[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

lerobot/common/datasets/v21/_remove_language_instruction.py

@@ -35,22 +35,30 @@ def fix_dataset(repo_id: str) -> str:
 
     dataset_info = get_dataset_config_info(repo_id, "default")
     with SuppressWarnings():
-        lerobot_metadata = LeRobotDatasetMetadata(repo_id, revision=V20, force_cache_sync=True)
+        lerobot_metadata = LeRobotDatasetMetadata(
+            repo_id, revision=V20, force_cache_sync=True
+        )
 
-    meta_features = {key for key, ft in lerobot_metadata.features.items() if ft["dtype"] != "video"}
+    meta_features = {
+        key for key, ft in lerobot_metadata.features.items() if ft["dtype"] != "video"
+    }
     parquet_features = set(dataset_info.features)
 
     diff_parquet_meta = parquet_features - meta_features
     diff_meta_parquet = meta_features - parquet_features
 
     if diff_parquet_meta:
-        raise ValueError(f"In parquet not in info.json: {parquet_features - meta_features}")
+        raise ValueError(
+            f"In parquet not in info.json: {parquet_features - meta_features}"
+        )
 
     if not diff_meta_parquet:
         return f"{repo_id}: skipped (no diff)"
 
     if diff_meta_parquet:
-        logging.warning(f"In info.json not in parquet: {meta_features - parquet_features}")
+        logging.warning(
+            f"In info.json not in parquet: {meta_features - parquet_features}"
+        )
         assert diff_meta_parquet == {"language_instruction"}
         lerobot_metadata.features.pop("language_instruction")
         write_info(lerobot_metadata.info, lerobot_metadata.root)

lerobot/common/datasets/v21/convert_dataset_v20_to_v21.py

@@ -37,8 +37,16 @@ import logging
 from huggingface_hub import HfApi
 
 from lerobot.common.datasets.lerobot_dataset import CODEBASE_VERSION, LeRobotDataset
-from lerobot.common.datasets.utils import EPISODES_STATS_PATH, STATS_PATH, load_stats, write_info
-from lerobot.common.datasets.v21.convert_stats import check_aggregate_stats, convert_stats
+from lerobot.common.datasets.utils import (
+    EPISODES_STATS_PATH,
+    STATS_PATH,
+    load_stats,
+    write_info,
+)
+from lerobot.common.datasets.v21.convert_stats import (
+    check_aggregate_stats,
+    convert_stats,
+)
 
 V20 = "v2.0"
 V21 = "v2.1"
@@ -79,13 +87,21 @@ def convert_dataset(
 
     hub_api = HfApi()
     if hub_api.file_exists(
-        repo_id=dataset.repo_id, filename=STATS_PATH, revision=branch, repo_type="dataset"
+        repo_id=dataset.repo_id,
+        filename=STATS_PATH,
+        revision=branch,
+        repo_type="dataset",
     ):
         hub_api.delete_file(
-            path_in_repo=STATS_PATH, repo_id=dataset.repo_id, revision=branch, repo_type="dataset"
+            path_in_repo=STATS_PATH,
+            repo_id=dataset.repo_id,
+            revision=branch,
+            repo_type="dataset",
         )
 
-    hub_api.create_tag(repo_id, tag=CODEBASE_VERSION, revision=branch, repo_type="dataset")
+    hub_api.create_tag(
+        repo_id, tag=CODEBASE_VERSION, revision=branch, repo_type="dataset"
+    )
 
 
 if __name__ == "__main__":

lerobot/common/datasets/v21/convert_stats.py

@@ -17,12 +17,18 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 import numpy as np
 from tqdm import tqdm
 
-from lerobot.common.datasets.compute_stats import aggregate_stats, get_feature_stats, sample_indices
+from lerobot.common.datasets.compute_stats import (
+    aggregate_stats,
+    get_feature_stats,
+    sample_indices,
+)
 from lerobot.common.datasets.lerobot_dataset import LeRobotDataset
 from lerobot.common.datasets.utils import write_episode_stats
 
 
-def sample_episode_video_frames(dataset: LeRobotDataset, episode_index: int, ft_key: str) -> np.ndarray:
+def sample_episode_video_frames(
+    dataset: LeRobotDataset, episode_index: int, ft_key: str
+) -> np.ndarray:
     ep_len = dataset.meta.episodes[episode_index]["length"]
     sampled_indices = sample_indices(ep_len)
     query_timestamps = dataset._get_query_timestamps(0.0, {ft_key: sampled_indices})
@@ -45,11 +51,14 @@ def convert_episode_stats(dataset: LeRobotDataset, ep_idx: int):
 
         axes_to_reduce = (0, 2, 3) if ft["dtype"] in ["image", "video"] else 0
         keepdims = True if ft["dtype"] in ["image", "video"] else ep_ft_data.ndim == 1
-        ep_stats[key] = get_feature_stats(ep_ft_data, axis=axes_to_reduce, keepdims=keepdims)
+        ep_stats[key] = get_feature_stats(
+            ep_ft_data, axis=axes_to_reduce, keepdims=keepdims
+        )
 
         if ft["dtype"] in ["image", "video"]:  # remove batch dim
             ep_stats[key] = {
-                k: v if k == "count" else np.squeeze(v, axis=0) for k, v in ep_stats[key].items()
+                k: v if k == "count" else np.squeeze(v, axis=0)
+                for k, v in ep_stats[key].items()
             }
 
     dataset.meta.episodes_stats[ep_idx] = ep_stats
@@ -95,5 +104,9 @@ def check_aggregate_stats(
             if key in reference_stats and stat in reference_stats[key]:
                 err_msg = f"feature='{key}' stats='{stat}'"
                 np.testing.assert_allclose(
-                    val, reference_stats[key][stat], rtol=rtol, atol=atol, err_msg=err_msg
+                    val,
+                    reference_stats[key][stat],
+                    rtol=rtol,
+                    atol=atol,
+                    err_msg=err_msg,
                 )