = 'dev-v1.1.json'
logger.warning(msg)
if DEBUG_ON:
logger.error('***DEBUGING MODE***')
train_path = os.path.join(
args.data_dir, train_path) # args.data_dir=data/, data/train-v2.0.json
valid_path = os.path.join(args.data_dir, dev_path) # data/dev-v2.0.json
logger.info('The path of training data: {}'.format(train_path))
logger.info('The path of validation data: {}'.format(valid_path))
logger.info('{}-dim word vector path: {}'.format(
args.embedding_dim, args.glove)) # embedding_dim=300
# could be fasttext embedding
emb_path = args.glove # data/glove.840B.300d.txt
embedding_dim = args.embedding_dim
set_environment(args.seed)
if args.fasttext_on: # store_true
logger.info('Loading fasttext vocab.')
else:
logger.info('Loading glove vocab.')
# load data
train_data = load_data(train_path, v2_on=v2_on)
dev_data = load_data(valid_path, False, v2_on=v2_on)
"""From GLoVe to acquire tokens, to set()"""
wemb_vocab = load_emb_vocab(emb_path,
embedding_dim,
fast_vec_format=args.fasttext_on)
logger.info('Build vocabulary')
"""
'--sort_all', action='store_true',
sort the vocabulary by frequencies of all words, Otherwise consider question words first.
"""
vocab, _, _ = build_vocab(train_data + dev_data,
wemb_vocab,
sort_all=args.sort_all,
clean_on=True,
cl_on=False)
logger.info('Done with vocabulary collection')
# loading ner/pos tagging vocab
resource_path = 'resource'
logger.info('Loading resource')
with open(os.path.join(resource_path, 'vocab_tag.pick'), 'rb') as f:
vocab_tag = pickle.load(f)
with open(os.path.join(resource_path, 'vocab_ner.pick'), 'rb') as f:
vocab_ner = pickle.load(f)
meta_path = gen_name(args.data_dir, args.meta, version, suffix='pick')
logger.info('building embedding')
embedding = build_embedding(emb_path,
vocab,
embedding_dim,
fast_vec_format=args.fasttext_on)
meta = {
'vocab': vocab,
'vocab_tag': vocab_tag,
'vocab_ner': vocab_ner,
'embedding': embedding
}
with open(meta_path, 'wb') as f:
pickle.dump(meta, f)
logger.info('building training data')
train_fout = gen_name(args.data_dir, args.train_data, version)
build_data(train_data,
vocab,
vocab_tag,
vocab_ner,
train_fout,
True,
NLP=NLP,
v2_on=v2_on)
logger.info('building dev data')
dev_fout = gen_name(args.data_dir, args.dev_data, version)
build_data(dev_data,
vocab,
vocab_tag,
vocab_ner,
dev_fout,
False,
NLP=NLP,
v2_on=v2_on)
end_time = time.time()
logger.warning('It totally took {} minutes to processe the data!!'.format(
(end_time - start_time) / 60.))
def main():
args = set_args()
global logger
start_time = time.time()
logger = create_logger(__name__, to_disk=True, log_file=args.log_file)
v2_on = args.v2_on
version = 'v1'
if v2_on:
msg = '~Processing SQuAD v2.0 dataset~'
# train_path = 'train-v2.0.json'
# dev_path = 'dev-v2.0.json'
train_path = 'msmarco_squad_train.json'
dev_path = 'msmarco_squad_dev.json'
version = 'v2'
else:
msg = '~Processing SQuAD dataset~'
train_path = 'train-v1.1.json'
dev_path = 'dev-v1.1.json'
logger.warning(msg)
if DEBUG_ON:
logger.error('***DEBUGING MODE***')
train_path = os.path.join(args.data_dir, train_path)
valid_path = os.path.join(args.data_dir, dev_path)
logger.info('Train path is: {}'.format(train_path))
logger.info('The path of training data: {}'.format(train_path))
logger.info('The path of validation data: {}'.format(valid_path))
logger.info('{}-dim word vector path: {}'.format(args.embedding_dim,
args.glove))
# could be fasttext embedding
emb_path = args.glove
embedding_dim = args.embedding_dim
set_environment(args.seed)
if args.fasttext_on:
logger.info('Loading fasttext vocab.')
else:
logger.info('Loading glove vocab.')
