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
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()
其他回答
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']
答案取决于版本和情况。最近版本的Python（从3.3开始）的最一般的答案首先由J.F.Sebastian在下面描述。1它使用Pool.starmap方法，接受一系列参数元组。然后，它会自动将每个元组中的参数解包，并将它们传递给给定的函数：
import multiprocessing
from itertools import product
def merge_names(a, b):
return '{} & {}'.format(a, b)
if __name__ == '__main__':
names = ['Brown', 'Wilson', 'Bartlett', 'Rivera', 'Molloy', 'Opie']
with multiprocessing.Pool(processes=3) as pool:
results = pool.starmap(merge_names, product(names, repeat=2))
print(results)
# Output: ['Brown & Brown', 'Brown & Wilson', 'Brown & Bartlett', ...
对于早期版本的Python，您需要编写一个助手函数来显式地解包参数。如果要与一起使用，还需要编写一个包装器，将Pool转换为上下文管理器。（感谢穆恩指出了这一点。）
import multiprocessing
from itertools import product
from contextlib import contextmanager
def merge_names(a, b):
return '{} & {}'.format(a, b)
def merge_names_unpack(args):
return merge_names(*args)
@contextmanager
def poolcontext(*args, **kwargs):
pool = multiprocessing.Pool(*args, **kwargs)
yield pool
pool.terminate()
if __name__ == '__main__':
names = ['Brown', 'Wilson', 'Bartlett', 'Rivera', 'Molloy', 'Opie']
with poolcontext(processes=3) as pool:
results = pool.map(merge_names_unpack, product(names, repeat=2))
print(results)
# Output: ['Brown & Brown', 'Brown & Wilson', 'Brown & Bartlett', ...
在更简单的情况下，使用固定的第二个参数，也可以使用partial，但仅在Python 2.7+中使用。
import multiprocessing
from functools import partial
from contextlib import contextmanager
@contextmanager
def poolcontext(*args, **kwargs):
pool = multiprocessing.Pool(*args, **kwargs)
yield pool
pool.terminate()
def merge_names(a, b):
return '{} & {}'.format(a, b)
if __name__ == '__main__':
names = ['Brown', 'Wilson', 'Bartlett', 'Rivera', 'Molloy', 'Opie']
with poolcontext(processes=3) as pool:
results = pool.map(partial(merge_names, b='Sons'), names)
print(results)
# Output: ['Brown & Sons', 'Wilson & Sons', 'Bartlett & Sons', ...
1.这大部分都是由他的答案激发的，而他的答案很可能应该被接受。但由于这本书一直停留在顶端，似乎最好为未来读者改进它。
另一种方法是将列表列表传递给单参数例程：
import os
from multiprocessing import Pool
def task(args):
print "PID =", os.getpid(), ", arg1 =", args[0], ", arg2 =", args[1]
pool = Pool()
pool.map(task, [
[1,2],
[3,4],
[5,6],
[7,8]
])
然后可以用自己喜欢的方法构造一个参数列表。
您可以使用以下两个函数，以避免为每个新函数编写包装器：
import itertools
from multiprocessing import Pool
def universal_worker(input_pair):
function, args = input_pair
return function(*args)
def pool_args(function, *args):
return zip(itertools.repeat(function), zip(*args))
将函数函数与参数arg_0、arg_1和arg_2的列表一起使用，如下所示：
pool = Pool(n_core)
list_model = pool.map(universal_worker, pool_args(function, arg_0, arg_1, arg_2)
pool.close()
pool.join()
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()
