apriori算法python代码实现

下面是Apriori算法的Python实现：

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 not [item] in C1:
                C1.append([item])
    C1.sort()
    return map(frozenset, C1)

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

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 = 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)
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData

dataSet = loadDataSet()
L, suppData = apriori(dataSet, minSupport=0.5)
print(L)
print(suppData)

在这个代码中，我们首先定义了一个数据集。然后我们使用`createC1()`函数创建了初始候选项集。接下来，我们使用`scanD()`函数计算支持度，并得到频繁项集。接着使用`aprioriGen()`函数生成新的候选项集，并使用它计算新的支持度。最后，我们使用`apriori()`函数得到所有的频繁项集以及他们的支持度。