数据科学 9 机器学习： 决策树2

• g(D2,A1) = H(D2) - H(D2 | A1) = 0.251
• g(D2,A2) = H(D2) - H(D2 | A2) = 0.918

• g(D2,A3) = H(D2) - H(D2 | A3) = 0.474

  
  

# 构建出来的结果
{'有自己的房子': {0: {'有工作': {0: 'no', 1: 'yes'}}, 1: 'yes'}}

"""
函数说明:统计classList中出现此处最多的元素(类标签)
Parameters:
    classList - 类标签列表
Returns:
    sortedClassCount[0][0] - 出现此处最多的元素(类标签)
"""
def majorityCnt(classList):
    classCount = {}
    for vote in classList: #统计classList中每个元素出现的次数
        if vote not in classCount.keys():classCount[vote] = 0
        classCount[vote] += 1
    sortedClassCount = sorted(classCount.items(), key = operator.itemgetter(1), reverse = True) #根据字典的值降序排序
    return sortedClassCount[0][0] #返回classList中出现次数最多的元素

"""
函数说明:创建决策树
Parameters:
    dataSet - 训练数据集
    labels - 分类属性标签
    featLabels - 存储选择的最优特征标签
Returns:
    myTree - 决策树
"""
def createTree(dataSet, labels, featLabels):
    classList = [example[-1] for example in dataSet] #取分类标签(是否放贷:yes or no)
    if classList.count(classList[0]) == len(classList): #如果类别完全
相同则停止继续划分
        return classList[0]
    if len(dataSet[0]) == 1: #遍历完所有特征时返回出现次数最多的类标签
        return majorityCnt(classList)
    bestFeat = chooseBestFeatureToSplit(dataSet) #选择最优特征
    bestFeatLabel = labels[bestFeat] #最优特征的标签
    featLabels.append(bestFeatLabel)
    myTree = {bestFeatLabel:{}} #根据最优特征的标签生成树
    del(labels[bestFeat]) #删除已经使用特征标签
    featValues = [example[bestFeat] for example in dataSet] #得到训练集中所有最优特征的属性值
    uniqueVals = set(featValues) #去掉重复的属性值
    for value in uniqueVals: #遍历特征，创建决策树。
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet,bestFeat, value), labels, featLabels)
    return myTree

if __name__ == '__main__':
    dataSet, labels = createDataSet()
    featLabels = []
    myTree = createTree(dataSet, labels, featLabels)
    print(myTree)

"""
函数说明:使用决策树分类
Parameters:
    inputTree - 已经生成的决策树
    featLabels - 存储选择的最优特征标签
    testVec - 测试数据列表，顺序对应最优特征标签
Returns:
    classLabel - 分类结果
"""
def classify(inputTree, featLabels, testVec):
    firstStr = next(iter(inputTree))
    #获取决策树结点
    secondDict = inputTree[firstStr]
    #下⼀个字典
    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

if __name__ == '__main__':
    dataSet, labels = createDataSet()
    featLabels = []
    myTree = createTree(dataSet, labels, featLabels)
    testVec = [0,1] #测试数据
    result = classify(myTree, featLabels, testVec)
    if result == 'yes':
        print('放贷')
    if result == 'no':
        print('不放贷')

import pickle
"""
函数说明:存储决策树
Parameters:
    inputTree - 已经生成的决策树
    filename - 决策树的存储文件名
Returns:
    无
"""
def storeTree(inputTree, filename):
    with open(filename, 'wb') as fw:
        pickle.dump(inputTree, fw)

if __name__ == '__main__':
    myTree = {'有自己的房子': {0: {'有工作': {0: 'no', 1: 'yes'}}, 1: 'yes'}}
    storeTree(myTree, 'classifierStorage.txt')

import pickle
"""
函数说明:读取决策树
Parameters:
    filename - 决策树的存储文件名
Returns:
    pickle.load(fr) - 决策树字典
"""
def grabTree(filename):
    fr = open(filename, 'rb')
    return pickle.load(fr)

if __name__ == '__main__':
    myTree = grabTree('classifierStorage.txt')
    print(myTree)