def cal_confidence_score(sample, model_name):
'''
给未标注数据打标签，并且计算得分，返回结果
:param model: 模型
:param sample: 对象
:return: 预测的功能点名称 置信度
'''
model = Tagger()
model.open(model_name)
# unlabeled sample features
feature_sequence = build_model_features(sample, 17, False)
# words
# words = sample.sen_words
chars = list(sample.sentence)
model.set(feature_sequence)
predicted_labels = model.tag()
# get predicted_fps
fp_list = []
fp = ''
for index, label in enumerate(predicted_labels):
if label == 'B' or label == 'I' or label == 'E':
fp += chars[index]
if label == 'N' and len(fp) > 0:
fp_list.append(fp)
fp = ''
# calculate the probability of tagging
crf_confidence = model.probability(predicted_labels)
lan_confidence = 0
filtered_fp_list = []
for fp_name in fp_list:
filtered_fp_list.append(fp_name)
if len(filtered_fp_list) == 0:
predicted_fps = 'null'
else:
predicted_fps = ' '.join(filtered_fp_list)
# print(str(sample.story_id) +' '+ sample.sentence +' '+ fp +' '+ str(confidence))
# 为防止多进程乱序执行导致结果跟sample不对应，因此同时返回sample信息
return sample.story_id, sample.sentence, predicted_fps, crf_confidence
pickle.dump({
'dataset': dataset,
'thetas': thetas
}, open(FLEXCRF_TEST_DATA_FILE, 'wb'))
else:
dd = pickle.load(open(FLEXCRF_TEST_DATA_FILE))
dataset = dd['dataset']
thetas = dd['thetas']
# -- Start classification ------------------------------------------------
for seq in range(len(dataset)):
# -- with crfsuite
s_ = tagger.tag(data['X'][seq])
y_ = np.array([int(model.labels[s]) for s in s_])
prob_ = tagger.probability(s_)
print "\n-- With crfsuite:"
print "labels:\n", s_, "\n", y_
print "probability:\t %f" % prob_
# -- with flexcrf
f_xy, y = dataset[seq]
theta = thetas[seq]
m_xy, f_m_xy = _compute_all_potentials(f_xy, theta)
y_pred = viterbi_decoder(m_xy)
# ADD CODE TO COMPUTE POSTERIOR PROBABILITY WITH FLEXCRF HERE ....
