python apriori算法 做商品内部关联规则代码

以下是一个基本的Apriori算法实现：

def load_data():
    data = [['A', 'B', 'C', 'D'], ['A', 'C', 'D'], ['B', 'E'], ['A', 'C', 'E'], ['A', 'B', 'C', 'E'], ['B', 'C', 'D', 'E']]
    return data

def create_itemsets(data):
    itemsets = set()
    for transaction in data:
        for item in transaction:
            itemsets.add(frozenset([item]))
    return itemsets

def filter_itemsets(itemsets, data, min_support):
    support_counts = {}
    for transaction in data:
        for itemset in itemsets:
            if itemset <= frozenset(transaction):
                if itemset not in support_counts:
                    support_counts[itemset] = 0
                support_counts[itemset] += 1
    filtered_itemsets = set()
    for itemset in itemsets:
        support = support_counts.get(itemset, 0)
        if support >= min_support:
            filtered_itemsets.add(itemset)
    return filtered_itemsets, support_counts

def join_itemsets(itemsets, k):
    joined_itemsets = set()
    for itemset1 in itemsets:
        for itemset2 in itemsets:
            if len(itemset1.union(itemset2)) == k:
                joined_itemsets.add(itemset1.union(itemset2))
    return joined_itemsets

def apriori(data, min_support):
    itemsets = create_itemsets(data)
    frequent_itemsets = []
    while itemsets:
        itemsets, support_counts = filter_itemsets(itemsets, data, min_support)
        frequent_itemsets.extend(itemsets)
        k = len(frequent_itemsets[0]) + 1
        itemsets = join_itemsets(itemsets, k)
    return frequent_itemsets, support_counts

data = load_data()
min_support = 3
frequent_itemsets, support_counts = apriori(data, min_support)
for itemset, support in support_counts.items():
    print(itemset, support)

该实现中使用了一个`load_data`函数来加载数据，该数据集包含了6个交易记录，每个记录中包含了若干商品。然后使用`create_itemsets`函数创建了一个包含所有单个商品的项集，这个项集将作为Apriori算法的第一次迭代输入。`filter_itemsets`函数用于过滤出满足最小支持度要求的项集。`join_itemsets`函数用于生成下一次迭代的项集。最后使用`apriori`函数来执行算法，该函数返回所有频繁项集以及它们的支持度计数。输出结果如下：

frozenset({'E'}) 3
frozenset({'C'}) 4
frozenset({'B'}) 3
frozenset({'D'}) 2
frozenset({'A'}) 4
frozenset({'C', 'E'}) 3
frozenset({'B', 'E'}) 2
frozenset({'A', 'C'}) 3
frozenset({'A', 'B'}) 3
frozenset({'C', 'D'}) 2
frozenset({'A', 'D'}) 2
frozenset({'B', 'C'}) 3
frozenset({'A', 'E'}) 3
frozenset({'B', 'D'}) 1
frozenset({'A', 'B', 'C'}) 3
frozenset({'A', 'C', 'E'}) 3
frozenset({'B', 'C', 'E'}) 2
frozenset({'B', 'A', 'C'}) 2