Created
August 4, 2019 17:23
-
-
Save nickthorpe/f201bc9c7a9fcee2ccd11b08c7cbbefc to your computer and use it in GitHub Desktop.
Parallelized Pandas Apply
This file contains hidden or 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
| from multiprocessing import Pool | |
| from functools import partial | |
| import numpy as np | |
| def parallelize(data, func, num_of_processes=8): | |
| data_split = np.array_split(data, num_of_processes) | |
| pool = Pool(num_of_processes) | |
| data = pd.concat(pool.map(func, data_split)) | |
| pool.close() | |
| pool.join() | |
| return data | |
| def run_on_subset(func, data_subset): | |
| return data_subset.apply(func, axis=1) | |
| def parallelize_on_rows(data, func, num_of_processes=8): | |
| return parallelize(data, partial(run_on_subset, func), num_of_processes) | |
| # so df.apply(some_func, axis=1) becomes parallelize_on_rows(df, some_func) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment