我想在某个位置将一个项目插入OrderedDict。使用gist的this回答我的问题是它在python 3上不起作用。
这是使用的实现
from collections import OrderedDict
class ListDict(OrderedDict):
def __init__(self, *args, **kwargs):
super(ListDict, self).__init__(*args, **kwargs)
def __insertion(self, link_prev, key_value):
key, value = key_value
if link_prev[2] != key:
if key in self:
del self[key]
link_next = link_prev[1]
self._OrderedDict__map[key] = link_prev[1] = link_next[0] = [link_prev, link_next, key]
dict.__setitem__(self, key, value)
def insert_after(self, existing_key, key_value):
self.__insertion(self._OrderedDict__map[existing_key], key_value)
def insert_before(self, existing_key, key_value):
self.__insertion(self._OrderedDict__map[existing_key][0], key_value)
使用它就像
ld = ListDict([(1,1), (2,2), (3,3)])
ld.insert_before(2, (1.5, 1.5))
给
File "...", line 35, in insert_before
self.__insertion(self._OrderedDict__map[existing_key][0], key_value)
AttributeError: 'ListDict' object has no attribute '_OrderedDict__map'
它适用于python 2.7。它在python 3中失败的原因是什么?检查OrderedDict实现的源代码显示使用self.__map
而不是self._OrderedDict__map
。将代码更改为self.__map
的用法给出
AttributeError: 'ListDict' object has no attribute '_ListDict__map'
怎么会?我怎样才能在python 3中完成这项工作? OrderedDict使用内部__map
属性来存储双向链表。那么我该如何正确访问这个属性呢?
我不确定你会不会更好地服从你的代码中的单独列表和dict,但这里是对这样一个对象的纯Python实现的抨击。这将比Python 3.5中的实际OrderedDict
慢一个数量级,正如我在评论has been rewritten in C中指出的那样。
"""
A list/dict hybrid; like OrderedDict with insert_before and insert_after
"""
import collections.abc
class MutableOrderingDict(collections.abc.MutableMapping):
def __init__(self, iterable_or_mapping=None, **kw):
# This mimics dict's initialization and accepts the same arguments
# Of course, you have to pass an ordered iterable or mapping unless you
# want the order to be arbitrary. Garbage in, garbage out and all :)
self.__data = {}
self.__keys = []
if iterable_or_mapping is not None:
try:
iterable = iterable_or_mapping.items()
except AttributeError:
iterable = iterable_or_mapping
for key, value in iterable:
self.__keys.append(key)
self.__data[key] = value
for key, value in kw.items():
self.__keys.append(key)
self.__data[key] = value
def insert_before(self, key, new_key, value):
try:
self.__keys.insert(self.__keys.index(key), new_key)
except ValueError:
raise KeyError(key) from ValueError
else:
self.__data[new_key] = value
def insert_after(self, key, new_key, value):
try:
self.__keys.insert(self.__keys.index(key) + 1, new_key)
except ValueError:
raise KeyError(key) from ValueError
else:
self.__data[new_key] = value
def __getitem__(self, key):
return self.__data[key]
def __setitem__(self, key, value):
self.__keys.append(key)
self.__data[key] = value
def __delitem__(self, key):
del self.__data[key]
self.__keys.remove(key)
def __iter__(self):
return iter(self.__keys)
def __len__(self):
return len(self.__keys)
def __contains__(self, key):
return key in self.__keys
def __eq__(self, other):
try:
return (self.__data == dict(other.items()) and
self.__keys == list(other.keys()))
except AttributeError:
return False
def keys(self):
for key in self.__keys:
yield key
def items(self):
for key in self.__keys:
yield key, self.__data[key]
def values(self):
for key in self.__keys:
yield self.__data[key]
def get(self, key, default=None):
try:
return self.__data[key]
except KeyError:
return default
def pop(self, key, default=None):
value = self.get(key, default)
self.__delitem__(key)
return value
def popitem(self):
try:
return self.__data.pop(self.__keys.pop())
except IndexError:
raise KeyError('%s is empty' % self.__class__.__name__)
