threading vs multiprocessing

from __future__ import print_function
import threading
import mmap
import multiprocessing as mp

try:
   xrange
except NameError:
   xrange = range

class ThreadOrProcess(object):

    def __init__(self, data, use_threading=True):
        self.data = data
        self.use_threading = use_threading

        if self.use_threading:
            self.lookup = dict()
            self.thread = threading.Thread(target=self.threaded_create_lookup,
                                           name="lookup maker thread")
            self.thread.start()
            #self.check_progress()
            self.thread.join()

        else:
            self.lookup = mp.Manager().dict()
            self.process = mp.Process(target=self.mp_create_lookup,
                                      name="lookup maker process")
            self.process.start()
            #self.check_progress()
            self.process.join()

    def check_progress(self):
        before, after = float("nan"), float("nan")
        while before != after:
            before = len(self.lookup)
            print("%s: %d items" % (time.asctime(), before))
            time.sleep(0.01)
            after = len(self.lookup)

    def threaded_create_lookup(self):
        lino, record_start = 0, 0
        for line in self.data:
            if not line:
                break
            self.lookup[lino] = record_start
            lino += 1
            record_start += len(line)
        return self.lookup

    def mp_create_lookup(self):
        lino, record_start = 0, 0
        for line in self.data:
            if not line:
                break
            self.lookup[lino] = record_start
            lino += 1
            record_start += len(line)
        return self.lookup

if __name__ == "__main__":
    import os
    import csv
    import time
    import string

    # ---- create test data
    if not os.path.exists("testfile.csv"):
        with open("testfile.csv", "wb") as f:
            writer = csv.writer(f)
            record = list(string.ascii_letters)
            for i in xrange(10 ** 5):
                writer.writerow([i] + record)

    # ---- threading
    start = time.time()
    f = open("testfile.csv", "r")
    #threader = ThreadOrProcess(f, True)
    #print(len(dict(threader.lookup)))
    print("threading approach took: %3.3f seconds" % (time.time() - start))

    print("***********************************************")
    # ---- multiprocessing
    start = time.time()
    f.seek(0)
    processer = ThreadOrProcess(f, False)
    print(len(dict(processer.lookup)))
    print("mp approach took: %3.3f seconds" % (time.time() - start))