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_regression():

    '''

    加载用于回归问题的数据集

    '''

    #使用 scikit-learn 自带的一个糖尿病病人的数据集

    diabetes = datasets.load_diabetes()

    # 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(diabetes.data,diabetes.target,test_size=0.25,random_state=0) 

#集成学习梯度提升决策树GradientBoostingRegressor回归模型

def test_GradientBoostingRegressor(*data):

    X_train,X_test,y_train,y_test=data

    regr=ensemble.GradientBoostingRegressor()

    regr.fit(X_train,y_train)

    print("Training score:%f"%regr.score(X_train,y_train))

    print("Testing score:%f"%regr.score(X_test,y_test))

# 获取分类数据

X_train,X_test,y_train,y_test=load_data_regression()

# 调用 test_GradientBoostingRegressor

test_GradientBoostingRegressor(X_train,X_test,y_train,y_test) 

def test_GradientBoostingRegressor_num(*data):

    '''

    测试 GradientBoostingRegressor 的预测性能随 n_estimators 参数的影响

    '''

    X_train,X_test,y_train,y_test=data

    nums=np.arange(1,200,step=2)

    fig=plt.figure()

    ax=fig.add_subplot(1,1,1)

    testing_scores=[]

    training_scores=[]

    for num in nums:

        regr=ensemble.GradientBoostingRegressor(n_estimators=num)

        regr.fit(X_train,y_train)

        training_scores.append(regr.score(X_train,y_train))

        testing_scores.append(regr.score(X_test,y_test))

    ax.plot(nums,training_scores,label="Training Score")

    ax.plot(nums,testing_scores,label="Testing Score")

    ax.set_xlabel("estimator num")

    ax.set_ylabel("score")

    ax.legend(loc="lower right")

    ax.set_ylim(0,1.05)

    plt.suptitle("GradientBoostingRegressor")

    plt.show()

# 调用 test_GradientBoostingRegressor_num

test_GradientBoostingRegressor_num(X_train,X_test,y_train,y_test) 

def test_GradientBoostingRegressor_maxdepth(*data):

    '''

    测试 GradientBoostingRegressor 的预测性能随 max_depth 参数的影响

    '''

    X_train,X_test,y_train,y_test=data

    maxdepths=np.arange(1,20)

    fig=plt.figure()

    ax=fig.add_subplot(1,1,1)

    testing_scores=[]

    training_scores=[]

    for maxdepth in maxdepths:

        regr=ensemble.GradientBoostingRegressor(max_depth=maxdepth,max_leaf_nodes=None)

        regr.fit(X_train,y_train)

        training_scores.append(regr.score(X_train,y_train))

        testing_scores.append(regr.score(X_test,y_test))

    ax.plot(maxdepths,training_scores,label="Training Score")

    ax.plot(maxdepths,testing_scores,label="Testing Score")

    ax.set_xlabel("max_depth")

    ax.set_ylabel("score")

    ax.legend(loc="lower right")

    ax.set_ylim(-1,1.05)

    plt.suptitle("GradientBoostingRegressor")

    plt.show()

# 调用 test_GradientBoostingRegressor_maxdepth

test_GradientBoostingRegressor_maxdepth(X_train,X_test,y_train,y_test) 

def test_GradientBoostingRegressor_learning(*data):

    '''

    测试 GradientBoostingRegressor 的预测性能随 learning_rate 参数的影响

    '''

    X_train,X_test,y_train,y_test=data

    learnings=np.linspace(0.01,1.0)

    fig=plt.figure()

    ax=fig.add_subplot(1,1,1)

    testing_scores=[]

    training_scores=[]

    for learning in learnings:

        regr=ensemble.GradientBoostingRegressor(learning_rate=learning)

        regr.fit(X_train,y_train)

        training_scores.append(regr.score(X_train,y_train))

        testing_scores.append(regr.score(X_test,y_test))

    ax.plot(learnings,training_scores,label="Training Score")

    ax.plot(learnings,testing_scores,label="Testing Score")

    ax.set_xlabel("learning_rate")

    ax.set_ylabel("score")

    ax.legend(loc="lower right")

    ax.set_ylim(-1,1.05)

    plt.suptitle("GradientBoostingRegressor")

    plt.show()

