能让你轻松的实现自然语言处理的5个Python库

text = "Hello there, how are you doing today? The weather is great today. python is awsome"

##sentece tokenize (Separated by sentence)
['Hello there, how are you doing today?', 'The weather is great today.', 'python is awsome']
##word tokenizer (Separated by words)
['Hello', 'there', ',', 'how', 'are', 'you', 'doing', 'today', '?', 'The', 'weather', 'is', 'great', 'today', '.','python', 'is', 'awsome']

text = 'An sincerity so extremity he additions.'
--------------------------------
('An', 'DT'), ('sincerity', 'NN'), ('so', 'RB'), ('extremity', 'NN'), ('he', 'PRP'), ('additions', 'VBZ')]

sent1 = he is a good boy
sent2 = she is a good girl
            |
            |
        girl good boy   
sent1    0    1    1     
sent2    1    0    1

import nltk
#nltk.download('punkt')
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer
import re
ps = PorterStemmer()
text = 'Hello there,how are you doing today? I am Learning Python.'
text = re.sub("[^a-zA-Z0-9]"," ",text)
text = word_tokenize(text)
text_with_no_stopwords = [ps.stem(word) for word in text if word not in stopwords.words('english')]
text = " ".join(text_with_no_stopwords) 
text
-----------------------------------------------OUTPUT------------------------------------
'hello today I learn python'

import spacy
nlp = spacy.load('en_core_web_sm')
text = "I am Learning Python Nowdays"
text2 = nlp(text)
for token in text2:
  print(token,token.idx)
------------------------------OUTPUT-----------------------
I 0
am 2
Learning 5
Python 14
Nowdays 21