我有两本字典，但为了简化起见，我就选这两本:
>>> x = dict(a=1, b=2)
>>> y = dict(a=2, b=2)
现在，我想比较x中的每个键值对在y中是否有相同的对应值，所以我这样写:
>>> for x_values, y_values in zip(x.iteritems(), y.iteritems()):
if x_values == y_values:
print 'Ok', x_values, y_values
else:
print 'Not', x_values, y_values
它的工作原理是返回一个元组，然后比较是否相等。
我的问题:
这对吗?还有更好的办法吗?最好不是在速度上，我说的是代码优雅。
更新:我忘了提到，我必须检查有多少键，值对是相等的。
当前回答
Code
def equal(a, b):
type_a = type(a)
type_b = type(b)
if type_a != type_b:
return False
if isinstance(a, dict):
if len(a) != len(b):
return False
for key in a:
if key not in b:
return False
if not equal(a[key], b[key]):
return False
return True
elif isinstance(a, list):
if len(a) != len(b):
return False
while len(a):
x = a.pop()
index = indexof(x, b)
if index == -1:
return False
del b[index]
return True
else:
return a == b
def indexof(x, a):
for i in range(len(a)):
if equal(x, a[i]):
return i
return -1
Test
>>> a = {
'number': 1,
'list': ['one', 'two']
}
>>> b = {
'list': ['two', 'one'],
'number': 1
}
>>> equal(a, b)
True
其他回答
下面的代码将帮助您比较python中的dict列表
def compate_generic_types(object1, object2):
if isinstance(object1, str) and isinstance(object2, str):
return object1 == object2
elif isinstance(object1, unicode) and isinstance(object2, unicode):
return object1 == object2
elif isinstance(object1, bool) and isinstance(object2, bool):
return object1 == object2
elif isinstance(object1, int) and isinstance(object2, int):
return object1 == object2
elif isinstance(object1, float) and isinstance(object2, float):
return object1 == object2
elif isinstance(object1, float) and isinstance(object2, int):
return object1 == float(object2)
elif isinstance(object1, int) and isinstance(object2, float):
return float(object1) == object2
return True
def deep_list_compare(object1, object2):
retval = True
count = len(object1)
object1 = sorted(object1)
object2 = sorted(object2)
for x in range(count):
if isinstance(object1[x], dict) and isinstance(object2[x], dict):
retval = deep_dict_compare(object1[x], object2[x])
if retval is False:
print "Unable to match [{0}] element in list".format(x)
return False
elif isinstance(object1[x], list) and isinstance(object2[x], list):
retval = deep_list_compare(object1[x], object2[x])
if retval is False:
print "Unable to match [{0}] element in list".format(x)
return False
else:
retval = compate_generic_types(object1[x], object2[x])
if retval is False:
print "Unable to match [{0}] element in list".format(x)
return False
return retval
def deep_dict_compare(object1, object2):
retval = True
if len(object1) != len(object2):
return False
for k in object1.iterkeys():
obj1 = object1[k]
obj2 = object2[k]
if isinstance(obj1, list) and isinstance(obj2, list):
retval = deep_list_compare(obj1, obj2)
if retval is False:
print "Unable to match [{0}]".format(k)
return False
elif isinstance(obj1, dict) and isinstance(obj2, dict):
retval = deep_dict_compare(obj1, obj2)
if retval is False:
print "Unable to match [{0}]".format(k)
return False
else:
retval = compate_generic_types(obj1, obj2)
