Created
September 6, 2018 23:26
-
-
Save tremby/3652b4fae84554b4c0f7a8c2ccf0d82f to your computer and use it in GitHub Desktop.
Calculate the expected number of duplicates when choosing n items from a pool of m, p times
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 | |
from collections import Counter | |
from itertools import chain | |
POOL_SIZE = 100 | |
PAGE_SIZE = 9 | |
NUM_PAGES = 2 | |
ITERATIONS = 10000 | |
pool = set(range(POOL_SIZE)) | |
dupe_counts = [] | |
for i in xrange(ITERATIONS): | |
pages = [random.sample(pool, PAGE_SIZE) for p in xrange(NUM_PAGES)] | |
duplicates = [item for (item, count) in Counter(chain(*pages)).iteritems() if count > 1] | |
dupe_counts.append(len(duplicates)) | |
print(""" | |
Over {iterations} iterations | |
getting {num_pages} pages, each of size {page_size}, | |
from a pool of {pool_size} entries, | |
there were an average of {average} duplicates. | |
""".format( | |
iterations=ITERATIONS, | |
num_pages=NUM_PAGES, | |
page_size=PAGE_SIZE, | |
pool_size=POOL_SIZE, | |
average=sum(dupe_counts) / float(len(dupe_counts)) | |
)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment