file_path=r‘D:\PycharmProjects\data\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]))#对每封邮件做预处理
sms.close()

print(sms_label)
print(sms_data)

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

print(nltk.__doc__)

def get_wordnet_pos(treebank_tag):
    if treebank_tag.startswith(‘J‘):
        return nltk.corpus.wordnet.ADJ
    elif treebank_tag.startswith(‘V‘):
        return nltk.corpus.wordnet.VERB
    elif treebank_tag.startswith(‘N‘):
        return nltk.corpus.wordnet.NOUN
    elif treebank_tag.startswith(‘R‘):
        return nltk.corpus.wordnet.ADV
    else:
        return nltk.corpus.wordnet.NOUN

#预处理
def preprocessing(text):
    tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]#分词
    stops = stopwords.words("english")#停用词
    tokens = [token for token in tokens if token not in stops]#去掉停用词
    tokens = [token.lower() for token in tokens if len(token) >= 3]#将大写字母变为小写

    tag=nltk.pos_tag(tokens)#词性
    lmtzr = WordNetLemmatizer()
    tokens = [lmtzr.lemmatize(token,pos=get_wordnet_pos(tag[i][1])) for i,token in enumerate(tokens)]
    preprocessed_text = ‘‘.join(tokens)
    return preprocessed_text

# 按0.8:0.2比例分为训练集和测试集
import numpy as np
from sklearn.model_selection import train_test_split

sms_data = np.array(sms_data)
sms_label = np.array(sms_label)
x_train, x_test, y_train, y_test = train_test_split(sms_data, sms_label, test_size=0.2, random_state=0,
                                                    stratify=sms_label)
print(len(sms_data),len(x_train),len(x_test))
print(x_train)