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]}
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
使用dict.popitem()在直接的嵌套列表类递归中:
def flatten(d):
if d == {}:
return d
else:
k,v = d.popitem()
if (dict != type(v)):
return {k:v, **flatten(d)}
else:
flat_kv = flatten(v)
for k1 in list(flat_kv.keys()):
flat_kv[k + '_' + k1] = flat_kv[k1]
del flat_kv[k1]
return {**flat_kv, **flatten(d)}
其他回答
这与imran和ralu的回答相似。它不使用生成器,而是使用闭包的递归:
def flatten_dict(d, separator='_'):
final = {}
def _flatten_dict(obj, parent_keys=[]):
for k, v in obj.iteritems():
if isinstance(v, dict):
_flatten_dict(v, parent_keys + [k])
else:
key = separator.join(parent_keys + [k])
final[key] = v
_flatten_dict(d)
return final
>>> print flatten_dict({'a': 1, 'c': {'a': 2, 'b': {'x': 5, 'y' : 10}}, 'd': [1, 2, 3]})
{'a': 1, 'c_a': 2, 'c_b_x': 5, 'd': [1, 2, 3], 'c_b_y': 10}
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
如果你不介意递归函数,这里有一个解决方案。我还冒昧地包含了一个排除参数,以防您希望维护一个或多个值。
代码:
def flatten_dict(dictionary, exclude = [], delimiter ='_'):
flat_dict = dict()
for key, value in dictionary.items():
if isinstance(value, dict) and key not in exclude:
flatten_value_dict = flatten_dict(value, exclude, delimiter)
for k, v in flatten_value_dict.items():
flat_dict[f"{key}{delimiter}{k}"] = v
else:
flat_dict[key] = value
return flat_dict
用法:
d = {'a':1, 'b':[1, 2], 'c':3, 'd':{'a':4, 'b':{'a':7, 'b':8}, 'c':6}, 'e':{'a':1,'b':2}}
flat_d = flatten_dict(dictionary=d, exclude=['e'], delimiter='.')
print(flat_d)
输出:
{'a': 1, 'b': [1, 2], 'c': 3, 'd.a': 4, 'd.b.a': 7, 'd.b.b': 8, 'd.c': 6, 'e': {'a': 1, 'b': 2}}
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。
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)