[GitHub Action] Lint and format code with Ruff

Author: actions-user

examples/spaceship-titanic/baseline.py

@@ -6,9 +6,7 @@ def predict(test: Path, save: Path):
     # TODO: Add a model here
 
     test_data = pd.read_csv(test)
-    submission = pd.DataFrame(
-        {"PassengerId": test_data["PassengerId"], "Transported": False}
-    )
+    submission = pd.DataFrame({"PassengerId": test_data["PassengerId"], "Transported": False})
     submission.to_csv(save, index=False)
     print(f"Test submission saved to {save}")
 

examples/spaceship-titanic/evaluate.py

@@ -12,24 +12,14 @@ class InvalidSubmissionError(Exception):
     pass
 
 
-def prepare_for_accuracy_metric(
-    submission: pd.DataFrame,
-    answers: pd.DataFrame,
-    target_column: str,
-    id_column: str,
-) -> dict:
-
+def prepare_for_accuracy_metric(submission: pd.DataFrame, answers: pd.DataFrame, target_column: str, id_column: str) -> dict:
     # Answers checks
-    assert (
-        target_column in answers.columns
-    ), f"Answers must have a `{target_column}` column"
+    assert target_column in answers.columns, f"Answers must have a `{target_column}` column"
     assert id_column in answers.columns, f"Answers must have a `{id_column}` column"
 
     # Submission checks
     if len(submission) != len(answers):
-        raise InvalidSubmissionError(
-            "Submission must have the same length as the answers."
-        )
+        raise InvalidSubmissionError("Submission must have the same length as the answers.")
     if target_column not in submission.columns:
         raise InvalidSubmissionError(f"Submission must have a `{target_column}` column")
     if id_column not in submission.columns:
@@ -40,9 +30,7 @@ def prepare_for_accuracy_metric(
     answers = answers.sort_values(id_column)
 
     if (submission[id_column].values != answers[id_column].values).any():
-        raise InvalidSubmissionError(
-            f"Submission and Answers `{id_column}`'s do not match"
-        )
+        raise InvalidSubmissionError(f"Submission and Answers `{id_column}`'s do not match")
 
     y_pred = submission[target_column].to_numpy()
     y_true = answers[target_column].to_numpy()
@@ -52,10 +40,7 @@ def prepare_for_accuracy_metric(
 
 def grade(submission: pd.DataFrame, answers: pd.DataFrame) -> float:
     accuracy_inputs = prepare_for_accuracy_metric(
-        submission=submission,
-        answers=answers,
-        target_column="Transported",
-        id_column="PassengerId",
+        submission=submission, answers=answers, target_column="Transported", id_column="PassengerId"
     )
     return accuracy_score(**accuracy_inputs)
 
@@ -70,9 +55,7 @@ def grade(submission: pd.DataFrame, answers: pd.DataFrame) -> float:
 
     # Check if files exist before proceeding
     if not answers_path.exists():
-        print(
-            f"Error: Answers file not found at {answers_path}"
-        )  # Updated path in error message
+        print(f"Error: Answers file not found at {answers_path}")  # Updated path in error message
         sys.exit(1)
 
     if not submission_path.exists():

examples/spaceship-titanic/optimize.py

@@ -6,9 +6,7 @@ def predict(test: Path, save: Path):
     # TODO: Add a model here
 
     test_data = pd.read_csv(test)
-    submission = pd.DataFrame(
-        {"PassengerId": test_data["PassengerId"], "Transported": False}
-    )
+    submission = pd.DataFrame({"PassengerId": test_data["PassengerId"], "Transported": False})
     submission.to_csv(save, index=False)
     print(f"Test submission saved to {save}")
 

examples/spaceship-titanic/utils.py

@@ -32,9 +32,7 @@ def split_data(public: Path, private: Path):
     new_test.to_csv(private / "test.csv", index=False)
     print("test sample shape:", new_test.shape)
     print(f"Validation data saved to {public / 'test.csv'}")
-    new_test.drop("Transported", axis="columns").to_csv(
-        public / "test.csv", index=False
-    )
+    new_test.drop("Transported", axis="columns").to_csv(public / "test.csv", index=False)
 
     # remove the previous files
     os.remove("train.csv")