#!/usr/bin/env python
__author__ = "Mageswaran Dhandapani"
__copyright__ = "Copyright 2020, The Spark Structured Playground Project"
__credits__ = []
__license__ = "Apache License"
__version__ = "2.0"
__maintainer__ = "Mageswaran Dhandapani"
__email__ = "mageswaran1989@gmail.com"
__status__ = "Education Purpose"
# https://stackoverflow.com/questions/18603270/progress-indicator-during-pandas-operations
import pandas as pd
import numpy as np
import multiprocessing
from functools import partial
def _df_split(tup_arg, **kwargs):
split_ind, df_split, df_f_name = tup_arg
return (split_ind, getattr(df_split, df_f_name)(**kwargs))
[docs]def df_multi_core(df, df_f_name, subset=None, njobs=-1, **kwargs):
if njobs == -1:
njobs = multiprocessing.cpu_count()
pool = multiprocessing.Pool(processes=njobs)
try:
splits = np.array_split(df[subset], njobs)
except ValueError:
splits = np.array_split(df, njobs)
pool_data = [(split_ind, df_split, df_f_name) for split_ind, df_split in enumerate(splits)]
results = pool.map(partial(_df_split, **kwargs), pool_data)
pool.close()
pool.join()
results = sorted(results, key=lambda x:x[0])
results = pd.concat([split[1] for split in results])
return results