def __init__(
self,
tokenizer: algorithm(Document(), List(Sentence())),
feature_extractor: algorithm(Sentence(), Flags()),
):
self.tokenizer = tokenizer
self.feature_extractor = feature_extractor
def test_polimorphic_interface():
interface = algorithm(MatrixContinuousDense(), MatrixContinuousDense())
assert interface.is_compatible(ExactAlgorithm)
assert interface.is_compatible(HigherInputAlgorithm)
interface = algorithm(MatrixContinuousDense(), MatrixContinuous())
assert interface.is_compatible(LowerOutputAlgorithm)
def __init__(
self,
tokenizer: algorithm(Sentence(), List(Word())),
feature_extractor: algorithm(Word(), Flags()),
include_text: Boolean(),
):
self.tokenizer = tokenizer
self.feature_extractor = feature_extractor
self.include_text = include_text
def __init__(
self,
extractors: Distinct(
algorithm(Word(), Flags()), exceptions=["MultipleFeatureExtractor"]
),
merger: algorithm(List(Flags()), Flags()),
):
self.extractors = extractors
self.merger = merger
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,
affix_length: DiscreteValue(min=2, max=6),
min_stem_length: DiscreteValue(min=1, max=4),
cutoff: DiscreteValue(min=0, max=10),
backoff: algorithm(
Seq[Seq[Word]], Supervised[Seq[Seq[Postag]]], Seq[Seq[Postag]]
),
):
self.affix_length = affix_length
self.min_stem_length = min_stem_length
self.cutoff = cutoff
self.backoff = backoff
self.tagger = _AffixTagger
self.values = dict(
affix_length=affix_length,
min_stem_length=min_stem_length,
cutoff=cutoff,
backoff=backoff,
)
NltkTagger.__init__(self)
def __init__(self, dependance: algorithm(Word, Stem)):
pass
def __init__(self, dependance: algorithm(Sentence, Document)):
pass
def __init__(self, stem: algorithm(Word, Stem)):
pass
def __init__(self, ub: algorithm(Sentence, Document)):
pass
def __init__(self,
tokenizer: algorithm(Sentence(), List(Word())),
token_feature_extractor: algorithm(Word(), Flags()),
# token_sentence_encoder: algorithm(Word(), )
):
pass
def __init__(self, tokenizer: algorithm(Sentence(), List(Word()))):
self.tokenizer = tokenizer