使用python对决策树算法进行学习

#-*-coding:utf-8-*-
from math import log
import operator

def calcShanonEnt(dataSet):
    '''
    计算给定数据集的香农熵
    :param dataSet:
    :return:shanonEnt
    '''
    numEntries = len(dataSet)
    labelCounts={}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel]=0
        labelCounts[currentLabel] +=1
    shanonEnt = 0.0
    for key in labelCounts:
        prob= float(labelCounts[key])/numEntries
        shanonEnt -= prob*log(prob,2)
    return shanonEnt
def splitDataSet(dataSet,axis,value):
    '''
    按照给特定特征划分数据集
    :param dataSet:
    :param axis:
    :param value:
    :return:
    '''
    retDataSet=[]
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]
            reducedFeatVec.extend(featVec[ax