Sum Values In A List Of Lists Of Dictionaries Using Common Key-value Pairs

How do I sum duplicate elements in a list of lists of dictionaries? Sample list: data = [ [ {'user': 1, 'rating': 0}, {'user': 2, 'rating': 10},

Solution 1:

With pandas:

>>> import pandas as pd
>>> [pd.DataFrame(dicts).groupby('user', as_index=False, sort=False).sum().to_dict(orient='records') for dicts in data]
[[{'user': 1, 'rating': 20},
  {'user': 2, 'rating': 10},
  {'user': 3, 'rating': 10}],
 [{'user': 4, 'rating': 4},
  {'user': 2, 'rating': 80},
  {'user': 1, 'rating': 30}]]

Solution 2:

You can try:

from itertools import groupby

result = []
for lst in data:
    sublist = sorted(lst, key=lambda d: d['user'])
    grouped = groupby(sublist, key=lambda d: d['user'])
    result.append([
        {'user': name, 'rating': sum([d['rating'] for d in group])}
        for name, group in grouped])

# Sort the `result` `rating` wise:
result = [sorted(sub, key=lambda d: d['rating']) for sub in result]

# %%timeit# 7.54 µs ± 220 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)

---

UPDATE (A more efficient solution):

result = []
for lst in data:
    visited = {}
    for d in lst:
        if d['user'] in  visited:
            visited[d['user']]['rating'] += d['rating'] 
        else:
            visited[d['user']] = d

    result.append(sorted(visited.values(), key=lambda d: d['rating']))

# %% timeit# 2.5 µs ± 54 ns per loop (mean ± std. dev. of 7 runs, 100000 loops each)

Result:

# print(result)
[
    [
        {'user': 2, 'rating': 10},
        {'user': 3, 'rating': 10},
        {'user': 1, 'rating': 20}
    ],
    [
        {'user': 4, 'rating': 4},
        {'user': 1, 'rating': 30},
        {'user': 2, 'rating': 80}
    ]
]

Solution 3:

op = []
for lst in data:
    rating_of_user = {}
    for e in lst:
        user, rating = e['user'], e['rating']
        rating_of_user[user] = rating_of_user.get(user, 0) + rating
    op.append([{'user': u, 'rating': r} for u, r in rating_of_user.items()])

N.B.: since Python 3.7 dictionaries officially preserve the insertion order

Solution 4:

This should work:

from collections import defaultdict

data_without_duplicates = []
for l in data:
    users_ratings = defaultdict(int)
    for d in l:
        users_ratings[d["user"]] += d["rating"]
    data_without_duplicates.append(
        [{"user": user, "rating": rating} for user, rating in users_ratings.items()]
    )

Solution 5:

importpprintdata= [
        [
            {'user': 1, 'rating': 0},
            {'user': 2, 'rating': 10},
            {'user': 1, 'rating': 20},
            {'user': 3, 'rating': 10}
        ],
        [
            {'user': 4, 'rating': 4},
            {'user': 2, 'rating': 80},
            {'user': 1, 'rating': 20},
            {'user': 1, 'rating': 10}
        ],
    ]

def find(user, l):
    for i, d in enumerate(l):
        ifuser== d['user']:
            return i
    return -1

data_sum = []

for l in data:
    list_sum = []
    for d in l:
        idx = find(d['user'], list_sum)
        ifidx== -1:
            list_sum.append(d)
        else:
            list_sum[idx]['rating'] += d['rating']
    data_sum.append(list_sum)

pprint.pprint(data_sum)