Created
June 9, 2015 13:46
-
-
Save yanmhlv/383437e1cf478e9ae922 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import timeit | |
time_python = timeit.timeit(""" | |
from itertools import groupby | |
from random import randint | |
import pandas as pd | |
accruals = [ | |
{'account': i, 'value': i * randint(0, 20), 'foo': randint(0, 10)} | |
for i in range(5000) | |
] | |
payments = [ | |
{'account': i, 'value': i * randint(0, 10), 'foo': randint(0, 10)} | |
for i in range(5000) | |
] | |
accruals = groupby(accruals, key=lambda x: (x['account'], x['foo'])) | |
accruals = {key: list(values) for key, values in accruals} | |
payments = groupby(payments, key=lambda x: (x['account'], x['foo'])) | |
payments = {key: list(values) for key, values in payments} | |
result = {} | |
for accrual_key, values in accruals.items(): | |
result[accrual_key] = sum(v['value'] for v in values) - sum(v['value'] for v in payments.get(accrual_key, [])) | |
for payment_key, values in payments.items(): | |
if payment_key in result: | |
continue | |
result[payment_key] = 0 - sum(v['value'] for v in values) | |
# result = pd.DataFrame([{'account': key[0], 'foo': key[1], 'saldo': value} for key, value in result.items()]) | |
""", number=100) | |
print('time_python', time_python) | |
time_pandas = timeit.timeit(""" | |
import pandas as pd | |
from random import randint | |
accruals = [ | |
{'account': i, 'value': i * randint(0, 20), 'foo': randint(0, 10)} | |
for i in range(5000) | |
] | |
payments = [ | |
{'account': i, 'value': i * randint(0, 10), 'foo': randint(0, 10)} | |
for i in range(5000) | |
] | |
accruals = pd.DataFrame(accruals, columns=['account', 'value', 'foo']).set_index(['account', 'foo']) | |
payments = pd.DataFrame(payments, columns=['account', 'value', 'foo']).set_index(['account', 'foo']) | |
# [row.to_dict() for _, row in accruals.sub(payments, fill_value=0).iterrows()] | |
# accruals.sub(payments, fill_value=0).to_dict('records') | |
df = accruals.sub(payments, fill_value=0) | |
# df.to_dict('records') | |
df.to_json('records') | |
""", number=100) | |
print('time_pandas', time_pandas) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment