决策树的python实现方法

#还是没有算完，这时候就会采用多数表决的方式计算节点分类
def majorityCnt(classList):
    classCount = {}
    for vote in classList:
        if vote not in classCount.keys():
            classCount[vote] = 0
        classCount[vote] += 1
    return max(classCount)        
   
def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]
    if classList.count(classList[0]) ==len(classList):#类别相同则停止划分
        return classList[0]
    if len(dataSet[0]) == 1:#所有特征已经用完
        return majorityCnt(classList)
    bestFeat = chooseBestFeatureToSplit(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel:{}}
    del(labels[bestFeat])
    featValues = [example[bestFeat] for example in dataSet]
    uniqueVals = set(featValues)
    for value in uniqueVals:
        subLabels = labels[:]#为了不改变原始列表的内容复制了一下
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet,
                                        bestFeat, value),subLabels)
    return myTree
   
def main():
    data,label = createDataSet()
    t1 = time.clock()
    myTree = createTree(data,label)
    t2 = time.clock()
    print myTree
    print 'execute for ',t2-t1
if __name__=='__main__':
    main()

希望本文所述对大家的Python程序设计有所帮助。