我发现自己经常制作多级词典。我总是必须编写非常冗长的代码来使用大量临时变量迭代字典的所有级别。
有没有办法概括这个函数来迭代多个级别,而不是硬编码并手动指定有多少级别?
def iterate_multilevel_dictionary(d, number_of_levels):
# How to auto-detect number of levels?
# number_of_levels = 0
if number_of_levels == 1:
for k1, v1 in d.items():
yield k1, v1
if number_of_levels == 2:
for k1, v1 in d.items():
for k2, v2 in v1.items():
yield k1, k2, v2
if number_of_levels == 3:
for k1, v1 in d.items():
for k2, v2 in v1.items():
for k3, v3 in v2.items():
yield k1, k2, k3, v3
# Level 1
d_level1 = {"a":1,"b":2,"c":3}
for items in iterate_multilevel_dictionary(d_level1, number_of_levels=1):
print(items)
# ('a', 1)
# ('b', 2)
# ('c', 3)
# Level 2
d_level2 = {"group_1":{"a":1}, "group_2":{"b":2,"c":3}}
for items in iterate_multilevel_dictionary(d_level2, number_of_levels=2):
print(items)
#('group_1', 'a', 1)
#('group_2', 'b', 2)
#('group_2', 'c', 3)
# Level 3
d_level3 = {"collection_1":d_level2}
for items in iterate_multilevel_dictionary(d_level3, number_of_levels=3):
print(items)
# ('collection_1', 'group_1', 'a', 1)
# ('collection_1', 'group_2', 'b', 2)
# ('collection_1', 'group_2', 'c', 3)
我在看到@VoNWooDSoN 的答案后写了这篇文章。我将它变成了一个迭代器,而不是在函数内部打印,并进行了一些更改以使其更具可读性。所以请在这里查看他的原始答案。
def flatten(d, base=()):
for k, v in d.items():
if isinstance(v, dict):
yield from flatten(v, base + (k,))
else:
yield base + (k, v)
1- 屈服而不是打印。
2-
isinstance()
而不是 type
,这样 dict
的子类也可以工作。您还可以使用 MutableMapping
模块中的 typing
代替 dict
使其更通用。
3- IMO,从
(k, v)
获取 .items()
对比 k
和 d[k]
更具可读性。
您是否想将其扩展到更通用的CAN(不必像OP中的解决方案一样)接受
depths
的数量以防万一?
考虑这些例子:
d_level1 = {"a": 1, "b": 2, "c": 3}
d_level2 = {"group_1": {"a": 1}, "group_2": {"b": 2, "c": 3}}
d_level3 = {"collection_1": d_level2}
for items in flatten(d_level3):
print(items)
print('------------------------------')
for items in flatten(d_level3, depth=0):
print(items)
print('------------------------------')
for items in flatten(d_level3, depth=1):
print(items)
print('------------------------------')
for items in flatten(d_level3, depth=2):
print(items)
输出:
('collection_1', 'group_1', 'a', 1)
('collection_1', 'group_2', 'b', 2)
('collection_1', 'group_2', 'c', 3)
------------------------------
('collection_1', {'group_1': {'a': 1}, 'group_2': {'b': 2, 'c': 3}})
------------------------------
('collection_1', 'group_1', {'a': 1})
('collection_1', 'group_2', {'b': 2, 'c': 3})
------------------------------
('collection_1', 'group_1', 'a', 1)
('collection_1', 'group_2', 'b', 2)
('collection_1', 'group_2', 'c', 3)
depth=None
不考虑深度(仍然按照你想要的方式工作)。但现在通过指定从 0
到 2
的深度,您可以看到我们能够迭代我们想要的深度。这是代码:
def flatten(d, base=(), depth=None):
for k, v in d.items():
if not isinstance(v, dict):
yield base + (k, v)
else:
if depth is None:
yield from flatten(v, base + (k,))
else:
if depth == 0:
yield base + (k, v)
else:
yield from flatten(v, base + (k,), depth - 1)
这里有一个快速但肮脏的解决方案:
d_level1 = {"a":1,"b":2,"c":3}
d_level2 = {"group_1":{"a":1}, "group_2":{"b":2,"c":3}}
d_level3 = {"collection_1":d_level2}
def flatten(d_in, base=()):
for k in d_in:
if type(d_in[k]) == dict:
flatten(d_in[k], base+(k,))
else:
print(base + (k, d_in[k]))
flatten(d_level1)
