机器学习实战——决策树

from math import log

#以决策为标准计算信息熵
def calcShannonEnt(dataSet):
    numEntries  = len(dataSet)
    labelCounts = {}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel] = 0
        labelCounts[currentLabel] += 1
    shannonEnt = 0.0
    for key in labelCounts:
        prob = float(labelCounts[key])/numEntries
        shannonEnt -= prob *log(prob,2)
    return shannonEnt

def creatDataSet():
    dataSet = [[1,1,'yes'],[1,1,'yes'],[1,0,'no'],[0,1,'no'],[0,1,'no']]
    labels = ['no surfacing','flippers']
    return dataSet,labels

def splitDataSet(dataSet,axis,value):
    retDataSet = []#根据特征新建链表
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]
            re