flake8/linter fixes

Author: brifordwylie

scripts/sagemaker_feature_group_issue.py

@@ -8,43 +8,42 @@
 # Toggle this flag to test spawn mode fix
 USE_SPAWN_MODE = True  # Set to True to fix the Tahoe hang issue
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     if USE_SPAWN_MODE:
         print("Using SPAWN mode (fix for Tahoe)")
-        multiprocessing.set_start_method('spawn', force=True)
-        multiprocess.set_start_method('spawn', force=True)
+        multiprocessing.set_start_method("spawn", force=True)
+        multiprocess.set_start_method("spawn", force=True)
     else:
         print("Using default fork mode (will hang on Tahoe)")
 
     # Create fake data
-    data = pd.DataFrame({
-        'record_id': [f'id_{i}' for i in range(10)],
-        'feature_1': [float(i) for i in range(10)],
-        'feature_2': [float(i * 2) for i in range(10)],
-        'event_time': [time.time()] * 10
-    })
+    data = pd.DataFrame(
+        {
+            "record_id": [f"id_{i}" for i in range(10)],
+            "feature_1": [float(i) for i in range(10)],
+            "feature_2": [float(i * 2) for i in range(10)],
+            "event_time": [time.time()] * 10,
+        }
+    )
 
     # Setup SageMaker session
     sagemaker_session = sagemaker.Session()
 
     # Define feature group
-    feature_group_name = 'temp_delete_me'
-    feature_group = FeatureGroup(
-        name=feature_group_name,
-        sagemaker_session=sagemaker_session
-    )
+    feature_group_name = "temp_delete_me"
+    feature_group = FeatureGroup(name=feature_group_name, sagemaker_session=sagemaker_session)
 
     # Create feature definitions
     feature_group.load_feature_definitions(data_frame=data)
 
     # Create feature group
     print("Creating feature group...")
     feature_group.create(
-        s3_uri=f's3://{sagemaker_session.default_bucket()}/featurestore',
-        record_identifier_name='record_id',
-        event_time_feature_name='event_time',
+        s3_uri=f"s3://{sagemaker_session.default_bucket()}/featurestore",
+        record_identifier_name="record_id",
+        event_time_feature_name="event_time",
         role_arn=sagemaker.get_execution_role(),
-        enable_online_store=True
+        enable_online_store=True,
     )
 
     # Wait for feature group to be created (can take 1-2 minutes)
@@ -58,10 +57,5 @@
 
     # This will hang on macOS Tahoe with USE_SPAWN_MODE=False
     print("Starting ingest...")
-    feature_group.ingest(
-        data_frame=data,
-        max_workers=2,
-        max_processes=2,
-        wait=True
-    )
-    print("Ingest completed!")
+    feature_group.ingest(data_frame=data, max_workers=2, max_processes=2, wait=True)
+    print("Ingest completed!")

scripts/test_feature_set_creation.py

@@ -6,9 +6,9 @@
 import multiprocessing
 import multiprocess
 
-if __name__ == '__main__':
-    multiprocessing.set_start_method('spawn', force=True)
-    multiprocess.set_start_method('spawn', force=True)
+if __name__ == "__main__":
+    multiprocessing.set_start_method("spawn", force=True)
+    multiprocess.set_start_method("spawn", force=True)
 
     s3_path = "s3://workbench-public-data/comp_chem/aqsol_public_data.csv"
     aqsol_data = wr.s3.read_csv(s3_path)
@@ -17,4 +17,4 @@
     to_features = PandasToFeatures("temp_delete_me")
     to_features.set_input(aqsol_data, id_column="id")
     to_features.set_output_tags(["aqsol", "public"])
-    to_features.transform()
+    to_features.transform()

src/workbench/core/transforms/pandas_transforms/pandas_to_features.py

@@ -335,16 +335,19 @@ def mac_spawn_hack(self):
         This forces spawn mode on macOS to avoid the hang.
         """
         import platform
+
         if platform.system() == "Darwin":  # macOS
             self.log.warning("macOS detected, forcing 'spawn' mode for multiprocessing (Tahoe hang workaround)")
             import multiprocessing
+
             try:
                 import multiprocess
-                multiprocess.set_start_method('spawn', force=True)
+
+                multiprocess.set_start_method("spawn", force=True)
             except (RuntimeError, ImportError):
                 pass  # Already set or multiprocess not available
             try:
-                multiprocessing.set_start_method('spawn', force=True)
+                multiprocessing.set_start_method("spawn", force=True)
             except RuntimeError:
                 pass  # Already set