我将所提出的与 perfplot 比较,并发现

x | y   # Python 3.9+

是最快的解决方案,与旧的好解决方案

{**x, **y}

和

temp = x.copy()
temp.update(y)

此分類上一篇

---

重复字符的代码:

from collections import ChainMap
from itertools import chain
import perfplot


def setup(n):
    x = dict(zip(range(n), range(n)))
    y = dict(zip(range(n, 2 * n), range(n, 2 * n)))
    return x, y


def copy_update(x, y):
    temp = x.copy()
    temp.update(y)
    return temp


def add_items(x, y):
    return dict(list(x.items()) + list(y.items()))


def curly_star(x, y):
    return {**x, **y}


def chain_map(x, y):
    return dict(ChainMap({}, y, x))


def itertools_chain(x, y):
    return dict(chain(x.items(), y.items()))


def python39_concat(x, y):
    return x | y


b = perfplot.bench(
    setup=setup,
    kernels=[
        copy_update,
        add_items,
        curly_star,
        chain_map,
        itertools_chain,
        python39_concat,
    ],
    labels=[
        "copy_update",
        "dict(list(x.items()) + list(y.items()))",
        "{**x, **y}",
        "chain_map",
        "itertools.chain",
        "x | y",
    ],
    n_range=[2 ** k for k in range(18)],
    xlabel="len(x), len(y)",
    equality_check=None,
)
b.save("out.png")
b.show()

最好的版本我可以想象,而不使用复制将是:

from itertools import chain
x = {'a':1, 'b': 2}
y = {'b':10, 'c': 11}
dict(chain(x.iteritems(), y.iteritems()))

它比 dict(x.items() + y.items()) 更快,但不像 n = copy(a); n.update(b),至少在 CPython 上。

我个人最喜欢这个版本,因为它在一个单一的功能合成中描述了我想要的东西相当好,唯一的小问题是,它并不完全显而易见,Y的值超过X的值,但我不认为很难找到它。

一种替代:

z = x.copy()
z.update(y)

新在Python 3.9:使用联盟操作器(<unk>)合并类似于设置的句子:

>>> d = {'a': 1, 'b': 2}
>>> e = {'a': 9, 'c': 3}
>>> d | e
{'a': 9, 'b': 2, 'c': 3}

对于匹配密钥,正确的指数需要先行。

这也适用于<unk>=更改一个dict in-place:

>>> e |= d    # e = e | d
>>> e
{'a': 1, 'c': 3, 'b': 2}

x = {'a': 1, 'b': 2}
y = {'b': 3, 'c': 4}

>>> z
{'a': 1, 'b': 3, 'c': 4}

z = {**x, **y}

z = {**x, 'foo': 1, 'bar': 2, **y}

>>> z
{'a': 1, 'b': 3, 'foo': 1, 'bar': 2, 'c': 4}

z = x.copy()
z.update(y) # which returns None since it mutates z

def merge_two_dicts(x, y):
    """Given two dictionaries, merge them into a new dict as a shallow copy."""
    z = x.copy()
    z.update(y)
    return z

z = merge_two_dicts(x, y)

def merge_dicts(*dict_args):
    """
    Given any number of dictionaries, shallow copy and merge into a new dict,
    precedence goes to key-value pairs in latter dictionaries.
    """
    result = {}
    for dictionary in dict_args:
        result.update(dictionary)
    return result

z = merge_dicts(a, b, c, d, e, f, g) 

和 g 的关键值对将先行于字典 a 到 f 等。

z = dict(x.items() + y.items())

>>> c = dict(a.items() + b.items())
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: unsupported operand type(s) for +: 'dict_items' and 'dict_items'

同样,在 Python 3 (viewitems() 在 Python 2.7) 中采取元素的合并也会失败,当值是不可破坏的对象(如列表,例如)。即使您的值是可破坏的,因为套件是无形的,行为与先例无定义。

>>> c = dict(a.items() | b.items())

>>> x = {'a': []}
>>> y = {'b': []}
>>> dict(x.items() | y.items())
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: unhashable type: 'list'

>>> x = {'a': 2}
>>> y = {'a': 1}
>>> dict(x.items() | y.items())
{'a': 2}

另一个你不应该使用的黑客:

z = dict(x, **y)

