Python实现数据挖掘中Apriori算法

def loadDataSet():
    D = [[1,3,4],[2,3,5],[1,2,3,5],[2,5]]
    return D
    
D = loadDataSet()
D
#输出
[[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]
#辅助函数
def createC1 (D):
    C1 = []
    for i in D:
        for j in i:
            if not {j} in C1:
                C1.append({j})
    return list(map(frozenset,C1)) #frozenset(不可变集合)
    
C1 = createC1(D)
C1
[frozenset({1}),
 frozenset({3}),
 frozenset({4}),
 frozenset({2}),
 frozenset({5})]
 #辅助函数
def scanD(D,Ck,minSupport):#D，原始数据集；Ck，候选项集；minSupport：最小支持度
    S = {}
    for i in D:
        for j in Ck:
            if j.issubset(i):  #issubset用于检查j史否认为i的子集
                if j not in S.keys():
                    S[j] = 1
                else:
                    S[j] += 1
    numItems = float(len(D)) #事务总量
    L = []
    N = []
    supportData = {}
    for key in S:
        support = S[key] / numItems
        supportData[key] = support
        if support >= minSupport:
            L.append(key)
        else:
            N.append(key)
    return L,N,supportData
L,N,supportData = scanD(D,C1,0.5)

L
[frozenset({1}), frozenset({3}), frozenset({2}), frozenset({5})]

N
[frozenset({4})]

supportData
{frozenset({1}): 0.5,
 frozenset({3}): 0.75,
 frozenset({4}): 0.25,
 frozenset({2}): 0.75,
 frozenset({5}): 0.75}
#辅助函数 
def aprioriGen(Lk,k,N):
    Ck = []   #k+1候选项集
    lenLk = len(Lk)
    for i in range(lenLk):
        #子连接运算
        for j in range(i + 1,lenLk):
            L1 = list(Lk[i])[:k-2]
            L1.sort
            L2 = list(Lk[j])[:k-2]
            L2.sort()
            if L1 == L2:
                Ck.append(Lk[i]|Lk[j]) #加入并集
        for i in N:
            for j in Ck:
                if set(i).issubset(j):
                    Ck.remove(j)
    return Ck
    
def apriori(D,minSupport = 0.5):
    C1 = createC1(D)
    L1,N,supportData = scanD(D,C1,minSupport)
    L = [L1]
    k = 2
    while (len(L[k-2]) > 0):
        Ck = aprioriGen(L[k-2],k,N)
        Lk,Nk,supK = scanD(D,Ck,minSupport)
        supportData.update(supK)
        N += Nk
        L.append(Lk)
        k += 1
    return L,N,supportData
L,N,supportData = apriori(D,minSupport = 0.5)

L
[[frozenset({1}), frozenset({3}), frozenset({2}), frozenset({5})],
 [frozenset({1, 3}), frozenset({2, 3}), frozenset({3, 5}), frozenset({2, 5})],
 [frozenset({2, 3, 5})],
 []]

N
[frozenset({4}), frozenset({1, 2}), frozenset({1, 5})]

supportData
{frozenset({1}): 0.5,
 frozenset({3}): 0.75,
 frozenset({4}): 0.25,
 frozenset({2}): 0.75,
 frozenset({5}): 0.75,
 frozenset({1, 3}): 0.5,
 frozenset({2, 3}): 0.5,
 frozenset({3, 5}): 0.5,
 frozenset({2, 5}): 0.75,
 frozenset({1, 2}): 0.25,
 frozenset({1, 5}): 0.25,
 frozenset({2, 3, 5}): 0.5}

第一次发文章，但是Python还没有学完，数据挖掘课程需要敲代码，然后在B站上看了几个UP主的讲解，按照视频简单的敲了下代码。链接是我看的几位UP主的讲解，有需要的小伙伴可以去看下(https://www.bilibili.com/video/BV15Z4y1p7ev?p=2)