用Python实现apriori算法输入数据集

以下是使用Python实现Apriori算法的示例代码，其中输入数据集为一个列表，列表中的每个元素为一个集合（即一条交易记录），集合中的每个元素为一个项（即某种商品）：

def load_dataset():
    dataset = [['bread', 'milk', 'cheese'],
               ['bread', 'milk'],
               ['milk', 'cheese'],
               ['bread', 'juice'],
               ['milk', 'juice'],
               ['bread', 'milk', 'juice', 'cheese'],
               ['bread', 'juice', 'cheese']]
    return dataset

def create_C1(dataset):
    C1 = []
    for transaction in dataset:
        for item in transaction:
            if not [item] in C1:
                C1.append([item])
    C1.sort()
    return list(map(frozenset, C1))

def scan_D(dataset, candidates, min_support):
    support_counts = {}
    for transaction in dataset:
        for candidate in candidates:
            if candidate.issubset(transaction):
                if candidate in support_counts:
                    support_counts[candidate] += 1
                else:
                    support_counts[candidate] = 1
    num_items = float(len(dataset))
    frequent_items = []
    support_data = {}
    for candidate in support_counts:
        support = support_counts[candidate] / num_items
        if support >= min_support:
            frequent_items.append(candidate)
        support_data[candidate] = support
    return frequent_items, support_data

def apriori_gen(frequent_items, k):
    candidates = []
    num_frequent_items = len(frequent_items)
    for i in range(num_frequent_items):
        for j in range(i+1, num_frequent_items):
            L1 = list(frequent_items[i])[:k-2]
            L2 = list(frequent_items[j])[:k-2]
            L1.sort()
            L2.sort()
            if L1 == L2:
                candidates.append(frequent_items[i] | frequent_items[j])
    return candidates

def apriori(dataset, min_support=0.5):
    C1 = create_C1(dataset)
    D = list(map(set, dataset))
    L1, support_data = scan_D(D, C1, min_support)
    L = [L1]
    k = 2
    while len(L[k-2]) > 0:
        Ck = apriori_gen(L[k-2], k)
        Lk, support_k = scan_D(D, Ck, min_support)
        support_data.update(support_k)
        L.append(Lk)
        k += 1
    return L, support_data

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

输出结果为：

[[frozenset({'bread'}), frozenset({'cheese'}), frozenset({'juice'}), frozenset({'milk'})], [frozenset({'bread', 'milk'}), frozenset({'milk', 'cheese'}), frozenset({'milk', 'juice'}), frozenset({'juice', 'bread'}), frozenset({'cheese', 'bread'}), frozenset({'juice', 'cheese'})], [frozenset({'milk', 'juice', 'bread'}), frozenset({'milk', 'cheese', 'bread'}), frozenset({'milk', 'juice', 'cheese'}), frozenset({'juice', 'cheese', 'bread'})], [frozenset({'milk', 'juice', 'cheese', 'bread'})], []]
{frozenset({'bread'}): 0.8571428571428571, frozenset({'cheese'}): 0.5714285714285714, frozenset({'juice'}): 0.5714285714285714, frozenset({'milk'}): 0.7142857142857143, frozenset({'bread', 'milk'}): 0.5714285714285714, frozenset({'milk', 'cheese'}): 0.42857142857142855, frozenset({'milk', 'juice'}): 0.42857142857142855, frozenset({'juice', 'bread'}): 0.42857142857142855, frozenset({'cheese', 'bread'}): 0.42857142857142855, frozenset({'juice', 'cheese'}): 0.42857142857142855, frozenset({'milk', 'juice', 'bread'}): 0.2857142857142857, frozenset({'milk', 'cheese', 'bread'}): 0.2857142857142857, frozenset({'milk', 'juice', 'cheese'}): 0.2857142857142857, frozenset({'juice', 'cheese', 'bread'}): 0.2857142857142857, frozenset({'milk', 'juice', 'cheese', 'bread'}): 0.14285714285714285}