mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
5d7fbac0ad
* math prompt improvements * ignore brackets in complex_arithmetic results * improve additional instruction in prompt of polynomial_equations * more strict tests for score_answer in polynomial_equations * simplify special reward handling * fix test_intermediate_integration * fix sokoban dataset * add common dataset score_answer consistency test
55 lines
1.9 KiB
Python
55 lines
1.9 KiB
Python
import pytest
|
|
|
|
from reasoning_gym.logic.self_reference import SelfReferenceConfig, SelfReferenceDataset
|
|
|
|
|
|
def test_self_reference():
|
|
"""Test basic properties and solution of generated items"""
|
|
|
|
# Easy
|
|
config = SelfReferenceConfig(seed=42, size=20, difficulty=1)
|
|
dataset = SelfReferenceDataset(config)
|
|
|
|
for item in dataset:
|
|
assert isinstance(item, dict)
|
|
assert "question" in item
|
|
assert "answer" in item
|
|
assert "metadata" in item
|
|
|
|
# Test the scoring
|
|
assert dataset.score_answer(answer=item["answer"], entry=item) == 1.0
|
|
assert dataset.score_answer(answer=99, entry=item) == 0.0
|
|
assert dataset.score_answer(answer="99", entry=item) == 0.0
|
|
assert dataset.score_answer(answer=None, entry=item) == 0.0
|
|
|
|
# # Medium
|
|
config = SelfReferenceConfig(seed=42, size=1, difficulty=5)
|
|
dataset = SelfReferenceDataset(config)
|
|
|
|
for item in dataset:
|
|
assert isinstance(item, dict)
|
|
assert "question" in item
|
|
assert "answer" in item
|
|
assert "metadata" in item
|
|
|
|
# Test the scoring
|
|
assert dataset.score_answer(answer=item["answer"], entry=item) == 1.0
|
|
assert dataset.score_answer(answer=99, entry=item) == 0.0
|
|
assert dataset.score_answer(answer="99", entry=item) == 0.0
|
|
assert dataset.score_answer(answer=None, entry=item) == 0.0
|
|
|
|
# # Hard
|
|
config = SelfReferenceConfig(seed=42, size=1, difficulty=10)
|
|
dataset = SelfReferenceDataset(config)
|
|
|
|
for item in dataset:
|
|
assert isinstance(item, dict)
|
|
assert "question" in item
|
|
assert "answer" in item
|
|
assert "metadata" in item
|
|
|
|
# Test the scoring
|
|
assert dataset.score_answer(answer=item["answer"], entry=item) == 1.0
|
|
assert dataset.score_answer(answer=99, entry=item) == 0.0
|
|
assert dataset.score_answer(answer="99", entry=item) == 0.0
|
|
assert dataset.score_answer(answer=None, entry=item) == 0.0
|