python中文分词库jieba使用方法详解

import jieba
sentence = '我爱自然语言处理'
# 创建【Tokenizer.cut 生成器】对象
generator = jieba.cut(sentence)
# 遍历生成器，打印分词结果
words = '/'.join(generator)
print(words)

import jieba
print(jieba.lcut('我爱南海中学'))

import jieba
sentence = '订单数据分析'
print('精准模式：', jieba.lcut(sentence))
print('全模式：', jieba.lcut(sentence, cut_all=True))
print('搜索引擎模式：', jieba.lcut_for_search(sentence))

jieba.posseg
import jieba.posseg as jp
sentence = '我爱Python数据分析'
posseg = jp.cut(sentence)
for i in posseg:
 print(i.__dict__)
 # print(i.word, i.flag)

{‘word': ‘我', ‘flag': ‘r'}
{‘word': ‘爱', ‘flag': ‘v'}
{‘word': ‘Python', ‘flag': ‘eng'}
{‘word': ‘数据分析', ‘flag': ‘l'}

jieba.tokenize(sentence)
import jieba
sentence = '订单数据分析'
generator = jieba.tokenize(sentence)
for position in generator:
 print(position)

(‘订单', 0, 2)
(‘数据分析', 2, 6)

import jieba, os, pandas as pd
# 词典所在位置
print(jieba.__file__)
jieba_dict = os.path.dirname(jieba.__file__) + r'\dict.txt'
# 读取字典
df = pd.read_table(jieba_dict, sep=' ', header=None)[[0, 2]]
print(df.head())
# 转字典
dt = dict(df.values)
print(dt.get('暨南大学'))

import jieba
sentence = '天长地久有时尽，此恨绵绵无绝期'
# 添词
jieba.add_word('时尽', 999, 'nz')
print('添加【时尽】：', jieba.lcut(sentence))
# 删词
jieba.del_word('时尽')
print('删除【时尽】：', jieba.lcut(sentence))

import os, jieba
# 创建自定义字典
my_dict = 'my_dict.txt'
with open(my_dict, 'w', encoding='utf-8') as f:
 f.write('慕容紫英 9 nr\n云天河 9 nr\n天河剑 9 nz')
# 加载字典进行测试
sentence = '慕容紫英为云天河打造了天河剑'
print('加载前：', jieba.lcut(sentence))
jieba.load_userdict(my_dict)
print('加载后：', jieba.lcut(sentence))
os.remove(my_dict)

import jieba
sentence = '上穷碧落下黄泉，两处茫茫皆不见'
print('修正前：', ' | '.join(jieba.cut(sentence)))
jieba.suggest_freq(('落', '下'), True)
print('修正后：', ' | '.join(jieba.cut(sentence)))

import jieba
sentence = '中心小学放假'
DAG = jieba.get_DAG(sentence)
print(DAG)
route = {}
jieba.calc(sentence, DAG, route)
print(route)

import jieba, re
sentence = 'Blade Master疾风刺杀Archmage'
jieba.add_word('Blade Master') # 添词
print('修改前：', jieba.lcut(sentence))
jieba.re_han_default = re.compile('(.+)', re.U) # 修改格式
print('修改后：', jieba.lcut(sentence))

import jieba.analyse as ja, jieba
text = '柳梦璃施法破解了狐仙的法术'
jieba.add_word('柳梦璃', tag='nr')
keywords1 = ja.extract_tags(text, allowPOS=('n', 'nr', 'ns', 'nt', 'nz'))
print('基于TF-IDF：', keywords1)
keywords2 = ja.textrank(text, allowPOS=('n', 'nr', 'ns', 'nt', 'nz'))
print('基于TextRank：', keywords2)

import jieba
text = '柳梦璃解梦C法'
print(jieba.lcut(text, HMM=False)) # ['柳', '梦', '璃', '解梦', 'C', '法']
print(jieba.lcut(text)) # ['柳梦璃', '解梦', 'C', '法']
jieba.finalseg.emit_P['B']['C'] = -1e-9 # begin
print(jieba.lcut(text)) # ['柳梦璃', '解梦', 'C', '法']
jieba.finalseg.emit_P['M']['梦'] = -100 # middle
print(jieba.lcut(text)) # ['柳', '梦璃', '解梦', 'C', '法']
jieba.finalseg.emit_P['S']['梦'] = -.1 # single
print(jieba.lcut(text)) # ['柳', '梦', '璃', '解梦', 'C', '法']
jieba.finalseg.emit_P['E']['梦'] = -.01 # end
print(jieba.lcut(text)) # ['柳梦', '璃', '解梦', 'C', '法']
jieba.del_word('柳梦') # Force_Split_Words
print(jieba.lcut(text)) # ['柳', '梦', '璃', '解梦', 'C', '法']