Last active
September 25, 2015 17:39
-
-
Save AfonsoTsukamoto/a879a97806026dbc94fb to your computer and use it in GitHub Desktop.
A function for the min definition necessary for parallel operations with python's multiprocessing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import multiprocessing | |
# Parallel | |
# So, it goes like this: | |
# Given the number of 'to process' items, | |
# Check how the distribution for cores will be (eg: 100 items on 2 cores = 50) | |
# Then, split items in *number of cores* collections and spread them aroung a | |
# subprocess pool | |
# To split the set, we create the interval [0, number_of_items] and make it | |
# go up the original items collection *number of cores* times | |
# [Return] tuple with : 'map appliable' pool of subprocesses | |
# 'splitted' dataset | |
def split_dataset(data, set_size, cores): | |
splitted_dataset = [] | |
for i in range(0, cores): | |
splitted_dataset.append(data[i*set_size:(i+1)*set_size]) | |
return splitted_dataset | |
def parallelize(data): | |
number_of_cores = multiprocessing.cpu_count() | |
set_size = len(data) / number_of_cores | |
splitted = split_dataset(data, set_size, number_of_cores) | |
pool = multiprocessing.Pool(number_of_cores) | |
return (pool, splitted) | |
# For testes | |
import time | |
import random | |
def func(numb): | |
print "processing %s" % numb | |
val = random.randint(1, numb[0] + 2) | |
time.sleep(int(val)) | |
print "ended processing %s" % numb | |
data = list(range(0,100)) | |
pool, dataset = parallelize(data) | |
pool.map(func, dataset) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment