假设你有一本这样的字典:

{'a': 1,
 'c': {'a': 2,
       'b': {'x': 5,
             'y' : 10}},
 'd': [1, 2, 3]}

你会如何把它平摊成这样:

{'a': 1,
 'c_a': 2,
 'c_b_x': 5,
 'c_b_y': 10,
 'd': [1, 2, 3]}

当前回答

我总是喜欢通过.items()访问字典对象,所以为了平抑字典,我使用下面的递归生成器flat_items(d)。如果你想再次使用dict,只需像这样简单地包装它:flat = dict(flat_items(d))

def flat_items(d, key_separator='.'):
    """
    Flattens the dictionary containing other dictionaries like here: https://stackoverflow.com/questions/6027558/flatten-nested-python-dictionaries-compressing-keys

    >>> example = {'a': 1, 'c': {'a': 2, 'b': {'x': 5, 'y' : 10}}, 'd': [1, 2, 3]}
    >>> flat = dict(flat_items(example, key_separator='_'))
    >>> assert flat['c_b_y'] == 10
    """
    for k, v in d.items():
        if type(v) is dict:
            for k1, v1 in flat_items(v, key_separator=key_separator):
                yield key_separator.join((k, k1)), v1
        else:
            yield k, v

其他回答

你可以使用递归来平展你的字典。

import collections


def flatten(
    nested_dict,
    seperator='.',
    name=None,
):
    flatten_dict = {}

    if not nested_dict:
        return flatten_dict

    if isinstance(
        nested_dict,
        collections.abc.MutableMapping,
    ):
        for key, value in nested_dict.items():
            if name is not None:
                flatten_dict.update(
                    flatten(
                        nested_dict=value,
                        seperator=seperator,
                        name=f'{name}{seperator}{key}',
                    ),
                )
            else:
                flatten_dict.update(
                    flatten(
                        nested_dict=value,
                        seperator=seperator,
                        name=key,
                    ),
                )
    else:
        flatten_dict[name] = nested_dict

    return flatten_dict


if __name__ == '__main__':
    nested_dict = {
        1: 'a',
        2: {
            3: 'c',
            4: {
                5: 'e',
            },
            6: [1, 2, 3, 4, 5, ],
        },
    }

    print(
        flatten(
            nested_dict=nested_dict,
        ),
    )

输出:

{
   "1":"a",
   "2.3":"c",
   "2.4.5":"e",
   "2.6":[1, 2, 3, 4, 5]
}

我尝试了本页上的一些解决方案-虽然不是全部-但我尝试的那些都无法处理dict的嵌套列表。

考虑这样一个词典:

d = {
        'owner': {
            'name': {'first_name': 'Steven', 'last_name': 'Smith'},
            'lottery_nums': [1, 2, 3, 'four', '11', None],
            'address': {},
            'tuple': (1, 2, 'three'),
            'tuple_with_dict': (1, 2, 'three', {'is_valid': False}),
            'set': {1, 2, 3, 4, 'five'},
            'children': [
                {'name': {'first_name': 'Jessica',
                          'last_name': 'Smith', },
                 'children': []
                 },
                {'name': {'first_name': 'George',
                          'last_name': 'Smith'},
                 'children': []
                 }
            ]
        }
    }

以下是我的临时解决方案:

def flatten_dict(input_node: dict, key_: str = '', output_dict: dict = {}):
    if isinstance(input_node, dict):
        for key, val in input_node.items():
            new_key = f"{key_}.{key}" if key_ else f"{key}"
            flatten_dict(val, new_key, output_dict)
    elif isinstance(input_node, list):
        for idx, item in enumerate(input_node):
            flatten_dict(item, f"{key_}.{idx}", output_dict)
    else:
        output_dict[key_] = input_node
    return output_dict

生产:

{
  owner.name.first_name: Steven,
  owner.name.last_name: Smith,
  owner.lottery_nums.0: 1,
  owner.lottery_nums.1: 2,
  owner.lottery_nums.2: 3,
  owner.lottery_nums.3: four,
  owner.lottery_nums.4: 11,
  owner.lottery_nums.5: None,
  owner.tuple: (1, 2, 'three'),
  owner.tuple_with_dict: (1, 2, 'three', {'is_valid': False}),
  owner.set: {1, 2, 3, 4, 'five'},
  owner.children.0.name.first_name: Jessica,
  owner.children.0.name.last_name: Smith,
  owner.children.1.name.first_name: George,
  owner.children.1.name.last_name: Smith,
}

一个临时的解决方案,但并不完美。 注意:

它不保留空字典,例如地址:{}k/v对。 它不会将嵌套元组中的字典平铺——尽管使用python元组类似于列表的事实很容易添加它。

代码:

test = {'a': 1, 'c': {'a': 2, 'b': {'x': 5, 'y' : 10}}, 'd': [1, 2, 3]}

def parse_dict(init, lkey=''):
    ret = {}
    for rkey,val in init.items():
        key = lkey+rkey
        if isinstance(val, dict):
            ret.update(parse_dict(val, key+'_'))
        else:
            ret[key] = val
    return ret

print(parse_dict(test,''))

结果:

$ python test.py
{'a': 1, 'c_a': 2, 'c_b_x': 5, 'd': [1, 2, 3], 'c_b_y': 10}

我使用python3.2,更新为您的python版本。

使用发电机:

def flat_dic_helper(prepand,d):
    if len(prepand) > 0:
        prepand = prepand + "_"
    for k in d:
        i = d[k]
        if isinstance(i, dict):
            r = flat_dic_helper(prepand + k,i)
            for j in r:
                yield j
        else:
            yield (prepand + k,i)

def flat_dic(d):
    return dict(flat_dic_helper("",d))

d = {'a': 1, 'c': {'a': 2, 'b': {'x': 5, 'y' : 10}}, 'd': [1, 2, 3]}
print(flat_dic(d))


>> {'a': 1, 'c_a': 2, 'c_b_x': 5, 'd': [1, 2, 3], 'c_b_y': 10}

这并不局限于字典,而是实现.items()的每个映射类型。进一步列表更快,因为它避免了if条件。尽管如此,功劳还是归于伊姆兰:

def flatten(d, parent_key=''):
    items = []
    for k, v in d.items():
        try:
            items.extend(flatten(v, '%s%s_' % (parent_key, k)).items())
        except AttributeError:
            items.append(('%s%s' % (parent_key, k), v))
    return dict(items)