Convert directory fbcode/torchrec to use the Ruff Formatter (#2566)

Summary:
Pull Request resolved: #2566

Converts the directory specified to use the Ruff formatter in pyfmt

ruff_dog

If this diff causes merge conflicts when rebasing, please run
`hg status -n -0 --change . -I '**/*.{py,pyi}' | xargs -0 arc pyfmt`
on your diff, and amend any changes before rebasing onto latest.
That should help reduce or eliminate any merge conflicts.

allow-large-files

Reviewed By: amyreese

Differential Revision: D66013071

fbshipit-source-id: ee300de212220e068deb208761940a24624a3a5b

Author: Thomas Polasek

benchmarks/ebc_benchmarks.py

@@ -163,7 +163,6 @@ def get_fused_ebc_uvm_time(
     location: EmbeddingLocation,
     epochs: int = 100,
 ) -> Tuple[float, float]:
-
     fused_ebc = FusedEmbeddingBagCollection(
         tables=embedding_bag_configs,
         optimizer_type=torch.optim.SGD,
@@ -195,7 +194,6 @@ def get_ebc_comparison(
     device: torch.device,
     epochs: int = 100,
 ) -> Tuple[float, float, float, float, float]:
-
     # Simple EBC module wrapping a list of nn.EmbeddingBag
     ebc = EmbeddingBagCollection(
         tables=embedding_bag_configs,

benchmarks/ebc_benchmarks_utils.py

@@ -26,7 +26,6 @@ def get_random_dataset(
     embedding_bag_configs: List[EmbeddingBagConfig],
     pooling_factors: Optional[Dict[str, int]] = None,
 ) -> IterableDataset[Batch]:
-
     if pooling_factors is None:
         pooling_factors = {}
 
@@ -57,7 +56,6 @@ def train_one_epoch(
     dataset: IterableDataset[Batch],
     device: torch.device,
 ) -> float:
-
     start_time = time.perf_counter()
 
     for data in dataset:
@@ -82,7 +80,6 @@ def train_one_epoch_fused_optimizer(
     dataset: IterableDataset[Batch],
     device: torch.device,
 ) -> float:
-
     start_time = time.perf_counter()
 
     for data in dataset:
@@ -106,7 +103,6 @@ def train(
     device: torch.device,
     epochs: int = 100,
 ) -> Tuple[float, float]:
-
     training_time = []
     for _ in range(epochs):
         if optimizer:

examples/bert4rec/bert4rec_main.py

@@ -35,7 +35,6 @@
 
 # OSS import
 try:
-
     # pyre-ignore[21]
     # @manual=//torchrec/github/examples/bert4rec:bert4rec_metrics
     from bert4rec_metrics import recalls_and_ndcgs_for_ks

examples/golden_training/train_dlrm_data_parallel.py

@@ -160,7 +160,7 @@ def train(
     )
 
     def dense_filter(
-        named_parameters: Iterator[Tuple[str, nn.Parameter]]
+        named_parameters: Iterator[Tuple[str, nn.Parameter]],
     ) -> Iterator[Tuple[str, nn.Parameter]]:
         for fqn, param in named_parameters:
             if "sparse" not in fqn:

examples/retrieval/two_tower_retrieval.py

@@ -27,7 +27,6 @@
 
 # OSS import
 try:
-
     # pyre-ignore[21]
     # @manual=//torchrec/github/examples/retrieval:knn_index
     from knn_index import get_index

tools/lint/black_linter.py

@@ -179,7 +179,9 @@ def main() -> None:
         level=(
             logging.NOTSET
             if args.verbose
-            else logging.DEBUG if len(args.filenames) < 1000 else logging.INFO
+            else logging.DEBUG
+            if len(args.filenames) < 1000
+            else logging.INFO
         ),
         stream=sys.stderr,
     )

torchrec/datasets/criteo.py

@@ -351,8 +351,9 @@ def get_file_row_ranges_and_remainder(
 
             # If the ranges overlap.
             if rank_left_g <= file_right_g and rank_right_g >= file_left_g:
-                overlap_left_g, overlap_right_g = max(rank_left_g, file_left_g), min(
-                    rank_right_g, file_right_g
+                overlap_left_g, overlap_right_g = (
+                    max(rank_left_g, file_left_g),
+                    min(rank_right_g, file_right_g),
                 )
 
