关联规则apriori算法代码

以下是关联规则Apriori算法的代码示例：

def generate_candidates(itemset, k):
    candidates = []
    n = len(itemset)
    for i in range(n):
        for j in range(i+1, n):
            # 获取前k-2个项相同的两个项集
            if itemset[i][:k-2] == itemset[j][:k-2]:
                # 合并两个项集
                candidate = itemset[i] + [itemset[j][-1]]
                candidates.append(candidate)
    return candidates

def prune_candidates(candidates, prev_itemset, k):
    pruned_candidates = []
    for candidate in candidates:
        # 检查候选项集的所有子集是否都在上一级频繁项集中
        subsets = itertools.combinations(candidate, k-1)
        if all(subset in prev_itemset for subset in subsets):
            pruned_candidates.append(candidate)
    return pruned_candidates

def calculate_support(itemset, transactions):
    count = 0
    for transaction in transactions:
        if set(itemset).issubset(transaction):
            count += 1
    support = count / len(transactions)
    return support

def apriori(transactions, min_support):
    itemset = [[item] for item in set(itertools.chain(*transactions))]
    frequent_itemsets = []
    k = 2
    while itemset:
        candidates = generate_candidates(itemset, k)
        candidates = prune_candidates(candidates, frequent_itemsets[-1], k)
        frequent_itemsets_k = []
        for candidate in candidates:
            support = calculate_support(candidate, transactions)
            if support >= min_support:
                frequent_itemsets_k.append(candidate)
        frequent_itemsets.extend(frequent_itemsets_k)
        itemset = frequent_itemsets_k
        k += 1
    return frequent_itemsets

# 示例数据
transactions = [['A', 'B', 'E'], ['A', 'B', 'C', 'E'], ['A', 'B', 'C'], ['B', 'D'], ['B', 'C'], ['A', 'B', 'D'], ['B', 'C', 'D'], ['A', 'C'], ['B', 'C'], ['A', 'C']]
min_support = 0.3

# 调用Apriori算法
frequent_itemsets = apriori(transactions, min_support)
print(frequent_itemsets)

这段代码实现了Apriori算法，通过输入的交易数据和最小支持度，计算出频繁项集。具体步骤包括生成候选项集、剪枝、计算支持度等。最后输出频繁项集。