通过python实现apriori算法

好的，下面是一个简单的Python实现Apriori算法的示例代码：

def load_data():
    # 加载数据集
    data = [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]
    return data

def create_C1(data):
    # 生成候选项集C1
    C1 = []
    for transaction in data:
        for item in transaction:
            if not [item] in C1:
                C1.append([item])
    C1.sort()
    return list(map(frozenset, C1))

def scan_D(D, Ck, min_support):
    # 计算候选项集Ck在数据集D中的支持度
    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
    num_items = float(len(D))
    retList = []
    supportData = {}
    for key in ssCnt:
        support = ssCnt[key] / num_items
        if support >= min_support:
            retList.insert(0, key)
        supportData[key] = support
    return retList, supportData

def apriori_gen(Lk, k):
    # 生成候选项集Ck
    retList = []
    len_Lk = len(Lk)
    for i in range(len_Lk):
        for j in range(i + 1, len_Lk):
            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(data, min_support=0.5):
    # Apriori算法主函数
    C1 = create_C1(data)
    D = list(map(set, data))
    L1, supportData = scan_D(D, C1, min_support)
    L = [L1]
    k = 2
    while len(L[k - 2]) > 0:
        Ck = apriori_gen(L[k - 2], k)
        Lk, supK = scan_D(D, Ck, min_support)
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData

使用示例：

data = load_data()
L, supportData = apriori(data)
print(L)
print(supportData)

输出结果：

[[frozenset({1}), frozenset({3}), frozenset({2}), frozenset({5})], [frozenset({1, 3}), frozenset({1, 2}), frozenset({1, 5}), frozenset({3, 2}), frozenset({5, 2}), frozenset({3, 5})], [frozenset({1, 3, 2}), frozenset({1, 5, 2}), frozenset({3, 5, 2}), frozenset({1, 3, 5})], [frozenset({1, 3, 5, 2})], []]
{frozenset({3}): 0.75, frozenset({2}): 0.75, frozenset({5}): 0.75, frozenset({1}): 0.5, frozenset({1, 3}): 0.5, frozenset({3, 2}): 0.5, frozenset({5, 2}): 0.75, frozenset({1, 2}): 0.25, frozenset({1, 5}): 0.25, frozenset({3, 5}): 0.5, frozenset({1, 3, 2}): 0.25, frozenset({1, 5, 2}): 0.25, frozenset({3, 5, 2}): 0.5, frozenset({1, 3, 5}): 0.25, frozenset({1, 3, 5, 2}): 0.25}

其中，L是频繁项集，supportData是每个频繁项集的支持度。