Remove some field from nested dictionary? - python

For example I have a dict:
{
"a" : 123,
"b" : {
"a" : 24324,
"c" : 9
},
"c" : {
"a" : 123,
"b" : 64
}
}
What is the best way to remove all a fields from this dictionary? I understand, that I can do an iteration over this dict, remove a field, that iterate on the keys, which are also dicts and so on.
But maybe there is more elegant way to do it?
EDIT
Thanks for your answers! But what about a situation, when keys can be lists, like "b" : [{"a" : 1, "c" : 2}]

Well, internally you have to process the items one by one, either by manual iteration or recursion.
Here's an attempt using recursion:
def remove_keys(d, to_remove):
if not isinstance(d, dict):
return d
return {k: remove_keys(v, to_remove)
for k, v in d.items() if k not in to_remove}
You would simply pass the dictionary to process as the first argument and the name of the keys to remove (as a set, preferably) as the second argument. In your case:
remove_keys(d, {"a"})
Whether it's more elegant or not, it depends on your taste, I would say :).
If you want to actually mutate the dictionary:
def remove_keys_m(d, to_remove):
if not isinstance(d, dict):
return d
for k in to_remove:
if k in d:
del d[k]
for k in d:
d[k] = remove_keys(d[k], to_remove)
return d

def remove_entries(d, k):
if k in d:
del d[k]
for value in d.values():
if isinstance(value, dict):
remove_entries(value, k)
Here's a pretty basic recursive function for doing it
Edit:
If you also want to handle lists nested in dicts, nested in lists, etc, something like the below will owrk.
def remove_from_dict_in_list(l, k):
for i in l:
if isinstance(i, list):
remove_from_dict_in_list(i, k)
elif isinstance(i, dict):
remove_entries(i, k)
def remove_entries(d, k):
if k in d:
del d[k]
for value in d.values():
if isinstance(value, dict):
remove_entries(value, k)
elif isinstance(value, list):
remove_from_dict_in_list(value, k)

While a recursive solution is more robust, here is a simpler solution that will work for the posted example and any other dictionary with only one nested layer:
s = {
"a" : 123,
"b" : {
"a" : 24324,
"c" : 9
},
"c" : {
"a" : 123,
"b" : 64
}
}
final_data = {a:{c:d for c, d in b.items() if c != "a"} for a, b in s.items() if a != "a"}
Output:
{'c': {'b': 64}, 'b': {'c': 9}}

I think this example will answer your question.
dic = {"a": 1,
"b": {"a": 2,
"c": {"a": 3}},
"d": 4}
key_to_del = "a"
def get_key(dic):
for key, value in dic.items():
if key == key_to_del:
del dic[key]
if isinstance(value, dict):
get_key(value)
return dic
print "BEFOR", dic
print "AFTER", get_key(dic)
enter image description here

Related

From a given nested dictionary, find all the nested keys sequences

I have a nested dictionary which looks like this:
dct = {"A": {"AA": "aa", "BB": {"BBB": "bbb", "CCC": "ccc"}}}
I want to extract all the key sequences in the list format till I reach the deepest key:value pair.
The expected output is something like this:
["A->AA", "A->BB->BBB", "A->BB->CCC"]
The solution I tried is:
for k, v in dct.items():
if isinstance(v, dict):
# traverse nested dict
for x in find_keys(v):
yield "{}_{}".format(k, x)
print("{}_{}".format(k, x))
else:
yield k
print(k)
but it doesnot seem to work as expected.
I guess you are almost there (or omitted some parts by mistake):
def find_keys(dct):
for k, v in dct.items():
if isinstance(v, dict):
yield from (f"{k}->{x}" for x in find_keys(v))
else:
yield k
dct = {"A": {"AA": "aa", "BB": {"BBB": "bbb", "CCC": "ccc"}}}
print(*find_keys(dct)) # A->AA A->BB->BBB A->BB->CCC
If you want to use return instead, then:
def find_keys(dct):
result = []
for k, v in dct.items():
if isinstance(v, dict):
result += [f"{k}->{x}" for x in find_keys(v)]
else:
result.append(k)
return result

