python 集成学习 AdaBoostClassifier，AdaBoostRegressor模型

运行环境：win10 64位 py 3.6 pycharm 2018.1.1

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

#加载分类数据集
def load_data_classification():
    digits = datasets.load_digits()
    return cross_validation.train_test_split(digits.data,digits.target,test_size=0.25,random_state=0)

def test_AdaBoostClassifier(*data):
    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()

X_train,X_test,y_train,y_test = load_data_classification()
test_AdaBoostClassifier(X_train,X_test,y_train,y_test)

####不同类型个体分类器的影响
def test_AdaBoostClassifier_Base_classifier(*data):
    X_train, X_test, y_train, y_test = data
    ##绘图
    fig = plt.figure()
    ax = fig.add_subplot(2,1,1)
    ###默认的分类器
    clf = ensemble.AdaBoostClassifier(learning_rate=0.1)
    clf.fit(X_train,y_train)
    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")
    ###默认的贝叶斯分类器
    ax = fig.add_subplot(2,1,2)
    clf = ensemble.AdaBoostClassifier(learning_rate=0.1,base_estimator=naive_bayes.GaussianNB())
    clf.fit(X_train, y_train)
    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 GaussianNB")
    plt.show()

X_train,X_test,y_train,y_test = load_data_classification()
test_AdaBoostClassifier_Base_classifier(X_train,X_test,y_train,y_test)

#考察学习率的影响
def test_AdaBoostClassifier_learning_rate(*data):
    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='Traning 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()
X_train,X_test,y_train,y_test = load_data_classification()
test_AdaBoostClassifier_learning_rate(X_train,X_test,y_train,y_test)

#最后考察algorithm的影响：
def test_AdaBoostClassifier_algorithm(*data):
    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
            estimator_num = len(clf.estimators_)
            X = range(1,estimator_num+1)

            ax.plot(list(X),list(clf.staged_score(X_train,y_train)),label='%s:Traning Score'%algorithm[i])
            ax.plot(list(X),list(clf.staged_score(X_test, y_test)),label='%s:Testing Score' %algorithm[i])
        ax.set_xlabel("estimator num")
        ax.set_ylabel("score")
        ax.legend(loc='lower right')
        ax.set_title('learning rate:%f'%learning_rate)
    fig.suptitle('AdaBoostClassifier')
    plt.show()
X_train,X_test,y_train,y_test = load_data_classification()
test_AdaBoostClassifier_algorithm(X_train,X_test,y_train,y_test)

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

#加载回归数据
def load_data_regression():
    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,test_size=0.25,random_state=0)

#AdaBoostRegressor 回归器
def test_AdaBoostRegressor(*data):
    X_train, X_test, y_train, y_test = data
    regr = ensemble.AdaBoostRegressor()
    regr.fit(X_train,y_train)
    ##绘图
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    estimators_num = len(regr.estimators_)
    X = range(1,estimators_num+1)
    ax.plot(list(X), list(regr.staged_score(X_train, y_train)), label='Traing score')
    ax.plot(list(X), list(regr.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("AdaBoostRegress")
    plt.show()
X_train, X_test, y_train, y_test = load_data_regression()
test_AdaBoostRegressor(X_train, X_test, y_train, y_test)

# 不同类型个体分类器的影响
def test_AdaBoostClassifier_Base_regr(*data):
    X_train, X_test, y_train, y_test = data
    ##绘图
    fig = plt.figure()
    regrs = [ensemble.AdaBoostRegressor(),ensemble.AdaBoostRegressor(base_estimator=svm.LinearSVR(epsilon=0.01,C=100))]
    labels = ['Decision Tree Regressor','Linear SVM Regressor']
    for i, regr in enumerate(regrs):
        ax = fig.add_subplot(2,1,i+1)
        regr.fit(X_train,y_train)
        ###默认的分类器
        estimators_num = len(regr.estimators_)
        X = range(1,estimators_num+1)
        ax.plot(list(X),list(regr.staged_score(X_train,y_train)),label='Traing score')
        ax.plot(list(X),list(regr.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(-1,1)
        ax.set_title("Base_Estimator:%s"%labels[i])
    plt.suptitle("AdaBoostRegressor")
    plt.show()
X_train,X_test,y_train,y_test = load_data_regression()
test_AdaBoostClassifier_Base_regr(X_train,X_test,y_train,y_test)

#下面考察学习率的影响
def test_AdaBoostRegressor_learning_rate(*data):
    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:
        regr = ensemble.AdaBoostRegressor(learning_rate=learning_rate,n_estimators=500)
        regr.fit(X_train,y_train)
        traing_scores.append(regr.score(X_train,y_train))
        testing_scores.append(regr.score(X_test,y_test))
    ax.plot(learning_rates,traing_scores,label='Traning 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('AdaBoostRegressor')
    plt.show()
X_train,X_test,y_train,y_test = load_data_regression()
test_AdaBoostRegressor_learning_rate(X_train,X_test,y_train,y_test)

#下面考察损失函数的影响
def test_AdaBoostRegressor_loss(*data):
    X_train, X_test, y_train, y_test = data
    losses=['linear','square','exponential']
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    for i,loss in enumerate(losses):
        regr = ensemble.AdaBoostRegressor(loss=loss,n_estimators=30)
        regr.fit(X_train,y_train)
        #绘图
        estimators_num=len(regr.estimators_)
        X = range(1,estimators_num+1)
        ax.plot(list(X),list(regr.staged_score(X_train,y_train)),label='Traning Score:loss=%s'%loss)
        ax.plot(list(X), list(regr.staged_score(X_test, y_test)), label='Traning Score:loss=%s' % loss)
        ax.set_xlabel("estimator num")
        ax.set_ylabel("score")
        ax.legend(loc='best')
        ax.set_ylim(-1,1)
    ax.set_title('AdaBoostRegressor')
    plt.show()
X_train,X_test,y_train,y_test = load_data_regression()
test_AdaBoostRegressor_loss(X_train,X_test,y_train,y_test)