#151txt到155txt为测试邮件def predicttxtFile本调用getWordFromFile获取所有单词words getWordFromFilerCUserscloudDesktop5email_ds+txtFile本计算toplords在测试螂件中的词颜向量currentVctor array list maplambda xwordscount xtopWords本调用训练

def predict(txtFile): # 调用getWordFromFile获取所有单词 words = getWordFromFile(r'C:/Users/cloud/Desktop/5/email_ds' + txtFile)

# 计算topWords在测试邮件中的词频向量
currentVector = [words.count(x) for x in topWords]

# 调用训练好的模型进行预测
result = model.predict(np.array(currentVector).reshape(1, -1))

# 返回的是一个二分类的结果，predict_proba返回的是对于预测为各个类别的概率
print(model.predict_proba(np.array(currentVector).reshape(1, -1)))

return '垃圾邮件' if result == 1 else '正常邮件'

for mail in ('%d.txt' % i for i in range(151, 156)): print(mail, predict(mail), sep=':')