# load data
train_data = load_data(train_path, v2_on=v2_on, limit=20000)
dev_data = load_data(valid_path, False, v2_on=v2_on, limit=500)
wemb_vocab = load_emb_vocab(emb_path,
embedding_dim,
fast_vec_format=args.fasttext_on)
logger.info('Build vocabulary')
vocab, _, _ = build_vocab(train_data + dev_data,
wemb_vocab,
sort_all=args.sort_all,
clean_on=True,
cl_on=False)
logger.info('Done with vocabulary collection')
# loading ner/pos tagging vocab
resource_path = 'resource'
logger.info('Loading resource')
with open(os.path.join(resource_path, 'vocab_tag.pick'), 'rb') as f:
vocab_tag = pickle.load(f)
with open(os.path.join(resource_path, 'vocab_ner.pick'), 'rb') as f:
vocab_ner = pickle.load(f)
meta_path = gen_name(args.data_dir, args.meta, version, suffix='pick')
logger.info('building embedding')
embedding = build_embedding(emb_path,
vocab,
embedding_dim,
fast_vec_format=args.fasttext_on)
meta = {
'vocab': vocab,
'vocab_tag': vocab_tag,
'vocab_ner': vocab_ner,
'embedding': embedding
}
with open(meta_path, 'wb') as f:
pickle.dump(meta, f)
del meta
del embedding
logger.info('deleted meta and embedding')
logger.info('building training data')
train_fout = gen_name(args.data_dir, args.train_data, version)
build_data(train_data,
vocab,
vocab_tag,
vocab_ner,
train_fout,
True,
NLP=NLP,
v2_on=v2_on)
logger.info('building dev data')
dev_fout = gen_name(args.data_dir, args.dev_data, version)
build_data(dev_data,
vocab,
vocab_tag,
vocab_ner,
dev_fout,
False,
NLP=NLP,
v2_on=v2_on)
end_time = time.time()
logger.warning('It totally took {} minutes to processe the data!!'.format(
(end_time - start_time) / 60.))
def main():
# Create a argument parser and read arguments from command line
args = set_args()
# logger will be a global variable
global logger
start_time = time.time()
logger = create_logger(__name__, to_disk=True, log_file=args.log_file)
v2_on = args.v2_on
if v2_on:
msg = '~Processing SQuAD v2.0 dataset~'
train_path = 'train-v2.0.json'
dev_path = 'dev-v2.0.json'
version = 'v2'
else:
msg = '~Processing SQuAD v1.1 dataset~'
train_path = 'train-v1.1.json'
dev_path = 'dev-v1.1.json'
version = 'v1'
logger.warning(msg)
if DEBUG_ON:
logger.error('***DEBUGGING MODE***')
train_path = os.path.join(args.data_dir, train_path)
valid_path = os.path.join(args.data_dir, dev_path)
logger.info('The path of training data: {}'.format(train_path))
logger.info('The path of validation data: {}'.format(valid_path))
logger.info('{}-dim word vector path: {}'.format(args.embedding_dim, args.glove))
# could be fasttext embedding
emb_path = args.glove
embedding_dim = args.embedding_dim
set_environment(args.seed)
if args.fasttext_on:
logger.info('Loading fasttext vocab.')
else:
logger.info('Loading glove vocab.')
# load data
train_data = load_data(train_path, v2_on=v2_on)
dev_data = load_data(valid_path, False, v2_on=v2_on)
wemb_vocab = load_emb_vocab(emb_path, embedding_dim, fast_vec_format=args.fasttext_on)
logger.info('Build vocabulary')
vocab, _, _ = build_vocab(train_data + dev_data, wemb_vocab, sort_all=args.sort_all, clean_on=True, cl_on=False)
logger.info('Done with vocabulary collection')
# loading ner/pos tagging vocab
resource_path = 'resource'
logger.info('Loading resource')
# what do these vocab tags and vocab ners do?
with open(os.path.join(resource_path, 'vocab_tag.pick'), 'rb') as f:
vocab_tag = pickle.load(f)
with open(os.path.join(resource_path, 'vocab_ner.pick'), 'rb') as f:
vocab_ner = pickle.load(f)
meta_path = gen_name(args.data_dir, args.meta, version, suffix='pick')
logger.info('building embedding')
embedding = build_embedding(emb_path, vocab, embedding_dim, fast_vec_format=args.fasttext_on)
meta = {'vocab': vocab, 'vocab_tag': vocab_tag, 'vocab_ner': vocab_ner, 'embedding': embedding}
with open(meta_path, 'wb') as f:
pickle.dump(meta, f)
logger.info('building training data')
train_fout = gen_name(args.data_dir, args.train_data, version)
build_data(train_data, vocab, vocab_tag, vocab_ner, train_fout, True, NLP=NLP, v2_on=v2_on,
bert_tokenizer=BERT_TOKENIZER)
logger.info('building dev data')
dev_fout = gen_name(args.data_dir, args.dev_data, version)
build_data(dev_data, vocab, vocab_tag, vocab_ner, dev_fout, False, NLP=NLP, v2_on=v2_on,
bert_tokenizer=BERT_TOKENIZER)
end_time = time.time()
logger.warning('It totally took {} minutes to process the data!!'.format((end_time - start_time) / 60.))