[实战] 树回归算法

全局建模的不足：
线性回归算法，在全局上拟合所有的样本，使得整体上误差最小。
但是当数据有众多的特征并且特征之间的关系十分复杂时，建立全局模型的想法就显得十分的困难，并且效果也不会太好。
在实际生活中，很多问题都是非线性的，不可能使用全局线性模型来拟合任意的数据。

局部性建模：
对于一些复杂的非线性的数据，我们可以将数据切分成很多分易建模的数据，然后再各个子段分别使用模型进行建模。

基于决策树的想法：
决策树是按照信息熵增的大小顺序将属性进行排序，并按各个属性的所有可能值将数据进行划分。使得一旦按照某种特征进行划分后，该特征在之后的算法执行过程中不再起作用，切分方式过于迅速，并且划分的过于细致。

因此，我们可以使用二元切分法，即每次把数据集（按照某一属性的某一属性值）切成两份，大于该属性值的数据进入左子树，其他进入右子树。类似于形成了一个决策二叉树。
当数据满足某些条件后，就不在进行划分，形成叶子节点，叶子节点代表当前的决策结果。

两类不同的叶子节点：
根据叶子节点信息的不同，可以将算法分为两类：
1：回归树： 叶子节点为当前子数据集的目标变量的均值（单个数）
2：模型树 ：叶子节点为由当前子数据集，训练得到的一条预测直线（预测直线的参数向量w）

代码：

'''
from numpy import *

#加载数据集
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) #map all elements to float()
        dataMat.append(fltLine)
    return dataMat

#按照某一属性的某一属性值将数据进行划分为mat0和mat1
def binSplitDataSet(dataSet, feature, value):
    mat0 = dataSet[nonzero(dataSet[:,feature] > value)[0],:][0]
    mat1 = dataSet[nonzero(dataSet[:,feature] <= value)[0],:][0]
    return mat0,mat1

#回归树的叶子节点的计算方法：求所有数据的目标变量的均值
def regLeaf(dataSet):#returns the value used for each leaf
    return mean(dataSet[:,-1])

#回归树的误差计算：子集所有数据的方差总和
def regErr(dataSet):
    return var(dataSet[:,-1]) * shape(dataSet)[0]

#使用线性回归公式对数据进行拟合
def linearSolve(dataSet):   #helper function used in two places
    m,n = shape(dataSet)
    X = mat(ones((m,n))); Y = mat(ones((m,1)))#create a copy of data with 1 in 0th postion
    X[:,1:n] = dataSet[:,0:n-1]; Y = dataSet[:,-1]#and strip out Y
    xTx = X.T*X
    if linalg.det(xTx) == 0.0:
        raise NameError('This matrix is singular, cannot do inverse,\n\
        try increasing the second value of ops')
    ws = xTx.I * (X.T * Y)
    return ws,X,Y

#模型树的叶子节点的计算方法：线性回归公式对数据进行拟合
def modelLeaf(dataSet):#create linear model and return coeficients
    ws,X,Y = linearSolve(dataSet)
    return ws

#模型树误差计算方法：偏差平方和
def modelErr(dataSet):
    ws,X,Y = linearSolve(dataSet)
    yHat = X * ws
    return sum(power(Y - yHat,2))

#遍历所有的属性和属性值，找到使误差和最小的划分属性和属性值
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):  #exit cond 3
        return None, leafType(dataSet)
    return bestIndex,bestValue#returns the best feature to split on
                              #and the value used for that split
                              
#递归创建二分决策树
def createTree(dataSet, leafType=regLeaf, errType=regErr, ops=(1,4)):#assume dataSet is NumPy Mat so we can array filtering
    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  

#判断当前节点是否是非叶子节点
def isTree(obj):
    return (type(obj).__name__=='dict')
    
#获取该节点数据的均值
def getMean(tree):
    if isTree(tree['right']): tree['right'] = getMean(tree['right'])
    if isTree(tree['left']): tree['left'] = getMean(tree['left'])
    return (tree['left']+tree['right'])/2.0
    
 #后剪枝优化
 #用测试集来判断叶节点合并是否能降低测试误差，若是的话则合并
def prune(tree, testData):
    if shape(testData)[0] == 0: return getMean(tree) #if we have no test data collapse the tree
    if (isTree(tree['right']) or isTree(tree['left'])):#if the branches are not trees try to prune them
        lSet, rSet = binSplitDataSet(testData, tree['spInd'], tree['spVal'])
    if isTree(tree['left']): tree['left'] = prune(tree['left'], lSet)
    if isTree(tree['right']): tree['right'] =  prune(tree['right'], rSet)
    #if they are now both leafs, see if we can merge them
    if not isTree(tree['left']) and not isTree(tree['right']):
        lSet, rSet = binSplitDataSet(testData, tree['spInd'], tree['spVal'])
        errorNoMerge = sum(power(lSet[:,-1] - tree['left'],2)) +\
            sum(power(rSet[:,-1] - tree['right'],2))
        treeMean = (tree['left']+tree['right'])/2.0
        errorMerge = sum(power(testData[:,-1] - treeMean,2))
        if errorMerge < errorNoMerge: 
            print "merging"
            return treeMean
        else: return tree
    else: return tree
    
#回归树的叶子节点预测值
def regTreeEval(model, inDat):
    return float(model)

#模型树的叶子接待你预测值
def modelTreeEval(model, inDat):
    n = shape(inDat)[1]
    X = mat(ones((1,n+1)))
    X[:,1:n+1]=inDat
    return float(X*model)

#根据测试数据inData的各个属性值，不断判断进入分支，直到到达叶子节点，并返回预测值
def treeForeCast(tree, inData, modelEval=regTreeEval):
    if not isTree(tree): return modelEval(tree, inData)
    if inData[tree['spInd']] > tree['spVal']:
        if isTree(tree['left']): return treeForeCast(tree['left'], inData, modelEval)
        else: return modelEval(tree['left'], inData)
    else:
        if isTree(tree['right']): return treeForeCast(tree['right'], inData, modelEval)
        else: return modelEval(tree['right'], inData)
       
#预测测试集中每个数据的预测值
def createForeCast(tree, testData, modelEval=regTreeEval):
    m=len(testData)
    yHat = mat(zeros((m,1)))
    for i in range(m):
        yHat[i,0] = treeForeCast(tree, mat(testData[i]), modelEval)
    return yHat