Sort the entire sub-dictionary using the values ​​of one of the subtasks

Question

I have a data structure, as shown below, and I would like to sort all the auxiliary dictionaries that should be sorted based on the values ​​of the "order" column.

Input:

to_sort = [
('Fruits', 
    {
    'size': {1:[4, 2, 7,9]}, 
    'name': {1:['Orange', 'Apple', 'Kiwi', 'Mango']},
    'color': {1:['Orange', 'Red', 'Brown','Green']},
    'order': {1:[2, 1, 4,3]}
    }
)
]

output:

[
('Fruits', 
    {
    'size': {1:[2, 4, 9, 7]}, 
    'name': {1:['Apple', 'Orange', 'Mango', 'Kiwi']},
    'color':{1:['Red', 'Orange', 'Green', 'Brown']},
    'order':{1:[1, 2, 3, 4]}
    }
)
]

I tried using lambda

sort = to_sort[1]
print(sorted(sort.items(), key=lambda i: i['order'].values()))

I get "tuple indices should be integers or fragments, not str" error

Answer 1

Assuming you are fine with changing the data structure as indicated in the comments, this will work for you. This is adapted from this other question: Sorting a list based on values ​​from another list?

to_sort = [('Fruits', {
    'size': [4, 2, 7,9],
    'name': ['Orange', 'Apple', 'Kiwi', 'Mango'],
    'color': ['Orange', 'Red', 'Brown','Green'],
    'order': [2, 1, 4,3]
    })
]

postsort = []
for category, catdata in to_sort:
    sorteddata = {}
    for name, namedata in catdata.iteritems():
        sorteddata[name] = [x for (y,x) in sorted(zip(catdata['order'], namedata))]
    postsort.append((category, sorteddata))
print postsort

Result:

[(
    'Fruits',
    {
        'color': ['Red', 'Orange', 'Green', 'Brown'],
        'size': [2, 4, 9, 7],
        'order': [1, 2, 3, 4],
        'name': ['Apple', 'Orange', 'Mango', 'Kiwi']
    }
)]

, , .

Answer 2

,

, (edit), 123):

>>> to_sort = [
... ('Fruits', 
...     {
...     'size': {1:[4, 2, 7,9]}, 
...     'name': {1:['Orange', 'Apple', 'Kiwi', 'Mango']},
...     'color': {123:['Orange', 'Red', 'Brown','Green']},
...     'order': {1:[2, 1, 4,3]}
...     }
... )
... ]
>>> d = to_sort[0][1]
>>> keys = list(d.keys())
>>> idx = keys.index('order')
>>> ordered_kv = zip(keys, zip(*sorted(zip(*(d[k][n] for k in keys for n in d[k])), key = lambda t:t[idx])))
>>> sorted_dict = {k:{n:list(v) for n in d[k]} for k,v in ordered_kv}
>>> from pprint import pprint
>>> pprint(sorted_dict)
{'color': {123: ['Red', 'Orange', 'Green', 'Brown']},
 'name': {1: ['Apple', 'Orange', 'Mango', 'Kiwi']},
 'order': {1: [1, 2, 3, 4]},
 'size': {1: [2, 4, 9, 7]}}

: -, 'order':

>>> keys = list(to_sort[0][1].keys())
>>> idx = keys.index('order')

zip , :

>>> list(zip(*(d[k][n] for k in keys for n in d[k])))
[(4, 2, 'Orange', 'Orange'), (2, 1, 'Red', 'Apple'), (7, 4, 'Brown', 'Kiwi'), (9, 3, 'Green', 'Mango')]

idx, "unzipped" ( zip-splat:

>>> list(zip(*sorted(zip(*(d[k][n] for k in keys for n in d[k])), key=lambda t:t[idx])))
[(2, 4, 9, 7), (1, 2, 3, 4), ('Red', 'Orange', 'Green', 'Brown'), ('Apple', 'Orange', 'Mango', 'Kiwi')]

, , , , :

>>> ordered_kv = zip(keys, zip(*sorted(zip(*(d[k][n] for k in keys for n in d[k])), key = lambda t:t[idx])))
>>> sorted_dict = {k:{n:list(v) for n in d[k]} for k,v in ordered_kv}
>>> from pprint import pprint
>>> pprint(sorted_dict)
{'color': {123: ['Red', 'Orange', 'Green', 'Brown']},
 'name': {1: ['Apple', 'Orange', 'Mango', 'Kiwi']},
 'order': {1: [1, 2, 3, 4]},
 'size': {1: [2, 4, 9, 7]}}

...

pandas , . :

>>> import pandas as pd
>>> df = pd.DataFrame({k: pd.Series(v[1]) for k,v in to_sort[0][1].items()})
>>> df
    color    name  order  size
0  Orange  Orange      2     4
1     Red   Apple      1     2
2   Brown    Kiwi      4     7
3   Green   Mango      3     9

, pandas DataFrame, , DataFrame, . , :

>>> df.sort_values('order')
    color    name  order  size
1     Red   Apple      1     2
0  Orange  Orange      2     4
3   Green   Mango      3     9
2   Brown    Kiwi      4     7