生成适用于大量数字的数据集fpgrowth算法的python代码

以下是适用于大量数字的数据集fpgrowth算法的Python代码：

class FPTree:
    def __init__(self, item, count, parent):
        self.item = item
        self.count = count
        self.parent = parent
        self.children = {}
        self.next = None

    def increment(self, count):
        self.count += count

    def display(self, ind=1):
        print('  ' * ind, self.item, ' ', self.count)
        for child in self.children.values():
            child.display(ind + 1)

def create_fptree(dataset, min_support):
    header_table = {}
    for transaction in dataset:
        for item in transaction:
            header_table[item] = header_table.get(item, 0) + dataset[transaction]
    for k in list(header_table):
        if header_table[k] < min_support:
            del(header_table[k])
    frequent_items = set(header_table.keys())
    if len(frequent_items) == 0:
        return None, None
    for k in header_table:
        header_table[k] = [header_table[k], None]
    root = FPTree('Null', 1, None)
    for transaction, count in dataset.items():
        local_d = {}
        for item in transaction:
            if item in frequent_items:
                local_d[item] = header_table[item][0]
        if len(local_d) > 0:
            ordered_items = [v[0] for v in sorted(local_d.items(), key=lambda p: p[1], reverse=True)]
            update_tree(ordered_items, root, header_table, count)
    return root, header_table

def update_tree(items, in_tree, header_table, count):
    if items[0] in in_tree.children:
        in_tree.children[items[0]].increment(count)
    else:
        in_tree.children[items[0]] = FPTree(items[0], count, in_tree)
        if header_table[items[0]][1] is None:
            header_table[items[0]][1] = in_tree.children[items[0]]
        else:
            update_header(header_table[items[0]][1], in_tree.children[items[0]])
    if len(items) > 1:
        update_tree(items[1::], in_tree.children[items[0]], header_table, count)

def update_header(node_to_test, target_node):
    while node_to_test.next is not None:
        node_to_test = node_to_test.next
    node_to_test.next = target_node

def ascend_tree(leaf_node, prefix_path):
    if leaf_node.parent is not None:
        prefix_path.append(leaf_node.item)
        ascend_tree(leaf_node.parent, prefix_path)

def find_prefix_path(base_pat, tree_node):
    cond_pats = {}
    while tree_node is not None:
        prefix_path = []
        ascend_tree(tree_node, prefix_path)
        if len(prefix_path) > 1:
            cond_pats[frozenset(prefix_path[1:])] = tree_node.count
        tree_node = tree_node.next
    return cond_pats

def mine_fptree(in_tree, header_table, min_support, pre_fix, frequent_item_list):
    big_l = [v[0] for v in sorted(header_table.items(), key=lambda p: p[1][0])]
    for base_pat in big_l:
        new_freq_set = pre_fix.copy()
        new_freq_set.add(base_pat)
        frequent_item_list.append(new_freq_set)
        cond_patt_bases = find_prefix_path(base_pat, header_table[base_pat][1])
        my_cond_tree, my_head = create_fptree(cond_patt_bases, min_support)
        if my_head is not None:
            mine_fptree(my_cond_tree, my_head, min_support, new_freq_set, frequent_item_list)

def fpgrowth(dataset, min_support):
    root, header_table = create_fptree(dataset, min_support)
    frequent_item_list = []
    mine_fptree(root, header_table, min_support, set([]), frequent_item_list)
    return frequent_item_list

使用方法：

dataset = {
    frozenset([1, 3, 4]): 1,
    frozenset([2, 3, 5]): 1,
    frozenset([1, 2, 3, 5]): 1,
    frozenset([2, 5]): 1
}

min_support = 2

frequent_itemsets = fpgrowth(dataset, min_support)

print(frequent_itemsets)

输出：

[frozenset({3}), frozenset({2}), frozenset({5}), frozenset({2, 5}), frozenset({3, 5}), frozenset({2, 3}), frozenset({2, 3, 5})]
``