FP-growth算法python实现含数据集，并给出文档

FP-growth算法是一种用于频繁项集挖掘的快速算法，它构建一棵FP树来表示数据集，并利用该树来快速发现频繁项集。

下面是FP-growth算法的Python实现，并附带一个数据集。

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

    def inc(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 load_dataset():
    return [['bread', 'milk'], ['bread', 'diaper', 'beer', 'egg'], ['milk', 'diaper', 'beer', 'cola'], ['bread', 'milk', 'diaper', 'beer'], ['bread', 'milk', 'diaper', 'cola']]


def create_tree(dataset, min_sup=1):
    header_table = {}
    for trans in dataset:
        for item in trans:
            header_table[item] = header_table.get(item, 0) + dataset[trans]

    for k in header_table.copy().keys():
        if header_table[k] < min_sup:
            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]

    root = TreeNode('Null Set', 1, None)

    for tran, count in dataset.items():
        local_dic = {}
        for item in tran:
            if item in freq_item_set:
                local_dic[item] = header_table[item][0]
        if len(local_dic) > 0:
            ordered_items = [v[0] for v in sorted(local_dic.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]].inc(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, header_table):
    tree_node = header_table[base_pat][1]
    prefix_path = []
    while tree_node is not None:
        prefix_path = []
        ascend_tree(tree_node, prefix_path)
        if len(prefix_path) > 1:
            conditional_patterns_base = prefix_path[1:]
            yield conditional_patterns_base, tree_node.count
        tree_node = tree_node.next


def mine_tree(in_tree, header_table, min_sup, 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)
        conditional_patterns = list(find_prefix_path(base_pat, header_table))
        conditional_tree, conditional_head = create_tree(conditional_patterns, min_sup)
        if conditional_head is not None:
            mine_tree(conditional_tree, conditional_head, min_sup, new_freq_set, freq_item_list)


if __name__ == '__main__':
    dataset = load_dataset()
    root, header_table = create_tree(dataset, 3)
    root.display()
    freq_items = []
    mine_tree(root, header_table, 3, set([]), freq_items)
    print(freq_items)

数据集：

[['bread', 'milk'], ['bread', 'diaper', 'beer', 'egg'], ['milk', 'diaper', 'beer', 'cola'], ['bread', 'milk', 'diaper', 'beer'], ['bread', 'milk', 'diaper', 'cola']]

其中，每个元素代表一条交易记录。交易记录中的每个元素代表一个商品。