def speeds():
"""
Test the naive rule finder vs. the simple one from the paper.
"""
import random
random.seed(123456)
transactions = generate_transactions(num_transactions=random.randint(
250, 500),
unique_items=random.randint(8, 9),
items_row=(10, 50))
itemsets, num_transactions = itemsets_from_transactions(transactions, 0.1)
import time
min_conf = 0.5
print(itemsets)
st = time.perf_counter()
rules_apri = generate_rules_apriori(itemsets, min_conf, num_transactions)
rules_apri = list(rules_apri)
time_formatted = round(time.perf_counter() - st, 40)
print('Fast apriori ran in {} s'.format(time_formatted))
st = time.perf_counter()
rules_simple = generate_rules_simple(itemsets, min_conf, num_transactions)
rules_simple = list(rules_simple)
time_formatted = round(time.perf_counter() - st, 40)
print('Simple apriori ran in {} s'.format(time_formatted))
st = time.perf_counter()
rules_naive = generate_rules_naively(itemsets, min_conf, num_transactions)
rules_naive = list(rules_naive)
time_formatted = round(time.perf_counter() - st, 40)
print('Naive apriori ran in {} s'.format(time_formatted))
def test_generate_rules_apriori_large():
"""
Test with lots of data.
This test will fail if the second argument to `_ap_genrules` is not
validated as non-empty before the recursive function call. We must have
if H_m_copy:
yield from _ap_genrules
for this test to pass.
"""
transactions = generate_transactions(num_transactions=100,
unique_items=30,
items_row=(1, 20),
seed=123)
itemsets, num_transactions = itemsets_from_transactions(transactions, 0.1)
min_conf = 0.3
rules_apri = generate_rules_apriori(itemsets, min_conf, num_transactions)
rules_naive = generate_rules_naively(itemsets, min_conf, num_transactions)
rules_apri = list(rules_apri)
rules_naive = list(rules_naive)
# Test equal length, since no duplicates should be returned by apriori
assert len(rules_apri) == len(rules_naive)
# Test equal results
assert set(rules_apri) == set(rules_naive)
rules_apri = generate_rules_apriori(itemsets, min_conf, num_transactions)
rules_naive = generate_rules_naively(itemsets, min_conf, num_transactions)
rules_apri = list(rules_apri)
rules_naive = list(rules_naive)
# Test equal length, since no duplicates should be returned by apriori
assert len(rules_apri) == len(rules_naive)
# Test equal results
assert set(rules_apri) == set(rules_naive)
input_data = [
list(
generate_transactions(num_transactions=random.randint(15, 25),
unique_items=random.randint(1, 8),
items_row=(1, random.randint(2, 6))))
for i in range(10)
]
@pytest.mark.parametrize("transactions", input_data)
def test_generate_rules_simple_vs_naive(transactions):
"""
Test the naive rule finder vs. the simple one from the paper.
"""
itemsets, num_transactions = itemsets_from_transactions(transactions, 0.25)
min_conf = 0.1
rules_naive = generate_rules_naively(itemsets, min_conf, num_transactions)