def calcGini(dataSet):numEntries=len(dataSet)labelCounts={}#给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]=0labelCounts[currentLabel]+=1Gini=1.0#以2为底数计算香农熵for key in labelCounts:prob = float(labelCounts[key])/numEntriesGini-=prob*probreturn Gini

def splitDataSet(dataSet,axis,value):retDataSet=[]for featVec in dataSet:if featVec[axis]==value:reducedFeatVec=featVec[:axis]reducedFeatVec.extend(featVec[axis+1:])retDataSet.append(reducedFeatVec)return retDataSet

def splitContinuousDataSet(dataSet,axis,value,direction):retDataSet=[]for featVec in dataSet:if direction==0:if featVec[axis]>value:reducedFeatVec=featVec[:axis]reducedFeatVec.extend(featVec[axis+1:])retDataSet.append(reducedFeatVec)else:if featVec[axis]<=value:reducedFeatVec=featVec[:axis]reducedFeatVec.extend(featVec[axis+1:])retDataSet.append(reducedFeatVec)return retDataSet

def chooseBestFeatureToSplit(dataSet,labels):numFeatures=len(dataSet[0])-1bestGiniIndex=100000.0bestFeature=-1bestSplitDict={}for i in range(numFeatures):featList=[example[i] for example in dataSet]#对连续型特征进行处理if type(featList[0]).__name__=='float' or type(featList[0]).__name__=='int':#产生n-1个候选划分点sortfeatList=sorted(featList)splitList=[]for j in range(len(sortfeatList)-1):splitList.append((sortfeatList[j]+sortfeatList[j+1])/2.0)bestSplitGini=10000slen=len(splitList)#求用第j个候选划分点划分时，得到的信息熵，并记录最佳划分点for j in range(slen):value=splitList[j]newGiniIndex=0.0subDataSet0=splitContinuousDataSet(dataSet,i,value,0)subDataSet1=splitContinuousDataSet(dataSet,i,value,1)prob0=len(subDataSet0)/float(len(dataSet))newGiniIndex+=prob0*calcGini(subDataSet0)prob1=len(subDataSet1)/float(len(dataSet))newGiniIndex+=prob1*calcGini(subDataSet1)if newGiniIndex<bestSplitGini:bestSplitGini=newGiniIndexbestSplit=j#用字典记录当前特征的最佳划分点bestSplitDict[labels[i]]=splitList[bestSplit]GiniIndex=bestSplitGini#对离散型特征进行处理else:uniqueVals=set(featList)newGiniIndex=0.0#计算该特征下每种划分的信息熵for value in uniqueVals:subDataSet=splitDataSet(dataSet,i,value)prob=len(subDataSet)/float(len(dataSet))newGiniIndex+=prob*calcGini(subDataSet)GiniIndex=newGiniIndexif GiniIndex<bestGiniIndex:bestGiniIndex=GiniIndexbestFeature=i#若当前节点的最佳划分特征为连续特征，则将其以之前记录的划分点为界进行二值化处理#即是否小于等于bestSplitValue#并将特征名改为 name<=value的格式if type(dataSet[0][bestFeature]).__name__=='float' or type(dataSet[0][bestFeature]).__name__=='int':      bestSplitValue=bestSplitDict[labels[bestFeature]]        labels[bestFeature]=labels[bestFeature]+'<='+str(bestSplitValue)for i in range(shape(dataSet)[0]):if dataSet[i][bestFeature]<=bestSplitValue:dataSet[i][bestFeature]=1else:dataSet[i][bestFeature]=0return bestFeature

def majorityCnt(classList):classCount={}for vote in classList:if vote not in classCount.keys():classCount[vote]=0classCount[vote]+=1return max(classCount)

def classify(inputTree,featLabels,testVec):firstStr=list(inputTree.keys())[0]if '<=' in firstStr:featvalue=float(re.compile("(<=.+)").search(firstStr).group()[2:])featkey=re.compile("(.+<=)").search(firstStr).group()[:-2]secondDict=inputTree[firstStr]featIndex=featLabels.index(featkey)if testVec[featIndex]<=featvalue:judge=1else:judge=0for key in secondDict.keys():if judge==int(key):if type(secondDict[key]).__name__=='dict':classLabel=classify(secondDict[key],featLabels,testVec)else:classLabel=secondDict[key]else:secondDict=inputTree[firstStr]featIndex=featLabels.index(firstStr)for key in secondDict.keys():if testVec[featIndex]==key:if type(secondDict[key]).__name__=='dict':classLabel=classify(secondDict[key],featLabels,testVec)else:classLabel=secondDict[key]return classLabeldef testing(myTree,data_test,labels):error=0.0for i in range(len(data_test)):if classify(myTree,labels,data_test[i])!=data_test[i][-1]:error+=1print ('myTree %d' %error)return float(error)def testingMajor(major,data_test):error=0.0for i in range(len(data_test)):if major!=data_test[i][-1]:error+=1print ('major %d' %error)return float(error)

def createTree(dataSet,labels,data_full,labels_full,data_test):classList=[example[-1] for example in dataSet]if classList.count(classList[0])==len(classList):return classList[0]if len(dataSet[0])==1:return majorityCnt(classList)temp_labels=copy.deepcopy(labels)bestFeat=chooseBestFeatureToSplit(dataSet,labels)bestFeatLabel=labels[bestFeat]myTree={bestFeatLabel:{}}if type(dataSet[0][bestFeat]).__name__=='str':currentlabel=labels_full.index(labels[bestFeat])featValuesFull=[example[currentlabel] for example in data_full]uniqueValsFull=set(featValuesFull)featValues=[example[bestFeat] for example in dataSet]uniqueVals=set(featValues)del(labels[bestFeat])#针对bestFeat的每个取值，划分出一个子树。for value in uniqueVals:subLabels=labels[:]if type(dataSet[0][bestFeat]).__name__=='str':uniqueValsFull.remove(value)myTree[bestFeatLabel][value]=createTree(splitDataSet\(dataSet,bestFeat,value),subLabels,data_full,labels_full,\splitDataSet(data_test,bestFeat,value))if type(dataSet[0][bestFeat]).__name__=='str':for value in uniqueValsFull:myTree[bestFeatLabel][value]=majorityCnt(classList)#进行测试，若划分没有提高准确率，则不进行划分，返回该节点的投票值作为节点类别if testing(myTree,data_test,temp_labels)<testingMajor(majorityCnt(classList),data_test):return myTreereturn majorityCnt(classList)