def __init__(
self,
lowercase: Boolean(),
stopwords_remove: Boolean(),
binary: Boolean(),
inner_tokenizer: algorithm(Sentence(), List(Word())),
inner_stemmer: algorithm(Word(), Stem()),
inner_stopwords: algorithm(List(Word()), List(Word())),
):
self.stopwords_remove = stopwords_remove
self.inner_tokenizer = inner_tokenizer
self.inner_stemmer = inner_stemmer
self.inner_stopwords = inner_stopwords
SklearnTransformer.__init__(self)
_CountVectorizer.__init__(self, lowercase=lowercase, binary=binary)
def __init__(
self,
language: CategoricalValue(
"danish",
"dutch",
"english",
"finnish",
"french",
"german",
"hungarian",
"italian",
"norwegian",
"portuguese",
"russian",
"spanish",
"swedish",
"turkish",
),
):
self.language = language
from nltk.corpus import stopwords
self.words = stopwords.words(language)
SklearnTransformer.__init__(self)
def run(self, input: Seq[Sentence]) -> MatrixContinuousDense:
"""This methods receive a document list and transform this into a dense continuous matrix.
"""
return SklearnTransformer.run(self, input)
def run(self, input: Seq[Word]) -> Seq[Word]:
"""This methods receive a word list list and transform this into a word list list without stopwords.
"""
return SklearnTransformer.run(self, input)
def run(self, input: List(Word())) -> List(Word()):
"""This methods receive a word list list and transform this into a word list list without stopwords.
"""
return SklearnTransformer.run(self, input)
def train(self):
SklearnTransformer.train(self)
def run(self, input: List(Sentence())) -> MatrixContinuousSparse():
return SklearnTransformer.run(self, input)