nlp 停用词处理java_NLP入门：文本预处理（一）停用词

文本预处理——去停用词

停用词文本可以从https://pan.baidu.com/s/1q21hIK95QU9qDstptd8V8g 自提，不谢

该停用词文本转自https://blog.csdn.net/FontThrone/article/details/74200026，自己还未创建新的停用词，后续更新。。。。

# - * - coding: utf - 8 -*-

import sys

# 获取停用词的List

def GetListOfStopWords(filepath):

f_stop = open(filepath, encoding='utf-8')

try:

f_stop_text = f_stop.read()

finally:

f_stop.close()

f_stop_seg_list = f_stop_text.split('\n')

return f_stop_seg_list

# 保存List

# def SaveFile(list, filename):

# f_stop = open(filename, 'w', encoding='utf-8')

# for item in range(len(list)):

# if item != len(list):

# f_stop.writelines((list[item].encode('utf-8')) + '\n')

# else:

# f_stop.writelines(list[item].encode('utf-8'