def process_y_dataset(self,
data: List[List[str]],
max_len: Optional[int] = None,
subset: Optional[List[int]] = None) -> np.ndarray:
if subset is not None:
target = utils.get_list_subset(data, subset)
else:
target = data[:]
y = np.array(target)
return y
def process_y_dataset(self,
data: List[str],
max_len: Optional[int] = None,
subset: Optional[List[int]] = None) -> np.ndarray:
if subset is not None:
target = utils.get_list_subset(data, subset)
else:
target = data
if self.multi_label:
return self.multi_label_binarizer.fit_transform(target)
else:
numerized_samples = self.numerize_label_sequences(target)
return to_categorical(numerized_samples, len(self.label2idx))
def process_x_dataset(self,
data: List[List[str]],
max_len: Optional[int] = None,
subset: Optional[List[int]] = None) -> np.ndarray:
if max_len is None:
max_len = self.sequence_length
if subset is not None:
target = utils.get_list_subset(data, subset)
else:
target = data
numerized_samples = self.numerize_token_sequences(target)
return pad_sequences(numerized_samples, max_len, padding='post', truncating='post')
def process_y_dataset(self,
data: List[List[str]],
max_len: Optional[int] = None,
subset: Optional[List[int]] = None) -> np.ndarray:
if subset is not None:
target = utils.get_list_subset(data, subset)
else:
target = data[:]
numerized_samples = self.numerize_label_sequences(target)
padded_seq = pad_sequences(numerized_samples,
max_len,
padding='post',
truncating='post')
return to_categorical(padded_seq, len(self.label2idx))
def test_get_list_subset(self):
x = list(range(0, 100))
subset = get_list_subset(x, list(range(10, 20)))
assert subset == [10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
