from hanziconv import HanziConv
import pandas as pd
import jieba

df = pd.read_excel('../Data/十种科室数据集.xlsx', sheet_name='Sheet1')
text = df['ask'].tolist()
stopwords = [line.strip() for line in open('../Data/hit_stopwords.txt', 'r', encoding='utf-8').readlines()]
result = []
for line in text:
    # 精确模式，繁体转换
    seg_list = jieba.cut(HanziConv.toSimplified(line))
    # print(" ".join(seg_list))

    seg_list = [i for i in seg_list if i not in stopwords]
    result.append(' '.join(seg_list))

df_result = pd.DataFrame({'分词': result, 'title': df.title})
df_result.to_excel('../Result/科室分词结果.xlsx', sheet_name='Sheet1', index=False)