# 调用 test_GradientBoostingRegressor_learning

test_GradientBoostingRegressor_learning(X_train,X_test,y_train,y_test) 

def test_GradientBoostingRegressor_subsample(*data):

    '''

    测试 GradientBoostingRegressor 的预测性能随 subsample 参数的影响

    '''

    X_train,X_test,y_train,y_test=data

    fig=plt.figure()

    ax=fig.add_subplot(1,1,1)

    subsamples=np.linspace(0.01,1.0,num=20)

    testing_scores=[]

    training_scores=[]

    for subsample in subsamples:

        regr=ensemble.GradientBoostingRegressor(subsample=subsample)

        regr.fit(X_train,y_train)

        training_scores.append(regr.score(X_train,y_train))

        testing_scores.append(regr.score(X_test,y_test))

    ax.plot(subsamples,training_scores,label="Training Score")

    ax.plot(subsamples,testing_scores,label="Training Score")

    ax.set_xlabel("subsample")

    ax.set_ylabel("score")

    ax.legend(loc="lower right")

    ax.set_ylim(-1,1.05)

    plt.suptitle("GradientBoostingRegressor")

    plt.show()

# 调用 test_GradientBoostingRegressor_subsample

test_GradientBoostingRegressor_subsample(X_train,X_test,y_train,y_test) 

def test_GradientBoostingRegressor_loss(*data):

    '''

    测试 GradientBoostingRegressor 的预测性能随不同的损失函数和 alpha 参数的影响

    '''

    X_train,X_test,y_train,y_test=data

    fig=plt.figure()

    nums=np.arange(1,200,step=2)

    ########## 绘制 huber ######

    ax=fig.add_subplot(2,1,1)

    alphas=np.linspace(0.01,1.0,endpoint=False,num=5)

    for alpha in alphas:

        testing_scores=[]

        training_scores=[]

        for num in nums:

            regr=ensemble.GradientBoostingRegressor(n_estimators=num,loss='huber',alpha=alpha)

            regr.fit(X_train,y_train)

            training_scores.append(regr.score(X_train,y_train))

            testing_scores.append(regr.score(X_test,y_test))

        ax.plot(nums,training_scores,label="Training Score:alpha=%f"%alpha)

        ax.plot(nums,testing_scores,label="Testing Score:alpha=%f"%alpha)

    ax.set_xlabel("estimator num")

    ax.set_ylabel("score")

    ax.legend(loc="lower right",framealpha=0.4)

    ax.set_ylim(0,1.05)

    ax.set_title("loss=%huber")

    plt.suptitle("GradientBoostingRegressor")

    #### 绘制 ls  和 lad

    ax=fig.add_subplot(2,1,2)

    for loss in ['ls','lad']:

        testing_scores=[]

        training_scores=[]

        for num in nums:

            regr=ensemble.GradientBoostingRegressor(n_estimators=num,loss=loss)

            regr.fit(X_train,y_train)

            training_scores.append(regr.score(X_train,y_train))

            testing_scores.append(regr.score(X_test,y_test))

        ax.plot(nums,training_scores,label="Training Score:loss=%s"%loss)

        ax.plot(nums,testing_scores,label="Testing Score:loss=%s"%loss)

    ax.set_xlabel("estimator num")

    ax.set_ylabel("score")

    ax.legend(loc="lower right",framealpha=0.4)

    ax.set_ylim(0,1.05)

    ax.set_title("loss=ls,lad")

    plt.suptitle("GradientBoostingRegressor")

    plt.show()

# 调用 test_GradientBoostingRegressor_loss

test_GradientBoostingRegressor_loss(X_train,X_test,y_train,y_test) 

def test_GradientBoostingRegressor_max_features(*data):

    '''

    测试 GradientBoostingRegressor 的预测性能随 max_features 参数的影响

    '''

