def __init__(self,
config: SerializableDict = None,
map_x=True,
map_y=True,
lower=False,
**kwargs) -> None:
super().__init__(**merge_locals_kwargs(locals(), kwargs))
self.token_vocab = VocabTF()
self.pos_vocab = VocabTF(pad_token=None, unk_token=None)
self.ner_vocab = VocabTF(pad_token=None)
self.deprel_vocab = VocabTF(pad_token=None, unk_token=None)
self.rel_vocab = VocabTF(pad_token=None, unk_token=None)
def vocab_from_txt(txt_file_path,
bigram_only=False,
window_size=4,
**kwargs) -> Tuple[VocabTF, VocabTF, VocabTF]:
char_vocab, ngram_vocab, tag_vocab = VocabTF(), VocabTF(), VocabTF(
pad_token=None, unk_token=None)
for X, Y in generate_ngram_bmes(txt_file_path,
bigram_only,
window_size,
gold=True):
char_vocab.update(X[0])
for ngram in X[1:]:
ngram_vocab.update(filter(lambda x: x, ngram))
tag_vocab.update(Y)
return char_vocab, ngram_vocab, tag_vocab
def _load(path,
vocab,
normalize=False) -> Tuple[VocabTF, Union[np.ndarray, None]]:
if not vocab:
vocab = VocabTF()
if not path:
return vocab, None
assert vocab.unk_idx is not None
word2vec, dim = load_word2vec(path)
for word in word2vec:
vocab.get_idx(word)
pret_embs = np.zeros(shape=(len(vocab), dim), dtype=np.float32)
state = np.random.get_state()
np.random.seed(0)
bias = np.random.uniform(low=-0.001, high=0.001,
size=dim).astype(dtype=np.float32)
scale = np.sqrt(3.0 / dim)
for word, idx in vocab.token_to_idx.items():
vec = word2vec.get(word, None)
if vec is None:
vec = word2vec.get(word.lower(), None)
# if vec is not None:
# vec += bias
if vec is None:
# vec = np.random.uniform(-scale, scale, [dim])
vec = np.zeros([dim], dtype=np.float32)
pret_embs[idx] = vec
# noinspection PyTypeChecker
np.random.set_state(state)
return vocab, pret_embs
def __init__(self,
filepath: str = None,
vocab: VocabTF = None,
expand_vocab=True,
lowercase=False,
input_dim=None,
output_dim=None,
unk=None,
normalize=False,
embeddings_initializer='VarianceScaling',
embeddings_regularizer=None,
activity_regularizer=None,
embeddings_constraint=None,
mask_zero=True,
input_length=None,
name=None,
**kwargs):
if vocab is None:
vocab = VocabTF()
self.vocab = vocab
super().__init__(filepath, vocab, expand_vocab, lowercase, input_dim,
output_dim, unk, normalize, embeddings_initializer,
embeddings_regularizer, activity_regularizer,
embeddings_constraint, mask_zero, input_length, name,
**kwargs)
def fit(self, trn_path: str, **kwargs) -> int:
self.vocab = VocabTF()
num_samples = 0
for x, y in self.file_to_inputs(trn_path):
self.vocab.update(x)
num_samples += 1
return num_samples
def fit(self, trn_path: str, **kwargs) -> int:
self.word_vocab = VocabTF()
self.tag_vocab = VocabTF(pad_token=None, unk_token=None)
num_samples = 0
for words, tags in self.file_to_inputs(trn_path, True):
self.word_vocab.update(words)
self.tag_vocab.update(tags)
num_samples += 1
if self.char_vocab:
self.char_vocab = VocabTF()
for word in self.word_vocab.token_to_idx.keys():
if word in (self.word_vocab.pad_token,
self.word_vocab.unk_token):
continue
self.char_vocab.update(list(word))
return num_samples
def load_vocabs(self, save_dir, filename='vocabs.json'):
save_dir = get_resource(save_dir)
vocabs = SerializableDict()
vocabs.load_json(os.path.join(save_dir, filename))
for key, value in vocabs.items():
vocab = VocabTF()
vocab.copy_from(value)
setattr(self.transform, key, vocab)
def vocab_from_tsv(tsv_file_path, lower=False, lock_word_vocab=False, lock_char_vocab=True, lock_tag_vocab=True) \
-> Tuple[VocabTF, VocabTF, VocabTF]:
word_vocab = VocabTF()
char_vocab = VocabTF()
tag_vocab = VocabTF(unk_token=None)
with open(tsv_file_path, encoding='utf-8') as tsv_file:
for line in tsv_file:
cells = line.strip().split()
if cells:
word, tag = cells
if lower:
word_vocab.add(word.lower())
else:
word_vocab.add(word)
char_vocab.update(list(word))
tag_vocab.add(tag)
if lock_word_vocab:
word_vocab.lock()
if lock_char_vocab:
char_vocab.lock()
if lock_tag_vocab:
tag_vocab.lock()
return word_vocab, char_vocab, tag_vocab
def __init__(self,
filepath: str = None,
vocab: VocabTF = None,
expand_vocab=True,
lowercase=True,
input_dim=None,
output_dim=None,
unk=None,
normalize=False,
embeddings_initializer='VarianceScaling',
embeddings_regularizer=None,
activity_regularizer=None,
embeddings_constraint=None,
mask_zero=True,
input_length=None,
name=None,
cpu=True,
**kwargs):
filepath = get_resource(filepath)
word2vec, _output_dim = load_word2vec(filepath)
if output_dim:
assert output_dim == _output_dim, f'output_dim = {output_dim} does not match {filepath}'
output_dim = _output_dim
# if the `unk` token exists in the pretrained,
# then replace it with a self-defined one, usually the one in word vocab
if unk and unk in word2vec:
word2vec[vocab.safe_unk_token] = word2vec.pop(unk)
if vocab is None:
vocab = VocabTF()
vocab.update(word2vec.keys())
if expand_vocab and vocab.mutable:
for word in word2vec:
vocab.get_idx(word.lower() if lowercase else word)
if input_dim:
assert input_dim == len(
vocab), f'input_dim = {input_dim} does not match {filepath}'
input_dim = len(vocab)
# init matrix
self._embeddings_initializer = embeddings_initializer
embeddings_initializer = tf.keras.initializers.get(
embeddings_initializer)
with tf.device('cpu:0') if cpu else DummyContext():
pret_embs = embeddings_initializer(
shape=[input_dim, output_dim]).numpy()
# insert to pret_embs
for word, idx in vocab.token_to_idx.items():
vec = word2vec.get(word, None)
# Retry lower case
if vec is None and lowercase:
vec = word2vec.get(word.lower(), None)
if vec is not None:
pret_embs[idx] = vec
if normalize:
pret_embs /= np.std(pret_embs)
if not name:
name = os.path.splitext(os.path.basename(filepath))[0]
super().__init__(input_dim,
output_dim,
tf.keras.initializers.Constant(pret_embs),
embeddings_regularizer,
activity_regularizer,
embeddings_constraint,
mask_zero,
input_length,
name=name,
**kwargs)
self.filepath = filepath
self.expand_vocab = expand_vocab
self.lowercase = lowercase