/// <summary>
/// 根据样本数据创建CART决策树
/// </summary>
/// <param name="data"></param>
/// <returns></returns>
public static CARTTree Create(CARTData data)
{
var tree = new CARTTree()
{
_root = new CARTNode()
};
var attrIdxs = Enumerable.Range(0, data.J - 1).ToList(); // 输入属性索引列表
Create(tree._root, attrIdxs, data.trainSet);
return(Prune(tree, data));
}
/// <summary>
/// 剪枝
/// </summary>
/// <param name="tree">完全生长的决策树</param>
/// <param name="data">提供验证数据集</param>
/// <returns></returns>
private static CARTTree Prune(CARTTree tree, CARTData data)
{
// 获取最优子树序列
var list = new List <CARTTree>()
{
tree
}; // 最优子树序列
var curTree = tree;
while (!Is_ThreeNode_Tree(curTree))
{
curTree = GetSubTree(curTree);
list.Add(curTree);
}
// 使用验证集获得最终的最优子树
// 验证集，最小平方误差
double min_err = double.MaxValue;
CARTTree best_tree = null; // 最小平方误差对应的最优子树
for (int i = 0; i < list.Count; i++)
{
var sub_tree = list[i];
double squareErrSum = 0;
for (int k = 0; k < data.verifySet.Count; k++)
{
squareErrSum += Judge(data.verifySet[k], sub_tree);
}
if (min_err > squareErrSum)
{
min_err = squareErrSum;
best_tree = sub_tree;
}
}
return(best_tree);
}