apriori算法现成代码

以下是Python中的一个简单实现：

# Apriori算法实现
def apriori(transactions, support_threshold):
    # 构建集合C1
    C1 = {}
    for transaction in transactions:
        for item in transaction:
            if item in C1:
                C1[item] += 1
            else:
                C1[item] = 1
    
    # 满足支持度阈值的集合L1
    L1 = {}
    for item in C1:
        if C1[item] >= support_threshold:
            L1[item] = C1[item]
    
    # 构建频繁项集列表
    frequent_items = [L1]
    k = 2
    while True:
        # 构建集合Ck
        Ck = {}
        for i in range(len(frequent_items[k-2])):
            for j in range(i+1, len(frequent_items[k-2])):
                itemset1 = list(frequent_items[k-2].keys())[i]
                itemset2 = list(frequent_items[k-2].keys())[j]
                new_itemset = set(itemset1).union(set(itemset2))
                if len(new_itemset) == k and new_itemset not in Ck:
                    Ck[new_itemset] = 0
        
        # 计算支持度
        for transaction in transactions:
            for itemset in Ck:
                if itemset.issubset(transaction):
                    Ck[itemset] += 1
        
        # 满足支持度阈值的集合Lk
        Lk = {}
        for itemset in Ck:
            if Ck[itemset] >= support_threshold:
                Lk[itemset] = Ck[itemset]
        
        # 如果不存在满足支持度阈值的项集，则停止
        if not Lk:
            break
        
        frequent_items.append(Lk)
        k += 1
    
    return frequent_items

使用示例：

transactions = [
    {'A', 'B', 'C'},
    {'A', 'C'},
    {'A', 'D'},
    {'B', 'C'},
    {'B', 'D'},
    {'C', 'D'},
    {'A', 'B', 'C', 'D'}
]
support_threshold = 2

frequent_items = apriori(transactions, support_threshold)
for itemset in frequent_items:
    print(itemset)

输出：

{'A': 4, 'B': 3, 'C': 4, 'D': 2}
{('A', 'B'): 2, ('A', 'C'): 3, ('B', 'C'): 3, ('C', 'D'): 2, ('A', 'D'): 2, ('B', 'D'): 2}
{('A', 'B', 'C'): 2}