自然语言处理 NLP情感分析项目 测试数据集加载核心代码实现

import re  

pattern = r"([,。?]+)" 

flags = [",","。","?"]

sentence_txt = []

with open("./train.txt","r",encoding="utf-8") as reader_file:

    for line in reader_file:

        spilt_list = re.split(pattern=pattern, string=line)

        segment = ""

        for segment_i in spilt_list:            

            segment += segment_i

            if segment_i in flags :

                sentence_txt.append("".join(segment.split())+"\r")

                segment = ""

        sentence_txt.append("\r")

with open("./spilt_val.txt","w",encoding="utf-8") as writer_file:

    writer_file.writelines(sentence_txt)

Logo

技术共进,成长同行——讯飞AI开发者社区

更多推荐