机器学习实战，第三章，临时代码

#coding=utf-8

from math import log

def calcShannonEnt(dataSet):

    numEntries=len(dataSet)

    labelCounts={}

    # 为所有可能分类创建字典

    for featVec in dataSet:

        currentLabel=featVec[-1]

        if currentLabel not in labelCounts.keys():

            labelCounts[currentLabel]=0

            labelCounts[currentLabel]+=1

    shannonEnt=0.0 # 香农熵

    for key in labelCounts:

        prob=float(labelCounts[key])/numEntries

        shannonEnt-=prob*log(prob,2) # 以2为底求对数

    return shannonEnt



def createDataSet():

    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):

    # python在函数中传递的是列表的引用，在函数内部对列表对象的修改，

    # 将会影响该列表对象的整个生存周期。所以需要在函数的开始声明新的list