python中jieba模块的深入了解

The main function that segments an entire sentence that contains Chinese characters into separated words.

import jieba
sentence = 'python是世界上最好的编程语言'
ls = jieba.cut(sentence, cut_all=False)
print(ls)
# <generator object Tokenizer.cut at 0x000001966B14EA98>

print(type(ls))
# <class 'generator'>

# ①''.join
ls_1 = ' '.join(ls)
print(ls_1)
# python 是 世界 上 最好 的 编程 编程语言 语言

# ②for循环遍历
for i in ls:
    print(i)
'''
python
是
世界
上
最好
的
编程语言
'''

# ③列表推导式
ls_2 = [i for i in ls]
print(ls_2)
# ['python', '是', '世界', '上', '最好', '的', '编程语言']

    def lcut(self, *args, **kwargs):
        return list(self.cut(*args, **kwargs))

import jieba
sentence = 'python是世界上最好的编程语言'
ls = jieba.cut(sentence, cut_all=False)
print(ls)
print(list(ls))
ls1 = jieba.lcut(sentence, cut_all=True)
print(ls1)
ls2 = jieba.lcut(sentence)
print(ls2)

import jieba
sentence = 'python是世界上最好的编程语言'
ls3 = jieba.cut_for_search(sentence)
print(ls3)
# <generator object Tokenizer.cut_for_search at 0x00000199C7A3D9A8>
print(list(ls3))
# ['python', '是', '世界', '上', '最好', '的', '编程', '语言', '编程语言']
ls4 = jieba.lcut_for_search(sentence)
print(ls4)
# ['python', '是', '世界', '上', '最好', '的', '编程', '语言', '编程语言']

Add a word to dictionary.
freq and tag can be omitted, freq defaults to be a calculated value that ensures the word can be cut out.

import jieba
sentence = 'python是世界上最好的编程语言'
ls2 = jieba.lcut(sentence)
print(ls2)
ls5 = jieba.add_word('最好的')
ls6 = jieba.lcut(sentence)
print(ls6)

import jieba
sentence = 'python是世界上最好的编程语言'
ls2 = jieba.lcut(sentence)
print(ls2)
ls7 = jieba.del_word('世界')
ls8 = jieba.lcut(sentence)
print(ls8)

 """
        Suggest word frequency to force the characters in a word to be
        joined or splitted.
        Parameter:
            - segment : The segments that the word is expected to be cut into,
                        If the word should be treated as a whole, use a str.
            - tune : If True, tune the word frequency.
        Note that HMM may affect the final result. If the result doesn't change,
        set HMM=False.
        """

  """
        Tokenize a sentence and yields tuples of (word, start, end)
        Parameter:
            - sentence: the str(unicode) to be segmented.
            - mode: "default" or "search", "search" is for finer segmentation.
            - HMM: whether to use the Hidden Markov Model.
        """

# -*- coding: utf-8-*-
import jieba
sentence = 'python是世界上最好的编程语言'
ls = jieba.cut(sentence, cut_all=False)
# print(ls)
# print(list(ls))
# # <generator object Tokenizer.cut at 0x0000019F5E44DA98>
# print(type(ls))
# # <class 'generator'>
 
# # ①''.join
# ls_1 = ' '.join(ls)
# print(ls_1)
# # python 是 世界 上 最好 的 编程语言
# ②for循环遍历
# for i in ls:
#     print(i)
# '''
# python
# 是
# 世界
# 上
# 最好
# 的
# 编程语言
# '''
# # ③列表推导式
# ls_2 = [i for i in ls]
# print(ls_2)
# # ['python', '是', '世界', '上', '最好', '的', '编程语言']
# ls1 = jieba.lcut(sentence, cut_all=True)
# print(ls1)
ls2 = jieba.lcut(sentence)
print(ls2)
 
# ls3 = jieba.cut_for_search(sentence)
# print(ls3)
# # <generator object Tokenizer.cut_for_search at 0x00000199C7A3D9A8>
# print(list(ls3))
# # ['python', '是', '世界', '上', '最好', '的', '编程', '语言', '编程语言']
# ls4 = jieba.lcut_for_search(sentence)
# print(ls4)
# ['python', '是', '世界', '上', '最好', '的', '编程', '语言', '编程语言']
 
# ls5 = jieba.load_userdict('文案.txt')
# ls6 = jieba.lcut(sentence)
# print(ls6)
# ls5 = jieba.add_word('最好的')
# ls6 = jieba.lcut(sentence)
# print(ls6)
ls7 = jieba.del_word('世界')
ls8 = jieba.lcut(sentence)
print(ls8)