集成学习

from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import VotingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
log_clf = LogisticRegression()
rnd_clf = RandomForestClassifier()
svm_clf = SVC()
voting_clf = VotingClassifier(estimators=[('lr', log_clf), ('rf', rnd_clf), ('svc', svm_clf)],voting='hard')
voting_clf.fit(X_train, y_train)

逻辑回归、kNN、决策树、SVM

log_clf = LogisticRegression()
svm_clf = SVC(probability=True)
voting_clf = VotingClassifier(estimators=[('lr', log_clf),('svc',svm_clf)],voting='soft')
voting_clf.fit(X_train, y_train)

from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier
bag_clf = BaggingClassifier(DecisionTreeClassifier(), n_estimators=500, max_samples=100, bootstrap=True, n_jobs=-1)
#子模型数量、每次取的样本数、有放回
bag_clf.fit(X_train, y_train)
y_pred = bag_clf.predict(X_test)

bag_clf = BaggingClassifier(DecisionTreeClassifier(), n_estimators=500,bootstrap=True, n_jobs=-1, oob_score=True)
bag_clf.fit(X_train, y_train)
bag_clf.oob_score_

当你在处理高维度输入下（例如图片） 此方法尤其有效。对训练实例和特征的采样被叫做随机贴片。保留了所有的训练实例（如 bootstrap=False 和 max_samples=1.0 ） ，但是对特征采样（bootstrap_features=True 并且/或者 max_features 小于 1.0） 叫做随机子空间。

from sklearn.ensemble import RandomForestClassifier
rnd_clf = RandomForestClassifier(n_estimators=500, max_leaf_nodes=16,n_jobs=-1)
rnd_clf.fit(X_train, y_train)
y_pred_rf = rnd_clf.predict(X_test)

ExtraTreesClassifier

from sklearn.ensemble import AdaBoostClassifier
ada_clf = AdaBoostClassifier(DecisionTreeClassifier(max_depth=1), n_estimators=200,algorithm="SAMME.R", learning_rate=0.5)
ada_clf.fit(X_train, y_train)

from sklearn.ensemble import GradientBoostingRegressor
gbrt = GradientBoostingRegressor(max_depth=2, n_estimators=3, learning_rate=1.0)
gbrt.fit(X, y)

Stacking