关联规则aprior算法代码实现

以下是Apriori算法的Python实现：

def loadDataSet():
    """
    创建一个用于测试的简单数据集
    """
    return [[1,3,4],[2,3,5],[1,2,3,5],[2,5]]

def createC1(dataSet):
    """
    创建初始候选项集C1
    """
    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):
    """
    从候选项集Ck生成符合最小支持度的项集Lk
    """
    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):
    """
    根据Lk生成候选项集Ck+1
    """
    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 = 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

使用方法如下：

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

其中，`dataSet`是数据集，`minSupport`是最小支持度。`L`即为频繁项集，`suppData`是包含支持度信息的字典。