How to concat list of dicts with same key-value python-CodePudding

I have a list of dicts stored in the list. I want to merge the same dicts in to one.

Input:

        data = [
        {'company': 'DAZ', 'process': 'Acesses', 'task': 'security', 'cmp_hours': 5106, 'prc_hours':744, 'hours':6}, 
        {'company': 'DAZ', 'process': 'Acesses', 'task': 'Approve', 'cmp_hours': 5106, 'prc_hours':744, 'hours':10}, 
        {'company': 'CAP', 'process': 'Agreements', 'task': 'Check', 'cmp_hours': 400, 'prc_hours':50, 'hours':5}, 
        {'company': 'CAP', 'process': 'Offboarding', 'task': 'Formation', 'cmp_hours': 400, 'prc_hours':75, 'hours':7}, 
        {'company': 'TOO', 'process': 'Offboarding', 'task': 'Formation', 'cmp_hours': 200, 'prc_hours':32, 'hours':2}
          ]

Required Output:

 [
    {
    'DAZ': {'cmp_hours':5106, 'processes': [{'process': 'Acesses', 'prc_hours' : 744,'tasks': [{'task': 'security', 'hours': 6}, {'task': 'Approve', 'hours': 10}]}]},
    'CAP': {'cmp_hours':400, 'processes': [{'process': 'Agreements', 'prc_hours' : 50,'tasks': [{'task': 'Check', 'hours': 5}]}, {'process_name': 'Offboarding', 'prc_hours' : 75,'tasks': [{'task': 'Formation', 'hours': 7}]}]},
    'TOO': {'cmp_hours':200, 'processes': [{'process': 'Offboarding', 'prc_hours' : 32,'tasks': [{'task': 'Formation', 'hours': 2}]}]}
    }
 ]

Approximate structure

  [{company : {cmp_hours, 'processes': [{process, prc_hours, 'tasks':[{task, hours}]}]}}]

CodePudding user response：

You can use collections.defaultdict with recursion:

from collections import defaultdict
def merge(d, p):
   r = defaultdict(list)
   for i in d:
     r[i[p[0][0]]].append(i)
   if p[0][1] is None:
     return {a:{p[0][-1]:sum(i[p[0][-1]] for i in b), 
                **merge(b, p[1:])} for a, b in r.items()}
   return {p[0][1]:[{p[0][0]:a, p[0][-1]:sum(i[p[0][-1]] for i in b), 
                     **({} if not p[1:] else merge(b, p[1:]))} for a, b in r.items()]}
  
data = [{'company': 'DAZ', 'process': 'Acesses', 'task': 'security', 'cmp_hours': 5106, 'prc_hours': 744, 'hours': 6}, {'company': 'DAZ', 'process': 'Acesses', 'task': 'Approve', 'cmp_hours': 5106, 'prc_hours': 744, 'hours': 10}, {'company': 'CAP', 'process': 'Agreements', 'task': 'Check', 'cmp_hours': 400, 'prc_hours': 50, 'hours': 5}, {'company': 'CAP', 'process': 'Offboarding', 'task': 'Formation', 'cmp_hours': 400, 'prc_hours': 75, 'hours': 7}, {'company': 'TOO', 'process': 'Offboarding', 'task': 'Formation', 'cmp_hours': 200, 'prc_hours': 32, 'hours': 2}]
print(merge(data, [['company', None, 'cmp_hours'], ['process', 'processes', 'prc_hours'], ['task', 'tasks', 'hours']]))

Output:

{'DAZ': {'cmp_hours': 10212, 'processes': [{'process': 'Acesses', 'prc_hours': 1488, 'tasks': [{'task': 'security', 'hours': 6}, {'task': 'Approve', 'hours': 10}]}]}, 'CAP': {'cmp_hours': 800, 'processes': [{'process': 'Agreements', 'prc_hours': 50, 'tasks': [{'task': 'Check', 'hours': 5}]}, {'process': 'Offboarding', 'prc_hours': 75, 'tasks': [{'task': 'Formation', 'hours': 7}]}]}, 'TOO': {'cmp_hours': 200, 'processes': [{'process': 'Offboarding', 'prc_hours': 32, 'tasks': [{'task': 'Formation', 'hours': 2}]}]}}