def build_vectorization_pipeline(self) -> Tuple[List[Tuple[str, Any]], Callable[[], List[str]]]:
vect_cur = CountVectorizer(strip_accents='unicode', analyzer='word',
stop_words=self._build_stop_words(), tokenizer=vectorizers.whole_value_as_token)
vect_amount = vectorizers.NumberVectorizer()
def get_feature_names_(vect_cur_, vect_amount_):
def res():
return ['currency_' + str(c) for c in vect_cur_.get_feature_names()] \
+ ['amount_' + str(fn) for fn in vect_amount_.get_feature_names()]
return res
return [
('vect', FeatureUnion(transformer_list=[
('currency', Pipeline([
('selector', vectorizers.DictItemSelector(item='currency')),
('clean', vectorizers.ReplaceNoneTransformer('')),
('vect', vect_cur),
('tfidf', TfidfTransformer()),
])),
('amount', Pipeline([
('selector', vectorizers.DictItemSelector(item='amount')),
('vect', vect_amount),
]))
]))
], get_feature_names_(vect_cur, vect_amount)
def build_vectorization_pipeline(self) -> Tuple[List[Tuple[str, Any]], Callable[[], List[str]]]:
vect_numerator = vectorizers.NumberVectorizer()
vect_denominator = vectorizers.NumberVectorizer()
def get_feature_names_(vect_numerator, vect_denominator):
def res():
return ['numerator_' + str(c) for c in vect_numerator.get_feature_names()] \
+ ['denominator_' + str(c) for c in vect_denominator.get_feature_names()]
return res
return [
('vect', FeatureUnion(transformer_list=[
('numerator', Pipeline([
('selector', vectorizers.DictItemSelector(item='numerator')),
('vect', vect_numerator),
])),
('denominator', Pipeline([
('selector', vectorizers.DictItemSelector(item='denominator')),
('vect', vect_denominator),
]))
]))
], get_feature_names_(vect_numerator, vect_denominator)
def build_vectorization_pipeline(self) -> Tuple[List[Tuple[str, Any]], Callable[[], List[str]]]:
vect = vectorizers.NumberVectorizer(to_float_converter=lambda d: d.total_seconds() if d else 0 if d else 0)
return [('vect', vect)], self._wrap_get_feature_names(vect)
def build_vectorization_pipeline(self) -> Tuple[List[Tuple[str, Any]], Callable[[], List[str]]]:
vect = vectorizers.NumberVectorizer()
return [('vect', vect)], self._wrap_get_feature_names(vect)