李航 统计学习 例5.3 利用ID3算法建立决策树

from numpy import *
from math import log
import operator

def calcShannonEnt(dataset):
    numdataset=len(dataset)
    labelCount={}
    for data in dataset:
        curlabel=data[-1]
        if curlabel not in labelCount.keys():
            labelCount[curlabel]=0
        labelCount[curlabel]+=1
    shannonEnt=0.0
    for key in labelCount:
        prob=float(labelCount[key])/numdataset
        shannonEnt-=prob*log(prob,2)
    return shannonEnt

def creatDataSet():
    dataset=[['青年','否','否','一般','否'],
             ['青年','否','否','好','否'],
             ['青年','是','否','好','是'],
             ['青年','是','是','一般','是'],
             ['青年','否','否','一般','否'],
             ['中年','否','否','一般',