import csv
import nltk
from mistune import preprocessing
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer

def preprocessing(text):
    # 分词
    fenge = []
    for sent in nltk.sent_tokenize(text):
        for word in nltk.word_tokenize(sent):
            fenge.append(word)
    # 停用词
    stops = stopwords.words("english")
    tingyong = [i for i in fenge if i not in stops]
    # 磁性标注
    nltk.pos_tag(tingyong)
    # 磁性还原
    lemmatizer = WordNetLemmatizer()
    huanyuan = []
    for i in tingyong:
        huanyuan.append(lemmatizer.lemmatize(i, pos=‘v‘))
    for i in tingyong:
        huanyuan.append(lemmatizer.lemmatize(i, pos=‘a‘))
    for i in tingyong:
        huanyuan.append(lemmatizer.lemmatize(i, pos=‘n‘))

    return huanyuan

file_path=r‘C:\Users\we\Desktop\SMSSpamCollection‘
sms=open(file_path,‘r‘,encoding=‘utf-8‘)
sms_data=[]
sms_label=[]
csv_reader=csv.reader(sms,delimiter=‘\t‘)
for line in csv_reader:
    sms_label.append(line[0])
    sms_data.append(preprocessing(line[1]))
sms.close()

print("分词标注停用还原后的数据",sms_data[1:10])
print("邮件分类2",sms_label)