def read_data(source_path: str, word_alphabet: Alphabet, char_alphabet: Alphabet,
pos_alphabet: Alphabet, chunk_alphabet: Alphabet, ner_alphabet: Alphabet,
max_size=None, normalize_digits=True):
data = []
max_length = 0
max_char_length = 0
print('Reading data from %s' % source_path)
counter = 0
reader = CoNLL03Reader(source_path, word_alphabet, char_alphabet, pos_alphabet, chunk_alphabet, ner_alphabet)
inst = reader.getNext(normalize_digits)
while inst is not None and (not max_size or counter < max_size):
counter += 1
if counter % 10000 == 0:
print("reading data: %d" % counter)
sent = inst.sentence
data.append([sent.word_ids, sent.char_id_seqs, inst.pos_ids, inst.chunk_ids, inst.ner_ids])
max_len = max([len(char_seq) for char_seq in sent.char_seqs])
if max_char_length < max_len:
max_char_length = max_len
if max_length < inst.length():
max_length = inst.length()
inst = reader.getNext(normalize_digits)
reader.close()
print("Total number of data: %d" % counter)
data_size = len(data)
char_length = min(MAX_CHAR_LENGTH, max_char_length)
wid_inputs = np.empty([data_size, max_length], dtype=np.int64)
cid_inputs = np.empty([data_size, max_length, char_length], dtype=np.int64)
pid_inputs = np.empty([data_size, max_length], dtype=np.int64)
chid_inputs = np.empty([data_size, max_length], dtype=np.int64)
nid_inputs = np.empty([data_size, max_length], dtype=np.int64)
masks = np.zeros([data_size, max_length], dtype=np.float32)
single = np.zeros([data_size, max_length], dtype=np.int64)
lengths = np.empty(data_size, dtype=np.int64)
for i, inst in enumerate(data):
wids, cid_seqs, pids, chids, nids = inst
inst_size = len(wids)
lengths[i] = inst_size
# word ids
wid_inputs[i, :inst_size] = wids
wid_inputs[i, inst_size:] = PAD_ID_WORD
for c, cids in enumerate(cid_seqs):
cid_inputs[i, c, :len(cids)] = cids
cid_inputs[i, c, len(cids):] = PAD_ID_CHAR
cid_inputs[i, inst_size:, :] = PAD_ID_CHAR
# pos ids
pid_inputs[i, :inst_size] = pids
pid_inputs[i, inst_size:] = PAD_ID_TAG
# chunk ids
chid_inputs[i, :inst_size] = chids
chid_inputs[i, inst_size:] = PAD_ID_TAG
# ner ids
nid_inputs[i, :inst_size] = nids
nid_inputs[i, inst_size:] = PAD_ID_TAG
# masks
masks[i, :inst_size] = 1.0
for j, wid in enumerate(wids):
if word_alphabet.is_singleton(wid):
single[i, j] = 1
words = torch.from_numpy(wid_inputs)
chars = torch.from_numpy(cid_inputs)
pos = torch.from_numpy(pid_inputs)
chunks = torch.from_numpy(chid_inputs)
ners = torch.from_numpy(nid_inputs)
masks = torch.from_numpy(masks)
single = torch.from_numpy(single)
lengths = torch.from_numpy(lengths)
data_tensor = {'WORD': words, 'CHAR': chars, 'POS': pos, 'CHUNK': chunks,
'NER': ners, 'MASK': masks, 'SINGLE': single, 'LENGTH': lengths}
return data_tensor, data_size
def read_bucketed_data(source_path: str,
word_alphabet: Alphabet,
char_alphabet: Alphabet,
pos_alphabet: Alphabet,
type_alphabet: Alphabet,
max_size=None,
normalize_digits=True,
symbolic_root=False,
symbolic_end=False):
data = [[] for _ in _buckets]
max_char_length = [0 for _ in _buckets]
print('Reading data from %s' % source_path)
counter = 0
reader = CoNLLXReader(source_path, word_alphabet, char_alphabet,
pos_alphabet, type_alphabet)
inst = reader.getNext(normalize_digits=normalize_digits,
