隨機森林和決策樹交叉驗證的使用

##導入包
import matplotlib.pyplot as plt
from sklearn.tree import  DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_wine

##導入數據集
wine=load_wine()

from sklearn.model_selection import  train_test_split
from sklearn.model_selection import  cross_val_score

Xtrain,Xtest,Ytrain,Ytest=train_test_split(wine.data,wine.target,test_size=0.3)
#決策樹模型
clf=DecisionTreeClassifier(random_state=0)

#隨機森林模型
rfc=RandomForestClassifier(random_state=0)

##訓練集訓練
clf=clf.fit(Xtrain,Ytrain)
rfc=rfc.fit(Xtrain,Ytrain)

##測試集測試效果得分
score_c=clf.score(Xtest,Ytest)
score_r=rfc.score(Xtest,Ytest)

print("Single Tree:{}".format(score_c)
      ,"Random forest:{}".format(score_r))

##交叉驗證，
##將數據集划分為n份，依次取每一份做測試集，n-1份做訓練集，多次訓練模型以觀測模型的穩定性

rfc_1=[]
clf_1=[]

for i in range(10):
    rfc=RandomForestClassifier(n_estimators=25)
    rfc_s=cross_val_score(rfc,wine.data,wine.target,cv=10).mean()  ##cv=10，將數據集分為10份進行測試，數據集傳的是完整數據集，不需要分割成測試和訓練
    rfc_1.append(rfc_s)
    clf=DecisionTreeClassifier()
    clf_s=cross_val_score(clf,wine.data,wine.target,cv=10).mean()
    clf_1.append(clf_s)

plt.plot(range(1,11),rfc_1,label="Random Forest")
plt.plot(range(1,11),clf_1,label="Decision Tree")
plt.legend()
plt.show()