In the Python multiprocessing
library, is there a variant of pool.map
which supports multiple arguments?
text = "test"
def harvester(text, case):
X = case[0]
text+ str(X)
if __name__ == '__main__':
pool = multiprocessing.Pool(processes=6)
case = RAW_DATASET
pool.map(harvester(text,case),case, 1)
pool.close()
pool.join()
is there a variant of pool.map which support multiple arguments?
Python 3.3 includes pool.starmap()
method:
#!/usr/bin/env python3
from functools import partial
from itertools import repeat
from multiprocessing import Pool, freeze_support
def func(a, b):
return a + b
def main():
a_args = [1,2,3]
second_arg = 1
with Pool() as pool:
L = pool.starmap(func, [(1, 1), (2, 1), (3, 1)])
M = pool.starmap(func, zip(a_args, repeat(second_arg)))
N = pool.map(partial(func, b=second_arg), a_args)
assert L == M == N
if __name__=="__main__":
freeze_support()
main()
For older versions:
#!/usr/bin/env python2
import itertools
from multiprocessing import Pool, freeze_support
def func(a, b):
print a, b
def func_star(a_b):
"""Convert `f([1,2])` to `f(1,2)` call."""
return func(*a_b)
def main():
pool = Pool()
a_args = [1,2,3]
second_arg = 1
pool.map(func_star, itertools.izip(a_args, itertools.repeat(second_arg)))
if __name__=="__main__":
freeze_support()
main()
1 1
2 1
3 1
Notice how itertools.izip()
and itertools.repeat()
are used here.
Due to the bug mentioned by @unutbu you can't use functools.partial()
or similar capabilities on Python 2.6, so the simple wrapper function func_star()
should be defined explicitly. See also the workaround suggested by uptimebox
.