吳裕雄 python 機器學習——多項式貝葉斯分類器MultinomialNB模型

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 數據集
def load_data():
    '''
    加載用於分類問題的數據集。這里使用 scikit-learn 自帶的 digits 數據集
    '''
    digits=datasets.load_digits()
    return train_test_split(digits.data,digits.target,test_size=0.25,random_state=0,stratify=digits.target)

#多項式貝葉斯分類器MultinomialNB模型
def test_MultinomialNB(*data):
    X_train,X_test,y_train,y_test=data
    cls=naive_bayes.MultinomialNB()
    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))
    
# 產生用於分類問題的數據集
X_train,X_test,y_train,y_test=load_data()
# 調用 test_GaussianNB    
test_MultinomialNB(X_train,X_test,y_train,y_test)

def test_MultinomialNB_alpha(*data):
    '''
    測試 MultinomialNB 的預測性能隨 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.MultinomialNB(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("MultinomialNB")
    ax.set_xscale("log")
    plt.show()
    
# 調用 test_MultinomialNB_alpha    
test_MultinomialNB_alpha(X_train,X_test,y_train,y_test)