python之实战----朴素贝叶斯之手写数字位图

先导入数据，输出看看，在画画图吧

#-*- coding=utf-8 -*-
import numpy  as np
from sklearn import datasets,naive_bayes
from sklearn.model_selection  import train_test_split
import matplotlib.pyplot as plt 
def show_digits():
    '''
    输出数据集里的数字
    '''
    digits=datasets.load_digits()
    fig=plt.figure()
    print("vector from image 0:",digits.data[0])
    for i in range(25):
        ax=fig.add_subplot(5,5,i+1)
        ax.imshow(digits.images[i],cmap=plt.cm.gray_r,interpolation='nearest')#interpolation插值
    plt.show()

def load_data():
    iris=datasets.load_iris()
    X_train=iris.data
    y_train=iris.target
    return train_test_split(X_train,y_train, test_size=0.25,random_state=0,stratify=y_train)
 
if __name__=='__main__':
   show_digits()

输出结果：

PS E:\p> python test.py
('vector from image 0:', array([  0.,   0.,   5.,  13.,   9.,   1.,   0.,   0.,   0.,   0.,  13.,
        15.,  10.,  15.,   5.,   0.,   0.,   3.,  15.,   2.,   0.,  11.,
         8.,   0.,   0.,   4.,  12.,   0.,   0.,   8.,   8.,   0.,   0.,
         5.,   8.,   0.,   0.,   9.,   8.,   0.,   0.,   4.,  11.,   0.,
         1.,  12.,   7.,   0.,   0.,   2.,  14.,   5.,  10.,  12.,   0.,
         0.,   0.,   0.,   6.,  13.,  10.,   0.,   0.,   0.]))

1.特征的条件概率分布满足高斯分布，多项式分布，伯努利（二）

#-*- coding=utf-8 -*-
import numpy  as np
from sklearn import datasets,naive_bayes
from sklearn.model_selection  import train_test_split
import matplotlib.pyplot as plt 
"""
def show_digits():
    '''
    输出数据集里的数字
    '''
    digits=datasets.load_digits()
    fig=plt.figure()
    print("vector from image 0:",digits.data[0])
    for i in range(25):
        ax=fig.add_subplot(5,5,i+1)
        ax.imshow(digits.images[i],cmap=plt.cm.gray_r,interpolation='nearest')#interpolation插值
    plt.show()
"""
def load_data():
    iris=datasets.load_iris()
    X_train=iris.data
    y_train=iris.target
    return train_test_split(X_train,y_train, test_size=0.25,random_state=0,stratify=y_train)


def test_GaussianNB(*data):
    X_train,X_test,y_train,y_test=data
    cls=naive_bayes.GaussianNB()
    cls.fit(X_train,y_train)
    print('GaussianNB Train score :%.2f'%cls.score(X_train,y_train))
    print('GaussianNB Test score :%.2f'%cls.score(X_test,y_test))

def test_MultinomialNB(*data):
    X_train,X_test,y_train,y_test=data
    cls=naive_bayes.MultinomialNB()
    cls.fit(X_train,y_train)
    print('MultinomialNB Train score :%.2f'%cls.score(X_train,y_train))
    print('MultinomialNB Test score :%.2f'%cls.score(X_test,y_test))


def test_BernoulliNB(*data):
    X_train,X_test,y_train,y_test=data
    cls=naive_bayes.BernoulliNB()
    cls.fit(X_train,y_train)
    print('BernoulliNB Train score :%.2f'%cls.score(X_train,y_train))
    print('BernoulliNB Test score :%.2f'%cls.score(X_test,y_test))

if __name__=='__main__':
    X_train,X_test,y_train,y_test=load_data()
    test_GaussianNB(X_train,X_test,y_train,y_test)
    test_MultinomialNB(X_train,X_test,y_train,y_test)
    test_BernoulliNB(X_train,X_test,y_train,y_test)

其结果：

PS E:\p> python test.py
GaussianNB Train score :0.95
GaussianNB Test score :0.97
MultinomialNB Train score :0.96
MultinomialNB Test score :1.00
BernoulliNB Train score :0.34
BernoulliNB Test score :0.32

换一个数据集就不一样了

def load_data():
    digits=datasets.load_digits()
    X_train=digits.data
    y_train=digits.target
    return train_test_split(X_train,y_train, test_size=0.25,random_state=0,stratify=y_train)

对应输出

PS E:\p> python test.py
GaussianNB Train score :0.85
GaussianNB Test score :0.84
MultinomialNB Train score :0.91
MultinomialNB Test score :0.90
BernoulliNB Train score :0.87
BernoulliNB Test score :0.87