apriori

#This code hasn't been adjusted according to the datset at hand as of now. I'll make commits to it on a later date.

def generate_candidates(itemset, k):
    candidates = []
    n = len(itemset)
    for i in range(n):
        for j in range(i+1, n):
            L1 = itemset[i][:k-2]
            L2 = itemset[j][:k-2]
            if L1 == L2:
                candidates.append(itemset[i] + [itemset[j][-1]])
    return candidates

def prune(itemset, candidates):
    pruned = []
    for candidate in candidates:
        subsets = [candidate[:i] + candidate[i+1:] for i in range(len(candidate))]
        if all(subset in itemset for subset in subsets):
            pruned.append(candidate)
    return pruned

def apriori(dataset, min_support):
    itemset = [[item] for item in dataset]
    k = 2
    frequent_itemsets = []
    while itemset:
        candidates = generate_candidates(itemset, k)
        counts = {tuple(candidate): 0 for candidate in candidates}  # Convert lists to tuples
        for transaction in dataset:
            for candidate in candidates:
                if set(candidate).issubset(set(transaction)):
                    counts[tuple(candidate)] += 1  # Convert lists to tuples
        frequent_itemsets.extend([list(itemset) for itemset, count in counts.items() if count >= min_support])  # Convert tuples back to lists
        itemset = prune(itemset, candidates)
        k += 1
    return frequent_itemsets

# Example usage
dataset = [
    ['bread', 'milk'],
    ['bread', 'diapers', 'beer', 'eggs'],
    ['milk', 'diapers', 'beer', 'cola'],
    ['bread', 'milk', 'diapers', 'beer'],
    ['bread', 'milk', 'diapers', 'cola']
]
min_support = 3
frequent_itemsets = apriori(dataset, min_support)
print(frequent_itemsets)