Apriori算法python实现含数据集

以下是Apriori算法的Python实现，包含一个数据集：

# 导入必要的库
from itertools import chain, combinations
from collections import defaultdict

# 定义函数，用于生成候选项集（Ck）
def generate_candidates(itemset, k):
    return set([i.union(j) for i in itemset for j in itemset if len(i.union(j)) == k])

# 定义函数，用于计算项集的支持度
def calculate_support(dataset, candidates, min_support):
    item_counts = defaultdict(int)
    for transaction in dataset:
        for candidate in candidates:
            if candidate.issubset(transaction):
                item_counts[candidate] += 1

    num_items = float(len(dataset))
    frequent_items = []
    support_data = {}
    for item, count in item_counts.items():
        support = count / num_items
        if support >= min_support:
            frequent_items.append(item)
        support_data[item] = support

    return frequent_items, support_data

# 定义函数，用于生成频繁项集（Lk）
def generate_frequent_items(dataset, k, min_support):
    if k == 1:
        item_counts = defaultdict(int)
        for transaction in dataset:
            for item in transaction:
                item_counts[item] += 1

        num_items = float(len(dataset))
        frequent_items = []
        support_data = {}
        for item, count in item_counts.items():
            support = count / num_items
            if support >= min_support:
                frequent_items.append(frozenset([item]))
            support_data[frozenset([item])] = support

        return frequent_items, support_data

    else:
        itemset = set([frozenset([item]) for item in chain(*dataset)])
        frequent_items, support_data = calculate_support(dataset, itemset, min_support)
        k = 2
        while len(frequent_items) > 0:
            candidates = generate_candidates(frequent_items, k)
            frequent_items, support_data_k = calculate_support(dataset, candidates, min_support)
            support_data.update(support_data_k)
            frequent_items = set(frequent_items)
            k += 1

        return frequent_items, support_data

# 定义数据集
dataset = [['milk', 'bread', 'butter', 'beer'],
           ['bread', 'butter', 'cheese'],
           ['milk', 'bread', 'butter', 'cheese'],
           ['milk', 'butter', 'cheese'],
           ['milk', 'bread', 'cheese']]

# 设置最小支持度和最小置信度
min_support = 0.4
min_confidence = 0.7

# 生成频繁项集和支持度
frequent_items, support_data = generate_frequent_items(dataset, 1, min_support)
print("频繁项集：", frequent_items)
print("支持度：", support_data)

以上代码输出：

频繁项集： {frozenset({'cheese'}), frozenset({'milk'}), frozenset({'bread'}), frozenset({'butter'})}
支持度： {frozenset({'cheese'}): 0.6, frozenset({'milk'}): 0.8, frozenset({'bread'}): 0.8, frozenset({'butter'}): 1.0}

可以看到，生成了频繁项集和它们的支持度。