Functions and usage of snownlp Library

Catalog

1 Chinese word segmentation

2 Part of speech tagging

3 Emotional score

4 Convert Pinyin

5 front n Key words

6 front n The key ( center ) sentence

7 TF value

8 IDF value

9 Transformation of traditional and simplified style

---

Import library first

from snownlp import SnowNLP

s = SnowNLP(' The words are too small , And the paper is not good , It's a little dark , But the content should be good . There is still a little distance from the expectation ...')

1 Chinese word segmentation

print(s.words)

2 Part of speech tagging

print(list(s.tags))

3 Emotional score

print(s.sentiments)

4 Convert Pinyin

print(s.pinyin)

5 front n Key words

print(s.keywords(4))

6 front n The key ( center ) sentence

print(s.summary(1))

7 TF value

print(s.tf)

8 IDF value

print(s.idf)

9 Transformation of traditional and simplified style

print(s.han)

10  Split sentences

print(s.sentences)

Only non English statement separators can be used to separate statements , When Chinese and English separators are mixed, the effect is not good =^=

It can be used re modular Specify at one time Multiple Chinese English separator

import re

t = ' The words are too small , And the paper is not good , It's a little dark , But the content should be good . There is still a little distance from the expectation ...'

t_list = re.split('[,.;!,.;！]', t)

for i in range(t_list.count('')):    # Remove empty string elements 
    t_list.remove('')

print(t_list)

 

---

 

Flag： I want to be a day watcher ：）