Apriori算法python实现

非常感谢您的提问！关于 Apriori 算法的 Python 实现，这是一个比较常见的数据挖掘算法，可以在 GitHub 上找到一些实现代码。下面是一个例子：

import itertools

def generate_candidates(itemset, k):
    return set([i.union(j) for i in itemset for j in itemset if len(i.union(j)) == k])

def support_prune(dataset, candidates, threshold):
    frequent = dict()
    for candidate in candidates:
        support = sum(1 for row in dataset if candidate.issubset(row))
        if support/len(dataset) >= threshold:
            frequent[candidate] = support
    return frequent

def apriori(dataset, threshold):
    itemset = [set([item]) for row in dataset for item in row]
    k = 1
    frequent = dict()
    while True:
        candidates_k = generate_candidates(itemset, k)
        frequent_k = support_prune(dataset, candidates_k, threshold)
        if not frequent_k:
            break
        frequent.update(frequent_k)
        itemset = frequent_k.keys()
        k += 1
    return frequent

transactions = [['Bread', 'Milk'], ['Bread', 'Diapers', 'Beer', 'Eggs'],
                ['Milk', 'Diapers', 'Beer', 'Cola'],
                ['Bread', 'Milk', 'Diapers', 'Beer'],
                ['Bread', 'Milk', 'Diapers', 'Cola']]

frequent_itemsets = apriori(transactions, 0.4)

for itemset, support in frequent_itemsets.items():
    print(str(itemset) + ': ' + str(round(support/len(transactions), 2)))

希望这个简单的实现能够帮助到您！