linux中利用python计算熵

熵反应信息的混乱程度熵的计算公式为

p*log(p,2)对每个分类的概率进行求和，值越大反应信息越混乱，用python实现的代码:

from math import log
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=shannonEnt-prob*log(prob,2)
	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
myDat,labels=createDataset()
print myDat
shan=calcShannonEnt(myDat)
print shan