def get_lexicon_count_pipeline(tokenizer):
lexpipe = skpipeline.Pipeline([
('lexfeatures', CountBasedTransformer(tokenizer)),
('lexvect', dv.DictVectorizer()),
])
return lexpipe
def get_named_entity_weight_pipeline(language):
ntransformer = NNEsTransformer(language)
nvect = dv.DictVectorizer()
ne_rate_pipe = skpipeline.Pipeline([
('neratefeat', ntransformer),
('neratevect', nvect),
])
return ne_rate_pipe
def get_keyword_pipeline(word):
ttransformer = TermPresenceTransformer(word)
tvect = dv.DictVectorizer()
wordpipe = skpipeline.Pipeline([
('wordpresfeat', ttransformer),
('wordpresvect', tvect),
])
return wordpipe
def get_polylglot_polarity_count_pipe(lang):
ptransformer = PolyglotPolarityCountTransformer(lang)
tvect = dv.DictVectorizer()
polaritypipe = skpipeline.Pipeline([
('polyglotpolaritycfeat', ptransformer),
('polyglotpolaritycvect', tvect),
])
return polaritypipe
def get_polylglot_polarity_value_pipe(lang):
ptransformer = PolyglotPolarityValueTransformer(lang)
tvect = dv.DictVectorizer()
polaritypipe = skpipeline.Pipeline([
('polyglotpolarityvfeat', ptransformer),
('polyglotpolarityvvect', tvect),
])
return polaritypipe
def vectorizer():
dict_vec = dict_vectorizer.DictVectorizer(sparse=False)
data = dict_vec.fit_transform([{
'name': 'jiujue',
'age': 10
}, {
'name': 'mmp',
'age': 11
}, {
'name': 'sam',
'age': 12
}])
print(dict_vec.get_feature_names())
print(data)
print(type(data))
pass