refactor: improve code readability and formatting in Hugging Face integration files

- Reformatted dictionary comprehension for better readability in `HuggingFaceHubClient`.
- Consolidated multiple lines into a single line for downloading processor datasets and artifacts.
- Streamlined logging message formatting in `_load_column_config` function.
- Removed unnecessary blank lines in various files to enhance code cleanliness.

Author: davidberenstein1957

src/data_designer/integrations/huggingface/client.py

@@ -652,7 +652,10 @@ def _build_column_stats_by_type(self, analysis: DatasetProfilerResults) -> dict[
             except (ValueError, TypeError):
                 continue
 
-        return {col_type: [pydantic_to_dict(stat) for stat in stats_list] for col_type, stats_list in column_stats_by_type.items()}
+        return {
+            col_type: [pydantic_to_dict(stat) for stat in stats_list]
+            for col_type, stats_list in column_stats_by_type.items()
+        }
 
     def _sort_column_types(self, column_stats_by_type: dict[str, list[dict[str, Any]]]) -> list[str]:
         """Sort column types by display order.
@@ -857,12 +860,8 @@ def _load_processors_from_hub(
             processor_files = [f for f in repo_files if f.startswith("processors/")]
 
             processor_groups = HuggingFaceHubClient._group_processor_files(processor_files)
-            processor_datasets = HuggingFaceHubClient._download_processor_datasets(
-                repo_id, token, processor_groups
-            )
-            processor_artifacts = HuggingFaceHubClient._download_processor_artifacts(
-                repo_id, token, processor_groups
-            )
+            processor_datasets = HuggingFaceHubClient._download_processor_datasets(repo_id, token, processor_groups)
+            processor_artifacts = HuggingFaceHubClient._download_processor_artifacts(repo_id, token, processor_groups)
 
             return processor_datasets or None, processor_artifacts or None
         except (HfHubHTTPError, FileNotFoundError, Exception):

src/data_designer/integrations/huggingface/hub_results.py

@@ -40,4 +40,3 @@ class HubDatasetResults:
 
     model_configs: list[dict[str, Any]] | None = None
     """Model configurations if available."""
-

src/data_designer/integrations/huggingface/reconstruction.py

@@ -266,7 +266,5 @@ def _load_column_config(
     try:
         return config_class.model_validate(col_config_dict)
     except Exception as e:
-        logger.warning(
-            f"Failed to load column config '{col_config_dict.get('name', 'unknown')}': {e}. Skipping."
-        )
+        logger.warning(f"Failed to load column config '{col_config_dict.get('name', 'unknown')}': {e}. Skipping.")
         return None

src/data_designer/interface/huggingface/__init__.py

@@ -15,4 +15,3 @@
 HuggingFaceHubMixin = HuggingFaceHubClient
 
 __all__ = ["HuggingFaceHubMixin", "HuggingFaceHubClient", "pull_from_hub", "HubDatasetResults", "resolve_hf_token"]
-

tests/integrations/huggingface/test_client.py

@@ -321,6 +321,7 @@ def test_build_sample_records_empty(self, client: HuggingFaceHubClient) -> None:
 
     def test_build_config_types_summary(self, client: HuggingFaceHubClient) -> None:
         """Test building config types summary."""
+
         class Config1:
             pass
 
@@ -352,9 +353,11 @@ def test_pull_from_hub_basic(
         mock_hf_dataset.to_pandas.return_value = pd.DataFrame({"col1": [1, 2, 3]})
         mock_load_dataset.return_value = mock_hf_dataset
 
-        with patch.object(HuggingFaceHubClient, "_load_analysis_from_hub", return_value=None), patch.object(
-            HuggingFaceHubClient, "_load_processors_from_hub", return_value=(None, None)
-        ), patch.object(HuggingFaceHubClient, "_load_configs_from_hub", return_value=(None, None, None)):
+        with (
+            patch.object(HuggingFaceHubClient, "_load_analysis_from_hub", return_value=None),
+            patch.object(HuggingFaceHubClient, "_load_processors_from_hub", return_value=(None, None)),
+            patch.object(HuggingFaceHubClient, "_load_configs_from_hub", return_value=(None, None, None)),
+        ):
             result = HuggingFaceHubClient.pull_from_hub(
                 "test-user/test-dataset",
                 token="test-token",