style: update ruff

.github/workflows/linting.yml

@@ -51,4 +51,4 @@ jobs:
           python-version: ${{ matrix.python-version }}
           extras-require: test
       - name: Check style against standards using ruff
-        run: ruff .
+        run: ruff check .

.vscode/settings.json

@@ -17,6 +17,10 @@
   },
   "notebook.diff.ignoreMetadata": true,
 
+  // Pytest
+  "python.testing.unittestEnabled": false,
+  "python.testing.pytestEnabled": true,
+
   // Format all files on save
   "editor.formatOnSave": true,
   "editor.defaultFormatter": "esbenp.prettier-vscode",

CONTRIBUTING.rst

@@ -37,7 +37,7 @@ You want to make some kind of change to the code base
 #. if needed, fork the repository to your own Github profile and create your own feature branch off of the latest main commit. While working on your feature branch, make sure to stay up to date with the main branch by pulling in changes, possibly from the 'upstream' repository (follow the instructions `here <https://help.github.com/articles/configuring-a-remote-for-a-fork/>`__ and `here <https://help.github.com/articles/syncing-a-fork/>`__);
 #. make sure the existing tests still work by running ``python setup.py test``;
 #. add your own tests (if necessary);
-#. ensure the code is correctly linted (``ruff .``) and formatted (``ruff format .``);
+#. ensure the code is correctly linted (``ruff check.``) and formatted (``ruff format .``);
 #. see our `developer's readme <README.dev.md>`_ for detailed information on our style conventions, etc.;
 #. update or expand the documentation;
 #. `push <http://rogerdudler.github.io/git-guide/>`_ your feature branch to (your fork of) the DeepRank2 repository on GitHub;

README.dev.md

@@ -48,7 +48,7 @@ We use [ruff](https://docs.astral.sh/ruff/) for linting, sorting imports and for
 
 If you are using VS code, please install and activate the [Ruff extension](https://marketplace.visualstudio.com/items?itemName=charliermarsh.ruff) to automatically format and check linting.
 
-Otherwise, please ensure check both linting (`ruff fix .`) and formatting (`ruff format .`) before requesting a review.
+Otherwise, please ensure check both linting (`ruff check .`) and formatting (`ruff format .`) before requesting a review.
 
 We use [prettier](https://prettier.io/) for formatting most other files. If you are editing or adding non-python files and using VS code, the [Prettier extension](https://marketplace.visualstudio.com/items?itemName=esbenp.prettier-vscode) can be installed to auto-format these files as well.
 

deeprank2/trainer.py

@@ -21,7 +21,7 @@
 from deeprank2.utils.earlystopping import EarlyStopping
 from deeprank2.utils.exporters import HDF5OutputExporter, OutputExporter, OutputExporterCollection
 
-# ruff: noqa: PYI041 (redundant-numeric-union), they are used differently in this module
+# ruff: noqa: PYI041 (usage depends on type in this module)
 _log = logging.getLogger(__name__)
 
 

deeprank2/utils/community_pooling.py

@@ -11,7 +11,7 @@
 from torch_geometric.nn.pool.pool import pool_batch, pool_edge
 from torch_scatter import scatter_max, scatter_mean
 
-# ruff: noqa: ANN001, ANN201 (missing type hints and return types)
+# ruff: noqa: ANN001, ANN201
 
 
 def plot_graph(graph, cluster) -> None:  # noqa:D103

env/deeprank2-docker.yml

@@ -38,7 +38,7 @@ dependencies:
   - freesasa>=2.1.0
   - tensorboard>=0.9.0
   - protobuf>=3.20.1
-  - ruff>=0.1.13
+  - ruff>=0.3.0
   - dill>=0.3.8
   - pyarrow>=15.0.0
   - pip:

env/deeprank2.yml

@@ -38,6 +38,6 @@ dependencies:
   - freesasa>=2.1.0
   - tensorboard>=0.9.0
   - protobuf>=3.20.1
-  - ruff>=0.1.13
+  - ruff>=0.3.0
   - dill>=0.3.8
   - pyarrow>=15.0.0

pyproject.toml

@@ -66,6 +66,8 @@ exclude = ["tests*", "*tests.*", "*tests"]
 
 [tool.ruff]
 line-length = 159
+
+[tool.ruff.lint]
 select = ["ALL"]
 ignore = [
     # Unrealistic for this code base
@@ -105,22 +107,9 @@ ignore = [
     "D413", # Missing blank line after last section 
 ]
 
-# Allow autofix for all enabled rules.
+# Autofix settings
 fixable = ["ALL"]
 unfixable = ["F401"] # unused imports (should not disappear while editing)
-
-[tool.ruff.lint.per-file-ignores]
-"tests/*" = [
-    "S101",    # Use of `assert` detected
-    "PLR2004", # Magic value used in comparison
-    "D101",    # Missing class docstring
-    "D102",    # Missing docstring in public method
-    "D103",    # Missing docstring in public function
-]
-"docs/*" = ["ALL"]
-"tests/perf/*" = ["T201"] # Use of print statements
-
-[tool.ruff.lint]
 extend-safe-fixes = [
     "D415",   # First line should end with a period, question mark, or exclamation point
     "D300",   # Use triple double quotes `"""`
@@ -132,5 +121,16 @@ extend-safe-fixes = [
     "B006",   # Mutable default argument
 ]
 
