After a lot of research I found that Python has no good groupby function that you can use in a single line (like Linq GroupBy of C#). For that, I've made a sample reusable groupby function that works with one or more keys, I wouldn't say it has great performance (actually far from it). But, it works and it is easier to use :)
You may want to make changes based on your input:
import copy
import itertools
def yogee_groupby(coll, keys):
copied_collection = copy.deepcopy(coll)
master_key = ""
if len(keys) > 1:
copied_collection = copy.deepcopy(coll)
for key in keys:
master_key = master_key + key
for an_element in copied_collection:
element_key = ""
for key in keys:
element_key = element_key + an_element[key]
an_element[master_key] = element_key
else:
master_key = keys[0]
grouped = {}
sorted_collection = sorted(copied_collection, key = lambda item: item[master_key])
for k, g in itertools.groupby(sorted_collection, lambda item: item[master_key]):
group = list(g)
if len(keys) > 1:
for an_element in group:
an_element.pop(master_key, None)
grouped[k] = group
return grouped
def test_groupby_2():
test_data = [
{
"E1": "V1",
"E2": "V2",
"E3": ["V31","V32","V33","V34"],
"E3": {"E31":"V31","E32": "V32","E33": "V33","E34":"V34"}
},
{
"E1": "W1",
"E2": "W2",
"E3": ["W31","W32","W33","W34"],
"E3": {"E31":"W31","E32": "W32","E33": "W33","E34":"W34"}
},
{
"E1": "V1",
"E2": "V2",
"E3": ["VV31","VV32","VV33","VV34"],
"E3": {"E31":"VV31","E32": "VV32","E33": "VV33","E34":"VV34"}
},
{
"E1": "V1",
"E2": "V22",
"E3": ["X31","X32","X33","X34"],
"E3": {"E31":"X31","E32": "X32","E33": "X33","E34":"X34"}
},
]
grouped = yogee_groupby(test_data, ["E1", "E2"])
print(grouped)
grouped = yogee_groupby(test_data, ["E1"])
print(grouped)
test_groupby_2()
