集成学习

integr/ada_train.py

@@ -0,0 +1,20 @@
+
+# -*- encoding:utf-8 -*-
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import AdaBoostClassifier
+
+from sklearn.datasets import load_wine
+wine = load_wine()
+Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=0.3)
+
+bdt1 = AdaBoostClassifier(DecisionTreeClassifier(max_depth=2, min_samples_split=20, min_samples_leaf=5),n_estimators=2)
+bdt1.fit(Xtrain, Ytrain)
+print("bdt1",bdt1.score(Xtest,Ytest))
+
+#分类器越多效果越好
+bdt2 = AdaBoostClassifier(DecisionTreeClassifier(max_depth=2, min_samples_split=20, min_samples_leaf=5),n_estimators=30)
+bdt2.fit(Xtrain, Ytrain)
+print("bdt2",bdt2.score(Xtest,Ytest))
+

integr/gbdt_train.py

@@ -0,0 +1,20 @@
+#coding=utf-8
+#coding:utf-8
+#-*- coding:utf-8 -*-
+ 
+import numpy as np
+from sklearn.ensemble import GradientBoostingClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.datasets import load_wine
+wine = load_wine()
+Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=0.3)
+#print (X,y)
+ 
+#默认参数
+#Accuracy : 0.9856
+#AUC Score (Train): 0.862264
+gbm1 = GradientBoostingClassifier( n_estimators=500,max_depth=10,max_features='sqrt', random_state=10)
+gbm1.fit(Xtrain,Ytrain)
+print("gbdt1",gbm1.score(Xtest,Ytest))
+ 
+