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

added linting checks

Browse source
This commit is contained in:
joesharratt1229 2025-01-31 07:19:55 +00:00
parent d7ebe409d8
commit ca3a841bf6
2 changed files with 13 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

18
tests/test_countdown.py
View file

@ -64,14 +64,16 @@ def test_countdown_game_items():
# Verify expression evaluates correctly
expr = item["metadata"]["expression"]
#check score
assert dataset.score_answer(answer=expr, metadata=item["metadata"]) == 1.0 #correct answer
assert dataset.score_answer(answer="45+2", metadata=item["metadata"]) == 0.05 #wrong answer but an attempt
assert dataset.score_answer(answer="a wrong solution", metadata=item["metadata"]) == 0.01 #wrong answer but incorrectly formatted
assert dataset.score_answer(answer="", metadata=item["metadata"]) == 0.01 #wrong answer but empty string
assert dataset.score_answer(answer=None, metadata=item["metadata"]) == 0.0 #no answer
# check score
assert dataset.score_answer(answer=expr, metadata=item["metadata"]) == 1.0 # correct answer
assert dataset.score_answer(answer="45+2", metadata=item["metadata"]) == 0.05 # wrong answer but an attempt
assert (
dataset.score_answer(answer="a wrong solution", metadata=item["metadata"]) == 0.01
) # wrong answer but incorrectly formatted
assert dataset.score_answer(answer="", metadata=item["metadata"]) == 0.01 # wrong answer but empty string
assert dataset.score_answer(answer=None, metadata=item["metadata"]) == 0.0 # no answer
try:
result = eval(expr) # Safe here since we control expression generation
assert result == item["metadata"]["target"]