                 # Convert overlap in global numbers to (local) numbers specific to the

torchrec/datasets/random.py

@@ -33,7 +33,6 @@ def __init__(
         *,
         min_ids_per_features: Optional[List[int]] = None,
     ) -> None:
-
         self.keys = keys
         self.keys_length: int = len(keys)
         self.batch_size = batch_size
@@ -76,7 +75,6 @@ def __next__(self) -> Batch:
         return batch
 
     def _generate_batch(self) -> Batch:
-
         values = []
         lengths = []
         for key_idx, _ in enumerate(self.keys):

torchrec/datasets/test_utils/criteo_test_utils.py

@@ -103,7 +103,6 @@ def _create_dataset_npys(
         labels: Optional[np.ndarray] = None,
     ) -> Generator[Tuple[str, ...], None, None]:
         with tempfile.TemporaryDirectory() as tmpdir:
-
             if filenames is None:
                 filenames = [filename]
 

torchrec/distributed/batched_embedding_kernel.py

@@ -785,9 +785,7 @@ def purge(self) -> None:
     def named_split_embedding_weights(
         self, prefix: str = "", recurse: bool = True, remove_duplicate: bool = True
     ) -> Iterator[Tuple[str, torch.Tensor]]:
-        assert (
-            remove_duplicate
-        ), "remove_duplicate=False not supported in BaseBatchedEmbedding.named_split_embedding_weights"
+        assert remove_duplicate, "remove_duplicate=False not supported in BaseBatchedEmbedding.named_split_embedding_weights"
         for config, param in zip(
             self._config.embedding_tables,
             self.emb_module.split_embedding_weights(),
@@ -899,9 +897,7 @@ def named_parameters(
     def named_split_embedding_weights(
         self, prefix: str = "", recurse: bool = True, remove_duplicate: bool = True
     ) -> Iterator[Tuple[str, torch.Tensor]]:
-        assert (
-            remove_duplicate
-        ), "remove_duplicate=False not supported in BaseBatchedEmbedding.named_split_embedding_weights"
+        assert remove_duplicate, "remove_duplicate=False not supported in BaseBatchedEmbedding.named_split_embedding_weights"
         for config, tensor in zip(
             self._config.embedding_tables,
             self.split_embedding_weights(),
@@ -1082,8 +1078,9 @@ def named_parameters(
         combined_key = "/".join(
             [config.name for config in self._config.embedding_tables]
         )
-        yield append_prefix(prefix, f"{combined_key}.weight"), cast(
-            nn.Parameter, self._emb_module.weights
+        yield (
+            append_prefix(prefix, f"{combined_key}.weight"),
+            cast(nn.Parameter, self._emb_module.weights),
         )
 
 
@@ -1101,7 +1098,8 @@ def __init__(
         self._pg = pg
 
         self._pooling: PoolingMode = pooling_type_to_pooling_mode(
-            config.pooling, sharding_type  # pyre-ignore[6]
+            config.pooling,
+            sharding_type,  # pyre-ignore[6]
         )
 
         self._local_rows: List[int] = []
@@ -1220,9 +1218,7 @@ def purge(self) -> None:
     def named_split_embedding_weights(
         self, prefix: str = "", recurse: bool = True, remove_duplicate: bool = True
     ) -> Iterator[Tuple[str, torch.Tensor]]:
-        assert (
-            remove_duplicate
-        ), "remove_duplicate=False not supported in BaseBatchedEmbedding.named_split_embedding_weights"
+        assert remove_duplicate, "remove_duplicate=False not supported in BaseBatchedEmbedding.named_split_embedding_weights"
         for config, tensor in zip(
             self._config.embedding_tables,
             self.emb_module.split_embedding_weights(),
@@ -1362,9 +1358,7 @@ def named_parameters(
     def named_split_embedding_weights(
         self, prefix: str = "", recurse: bool = True, remove_duplicate: bool = True
     ) -> Iterator[Tuple[str, PartiallyMaterializedTensor]]:
-        assert (
-            remove_duplicate
-        ), "remove_duplicate=False not supported in BaseBatchedEmbedding.named_split_embedding_weights"
+        assert remove_duplicate, "remove_duplicate=False not supported in BaseBatchedEmbedding.named_split_embedding_weights"
         for config, tensor in zip(
             self._config.embedding_tables,
             self.split_embedding_weights(),
@@ -1567,6 +1561,7 @@ def named_parameters(
         combined_key = "/".join(
             [config.name for config in self._config.embedding_tables]
         )
-        yield append_prefix(prefix, f"{combined_key}.weight"), cast(
-            nn.Parameter, self._emb_module.weights
+        yield (
+            append_prefix(prefix, f"{combined_key}.weight"),
+            cast(nn.Parameter, self._emb_module.weights),
         )