FP-growth算法代码

以下是Python实现的FP-growth算法代码：

class TreeNode:
    def __init__(self, name, count, parent):
        self.name = name
        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.name, ' ', self.count)
        for child in self.children.values():
            child.display(ind + 1)


def create_fptree(dataset, minsup):
    """
    根据数据集创建FP树
    :param dataset: 数据集，格式为列表的列表
    :param minsup: 最小支持度
    :return: FP树，头指针表
    """
    header_table = {}
    for trans in dataset:
        for item in trans:
            header_table[item] = header_table.get(item, 0) + dataset[trans]
    keys = list(header_table.keys())
    for k in keys:
        if header_table[k] < minsup:
            del (header_table[k])
    freq_item_set = set(header_table.keys())
    if len(freq_item_set) == 0:
        return None, None
    for k in header_table:
        header_table[k] = [header_table[k], None]
    tree = TreeNode('Null Set', 1, None)
    for trans, count in dataset.items():
        local_D = {}
        for item in trans:
            if item in freq_item_set:
                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, tree, header_table, count)
    return tree, header_table


def update_tree(items, in_tree, header_table, count):
    """
    更新FP树
    :param items: 项集
    :param in_tree: 当前子树
    :param header_table: 头指针表
    :param count: 频数
    :return: None
    """
    if items[0] in in_tree.children:
        in_tree.children[items[0]].increment(count)
    else:
        in_tree.children[items[0]] = TreeNode(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.name)
        ascend_tree(leaf_node.parent, prefix_path)


def find_prefix_path(base_pat, tree_node):
    """
    查找某项的前缀路径
    :param base_pat: 项
    :param tree_node: 树节点
    :return: 前缀路径列表
    """
    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_tree(in_tree, header_table, minsup, pre_fix, freq_item_list):
    """
    递归挖掘FP树
    :param in_tree: 当前子树
    :param header_table: 头指针表
    :param minsup: 最小支持度
    :param pre_fix: 前缀
    :param freq_item_list: 频繁项列表
    :return: None
    """
    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)
        freq_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, minsup)
        if my_head is not None:
            mine_tree(my_cond_tree, my_head, minsup, new_freq_set, freq_item_list)

其中，`create_fptree`函数用于创建FP树和头指针表，`update_tree`函数用于更新FP树，`find_prefix_path`函数用于查找某项的前缀路径，`mine_tree`函数用于递归挖掘FP树，最终返回频繁项集列表。