def predict(
query,
model_path,
stopwords_path,
person_name_path,
place_name_path,
common_char_path,
segment_sep,
domain_sample_path,
ngram,
pmi_path,
entropy_path,
):
logger.info('model predict')
# get feature
feat = Feature(stopwords_path=stopwords_path,
person_name_path=person_name_path,
place_name_path=place_name_path,
common_char_path=common_char_path,
segment_sep=segment_sep,
domain_sample_path=domain_sample_path,
ngram=ngram,
pmi_path=pmi_path,
entropy_path=entropy_path)
features, terms = feat.get_feature(query, is_word_segmented=False)
# predict classification model
model = load_pkl(model_path)
logger.debug("model predict")
label_pred = model.predict(features)
logger.info("words: %s" % terms)
logger.info("predict label: %s" % label_pred)
print("predict label: %s" % label_pred)
return label_pred
def tfidf_word_feature(data_set,
is_infer=False,
feature_vec_path='',
word_vocab=None):
"""
Get TFIDF ngram feature by word
"""
if is_infer:
vectorizer = load_pkl(feature_vec_path)
data_feature = vectorizer.transform(data_set)
else:
vectorizer = TfidfVectorizer(analyzer='word',
vocabulary=word_vocab,
sublinear_tf=True)
data_feature = vectorizer.fit_transform(data_set)
vocab = vectorizer.vocabulary_
logger.debug('vocab size: %d' % len(vocab))
logger.debug(data_feature.shape)
# if not self.is_infer:
save_pkl(vectorizer, feature_vec_path, overwrite=True)
return data_feature
def _init(self):
self.model = load_pkl(self.model_path)
self.inited = True
def check_inited(self):
if not self.inited:
self.model = load_pkl(self.model_path)
logger.debug('Loaded model: {}'.format(self.model_path))
self.inited = True