sklearn中的朴素贝叶斯模型及其应用

1、（1）多项式

from sklearn.datasets import load_iris

iris = load_iris()

from sklearn.naive_bayes import GaussianNB#贝叶斯

gnb = GaussianNB()

pred = gnb.fit(iris.data,iris.target)

y_pred = pred.predict(iris.data)#预测

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

from sklearn.naive_bayes import BernoulliNB

bnl = BernoulliNB()

pred = bnl.fit(iris.data,iris.target)#g构造模型

y_pred = pred.predict(iris.data)#预测

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

（2）高斯分布型

from sklearn.naive_bayes import GaussianNB

gnb1=GaussianNB()#构造建立模型

pred=gnb1.fit(iris.data,iris.target)#模型训练，拟合

y_pred=gnb1.predict(iris.data)#分类预测

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

scores=cross_val_score(gnb1,iris.data,iris.target,cv=10)

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

print(y_pred)

（3）伯努利型

from sklearn.naive_bayes import BernoulliNB

gnb2=BernoulliNB()#构造

pred=gnb2.fit(iris.data,iris.target)#模型训练，拟合

y_pred=gnb2.predict(iris.data)#分类预测

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

scores=cross_val_score(gnb2,iris.data,iris.target,cv=10)

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

print(y_pred)

 

2、

from sklearn.datasets import load_iris

iris = load_iris()

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())

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

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

3、

import csv

file_path=r'D:\1\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)#将列表转化为字符串

sms_data=sms_data.lower()#对大小写进行处理

sms_data=sms_data.split()#变成列表的形式

sms_data1=[]#存放处理后的内容

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