-
-
Save ved93/bb43f2b4d312b28bd9092b49f56b7737 to your computer and use it in GitHub Desktop.
pandas DataFrame apply multiprocessing
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
| import multiprocessing | |
| import pandas as pd | |
| import numpy as np | |
| def _apply_df(args): | |
| df, func, kwargs = args | |
| return df.apply(func, **kwargs) | |
| def apply_by_multiprocessing(df, func, **kwargs): | |
| workers = kwargs.pop('workers') | |
| pool = multiprocessing.Pool(processes=workers) | |
| result = pool.map(_apply_df, [(d, func, kwargs) | |
| for d in np.array_split(df, workers)]) | |
| pool.close() | |
| return pd.concat(list(result)) | |
| def square(x): | |
| return x**x | |
| if __name__ == '__main__': | |
| df = pd.DataFrame({'a':range(10), 'b':range(10)}) | |
| apply_by_multiprocessing(df, square, axis=1, workers=4) | |
| ## run by 4 processors | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment