Am building a tree selector, I need to structure my data like a tree of grouped items. I have bellow input which is a list of dictionaries.
data = [
{'region': 'R1', 'group': 'G1', 'category': 'C1', 'item': 'I2'},
{'region': 'R1', 'group': 'G1', 'category': 'C1', 'item': 'I1'},
{'region': 'R1', 'group': 'G2', 'category': 'C2', 'item': 'I3'},
{'region': 'R2', 'group': 'G1', 'category': 'C1', 'item': 'I1'},
{'region': 'R2', 'group': 'G2', 'category': 'C2', 'item': 'I3'},
{'region': 'R2', 'group': 'G2', 'category': 'C2', 'item': 'I4'},
{'region': 'R2', 'group': 'G2', 'category': 'C3', 'item': 'I5'},
]
I want to get the following output
result = {
"regions": [
{
"name": "R1",
"groups": [
{
"name": "G1",
"categories": [
{"name": "C1","items": [{ "name": "I2"},{"name": "I1"}]}
]
},
{
"name": "G2",
"categories": [
{"name": "C2", "items": [{"name": "I3"}]}
]
}
]
},
{
"name": "R2",
"groups": [
{
"name": "G1",
"categories": [
{"name": "C1","items": [{"name": "I1"}]}
]
},
{
"name": "G2",
"categories": [
{"name": "C2","items": [{"name": "I3"},{"name": "I4"}]},
{"name": "C3", "items": [{"name": "I5"}]}
]
}
]
}
]
}
After some researches I come up with this solution
from collections import OrderedDict
d = OrderedDict()
for aggr in data:
d.setdefault(
key=(aggr['region'], aggr['group'], aggr['category']),
default=list()
).append({"name": aggr['item']})
d1 = OrderedDict()
for k, v in d.items():
d1.setdefault(
key=(k[0], k[1]),
default=list()
).append({"name": k[2], "items": v})
d2 = OrderedDict()
for k, v in d1.items():
d2.setdefault(
key=k[0],
default=list()
).append({"name": k[1], "categories": v})
result = {"regions": [{"name": k, "groups": v} for k, v in d2.items()]}
It's working but I believe it's not the most pythonic solution. I did not manage to simplify it.
Any help to propose another solution or improvement on above codes will be appreciated
CodePudding user response:
As long as the items are sorted, like in your example, you could use groupby
from itertools
in a recursive function, like:
from itertools import groupby
from operator import itemgetter
def plural(word):
return f"{word}s" if word[-1] != 'y' else f"{word[:-1]}ies"
def grouping(records, *keys):
if len(keys) == 1:
return [{"name": record[keys[0]]} for record in records]
return [
{"name": key, plural(keys[1]): grouping(group, *keys[1:])}
for key, group in groupby(records, itemgetter(keys[0]))
]
result = {"regions": grouping(data, "region", "group", "category", "item")}
If the sorting isn't guaranteed, then you could adjust grouping
in the following way
def grouping(records, *keys):
if len(keys) == 1:
return [{"name": record[keys[0]]} for record in records]
key_func = itemgetter(keys[0])
records = sorted(records, key=key_func)
return [
{"name": key, plural(keys[1]): grouping(group, *keys[1:])}
for key, group in groupby(records, key_func)
]
or sort the data
beforehand
keys = ["region", "group", "category", "item"]
data = sorted(data, key=itemgetter(*keys))
result = {"regions": grouping(data, *keys)}
Result of first version for data
as provided in the question:
result = {
"regions": [
{
"name": "R1",
"groups": [
{
"name": "G1",
"categories": [
{"name": "C1", "items": [{"name": "I2"}, {"name": "I1"}]
}
]
},
{
"name": "G2",
"categories": [
{"name": "C2", "items": [{"name": "I3"}]}
]
}
]
},
{
"name": "R2",
"groups": [
{
"name": "G1",
"categories": [
{"name": "C1", "items": [{"name": "I1"}]}
]
},
{
"name": "G2",
"categories": [
{"name": "C2", "items": [{"name": "I3"}, {"name": "I4"}]},
{"name": "C3", "items": [{"name": "I5"}]}
]
}
]
}
]
}