def set_params(self, **kwargs):
CountVectorizer.set_params(self, **kwargs)
CountVectorizer.__init__(self,
preprocessor=get_preprocessor(
self.column, self.size, self.terminator),
ngram_range=(1, self.size),
analyzer='char',
binary=self.binary)
def set_params(self, **kwargs):
CountVectorizer.set_params(self, **kwargs)
CountVectorizer.__init__(self,
preprocessor=get_preprocessor(self.column,
self.size,
self.terminator),
ngram_range=(1, self.size),
analyzer='char',
binary=self.binary)
def __init__(self, lang, **kwargs):
CountVectorizer.__init__(self, kwargs)
try:
self.stemmer = SnowballStemmer(lang.lower()).stem
self.vect = CountVectorizer()
self.analyzer = self.analyzer_nltk
except ValueError:
pass
def __init__(self, large_file=False):
if large_file:
HashingVectorizer.__init__(self)
else:
# Over ride the built in string processing by assigning the
# tokenizer, preprocessor and lowercase parameters as below.
CountVectorizer.__init__(self, tokenizer=identity,
preprocessor=None,
lowercase=False)
def __init__(self, column, binary=False, size=3, terminator='$'):
self.column = column
self.size = size
self.terminator = terminator
CountVectorizer.__init__(self,
preprocessor=get_preprocessor(
self.column, self.size, self.terminator),
ngram_range=(1, size),
analyzer='char',
binary=binary)
def __init__(self, column, binary=False, size=3, terminator='$'):
self.column = column
self.size = size
self.terminator = terminator
CountVectorizer.__init__(self,
preprocessor=get_preprocessor(self.column,
self.size,
self.terminator),
ngram_range=(1, size),
analyzer='char',
binary=binary)
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,
input="content",
encoding="utf-8",
decode_error="strict",
strip_accents=None,
lowercase=True,
preprocessor=None,
tokenizer=None,
stop_words=None,
token_pattern="(?u)\b\w\w+\b",
ngram_range=(1, 1),
analyzer="word",
max_df=1.0,
min_df=1,
max_features=None,
vocabulary=None,
binary=False,
dtype=numpy.int64,
progress_bar_resolution_seconds=.333,
progress_bar_clear_when_done=False):
CountVectorizer.__init__(self,
input=input,
encoding=encoding,
decode_error=decode_error,
strip_accents=strip_accents,
lowercase=lowercase,
preprocessor=preprocessor,
tokenizer=tokenizer,
stop_words=stop_words,
token_pattern=token_pattern,
ngram_range=ngram_range,
analyzer=analyzer,
max_df=max_df,
min_df=min_df,
max_features=max_features,
vocabulary=vocabulary,
binary=binary,
dtype=dtype)
ProgressBarVectorizer.__init__(self, progress_bar_resolution_seconds,
progress_bar_clear_when_done)
def __init__(self, stopwords_list=None, max_features=None):
CountVectorizer.__init__(self,analyzer="word",\
strip_accents="unicode",\
stop_words=stopwords_list,\
max_features=max_features)
self.en_lemmatizer = nltk.stem.WordNetLemmatizer()
def __init__(self, analyzer=BOWAnalyzer, max_df=None): CountVectorizer.__init__(self, analyzer=analyzer, max_df=max_df)
def __init__(self,
n_grams=1,
first_last_sentence_only=False):
CountVectorizer.__init__(self, ngram_range=(n_grams, n_grams))
self.first_last_sentence_only = first_last_sentence_only
self.term_dict = {}
def __init__(self, **kwargs):
CountVectorizer.__init__(self, **kwargs)
def __init__(self):
CountVectorizer.__init__(self, binary=True,
tokenizer=identity,
preprocessor=None,
lowercase=False)
def __init__(self, window=None, sentence_splitter="\n", directional=False, **args):
self.window = window
self.sentence_splitter = sentence_splitter
self.directional = directional
CountVectorizer.__init__(self, **args)