Nested dictionary with different number of layers in each key [duplicate]

This question already has answers here:
Flatten nested dictionaries, compressing keys
(32 answers)
Closed 2 years ago.
I have nested dictionary like following
{
"A":
{"B":
{"C":
{"D": ['1','2','3']
}
}
},
"AA":
{"BB":
{"CC": ['11', '22']}
}
}
I have to create a new dictionary in the following format:
{"xx-A-B-C-D": ['1','2','3'], "xx-AA-BB-CC": ['11','22']}
That is, the keys of the new dictionary are the original dictionary keys concatenated with 'xx' as the prefix, and the values are the values of the original dictionary.
I am still stuck after trying out for 5 hours.
Any one care to peel the onion?
The following functions are my 2 attempts.
def get_value_from_dict(dict_obj, target):
results = []
def _get_value_from_dict(obj, results, target):
if isinstance(obj, dict):
for key, value in obj.items():
if key == target:
results.append(value)
elif isinstance(value, (list, dict)):
_get_value_from_dict(value, results, target)
elif isinstance(obj, list):
for item in obj:
_get_value_from_dict(item, results, target)
return results
results = _get_value_from_dict(dict_obj, results, target)
return results
def myprint(d):
for k, v in d.items():
if isinstance(v, dict):
myprint(v)
else:
print("{0} : {1}".format(k, v))
Use flatten_dict library:
Step 1: Install using pip install flatten-dict
Step 2:
2.1. Use the flatten function with the dictionary as an argument, and special_reducer to determine how to concatenate values.
d= {
"A":
{"B":
{"C":
{"D": ['1','2','3']
}
}
},
"AA":
{"BB":
{"CC": ['11', '22']}
}
}
from flatten_dict import flatten
def special_reducer(k1, k2, seperator='-', prefix='xx'):
if k1 is None:
return prefix + seperator + k2
else:
return k1 + seperator + k2
r = flatten(d, reducer=special_reducer)
# {'xx-A-B-C-D': ['1', '2', '3'], 'xx-AA-BB-CC': ['11', '22']}
print(r)

Is there a pythonic way to process tree-structured dict keys?

I'm looking for a pythonic idiom to turn a list of keys and a value into a dict with those keys nested. For example:
dtree(["a", "b", "c"]) = 42
or
dtree("a/b/c".split(sep='/')) = 42
would return the nested dict:
{"a": {"b": {"c": 42}}}
This could be used to turn a set of values with hierarchical keys into a tree:
dtree({
"a/b/c": 10,
"a/b/d": 20,
"a/e": "foo",
"a/f": False,
"g": 30 })
would result in:
{ "a": {
"b": {
"c": 10,
"d": 20 },
"e": foo",
"f": False },
"g": 30 }
I could write some FORTRANish code to do the conversion using brute force and multiple loops and maybe collections.defaultdict, but it seems like a language with splits and joins and slices and comprehensions should have a primitive that turns a list of strings ["a","b","c"] into nested dict keys ["a"]["b"]["c"]. What is the shortest way to do this without using eval on a dict expression string?
I'm looking for a pythonic idiom to turn a list of keys and a value into a dict with those keys nested.
reduce(lambda v, k: {k: v}, reversed("a/b/c".split("/")), 42)
This could be used to turn a set of values with hierarchical keys into a tree
def hdict(keys, value, sep="/"):
return reduce(lambda v, k: {k: v}, reversed(keys.split(sep)), value)
def merge_dict(trg, src):
for k, v in src.items():
if k in trg:
merge_dict(trg[k], v)
else:
trg[k] = v
def hdict_from_dict(src):
result = {}
for sub_hdict in map(lambda kv: hdict(*kv), src.items()):
merge_dict(result, sub_hdict)
return result
data = {
"a/b/c": 10,
"a/b/d": 20,
"a/e": "foo",
"a/f": False,
"g": 30 }
print(hdict_from_dict(data))
Another overall solution using collections.defaultdict
import collections
def recursive_dict():
return collections.defaultdict(recursive_dict)
def dtree(inp):
result = recursive_dict()
for keys, value in zip(map(lambda s: s.split("/"), inp), inp.values()):
reduce(lambda d, k: d[k], keys[:-1], result)[keys[-1]] = value
return result
import json
print(json.dumps(dtree({
"a/b/c": 10,
"a/b/d": 20,
"a/e": "foo",
"a/f": False,
"g": 30 }), indent=4))
Or just for grins since reduce is the coolest thing since sliced bread, you could save one SLOC by using it twice :-)
def dmerge(x, y):
result = x.copy()
k = next(iter(y))
if k in x:
result[k] = dmerge(x[k], y[k])
else:
result.update(y)
return result
def hdict(keys, value, sep="/"):
return reduce(lambda v, k: {k: v}, reversed(keys.split(sep)), value)
def hdict_from_dict(src):
return reduce(lambda x, y: dmerge(x, y), [hdict(k, v) for k, v in src.items()])
data = {
"a/b/c": 10,
"a/b/d": 20,
"a/e": "foo",
"a/f": False,
"g": 30 }
print("flat:", data)
print("tree:", hdict_from_dict(data))

