Python实现天气决策树模型

from math import log
import operator

def calcShannonEnt(dataSet): #计算数据的熵
    numEntries=len(dataSet) #数据条数
    labelCounts={}
    for featVec in dataSet:
        currentLabel=featVec[-1]#每一行最后一个字（类别）
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel]=0
        labelCounts[currentLabel]+=1 #统计有多少个类似以及每个类的数量
    shannonEnt=0
    for key in labelCounts:
        prob=float(labelCounts[key])/numEntries #计算单个类的熵值
        shannonEnt-=prob*log(prob,2)#累加每个类的熵值
        return shannonEnt
    
def createDataSet1(): #创建示例数据
    dataSet = [[‘晴天‘,‘高温‘,‘中湿‘,‘无风‘,‘不宜‘],
               [‘晴天‘,‘高温‘,‘中湿‘,‘有风‘,‘不宜‘],
               [‘多云‘,‘高温‘,‘低湿‘,‘无风‘,‘适宜‘],
               [‘雨天‘,‘低温‘,‘高湿‘,‘无风‘,‘适宜‘],
               [‘雨天‘,‘低温‘,‘低湿‘,‘无风‘,‘适宜‘],
               [‘雨天‘,‘低温‘,‘低湿‘,‘有风‘,‘不宜‘],
               [‘多云‘,‘低温‘,‘低湿‘,‘有风‘,‘适宜‘],
               [‘晴天‘,‘中温‘,‘高湿‘,‘无风‘,‘不宜‘],
               [‘晴天‘,‘低温‘,‘低湿‘,‘无风‘,‘适宜‘],
               [‘雨天‘,‘中温‘,‘低湿‘,‘无风‘,‘适宜‘],
               [‘晴天‘,‘中温‘,‘低湿‘,‘有风‘,‘适宜‘],
               [‘多云‘,‘中温‘,‘中湿‘,‘有风‘,‘适宜‘],
               [‘多云‘,‘高温‘,‘低湿‘,‘无风‘,‘适宜‘],
               [‘雨天‘,‘中温‘,‘低湿‘,‘有风‘,‘不宜‘]]
    labels = [‘天气‘,‘温度‘,‘湿度‘,‘风况‘]#两个特征
    return dataSet,labels

def splitDataSet(dataSet,axis,value):#按某个特征分类后的数据
    retDataSet=[]
    for featVec in dataSet:
        if featVec[axis]==value:
            reducedFeatVec = featVec[:axis]
            reducedFeatVec.extend(featVec[axis+1:])
            retDataSet.append(reducedFeatVec)
    return retDataSet

def chooseBestFeatureToSplit(dataSet): #选择最优的分类特征
    numFeatures = len(dataSet[0])-1
    baseEntropy = calcShannonEnt(dataSet)#原始的熵
    bestInfoGain = 0
    bestFeature = -1
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]
        uniqueVals = set(featList)
        newEntropy = 0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet,i,value)
            prob = len(subDataSet)/float(len(dataSet))
            newEntropy +=prob*calcShannonEnt(subDataSet)#按特征分类后的熵
        infoGain = baseEntropy - newEntropy #原始熵与按特征分类后的熵的差值
        if (infoGain>bestInfoGain):#若按某特征划分后，熵值减少的最大，则次特征为最优分类特征
           bestInfoGain=infoGain
           bestFeature = i
    return bestFeature
 
def majorityCnt(classList):#按分类后类别数量排序，比如：最后分类为两男一女，则判断为男：
    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]

def createTree(dataSet,labels):
    classList=[example[-1] for example in dataSet] #类别：男女
    if classList.count(classList[0])==len(classList):
       return classList[0]
    if len(dataSet[0])==1:
        return majorityCnt(classList)
    bestFeat=chooseBestFeatureToSplit(dataSet)#选择最优特征
    bestFeatLabel=labels[bestFeat]
    myTree={bestFeatLabel:{}}#分类结果以字典的形式保存
    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

if __name__==‘__main__‘:
    dataSet, labels=createDataSet1()#创造示例数据
    print(createTree(dataSet,labels))#输出决策树模型