symbolic_root=symbolic_root,
symbolic_end=symbolic_end)
while inst is not None and (not max_size or counter < max_size):
counter += 1
if counter % 10000 == 0:
print("reading data: %d" % counter)
inst_size = inst.length()
sent = inst.sentence
for bucket_id, bucket_size in enumerate(_buckets):
if inst_size < bucket_size:
data[bucket_id].append([
sent.word_ids, sent.char_id_seqs, inst.pos_ids, inst.heads,
inst.type_ids
])
max_len = max([len(char_seq) for char_seq in sent.char_seqs])
if max_char_length[bucket_id] < max_len:
max_char_length[bucket_id] = max_len
break
inst = reader.getNext(normalize_digits=normalize_digits,
symbolic_root=symbolic_root,
symbolic_end=symbolic_end)
reader.close()
print("Total number of data: %d" % counter)
bucket_sizes = [len(data[b]) for b in range(len(_buckets))]
data_tensors = []
for bucket_id in range(len(_buckets)):
bucket_size = bucket_sizes[bucket_id]
if bucket_size == 0:
data_tensors.append((1, 1))
continue
bucket_length = _buckets[bucket_id]
char_length = min(MAX_CHAR_LENGTH, max_char_length[bucket_id])
wid_inputs = np.empty([bucket_size, bucket_length], dtype=np.int64)
cid_inputs = np.empty([bucket_size, bucket_length, char_length],
dtype=np.int64)
pid_inputs = np.empty([bucket_size, bucket_length], dtype=np.int64)
hid_inputs = np.empty([bucket_size, bucket_length], dtype=np.int64)
tid_inputs = np.empty([bucket_size, bucket_length], dtype=np.int64)
masks = np.zeros([bucket_size, bucket_length], dtype=np.float32)
single = np.zeros([bucket_size, bucket_length], dtype=np.int64)
lengths = np.empty(bucket_size, dtype=np.int64)
for i, inst in enumerate(data[bucket_id]):
wids, cid_seqs, pids, hids, tids = inst
inst_size = len(wids)
lengths[i] = inst_size
# word ids
wid_inputs[i, :inst_size] = wids
wid_inputs[i, inst_size:] = PAD_ID_WORD
for c, cids in enumerate(cid_seqs):
cid_inputs[i, c, :len(cids)] = cids
cid_inputs[i, c, len(cids):] = PAD_ID_CHAR
cid_inputs[i, inst_size:, :] = PAD_ID_CHAR
# pos ids
pid_inputs[i, :inst_size] = pids
pid_inputs[i, inst_size:] = PAD_ID_TAG
# type ids
tid_inputs[i, :inst_size] = tids
tid_inputs[i, inst_size:] = PAD_ID_TAG
# heads
hid_inputs[i, :inst_size] = hids
hid_inputs[i, inst_size:] = PAD_ID_TAG
# masks
masks[i, :inst_size] = 1.0
for j, wid in enumerate(wids):
if word_alphabet.is_singleton(wid):
single[i, j] = 1
words = torch.from_numpy(wid_inputs)
chars = torch.from_numpy(cid_inputs)
pos = torch.from_numpy(pid_inputs)
heads = torch.from_numpy(hid_inputs)
types = torch.from_numpy(tid_inputs)
masks = torch.from_numpy(masks)
single = torch.from_numpy(single)
lengths = torch.from_numpy(lengths)
data_tensor = {
'WORD': words,
'CHAR': chars,
'POS': pos,
'HEAD': heads,
'TYPE': types,
'MASK': masks,
'SINGLE': single,
'LENGTH': lengths
}
data_tensors.append(data_tensor)
return data_tensors, bucket_sizes
def read_data(source_path: str, word_alphabet: Alphabet, char_alphabet: Alphabet, pos_alphabet: Alphabet, type_alphabet: Alphabet,
max_size=None, normalize_digits=True, symbolic_root=False, symbolic_end=False):
data = []
max_length = 0
max_char_length = 0
print('Reading data from %s' % source_path)
counter = 0
data_tensors = []
reader = CoNLLXReader(source_path, word_alphabet, char_alphabet, pos_alphabet, type_alphabet)
