在Python中，计算两个列表之间差异的最佳方法是什么？

例

A = [1,2,3,4]
B = [2,5]

A - B = [1,3,4]
B - A = [5]

使用set，如果你不关心项目的顺序或重复。如果您使用列表理解，请执行以下操作：

>>> def diff(first, second):
        second = set(second)
        return [item for item in first if item not in second]

>>> diff(A, B)
[1, 3, 4]
>>> diff(B, A)
[5]
>>> 

如果顺序无关紧要，则可以简单地计算出设定差：

>>> set([1,2,3,4]) - set([2,5])
set([1, 4, 3])
>>> set([2,5]) - set([1,2,3,4])
set([5])

你可以做一个

list(set(A)-set(B))

和

list(set(B)-set(A))

一班轮：

diff = lambda l1,l2: [x for x in l1 if x not in l2]
diff(A,B)
diff(B,A)

要么：

diff = lambda l1,l2: filter(lambda x: x not in l2, l1)
diff(A,B)
diff(B,A)

上面的例子简化了计算差异的问题。假设排序或重复数据删除无疑会更轻松地计算差异，但是如果您的比较无法提供这些假设，那么您将需要一个非平凡的diff算法实现。请参阅python标准库中的difflib。

from difflib import SequenceMatcher 

squeeze=SequenceMatcher( None, A, B )

print "A - B = [%s]"%( reduce( lambda p,q: p+q, 
                               map( lambda t: squeeze.a[t[1]:t[2]], 
                                    filter(lambda x:x[0]!='equal', 
                                           squeeze.get_opcodes() ) ) ) )

A-B = [[1、3、4]]

Python 2.7.3（默认，2014年2月27日，19:58:35）-IPython 1.1.0-timeit：（github gist）

def diff(a, b):
  b = set(b)
  return [aa for aa in a if aa not in b]

def set_diff(a, b):
  return list(set(a) - set(b))

diff_lamb_hension = lambda l1,l2: [x for x in l1 if x not in l2]

diff_lamb_filter = lambda l1,l2: filter(lambda x: x not in l2, l1)

from difflib import SequenceMatcher
def squeezer(a, b):
  squeeze = SequenceMatcher(None, a, b)
  return reduce(lambda p,q: p+q, map(
    lambda t: squeeze.a[t[1]:t[2]],
      filter(lambda x:x[0]!='equal',
        squeeze.get_opcodes())))

结果：

# Small
a = range(10)
b = range(10/2)

timeit[diff(a, b)]
100000 loops, best of 3: 1.97 µs per loop

timeit[set_diff(a, b)]
100000 loops, best of 3: 2.71 µs per loop

timeit[diff_lamb_hension(a, b)]
100000 loops, best of 3: 2.1 µs per loop

timeit[diff_lamb_filter(a, b)]
100000 loops, best of 3: 3.58 µs per loop

timeit[squeezer(a, b)]
10000 loops, best of 3: 36 µs per loop

# Medium
a = range(10**4)
b = range(10**4/2)

timeit[diff(a, b)]
1000 loops, best of 3: 1.17 ms per loop

timeit[set_diff(a, b)]
1000 loops, best of 3: 1.27 ms per loop

timeit[diff_lamb_hension(a, b)]
1 loops, best of 3: 736 ms per loop

timeit[diff_lamb_filter(a, b)]
1 loops, best of 3: 732 ms per loop

timeit[squeezer(a, b)]
100 loops, best of 3: 12.8 ms per loop

# Big
a = xrange(10**7)
b = xrange(10**7/2)

timeit[diff(a, b)]
1 loops, best of 3: 1.74 s per loop

timeit[set_diff(a, b)]
1 loops, best of 3: 2.57 s per loop

timeit[diff_lamb_filter(a, b)]
# too long to wait for

timeit[diff_lamb_filter(a, b)]
# too long to wait for

timeit[diff_lamb_filter(a, b)]
# TypeError: sequence index must be integer, not 'slice'

@ roman-bodnarchuk列表推导函数def diff（a，b）似乎更快。

A = [1,2,3,4]
B = [2,5]

#A - B
x = list(set(A) - set(B))
#B - A 
y = list(set(B) - set(A))

print x
print y 

您可能需要使用set而不是list。

如果您希望差异递归地深入到列表中的项目，我为python编写了一个软件包： https //github.com/erasmose/deepdiff

安装

从PyPi安装：

pip install deepdiff

如果您是Python3，则还需要安装：

pip install future six

用法示例

>>> from deepdiff import DeepDiff
>>> from pprint import pprint
>>> from __future__ import print_function

同一对象返回空

>>> t1 = {1:1, 2:2, 3:3}
>>> t2 = t1
>>> ddiff = DeepDiff(t1, t2)
>>> print (ddiff.changes)
    {}

项目类型已更改

>>> t1 = {1:1, 2:2, 3:3}
>>> t2 = {1:1, 2:"2", 3:3}
>>> ddiff = DeepDiff(t1, t2)
>>> print (ddiff.changes)
    {'type_changes': ["root[2]: 2=<type 'int'> vs. 2=<type 'str'>"]}

项目的价值已更改

>>> t1 = {1:1, 2:2, 3:3}
>>> t2 = {1:1, 2:4, 3:3}
>>> ddiff = DeepDiff(t1, t2)
>>> print (ddiff.changes)
    {'values_changed': ['root[2]: 2 ====>> 4']}

