def transform(self, data_pack: DataPack, verbose=1) -> DataPack:
"""
Apply transformation on data, create `letter-ngram` representation.
:param data_pack: Inputs to be preprocessed.
:param verbose: Verbosity.
:return: Transformed data as :class:`DataPack` object.
"""
data_pack = data_pack.copy()
units = self._default_processor_units()
data_pack.apply_on_text(chain_transform(units),
inplace=True,
verbose=verbose)
data_pack.apply_on_text(self._left_fixedlength_unit.transform,
mode='left',
inplace=True,
verbose=verbose)
data_pack.apply_on_text(self._right_fixedlength_unit.transform,
mode='right',
inplace=True,
verbose=verbose)
post_units = [processor_units.NgramLetterUnit(reduce_dim=False)]
if self._with_word_hashing:
term_index = self._context['vocab_unit'].state['term_index']
post_units.append(processor_units.WordHashingUnit(term_index))
data_pack.apply_on_text(chain_transform(post_units),
inplace=True,
verbose=verbose)
return data_pack
def fit(self, data_pack: DataPack, verbose=1):
"""
Fit pre-processing context for transformation.
:param data_pack: data_pack to be preprocessed.
:param verbose: Verbosity.
:return: class:`BasicPreprocessor` instance.
"""
units = self._default_processor_units()
data_pack = data_pack.apply_on_text(chain_transform(units),
verbose=verbose)
fitted_filter_unit = build_unit_from_data_pack(self._filter_unit,
data_pack,
flatten=False,
mode='right',
verbose=verbose)
data_pack = data_pack.apply_on_text(fitted_filter_unit.transform,
mode='right',
verbose=verbose)
self._context['filter_unit'] = fitted_filter_unit
vocab_unit = build_vocab_unit(data_pack, verbose=verbose)
self._context['vocab_unit'] = vocab_unit
self._context['vocab_size'] = len(vocab_unit.state['term_index']) + 1
self._context['input_shapes'] = [(self._fixed_length_left, ),
(self._fixed_length_right, )]
return self
def transform(self, data_pack: DataPack, verbose: int = 1) -> DataPack:
"""
Apply transformation on data, create `tri-letter` representation.
:param data_pack: Inputs to be preprocessed.
:param verbose: Verbosity.
:return: Transformed data as :class:`DataPack` object.
"""
units = self._default_processor_units()
units.append(self._context['vocab_unit'])
units.append(processor_units.FixedLengthUnit(text_length=30,
pad_mode='post'))
return data_pack.apply_on_text(chain_transform(units), verbose=verbose)
def fit(self, data_pack: DataPack, verbose: int = 1):
"""
Fit pre-processing context for transformation.
:param data_pack: data_pack to be preprocessed.
:param verbose: Verbosity.
:return: class:`NaivePreprocessor` instance.
"""
units = self._default_processor_units()
data_pack = data_pack.apply_on_text(chain_transform(units),
verbose=verbose)
vocab_unit = build_vocab_unit(data_pack, verbose=verbose)
self._context['vocab_unit'] = vocab_unit
return self
def fit(self, data_pack: DataPack, verbose=1):
"""
Fit pre-processing context for transformation.
:param verbose: Verbosity.
:param data_pack: data_pack to be preprocessed.
:return: class:`DSSMPreprocessor` instance.
"""
units = self._default_processor_units()
data_pack = data_pack.apply_on_text(chain_transform(units),
verbose=verbose)
vocab_unit = build_vocab_unit(data_pack, verbose=verbose)
self._context['vocab_unit'] = vocab_unit
triletter_dim = len(vocab_unit.state['term_index']) + 1
self._context['input_shapes'] = [(triletter_dim, ), (triletter_dim, )]
return self
def transform(self, data_pack: DataPack, verbose=1) -> DataPack:
"""
Apply transformation on data, create `tri-letter` representation.
:param data_pack: Inputs to be preprocessed.
:param verbose: Verbosity.
:return: Transformed data as :class:`DataPack` object.
"""
data_pack = data_pack.copy()
units = self._default_processor_units()
if self._with_word_hashing:
term_index = self._context['vocab_unit'].state['term_index']
units.append(processor_units.WordHashingUnit(term_index))
data_pack.apply_on_text(chain_transform(units),
inplace=True,
verbose=verbose)
return data_pack
def fit(self, data_pack: DataPack, verbose=1):
"""
Fit pre-processing context for transformation.
:param verbose: Verbosity.
:param data_pack: Data_pack to be preprocessed.
:return: class:`CDSSMPreprocessor` instance.
"""
units = self._default_processor_units()
units.append(processor_units.NgramLetterUnit())
data_pack = data_pack.apply_on_text(chain_transform(units),
verbose=verbose)
vocab_unit = build_vocab_unit(data_pack, verbose=verbose)
self._context['vocab_unit'] = vocab_unit
vocab_size = len(vocab_unit.state['term_index']) + 1
self._context['input_shapes'] = [(self._fixed_length_left, vocab_size),
(self._fixed_length_right, vocab_size)
]
return self
def transform(self, data_pack: DataPack, verbose=1) -> DataPack:
"""
Apply transformation on data, create fixed length representation.
:param data_pack: Inputs to be preprocessed.
:param verbose: Verbosity.
:return: Transformed data as :class:`DataPack` object.
"""
data_pack = data_pack.copy()
units = self._default_processor_units()
data_pack.apply_on_text(chain_transform(units),
inplace=True,
verbose=verbose)
data_pack.apply_on_text(self._context['filter_unit'].transform,
mode='right',
inplace=True,
verbose=verbose)
data_pack.apply_on_text(self._context['vocab_unit'].transform,
mode='both',
inplace=True,
verbose=verbose)
data_pack.append_text_length(inplace=True, verbose=verbose)
data_pack.apply_on_text(self._left_fixedlength_unit.transform,
mode='left',
inplace=True,
verbose=verbose)
data_pack.apply_on_text(self._right_fixedlength_unit.transform,
mode='right',
inplace=True,
verbose=verbose)
max_len_left = self._fixed_length_left
max_len_right = self._fixed_length_right
data_pack.left['length_left'] = data_pack.left['length_left'].apply(
lambda val: val if val <= max_len_left else max_len_left)
data_pack.right['length_right'] = data_pack.right[
'length_right'].apply(lambda val: val
if val <= max_len_right else max_len_right)
return data_pack
