feat(ruff): enable flake8-commas (#22386)

.ruff.toml

@@ -172,6 +172,7 @@ exclude = [
 [lint]
 select = [
   "AIR",  # Airflow
+  "COM",  # flake8-commas
   "E",    # pycodestyle
   "F",    # Pyflakes
   "FAST", # FastAPI

aerospace/hm-aerosandbox/src/main.py

@@ -100,7 +100,7 @@ def main() -> None:
                     )
                     for xi in np.cosspace(0, 1, 30)
                 ],
-            )
+            ),
         ],
     )
     vlm = asb.VortexLatticeMethod(
@@ -186,6 +186,7 @@ def main() -> None:
 
 if __name__ == "__main__":
     logging.basicConfig(
-        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+        level=logging.INFO,
+        format="%(asctime)s - %(levelname)s - %(message)s",
     )
     main()

aerospace/hm-openaerostruct/src/main.py

@@ -80,11 +80,13 @@ def main() -> None:
 
     # Perform the connections with the modified names within the 'aero_states' group
     problem.model.connect(
-        name + ".mesh", point_name + ".aero_states." + name + "_def_mesh"
+        name + ".mesh",
+        point_name + ".aero_states." + name + "_def_mesh",
     )
 
     problem.model.connect(
-        name + ".t_over_c", point_name + "." + name + "_perf." + "t_over_c"
+        name + ".t_over_c",
+        point_name + "." + name + "_perf." + "t_over_c",
     )
 
     # Import the Scipy Optimizer and set the driver of the problem to use it, which defaults to an SLSQP optimization method
@@ -105,6 +107,7 @@ def main() -> None:
 
 if __name__ == "__main__":
     logging.basicConfig(
-        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+        level=logging.INFO,
+        format="%(asctime)s - %(levelname)s - %(message)s",
     )
     main()

api-rust/scripts/download_model.py

@@ -40,7 +40,8 @@ def download_resnet18():
 
 if __name__ == "__main__":
     logging.basicConfig(
-        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+        level=logging.INFO,
+        format="%(asctime)s - %(levelname)s - %(message)s",
     )
     download_resnet18()
     download_labels()

authorization/hm-opal-client/opal_fetcher_postgres/provider.py

@@ -24,12 +24,14 @@ class PostgresConnectionParams(BaseModel):
 class PostgresFetcherConfig(FetcherConfig):
     fetcher: str = "PostgresFetchProvider"
     connection_params: PostgresConnectionParams | None = Field(
-        None, description="can be overridden or complement parts of the DSN"
+        None,
+        description="can be overridden or complement parts of the DSN",
     )
     query: str = Field(..., description="the query")
     fetch_one: bool = Field(False, description="fetch only one row")
     dict_key: str | None = Field(
-        None, description="array of dict will map to dict with provided dict_key"
+        None,
+        description="array of dict will map to dict with provided dict_key",
     )
 
 
@@ -68,11 +70,15 @@ async def __aenter__(self):
         )
 
         self._connection: asyncpg.Connection = await asyncpg.connect(
-            dsn, **connection_params
+            dsn,
+            **connection_params,
         )
 
         await self._connection.set_type_codec(
-            "jsonb", encoder=json.dumps, decoder=json.loads, schema="pg_catalog"
+            "jsonb",
+            encoder=json.dumps,
+            decoder=json.loads,
+            schema="pg_catalog",
         )
 
         self._transaction: Transaction = self._connection.transaction(readonly=True)

cloud-computing/hm-ray/applications/calculate/src/main.py

@@ -19,7 +19,8 @@ def sum_list(numbers: list[int]) -> int:
 
 if __name__ == "__main__":
     logging.basicConfig(
-        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+        level=logging.INFO,
+        format="%(asctime)s - %(levelname)s - %(message)s",
     )
     ray.init()
     logger.info(ray.cluster_resources())

cloud-computing/hm-ray/applications/process-flight-data/src/main.py

@@ -20,7 +20,7 @@ def process_flight_data(
     experiment_number: int,
 ) -> pd.DataFrame:
     mlflow.set_tracking_uri(
-        f"https://{mlflow_tracking_server_user_name}:{mlflow_tracking_server_password}@{mlflow_tracking_server_host}"
+        f"https://{mlflow_tracking_server_user_name}:{mlflow_tracking_server_password}@{mlflow_tracking_server_host}",
     )
     mlflow.set_experiment(mlflow_experiment_name)
 