def clear(self):
self.__keys = []
self.__data = {}
def update(self, mapping):
for key, value in mapping.items():
self.__keys.append(key)
self.__data[key] = value
def setdefault(self, key, default):
try:
return self[key]
except KeyError:
self[key] = default
return self[key]
def __repr__(self):
return 'MutableOrderingDict(%s)' % ', '.join(('%r: %r' % (k, v)
for k, v in self.items()))
我最终实现了整个collections.abc.MutableMapping
合同,因为没有一个方法很长,但你可能不会全部使用它们。特别是,__eq__
和popitem
有点武断。我将你在insert_*
方法上的签名更改为一个对我来说更自然的4参数。最后说明:仅在Python 3.5上测试过。如果没有一些(次要)更改,当然不会在Python 2上工作。
尝试在3.7中尝试新的dict对象,并认为我会尝试实现Two-Bit Alchemist用他的答案做的但只是覆盖了原生的dict类,因为3.7 dict是有序的。
''' Script that extends python3.7 dictionary to include insert_before and insert_after methods. '''
from sys import exit as sExit
class MutableDict(dict):
''' Class that extends python3.7 dictionary to include insert_before and insert_after methods. '''
def insert_before(self, key, newKey, val):
''' Insert newKey:value into dict before key'''
try:
__keys = list(self.keys())
__vals = list(self.values())
insertAt = __keys.index(key)
__keys.insert(insertAt, newKey)
__vals.insert(insertAt, val)
self.clear()
self.update({x: __vals[i] for i, x in enumerate(__keys)})
except ValueError as e:
sExit(e)
def insert_after(self, key, newKey, val):
''' Insert newKey:value into dict after key'''
try:
__keys = list(self.keys())
__vals = list(self.values())
insertAt = __keys.index(key) + 1
if __keys[-1] != key:
__keys.insert(insertAt, newKey)
__vals.insert(insertAt, val)
self.clear()
self.update({x: __vals[i] for i, x in enumerate(__keys)})
else:
self.update({newKey: val})
except ValueError as e:
sExit(e)
一点点测试:
In: v = MutableDict([('a', 1), ('b', 2), ('c', 3)])
Out: {'a': 1, 'b': 2, 'c': 3}
In: v.insert_before('a', 'g', 5)
Out: {'g': 5, 'a': 1, 'b': 2, 'c': 3}
In: v.insert_after('b', 't', 5)
Out: {'g': 5, 'a': 1, 'b': 2, 't': 5, 'c': 3}
编辑:我决定做一点基准测试,看看这会带来什么样的性能影响。我会用from timeit import timeit
获得基线。创建具有任意值的dict。
In: timeit('{x: ord(x) for x in string.ascii_lowercase[:27]}', setup='import string', number=1000000)
Out: 1.8214202160015702
看看使用与以前相同的任意值初始化MutableDict需要多长时间。
In: timeit('MD({x: ord(x) for x in string.ascii_lowercase[:27]})', setup='import string; from MutableDict import MutableDict as MD', number=1000000)
Out: 2.382507269998314
1.82 / 2.38 = 0.76。因此,如果我正在考虑这个问题,MutableDict在创建时会慢24%。
让我们看看插入需要多长时间。对于这个测试,我将使用insert_after方法,因为它稍微大一些。还将寻找一个接近结尾的键进行插入。在这种情况下,'t'。
In: timeit('v.insert_after("t", "zzrr", ord("z"))', setup='import string; from MutableDict import MutableDict as MD; v = MD({x: ord(x) for x in string.ascii_lowercase[:27]})' ,number=1000000)
Out: 3.9161406760104
2.38 / 3.91 = 0.60,插入__比初始化慢40%。在一百万个循环的小测试中也不错。为了比较时间关系,我们将测试这个:
In: timeit('"-".join(map(str, range(100)))', number=1000000)
Out: 10.342204540997045
不太相似,但我希望这些测试能帮助您(读者不一定是OP)决定在3.7项目中使用或不使用此类。
从Python 3.2开始,move_to_end
可用于在OrderedDict
中移动项目。以下代码将通过将提供的索引之后的所有项目移动到结尾来实现insert
功能。
请注意,这不是很有效,应该谨慎使用(如果有的话)。
def ordered_dict_insert(ordered_dict, index, key, value):
if key in ordered_dict:
raise KeyError("Key already exists")
if index < 0 or index > len(ordered_dict):
raise IndexError("Index out of range")
keys = list(ordered_dict.keys())[index:]
ordered_dict[key] = value
for k in keys:
ordered_dict.move_to_end(k)
可以做出明显的优化和改进,但这是一般的想法。
from collections import OrderedDict
od1 = OrderedDict([
('a', 1),
('b', 2),
('d', 4),
])
items = od1.items()
items.insert(2, ('c', 3))
od2 = OrderedDict(items)
print(od2) # OrderedDict([('a', 1), ('b', 2), ('c', 3), ('d', 4)])