Clean documentation

.github/pull_request_template.md

@@ -1,4 +1,4 @@
-### All Submissions
+### All submissions
 
 - [ ] Have you followed the guidelines in our [Contributing](../../CONTRIBUTING.md) document?
 - [ ] Have you checked to ensure there are no other open [Pull Requests](../../../pulls) for the same changes?

.github/workflows/ci.yaml

@@ -25,7 +25,6 @@ jobs:
         make build
 
     - name: Check docstrings
-      continue-on-error: true   # TODO: remove when all docstring issues are fixed
       run: |
         make docstring-check
 

Makefile

@@ -27,7 +27,7 @@ setup-tensorboard:
 	@echo '=== Setup TensorBoard ==='
 	$(UV) pip install -e ".[tensorboard]"
 
-check: lint format typecheck
+check: typecheck format lint docstring-check
 
 format:
 	@echo '=== Formatting ==='
@@ -73,8 +73,6 @@ si-test:
 	@echo '=== Running single integration test for $(T) ==='
 	$(UV) run $(PYTEST) -n auto -s $(PROJECT_NAME)/integration_tests/$(T) -m "integration"
 
-
-
 # If the first argument is run...
 ifeq ($(firstword $(MAKECMDGOALS)),run)
   # use the rest as arguments for run...

docs/getting-started/installation.md

@@ -58,7 +58,7 @@ HyperBench declares compatibility ranges for direct dependencies in `pyproject.t
 
 | Dependency | Supported range | Notes |
 | --- | --- | --- |
-| mkdocstrings[python] | `>=1.0.4,<2.0.0` |  |
+| mkdocstrings\[python\] | `>=1.0.4,<2.0.0` |  |
 | pre-commit | `>=4.5.1,<5.0.0` |  |
 | pytest | `>=9.0.3,<10.0.0` |  |
 | pytest-cov | `>=7.1.0,<8.0.0` |  |

examples/early_stopping.py

@@ -81,7 +81,8 @@
     train_dataset.enrich_node_features(
         enricher=LaplacianPositionalEncodingEnricher(
             num_features=num_features,
-            # In transductive setting, use total number of nodes to ensure consistent encoding across splits
+            # In transductive setting, use total number of nodes to ensure consistent encoding
+            # across splits
             # as the train dataset contain all nodes but may have no hyperedges where they appear
             num_nodes=train_dataset.hdata.num_nodes,
         ),

examples/external_dataset.py

@@ -81,7 +81,8 @@
     train_dataset.enrich_node_features(
         enricher=LaplacianPositionalEncodingEnricher(
             num_features=num_features,
-            # In transductive setting, use total number of nodes to ensure consistent encoding across splits
+            # In transductive setting, use total number of nodes to ensure consistent encoding
+            # across splits
             # as the train dataset contain all nodes but may have no hyperedges where they appear
             num_nodes=train_dataset.hdata.num_nodes,
         ),

hyperbench/__init__.py

@@ -10,5 +10,8 @@
 
 warnings.filterwarnings(
     "ignore",
-    message="ignore:Failing to pass a value to the 'type_params' parameter of 'typing._eval_type' is deprecated.*",
+    message=(
+        "ignore:Failing to pass a value to the 'type_params' parameter of "
+        "'typing._eval_type' is deprecated.*"
+    ),
 )

hyperbench/data/hif.py

@@ -25,7 +25,9 @@
 
 
 class HIFProcessor:
-    """A utility class to process HIF hypergraph data into `HData` format."""
+    """
+    A utility class to process HIF hypergraph data into `HData` format.
+    """
 
     @staticmethod
     def transform_attrs(
@@ -34,11 +36,13 @@ def transform_attrs(
     ) -> Tensor:
         """
         Extract and encode numeric attributes to tensor.
+
         Non-numeric attributes are discarded. Missing attributes are filled with ``0.0``.
 
         Args:
             attrs: Dictionary of attributes
-            attr_keys: Optional list of attribute keys to encode. If provided, ensures consistent ordering and fill missing with ``0.0``.
+            attr_keys: Optional list of attribute keys to encode. If provided,
+                ensures consistent ordering and fill missing with ``0.0``.
 
         Returns:
             attrs: Tensor of numeric attribute values
@@ -67,7 +71,6 @@ def process_hypergraph(cls, hypergraph: HIFHypergraph) -> HData:
         Returns:
             hdata: The processed hypergraph data.
         """
-
         num_nodes = len(hypergraph.nodes)
         x = cls.__process_x(hypergraph, num_nodes)
 
@@ -93,7 +96,8 @@ def process_hypergraph(cls, hypergraph: HIFHypergraph) -> HData:
                 )
 
             if hyperedge_id not in hyperedge_id_to_idx:
-                # Hyperedges start from 0 and are assigned IDs in the order they are first encountered in incidences
+                # Hyperedges start from 0 and are assigned IDs in the order they are
+                # first encountered in incidences
                 hyperedge_id_to_idx[hyperedge_id] = len(hyperedge_id_to_idx)
 
             node_ids.append(node_id_to_idx[node_id])
@@ -244,7 +248,9 @@ def __process_hyperedge_weights(
 
 
 class HIFLoader:
-    """A utility class to load hypergraphs from HIF format."""
+    """
+    A utility class to load hypergraphs from HIF format.
+    """
 
     @classmethod
     def load_from_url(cls, url: str, save_on_disk: bool = False) -> HData:
@@ -263,7 +269,8 @@ def load_from_url(cls, url: str, save_on_disk: bool = False) -> HData:
         response = requests.get(url, timeout=20)
         if response.status_code != 200:
             raise ValueError(
-                f"Failed to download dataset from URL {url!r} with status code {response.status_code}"
+                f"Failed to download dataset from URL {url!r} "
+                f"with status code {response.status_code}"
             )
 
         if not url.endswith((".json.zst", ".json")):
@@ -273,7 +280,9 @@ def load_from_url(cls, url: str, save_on_disk: bool = False) -> HData:
 
         if os.path.basename(url).count(".") > 2:
             raise ValueError(
-                f"URL {url!r} has an unexpected filename format. Expected at most one dot in the base filename before the extension (e.g., dataset.json or dataset.json.zst)."
+                f"URL {url!r} has an unexpected filename format. "
+                "Expected at most one dot in the base filename before the "
+                "extension (e.g., dataset.json or dataset.json.zst)."
             )
 
         if url.endswith(".json.zst"):
@@ -298,7 +307,8 @@ def load_from_url(cls, url: str, save_on_disk: bool = False) -> HData:
     @classmethod
     def load_from_path(cls, filepath: str) -> HData:
         """
-        Load a hypergraph from a local file path pointing to a .json or .json.zst file in HIF format.
+        Load a hypergraph from a local file path pointing to a .json or .json.zst file in HIF
+        format.
 
         Args:
             filepath: The local file path to the .json or .json.zst file
@@ -337,7 +347,10 @@ def load_by_name(
             hif_data = from_zst_file_to_json(zst_filename)
             return cls.__process_hif_data(hif_data, dataset_name)
 
-        github_url = f"https://raw.githubusercontent.com/hypernetwork-research-group/datasets/{GITHUB_COMMIT_SHA}/{dataset_name}.json.zst"
+        github_url = (
+            f"https://raw.githubusercontent.com/hypernetwork-research-group/datasets/"
+            f"{GITHUB_COMMIT_SHA}/{dataset_name}.json.zst"
+        )
         response = requests.get(github_url, timeout=20)
         if response.status_code == 200:
             dataset_bytes = response.content
@@ -348,15 +361,17 @@ def load_by_name(
             return hdata
 
         warnings.warn(
-            f"GitHub raw download failed for dataset {dataset_name!r} with status code {response.status_code}\n"
+            f"GitHub raw download failed for dataset {dataset_name!r} "
+            f"with status code {response.status_code}\n"
             "Falling back to Hugging Face Hub download for dataset",
             category=UserWarning,
             stacklevel=2,
         )
 
         if hf_sha is None:
             raise ValueError(
-                f"Failed to download dataset {dataset_name!r} from GitHub with status code {response.status_code} "
+                f"Failed to download dataset {dataset_name!r} from GitHub "
+                f"with status code {response.status_code} "
                 f"and no SHA provided for Hugging Face Hub fallback."
             )
 
@@ -384,7 +399,8 @@ def load_by_name(
                 shutil.copyfile(downloaded_path, zst_filename)
             except Exception as e:
                 raise ValueError(
-                    f"Failed to save downloaded dataset {dataset_name!r} to disk at {zst_filename!r}: {e!s}."
+                    f"Failed to save downloaded dataset {dataset_name!r} to disk at "
+                    f"{zst_filename!r}: {e!s}."
                 ) from e
 
         if os.path.isdir(hf_cache_dir):
@@ -394,7 +410,8 @@ def load_by_name(
                 shutil.rmtree(os.path.join(hf_cache_dir, ".locks", path_prefix))
             except Exception as e:
                 warnings.warn(
-                    f"Failed to clean up Hugging Face Hub cache after downloading dataset {dataset_name!r}: {e!s}.",
+                    f"Failed to clean up Hugging Face Hub cache after downloading "
+                    f"dataset {dataset_name!r}: {e!s}.",
                     category=UserWarning,
                     stacklevel=2,
                 )

hyperbench/data/loader.py

@@ -35,12 +35,14 @@ def collate(self, batch: list[HData]) -> HData:
         """
         Collates a list of `HData` objects into a single batched `HData` object.
 
-        This function combines multiple separate samples into a single batched representation suitable for mini-batch training.
-        It handles:
-        - Concatenating node features from all samples.
-        - Concatenating and offsetting hyperedges from all samples.
-        - Concatenating hyperedge attributes from all samples, if present.
-        - Concatenating hyperedge weights from all samples, if present.
+        This function combines multiple separate samples into a single batched representation
+        suitable for mini-batch training.
+
+        Handles:
+            - Concatenating node features from all samples.
+            - Concatenating and offsetting hyperedges from all samples.
+            - Concatenating hyperedge attributes from all samples, if present.
+            - Concatenating hyperedge weights from all samples, if present.
 
         Examples:
             Given ``batch = [HData_0, HData_1]``:
@@ -56,7 +58,7 @@ def collate(self, batch: list[HData]) -> HData:
             - ``HData_0`` (3 nodes, 2 hyperedges):
 
             >>> hyperedge_index = [[0, 1, 1, 2],  # Nodes 0, 1, 1, 2
-            ...                    [0, 0, 1, 1]]  # Hyperedge 0 contains {0,1}, Hyperedge 1 contains {1,2}
+            ...                    [0, 0, 1, 1]]  # HE 0 contains {0,1}, HE 1 contains {1,2}
 
             - ``HData_1`` (2 nodes, 1 hyperedge):