def bad_word_count_features_svm(config):
preprocessed_input = inference_preprocessing(config)
normalizer = count_features(config)
xy_split = normalizer.get_step('xy_split')
tfidf_word_vectorizer = bad_word_tfidf(preprocessed_input, config)
svm_multi = Step(name='svm_multi',
transformer=LinearSVCMultilabel(**config.svc_multilabel),
input_steps=[xy_split, normalizer, tfidf_word_vectorizer],
adapter={
'X': ([('normalizer', 'X'),
('bad_word_tfidf_word_vectorizer', 'features')
], sparse_hstack_inputs),
'y': ([('xy_split', 'y')]),
},
cache_dirpath=config.env.cache_dirpath)
svm_output = Step(name='svm_output',
transformer=Dummy(),
input_steps=[svm_multi],
adapter={
'y_pred':
([('svm_multi', 'prediction_probability')]),
},
cache_dirpath=config.env.cache_dirpath)
return svm_output
def hand_crafted_all_svm(config):
xy_split, normalizer, char_vector, word_vector, bad_word_vector = hand_crafted_all(
config)
svm_multi = Step(name='svm_multi',
transformer=LinearSVCMultilabel(**config.svc_multilabel),
input_steps=[
xy_split, normalizer, char_vector, word_vector,
bad_word_vector
],
adapter={
'X': ([('normalizer', 'X'),
('tfidf_char_vectorizer', 'features'),
('tfidf_word_vectorizer', 'features'),
('bad_word_tfidf_word_vectorizer', 'features')
], sparse_hstack_inputs),
'y': ([('xy_split', 'y')]),
},
cache_dirpath=config.env.cache_dirpath)
svm_output = Step(name='svm_output',
transformer=Dummy(),
input_steps=[svm_multi],
adapter={
'y_pred':
([('logreg_multi', 'prediction_probability')]),
},
cache_dirpath=config.env.cache_dirpath)
return svm_output
def tfidf_svm(config):
preprocessed_input = inference_preprocessing(config)
tfidf_char_vectorizer, tfidf_word_vectorizer = tfidf(
preprocessed_input, config)
svm_multi = Step(name='svm_multi',
transformer=LinearSVCMultilabel(**config.svc_multilabel),
input_steps=[
preprocessed_input, tfidf_char_vectorizer,
tfidf_word_vectorizer
],
adapter={
'X': ([('tfidf_char_vectorizer', 'features'),
('tfidf_word_vectorizer', 'features')],
sparse_hstack_inputs),
'y': ([('cleaning_output', 'y')]),
},
cache_dirpath=config.env.cache_dirpath)
svm_output = Step(name='svm_output',
transformer=Dummy(),
input_steps=[svm_multi],
adapter={
'y_pred':
([('logreg_multi', 'prediction_probability')]),
},
cache_dirpath=config.env.cache_dirpath)
return svm_output
def count_features_svm(config):
normalizer = count_features(config)
xy_split = normalizer.get_step('xy_split')
svm_multi = Step(name='svm_multi',
transformer=LinearSVCMultilabel(**config.svc_multilabel),
input_steps=[xy_split, normalizer],
adapter={'X': ([('normalizer', 'X')]),
'y': ([('xy_split', 'y')]),
},
cache_dirpath=config.env.cache_dirpath)
svm_output = Step(name='svm_output',
transformer=Dummy(),
input_steps=[svm_multi],
adapter={'y_pred': ([('svm_multi', 'prediction_probability')]),
},
cache_dirpath=config.env.cache_dirpath)
return svm_output