生成适用于数字的fpgrowth算法的python代码

以下是一个使用Python实现FPGrowth算法的示例代码：

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


def create_tree(data_set, min_support):
    header_table = {}
    for trans in data_set:
        for item in trans:
            header_table[item] = header_table.get(item, 0) + data_set[trans]

    for k in list(header_table.keys()):
        if header_table[k] < min_support:
            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]

    ret_tree = FPNode('Null Set', 1, None)
    for tran_set, count in data_set.items():
        local_data = {}
        for item in tran_set:
            if item in freq_item_set:
                local_data[item] = header_table[item][0]
        if len(local_data) > 0:
            ordered_items = [v[0] for v in sorted(local_data.items(), key=lambda p: p[1], reverse=True)]
            update_tree(ordered_items, ret_tree, header_table, count)

    return ret_tree, 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]] = FPNode(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.value)
        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_tree(in_tree, header_table, min_support, pre_fix, freq_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)
        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_tree(cond_patt_bases, min_support)
        if my_head is not None:
            mine_tree(my_cond_tree, my_head, min_support, new_freq_set, freq_item_list)


def load_data():
    data_set = [['r', 'z', 'h', 'j', 'p'],
                ['z', 'y', 'x', 'w', 'v', 'u', 't', 's'],
                ['z'],
                ['r', 'x', 'n', 'o', 's'],
                ['y', 'r', 'x', 'z', 'q', 't', 'p'],
                ['y', 'z', 'x', 'e', 'q', 's', 't', 'm']]
    return data_set


if __name__ == '__main__':
    data_set = load_data()
    tree, header_table = create_tree(data_set, 3)
    freq_items = []
    mine_tree(tree, header_table, 3, set([]), freq_items)
    print(freq_items)

此代码实现了FPGrowth算法，将数据加载到FP树中，然后从树中挖掘频繁项集。在FPNode类中，每个节点包含一个值、一个计数、一个父节点、一个子节点列表和一个指向相同项的下一个节点的链接。create_tree函数创建FP树，update_tree函数将数据加载到树中，find_prefix_path函数找到以某个项结尾的所有条件模式基，mine_tree函数递归地挖掘FP树中的频繁项集