《机器学习第十一章Apriori算法实践》

from numpy import *

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

dataSet = loadDataSet()
##print(dataSet)

def createC1(dataSet):
    C1 = []
    for transaction in dataSet:
##        print(transaction)
        for item in transaction:
            if not [item] in C1:
                C1.append([item])
##                print(C1)
                
    C1.sort()
    return list(map(frozenset, C1))#use frozen set so we
                            #can use it as a key in a dict    


##C1 = createC1(dataSet)
##print(C1)
##D = list(map(set,dataSet))
##print(D)

def scanD(D, Ck, minSupport):
    ssCnt = {}
    for tid in D:
        for can in Ck:
            if can.issubset(tid):
                if can not in ssCnt.keys():
                    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


##retList,supportData = scanD(D,C1,0.5)
##print(retList)
##print(supportData)

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

##print(aprioriGen(retList,1))


def apriori(dataSet, minSupport = 0.5):
    C1 = createC1(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)#scan DB to get Lk
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData

L,suppData = apriori(dataSet)
print(L[0])
print(L[1])
print(L[2])

print(suppData)