class Chatbot_port2(object):
def __init__(self):
# 分词工具，基于jieba分词，并去除停用词
seg = Seg()
self.ss = SentenceSimilarity(seg)
self.ss.restore_model()
with open("dataset/answer.txt", 'r', encoding='utf-8') as file_answer:
self.line = file_answer.readlines()
def chat(self, question):
question = question.strip()
top_10 = self.ss.similarity(question)
answer_index = top_10[0][0]
answer = self.line[answer_index]
return answer, top_10[0][1]
for sen in raw_test_sentences:
test_sentences.append(sen.strip())
for sen in test_sentences:
print(sen)
# 分词工具，基于jieba分词，并去除停用词
seg = Seg()
# 训练模型
ss = SentenceSimilarity(seg)
if train:
ss.set_sentences(train_sentences)
ss.TfidfModel() # tfidf模型
ss.save_model()
else:
ss.restore_model()
# 测试集
right_count = 0
print(os.getcwd())
file_result = open('dataset/test_output.txt', 'w',encoding='utf-8')
with open("dataset/answer.txt", 'r', encoding='utf-8') as file_answer:
line = file_answer.readlines()
for i in range(0, len(test_sentences)):
top_10 = ss.similarity(test_sentences[i])
answer_index = top_10[0][0]
answer = line[answer_index]
file_result.write(test_sentences[i]+'\t')