Skip to content

Fix hash probes #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hiway merged 4 commits into from
Jul 4, 2021
Merged

Fix hash probes #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
af46992
Fix tests filter size and false pos test size
cxsmith Apr 14, 2019
a75d926
Use exponents to make uncorrelated hash probe valu
cxsmith Apr 14, 2019
182c39d
Remove lin_comb from probe function name
cxsmith Apr 14, 2019
f97b5b0
Increase modulo space to prevent collisions
cxsmith Apr 14, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/bloom_filter/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,12 +3,12 @@

from .bloom_filter import (
BloomFilter,
get_bitno_lin_comb,
get_filter_bitno_probes,
get_bitno_seed_rnd,
)

__all__ = [
'BloomFilter',
'get_bitno_lin_comb',
'get_filter_bitno_probes',
'get_bitno_seed_rnd',
]
12 changes: 7 additions & 5 deletions src/bloom_filter/bloom_filter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -465,7 +465,7 @@ def hash2(int_list):
return simple_hash(int_list, MERSENNES2[0], MERSENNES2[1], MERSENNES2[2])


def get_bitno_lin_comb(bloom_filter, key):
def get_filter_bitno_probes(bloom_filter, key):
"""Apply num_probes_k hash functions to key. Generate the array index and bitmask corresponding to each result"""

# This one assumes key is either bytes or str (or other list of integers)
Expand All @@ -487,11 +487,13 @@ def get_bitno_lin_comb(bloom_filter, key):

hash_value1 = hash1(int_list)
hash_value2 = hash2(int_list)
probe_value = hash_value1

# We're using linear combinations of hash_value1 and hash_value2 to obtain num_probes_k hash functions
for probeno in range(1, bloom_filter.num_probes_k + 1):
bit_index = hash_value1 + probeno * hash_value2
yield bit_index % bloom_filter.num_bits_m
probe_value *= hash_value1
probe_value += hash_value2
probe_value %= MERSENNES1[2]
yield probe_value % bloom_filter.num_bits_m


def try_unlink(filename):
Expand All @@ -508,7 +510,7 @@ class BloomFilter(object):
def __init__(self,
max_elements=10000,
error_rate=0.1,
probe_bitnoer=get_bitno_lin_comb,
probe_bitnoer=get_filter_bitno_probes,
filename=None,
start_fresh=False):
# pylint: disable=R0913
Expand Down
5 changes: 3 additions & 2 deletions tests/test_bloom_filter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,14 +39,14 @@ def _test(description, values, trials, error_rate, probe_bitnoer=None, filename=
# R0914: We want some local variables too. This is just test code.
"""Some quick automatic tests for the bloom filter class"""
if not probe_bitnoer:
probe_bitnoer = bloom_filter.get_bitno_lin_comb
probe_bitnoer = bloom_filter.get_filter_bitno_probes

all_good = True

divisor = 100000

bloom = bloom_filter.BloomFilter(
max_elements=trials * 2,
max_elements=values.length() * 2,
error_rate=error_rate,
probe_bitnoer=probe_bitnoer,
filename=filename,
Expand Down Expand Up @@ -294,6 +294,7 @@ def test_bloom_filter():
all_good &= _test('states', States(), trials=100000, error_rate=0.01)

all_good &= _test('random', Random_content(), trials=10000, error_rate=0.1)
all_good &= _test('random', Random_content(), trials=1000000, error_rate=1E-9)
all_good &= _test('random', Random_content(), trials=10000, error_rate=0.1,
probe_bitnoer=bloom_filter.get_bitno_seed_rnd)

Expand Down