第11次作业 sklearn中的朴素贝叶斯模型及其应用

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

from sklearn import datasets
iris=datasets.load_iris()
from sklearn.naive_bayes import GaussianNB #高斯分布型
gnb=GaussianNB()
pred=gnb.fit(iris.data,iris.target)
y_pred=gnb.predict(iris.data)
print(iris.data.shape[0],(iris.target != y_pred).sum())

from sklearn import datasets
iris=datasets.load_iris()
from sklearn.naive_bayes import BernoulliNB #伯努利型
gnb=BernoulliNB()
pred=gnb.fit(iris.data,iris.target)
y_pred=gnb.predict(iris.data)
print(iris.data.shape[0],(iris.target != y_pred).sum())

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

from sklearn.naive_bayes import GaussianNB #高斯分布型
from sklearn.model_selection import cross_val_score
gnb = GaussianNB()
acores = cross_val_score(gnb, iris.data, iris.target, cv=10)
print("Accuracy:%.3f"%acores.mean())

from sklearn.naive_bayes import BernoulliNB #伯努利型
from sklearn.model_selection import cross_val_score
gnb = BernoulliNB()
acores = cross_val_score(gnb, iris.data, iris.target, cv=10)
print("Accuracy:%.3f"%acores.mean())

from sklearn.naive_bayes import MultinomialNB #多项式型
from sklearn.model_selection import cross_val_score
gnb = MultinomialNB()
acores = cross_val_score(gnb, iris.data, iris.target, cv=10)
print("Accuracy:%.3f"%acores.mean())

3.垃圾邮件分类

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