决策树实现

from  math import logimport operator# 计算数据集的熵def calsShannonEnt(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 * log(prob, 2)    return shannonEnt#创建数据集def createDataSet():    dataSet = [[1, 1, 'yes'],               [1, 1, 'yes'],               [1, 0, 'no'],               [0, 1, 'no'],               [0, 1, 'no']]    labels = ['no surfacing', 'flippers']    return dataSet, labels#按照给定特征划分数据集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#选择划分数据集的最好特征def chooseBestFeatureToSplit(dataSet):    numFeatures = len(dataSet[0]) - 1    baseEntropy = calsShannonEnt(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 * calsShannonEnt(subDataSet)        infoGain = baseEntropy - newEntropy        if (infoGain > bestInfoGain):            bestInfoGain = infoGain            bestFeature = i    return bestFeature#多数表决决定叶子分类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=operator.itemgetter(1), reverse=True)    return sortedClassCount[0][0]#创建树结构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#分类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#序列化树结构def storeTree(inputTree, filename):    import pickle    fw = open(filename, 'wb')    pickle.dump(inputTree, fw)    fw.close()#反序列化树结构def grabTree(filename):    import pickle    fr = open(filename, 'rb')    return pickle.load(fr)