Python: Efficient workaround for multiprocessing a function that is a data member of a class, from within that class

Question

I\'m aware of various discussions of limitations of the multiprocessing module when dealing with functions that are data members of a class (due to Pickling problems).

Answer 1

Steven Bethard has posted a way to allow methods to be pickled/unpickled. You could use it like this:

import multiprocessing as mp
import copy_reg
import types

def _pickle_method(method):
    # Author: Steven Bethard
    # http://bytes.com/topic/python/answers/552476-why-cant-you-pickle-instancemethods
    func_name = method.im_func.__name__
    obj = method.im_self
    cls = method.im_class
    cls_name = ''
    if func_name.startswith('__') and not func_name.endswith('__'):
        cls_name = cls.__name__.lstrip('_')
    if cls_name:
        func_name = '_' + cls_name + func_name
    return _unpickle_method, (func_name, obj, cls)

def _unpickle_method(func_name, obj, cls):
    # Author: Steven Bethard
    # http://bytes.com/topic/python/answers/552476-why-cant-you-pickle-instancemethods
    for cls in cls.mro():
        try:
            func = cls.__dict__[func_name]
        except KeyError:
            pass
        else:
            break
    return func.__get__(obj, cls)

# This call to copy_reg.pickle allows you to pass methods as the first arg to
# mp.Pool methods. If you comment out this line, `pool.map(self.foo, ...)` results in
# PicklingError: Can't pickle : attribute lookup
# __builtin__.instancemethod failed

copy_reg.pickle(types.MethodType, _pickle_method, _unpickle_method)

class MyClass(object):

    def __init__(self):
        self.my_args = [1,2,3,4]
        self.output  = {}

    def my_single_function(self, arg):
        return arg**2

    def my_parallelized_function(self):
        # Use map or map_async to map my_single_function onto the
        # list of self.my_args, and append the return values into
        # self.output, using each arg in my_args as the key.

        # The result should make self.output become
        # {1:1, 2:4, 3:9, 4:16}
        self.output = dict(zip(self.my_args,
                               pool.map(self.my_single_function, self.my_args)))

Then

pool = mp.Pool()   
foo = MyClass()
foo.my_parallelized_function()

yields

print foo.output
# {1: 1, 2: 4, 3: 9, 4: 16}