    X_train,X_test,y_train,y_test=data

    fig=plt.figure()

    ax=fig.add_subplot(1,1,1)

    max_features=np.linspace(0.01,1.0)

    testing_scores=[]

    training_scores=[]

    for features in max_features:

        regr=ensemble.GradientBoostingRegressor(max_features=features)

        regr.fit(X_train,y_train)

        training_scores.append(regr.score(X_train,y_train))

        testing_scores.append(regr.score(X_test,y_test))

    ax.plot(max_features,training_scores,label="Training Score")

    ax.plot(max_features,testing_scores,label="Training Score")

    ax.set_xlabel("max_features")

    ax.set_ylabel("score")

    ax.legend(loc="lower right")

    ax.set_ylim(0,1.05)

    plt.suptitle("GradientBoostingRegressor")

    plt.show()

# 调用 test_GradientBoostingRegressor_max_features

test_GradientBoostingRegressor_max_features(X_train,X_test,y_train,y_test)

吴裕雄 python 机器学习——集成学习梯度提升决策树GradientBoostingRegressor回归模型的更多相关文章

  1. 吴裕雄 python 机器学习——集成学习随机森林RandomForestRegressor回归模型

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

  2. 吴裕雄 python 机器学习——集成学习随机森林RandomForestClassifier分类模型

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

  3. 吴裕雄 python 机器学习——集成学习AdaBoost算法回归模型

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

  4. 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 sklear ...

  5. 吴裕雄 python 机器学习——数据预处理字典学习模型

    from sklearn.decomposition import DictionaryLearning #数据预处理字典学习DictionaryLearning模型 def test_Diction ...

  6. 吴裕雄 python 机器学习——人工神经网络感知机学习算法的应用

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

  7. 吴裕雄 python 机器学习——人工神经网络与原始感知机模型

    import numpy as np from matplotlib import pyplot as plt from mpl_toolkits.mplot3d import Axes3D from ...

  8. 吴裕雄 python 机器学习——分类决策树模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_s ...

  9. 吴裕雄 python 机器学习——回归决策树模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_s ...

随机推荐

  1. Win10安装4 —— 通过BIOS进入PE

    本文内容皆为作者原创,如需转载,请注明出处:https://www.cnblogs.com/xuexianqi/p/12369367.html 一:"BIOS"与"PE& ...

  2. shell登录 脚本 expect

    作用 工作中,我们运行命令.脚本或程序时,这些命令.脚本或程序都需要从终端输入某些继续运行的指令,而这些输入都需要人为的手工进行. 利用expect,则可以根据程序的提示,模拟标准输入提供给程序,从而 ...

  3. js集合

    var list = {};//声明 List[0] = 52;//赋值 List[1] = 57;//赋值

  4. Python 查看函数属于哪个模块

    help(函数名)出现的信息里包含了所在模块

  5. python 处理protobuf协议

    背景:需要用django基于python3模拟一个http接口,请求是post方式,body是protobuf string,返回也是protobuf string 设计:django获取pb str ...

  6. 《深入理解Java虚拟机》读书笔记十

    第十一章  晚期(运行期)优化 1.HotSpot虚拟机内的即时编译 解释器与编译器: 许多Java虚拟机的执行引擎在执行Java代码的时候都有解释执行(通过解释器执行)和编译执行(通过即时编译器产生 ...

  7. 【Python】循环控制保留字

  8. 是未来还是“有毒”？紧抓球鞋风口的毒APP机遇与危机并存

    编辑 | 于斌 出品 | 于见(mpyujian) 新一代的"潮流"之风正在席卷新生代消费市场,从去年开始,国内二手球鞋交易领域突然开始火爆,大有成为新一轮"风口&quo ...

  9. C#String类型转换成Brush类型

    C#String类型转换成Brush类型: using System.Windows.Media; BrushConverter brushConverter = new BrushConverter ...

  10. 剑指offer 面试题 删除链表中重复的节点

    题目描述 在一个排序的链表中,存在重复的结点,请删除该链表中重复的结点,重复的结点不保留,返回链表头指针. 例如,链表1->2->3->3->4->4->5 处理后 ...