@@ -39,7 +39,8 @@ def process_flight_data(
 
 if __name__ == "__main__":
     logging.basicConfig(
-        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+        level=logging.INFO,
+        format="%(asctime)s - %(levelname)s - %(message)s",
     )
 
     ray.init()

cloud-infrastructure/terraform/environments/production/aws/general/files/aws-glue/spark-scripts/src/hm_write_parquet_to_delta_table_adsb_2x_flight_trace_data.py

@@ -10,12 +10,13 @@
 from pyspark.sql.functions import col, concat, date_format, from_unixtime, lit, when
 
 logging.basicConfig(
-    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
 )
 logger = logging.getLogger(__name__)
 
 raw_parquet_paths = [
-    "s3://hm-production-bucket/data/raw-parquet/adsb_2x_flight_trace_data/"
+    "s3://hm-production-bucket/data/raw-parquet/adsb_2x_flight_trace_data/",
 ]
 delta_table_path = (
     "s3://hm-production-bucket/data/delta-tables/adsb_2x_flight_trace_data/"
@@ -46,18 +47,23 @@ def add_time_column(
 
 
 def add_date_column(
-    df: DataFrame, time_column_name: str, date_column_name: str
+    df: DataFrame,
+    time_column_name: str,
+    date_column_name: str,
 ) -> DataFrame:
     return df.withColumn(
         date_column_name,
         date_format(
-            from_unixtime(col(time_column_name) / lit(1000000000.0)), "yyyy-MM-dd"
+            from_unixtime(col(time_column_name) / lit(1000000000.0)),
+            "yyyy-MM-dd",
         ),
     )
 
 
 def add_dbflags_columns(
-    df: DataFrame, flag_column_name: str, columns_and_masks: list[tuple[str, int]]
+    df: DataFrame,
+    flag_column_name: str,
+    columns_and_masks: list[tuple[str, int]],
 ) -> DataFrame:
     for column_name, mask in columns_and_masks:
         df = df.withColumn(
@@ -68,7 +74,9 @@ def add_dbflags_columns(
 
 
 def add_trace_flags_columns(
-    df: DataFrame, flag_column_name: str, columns_and_masks: list[tuple[str, int]]
+    df: DataFrame,
+    flag_column_name: str,
+    columns_and_masks: list[tuple[str, int]],
 ) -> DataFrame:
     for column_name, mask in columns_and_masks:
         if column_name in [
@@ -78,14 +86,15 @@ def add_trace_flags_columns(
             df = df.withColumn(
                 column_name,
                 when(
-                    (col(flag_column_name).bitwiseAND(mask)) > 0, "geometric"
+                    (col(flag_column_name).bitwiseAND(mask)) > 0,
+                    "geometric",
                 ).otherwise("barometric"),
             )
         else:
             df = df.withColumn(
                 column_name,
                 when((col(flag_column_name).bitwiseAND(mask)) > 0, True).otherwise(
-                    False
+                    False,
                 ),
             )
     return df
@@ -101,7 +110,8 @@ def add_trace_on_ground_column(
         df = df.withColumn(
             trace_on_ground_column_name,
             when(
-                col(trace_altitude_ft_column_name) == lit(ground_value), True
+                col(trace_altitude_ft_column_name) == lit(ground_value),
+                True,
             ).otherwise(False),
         )
     return df
@@ -235,7 +245,10 @@ def add_coordinate_column(
 # Add "_coordinate"
 coordinate_column_name = "_coordinate"
 df = add_coordinate_column(
-    df, "trace_longitude_deg", "trace_latitude_deg", coordinate_column_name
+    df,
+    "trace_longitude_deg",
+    "trace_latitude_deg",
+    coordinate_column_name,
 )
 
 # Add "_time"
@@ -251,7 +264,7 @@ def add_coordinate_column(
     "mergeSchema": "true",
 }
 df.write.format("delta").options(**additional_options).partitionBy(*partitions).mode(
-    "append"
+    "append",
 ).save()
 
 job.commit()

cloud-infrastructure/terraform/environments/production/aws/general/files/aws-glue/spark-scripts/src/hm_write_parquet_to_delta_table_motor_data.py

@@ -8,7 +8,8 @@
 from pyspark.context import SparkContext
 
 logging.basicConfig(
-    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
 )
 logger = logging.getLogger(__name__)
 
@@ -46,7 +47,7 @@
     "mergeSchema": "true",
 }
 df.write.format("delta").options(**additional_options).partitionBy(*partitions).mode(
-    "overwrite"
+    "overwrite",
 ).save()
 
 job.commit()

