11.22

import numpy as np
from sklearn.naive_bayes import GaussianNB
from sklearn.datasets import load_iris
iris=load_iris()
NB_model=GaussianNB()
pre=NB_model.fit(iris.data,iris.target)
Y_pre=pre.predict(iris.data)
print(iris.data.shape[0],(iris.target!=Y_pre).sum())
from sklearn.naive_bayes import BernoulliNB
NB_model=BernoulliNB()
pre=NB_model.fit(iris.data,iris.target)
Y_pre=pre.predict(iris.data)
print(iris.data.shape[0],(iris.target!=Y_pre).sum())
from sklearn.naive_bayes import MultinomialNB
NB_model=MultinomialNB()
pre=NB_model.fit(iris.data,iris.target)
Y_pre=pre.predict(iris.data)
print(iris.data.shape[0],(iris.target!=Y_pre).sum()

　　

from sklearn.model_selection import cross_val_score
NB_model=GaussianNB()
sco=cross_val_score(NB_model,iris.data,iris.target,cv=10)
print("准确率:%.3f"%sco.mean())
from sklearn.model_selection import cross_val_score
NB_model=BernoulliNB()
sco=cross_val_score(NB_model,iris.data,iris.target,cv=10)
print("准确率:%.3f"%sco.mean())
from sklearn.model_selection import cross_val_score
NB_model=MultinomialNB()
sco=cross_val_score(NB_model,iris.data,iris.target,cv=10)
print("准确率:%.3f"%sco.mean())

　　

import csv
file_path=r'E:\jupyter\SMSSpamCollectionjsn.txt'
sms=open(file_path,'r',encoding='utf-8')
sms_data=[]#邮件的内容
sms_label=[]#邮件的类别
csv_reader=csv.reader(sms,delimiter='\t')
for line in csv_reader:
    sms_label.append(line[0])
    sms_data.append(line[1])
sms.close()
sms_data=str(sms_data)
sms_data=sms_data.lower
sms_data=sms_data.split()
sms_data1=[]
i=0
for i in sms_data:#去掉长度小于3的单词
    if len(i)>4:
        sms_data1.append(i)
        continue