inst = reader.getNext(normalize_digits=normalize_digits, symbolic_root=symbolic_root, symbolic_end=symbolic_end)
while inst is not None and (not max_size or counter < max_size):
counter += 1
if counter % 10000 == 0:
print("reading data: %d" % counter)
sent = inst.sentence
data.append([sent.bert_ids, sent.sub_idx, sent.word_ids, sent.char_id_seqs, inst.pos_ids, inst.heads, inst.type_ids])
max_len = max([len(char_seq) for char_seq in sent.char_seqs])
if max_char_length < max_len:
max_char_length = max_len
if max_length < inst.length():
max_length = inst.length()
inst = reader.getNext(normalize_digits=normalize_digits, symbolic_root=symbolic_root, symbolic_end=symbolic_end)
reader.close()
print("Total number of data: %d" % counter)
data_size = len(data)
char_length = min(MAX_CHAR_LENGTH, max_char_length)
bert_wid_inputs = np.empty([data_size, max_length], dtype=np.int64)
subword_word_indicator = np.empty([data_size, max_length], dtype=np.int64)
wid_inputs = np.empty([data_size, max_length], dtype=np.int64)
cid_inputs = np.empty([data_size, max_length, char_length], dtype=np.int64)
pid_inputs = np.empty([data_size, max_length], dtype=np.int64)
hid_inputs = np.empty([data_size, max_length], dtype=np.int64)
tid_inputs = np.empty([data_size, max_length], dtype=np.int64)
masks = np.zeros([data_size, max_length], dtype=np.float32)
single = np.zeros([data_size, max_length], dtype=np.int64)
lengths = np.empty(data_size, dtype=np.int64)
bert_lengths = np.empty(data_size, dtype=np.int64)
for i, inst in enumerate(data):
bert_wids, subword_ids, wids, cid_seqs, pids, hids, tids = inst
inst_size = len(wids)
bpe_st_size = len(bert_wids)
lengths[i] = inst_size
bert_lengths[i] = bpe_st_size
# word ids
wid_inputs[i, :inst_size] = wids
wid_inputs[i, inst_size:] = PAD_ID_WORD
# bert ids
bert_wid_inputs[i, :bpe_st_size] = bert_wids
bert_wid_inputs[i, bpe_st_size:] = 0
# subword
subword_word_indicator[i, :len(subword_ids)] = subword_ids
subword_word_indicator[i, len(subword_ids):] = 0
for c, cids in enumerate(cid_seqs):
cid_inputs[i, c, :len(cids)] = cids
cid_inputs[i, c, len(cids):] = PAD_ID_CHAR
cid_inputs[i, inst_size:, :] = PAD_ID_CHAR
# pos ids
pid_inputs[i, :inst_size] = pids
pid_inputs[i, inst_size:] = PAD_ID_TAG
# type ids
tid_inputs[i, :inst_size] = tids
tid_inputs[i, inst_size:] = PAD_ID_TAG
# heads
hid_inputs[i, :inst_size] = hids
hid_inputs[i, inst_size:] = PAD_ID_TAG
# masks
masks[i, :inst_size] = 1.0
for j, wid in enumerate(wids):
if word_alphabet.is_singleton(wid):
single[i, j] = 1
bert_wid_inputs = torch.from_numpy(bert_wid_inputs)
words = torch.from_numpy(wid_inputs)
chars = torch.from_numpy(cid_inputs)
pos = torch.from_numpy(pid_inputs)
heads = torch.from_numpy(hid_inputs)
types = torch.from_numpy(tid_inputs)
masks = torch.from_numpy(masks)
single = torch.from_numpy(single)
lengths = torch.from_numpy(lengths)
bert_lengths = torch.from_numpy(bert_lengths)
subword_word_indicator = torch.from_numpy(subword_word_indicator)
data_tensor = {'WORD': words, 'CHAR': chars, 'POS': pos, 'HEAD': heads, 'TYPE': types,
'MASK': masks, 'SINGLE': single, 'LENGTH': lengths, 'BERT_LENGTH': bert_lengths,
'BERT_WORD': bert_wid_inputs, 'SUB_IDX': subword_word_indicator}
return data_tensor, data_size
