def load_penn(path,
batch_size,
max_size=1000000,
min_freq=1,
gpu=False,
shuffle=True):
train_data = load_lines(os.path.join(path, 'train.txt'))
valid_data = load_lines(os.path.join(path, 'valid.txt'))
test_data = load_lines(os.path.join(path, 'test.txt'))
d = Dict(pad_token=u.PAD,
eos_token=u.EOS,
bos_token=u.BOS,
max_size=max_size,
min_freq=min_freq)
d.fit(train_data, valid_data)
train = PairedDataset(train_data, None, {'src': d}, batch_size, gpu=gpu)
valid = PairedDataset(valid_data,
None, {'src': d},
batch_size,
gpu=gpu,
evaluation=True)
test = PairedDataset(test_data,
None, {'src': d},
batch_size,
gpu=gpu,
evaluation=True)
return train.sort_(), valid.sort_(), test.sort_()
def load_dataset(src,
trg,
batch_size,
max_size=100000,
min_freq=5,
gpu=False,
shuffle=True,
sort_key=default_sort_key,
**kwargs):
"""
Wrapper function for dataset with sensible, overwritable defaults
"""
tweets_dict = Dict(pad_token='<pad>',
eos_token='<eos>',
bos_token='<bos>',
max_size=max_size,
min_freq=min_freq)
labels_dict = Dict(sequential=False, force_unk=False)
tweets_dict.fit(src)
labels_dict.fit(trg)
d = {'src': tweets_dict, 'trg': labels_dict}
splits = PairedDataset(src, trg, d, batch_size,
gpu=gpu).splits(shuffle=shuffle,
sort_key=sort_key,
**kwargs)
return splits
def load_penn(path, batch_size,
max_size=1000000, min_freq=1, gpu=False, shuffle=True,
sort_key=lambda pair: len(pair[0])):
train_data = load_lines(os.path.join(path, 'train.txt'))
train_labels = make_mock_labels(train_data)
valid_data = load_lines(os.path.join(path, 'valid.txt'))
valid_labels = make_mock_labels(valid_data)
test_data = load_lines(os.path.join(path, 'test.txt'))
test_labels = make_mock_labels(test_data)
ldict = Dict(pad_token=u.PAD, eos_token=u.EOS, bos_token=u.BOS,
max_size=max_size, min_freq=min_freq)
ldict.fit(train_data, valid_data)
mock = Dict().fit(train_labels)
d = {'src': ldict, 'trg': mock}
train = PairedDataset(train_data, train_labels, d, batch_size, gpu=gpu
).sort_(sort_key=sort_key)
valid = PairedDataset(valid_data, valid_labels, d, batch_size, gpu=gpu,
evaluation=True).sort_(sort_key=sort_key)
test = PairedDataset(test_data, test_labels, d, batch_size, gpu=gpu,
evaluation=True).sort_(sort_key=sort_key)
return train, valid, test
def load_from_lines(
path, batch_size, max_size=1000000, min_freq=5, gpu=False,
shuffle=True, sort_key=lambda x: len(x[0]), **kwargs):
lines = load_lines(path)
ldict = Dict(pad_token=u.PAD, eos_token=u.EOS, bos_token=u.BOS,
max_size=max_size, min_freq=min_freq)
ldict.fit(lines)
mock_labels = make_mock_labels(train)
mock = Dict()
mock.fit(mock_labels)
d = {'src': ldict, 'trg': mock}
splits = PairedDataset(lines, mock_labels, d, batch_size, gpu=gpu).splits(
shuffle=shuffle, sort_key=sort_key, **kwargs)
return splits
def load_split_data(path, batch_size, max_size, min_freq, max_len, device, processor):
"""
Load corpus that is already splitted in 'train.txt', 'valid.txt', 'test.txt'
"""
train = load_lines(os.path.join(path, 'train.txt'), max_len, processor)
valid = load_lines(os.path.join(path, 'valid.txt'), max_len, processor)
d = Dict(
pad_token=u.PAD, eos_token=u.EOS, bos_token=u.BOS,
max_size=max_size, min_freq=min_freq, force_unk=True
).fit(train, valid)
train = load_lines(os.path.join(path, 'train.txt'), max_len, processor)
valid = load_lines(os.path.join(path, 'valid.txt'), max_len, processor)
test = load_lines(os.path.join(path, 'test.txt'), max_len, processor)
train = PairedDataset(train, None, {'src': d}, batch_size, device=device)
valid = PairedDataset(valid, None, {'src': d}, batch_size, device=device)
test = PairedDataset(test, None, {'src': d}, batch_size, device=device)
return train.sort_(), valid.sort_(), test.sort_()
def load_from_lines(path,
batch_size,
max_size=1000000,
min_freq=5,
gpu=False,
shuffle=True,
**kwargs):
lines = load_lines(path)
ldict = Dict(pad_token=u.PAD,
eos_token=u.EOS,
bos_token=u.BOS,
max_size=max_size,
min_freq=min_freq).fit(lines)
return PairedDataset(lines, None, {
'src': ldict
}, batch_size, gpu=gpu).splits(shuffle=shuffle, **kwargs)
def shingle_dataset(args, vocab_dict=None, focus_size=None, right_size=None):
if focus_size:
args.focus_size = focus_size
if right_size:
args.right_size = right_size
# load the data:
if args.task == 'sentences':
dataset = list(
SentenceCouples(args.input,
max_items=args.max_items,
tokenize=args.tokenize,
level=args.level))
print(f'* loaded {len(dataset)} sentences')
elif args.task == 'snippets':
dataset = list(
SnippetCouples(args.input,
focus_size=args.focus_size,
right_size=args.right_size,
max_items=args.max_items))
print(f'* loaded {len(dataset)} snippets')
else:
raise ValueError("`Task` should be one of ('sentences', 'snippets')")
# random shuffle:
if args.shuffle:
print('* shuffling batches...')