Loop through all nested dictionary values?

for k, v in d.iteritems():
if type(v) is dict:
for t, c in v.iteritems():
print "{0} : {1}".format(t, c)
I'm trying to loop through a dictionary and print out all key value pairs where the value is not a nested dictionary. If the value is a dictionary I want to go into it and print out its key value pairs...etc. Any help?
EDIT
How about this? It still only prints one thing.
def printDict(d):
for k, v in d.iteritems():
if type(v) is dict:
printDict(v)
else:
print "{0} : {1}".format(k, v)
Full Test Case
Dictionary:
{u'xml': {u'config': {u'portstatus': {u'status': u'good'}, u'target': u'1'},
u'port': u'11'}}
Result:
xml : {u'config': {u'portstatus': {u'status': u'good'}, u'target': u'1'}, u'port': u'11'}
As said by Niklas, you need recursion, i.e. you want to define a function to print your dict, and if the value is a dict, you want to call your print function using this new dict.
Something like :
def myprint(d):
for k, v in d.items():
if isinstance(v, dict):
myprint(v)
else:
print("{0} : {1}".format(k, v))
There are potential problems if you write your own recursive implementation or the iterative equivalent with stack. See this example:
dic = {}
dic["key1"] = {}
dic["key1"]["key1.1"] = "value1"
dic["key2"] = {}
dic["key2"]["key2.1"] = "value2"
dic["key2"]["key2.2"] = dic["key1"]
dic["key2"]["key2.3"] = dic
In the normal sense, nested dictionary will be a n-nary tree like data structure. But the definition doesn't exclude the possibility of a cross edge or even a back edge (thus no longer a tree). For instance, here key2.2 holds to the dictionary from key1, key2.3 points to the entire dictionary(back edge/cycle). When there is a back edge(cycle), the stack/recursion will run infinitely.
root<-------back edge
/ \ |
_key1 __key2__ |
/ / \ \ |
|->key1.1 key2.1 key2.2 key2.3
| / | |
| value1 value2 |
| |
cross edge----------|
If you print this dictionary with this implementation from Scharron
def myprint(d):
for k, v in d.items():
if isinstance(v, dict):
myprint(v)
else:
print "{0} : {1}".format(k, v)
You would see this error:
> RuntimeError: maximum recursion depth exceeded while calling a Python object
The same goes with the implementation from senderle.
Similarly, you get an infinite loop with this implementation from Fred Foo:
def myprint(d):
stack = list(d.items())
while stack:
k, v = stack.pop()
if isinstance(v, dict):
stack.extend(v.items())
else:
print("%s: %s" % (k, v))
However, Python actually detects cycles in nested dictionary:
print dic
{'key2': {'key2.1': 'value2', 'key2.3': {...},
'key2.2': {'key1.1': 'value1'}}, 'key1': {'key1.1': 'value1'}}
"{...}" is where a cycle is detected.
As requested by Moondra this is a way to avoid cycles (DFS):
def myprint(d):
stack = list(d.items())
visited = set()
while stack:
k, v = stack.pop()
if isinstance(v, dict):
if k not in visited:
stack.extend(v.items())
else:
print("%s: %s" % (k, v))
visited.add(k)
Since a dict is iterable, you can apply the classic nested container iterable formula to this problem with only a couple of minor changes. Here's a Python 2 version (see below for 3):
import collections
def nested_dict_iter(nested):
for key, value in nested.iteritems():
if isinstance(value, collections.Mapping):
for inner_key, inner_value in nested_dict_iter(value):
yield inner_key, inner_value
else:
yield key, value
Test:
list(nested_dict_iter({'a':{'b':{'c':1, 'd':2},
'e':{'f':3, 'g':4}},