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/notebook.ipynb

@@ -38,7 +38,7 @@
     "        [\n",
     "            torchvision.transforms.transforms.ToTensor(),\n",
     "            torchvision.transforms.transforms.Normalize((0.1307,), (0.3081,)),\n",
-    "        ]\n",
+    "        ],\n",
     "    ),\n",
     ")"
    ]
@@ -51,7 +51,9 @@
    "source": [
     "# Upload the data to S3\n",
     "data_s3_uri = sagemaker_session.upload_data(\n",
-    "    path=\"data/\", bucket=s3_bucket, key_prefix=f\"{experiment_name}-data\"\n",
+    "    path=\"data/\",\n",
+    "    bucket=s3_bucket,\n",
+    "    key_prefix=f\"{experiment_name}-data\",\n",
     ")\n",
     "print(data_s3_uri)"
    ]

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/src/utils/get_test_data_loader.py

@@ -15,7 +15,7 @@ def get_test_data_loader(test_batch_size, training_dir, **kwargs):
             training_dir,
             train=False,
             transform=transforms.Compose(
-                [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]
+                [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))],
             ),
         ),
         batch_size=test_batch_size,

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/src/utils/get_train_data_loader.py

@@ -14,7 +14,7 @@ def get_train_data_loader(batch_size, training_dir, is_distributed, **kwargs):
         training_dir,
         train=True,
         transform=transforms.Compose(
-            [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]
+            [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))],
         ),
     )
     train_sampler = (

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/src/utils/test.py

@@ -24,5 +24,5 @@ def test(model, test_loader, device):
 
     test_loss /= len(test_loader.dataset)
     logger.info(
-        f"Test set: Average loss: {test_loss:.4f}, Accuracy: {correct}/{len(test_loader.dataset)} ({100.0 * correct / len(test_loader.dataset):.0f}%)\n"
+        f"Test set: Average loss: {test_loss:.4f}, Accuracy: {correct}/{len(test_loader.dataset)} ({100.0 * correct / len(test_loader.dataset):.0f}%)\n",
     )

cloud-platform/aws/amazon-sagemaker/pytorch-mnist/src/utils/train.py

@@ -33,11 +33,13 @@ def train(args):
         host_rank = args.hosts.index(args.current_host)
         os.environ["RANK"] = str(host_rank)
         dist.init_process_group(
-            backend=args.backend, rank=host_rank, world_size=world_size
+            backend=args.backend,
+            rank=host_rank,
+            world_size=world_size,
         )
         logger.info(
             f"Initialized the distributed environment: '{args.backend}' backend on {dist.get_world_size()} nodes. "
-            + f"Current host rank is {dist.get_rank()}. Number of gpus: {args.num_gpus}"
+            + f"Current host rank is {dist.get_rank()}. Number of gpus: {args.num_gpus}",
         )
 
     # set the seed for generating random numbers
@@ -46,16 +48,19 @@ def train(args):
         torch.cuda.manual_seed(args.seed)
 
     train_loader = get_train_data_loader(
-        args.batch_size, args.data_dir, is_distributed, **kwargs
+        args.batch_size,
+        args.data_dir,
+        is_distributed,
+        **kwargs,
     )
     test_loader = get_test_data_loader(args.test_batch_size, args.data_dir, **kwargs)
 
     logger.info(
-        f"Processes {len(train_loader.sampler)}/{len(train_loader.dataset)} ({100.0 * len(train_loader.sampler) / len(train_loader.dataset):.0f}%) of train data"
+        f"Processes {len(train_loader.sampler)}/{len(train_loader.dataset)} ({100.0 * len(train_loader.sampler) / len(train_loader.dataset):.0f}%) of train data",
     )
 
     logger.info(
-        f"Processes {len(test_loader.sampler)}/{len(test_loader.dataset)} ({100.0 * len(test_loader.sampler) / len(test_loader.dataset):.0f}%) of test data"
+        f"Processes {len(test_loader.sampler)}/{len(test_loader.dataset)} ({100.0 * len(test_loader.sampler) / len(test_loader.dataset):.0f}%) of test data",
     )
 
     model = Net().to(device)
@@ -82,7 +87,7 @@ def train(args):
             optimizer.step()
             if batch_idx % args.log_interval == 0:
                 logger.info(
-                    f"Train Epoch: {epoch} [{batch_idx * len(device_data)}/{len(train_loader.sampler)} ({100.0 * batch_idx / len(train_loader):.0f}%)] Loss: {loss.item():.6f}"
+                    f"Train Epoch: {epoch} [{batch_idx * len(device_data)}/{len(train_loader.sampler)} ({100.0 * batch_idx / len(train_loader):.0f}%)] Loss: {loss.item():.6f}",
                 )
         test(model, test_loader, device)
     save_model(model, args.model_dir)