python【】词性标注横排

>>> import re
>>> import jieba.posseg as pseg
>>> f = open('E:/序言.txt','r').read()
>>> words = pseg.cut(f)
>>> l = []
>>> m = []

>>> for w in words:
...   x = w.word
...   y = w.flag
...   l.append((x))
...   m.append((y))
...
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\oil\AppData\Local\Temp\jieba.cache
Loading model cost 0.893 seconds.
Prefix dict has been built succesfully.
>>> print(l)
['美国版', '序言', '\n', '\n', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '-', '\n', '\n', '\u3000', '\u3000', ' 目前', '已经', '有', '不少', '部', '哲学史', '了', ',', '我', '的', '目的', '并', '不是', '要', '仅仅', '在', '它们', '之中', '再', '加上', '一部', '。', '我', '的', '目的', '是', '要', '揭示', ',', '哲学', '乃是', '社会', '生活', '与', '政治', '生活', '的', '一个', '组成部分', ':', '它', '并', '不是', '卓越', '的', '个人', '所', '做出', '的', '孤立', '的', '思考', ',', '而是', '曾经', '有', '各种', '体系', '盛行', '过', '的', '各种', '社会', '性格', '的', '产物', '与', '成因', '。', '这', '一', '目的', '就', '要求', '我们', '对于', '一般', '历史',

----------------------------------------------

>>> for line in lines:
...   words = pseg.cut(line)
...   print(words)
...
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>
<generator object cut at 0x0000019655658048>
<generator object cut at 0x00000196556580A0>

>>>

--------------------------------------------

>>> import jieba.posseg as pseg
>>> import re
>>> l = []
>>> m = []
>>> f = open("E:/序言.txt",'r').read()
>>> c = "。"
>>> lines = f.split(c)
>>> s = open("E:/序言++.txt",'a+')
>>> for line in lines:
...   words = pseg.cut(line)
...   for w in words:
...     x = w.word
...     y = w.flag
...     print(x,y,file = s)
...
Building prefix dict from the default dictionary ...
Dumping model to file cache C:\Users\oil\AppData\Local\Temp\jieba.cache
Loading model cost 1.096 seconds.
Prefix dict has been built succesfully.
>>> s.close()
>>>

难道要把txt分割嘛?,越来月麻烦了 = =,暂时没有解决 , 也九先放一下了 ,这样的词性标注就对我来说一点用都没有了= =暂时

阅读更多
想对作者说点什么?

博主推荐

换一批

没有更多推荐了,返回首页