python实现apriori算法例题

以下是一个简单的Python实现Apriori算法的例子，用于查找频繁项集：

def load_dataset():
    return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]

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

def scan_dataset(dataset, candidates, min_support):
    support_counts = {}
    for transaction in dataset:
        for candidate in candidates:
            if candidate.issubset(transaction):
                if not candidate in support_counts:
                    support_counts[candidate] = 1
                else:
                    support_counts[candidate] += 1
    num_items = float(len(dataset))
    frequent_items = []
    support_data = {}
    for itemset in support_counts:
        support = support_counts[itemset] / num_items
        if support >= min_support:
            frequent_items.append(itemset)
        support_data[itemset] = support
    return frequent_items, support_data

def join_sets(itemset, length):
    return set([i.union(j) for i in itemset for j in itemset if len(i.union(j)) == length])

def apriori(dataset, min_support=0.5):
    candidates = create_candidates(dataset)
    frequent_items, support_data = scan_dataset(dataset, candidates, min_support)
    frequent_itemsets = [frequent_items]
    k = 2
    while len(frequent_itemsets[k-2]) > 0:
        candidate_sets = join_sets(frequent_itemsets[k-2], k)
        frequent_items_k, support_data_k = scan_dataset(dataset, candidate_sets, min_support)
        support_data.update(support_data_k)
        frequent_itemsets.append(frequent_items_k)
        k += 1
    return frequent_itemsets, support_data

dataset = load_dataset()
frequent_itemsets, support_data = apriori(dataset, min_support=0.5)
print("Frequent Itemsets:\n", frequent_itemsets)
print("Support Data:\n", support_data)

输出结果如下：

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

其中，`load_dataset()`函数用于加载数据集，`create_candidates()`函数用于创建候选项集，`scan_dataset()`函数用于计算每个项集的支持度，`join_sets()`函数用于将k-1项集结合成k项集，`apriori()`函数用于执行Apriori算法。在这个例子中，数据集为一个列表，其中每个元素都表示一笔交易，算法会输出所有频繁项集及其支持度。