class RelationClassifier:
"""
关系分类，使用bert进行文本分类
"""
def __init__(self):
self.predictor = Predictor(Path.relation_classifier_model)
def predict(self, text):
label, confidence = self.predictor.predict_text(text_a=text)
logger.debug('{} {} {}'.format(label, confidence, confidence >= 0.6))
if confidence < 0.6:
label = ''
return label, confidence
import os
import sys
import pandas as pd
from sklearn import metrics
base_path = os.path.join(os.path.dirname(__file__), '..')
sys.path.append(base_path)
from model.text_classification import Predictor
predictor = Predictor(os.path.join(base_path, 'carbot_data/model/kbqapc'))
examples = predictor.processor.get_dev_examples(os.path.join(base_path, 'data/train/kbqa/predicate_classification/'))
data_df = []
for example in examples:
pred, confidence = predictor.predict_text(example.text_a, example.text_b)
text = example.text_a
true = example.label
data_df.append({
'text': text,
'true': true,
'pred': pred,
'是否正确': '是' if true == pred else '否'
})
df = pd.DataFrame(data_df, columns=['text', 'true', 'pred', '是否正确'])
trues = df['true']
preds = df['pred']
labels = sorted(set(trues))
precision, recall, f1, num = metrics.precision_recall_fscore_support(y_true=trues, y_pred=preds, labels=labels,
average=None)
precision_total, recall_total, f1_total, num_total = metrics.precision_recall_fscore_support(y_true=trues, y_pred=preds,