if retval is False:
print "Unable to match [{0}]".format(k)
return False
return retval
由于似乎没有人提到deepdiff，为了完整起见，我将在这里添加它。我发现它非常方便获得(嵌套)对象的差异:
安装
pip install deepdiff
示例代码
import deepdiff
import json
dict_1 = {
"a": 1,
"nested": {
"b": 1,
}
}
dict_2 = {
"a": 2,
"nested": {
"b": 2,
}
}
diff = deepdiff.DeepDiff(dict_1, dict_2)
print(json.dumps(diff, indent=4))
输出
{
"values_changed": {
"root['a']": {
"new_value": 2,
"old_value": 1
},
"root['nested']['b']": {
"new_value": 2,
"old_value": 1
}
}
}
注意关于检查结果的漂亮打印:如果两个字典具有相同的属性键(可能与示例中的属性值不同)，上面的代码就可以工作。但是，如果存在一个“extra”属性是字典之一，json.dumps()将失败
TypeError: Object of type PrettyOrderedSet is not JSON serializable
解决方案:使用diff.to_json()和json.loads() / json.dumps()来漂亮地打印:
import deepdiff
import json
dict_1 = {
"a": 1,
"nested": {
"b": 1,
},
"extra": 3
}
dict_2 = {
"a": 2,
"nested": {
"b": 2,
}
}
diff = deepdiff.DeepDiff(dict_1, dict_2)
print(json.dumps(json.loads(diff.to_json()), indent=4))
输出:
{
"dictionary_item_removed": [
"root['extra']"
],
"values_changed": {
"root['a']": {
"new_value": 2,
"old_value": 1
},
"root['nested']['b']": {
"new_value": 2,
"old_value": 1
}
}
}
替代方案:使用pprint，结果是不同的格式:
import pprint
# same code as above
pprint.pprint(diff, indent=4)
输出:
{ 'dictionary_item_removed': [root['extra']],
'values_changed': { "root['a']": { 'new_value': 2,
'old_value': 1},
"root['nested']['b']": { 'new_value': 2,
'old_value': 1}}}
def dict_compare(d1, d2):
d1_keys = set(d1.keys())
d2_keys = set(d2.keys())
shared_keys = d1_keys.intersection(d2_keys)
added = d1_keys - d2_keys
removed = d2_keys - d1_keys
modified = {o : (d1[o], d2[o]) for o in shared_keys if d1[o] != d2[o]}
same = set(o for o in shared_keys if d1[o] == d2[o])
return added, removed, modified, same
x = dict(a=1, b=2)
y = dict(a=2, b=2)
added, removed, modified, same = dict_compare(x, y)
对两个字典进行深度比较的最简单的方法(也是最健壮的方法之一)是将它们序列化为JSON格式，对键进行排序，并比较字符串结果:
import json
if json.dumps(x, sort_keys=True) == json.dumps(y, sort_keys=True):
... Do something ...
>>> hash_1
{'a': 'foo', 'b': 'bar'}
>>> hash_2
{'a': 'foo', 'b': 'bar'}
>>> set_1 = set (hash_1.iteritems())
>>> set_1
set([('a', 'foo'), ('b', 'bar')])
>>> set_2 = set (hash_2.iteritems())
>>> set_2
set([('a', 'foo'), ('b', 'bar')])
>>> len (set_1.difference(set_2))
0
>>> if (len(set_1.difference(set_2)) | len(set_2.difference(set_1))) == False:
... print "The two hashes match."
...
The two hashes match.
>>> hash_2['c'] = 'baz'
>>> hash_2
{'a': 'foo', 'c': 'baz', 'b': 'bar'}
>>> if (len(set_1.difference(set_2)) | len(set_2.difference(set_1))) == False:
... print "The two hashes match."
...
>>>
>>> hash_2.pop('c')
'baz'
这是另一个选择:
>>> id(hash_1)
140640738806240
>>> id(hash_2)
140640738994848
所以你可以看到这两个id是不同的。但是丰富的比较操作符似乎可以做到这一点:
>>> hash_1 == hash_2
True
>>>
>>> hash_2
{'a': 'foo', 'b': 'bar'}
>>> set_2 = set (hash_2.iteritems())
>>> if (len(set_1.difference(set_2)) | len(set_2.difference(set_1))) == False:
... print "The two hashes match."
...
The two hashes match.
>>>
