class TSVTaggingTransform(TsvTaggingFormat, Transform):
def __init__(self,
config: SerializableDict = None,
map_x=True,
map_y=True,
use_char=False,
**kwargs) -> None:
super().__init__(**merge_locals_kwargs(locals(), kwargs))
self.word_vocab: Optional[Vocab] = None
self.tag_vocab: Optional[Vocab] = None
self.char_vocab: Optional[Vocab] = None
def fit(self, trn_path: str, **kwargs) -> int:
self.word_vocab = Vocab()
self.tag_vocab = Vocab(pad_token=None, unk_token=None)
num_samples = 0
for words, tags in generator_words_tags(trn_path,
gold=True,
lower=self.config.get(
'lower', False)):
self.word_vocab.update(words)
self.tag_vocab.update(tags)
num_samples += 1
if self.char_vocab:
self.char_vocab = Vocab()
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 create_types_shapes_values(self) -> Tuple[Tuple, Tuple, Tuple]:
types = tf.string, tf.string
shapes = [None], [None]
values = self.word_vocab.pad_token, self.tag_vocab.first_token
return types, shapes, values
def inputs_to_samples(self, inputs, gold=False):
lower = self.config.get('lower', False)
if gold:
if lower:
for x, y in inputs:
yield x.lower(), y
else:
yield from inputs
else:
for x in inputs:
yield x.lower() if lower else x, [self.padding_values[-1]
] * len(x)
def x_to_idx(self, x) -> Union[tf.Tensor, Tuple]:
return self.word_vocab.lookup(x)
def y_to_idx(self, y) -> tf.Tensor:
return self.tag_vocab.lookup(y)
def X_to_inputs(self, X: Union[tf.Tensor, Tuple[tf.Tensor]]) -> Iterable:
for xs in X:
words = []
for x in xs:
words.append(
str_tensor_to_str(x) if self.char_vocab else self.
word_vocab.idx_to_token[int(x)])
yield words
def Y_to_outputs(self,
Y: Union[tf.Tensor, Tuple[tf.Tensor]],
gold=False,
inputs=None,
X=None,
**kwargs) -> Iterable:
masks = Y._keras_mask if hasattr(Y, '_keras_mask') else tf.ones_like(Y)
if not gold:
Y = tf.argmax(Y, axis=2)
for ys, mask in zip(Y, masks):
tags = []
for y, m in zip(ys, mask):
if not m:
break
tags.append(self.tag_vocab.idx_to_token[int(y)])
yield tags
def input_is_single_sample(
self, input: Union[List[str], List[List[str]]]) -> bool:
return isinstance(input[0], str)
def input_truth_output_to_str(self, input: List[str], truth: List[str],
output: List[str]):
text = ''
for word, gold_tag, pred_tag in zip(input, truth, output):
text += ' '.join([word, gold_tag, pred_tag]) + '\n'
text += '\n'
return text
class TextTransform(Transform):
def __init__(self,
forward=True,
seq_len=10,
tokenizer='char',
config: SerializableDict = None,
map_x=True,
map_y=True,
**kwargs) -> None:
super().__init__(config,
map_x,
map_y,
seq_len=seq_len,
tokenizer=tokenizer,
forward=forward,
**kwargs)
self.vocab: Vocab = None
def tokenize_func(self):
if self.config.tokenizer == 'char':
return list
elif self.config.tokenizer == 'whitespace':
return lambda x: x.split()
else:
return lambda x: x.split(self.config.tokenizer)
def fit(self, trn_path: str, **kwargs) -> int:
self.vocab = Vocab()
num_samples = 0
for x, y in self.file_to_inputs(trn_path):
self.vocab.update(x)
num_samples += 1
return num_samples
def create_types_shapes_values(self) -> Tuple[Tuple, Tuple, Tuple]:
types = tf.string, tf.string
shapes = [None], [None]
defaults = self.vocab.pad_token, self.vocab.pad_token
return types, shapes, defaults
def file_to_inputs(self, filepath: str, gold=True):
forward = self.config.forward
seq_len = self.config.seq_len
buffer = []
tokenizer = self.tokenize_func()
with open(filepath,
encoding='utf-8') if forward else FileReadBackwards(
filepath, encoding="utf-8") as src:
for line in src:
tokens = tokenizer(line)
buffer += tokens
while len(buffer) > seq_len:
yield buffer[:seq_len], buffer[1:1 + seq_len]
buffer.pop(0)
def inputs_to_samples(self, inputs, gold=False):
forward = self.config.forward
for t in inputs:
if gold:
x, y = t
else:
x, y = t, t
if not forward:
x = list(reversed(x))
y = list(reversed(y))
yield x, y
def x_to_idx(self, x) -> Union[tf.Tensor, Tuple]:
return self.vocab.lookup(x)
def y_to_idx(self, y) -> tf.Tensor:
return self.x_to_idx(y)
def Y_to_outputs(self,
Y: Union[tf.Tensor, Tuple[tf.Tensor]],
gold=False) -> Iterable:
mask = Y._keras_mask
pred = tf.argmax(Y, axis=-1)
for ys, ms in zip(pred, mask):
ret = []
for y, m in zip(ys, ms):
if not m:
break
ret.append(self.vocab.idx_to_token[int(y)])
yield ret
def input_is_single_sample(self, input: Any) -> bool:
return isinstance(input[0], str)
