文本分类例子 下载 nltk 包方法

import nltk
import ssl
try:
     _create_unverified_https_context = ssl._create_unverified_context
except AttributeError:
        pass
else:
    ssl._create_default_https_context = _create_unverified_https_context

nltk.download()

再输入需要的包

 

#一个完整文本分类流程

#using NLTK library, we can do lot of text preprocesing
import nltk
from nltk.tokenize import word_tokenize
#function to split text into word
tokens = word_tokenize("The quick brown fox jumps over the lazy dog")
nltk.download('stopwords')
print(tokens)


from nltk.corpus import stopwords
stop_words = set(stopwords.words(‘english’))
tokens = [w for w in tokens if not w in stop_words]
print(tokens)


#NLTK provides several stemmer interfaces like Porter stemmer, #Lancaster Stemmer, Snowball Stemmer
from nltk.stem.porter import PorterStemmer
porter = PorterStemmer()
stems &