Apriori算法进行关联分析

最后附上代码：

#加载数据集
def loadDataSet():
    return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]

#构建候选集C1
def createC1(dataSet):
    C1 = []
    for transaction in dataSet:
        for item in transaction:
            if not [item] in C1:
                C1.append([item])

    C1.sort()
    return C1               #use frozen set so we
                            #can use it as a key in a dict
dataSet=loadDataSet()
data=createC1(dataSet)
print(data)

#这个函数的作用是返回符合指定支持度的集合，它有三个参数，参数分别是数据集，候选项集列表CK,以及感兴趣项集的最小支持度minSupport
#这个函数用于从Ck生成Lk (k是指数字)
def scanD(D, Ck, minSupport):
    ssCnt = {}
    for tid in D:
        for can in Ck:
            if can.issubset(tid):
                if not ssCnt.has_key(can): ssCnt[can]=1
                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

#构建候选集Ck
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: #if first k-2 elements are equal
                retList.append(Lk[i] | Lk[j]) #set union
    return retList


#得到频繁项集
def apriori(dataSet, minSupport = 0.5):
    C1 = createC1(dataSet)   #构建初始的候选集
    D = map(set, dataSet)    #将dataSet映射为一个set
    L1, supportData = scanD(D, C1, minSupport)   #得到L1频繁项集
    L = [L1]
    k = 2
    while (len(L[k-2]) > 0):
        Ck = aprioriGen(L[k-2], k)   #构建候选集Ck
        Lk, supK = scanD(D, Ck, minSupport)#scan DB to get Lk
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData

#下面这些函数都是生成关联规则的，如A->B  只要发生A，那么B也会发生的概率称为可信度

#这个是主函数，L是频繁项集合，包含频繁项集合支持度的字典，minConf是最小置信度
def generateRules(L, supportData, minConf=0.7):  #supportData is a dict coming from scanD
    bigRuleList = []
    for i in range(1, len(L)):#only get the sets with two or more items
        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

#对规则进行评估
def calcConf(freqSet, H, supportData, brl, minConf=0.7):
    prunedH = [] #create new list to return
    for conseq in H:
        conf = supportData[freqSet]/supportData[freqSet-conseq] #calc confidence
        if conf >= minConf:
            print (freqSet-conseq,'-->',conseq,'conf:',conf)
            brl.append((freqSet-conseq, conseq, conf))
            prunedH.append(conseq)
    return prunedH

#生成候选规则集合

def rulesFromConseq(freqSet, H, supportData, brl, minConf=0.7):
    m = len(H[0])
    if (len(freqSet) > (m + 1)): #try further merging
        Hmp1 = aprioriGen(H, m+1)#create Hm+1 new candidates
        Hmp1 = calcConf(freqSet, Hmp1, supportData, brl, minConf)
        if (len(Hmp1) > 1):    #need at least two sets to merge
            rulesFromConseq(freqSet, Hmp1, supportData, brl, minConf)

def pntRules(ruleList, itemMeaning):
    for ruleTup in ruleList:
        for item in ruleTup[0]:
            print (itemMeaning[item])
        print ("           -------->")
        for item in ruleTup[1]:
            print (itemMeaning[item])
        print ("confidence: %f" % ruleTup[2])
        print  ()     #print a blank line