吴裕雄 python 机器学习——集成学习AdaBoost算法分类模型

import numpy as np
import matplotlib.pyplot as plt

from sklearn import datasets,ensemble
from sklearn.model_selection import train_test_split

def load_data_classification():
    '''
    加载用于分类问题的数据集
    '''
    # 使用 scikit-learn 自带的 digits 数据集
    digits=datasets.load_digits() 
    # 分层采样拆分成训练集和测试集，测试集大小为原始数据集大小的 1/4
    return train_test_split(digits.data,digits.target,test_size=0.25,random_state=0,stratify=digits.target) 

#集成学习AdaBoost算法分类模型
def test_AdaBoostClassifier(*data):
    '''
    测试 AdaBoostClassifier 的用法，绘制 AdaBoostClassifier 的预测性能随基础分类器数量的影响
    '''
    X_train,X_test,y_train,y_test=data
    clf=ensemble.AdaBoostClassifier(learning_rate=0.1)
    clf.fit(X_train,y_train)
    ## 绘图
    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    estimators_num=len(clf.estimators_)
    X=range(1,estimators_num+1)
    ax.plot(list(X),list(clf.staged_score(X_train,y_train)),label="Traing score")
    ax.plot(list(X),list(clf.staged_score(X_test,y_test)),label="Testing score")
    ax.set_xlabel("estimator num")
    ax.set_ylabel("score")
    ax.legend(loc="best")
    ax.set_title("AdaBoostClassifier")
    plt.show()
    
# 获取分类数据
X_train,X_test,y_train,y_test=load_data_classification() 
# 调用 test_AdaBoostClassifier
test_AdaBoostClassifier(X_train,X_test,y_train,y_test) 

def test_AdaBoostClassifier_base_classifier(*data):
    '''
    测试  AdaBoostClassifier 的预测性能随基础分类器数量和基础分类器的类型的影响
    '''
    from sklearn.naive_bayes import GaussianNB
    
    X_train,X_test,y_train,y_test=data
    fig=plt.figure()
    ax=fig.add_subplot(2,1,1)
    ########### 默认的个体分类器 #############
    clf=ensemble.AdaBoostClassifier(learning_rate=0.1)
    clf.fit(X_train,y_train)
    ## 绘图
    estimators_num=len(clf.estimators_)
    X=range(1,estimators_num+1)
    ax.plot(list(X),list(clf.staged_score(X_train,y_train)),label="Traing score")
    ax.plot(list(X),list(clf.staged_score(X_test,y_test)),label="Testing score")
    ax.set_xlabel("estimator num")
    ax.set_ylabel("score")
    ax.legend(loc="lower right")
    ax.set_ylim(0,1)
    ax.set_title("AdaBoostClassifier with Decision Tree")
    ####### Gaussian Naive Bayes 个体分类器 ########
    ax=fig.add_subplot(2,1,2)
    clf=ensemble.AdaBoostClassifier(learning_rate=0.1,base_estimator=GaussianNB())
    clf.fit(X_train,y_train)
    ## 绘图
    estimators_num=len(clf.estimators_)
    X=range(1,estimators_num+1)
    ax.plot(list(X),list(clf.staged_score(X_train,y_train)),label="Traing score")
    ax.plot(list(X),list(clf.staged_score(X_test,y_test)),label="Testing score")
    ax.set_xlabel("estimator num")
    ax.set_ylabel("score")
    ax.legend(loc="lower right")
    ax.set_ylim(0,1)
    ax.set_title("AdaBoostClassifier with Gaussian Naive Bayes")
    plt.show()
    
# 调用 test_AdaBoostClassifier_base_classifier
test_AdaBoostClassifier_base_classifier(X_train,X_test,y_train,y_test) 

def test_AdaBoostClassifier_learning_rate(*data):
    '''
    测试  AdaBoostClassifier 的预测性能随学习率的影响
    '''
    X_train,X_test,y_train,y_test=data
    learning_rates=np.linspace(0.01,1)
    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)
    traing_scores=[]
    testing_scores=[]
    for learning_rate in learning_rates:
        clf=ensemble.AdaBoostClassifier(learning_rate=learning_rate,n_estimators=500)
        clf.fit(X_train,y_train)
        traing_scores.append(clf.score(X_train,y_train))
        testing_scores.append(clf.score(X_test,y_test))
    ax.plot(learning_rates,traing_scores,label="Traing score")
    ax.plot(learning_rates,testing_scores,label="Testing score")
    ax.set_xlabel("learning rate")
    ax.set_ylabel("score")
    ax.legend(loc="best")
    ax.set_title("AdaBoostClassifier")
    plt.show()
        
# 调用 test_AdaBoostClassifier_learning_rate
test_AdaBoostClassifier_learning_rate(X_train,X_test,y_train,y_test)

def test_AdaBoostClassifier_algorithm(*data):
    '''
    测试  AdaBoostClassifier 的预测性能随学习率和 algorithm 参数的影响
    '''
    X_train,X_test,y_train,y_test=data
    algorithms=['SAMME.R','SAMME']
    fig=plt.figure()
    learning_rates=[0.05,0.1,0.5,0.9]
    for i,learning_rate in enumerate(learning_rates):
        ax=fig.add_subplot(2,2,i+1)
        for i ,algorithm in enumerate(algorithms):
            clf=ensemble.AdaBoostClassifier(learning_rate=learning_rate,algorithm=algorithm)
            clf.fit(X_train,y_train)
            ## 绘图
            estimators_num=len(clf.estimators_)
            X=range(1,estimators_num+1)
            ax.plot(list(X),list(clf.staged_score(X_train,y_train)),label="%s:Traing score"%algorithms[i])
            ax.plot(list(X),list(clf.staged_score(X_test,y_test)),label="%s:Testing score"%algorithms[i])
        ax.set_xlabel("estimator num")
        ax.set_ylabel("score")
        ax.legend(loc="lower right")
        ax.set_title("learing rate:%f"%learning_rate)
    fig.suptitle("AdaBoostClassifier")
    plt.show()
    
# 调用 test_AdaBoostClassifier_algorithm
test_AdaBoostClassifier_algorithm(X_train,X_test,y_train,y_test)