apriori算法Python实现

以下是 Apriori 算法的 Python 实现示例：

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

def createC1(dataSet):
    # 创建候选项集C1
    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(D, Ck, minSupport):
    # 计算支持度
    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.append(key)
        supportData[key] = support
    return retList, supportData

def aprioriGen(Lk, k):
    # 创建候选项集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):
    # Apriori算法
    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)
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData

以上代码实现了 Apriori 算法的核心功能，可以通过调用 apriori 函数传入数据集和最小支持度参数来得到频繁项集和支持度信息。