添加和/或删除项目

>>> t1 = {1:1, 2:2, 3:3, 4:4}
>>> t2 = {1:1, 2:4, 3:3, 5:5, 6:6}
>>> ddiff = DeepDiff(t1, t2)
>>> pprint (ddiff.changes)
    {'dic_item_added': ['root[5, 6]'],
     'dic_item_removed': ['root[4]'],
     'values_changed': ['root[2]: 2 ====>> 4']}

弦差异

>>> t1 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":"world"}}
>>> t2 = {1:1, 2:4, 3:3, 4:{"a":"hello", "b":"world!"}}
>>> ddiff = DeepDiff(t1, t2)
>>> pprint (ddiff.changes, indent = 2)
    { 'values_changed': [ 'root[2]: 2 ====>> 4',
                          "root[4]['b']:\n--- \n+++ \n@@ -1 +1 @@\n-world\n+world!"]}
>>>
>>> print (ddiff.changes['values_changed'][1])
    root[4]['b']:
    --- 
    +++ 
    @@ -1 +1 @@
    -world
    +world!

弦差异2

>>> t1 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":"world!\nGoodbye!\n1\n2\nEnd"}}
>>> t2 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":"world\n1\n2\nEnd"}}
>>> ddiff = DeepDiff(t1, t2)
>>> pprint (ddiff.changes, indent = 2)
    { 'values_changed': [ "root[4]['b']:\n--- \n+++ \n@@ -1,5 +1,4 @@\n-world!\n-Goodbye!\n+world\n 1\n 2\n End"]}
>>>
>>> print (ddiff.changes['values_changed'][0])
    root[4]['b']:
    --- 
    +++ 
    @@ -1,5 +1,4 @@
    -world!
    -Goodbye!
    +world
     1
     2
     End

类型变更

>>> t1 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":[1, 2, 3]}}
>>> t2 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":"world\n\n\nEnd"}}
>>> ddiff = DeepDiff(t1, t2)
>>> pprint (ddiff.changes, indent = 2)
    { 'type_changes': [ "root[4]['b']: [1, 2, 3]=<type 'list'> vs. world\n\n\nEnd=<type 'str'>"]}

清单差异

>>> t1 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":[1, 2, 3]}}
>>> t2 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":[1, 2]}}
>>> ddiff = DeepDiff(t1, t2)
>>> pprint (ddiff.changes, indent = 2)
    { 'list_removed': ["root[4]['b']: [3]"]}

列表差异2：请注意，它没有考虑顺序

>>> # Note that it DOES NOT take order into account
... t1 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":[1, 2, 3]}}
>>> t2 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":[1, 3, 2]}}
>>> ddiff = DeepDiff(t1, t2)
>>> pprint (ddiff.changes, indent = 2)
    { }

包含字典的列表：

>>> t1 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":[1, 2, {1:1, 2:2}]}}
>>> t2 = {1:1, 2:2, 3:3, 4:{"a":"hello", "b":[1, 2, {1:3}]}}
>>> ddiff = DeepDiff(t1, t2)
>>> pprint (ddiff.changes, indent = 2)
    { 'dic_item_removed': ["root[4]['b'][2][2]"],
      'values_changed': ["root[4]['b'][2][1]: 1 ====>> 3"]}

最简单的方法

使用set（）。difference（set（））

list_a = [1,2,3]
list_b = [2,3]
print set(list_a).difference(set(list_b))

答案是 set([1])

如果是字典列表，则完整列表理解解决set方案会在解决方案提出时起作用

TypeError: unhashable type: 'dict'

测试用例

def diff(a, b):
    return [aa for aa in a if aa not in b]

d1 = {"a":1, "b":1}
d2 = {"a":2, "b":2}
d3 = {"a":3, "b":3}

>>> diff([d1, d2, d3], [d2, d3])
[{'a': 1, 'b': 1}]
>>> diff([d1, d2, d3], [d1])
[{'a': 2, 'b': 2}, {'a': 3, 'b': 3}]

如果需要，简单的代码可为您带来多个项目的不同：

a=[1,2,3,3,4]
b=[2,4]
tmp = copy.deepcopy(a)
for k in b:
    if k in tmp:
        tmp.remove(k)
print(tmp)

在查看In-operator的TimeComplexity时，在最坏的情况下它与O（n）一起使用。即使是套装。

因此，比较两个数组时，TimeComplexity在最佳情况下为O（n），在最坏情况下为O（n ^ 2）。

在最佳和最差情况下可与O（n）一起使用的另一种（但不幸的是更复杂）的解决方案是：

# Compares the difference of list a and b
# uses a callback function to compare items
def diff(a, b, callback):
  a_missing_in_b = []
  ai = 0
  bi = 0

  a = sorted(a, callback)
  b = sorted(b, callback)

  while (ai < len(a)) and (bi < len(b)):

    cmp = callback(a[ai], b[bi])
    if cmp < 0:
      a_missing_in_b.append(a[ai])
      ai += 1
    elif cmp > 0:
      # Item b is missing in a
      bi += 1
    else:
      # a and b intersecting on this item
      ai += 1
      bi += 1

  # if a and b are not of same length, we need to add the remaining items
  for ai in xrange(ai, len(a)):
    a_missing_in_b.append(a[ai])


  return a_missing_in_b

例如

>>> a=[1,2,3]
>>> b=[2,4,6]
>>> diff(a, b, cmp)
[1, 3]