机器学习实战-树回归
from numpy import *
def loadDataSet(filename):
dataMat = []
fr = open(filename)
for line in fr.readlines():
curLine = line.strip().split('\t')
fltLine = list(map(float, curLine))
dataMat.append(fltLine)
return dataMat
#根据阈值分割数据集
def binSplitDataSet(dataSet, feature, value):
mat0 = dataSet[nonzero(dataSet[:,feature] > value)[0], :]
mat1 = dataSet[nonzero(dataSet[:,feature] <= value)[0], :]
return mat0, mat1
#叶子结点的平均值
def regLea
...