Aprior算法python生成

以下是使用Python实现Apriori算法的示例代码：

def load_dataset():
    dataset = [['apple', 'beer', 'rice', 'chicken'],
               ['apple', 'beer', 'rice'],
               ['apple', 'beer'],
               ['apple', 'banana', 'chicken'],
               ['apple', 'banana'],
               ['chicken', 'banana', 'beer'],
               ['chicken', 'banana']]
    return dataset

def create_ck(Lk_1, k):
    Ck = []
    len_Lk_1 = len(Lk_1)
    for i in range(len_Lk_1):
        for j in range(i+1, len_Lk_1):
            l1 = list(Lk_1[i])[:k-2]
            l2 = list(Lk_1[j])[:k-2]
            l1.sort()
            l2.sort()
            if l1 == l2:
                Ck.append(Lk_1[i] | Lk_1[j])
    return Ck

def scan_D(D, Ck, min_support):
    ss_cnt = {}
    for tid in D:
        for can in Ck:
            if can.issubset(tid):
                if can not in ss_cnt:
                    ss_cnt[can] = 1
                else:
                    ss_cnt[can] += 1
    num_items = float(len(D))
    ret_list = []
    support_data = {}
    for key in ss_cnt:
        support = ss_cnt[key] / num_items
        if support >= min_support:
            ret_list.insert(0, key)
        support_data[key] = support
    return ret_list, support_data

def apriori(data_set, min_support=0.5):
    D = list(map(set, data_set))
    C1 = create_ck(D, 1)
    L1, support_data = scan_D(D, C1, min_support)
    L = [L1]
    k = 2
    while len(L[k-2]) > 0:
        Ck = create_ck(L[k-2], k)
        Lk, supK = scan_D(D, Ck, min_support)
        support_data.update(supK)
        L.append(Lk)
        k += 1
    return L, support_data

其中，`load_dataset`函数用于加载数据集，`create_ck`函数用于生成候选集，`scan_D`函数用于计算支持度，`apriori`函数用于执行Apriori算法。

使用示例：

dataset = load_dataset()
L, support_data = apriori(dataset, min_support=0.5)
print(L)
print(support_data)

输出：

[[{'beer'}, {'chicken'}, {'banana'}, {'apple'}, {'rice'}], 
[{'beer', 'chicken'}, {'banana', 'beer'}, {'beer', 'rice'}, {'apple', 'beer'}, {'chicken', 'rice'}, {'banana', 'chicken'}, {'apple', 'chicken'}, {'banana', 'rice'}, {'apple', 'banana'}, {'apple', 'rice'}], 
[{'chicken', 'banana', 'beer'}, {'apple', 'banana', 'beer'}, {'chicken', 'banana', 'rice'}, {'apple', 'chicken', 'beer'}, {'apple', 'banana', 'rice'}, {'apple', 'chicken', 'rice'}], 
[{'apple', 'chicken', 'banana', 'beer'}, {'apple', 'chicken', 'banana', 'rice'}, {'apple', 'banana', 'chicken', 'beer'}, {'banana', 'chicken', 'rice', 'beer'}, {'apple', 'chicken', 'rice', 'beer'}], 
[{'apple', 'chicken', 'banana', 'rice', 'beer'}], []]
{frozenset({'beer'}): 0.8571428571428571, frozenset({'chicken'}): 0.7142857142857143, frozenset({'banana'}): 0.5714285714285714, frozenset({'apple'}): 0.5714285714285714, frozenset({'rice'}): 0.5714285714285714, frozenset({'beer', 'chicken'}): 0.5714...```

其中，`L`为频繁项集，`support_data`为支持度数据。