added linting checks

open-thought · Jan 31, 2025 · 37375f0 · 37375f0
1 parent 4fea3c3
commit 37375f0
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 11 deletions.
diff --git a/reasoning_gym/games/countdown.py b/reasoning_gym/games/countdown.py
@@ -1,6 +1,6 @@
 from dataclasses import dataclass
 from random import Random
-from typing import List, Optional, Tuple, Dict, Any
+from typing import Any, Dict, List, Optional, Tuple
 
 import sympy
 from sympy import Symbol, symbols
@@ -158,7 +158,7 @@ def _generate_expression(self, rng: Random) -> Tuple[str, List[int], int]:
                 continue
 
         raise ValueError(f"Failed to generate valid expression after {max_attempts} attempts")
-    
+
     def score_answer(self, answer: Optional[str], metadata: Dict[str, Any]) -> float:
         """Determine if the solution provided solves the problem"""
         reward = 0.0
@@ -168,7 +168,7 @@ def score_answer(self, answer: Optional[str], metadata: Dict[str, Any]) -> float
                 solved = user_answer == metadata["target"]
                 if solved:
                     reward = 1.0
-                elif (len(answer.strip()) > 0): # encourage partial solutions
+                elif len(answer.strip()) > 0:  # encourage partial solutions
                     reward = 0.05
                 else:
                     reward = 0.01

diff --git a/tests/test_countdown.py b/tests/test_countdown.py
@@ -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"]