用python实现apriori算法

好的，以下是用Python实现apriori算法的示例代码：

from itertools import combinations

def generate_candidates(itemsets, k):
    # 生成候选项集
    candidates = set()
    for itemset1 in itemsets:
        for itemset2 in itemsets:
            if len(itemset1.union(itemset2)) == k:
                candidates.add(itemset1.union(itemset2))
    return candidates

def prune(itemsets, candidates, k):
    # 剪枝
    pruned_candidates = set()
    for candidate in candidates:
        subsets = combinations(candidate, k)
        if all([subset in itemsets for subset in subsets]):
            pruned_candidates.add(candidate)
    return pruned_candidates

def apriori(transactions, min_support=0.5):
    # Apriori算法
    itemsets = [frozenset([item]) for item in set(transactions)]
    k = 1
    frequent_itemsets = {}
    while itemsets:
        candidates = generate_candidates(itemsets, k+1)
        item_counts = {}
        for transaction in transactions:
            for candidate in candidates:
                if candidate.issubset(transaction):
                    if candidate not in item_counts:
                        item_counts[candidate] = 0
                    item_counts[candidate] += 1
        frequent_itemsets[k+1] = {itemset: item_counts[itemset]/len(transactions) for itemset in candidates if item_counts[itemset]/len(transactions) >= min_support}
        itemsets = frequent_itemsets[k+1].keys()
        itemsets = prune(itemsets, generate_candidates(itemsets, k+2), k)
        k += 1
    return frequent_itemsets

示例的输入是一个交易列表，其中每个交易是一个项的集合。函数apriori返回一个字典，其中键是项集大小k，值是频繁项集。

例如，对于以下交易列表：

transactions = [
    {'apple', 'banana', 'orange'},
    {'banana', 'pear'},
    {'pear', 'orange'},
    {'apple', 'banana', 'pear'},
    {'apple', 'pear'}
]

调用apriori函数并指定最小支持度为0.5：

frequent_itemsets = apriori(transactions, min_support=0.5)

将返回以下频繁项集：

{
    1: {
        frozenset({'banana'}): 0.8, 
        frozenset({'pear'}): 0.6, 
        frozenset({'apple'}): 0.6, 
        frozenset({'orange'}): 0.4
    }, 
    2: {
        frozenset({'banana', 'pear'}): 0.4, 
        frozenset({'banana', 'apple'}): 0.4, 
        frozenset({'pear', 'apple'}): 0.4
    }
}

这表示banana、pear和apple都是频繁项，它们的支持度分别为0.8、0.6和0.6。同时，(banana, pear)、(banana, apple)和(pear, apple)也是频繁项集，它们的支持度分别为0.4。