关联规则的python代码

关联规则（Association Rule）是指在大规模数据集中发现项与项之间的关系，通常用于市场分析、商品推荐等领域。Apriori算法是一种常用的关联规则挖掘算法。下面是使用Python实现Apriori算法的示例代码：

# 导入所需模块
from itertools import combinations
from collections import defaultdict

# 定义Apriori算法函数
def apriori(transactions, support):
    item_2_tranidxs = defaultdict(list)
    itemset = set()
    for tran_idx, transaction in enumerate(transactions):
        for item in transaction:
            item_2_tranidxs[item].append(tran_idx)
            itemset.add(frozenset([item]))

    valid_items = set()
    k = 1
    while True:
        cur_freqitems = set()
        cur_item_2_tranidxs = defaultdict(list)
        if k == 1:
            items = itemset
        else:
            prev_items = cur_items
            items = set([prev_items[i] | prev_items[j] for i in range(len(prev_items)) for j in range(i+1, len(prev_items)) if len(prev_items[i] | prev_items[j]) == k])
        
        for item in items:
            tranidxs = item_2_tranidxs[item.pop()] if k == 1 else item_2_tranidxs[item]
            if len(tranidxs)/len(transactions) >= support:
                cur_freqitems.add(item)
                valid_items |= item
                if k > 1:
                    cur_item_2_tranidxs[item] = tranidxs
        
        if not cur_freqitems:
            break
        
        cur_items = list(cur_freqitems)
        k += 1
        
        for item in cur_items:
            item_2_tranidxs[item].extend(cur_item_2_tranidxs[item])
        
    return [(item, len(item_2_tranidxs[item])/len(transactions)) for item in valid_items]

# 示例：使用mushroom数据集进行关联规则挖掘
with open('mushroom.dat') as f:
    transactions = [set(line.strip().split()) for line in f.readlines()]

support = 0.3
freqitems = apriori(transactions, support)

for item, _ in freqitems:
    print(', '.join(item))