[Python] multiprocessing when iterating over a DNA sequence alignment

I'm trying to apply multiprocessing to a function to calculate the Shannon entropy for every position of a DNA alignment to speed up the process. It just keeps running without returning anything and I can't figure out what is wrong with my code. I'm pretty new to multiprocessing so any help would be greatly appreciated.

from Bio import AlignIO
from multiprocessing import Pool
from scipy.stats import entropy
import pandas as pd
from time import perf_counter

path = 'path_to_aln_fasta'
alignment = AlignIO.read(path, 'fasta')


def calc_entropy(column):
series = pd.Series(column)
vals = series.value_counts(normalize=False)
return entropy(vals)


def pool_calc_entropy(alignment):
pool = Pool(8)
entropies = pool.map(calc_entropy, [alignment[:, i] for i in range(alignment.get_alignment_length())])
return entropies

start = perf_counter()
entropies_series = []
for i in range(alignment.get_alignment_length()):
column = alignment[:, i]
entropies_series.append(calc_entropy(column))

end = perf_counter()
series_time = end-start
print(f'series time: {series_time}')

start = perf_counter()
entropies_pool = pool_calc_entropy(alignment)
end = perf_counter()
parallel_time = end-start
print(f'parallel time: {parallel_time}')

print(f'pool time is {round((end-start)/(end-start), 2)} times faster than series time')

Continue reading...