sklearn中的朴素贝叶斯模型及其应用

Posted 2021-01-22 1158z

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()

##高斯分布型
from sklearn import datasets
iris = datasets.load_iris()

from sklearn.naive_bayes import GaussianNB
clf = GaussianNB()  #构造
pred = clf.fit(iris.data,iris.target)   #拟合
y_pred = pred.predict(iris.data)  #预测

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

##伯努利型
from sklearn import datasets
iris = datasets.load_iris()

from sklearn.naive_bayes import BernoulliNB
clf = BernoulliNB()  #构造
pred = clf.fit(iris.data,iris.target)   #拟合
y_pred = pred.predict(iris.data)   #预测

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

##多项式型
from sklearn import datasets
iris = datasets.load_iris()

from sklearn.naive_bayes import MultinomialNB
clf = MultinomialNB()    #构造
pred = clf.fit(iris.data,iris.target)   #拟合
y_pred = pred.predict(iris.data)   #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。

##使用sklearn.model_selection.cross_val_score()对高斯分布型进行验证
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import cross_val_score
clf = GaussianNB()
scores = cross_val_score(clf,iris.data,iris.target,cv=10)
print("Accuracy:%.3f"%scores.mean())

##使用sklearn.model_selection.cross_val_score()对伯努利型进行验证
from sklearn.naive_bayes import BernoulliNB
from sklearn.model_selection import cross_val_score
clf= BernoulliNB()
scores = cross_val_score(clf,iris.data,iris.target,cv=10)
print("Accuracy:%.3f"%scores.mean())

##使用sklearn.model_selection.cross_val_score()对多项式型进行验证
from sklearn.naive_bayes import BernoulliNB
from sklearn.model_selection import cross_val_score
clf= MultinomialNB()
scores = cross_val_score(clf,iris.data,iris.target,cv=10)
print("Accuracy:%.3f"%scores.mean())