机器学习实战 第九章树回归 错误总结

我的是python3.6
第一处：

def binSplitDataSet(dataSet, feature, value):
    mat0 = dataSet[np.nonzero(dataSet[:,feature] > value)[0],:][0]
    mat1 = dataSet[np.nonzero(dataSet[:,feature] <= value)[0],:][0]
    return mat0,mat1

改为：

def binSplitDataSet(dataSet, feature, value):
    mat0 = dataSet[np.nonzero(dataSet[:,feature] > value)[0],:]
    mat1 = dataSet[np.nonzero(dataSet[:,feature] <= value)[0],:]
    return mat0,mat1

第二处：

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()#这里错了
        dataMat.append(fltLine)
    return dataMat

改为：

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 = list(map(float,curLine)) #map all elements to float()
        dataMat.append(fltLine)
    return dataMat

参考：https://www.cnblogs.com/lilinpging/p/8601507.html
https://blog.csdn.net/chixujohnny/article/details/51773802
第三处：

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 = np.shape(dataSet)
    #the choice of the best feature is driven by Reduction in RSS error from mean
    S = errType(dataSet)
    bestS = np.inf; bestIndex = 0; bestValue = 0
    for featIndex in range(n-1):
        for splitVal in set((dataSet[:,featIndex].T.A.tolist())[0]):#这一行改成这样
            mat0, mat1 = binSplitDataSet(dataSet, featIndex, splitVal)
            if (np.shape(mat0)[0] < tolN) or (np.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 (np.shape(mat0)[0] < tolN) or (np.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

参考：https://blog.csdn.net/PIPIXIU/article/details/78127793