random.seed(args.rnd_seed)
random.shuffle(dataset)
for c in dataset[:10]:
print('\t'.join(' '.join(s[:10]) for s in c))
if vocab_dict is None:
vocab_dict = Dict(pad_token=u.PAD,
bos_token=u.BOS,
eos_token=u.EOS,
min_freq=args.min_item_freq,
sequential=True,
force_unk=True,
max_size=args.max_vocab_size)
focus, right = zip(*dataset)
del dataset
if not vocab_dict.fitted:
vocab_dict.fit(
focus, right
) # sometimes inefficient? # do a partial fit in the triple store?
train, valid = PairedDataset(src=(focus, ),
trg=(right, ),
d={
'src': (vocab_dict, ),
'trg': (vocab_dict, )
},
batch_size=args.batch_size,
gpu=args.gpu,
align_right=args.reverse,
fitted=False).splits(sort_by='src',
dev=args.dev,
test=None,
sort=True)
return train, valid, vocab_dict
else:
train, test, valid = load_from_lines(args.source_path,
args.batch_size,
min_freq=args.min_freq,
max_size=args.max_size,
gpu=args.gpu,
dev=args.dev,
test=args.text)
# save
if args.cache_data:
train.to_disk('data/%s_train.pt' % prefix)
test.to_disk('data/%s_test.pt' % prefix)
valid.to_disk('data/%s_valid.pt' % prefix)
# load from file
else:
train = PairedDataset.from_disk('data/%s_train.pt' % prefix)
test = PairedDataset.from_disk('data/%s_test.pt' % prefix)
valid = PairedDataset.from_disk('data/%s_valid.pt' % prefix)
train.set_gpu(args.gpu)
test.set_gpu(args.gpu)
valid.set_gpu(args.gpu)
train.set_batch_size(args.batch_size)
test.set_batch_size(args.batch_size)
valid.set_batch_size(args.batch_size)
print("* Number of train batches %d" % len(train))
print("Building model...")
model = SequenceVAE(args.emb_dim,
args.hid_dim,
args.z_dim,
parser.add_argument('--word_dropout', default=0.0, type=float)
parser.add_argument('--learning_rate_decay', default=0.5, type=float)
parser.add_argument('--start_decay_at', default=8, type=int)
parser.add_argument('--max_grad_norm', default=5., type=float)
parser.add_argument('--gpu', action='store_true')
parser.add_argument('--beam', action='store_true')
args = parser.parse_args()
vocab = args.vocab
size = args.train_len
batch_size = args.batch_size
sample_fn = getattr(d, args.sample_fn)
if args.path != '':
with open(args.path, 'rb+') as f:
dataset = PairedDataset.from_disk(f)
dataset.set_batch_size(args.batch_size)
dataset.set_gpu(args.gpu)
train, valid = dataset.splits(sort_by='src', dev=args.dev, test=None)
src_dict = dataset.dicts['src']
else:
src, trg = zip(*d.generate_set(size, vocab, args.min_len, args.max_len,
sample_fn))
src, trg = list(map(list, src)), list(map(list, trg))
src_dict = Dict(pad_token=u.PAD, eos_token=u.EOS, bos_token=u.BOS)
src_dict.fit(src, trg)
train, valid = PairedDataset(src,
trg, {
'src': src_dict,
'trg': src_dict
},
parser.add_argument('--pretrained', type=str, default='empty')
# Logging
parser.add_argument('--gen_src', default=None)
parser.add_argument('--gen_tgt', default=None)
parser.add_argument('--csv', type=str, default='empty')
parser.add_argument('--logging', action='store_true')
parser.add_argument('--visdom', action='store_true')
args = parser.parse_args()
src, trg = load_data(args.path, ('.answers', '.questions'))
src_dict = Dict(pad_token=u.PAD, eos_token=u.EOS, bos_token=u.BOS,
max_size=args.max_size, min_freq=args.min_freq)
src_dict.fit(src, trg)
train, valid = PairedDataset(
src, trg, {'src': src_dict, 'trg': src_dict},
batch_size=args.batch_size, gpu=args.gpu
).splits(dev=args.dev, test=None, sort_key=lambda pair: len(pair[0]))
print(' * vocabulary size. %d' % len(src_dict))
print(' * number of train batches. %d' % len(train))
print(' * maximum batch size. %d' % args.batch_size)
print('Building model...')
