关联分析--Apriori算法

把机器学习实战上的代码敲了一遍
由于python2报错的地方修改了
仅供参考

def loadDataSet():
    return [[1,3,4],[2,3,5],[1,2,3,5],[2,5]]

def createC1(dataSet):
    C1=[]
    for transaction in dataSet:
        for item in transaction:
            if [item] not in C1:
                C1.append([item])
    C1.sort()
    return list(map(frozenset,C1)) # 创建不可变的集合

def scanD(D,Ck,minSupport):
    ssCnt={}
    for tid in D:
        for can in Ck:
            if can.issubset(tid):
                if  can  not in ssCnt:
                    ssCnt[can]=1  #python3里没有has_key
                else:
                    ssCnt[can]+=1
    numItems=float(len(D))
    retList=[]
    supportData={}
    for key in ssCnt:
        support=ssCnt[key]/numItems
        if support>=minSupport:
            retList.insert(0,key)
        supportData[key]=support
    return retList,supportData

# 测试
# C1=createC1(dataSet)
# D=list(map(frozenset,dataSet))
# L1,supportData0=scanD(D,C1,0.5)
# print(L1,supportData0)


def aprioriGen(Lk, k): #creates Ck
    retList = []
    lenLk = len(Lk)
    for i in range(lenLk):
        for j in range(i+1, lenLk):
            L1 = list(Lk[i])[:k-2]; L2 = list(Lk[j])[:k-2]
            L1.sort(); L2.sort()
            if L1==L2:
                retList.append(Lk[i] | Lk[j])
    return retList

def apriori(dataSet, minSupport = 0.5):
    C1 = createC1(dataSet)
    D=list(map(frozenset, dataSet))
    L1, supportData = scanD(D, C1, minSupport)
    L = [L1]
    k = 2
    while (len(L[k-2]) > 0):
        Ck = aprioriGen(L[k-2], k)
        Lk, supK = scanD(D, Ck, minSupport)
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData


#关联规则函数
def generateRules(L,supportData,minConf=0.7):
    bigRuleList=[]
    for i in range(1,len(L)):
        for freqSet in L[i]:
            H1=[frozenset([item]) for item in freqSet]
            if(i>1):
                rulesFromConseq(freqSet,H1,supportData,bigRuleList,minConf)
            else:
                calcConf(freqSet,H1,supportData,bigRuleList,minConf)
    return  bigRuleList

def calcConf(freqSet,H,supportData,brl,minConf=0.7):
    prunedH=[] #频繁集长度大于2再划分时用到
    for conseq in H:
        conf=supportData[freqSet]/supportData[freqSet-conseq]
        if conf >=minConf:
            print(freqSet-conseq,'-->',conseq,'，可信度为：',conf)
            brl.append((freqSet-conseq,conseq,conf))
            prunedH.append(conseq)
    return prunedH

def rulesFromConseq(freqSet,H,supportData,brl,minConf=0.7):
    m=len(H[0])
    if len(freqSet)>(m+1):
        Hmp1=aprioriGen(H,m+1)
        Hmp1=calcConf(freqSet,Hmp1,supportData,brl,minConf)
        if(len(Hmp1)>1):
            rulesFromConseq(freqSet,Hmp1,supportData,brl,minConf)


# 测试
dataSet=loadDataSet()
L, supportData=apriori(dataSet)
rules=generateRules(L,supportData,0.5)