学习笔记（3):自然语言处理--词向量视频教学（word embedding）-项目实战之utils模块中读取停用词方法编写

立即学习:https://edu.csdn.net/course/play/9460/199584?utm_source=blogtoedu

# utils.py

import GrobalParament

# 去掉回车换行

def delete_r_n(line):

      return line.replace("\r","").replace("\n","").strip()

# 读取停用词

def get_stop_words(stop_words_dir):

      stop_word = []

      with open(stop_words_dir, "r", encoding = GrobalParament.encoding) as f_reader:

      for line in f_reader:

           line = delete_r_n(line)

           stop_words.append(line)

           stop_words = set(stop_words)

       retrun stop_words

if __name__ == "__main__": 

       stop_words = get_stop_words(GrobalParament.stop_word_dir)

       print(len(stop_words))

       print(stop_words[:20])