树回归：对复杂的关系建模。一般可以分为两种，一种是回归树，一种是模型树，

主要的区别在于对于叶节点的建模方式，回归树使用分段常数，模型树使用线性回归方程。

可以使用剪枝技术对于可能过拟合的树进行剪枝，剪枝一般分为预剪枝和后剪枝。

回归树和模型树都是2元树，每次总是选择最好的分割方式，分成两部分。

这个是自己写的Python语言的CART树回归程序，基本实现了其原理，注释比较多。-Tree Regression: modeling of complex relationships. Can generally be divided into two types, one is the regression trees, one is the model tree,

               　The main difference is that the modeling of leaf nodes, using a piecewise constant regression trees, tree model using linear regression equation.

               　You can use pruning techniques may be too fit for tree pruning, pruning pruning is generally divided into pre-and post-pruning.

               　Regression trees and model trees are two yuan tree, each division always choose the best way, is divided into two parts.

This is the Python language to write their own CART tree regression program, the basic realization of its principles, comment more.