def refill(batches, fdx, fdy, batch_size, FLAGS, sort_and_shuffle=True):
line_pairs = []
linex = fdx.readline()
# linex, liney = fdx.readline(), fdy.readline()
while linex:
y_tokens = tokenize(linex) # y_tokens are source of truth
orig_str = "".join(reverse_vocab[x] for x in y_tokens)
noisy_str = add_noise_to_string(orig_str, 0.2 / FLAGS['max_seq_len'],
FLAGS['max_seq_len'])
x_tokens = nlc_data.sentence_to_token_ids(
noisy_str, vocab,
tokenizer=get_tokenizer(FLAGS)) # x_tokens are noisy str
if len(x_tokens) < FLAGS['max_seq_len'] and len(
y_tokens) < FLAGS['max_seq_len']:
line_pairs.append((x_tokens, y_tokens))
if len(line_pairs) == batch_size * 16:
break
linex = fdx.readline()
# linex, liney = fdx.readline(), fdy.readline()
if sort_and_shuffle:
line_pairs = sorted(line_pairs, key=lambda e: len(e[0]))
for batch_start in range(0, len(line_pairs), batch_size):
x_batch, y_batch = zip(*line_pairs[batch_start:batch_start +
batch_size])
# if len(x_batch) < batch_size:
# break
batches.append((x_batch, y_batch))
if sort_and_shuffle:
random.shuffle(batches)
return
def tokenize(sent, vocab, depth=FLAGS.num_layers):
align = pow(2, depth - 1)
token_ids = nlc_data.sentence_to_token_ids(sent, vocab, get_tokenizer(FLAGS))
ones = [1] * len(token_ids)
pad = (align - len(token_ids)) % align
token_ids += [nlc_data.PAD_ID] * pad
ones += [0] * pad
source = np.array(token_ids).reshape([-1, 1])
mask = np.array(ones).reshape([-1, 1])
return source, mask
def tokenize(sent, vocab, depth=FLAGS.num_layers): align = pow(2, depth - 1) token_ids = nlc_data.sentence_to_token_ids(sent, vocab, get_tokenizer(FLAGS)) ones = [1] * len(token_ids) pad = (align - len(token_ids)) % align token_ids += [nlc_data.PAD_ID] * pad ones += [0] * pad source = np.array(token_ids).reshape([-1, 1]) mask = np.array(ones).reshape([-1, 1]) return source, mask
