手动实现决策树（ID3算法）

rom math import log
import operator
#计算熵
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 * log(prob, 2)
    return shannonent
#计算Gini指数
def calcGini(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if (currentLabel not in labelCounts.keys()):
            labelCounts[currentLabel] = 0
        labelCounts[currentLabel] += 1
    Gini = 0
    for key in labelCounts:
        prob = float(labelCounts[key]) / numEntries
        Gini += (prob * prob)
    return 1.0 - Gini
#切分数据集
def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reduceFeatVec = featVec[:axis]
            reduceFeatVec.extend(featVec[axis + 1:])
            retDataSet.append(reduceFeatVec)
    return retDataSet

#选择最好的数据划分方式
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

#递归构建决策树
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):
        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[:]
        temp = splitDataSet(dataSet, bestFeat, value)
        myTree[bestFeatLabel][value] = createTree(temp, subLabels)
    return myTree



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
myDat, labels = createDataSet()
myTree = createTree(myDat, labels)
print (myTree)

数据集为：

no surfacing           flippers          fish

Yes                         Yes                Yes

Yes                         Yes                Yes

Yes                         No                 No

No                         Yes                 No

No                         Yes                 No

 

输出结果：

{'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}