在Python多处理库中，是否有支持多个参数的pool.map变体？
import multiprocessing
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()
当前回答
Python 2的更好解决方案：
from multiprocessing import Pool
def func((i, (a, b))):
print i, a, b
return a + b
pool = Pool(3)
pool.map(func, [(0,(1,2)), (1,(2,3)), (2,(3, 4))])
输出
2 3 4
1 2 3
0 1 2
out[]:
[3, 5, 7]
其他回答
我认为以下内容会更好：
def multi_run_wrapper(args):
return add(*args)
def add(x,y):
return x+y
if __name__ == "__main__":
from multiprocessing import Pool
pool = Pool(4)
results = pool.map(multi_run_wrapper,[(1,2),(2,3),(3,4)])
print results
输出
[3, 5, 7]
这是我用来将多个参数传递给pool.imap fork中使用的单参数函数的例程的示例：
from multiprocessing import Pool
# Wrapper of the function to map:
class makefun:
def __init__(self, var2):
self.var2 = var2
def fun(self, i):
var2 = self.var2
return var1[i] + var2
# Couple of variables for the example:
var1 = [1, 2, 3, 5, 6, 7, 8]
var2 = [9, 10, 11, 12]
# Open the pool:
pool = Pool(processes=2)
# Wrapper loop
for j in range(len(var2)):
# Obtain the function to map
pool_fun = makefun(var2[j]).fun
# Fork loop
for i, value in enumerate(pool.imap(pool_fun, range(len(var1))), 0):
print(var1[i], '+' ,var2[j], '=', value)
# Close the pool
pool.close()
对我来说，以下是一个简单明了的解决方案：
from multiprocessing.pool import ThreadPool
from functools import partial
from time import sleep
from random import randint
def dosomething(var,s):
sleep(randint(1,5))
print(var)
return var + s
array = ["a", "b", "c", "d", "e"]
with ThreadPool(processes=5) as pool:
resp_ = pool.map(partial(dosomething,s="2"), array)
print(resp_)
输出：
a
b
d
e
c
['a2', 'b2', 'c2', 'd2', 'e2']
pool.map是否有支持多个参数的变体？
Python 3.3包含pool.starmap（）方法：
#!/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()
对于旧版本：
#!/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()
输出
1 1
2 1
3 1
注意这里是如何使用itertools.izip（）和itertools.crepeat（）的。
由于@unsubu提到的错误，您不能在Python 2.6上使用functools.partial（）或类似功能，因此应该显式定义简单包装函数func_tar（）。另请参阅uptimebox建议的解决方法。
另一个简单的选择是将函数参数包装在元组中，然后包装应该在元组中传递的参数。在处理大量数据时，这可能并不理想。我相信它会为每个元组创建副本。
from multiprocessing import Pool
def f((a,b,c,d)):
print a,b,c,d
return a + b + c +d
if __name__ == '__main__':
p = Pool(10)
data = [(i+0,i+1,i+2,i+3) for i in xrange(10)]
print(p.map(f, data))
p.close()
p.join()
以某种随机顺序给出输出：
0 1 2 3
1 2 3 4
2 3 4 5
3 4 5 6
4 5 6 7
5 6 7 8
7 8 9 10
6 7 8 9
8 9 10 11
9 10 11 12
[6, 10, 14, 18, 22, 26, 30, 34, 38, 42]
