#计算熵
def calcEnt(data):
num = len(data)
labelCounts = {}
for item in data:
label = item[-1]
if label not in labelCounts.keys():labelCounts[label] = 0
labelCounts[label] += 1
ent = 0
for key in labelCounts:
prob = labelCounts[key]*1.0/num
ent -= prob * log(prob,2)
return ent
#划分数据 根据某一特征axis 取出该特征某一特定值value的数据
def splitData(dataSet,axis,value):
retData=[]
for item in dataSet:
if item[axis]==value:
newItem = item[:axis]
newItem.extend(item[axis+1:])
retData.append(newItem)
return retData
#从特种中选择最好的方式 增益最高
def chooseBestFeature(dataSet):
numFeat = len(dataSet[0]) - 1
## 初始化 信息熵 最佳信息增益 最佳特征
baseEnt = calcEnt(dataSet)
bestGain = 0
bestFeat = -1
for i in range(numFeat):
##获取第i个特征的所有取值
uniFeats = set([item[i] for item in dataSet])
newEnt = 0
##计算按第i个特征分类的熵
for value in uniFeats:
##第i个特征值 value的概率
subData = splitData(dataSet,i,value)
prob = float(len(subData))/len(dataSet)
newEnt += prob * calcEnt(subData)
gain = baseEnt - newEnt
if gain>bestGain:
bestGain = gain
bestFeat = i
return bestFeat
## 返回类别最高的分类
def majorityCnt(classList):
classCount={}
for vote in classList:
if vote not in classCount.keys():
classCount[vote]=0
classCount[vote]+=1
sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
return sortedClassCount[0][0]
#建立表
def createTree(dataSet,labels):
classList = [item[-1] for item in dataSet]
##只包含一种分类 返回该分类
if len(set(classList))==1:
return classList[0]
if len(dataSet[0])==1:
return majorityCnt(classList)
uniFeats = set([item[bestFeat] for item in dataSet])
for value in uniFeats:
function(){ //外汇返佣 http://www.fx61.com/
subLabels = labels[:]
##根据不同的value 继续建立子分支
myTree[bestFeatLabel][value] = createTree(splitData(dataSet,bestFeat,value),subLabels)
return myTree