sklearn中的朴素贝叶斯模型及其应用

from sklearn import datasets
iris=datasets.load_iris()

#高斯分布型
from sklearn.naive_bayes import GaussianNB
gnb=GaussianNB()
pred=gnb.fit(iris.data,iris.target)
y_pred=pred.predict(iris.data)

print(‘高斯分布型:‘,iris.data.shape[0],(iris.target!=y_pred).sum())

#伯努利型
from sklearn.naive_bayes import BernoulliNB
bnb=BernoulliNB()
pred=bnb.fit(iris.data,iris.target)
y_pred=pred.predict(iris.data)

print(‘伯努利型:‘,iris.data.shape[0],(iris.target!=y_pred).sum())



#多项式型
from sklearn.naive_bayes import MultinomialNB
mnb=MultinomialNB()
pred=mnb.fit(iris.data,iris.target)
y_pred=pred.predict(iris.data)

print(‘多项式型:‘,iris.data.shape[0],(iris.target!=y_pred).sum())

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("Accuracy:%.3f"%scores.mean())
print(scores)


from sklearn.naive_bayes import BernoulliNB
from sklearn.model_selection import cross_val_score
bnb1=BernoulliNB()
scores=cross_val_score(bnb1,iris.data,iris.target,cv=10)
print("Accuracy:%.3f"%scores.mean())


from sklearn.naive_bayes import MultinomialNB
from sklearn.model_selection import cross_val_score
mnb1=MultinomialNB()
scores=cross_val_score(mnb1,iris.data,iris.target,cv=10)
print("Accuracy:%.3f"%scores.mean())

import csv
file_path=r‘G:\数据挖掘算法\11.26\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_data.append(line[1])
sms.close()
print("邮件总数:",len(sms_label))
print(sms_label)
print(sms_data)