《菜菜的机器学习sklearn课堂》随机森林应用泛化误差调参实例

from sklearn.model_selection import train_test_split



#划分30%的数据作为测试集

Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data, wine.target, test_size=0.3)



clf = DecisionTreeClassifier(random_state=0) #建立模型: 决策树

rfc = RandomForestClassifier(random_state=0) #建立模型: 随机森林



clf = clf.fit(Xtrain, Ytrain) # 训练模型: 决策树

rfc = rfc.fit(Xtrain, Ytrain) # 训练模型: 随即森林



score_c = clf.score(Xtest, Ytest) #返回预测的准确度: 随机森林

score_r = rfc.score(Xtest, Ytest) #返回预测的准确度: 决策树



# 打印出准确度

print("single Tree:{}".format(score_c),

      "Random Forest:{}".format(score_r)) 

single Tree:0.9444444444444444 Random Forest:0.9814814814814815

可见随机森林默认就比决策树准确度要高。



**4、画出随机森林和决策树在一组交叉验证下的效果对比**



> **交叉验证**  

> 将数据集划分为n份，依次取每一份做测试集，每n-1份做训练集，多次训练模型以观测模型稳定性的方法

from sklearn.model_selection import cross_val_score

import matplotlib.pyplot as plt

随机森林

rfc = RandomForestClassifier(n_estimators=25)

rfc_s = cross_val_score(rfc, wine.data, wine.target, cv=10)

决策树

clf = DecisionTreeClassifier()

clf_s = cross_val_score(clf, wine.data, wine.target, cv=10)

plt.plot(range(1,11), rfc_s, label = “RandomForest”)

plt.plot(range(1,11), clf_s, label = “Decision Tree”)

plt.legend()

plt.show()

![在这里插入图片描述](https://img-blog.csdnimg.cn/20210211213139202.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzczNDA5NQ==,size_16,color_FFFFFF,t_70)  

另一种更加简单有趣的写法：

label = “RandomForest”

for model in [RandomForestClassifier(n_estimators=25),DecisionTreeClassifier()]:

score = cross_val_score(model,wine.data, wine.target, cv=10)

print("{}:".format(label)),print(score.mean())

plt.plot(range(1,11),score,label = label)

plt.legend()

label = "DecisionTree" 

![在这里插入图片描述](https://img-blog.csdnimg.cn/20210211213509450.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzczNDA5NQ==,size_16,color_FFFFFF,t_70)  

**5、画出随机森林和决策树在十组交叉验证下的效果对比**

rfc_l = []

clf_l = []

for i in range(10):

rfc = RandomForestClassifier(n_estimators=25)

rfc_s = cross_val_score(rfc,wine.data,wine.target,cv=10).mean()

rfc_l.append(rfc_s)



clf = DecisionTreeClassifier()

clf_s = cross_val_score(clf,wine.data,wine.target,cv=10).mean()

clf_l.append(clf_s)

plt.plot(range(1,11), rfc_l, label=“Random Forest”)

plt.plot(range(1,11), clf_l, label=“Decision Tree”)

plt.legend()

plt.show()

![在这里插入图片描述](https://img-blog.csdnimg.cn/2021021122074319.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzczNDA5NQ==,size_16,color_FFFFFF,t_70)  

**6、n\_estimators的学习曲线**

#####【TIME WARNING: 2mins 30 seconds】#####

superpa = []

for i in range(200):

rfc = RandomForestClassifier(n_estimators=i+1,n_jobs=-1)

rfc_s = cross_val_score(rfc,wine.data,wine.target,cv=10).mean()

superpa.append(rfc_s)

print(max(superpa), superpa.index(max(superpa))) # 0.9888888888888889 53

plt.figure(figsize=[20,5])

plt.plot(range(1,201),superpa)

plt.show()

![在这里插入图片描述](https://img-blog.csdnimg.cn/20210211221112484.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,