model = EncoderDecoder(
# removed (args.hid_dim, args.hid_dim) added args.hid_dim
(args.layers, args.layers), args.emb_dim, args.hid_dim,
args.att_dim, src_dict, att_type=args.att_type, dropout=args.dropout,
bidi=args.bidi, cell=args.cell)
# Load Glove Pretrained Embeddings
parser.add_argument('--word_dropout', default=0.0, type=float)
parser.add_argument('--learning_rate_decay', default=0.5, type=float)
parser.add_argument('--start_decay_at', default=8, type=int)
parser.add_argument('--max_grad_norm', default=5., type=float)
parser.add_argument('--gpu', action='store_true')
parser.add_argument('--beam', action='store_true')
args = parser.parse_args()
vocab = args.vocab
size = args.train_len
batch_size = args.batch_size
sample_fn = getattr(d, args.sample_fn)
if args.path != '':
with open(args.path, 'rb+') as f:
dataset = PairedDataset.from_disk(f)
dataset.set_batch_size(args.batch_size)
dataset.set_gpu(args.gpu)
train, valid = dataset.splits(sort_by='src', dev=args.dev, test=None)
src_dict = dataset.dicts['src']
else:
src, trg = zip(*d.generate_set(
size, vocab, args.min_len, args.max_len, sample_fn))
src, trg = list(map(list, src)), list(map(list, trg))
src_dict = Dict(pad_token=u.PAD, eos_token=u.EOS, bos_token=u.BOS)
src_dict.fit(src, trg)
train, valid = PairedDataset(
src, trg, {'src': src_dict, 'trg': src_dict},
batch_size=args.batch_size, gpu=args.gpu
).splits(dev=args.dev, test=None, sort_by='src')
gpu=args.gpu, dev=args.dev, test=args.test)
elif args.source == 'penn':
train, test, valid = load_penn(
"~/corpora/penn", args.batch_size,
min_freq=args.min_freq, max_size=args.max_size, gpu=args.gpu)
else:
train, test, valid = load_from_lines(
args.source_path, args.batch_size,
min_freq=args.min_freq, max_size=args.max_size,
gpu=args.gpu, dev=args.dev, test=args.text)
if args.cache_data:
train.to_disk('data/%s_train.pt' % prefix)
test.to_disk('data/%s_test.pt' % prefix)
valid.to_disk('data/%s_valid.pt' % prefix)
else:
train = PairedDataset.from_disk('data/%s_train.pt' % prefix)
test = PairedDataset.from_disk('data/%s_test.pt' % prefix)
valid = PairedDataset.from_disk('data/%s_valid.pt' % prefix)
train.set_gpu(args.gpu), test.set_gpu(args.gpu), valid.set_gpu(args.gpu)
train.set_batch_size(args.batch_size), test.set_batch_size(args.batch_size)
valid.set_batch_size(args.batch_size)
datasets = {'train': train, 'valid': valid, 'test': test}
vocab = len(train.d['src'].vocab)
print("* Number of train batches %d" % len(train))
print("Building model...")
hid_dim = args.hid_dim if args.dec_hid_dim == 0 else (args.hid_dim, args.dec_hid_dim)
layers = args.layers if args.dec_layers == 0 else (args.layers, args.dec_layers)
model = SequenceVAE(
args.emb_dim, hid_dim, args.z_dim, train.d['src'],
num_layers=layers, cell=args.cell, bidi=not args.non_bidi,
for target in args.targets:
sample_fn = wrap_autoencode(getattr(d, target))
src, trg = zip(*d.generate_set(
args.train_len, args.vocab, args.min_len, args.max_len, sample_fn))
src, trg = list(map(list, src)), list(map(list, trg))
datasets[target] = {'src': src, 'trg': trg}
src_dict = Dict(pad_token=u.PAD, eos_token=u.EOS, bos_token=u.BOS)
src_dict.fit(*[data
for target in datasets
for data in datasets[target].values()])
for target in datasets:
train, valid = PairedDataset(
datasets[target]['src'], datasets[target]['trg'],
{'src': src_dict, 'trg': src_dict},
batch_size=args.batch_size, gpu=args.gpu).splits(
dev=args.dev, test=None,
shuffle=True, sort_key=lambda pair: len(pair[0]))
del datasets[target]
src, trg = zip(*d.generate_set(
int(args.train_len * 0.1), args.vocab, args.min_len, args.max_len,
getattr(d, target)))
src, trg = list(map(list, src)), list(map(list, trg))
test = PairedDataset(src, trg, {'src': src_dict, 'trg': src_dict},
batch_size=args.batch_size, gpu=args.gpu)
datasets[target] = {'train': train, 'valid': valid, 'test': test}
print('Building model...')
model = ForkableMultiTarget(
(args.layers, args.layers), args.emb_dim, (args.hid_dim, args.hid_dim),
args.att_dim, src_dict, att_type=args.att_type, dropout=args.dropout,