Searching lists vs. sets

search_example.py

import random
import string
from time import time


def random_string(length=20):
    chars = string.ascii_letters
    return ''.join(random.choice(chars) for i in range(length))


# Prepare haystack and needles
haystack = [random_string() for i in range(99000)]
needles = [random_string() for i in range(1000)]
haystack.extend(needles)
random.shuffle(haystack)

#Time haystack look-ups as a list
list_start = time()
for n in needles:
    if n in haystack:
        pass
list_duration = time() - list_start
print(f"Found needles in list in {format(list_duration, 'f')} seconds.")
# Found needles in list in 4.129141 seconds.

# Create set and add the same haystack with needles
set_haystack = set()
set_haystack.update(haystack)

# Time set look-ups for needles
set_start = time()
for n in needles:
    if n in set_haystack:
        pass
set_duration = time() - set_start
print(f"Found needles in set in {format(set_duration, 'f')} seconds.")
# Found needles in set in 0.000150 seconds.