西瓜书决策树ID3算法实现，离散属性

from math import log
import operator
import csv


def readDataset(filename):
    '''
    读取数据
    :param filename: 数据文件名，CSV格式
    :return:  以列表形式返回数据列表和特征列表
    '''
    with open(filename) as f:
        reader = csv.reader(f)
        header_row = next(reader)
        labels = header_row[1:7]
        dataset = []
        for line in reader:
            tempVect = line[1:7]
            tempVect.append(line[7])
            dataset.append(tempVect)
    return dataset, labels


def infoEnt(dataset):
    '''
    计算信息熵
    :param dataset:  输入数据集
    :return:  返回信息熵
    '''
    numdata = len(dataset)
    labels = {}
    for featVec in dataset:
        label = featVec[-1]
        if label not in labels.keys():
            labels[label] = 0
        labels[label] += 1
    infoEnt = 0
    for lab in labels.keys():
        prop = float(labels[lab