open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-27 17:23:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

updated algorithmics dataset (#269)

Browse source 
* updated algorithmic datasets
* added changes to symbolic and power
* updated power function test
This commit is contained in:
joesharratt1229 2025-03-05 23:32:53 +01:00 • committed by GitHub
parent f426db90ec
commit d9638df79c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 57 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

11
tests/test_gsm_symbolic.py
View file

@ -90,3 +90,14 @@ def test_gsm_symbolic_generators():
print(f"ok: q={len(question_set)}, a={len(answer_set)}")
i += 1
def test_gsm_symbolic_score_answer():
"""Test score answer function"""
config = GSMSymbolicDatasetConfig(size=100, seed=42)
dataset = GSMSymbolicDataset(config)
for i in range(len(dataset)):
item = dataset[i]
score = dataset.score_answer(item["answer"], item)
assert score == 1.0

20
tests/test_power_function.py
View file

@ -59,20 +59,6 @@ def test_power_function_score_function():
config = PowerFunctionConfig(seed=42)
dataset = PowerFunctionDataset(config)
item = dataset[0]
# Answer is within 1e-6 of solution
answer = str(item["metadata"]["solution"] - 1e-7)
assert dataset.score_answer(answer, item) == 1.0
# Answer is within 1e-1 of solution
answer = str(item["metadata"]["solution"] - 1e-2)
assert dataset.score_answer(answer, item) == 0.5
# Answer is far from solution
answer = str(item["metadata"]["solution"] - 1)
assert dataset.score_answer(answer, item) == 0.0
# Answer is None
answer = None
assert dataset.score_answer(answer, item) == 0.0
for item in dataset:
answer = item["answer"]
assert dataset.score_answer(answer, item) == 1.0