西瓜书 课后习题4.3 基于信息熵决策树，连续和离散属性，并验证模型

import matplotlib.pyplot as plt
import numpy as np
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[1:9]
        dataset = []
        for line in reader:
            tempVect = line[1:10]
            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]) / numdata
        infoEnt -= (prop * log(prop, 2))
    return infoEnt


def bestFeatureSplit(dataset):
    '''
    最优属性划分
    :param dataset: 输入需要划分的数据集
    :return:  返回最优划分属性的下标
    '''
    numFeature = len(dataset[0]) - 1
    baseInfoEnt = infoEnt(dataset)
    bestInfoGain = 0
    bestFeature = -1
    bestSplitPoint = None
    continuous = False
    for i in range(numFeature):
        featList = [example[i] for example in dataset]
        newEnt = 0
        if all(c in "0123456789.-" for c in featList[0]):  # 连续属性
            continuous = True
            featList.sort()
            tempFeatList = [float(feat) for feat in featList]  # 字符串转换成数字,用set(featList)会出现结果不稳定
            mediumPoints = []
            for index in range(len(tempFeatList) - 1):
                mediumPoints.append((tempFeatList[index] + tempFeatList[index + 1]) / 2)
            for point in mediumPo