在建立决策树时，需要平衡“准确度和复杂度”。
用#splits（分枝数量）来体现树的复杂度，树越大越复杂，对training set的准确度也越高。
如果不顾一切地让树增大，会导致overfitting/over learning（对训练集表现得好,but for future data, it may perform badly）。
The main role of this parameter is to save computing time by pruning off splits that are obviously not worthwhile.
cp(complexity parameter) is used to 'control this bias-variance tradeoff'. A prefect cp leads to a perfect balance.
cp is used to judge whether a split is allowed/whether to prune.
Any split that does not decrease the overall lack of fit by a factor of cp is not attempted. For instance, with anova splitting, this means that the overall R-squared must increase by cp at each step.
Essentially,the user informs the program that any split which does not improve the fit by cp will likely be pruned off by cross-validation, and that hence the program need not pursue it.
当增加一个节点引起的分类精确度变化量小于树复杂度变化的cp倍时，则须剪去该节点。
如何度量树的精确度变化？对训练集做10-fold交叉验证(cross validation)。（在rpart.control函数中的参数xval(number of cross-validations)默认值为10）
Therefore if we set this parameter small, we can get a big tree.