# ('a', 1)
# ('b', 2)
# ('c', 3)
flatten(d_level2)
#('group_1', 'a', 1)
#('group_2', 'b', 2)
#('group_2', 'c', 3)
flatten(d_level3)
# ('collection_1', 'group_1', 'a', 1)
# ('collection_1', 'group_2', 'b', 2)
# ('collection_1', 'group_2', 'c', 3)
注意!! Python 的递归限制约为 1000 次!因此,当在 python 中使用递归时,请仔细考虑您要做什么,并准备好在调用这样的递归函数时捕获 RuntimeError。
编辑: 通过评论,我意识到我犯了一个错误,我没有将密钥添加到 level1 字典输出中,并且我使用可变结构作为默认参数。我在打印声明中添加了这些和括号并重新发布。现在的输出与 OP 所需的输出相匹配,并使用更好、更现代的 python。
尝试一下这个代码
它还支持级别组合
from typing import List, Tuple
def iterate_multilevel_dictionary(d: dict):
dicts_to_iterate: List[Tuple[dict, list]] = [(d, [])]
'''
the first item is the dict object and the second object is the prefix keys
'''
while dicts_to_iterate:
current_dict, suffix = dicts_to_iterate.pop()
for k, v in current_dict.items():
if isinstance(v, dict):
dicts_to_iterate.append((v, suffix + [k]))
else:
yield suffix + [k] + [v]
if __name__ == '__main__':
d_level1 = {"a": 1, "b": 2, "c": 3}
print(f"test for {d_level1}")
for items in iterate_multilevel_dictionary(d_level1):
print(items)
d_level2 = {"group_1": {"a": 1}, "group_2": {"b": 2, "c": 3}}
print(f"test for {d_level2}")
for items in iterate_multilevel_dictionary(d_level2):
print(items)
d_level3 = {"collection_1": d_level2}
print(f"test for {d_level3}")
for items in iterate_multilevel_dictionary(d_level3):
print(items)
d_level123 = {}
[d_level123.update(i) for i in [d_level1, d_level2, d_level3]]
print(f"test for {d_level123}")
for items in iterate_multilevel_dictionary(d_level123):
print(items)
输出是:
test for {'a': 1, 'b': 2, 'c': 3}
['a', 1]
['b', 2]
['c', 3]
test for {'group_1': {'a': 1}, 'group_2': {'b': 2, 'c': 3}}
['group_2', 'b', 2]
['group_2', 'c', 3]
['group_1', 'a', 1]
test for {'collection_1': {'group_1': {'a': 1}, 'group_2': {'b': 2, 'c': 3}}}
['collection_1', 'group_2', 'b', 2]
['collection_1', 'group_2', 'c', 3]
['collection_1', 'group_1', 'a', 1]
test for {'a': 1, 'b': 2, 'c': 3, 'group_1': {'a': 1}, 'group_2': {'b': 2, 'c': 3}, 'collection_1': {'group_1': {'a': 1}, 'group_2': {'b': 2, 'c': 3}}}
['a', 1]
['b', 2]
['c', 3]
['collection_1', 'group_2', 'b', 2]
['collection_1', 'group_2', 'c', 3]
['collection_1', 'group_1', 'a', 1]
['group_2', 'b', 2]
['group_2', 'c', 3]
['group_1', 'a', 1]
使用递归是另一种方法,但我认为不使用递归进行编写更具挑战性且更高效:)
用于识别字典深度的线性解决方案。
d={'a':{1:1,2:2},"b":0,'c':"{}"}
print(d)
s=str(d)
dictionary_stack,dictionary_depth=0,0
def push():
global dictionary_depth
global dictionary_stack
dictionary_stack+=1
dictionary_depth=max(dictionary_depth,dictionary_stack)
def pop():
global dictionary_stack
dictionary_stack-=1
string_safety=False
for c in s:
if c =="'":
string_safety=not(string_safety)
if not(string_safety) and c =='{':
push()
if not(string_safety) and c =='}':
pop()
print(dictionary_depth)
输出:
{'a': {1:1, 2:2}, 'b': 0, 'c': '{}'}
2
nested_dict = {'A': {'key_B': 'value_B'},
'B': {'key_C': 'value_C'},
'C': {'key_C': {'key_D':'value_D'}}
}
def loop_nested(dictionary: dict):
for key in dictionary:
value = dictionary[key]
print(key)
if isinstance(value, dict):
loop_nested(value)
else:
print(value)
loop_nested(nested_dict)