极限森林

极限森林

from sklearn.ensemble import ExtraTreesClassifier,RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score
from sklearn import datasets
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
#决策树，进行裂分是根据信息增益最大进行裂分
#极限森林：样本随机，分裂条件随机（不是分类最好的条件）

X,y = datasets.load_wine(True)
clf = DecisionTreeClassifier()
cross_val_score(clf,X,y,cv = 6,scoring='accuracy').mean()#交叉验证

forest = RandomForestClassifier(n_estimators =100)
cross_val_score(forest,X,y,cv = 6,scoring='accuracy').mean()#交叉验证