Multiprocessing pandas apply

import multiprocessing as mp
import pandas.util.testing as pdt

def process_apply(x):
    # do some stuff to data here

def process(df):
    res = df.apply(process_apply, axis=1)
    return res

if __name__ == '__main__':
    p = mp.Pool(processes=8)
    split_dfs = np.array_split(big_df,8)
    pool_results = p.map(aoi_proc, split_dfs)
    p.close()
    p.join()

    # merging parts processed by different processes
    parts = pd.concat(pool_results, axis=0)

    # merging newly calculated parts to big_df
    big_df = pd.concat([big_df, parts], axis=1)

    # checking if the dfs were merged correctly
    pdt.assert_series_equal(parts['id'], big_df['id'])

Добавить комментарий