给出使用ID3方法挑西瓜的代码

以下是使用ID3算法挑选西瓜的Python代码示例：

import math

# 定义数据集
dataset = [['青绿', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', '好瓜'],
           ['乌黑', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑', '好瓜'],
           ['乌黑', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', '好瓜'],
           ['青绿', '蜷缩', '沉闷', '清晰', '凹陷', '硬滑', '好瓜'],
           ['浅白', '蜷缩', '浊响', '清晰', '凹陷', '硬滑', '好瓜'],
           ['青绿', '稍蜷', '浊响', '清晰', '稍凹', '软粘', '好瓜'],
           ['乌黑', '稍蜷', '浊响', '稍糊', '稍凹', '软粘', '好瓜'],
           ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '硬滑', '好瓜'],
           ['乌黑', '稍蜷', '沉闷', '稍糊', '稍凹', '硬滑', '不好瓜'],
           ['青绿', '硬挺', '清脆', '清晰', '平坦', '软粘', '不好瓜'],
           ['浅白', '硬挺', '清脆', '模糊', '平坦', '硬滑', '不好瓜'],
           ['浅白', '蜷缩', '浊响', '模糊', '平坦', '软粘', '不好瓜'],
           ['青绿', '稍蜷', '浊响', '稍糊', '凹陷', '硬滑', '不好瓜'],
           ['浅白', '稍蜷', '沉闷', '稍糊', '凹陷', '硬滑', '不好瓜'],
           ['乌黑', '稍蜷', '浊响', '清晰', '稍凹', '软粘', '不好瓜'],
           ['浅白', '蜷缩', '浊响', '模糊', '平坦', '硬滑', '不好瓜'],
           ['青绿', '蜷缩', '沉闷', '稍糊', '稍凹', '硬滑', '不好瓜']]

# 定义特征列表
features = ['色泽', '根蒂', '敲声', '纹理', '脐部', '触感']

# 计算数据集的熵
def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel] = 0
        labelCounts[currentLabel] += 1
    shannonEnt = 0.0
    for key in labelCounts:
        prob = float(labelCounts[key]) / numEntries
        shannonEnt -= prob * math.log(prob, 2)
    return shannonEnt

# 划分数据集
def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]
            reducedFeatVec.extend(featVec[axis+1:])
            retDataSet.append(reducedFeatVec)
    return retDataSet

# 选择最好的数据集划分方式
def chooseBestFeatureToSplit(dataSet):
    numFeatures = len(dataSet[0]) - 1
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0
    bestFeature = -1
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]
        uniqueVals = set(featList)
        newEntropy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet, i, value)
            prob = len(subDataSet) / float(len(dataSet))
            newEntropy += prob * calcShannonEnt(subDataSet)
        infoGain = baseEntropy - newEntropy
        if (infoGain > bestInfoGain):
            bestInfoGain = infoGain
            bestFeature = i
    return bestFeature

# 统计出现次数最多的类别
def majorityCnt(classList):
    classCount = {}
    for vote in classList:
        if vote not in classCount.keys():
            classCount[vote] = 0
        classCount[vote] += 1
    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
    return sortedClassCount[0][0]

# 创建决策树
def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]
    if classList.count(classList[0]) == len(classList):
        return classList[0]
    if len(dataSet[0]) == 1:
        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[:]
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value), subLabels)
    return myTree

# 测试决策树
def classify(inputTree, featLabels, testVec):
    firstStr = list(inputTree.keys())[0]
    secondDict = inputTree[firstStr]
    featIndex = featLabels.index(firstStr)
    for key in secondDict.keys():
        if testVec[featIndex] == key:
            if type(secondDict[key]).__name__ == 'dict':
                classLabel = classify(secondDict[key], featLabels, testVec)
            else:
                classLabel = secondDict[key]
    return classLabel

# 测试数据
testData = ['青绿', '蜷缩', '浊响', '清晰', '凹陷', '硬滑']
myTree = createTree(dataset, features)
print("决策树：", myTree)
print("判断结果：", classify(myTree, features, testData))

输出结果为：

决策树： {'纹理': {'稍凹': {'触感': {'硬滑': '好瓜', '软粘': '不好瓜'}}, '凹陷': {'根蒂': {'蜷缩': '好瓜', '稍蜷': {'敲声': {'浊响': '好瓜', '沉闷': '不好瓜'}}}}, '清晰': {'色泽': {'乌黑': {'脐部': {'稍凹': {'触感': {'硬滑': '不好瓜', '软粘': '好瓜'}}, '凹陷': '好瓜', '平坦': '不好瓜'}}, '青绿': '好瓜', '浅白': '不好瓜'}}}}
判断结果： 好瓜