'h':{'i':5, 'j':6}}))
# output: [('g', 4), ('f', 3), ('c', 1), ('d', 2), ('i', 5), ('j', 6)]
In Python 2, It might be possible to create a custom Mapping that qualifies as a Mapping but doesn't contain iteritems, in which case this will fail. The docs don't indicate that iteritems is required for a Mapping; on the other hand, the source gives Mapping types an iteritems method. So for custom Mappings, inherit from collections.Mapping explicitly just in case.
In Python 3, there are a number of improvements to be made. As of Python 3.3, abstract base classes live in collections.abc. They remain in collections too for backwards compatibility, but it's nicer having our abstract base classes together in one namespace. So this imports abc from collections. Python 3.3 also adds yield from, which is designed for just these sorts of situations. This is not empty syntactic sugar; it may lead to faster code and more sensible interactions with coroutines.
from collections import abc
def nested_dict_iter(nested):
for key, value in nested.items():
if isinstance(value, abc.Mapping):
yield from nested_dict_iter(value)
else:
yield key, value
Alternative iterative solution:
def myprint(d):
stack = d.items()
while stack:
k, v = stack.pop()
if isinstance(v, dict):
stack.extend(v.iteritems())
else:
print("%s: %s" % (k, v))
Slightly different version I wrote that keeps track of the keys along the way to get there
def print_dict(v, prefix=''):
if isinstance(v, dict):
for k, v2 in v.items():
p2 = "{}['{}']".format(prefix, k)
print_dict(v2, p2)
elif isinstance(v, list):
for i, v2 in enumerate(v):
p2 = "{}[{}]".format(prefix, i)
print_dict(v2, p2)
else:
print('{} = {}'.format(prefix, repr(v)))
On your data, it'll print
data['xml']['config']['portstatus']['status'] = u'good'
data['xml']['config']['target'] = u'1'
data['xml']['port'] = u'11'
It's also easy to modify it to track the prefix as a tuple of keys rather than a string if you need it that way.
Here is pythonic way to do it. This function will allow you to loop through key-value pair in all the levels. It does not save the whole thing to the memory but rather walks through the dict as you loop through it
def recursive_items(dictionary):
for key, value in dictionary.items():
if type(value) is dict:
yield (key, value)
yield from recursive_items(value)
else:
yield (key, value)
a = {'a': {1: {1: 2, 3: 4}, 2: {5: 6}}}
for key, value in recursive_items(a):
print(key, value)
Prints
a {1: {1: 2, 3: 4}, 2: {5: 6}}
1 {1: 2, 3: 4}
1 2
3 4
2 {5: 6}
5 6
A alternative solution to work with lists based on Scharron's solution
def myprint(d):
my_list = d.iteritems() if isinstance(d, dict) else enumerate(d)
for k, v in my_list:
if isinstance(v, dict) or isinstance(v, list):
myprint(v)
else:
print u"{0} : {1}".format(k, v)
I am using the following code to print all the values of a nested dictionary, taking into account where the value could be a list containing dictionaries. This was useful to me when parsing a JSON file into a dictionary and needing to quickly check whether any of its values are None.
d = {
"user": 10,
"time": "2017-03-15T14:02:49.301000",
"metadata": [
{"foo": "bar"},
"some_string"
]
}
def print_nested(d):
if isinstance(d, dict):
for k, v in d.items():
print_nested(v)
elif hasattr(d, '__iter__') and not isinstance(d, str):
for item in d:
print_nested(item)
elif isinstance(d, str):
print(d)
else:
print(d)
print_nested(d)
Output:
10
