Created
September 19, 2023 13:12
-
-
Save harabchuk/fe32f0096cef0d7c16f4cad9fd5d5f85 to your computer and use it in GitHub Desktop.
Compare search in array vs set
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import random | |
| import string | |
| import timeit | |
| def generate_random_string(length): | |
| return ''.join(random.choice(string.ascii_letters) for _ in range(length)) | |
| random_strings = [ | |
| generate_random_string(random.randint(7, 12)) for _ in range(500) | |
| ] | |
| def find_in_array(): | |
| count = 0 # do some job so that optimiser does not skip searching in array | |
| for _ in range(10000): | |
| string_to_find = random.choice(random_strings) # existing string | |
| count += 1 if string_to_find in random_strings else 2 | |
| return count | |
| def find_in_set(): | |
| count = 0 # do some job so that optimiser does not skip searching in set | |
| random_strings_set = set( | |
| random_strings | |
| ) # include the set generation into total time | |
| for _ in range(10000): | |
| string_to_find = random.choice(random_strings) # existig string | |
| count += 1 if string_to_find in random_strings_set else 2 | |
| return count | |
| time_taken_array = timeit.timeit(find_in_array, number=1) | |
| print(f"find string in array (10,000 runs): {time_taken_array:.10f} seconds") | |
| time_taken_set = timeit.timeit(find_in_set, number=1) | |
| print(f"find string in set (10,000 runs): {time_taken_set:.10f} seconds") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment