从外部录入数据集不用apriori库的关联规则apriori算法代码

以下是一个简单的关联规则Apriori算法的Python实现，可以从外部读取数据集文件。这个实现仅用于学习和演示目的，对于大规模数据集，建议使用更高效的实现。

import itertools

# 读取数据集
def load_dataset(filename):
    with open(filename, 'r') as f:
        dataset = [list(map(int, line.strip().split())) for line in f.readlines()]
    return dataset

# 计算项集的支持度
def support_count(dataset, itemset):
    count = 0
    for item in dataset:
        if set(itemset).issubset(item):
            count += 1
    return count

# 生成候选项集
def generate_candidate_itemsets(dataset, k):
    candidate_itemsets = []
    for item in dataset:
        for combination in itertools.combinations(item, k):
            if list(combination) not in candidate_itemsets:
                candidate_itemsets.append(list(combination))
    return candidate_itemsets

# 生成频繁项集
def generate_frequent_itemsets(dataset, min_support):
    frequent_itemsets = []
    k = 1
    while True:
        candidate_itemsets = generate_candidate_itemsets(dataset, k)
        frequent_itemsets_k = []
        for itemset in candidate_itemsets:
            support = support_count(dataset, itemset)
            if support >= min_support:
                frequent_itemsets_k.append(itemset)
        if len(frequent_itemsets_k) == 0:
            break
        frequent_itemsets += frequent_itemsets_k
        k += 1
    return frequent_itemsets

# 生成关联规则
def generate_association_rules(frequent_itemsets, min_confidence):
    association_rules = []
    for itemset in frequent_itemsets:
        for i in range(1, len(itemset)):
            for antecedent in itertools.combinations(itemset, i):
                antecedent = list(antecedent)
                consequent = list(set(itemset) - set(antecedent))
                support_antecedent = support_count(dataset, antecedent)
                support_consequent = support_count(dataset, consequent)
                confidence = support_count(dataset, itemset) / support_antecedent
                if confidence >= min_confidence:
                    association_rules.append((antecedent, consequent, confidence))
    return association_rules

if __name__ == '__main__':
    # 设置最小支持度和最小置信度
    min_support = 2
    min_confidence = 0.5

    # 读取数据集
    dataset = load_dataset('dataset.txt')

    # 生成频繁项集
    frequent_itemsets = generate_frequent_itemsets(dataset, min_support)
    print('Frequent Itemsets:')
    print(frequent_itemsets)

    # 生成关联规则
    association_rules = generate_association_rules(frequent_itemsets, min_confidence)
    print('Association Rules:')
    for antecedent, consequent, confidence in association_rules:
        print('{} => {}: {:.2f}'.format(antecedent, consequent, confidence))

在这个实现中，`load_dataset()`函数从外部文件中读取数据集，`support_count()`函数计算项集的支持度，`generate_candidate_itemsets()`函数生成候选项集，`generate_frequent_itemsets()`函数生成频繁项集，`generate_association_rules()`函数生成关联规则。您可以根据自己的需要调整代码。