CART回归树的构建

回归树的运行流程与分类树基本类似，但有以下两点不同之处： 

1.回归树的每个节点得到的是一个预测值而非分类树式的样本计数.  

2.第二，在分枝节点的选取上，回归树使用了最小化均方差

from numpy import *

def loadDataSet(fileName):      #general function to parse tab -delimited floats
    dataMat = []                #assume last column is target value
    fr = open(fileName)
    for line in fr.readlines():
        curLine = line.strip().split('\t')
        fltLine = map(float,curLine) #将每行的每个元素映射为浮点数
        dataMat.append(fltLine)
    return dataMat
#mat0, mat1 = binSplitDataSet(testMat, 1, 0.5)
def binSplitDataSet(dataSet, feature, value):
    print nonzero(dataSet[:,feature] > value)
    print nonzero(dataSet[:, feature] > value)[0]
    print dataSet[nonzero(dataSet[:, feature] > value)[0], :]
    mat0 = dataSet[nonzero(dataSet[:,feature] > value)[0],:][0]
    mat1 = dataSet[nonzero(dataSet[:,feature] <= value)[0],:][0]
    return mat0,mat1

def regLeaf(dataSet):#返回叶节点,回归树中的目标
    return mean(dataSet[:,-1])

def regErr(dataSet):#误差估计，计算目标变量的均方误差，需要返回总误差
    return var(dataSet[:,-1]) * shape(dataSet)[0]

def chooseBestSplit(dataSet, leafType=regLeaf, errType=regErr, ops=(1,4)):
    tolS = ops[0]; tolN = ops[1]
    #if all the target variables are the same value: quit and return value
    if len(set(dataSet[:,-1].T.tolist()[0])) == 1: #exit cond 1
        return None, leafType(dataSet)
    m,n = shape(dataSet)
    #the choice of the best feature is driven by Reduction in RSS error from mean
    S = errType(dataSet)
    bestS = inf; bestIndex = 0; bestValue = 0
    for featIndex in range(n-1):
        for splitVal in set(dataSet[:,featIndex]):
            mat0, mat1 = binSplitDataSet(dataSet, featIndex, splitVal)
            if (shape(mat0)[0] < tolN) or (shape(mat1)[0] < tolN): continue
            newS = errType(mat0) + errType(mat1)
            if newS < bestS: 
                bestIndex = featIndex
                bestValue = splitVal
                bestS = newS
    #if the decrease (S-bestS) is less than a threshold don't do the split
    if (S - bestS) < tolS: 
        return None, leafType(dataSet) #exit cond 2
    mat0, mat1 = binSplitDataSet(dataSet, bestIndex, bestValue)
    if (shape(mat0)[0] < tolN) or (shape(mat1)[0] < tolN):  #如果某个子集行数不大于tolN，也不应该切分
        return None, leafType(dataSet)
    return bestIndex,bestValue#returns the best feature to split on
                              #and the value used for that split

def createTree(dataSet, leafType=regLeaf, errType=regErr, ops=(1,4)):
    feat, val = chooseBestSplit(dataSet, leafType, errType, ops)#choose the best split
    if feat == None: return val #if the splitting hit a stop condition return val
    retTree = {}
    retTree['spInd'] = feat
    retTree['spVal'] = val
    lSet, rSet = binSplitDataSet(dataSet, feat, val)
    retTree['left'] = createTree(lSet, leafType, errType, ops)
    retTree['right'] = createTree(rSet, leafType, errType, ops)
    return retTree  

参考

1.http://www.lai18.com/content/1406280.html
2.机器学习实战