四种方法的具体的原理可以见博文
和西瓜书
先上代码根据结果分析
鸢尾花数据
# evaluate bagging algorithm for classification
from numpy import mean
from numpy import std
from sklearn.datasets import make_classification
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
# 我们使用多个KNN模型作为基模型演示投票法,其中每个模型采用不同的邻居值K参数:
# get a voting ensemble of models
def base_modellist():
# define the base models
models = list()
models.append(('DT1', DecisionTreeClassifier(max_depth=1)))
models.append(('DT2', DecisionTreeClassifier(max_depth=2)))
models.append(('DT3', DecisionTreeClassifier(max_depth=3)))
# define the voting ensemble
return models
def get_models():
models = dict()
models['DT1'] = DecisionTreeClassifier(max_depth=1)
models['DT2'] = DecisionTreeClassifier(max_depth=2)
models['DT3'] = DecisionTreeClassifier(max_depth=3)
models['DT100'] = DecisionTreeClassifier(max_depth=100)
models['bagging1'] = BaggingClassifier(base_estimator=DecisionTreeClassifier(max_depth=1),n_estimators=100,max_samples=0.3)
models['bagging3'] = BaggingClassifier(base_estimator=DecisionTreeClassifier(max_depth=3),</