吴裕雄--天生自然人工智能机器学习实战代码：回归决策树模型

女爷i 2021-11-05 10:31 219阅读 0赞

import numpy as np
    import matplotlib.pyplot as plt
    
    from sklearn import datasets
    from sklearn.model_selection import train_test_split
    from sklearn.tree import DecisionTreeClassifier,DecisionTreeRegressor
    
    def load_data():
        '''
        加载用于分类问题的数据集。数据集采用 scikit-learn 自带的 iris 数据集
        '''
        # scikit-learn 自带的 iris 数据集
        iris=datasets.load_iris()
        X_train=iris.data
        y_train=iris.target
        return train_test_split(X_train, y_train,test_size=0.25,random_state=0,stratify=y_train)
    
    #分类决策树DecisionTreeClassifier模型
    def test_DecisionTreeClassifier(*data):
        X_train,X_test,y_train,y_test=data
        clf = DecisionTreeClassifier()
        clf.fit(X_train, y_train)
        print("Training score:%f"%(clf.score(X_train,y_train)))
        print("Testing score:%f"%(clf.score(X_test,y_test)))
        
    # 产生用于分类问题的数据集
    X_train,X_test,y_train,y_test=load_data()
    # 调用 test_DecisionTreeClassifier
    test_DecisionTreeClassifier(X_train,X_test,y_train,y_test)

![1020928-20190712191609311-1247179322.png][]

def test_DecisionTreeClassifier_criterion(*data):
        '''
        测试 DecisionTreeClassifier 的预测性能随 criterion 参数的影响
        '''
        X_train,X_test,y_train,y_test=data
        criterions=['gini','entropy']
        for criterion in criterions:
            clf = DecisionTreeClassifier(criterion=criterion)
            clf.fit(X_train, y_train)
            print("criterion:%s"%criterion)
            print("Training score:%f"%(clf.score(X_train,y_train)))
            print("Testing score:%f"%(clf.score(X_test,y_test)))
            
    # 调用 test_DecisionTreeClassifier_criterion
    test_DecisionTreeClassifier_criterion(X_train,X_test,y_train,y_test)

![1020928-20190712191631324-1901202189.png][]

def test_DecisionTreeClassifier_splitter(*data):
        '''
        测试 DecisionTreeClassifier 的预测性能随划分类型的影响
        '''
        X_train,X_test,y_train,y_test=data
        splitters=['best','random']
        for splitter in splitters:
            clf = DecisionTreeClassifier(splitter=splitter)
            clf.fit(X_train, y_train)
            print("splitter:%s"%splitter)
            print("Training score:%f"%(clf.score(X_train,y_train)))
            print("Testing score:%f"%(clf.score(X_test,y_test)))
            
    # 调用 test_DecisionTreeClassifier_splitter
    test_DecisionTreeClassifier_splitter(X_train,X_test,y_train,y_test)

![1020928-20190712191651250-213855542.png][]

def test_DecisionTreeClassifier_depth(*data,maxdepth):
        '''
        测试 DecisionTreeClassifier 的预测性能随 max_depth 参数的影响
        '''
        X_train,X_test,y_train,y_test=data
        depths=np.arange(1,maxdepth)
        training_scores=[]
        testing_scores=[]
        for depth in depths:
            clf = DecisionTreeClassifier(max_depth=depth)
            clf.fit(X_train, y_train)
            training_scores.append(clf.score(X_train,y_train))
            testing_scores.append(clf.score(X_test,y_test))
    
        ## 绘图
        fig=plt.figure()
        ax=fig.add_subplot(1,1,1)
        ax.plot(depths,training_scores,label="traing score",marker='o')
        ax.plot(depths,testing_scores,label="testing score",marker='*')
        ax.set_xlabel("maxdepth")
        ax.set_ylabel("score")
        ax.set_title("Decision Tree Classification")
        ax.legend(framealpha=0.5,loc='best')
        plt.show()
        
    # 调用 test_DecisionTreeClassifier_depth
    test_DecisionTreeClassifier_depth(X_train,X_test,y_train,y_test,maxdepth=100)

![1020928-20190712191714713-1564825243.png][]

import os
    import pydotplus
    
    from io import StringIO
    from sklearn.tree import export_graphviz
    from sklearn.tree import DecisionTreeClassifier,DecisionTreeRegressor
    
    X_train,X_test,y_train,y_test=load_data()
    clf = DecisionTreeClassifier()
    clf.fit(X_train,y_train)
    export_graphviz(clf,"F://out")

![1020928-20190712191738472-1397077232.png][]

![1020928-20190712191755120-1534040603.png][]

转载于:https://www.cnblogs.com/tszr/p/11177963.html

[1020928-20190712191609311-1247179322.png]: /images/20211104/d1557ed5d99e4811954438efe6125ef4.png
[1020928-20190712191631324-1901202189.png]: /images/20211104/529760c3fe8a49bab03190d578f77e03.png
[1020928-20190712191651250-213855542.png]: /images/20211104/f602160cb98141d19dd700667dc028e9.png
[1020928-20190712191714713-1564825243.png]: /images/20211104/6ca81edb2dda434b97a246b7d3ca948c.png
[1020928-20190712191738472-1397077232.png]: /images/20211104/5eb88cce897c4dcda76bcfcef13dc386.png
[1020928-20190712191755120-1534040603.png]: /images/20211104/c36f7d6ce51d4aac9f64a49b1aa82566.png