字典的目的是采取可触摸的密钥(例如,frozensets或tuples),但这种方法在Python 3中失败,当密钥不是线条时。

>>> c = dict(a, **b)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: keyword arguments must be strings

和

dict(a=1, b=10, c=11)

{'a': 1, 'b': 10, 'c': 11}

>>> foo(**{('a', 'b'): None})
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: foo() keywords must be strings
>>> dict(**{('a', 'b'): None})
{('a', 'b'): None}

我的答案: merge_two_dicts(x,y)实际上对我来说看起来更清楚,如果我们实际上对可读性感兴趣。

from copy import deepcopy

def dict_of_dicts_merge(x, y):
    z = {}
    overlapping_keys = x.keys() & y.keys()
    for key in overlapping_keys:
        z[key] = dict_of_dicts_merge(x[key], y[key])
    for key in x.keys() - overlapping_keys:
        z[key] = deepcopy(x[key])
    for key in y.keys() - overlapping_keys:
        z[key] = deepcopy(y[key])
    return z

>>> x = {'a':{1:{}}, 'b': {2:{}}}
>>> y = {'b':{10:{}}, 'c': {11:{}}}
>>> dict_of_dicts_merge(x, y)
{'b': {2: {}, 10: {}}, 'a': {1: {}}, 'c': {11: {}}}

{k: v for d in dicts for k, v in d.items()} # iteritems in Python 2.7

dict((k, v) for d in dicts for k, v in d.items()) # iteritems in Python 2

from itertools import chain
z = dict(chain(x.items(), y.items())) # iteritems in Python 2

from timeit import repeat
from itertools import chain

x = dict.fromkeys('abcdefg')
y = dict.fromkeys('efghijk')

def merge_two_dicts(x, y):
    z = x.copy()
    z.update(y)
    return z

min(repeat(lambda: {**x, **y}))
min(repeat(lambda: merge_two_dicts(x, y)))
min(repeat(lambda: {k: v for d in (x, y) for k, v in d.items()}))
min(repeat(lambda: dict(chain(x.items(), y.items()))))
min(repeat(lambda: dict(item for d in (x, y) for item in d.items())))

>>> min(repeat(lambda: {**x, **y}))
1.0804965235292912
>>> min(repeat(lambda: merge_two_dicts(x, y)))
1.636518670246005
>>> min(repeat(lambda: {k: v for d in (x, y) for k, v in d.items()}))
3.1779992282390594
>>> min(repeat(lambda: dict(chain(x.items(), y.items()))))
2.740647904574871
>>> min(repeat(lambda: dict(item for d in (x, y) for item in d.items())))
4.266070580109954

$ uname -a
Linux nixos 4.19.113 #1-NixOS SMP Wed Mar 25 07:06:15 UTC 2020 x86_64 GNU/Linux

词典中的资源

z = MergeDict(x, y)

当使用这个新对象时,它将像合并词典一样行事,但它将有持续的创作时间和持续的记忆脚印,同时让原始词典无触摸。

当然,如果你使用结果很多,那么你会在某个时候达到创建一个真正的合并词典会是最快的解决方案的界限。

a = { 'x': 3, 'y': 4 }
b = MergeDict(a)  # we merge just one dict
b['x'] = 5
print b  # will print {'x': 5, 'y': 4}
print a  # will print {'y': 4, 'x': 3}

class MergeDict(object):
  def __init__(self, *originals):
    self.originals = ({},) + originals[::-1]  # reversed

  def __getitem__(self, key):
    for original in self.originals:
      try:
        return original[key]
      except KeyError:
        pass
    raise KeyError(key)

  def __setitem__(self, key, value):
    self.originals[0][key] = value

  def __iter__(self):
    return iter(self.keys())

  def __repr__(self):
    return '%s(%s)' % (
      self.__class__.__name__,
      ', '.join(repr(original)
          for original in reversed(self.originals)))

  def __str__(self):
    return '{%s}' % ', '.join(
        '%r: %r' % i for i in self.iteritems())

  def iteritems(self):
    found = set()
    for original in self.originals:
      for k, v in original.iteritems():
        if k not in found:
          yield k, v
          found.add(k)

  def items(self):
    return list(self.iteritems())

  def keys(self):
    return list(k for k, _ in self.iteritems())

  def values(self):
    return list(v for _, v in self.iteritems())