bodo

This seems to work, although it really should be built in to pandas import pandas as pd from joblib import Parallel, delayed import multiprocessing def tmpFunc(df): df[‘c’] = df.a + df.b return df def applyParallel(dfGrouped, func): retLst = Parallel(n_jobs=multiprocessing.cpu_count())(delayed(func)(group) for name, group in dfGrouped) return pd.concat(retLst) if __name__ == ‘__main__’: df = pd.DataFrame({‘a’: [6, 2, … Read more