2017-03-15T14:02:49.301000
bar
some_string
Your question already has been answered well, but I recommend using isinstance(d, collections.Mapping) instead of isinstance(d, dict). It works for dict(), collections.OrderedDict(), and collections.UserDict().
The generally correct version is:
def myprint(d):
for k, v in d.items():
if isinstance(v, collections.Mapping):
myprint(v)
else:
print("{0} : {1}".format(k, v))
Iterative solution as an alternative:
def traverse_nested_dict(d):
iters = [d.iteritems()]
while iters:
it = iters.pop()
try:
k, v = it.next()
except StopIteration:
continue
iters.append(it)
if isinstance(v, dict):
iters.append(v.iteritems())
else:
yield k, v
d = {"a": 1, "b": 2, "c": {"d": 3, "e": {"f": 4}}}
for k, v in traverse_nested_dict(d):
print k, v
Here's a modified version of Fred Foo's answer for Python 2. In the original response, only the deepest level of nesting is output. If you output the keys as lists, you can keep the keys for all levels, although to reference them you need to reference a list of lists.
Here's the function:
def NestIter(nested):
for key, value in nested.iteritems():
if isinstance(value, collections.Mapping):
for inner_key, inner_value in NestIter(value):
yield [key, inner_key], inner_value
else:
yield [key],value
To reference the keys:
for keys, vals in mynested:
print(mynested[keys[0]][keys[1][0]][keys[1][1][0]])
for a three-level dictionary.
You need to know the number of levels before to access multiple keys and the number of levels should be constant (it may be possible to add a small bit of script to check the number of nesting levels when iterating through values, but I haven't yet looked at this).
I find this approach a bit more flexible, here you just providing generator function that emits key, value pairs and can be easily extended to also iterate over lists.
def traverse(value, key=None):
if isinstance(value, dict):
for k, v in value.items():
yield from traverse(v, k)
else:
yield key, value
Then you can write your own myprint function, then would print those key value pairs.
def myprint(d):
for k, v in traverse(d):
print(f"{k} : {v}")
A test:
myprint({
'xml': {
'config': {
'portstatus': {
'status': 'good',
},
'target': '1',
},
'port': '11',
},
})
Output:
status : good
target : 1
port : 11
I tested this on Python 3.6.
Nested dictionaries looping using isinstance() and yield function.
**isinstance is afunction that returns the given input and reference is true or false as in below case dict is true so it go for iteration.
**Yield is used to return from a function without destroying the states of its local variable and when the function is called, the execution starts from the last yield statement. Any function that contains a yield keyword is termed a generator.
students= {'emp1': {'name': 'Bob', 'job': 'Mgr'},
'emp2': {'name': 'Kim', 'job': 'Dev','emp3': {'namee': 'Saam', 'j0ob': 'Deev'}},
'emp4': {'name': 'Sam', 'job': 'Dev'}}
def nested_dict_pairs_iterator(dict_obj):
for key, value in dict_obj.items():
# Check if value is of dict type
if isinstance(value, dict):
# If value is dict then iterate over all its values
for pair in nested_dict_pairs_iterator(value):
yield (key, *pair)
else:
# If value is not dict type then yield the value
yield (key, value)
for pair in nested_dict_pairs_iterator(students):
print(pair)
For a ready-made solution install ndicts
pip install ndicts
Import a NestedDict in your script
