sklearn代码14 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 在进行裂分的时候， 根据信息增益最大进行裂分，刻板

# 极限森林  1、样本随机 2、分裂条件随机（不是最好的裂分条件）
# 像在随机森林中一样，使用候选特征的随机子集，但不是寻找最有区别的阈值,
# 而是为每个候选特征随机绘制阀值
# 并选择这些随机生成的阈值中的最佳阈值作为划分规则

X,y = datasets.load_wine(True)

clf = DecisionTreeClassifier()

cross_val_score(clf,X,y,cv=6,scoring='accuracy').mean()

0.87023809523809526

forest = RandomForestClassifier(n_estimators=100)

cross_val_score(forest,X,y,cv = 8,scoring='accuracy').mean()

0.97801383399209496

extra = ExtraTreesClassifier(n_estimators=100,)

cross_val_score(extra,X,y,cv = 6,scoring='accuracy').mean()

0.97222222222222221

# 鸢尾花数据 特征只有四个，相对于葡萄酒，数据量简单
X,y = datasets.load_iris(True)

clf = DecisionTreeClassifier()

cross_val_score(clf,X,y,cv = 6,scoring='accuracy').mean()

0.95910493827160481

forest = RandomForestClassifier(n_estimators=100)

cross_val_score(forest,X,y,cv = 8,scoring='accuracy').mean()

0.95932539682539675

extra = ExtraTreesClassifier(n_estimators=100,)

cross_val_score(extra,X,y,cv = 6,scoring='accuracy').mean()

0.9521604938271605