• 機器學習之伯努利貝葉斯分類器bernoulliNB

# -*- coding: utf-8 -*-
"""
Created on Sun Nov 25 11:45:17 2018

@author: muli
"""

from sklearn import naive_bayes,datasets,cross_validation
import  numpy as np
import  matplotlib.pyplot as plt


def load_data():
    '''
    載入用於分類問題的資料集。這裡使用 scikit-learn 自帶的 digits 資料集

    :return: 一個元組，用於分類問題。元組元素依次為：訓練樣本集、測試樣本集、訓練樣本集對應的標記、測試樣本集對應的標記
    '''
    # 載入 scikit-learn 自帶的 digits 資料集
    digits=datasets.load_digits() 
    #分層取樣拆分成訓練集和測試集，測試集大小為原始資料集大小的 1/4
    return cross_validation.train_test_split(digits.data,digits.target,
		test_size=0.25,random_state=0,stratify=digits.target)


def test_BernoulliNB(*data):
    '''
    測試 BernoulliNB 的用法

    :param data: 可變引數。它是一個元組，這裡要求其元素依次為：訓練樣本集、測試樣本集、訓練樣本的標記、測試樣本的標記
    :return: None
    '''
    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))


def test_BernoulliNB_alpha(*data):
    '''
    測試 BernoulliNB 的預測效能隨 alpha 引數的影響

    :param data: 可變引數。它是一個元組，這裡要求其元素依次為：訓練樣本集、測試樣本集、訓練樣本的標記、測試樣本的標記
    :return: None
    '''
    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()


def test_BernoulliNB_binarize(*data):
    '''
    測試 BernoulliNB 的預測效能隨 binarize 引數的影響

    :param data: 可變引數。它是一個元組，這裡要求其元素依次為：訓練樣本集、測試樣本集、訓練樣本的標記、測試樣本的標記
    :return: None
    '''
    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()



if __name__=='__main__':
    # 產生用於分類問題的資料集
    X_train,X_test,y_train,y_test=load_data() 
    # 呼叫 test_BernoulliNB
#    test_BernoulliNB(X_train,X_test,y_train,y_test) 
    # 呼叫 test_BernoulliNB_alpha
#    test_BernoulliNB_alpha(X_train,X_test,y_train,y_test) 
    # 呼叫 test_BernoulliNB_binarize
    test_BernoulliNB_binarize(X_train,X_test,y_train,y_test)