open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-26 17:13:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove strip from ProceduralDataset::core score_answer() (#250)

Browse source 
* remove strip from ProceduralDataset::core score_answer(), strip in extract answer (optional, default=True)
* test: Move test_extract_answer() from test_dataset.py to test_utils.py
* refactor: Improve decimal reward computation with more flexible comparison
* fix: Implement rounding for format_number when round_if_needed is True
* test: Add test case for compute_decimal_reward with sign and zeros
This commit is contained in:
Andreas Köpf 2025-03-02 08:46:36 +01:00 • committed by GitHub
parent 16a4ea1193
commit ece6990709
6 changed files with 80 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/test_dataset.py
View file

@ -2,7 +2,6 @@ import pytest
from reasoning_gym.arithmetic.basic_arithmetic import BasicArithmeticDataset, BasicArithmeticDatasetConfig
from reasoning_gym.dataset import ReseedingDataset
from reasoning_gym.utils import extract_answer
def test_reseeding_dataset_iteration():
@ -41,12 +40,7 @@ def test_reseeding_dataset_iteration():
assert infinite_dataset.score_answer(test_item["answer"], test_item) == 1.0
def test_extract_answer():
assert extract_answer("This is a text. <final_answer>1234</final_answer>", tag_name="final_answer") == "1234"
# ignore single whitespae
assert extract_answer("This is a text. <answer>\n1234 </answer>", tag_name="answer") == "1234"
def test_basic_arithmetic_score_answer():
config = BasicArithmeticDatasetConfig(
min_terms=2, max_terms=3, min_digits=1, max_digits=2, operators=["+"], allow_parentheses=False, seed=42, size=10
)