import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets,naive_bayes
from sklearn.model_selection import train_test_split
# 加載 scikit-learn 自帶的 digits 資料集
def load_data():
'''
加載用于分類問題的資料集。這裡使用 scikit-learn 自帶的 digits 資料集
'''
digits=datasets.load_digits()
return train_test_split(digits.data,digits.target,test_size=0.25,random_state=0,stratify=digits.target)
#伯努利貝葉斯BernoulliNB模型
def test_BernoulliNB(*data):
X_train,X_test,y_train,y_test=data
cls=naive_bayes.BernoulliNB()
cls.fit(X_train,y_train)
print('Training Score: %.2f' % cls.score(X_train,y_train))
print('Testing Score: %.2f' % cls.score(X_test, y_test))
# 産生用于分類問題的資料集
X_train,X_test,y_train,y_test=load_data()
# 調用 test_BernoulliNB
test_BernoulliNB(X_train,X_test,y_train,y_test)
![](https://img.laitimes.com/img/_0nNw4CM6IyYiwiM6ICdiwiIn5GcuADM5YDM0ATN00iN1MTO1AzM5ADMzQDM5EDMy0COykDMyATMvwFNwkTMwIzLchjM5AjMwEzLcd2bsJ2Lc12bj5ycn9Gbi52YugTMwIzZtl2Lc9CX6MHc0RHaiojIsJye.png)
def test_BernoulliNB_alpha(*data):
'''
測試 BernoulliNB 的預測性能随 alpha 參數的影響
'''
X_train,X_test,y_train,y_test=data
alphas=np.logspace(-2,5,num=200)
train_scores=[]
test_scores=[]
for alpha in alphas:
cls=naive_bayes.BernoulliNB(alpha=alpha)
cls.fit(X_train,y_train)
train_scores.append(cls.score(X_train,y_train))
test_scores.append(cls.score(X_test, y_test))
## 繪圖
fig=plt.figure()
ax=fig.add_subplot(1,1,1)
ax.plot(alphas,train_scores,label="Training Score")
ax.plot(alphas,test_scores,label="Testing Score")
ax.set_xlabel(r"$\alpha$")
ax.set_ylabel("score")
ax.set_ylim(0,1.0)
ax.set_title("BernoulliNB")
ax.set_xscale("log")
ax.legend(loc="best")
plt.show()
# 調用 test_BernoulliNB_alpha
test_BernoulliNB_alpha(X_train,X_test,y_train,y_test)
def test_BernoulliNB_binarize(*data):
'''
測試 BernoulliNB 的預測性能随 binarize 參數的影響
'''
X_train,X_test,y_train,y_test=data
min_x=min(np.min(X_train.ravel()),np.min(X_test.ravel()))-0.1
max_x=max(np.max(X_train.ravel()),np.max(X_test.ravel()))+0.1
binarizes=np.linspace(min_x,max_x,endpoint=True,num=100)
train_scores=[]
test_scores=[]
for binarize in binarizes:
cls=naive_bayes.BernoulliNB(binarize=binarize)
cls.fit(X_train,y_train)
train_scores.append(cls.score(X_train,y_train))
test_scores.append(cls.score(X_test, y_test))
## 繪圖
fig=plt.figure()
ax=fig.add_subplot(1,1,1)
ax.plot(binarizes,train_scores,label="Training Score")
ax.plot(binarizes,test_scores,label="Testing Score")
ax.set_xlabel("binarize")
ax.set_ylabel("score")
ax.set_ylim(0,1.0)
ax.set_xlim(min_x-1,max_x+1)
ax.set_title("BernoulliNB")
ax.legend(loc="best")
plt.show()
# 調用 test_BernoulliNB_binarize
test_BernoulliNB_binarize(X_train,X_test,y_train,y_test)
轉載于:https://www.cnblogs.com/tszr/p/10794239.html