朴素贝叶斯应用：垃圾邮件分类

import csv
file_path =r‘E:\jupyter\SMSSpamCollectionjsn.txt‘#原始的邮件
sms=open(file_path,‘r‘,encoding=‘utf-8‘)
csv_reader=csv.reader(sms,delimiter=‘\t‘)
sms_data=[]#邮件的内容
sms_label=[]#邮件的类别
for line in csv_reader:
    sms_label.append(line[0])
    sms_data.append(line[1])
sms.close()

#对数据预处理
sms_data1 = []#存放处理过的邮件
for line in sms_data:#对邮件的内容进行处理
    for k in line:
        if k.isalpha() is False:
            # 不是字母，发生替换操作:
            newString = line.replace(k," ")
    dataList = newString.split(" ")
    sms_data1.append(dataList)

#去掉长度小于3的词和没有语义的词
sms_data2= []
for line in sms_data:
    dataList = []
    for i in line:
        if i != ‘‘ and len(i) > 3 and i.isalpha():
            dataList.append(i)
    dataString = ‘ ‘.join(dataList)
    sms_data.append(dataString)
sms_data =sms_data2

##训练集与测试集：将先验数据按一定比例进行拆分
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(sms_data2,sms_label,test_size=0.3,random_state=0,stratify=sms_label)
 
#提取数据特征，将文本解析为词向量
from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer=TfidfVectorizer(min_df=2,ngram_range=(1,2),stop_words=‘english‘,strip_accents=‘unicode‘,norm=‘l2‘)
X_train=vectorizer.fit_transform(x_train)
X_test=vectorizer.transform(x_test)


#朴素贝叶斯分类器
from sklearn.navie_bayes import MultinomialNB
clf= MultinomialNB().fit(X_train,y_train)
y_nb_pred=clf.predict(X_test)


#分类结果显示
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
print(y_nb_pred.shape,y_nb_pred)#x_test预测结果
print(‘nb_confusion_matrix:‘)
cm=confusion_matrix(y_test,y_nb_pred)#混淆矩阵
print(cm)
print(‘nb_classification_report:‘)
cr=classification_report(y_test,y_nb_pred)#主要分类指标的文本报告
print(cr)