DecisionTree tips from Udacity Jan 3, 2017 sklearn decisiontree classifier para: min_samples_split(最小可分样本) 选决策树特征时选信息增益(Gain)最大的 Gain = Original_Entropy - Entropy_after_classified 决策树容易过拟合,但容易解释,容易进行组合。 Please enable JavaScript to view the comments powered by Disqus.