参数
base_estimator:基学习器
n_estimators:基学习器的个数
algorithm:{'SAMMER,‘SAMME.R’}二选一
learning_rate:学习率。官网温馨提示：There is a trade-off between learning_rate and n_estimators.
random_state：random_state
loss:回归树特有
属性
feature_importances_:各个特征的重要程度。
n_class_：Adaboost分类器专有，类别数量
classes_：Adaboost分类器专有，分类结果列表
方法
fit(train_x,train_y)
score(test_x,test_y)
predict(test_x)
predict_proba(test_x)
predict_log_proba(test_x)
示例
from sklearm.tree import DecisionTreeClassifier
from sklearn.ensemble import AdaBoostClassifier
本例中单树为决策树。
clf = AdaBoostClassifier(DecisionTreeClassifier())
clf.fit(train_x,train_y)
print(clf.score(train_x,train_y))
result = clf.predict(test_x)