python apriori代码样例

下面是一个简单的 Python Apriori 代码样例，用于从数据集中挖掘频繁项集：

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

def createC1(dataSet):
    # 创建初始候选项集列表
    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):
    # 返回满足最小支持度要求的项集列表
    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):
    # 创建候选项集列表
    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):
    # 生成频繁项集
    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

这段代码实现了 Apriori 算法的主要功能，包括创建候选项集、扫描数据集、生成频繁项集等。你可以根据自己的需求进行修改和扩展。