作业11

#1.使用朴素贝叶斯模型对iris数据集进行花分类
#尝试使用3种不同类型的朴素贝叶斯：
#高斯分布型,多项式型,伯努利型

#GaussianNB
from sklearn import datasets
iris = datasets.load_iris()

from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()  #建立模型
pred=gnb.fit(iris.data,iris.target) #模型训练
y_pred=pred.predict(iris.data) #分类预测

print(iris.data.shape[0],(iris.target !=y_pred).sum())



#BernoulliNB
from sklearn import datasets
iris = datasets.load_iris()

from sklearn.naive_bayes import BernoulliNB
gnb = BernoulliNB()  #建立模型
gnb.fit(iris.data,iris.target) #模型训练
y_pred=gnb.predict(iris.data) #分类预测

print(iris.data.shape[0],(iris.target !=y_pred).sum())




#MultinomialNB
from sklearn import datasets
iris = datasets.load_iris()

from sklearn.naive_bayes import MultinomialNB
gnb = MultinomialNB()  #建立模型
pred=gnb.fit(iris.data,iris.target) #模型训练
y_pred=pred.predict(iris.data) #分类预测

print(iris.data.shape[0],(iris.target !=y_pred).sum())





#2.使用sklearn.model_selection.cross_val_score()，对模型进行验证。

#检测模型的好坏BernoulliNB
from sklearn.naive_bayes import BernoulliNB
from sklearn.model_selection import cross_val_score
gnb = BernoulliNB()
scores=cross_val_score(gnb,iris.data,iris.target,cv=10)
print("Accuray:%.3f"%scores.mean())



#检测模型的好坏MultinomialNB
from sklearn.naive_bayes import MultinomialNB
from sklearn.model_selection import cross_val_score
gnb = MultinomialNB()
scores=cross_val_score(gnb,iris.data,iris.target,cv=10)
print("Accuray:%.3f"%scores.mean())



#检测模型的好坏GaussianNB
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import cross_val_score
gnb = GaussianNB()
scores=cross_val_score(gnb,iris.data,iris.target,cv=10)
print("Accuray:%.3f"%scores.mean())

import csv
file_path=r‘C:\Users\pc\Desktop\SMSSpamCollectionjsn.txt‘
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.close()
print(len(sms_label))
sms_label