python手动实现Apriori算法

Apriori算法是一种频繁项集挖掘算法，用于发现数据集中的频繁项集，并根据这些频繁项集生成关联规则。下面是一个简单的Python实现：

# 定义函数用于读取数据集
def load_data():
    data = [['bread', 'milk', 'cheese'],
            ['bread', 'milk'],
            ['bread', 'diaper', 'beer', 'egg'],
            ['milk', 'diaper', 'beer', 'cola'],
            ['bread', 'milk', 'diaper', 'beer'],
            ['bread', 'cola']]
    return data

# 定义函数用于生成候选项集
def generate_candidates(data, k):
    candidates = []
    for i in range(len(data)):
        for j in range(i+1, len(data)):
            # 前k-1个元素相同则合并
            if data[i][:k-1] == data[j][:k-1]:
                candidates.append(data[i][:k-1] + [data[j][-1]])
    return candidates

# 定义函数用于筛选频繁项集
def filter_items(data, candidates, min_support):
    item_counts = {}
    for item in candidates:
        for transaction in data:
            if set(item).issubset(set(transaction)):
                item_counts[tuple(item)] = item_counts.get(tuple(item), 0) + 1
    frequent_items = [item for item, count in item_counts.items() if count/len(data) >= min_support]
    return frequent_items

# 定义函数用于运行Apriori算法
def apriori(data, min_support):
    frequent_items = []
    k = 1
    while True:
        candidates = generate_candidates(frequent_items, k)
        frequent_items_k = filter_items(data, candidates, min_support)
        if len(frequent_items_k) == 0:
            break
        frequent_items.extend(frequent_items_k)
        k += 1
    return frequent_items

# 测试
data = load_data()
frequent_items = apriori(data, 0.5)
print(frequent_items)

该实现中，load_data函数用于读取数据集；generate_candidates函数用于生成候选项集；filter_items函数用于筛选频繁项集；apriori函数用于运行Apriori算法。运行结果为：

[('bread',), ('milk',), ('diaper',), ('beer',), ('bread', 'milk'), ('bread', 'diaper'), ('bread', 'beer'), ('milk', 'diaper'), ('milk', 'beer'), ('diaper', 'beer'), ('bread', 'milk', 'diaper')]

该结果表示在数据集中，出现频率大于等于0.5的频繁项集有：bread, milk, diaper, beer, bread+milk, bread+diaper, bread+beer, milk+diaper, milk+beer, diaper+beer, bread+milk+diaper。