[Python] Setting global variables for python multiprocessing

I have a large array and an object I'd like to call multiple times with multiprocessing. Neither the data nor the object internals get modified.

This works:

import numpy as np
from multiprocessing import Pool

data = np.arange(400).reshape(20, 20)

class MyClass():
def __call__(self, indx):
return np.sum(data[:, indx])

my_class = MyClass()

def call_single_indx(indx):
result = my_class(indx)
return result

def launch_jobs(nmap=10, num_jobs=3):
with Pool(processes=num_jobs) as pool:
result = pool.map(call_single_indx, range(nmap))
result = np.array(result)
return result

if __name__ == "__main__":

result = launch_jobs()
print(result)


But this fails:

import numpy as np
from multiprocessing import Pool

data = None
my_class = None

def set_globals(n1, n2):
global data
data = np.arange(n1).reshape(n2, n2)
global my_class
my_class = MyClass()

class MyClass():
def __call__(self, indx):
return np.sum(data[:, indx])

def call_single_indx(indx):
result = my_class(indx)
return result

def launch_jobs(nmap=10, num_jobs=3):
with Pool(processes=num_jobs) as pool:
result = pool.map(call_single_indx, range(nmap))
result = np.array(result)
return result

if __name__ == "__main__":
set_globals(n1=400, n2=20)
launch_jobs()


How can I get my set_globals function to actually set the global variables so that all the processes share them?

I'm adding some more text here because the post is mostly code and it won't let me post without more details.

Continue reading...