中文分词模块jieba学习笔记

import jieba
sentence="我是长沙理工大学学生"
generator=jieba.cut(sentence)
words=" ".join(generator)

import jieba.posseg as jp
sentence="我是长沙理工大学学生"
posseg=jp.cut(sentence)
for i in posseg:
    print(i.__dict__)

import jieba
sentence="天长地久有时尽"
jieba.add_word("时尽",999,"nz")
print(jieba.cut(sentence))
jieba.del_word("时尽")
print(jieba.cut(sentence))

import jieba
my_dict="my_dict.txt"
with open(my_dict,"w",encoding="utf-8") as f:
    f.write("莫容紫英 9 nrn云天河 9 nrn天河剑 9 nz")
dentence="莫容紫英为云天河打造了云天剑"
pprint("加载前：",jieba.lcut(sentence))
jieba.load_userdict(my_dict)
print("加载后：",jieba.lcut(sentence))
os.remove(my_dict)