朴素贝叶斯应用：垃圾邮件分类(更新)

#读取数据集
import csv
file_path=r'jiangnan.txt'
sms=open(file_path,'r',encoding='utf-8')
sms_data=[]
sms_label=[]
text=csv.reader(sms,delimiter='\t')
text

#预处理
def preprocessing(text):
    #text=text.decode("utf-8")
    tokens=[word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]   #进行分词
    stops=stopwords.words('to')                        #去掉停用词
    tokens=[token for token in tokens if token not in stops]
 
    tokens=[token.lower() for token in tokens if len(token)>=3]
    lmtzr=WordNetLemmatizer()           #词性还原
    tokens=[lmtzr.lemmatize(token) for  token in tokens]
    preprocessed_text=' '.join(tokens)
    return preprocessed_text 

#将其向量化
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(sms_data,sms_label,test_size=0.3,random_state=0,stratify=sms_label)

from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer=TfidfVectorizer(min_df=2,ngram_range=(1,2),stop_words='english',strip_accents='unicode',norm='12')
X_train=vectorizer.fit_transform(x_train)
X_test=vectorizer.transform(x_test)

#朴素贝叶斯
from sklearn.naive_bayes import MultinomialNB
clf=MultinomialNB().fit(x_train,y_train)

#测试模型
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report


cm=confusion_matrix(y_test.y_nb_pred)
print(cm)

cr=classification_report(y_test.y_nb_pred)
print(cr)