Multiprocessing on pandas DataFrame

I am applying a function on a Dataframe column but I want to make it faster as the function takes a lot of processing time when done serially.

df[df['codes']=='None']['q'][:1].apply(lambda x: clf(x,candidate_labels))

Serially a single row just takes 2.52 secs for running but when running the code below using multiprocessing it's taking a lot longer 51.61 secs and I have about 2500 rows for processing so it is going to take a lot of time to run the function. I am looking to speed it up at least 20%.

import multiprocessing
import pandas as pd
import numpy as np

def clf(x):
    ...
    return list
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))
    
if __name__ == '__main__':
    tart_time = time.time()
    res=apply_by_multiprocessing(df[df['codes']=='None']['q'][:1],clf, workers=4)  
    print(res)
    print("--- %s seconds ---" % (time.time() - start_time))
    ## run by 4 processors

I have also tried different iterations for multiprocessing but none seem to speed up the flow instaed they slow down my code.

from pandarallel import pandarallel
import time
pandarallel.initialize(progress_bar=True)

start_time = time.time()
categories = df[df['codes']=='None']['q'][:10].parallel_apply(lambda x: clf(x,candidate_labels))
print("--- %s seconds ---" % (time.time() - start_time))

Another experiment:

import multiprocessing as mp

def clf:
    ...
    return list

if __name__ == '__main__':
    p = mp.Pool(processes=8)
    pool_results = p.map(clf, df[df['codes']=='None']['q'][:1])
    p.close()
    p.join()