from ndicts.ndicts import NestedDict
Initialize
dictionary = {
u'xml': {
u'config': {
u'portstatus': {u'status': u'good'},
u'target': u'1'
},
u'port': u'11'
}
}
nd = NestedDict(dictionary)
Iterate
for key, value in nd.items():
print(key, value)
While the original solution from #Scharron is beautiful and simple, it cannot handle the list very well:
def myprint(d):
for k, v in d.items():
if isinstance(v, dict):
myprint(v)
else:
print("{0} : {1}".format(k, v))
So this code can be slightly modified like this to handle list in elements:
def myprint(d):
for k, v in d.items():
if isinstance(v, dict):
myprint(v)
elif isinstance(v, list):
for i in v:
myprint(i)
else:
print("{0} : {1}".format(k, v))
These answers work for only 2 levels of sub-dictionaries. For more try this:
nested_dict = {'dictA': {'key_1': 'value_1', 'key_1A': 'value_1A','key_1Asub1': {'Asub1': 'Asub1_val', 'sub_subA1': {'sub_subA1_key':'sub_subA1_val'}}},
'dictB': {'key_2': 'value_2'},
1: {'key_3': 'value_3', 'key_3A': 'value_3A'}}
def print_dict(dictionary):
dictionary_array = [dictionary]
for sub_dictionary in dictionary_array:
if type(sub_dictionary) is dict:
for key, value in sub_dictionary.items():
print("key=", key)
print("value", value)
if type(value) is dict:
dictionary_array.append(value)
print_dict(nested_dict)
You can print recursively with a dictionary comprehension:
def print_key_pairs(d):
{k: print_key_pairs(v) if isinstance(v, dict) else print(f'{k}: {v}') for k, v in d.items()}
For your test case this is the output:
>>> print_key_pairs({u'xml': {u'config': {u'portstatus': {u'status': u'good'}, u'target': u'1'}, u'port': u'11'}})
status: good
target: 1
port: 11
Returns a tuple of each key and value and the key contains the full path
from typing import Mapping, Tuple, Iterator
def traverse_dict(nested: Mapping, parent_key="", keys_to_not_traverse_further=tuple()) -> Iterator[Tuple[str, str]]:
"""Each key is joined with it's parent using dot as a separator.
Once a `parent_key` matches `keys_to_not_traverse_further`
it will no longer find its child dicts.
"""
for key, value in nested.items():
if isinstance(value, abc.Mapping) and key not in keys_to_not_traverse_further:
yield from traverse_dict(value, f"{parent_key}.{key}", keys_to_not_traverse_further)
else:
yield f"{parent_key}.{key}", value
Let's test it
my_dict = {
"isbn": "123-456-222",
"author": {"lastname": "Doe", "firstname": "Jane"},
"editor": {"lastname": "Smith", "firstname": "Jane"},
"title": "The Ultimate Database Study Guide",
"category": ["Non-Fiction", "Technology"],
"first": {
"second": {"third": {"fourth": {"blah": "yadda"}}},
"fifth": {"sixth": "seventh"},
},
}
for k, v in traverse_dict(my_dict):
print(k, v)
Returns
.isbn 123-456-222
.author.lastname Doe
.author.firstname Jane
.editor.lastname Smith
.editor.firstname Jane
.title The Ultimate Database Study Guide
.category ['Non-Fiction', 'Technology']
.first.second.third.fourth.blah yadda
.first.fifth.sixth seventh
If you don't care about some child dicts e.g names in this case then
use the keys_to_not_traverse_further
for k, v in traverse_dict(my_dict, parent_key="", keys_to_not_traverse_further=("author","editor")):
print(k, v)
Returns
.isbn 123-456-222
.author {'lastname': 'Doe', 'firstname': 'Jane'}
.editor {'lastname': 'Smith', 'firstname': 'Jane'}
.title The Ultimate Database Study Guide
.category ['Non-Fiction', 'Technology']
.first.second.third.fourth.blah yadda
.first.fifth.sixth seventh

