机器学习实战代码3-4

def createTree(dataSet,labels):
    classList = [example[-1] for example in dataSet]
    if classList.count(classList[0]) == len(classList): 
        return classList[0]#stop splitting when all of the classes are equal#所有的类标签都相同，直接返回该类标签
    if len(dataSet[0]) == 1: #stop splitting when there are no more features in dataSet，#使用完了所有特征，仍然不能将数据集划分成仅包含唯一类别的分组，则返回出现次数最多的类别
        return majorityCnt(classList)
    bestFeat = chooseBestFeatureToSplit(dataSet)#当前数据集选取的最好特征
    print "bestFeat:",bestFeat
    bestFeatLabel = labels[bestFeat]#当前选取的最好特征与之对应的标签
    print "bestFeatLabel:",bestFeatLabel

    #开始创建树
    myTree = {bestFeatLabel:{}}
    del(labels[bestFeat])
    featValues = [example[bestFeat] for example in dataSet]
    uniqueVals = set(featValues)
    for value in uniqueVals:
        subLabels = labels[:]       #copy all of labels, so trees don't mess up existing labels
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels)#递归了
    return myTree