机器学习-决策树算法代码详解

ゞ浴缸里的玫瑰 2022-06-05 06:39 307阅读 0赞

from imp import reload
    from math import log
    import operator
    
    def createDataSet():
        dataSet = [[1, 1, 'yes'],
                   [1, 1, 'yes'],
                   [1, 0, 'no'],
                   [0, 1, 'no'],
                   [0, 1, 'no']]
        labels = ['no surfacing','flippers']
        #change to discrete values
        return dataSet, labels
    
    def calcShannonEnt(dataSet):#dateset is a n*m
        numEntries = len(dataSet)#the row of the dateset,n
        labelCounts = {}#this is a dict,used to count the lables
        for featVec in dataSet: #the the number of unique elements and their occurance
            currentLabel = featVec[-1]#featVec is a list ,it is the row of the dateset
            if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] = 0
            labelCounts[currentLabel] += 1
        shannonEnt = 0.0
        for key in labelCounts:#key is the KEY,and lableCounts[key] is its value
            prob = float(labelCounts[key])/numEntries#统计所有的不同标签出现的频次，计算他出现的概率
            shannonEnt -= prob * log(prob,2) #log base 2，count shannnonEnt
        return shannonEnt
        
    def splitDataSet(dataSet, axis, value):
        retDataSet = []#this is an empty list
        for featVec in dataSet:#featVec is the row of the dateset
            if featVec[axis] == value:#axis is its place where you want to split
                reducedFeatVec = featVec[:axis]     #chop out axis used for splitting
                reducedFeatVec.extend(featVec[axis+1:])#[1,2,3]extend[4,5]=[1,2,3,4,5]
                retDataSet.append(reducedFeatVec)#[1,2,3]append[4,5]=[1,2,3,[4,5]]
        return retDataSet
        
    def chooseBestFeatureToSplit(dataSet):
        numFeatures = len(dataSet[0]) - 1      #the last column is used for the labels.the value of len(dataSet[0])is its number of collos,the value of len(dateset))is its number of rows
        baseEntropy = calcShannonEnt(dataSet)#count the original shannonEnt
        bestInfoGain = 0.0; bestFeature = -1
        for i in range(numFeatures):        #iterate over all the features，每行有多少列，即有多少个分类特征，遍历所有分类特征，选取划分后ShannonEnt最小的特征为划分结果
            featList = [example[i] for example in dataSet]#create a list of all the examples of this feature,example include many row-list of the dataSet,example[i] is the ith value of the dataSet
            uniqueVals = set(featList)       #get a set of unique values#$# alist=[example[i] for example in dataSet],you can get a total column of dataSet
            newEntropy = 0.0
            for value in uniqueVals:#计算当前列出现所有结果分割下的ShannonEnt
                subDataSet = splitDataSet(dataSet, i, value)#利用dataSet的每一列中出现的所有的uniqueVals分割dataset，计算概率和shannonEnt,并求和
                prob = len(subDataSet)/float(len(dataSet))
                newEntropy += prob * calcShannonEnt(subDataSet)     
            infoGain = baseEntropy - newEntropy     #calculate the info gain; ie reduction in entropy
            if (infoGain > bestInfoGain):       #compare this to the best gain so far
                bestInfoGain = infoGain         #if better than current best, set to best
                bestFeature = i                 #the ith feature is the better feature for now
        return bestFeature                      #returns an integer
    
    def majorityCnt(classList):
        classCount={}
        for vote in classList:
            if vote not in classCount.keys(): classCount[vote] = 0
            classCount[vote] += 1
        sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
        return sortedClassCount[0][0]
    
    def createTree(dataSet,labels):
        classList = [example[-1] for example in dataSet]
        if classList.count(classList[0]) == len(classList): #第一个停止条件
            return classList[0]#stop splitting when all of the classes are equal
        if len(dataSet[0]) == 1: #stop splitting when there are no more features in dataSet
            return majorityCnt(classList)
        bestFeat = chooseBestFeatureToSplit(dataSet)#the return is an Int,which is a place of the row of the column`s feature，The best feature
        bestFeatLabel = labels[bestFeat]#特征中的一个
        myTree = {bestFeatLabel:{}}#创建一个树的字典
        del(labels[bestFeat])
        featValues = [example[bestFeat] for example in dataSet]#featValues是得到当前这一列特征的所有表达
        uniqueVals = set(featValues)
        for value in uniqueVals:
            subLabels = labels[:]       #copy all of labels, so trees don't mess up existing labels，在python中，参数是列表类型时，是按照引用方式传递，会改变他的值
            myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels)
            #value的值是上字典key bestFeatLable对应的值，但同时value也是一个字典，value是该字典的key，等号右边的部分是key下的值，该值同时可能又是一个字典
        return myTree
    '''
                bestFeatLabel='sunshine'
                myTree = {bestFeatLabel:{}}
                uniqueVals=['rain','mud','wind']
                for value in uniqueVals:
                myTree[bestFeatLabel][value]={"a dog"}
                print(myTree)
                >>{'sunshine': {'rain': {'a dog'}, 'mud': {'a dog'}, 'wind': {'a dog'}}}
                        
    '''
    
        
    def classify(inputTree,featLabels,testVec):#inputtree是已经生成了的树，testvec是测试向量，featlable是测试向量对应位置的标签
        firstStr = inputTree.keys()[0]
        secondDict = inputTree[firstStr]
        featIndex = featLabels.index(firstStr)
        key = testVec[featIndex]#判断测试向量在该分类下的值是否是决策树的叶节点，如果不是则继续递归判断，如果是，返回分类结果
        valueOfFeat = secondDict[key]
        if isinstance(valueOfFeat, dict): 
            classLabel = classify(valueOfFeat, featLabels, testVec)
        else: classLabel = valueOfFeat
        return classLabel