Filtering dictionaries and creating sub-dictionaries based on keys/values in Python?

Ok, I'm stuck, need some help from here on...
If I've got a main dictionary like this:
data = [ {"key1": "value1", "key2": "value2", "key1": "value3"},
{"key1": "value4", "key2": "value5", "key1": "value6"},
{"key1": "value1", "key2": "value8", "key1": "value9"} ]
Now, I need to go through that dictionary already to format some of the data, ie:
for datadict in data:
for key, value in datadict.items():
...filter the data...
Now, how would I in that same loop somehow (if possible... if not, suggest alternatives please) check for values of certain keys, and if those values match my presets then I would add that whole list to another dictionary, thus effectively creating smaller dictionaries as I go along out of this main dictionary based on certain keys and values?
So, let's say I want to create a sub-dictionary with all the lists in which key1 has value of "value1", which for the above list would give me something like this:
subdata = [ {"key1": "value1", "key2": "value2", "key1": "value3"},
{"key1": "value1", "key2": "value8", "key1": "value9"} ]
Here is a not so pretty way of doing it. The result is a generator, but if you really want a list you can surround it with a call to list(). Mostly it doesn't matter.
The predicate is a function which decides for each key/value pair if a dictionary in the list is going to cut it. The default one accepts all. If no k/v-pair in the dictionary matches it is rejected.
def filter_data(data, predicate=lambda k, v: True):
for d in data:
for k, v in d.items():
if predicate(k, v):
yield d
test_data = [{"key1":"value1", "key2":"value2"}, {"key1":"blabla"}, {"key1":"value1", "eh":"uh"}]
list(filter_data(test_data, lambda k, v: k == "key1" and v == "value1"))
# [{'key2': 'value2', 'key1': 'value1'}, {'key1': 'value1', 'eh': 'uh'}]
Net of the issues already pointed out in other comments and answers (multiple identical keys can't be in a dict, etc etc), here's how I'd do it:
def select_sublist(list_of_dicts, **kwargs):
return [d for d in list_of_dicts
if all(d.get(k)==kwargs[k] for k in kwargs)]
subdata = select_sublist(data, key1='value1')
The answer is too simple, so I guess we are missing some information. Anyway:
result = []
for datadict in data:
for key, value in datadict.items():
thefiltering()
if datadict.get('matchkey') == 'matchvalue':
result.append(datadict)
Also, you "main dictionary" is not a dictionary but a list. Just wanted to clear that up.
It's an old question, but for some reason there is no one-liner syntax answer:
{ k: v for k, v in <SOURCE_DICTIONARY>.iteritems() if <CONDITION> }
For example:
src_dict = { 1: 'a', 2: 'b', 3: 'c', 4: 'd' }
predicate = lambda k, v: k % 2 == 0
filtered_dict = { k: v for k, v in src_dict.iteritems() if predicate(k, v) }
print "Source dictionary:", src_dict
print "Filtered dictionary:", filtered_dict
Will produce the following output:
Source dictionary: {1: 'a', 2: 'b', 3: 'c', 4: 'd'}
Filtered dictionary: {2: 'b', 4: 'd'}
Inspired by the answer of Skurmedal, I split this into a recursive scheme to work with a database of nested dictionaries. In this case, a "record" is the subdictionary at the trunk. The predicate defines which records we are after -- those that match some (key,value) pair where these pairs may be deeply nested.
def filter_dict(the_dict, predicate=lambda k, v: True):
for k, v in the_dict.iteritems():
if isinstance(v, dict) and _filter_dict_sub(predicate, v):
yield k, v
def _filter_dict_sub(predicate, the_dict):
for k, v in the_dict.iteritems():
if isinstance(v, dict) and filter_dict_sub(predicate, v):
return True
if predicate(k, v):
return True
return False
Since this is a generator, you may need to wrap with dict(filter_dict(the_dict)) to obtain a filtered dictionary.

Categories