【无标题】

from numpy import *
def loadDataSet():
    return [['A','C','D'],
            ['B','C','E'],
            ['A','B','C','E'],
            ['B','E']]

def create(dataSet):
    C1 = []
    for transaction in dataSet:
        for item in transaction:
            if not[item] in C1:
                C1.append([item])
    C1.sort()
    return list(map(frozenset,C1))

def scanD(dataSet,Ck,minSupport):
    ssCnt = {}
    for tid in dataSet:
        for can in Ck:
            if can.issubset(tid):
                ssCnt[can] = ssCnt.get(can,0) +1
    retList=[]
    supportData={}
    for key in ssCnt:
        support = ssCnt[key]
        if support>=minSupport:
            retList.insert(0,key)
            supportData[key]=support
    print(supportData)
    return retList,supportData

def aprioriGen(Lk,k):
    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=2):
    C1=create(dataSet)
    D=list(map(set,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)
        L.append(Lk);supportData.update(supK)
        k+=1
    return L,supportData

if __name__ == '__main__':
    dataSet=loadDataSet()
    L,supportData=apriori(dataSet,minSupport=2)
     # print(L,supportData)