-[tool.ruff.isort]
-known-first-party = ["deeprank2"]
+isort.known-first-party = ["deeprank2"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/*" = [
+    "S101",    # Use of `assert` detected
+    "PLR2004", # Magic value used in comparison
+    "D101",    # Missing class docstring
+    "D102",    # Missing docstring in public method
+    "D103",    # Missing docstring in public function
+    "SLF001",  # private member access
+]
+"docs/*" = ["ALL"]
+"tests/perf/*" = ["T201"] # Use of print statements

tests/domain/test_forcefield.py

@@ -10,7 +10,7 @@ def test_atomic_forcefield() -> None:
     try:
         structure = get_structure(pdb, "101M")
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
 
     # The arginine C-zeta should get a positive charge
     arg = next(r for r in structure.get_chain("A").residues if r.amino_acid == arginine)

tests/features/__init__.py

@@ -55,7 +55,7 @@ def build_testgraph(  # noqa: C901
     try:
         structure: PDBStructure = get_structure(pdb, Path(pdb_path).stem)
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
 
     if not central_res:
         nodes = set()

tests/features/test_contact.py

@@ -43,7 +43,7 @@ def _get_contact(
     try:
         structure = get_structure(pdb, pdb_id)
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
 
     if not chains:
         chains = [structure.chains[0], structure.chains[0]]

tests/molstruct/test_structure.py

@@ -12,7 +12,7 @@ def _get_structure(path: str) -> PDBStructure:
     try:
         structure = get_structure(pdb, "101M")
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
 
     assert structure is not None
 

tests/perf/ppi_perf.py

@@ -41,7 +41,7 @@
     os.makedirs(os.path.join(processed_data_path, "atomic"))
 
 
-def get_pdb_files_and_target_data(data_path: str) -> (list[str], list):
+def get_pdb_files_and_target_data(data_path: str) -> tuple[list[str], list]:
     csv_data = pd.read_csv(os.path.join(data_path, "BA_values.csv"))
     pdb_files = glob.glob(os.path.join(data_path, "pdb", "*.pdb"))
     pdb_files.sort()

tests/perf/srv_perf.py

@@ -87,7 +87,7 @@
     os.makedirs(os.path.join(processed_data_path, "atomic"))
 
 
-def get_pdb_files_and_target_data(data_path: str) -> (list[str], list, list, list, list):
+def get_pdb_files_and_target_data(data_path: str) -> tuple[list[str], list, list, list, list]:
     csv_data = pd.read_csv(os.path.join(data_path, "srv_target_values.csv"))
     # before running this script change .ent to .pdb
     pdb_files = glob.glob(os.path.join(data_path, "pdb", "*.pdb"))

tests/test_dataset.py

@@ -31,7 +31,7 @@ def _compute_features_manually(
     hdf5_path: str,
     features_transform: dict,
     feat: str,
-) -> (NDArray, float, float):
+) -> tuple[NDArray, float, float]:
     """Return specified feature.
 
     This function returns the feature specified read from the hdf5 file, after applying manually features_transform dict.

tests/test_querycollection.py

@@ -21,7 +21,7 @@ def _querycollection_tester(
     feature_modules: ModuleType | list[ModuleType] | None = None,
     cpu_count: int = 1,
     combine_output: bool = True,
-) -> (QueryCollection, str, list[str]):
+) -> tuple[QueryCollection, str, list[str]]:
     """
     Generic function to test QueryCollection class.
 
@@ -279,6 +279,6 @@ def test_querycollection_duplicates_add() -> None:
         "1ATN_2w_2",
         "1ATN_3w",
     ]
-    assert queries._ids_count["residue-ppi:A-B:1ATN_1w"] == 3  # noqa: SLF001
-    assert queries._ids_count["residue-ppi:A-B:1ATN_2w"] == 2  # noqa: SLF001
-    assert queries._ids_count["residue-ppi:A-B:1ATN_3w"] == 1  # noqa: SLF001
+    assert queries._ids_count["residue-ppi:A-B:1ATN_1w"] == 3
+    assert queries._ids_count["residue-ppi:A-B:1ATN_2w"] == 2
+    assert queries._ids_count["residue-ppi:A-B:1ATN_3w"] == 1

tests/utils/test_buildgraph.py

@@ -12,7 +12,7 @@ def test_get_structure_complete() -> None:
     try:
         structure = get_structure(pdb, "101M")
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
 
     assert structure is not None
 
@@ -40,7 +40,7 @@ def test_get_structure_from_nmr_with_dna() -> None:
     try:
         structure = get_structure(pdb, "101M")
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
 
     assert structure is not None
     assert structure.chains[0].residues[0].amino_acid is None  # DNA
@@ -52,7 +52,7 @@ def test_residue_contact_pairs() -> None:
     try:
         structure = get_structure(pdb, "1ATN")
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
     residue_pairs = get_residue_contact_pairs(pdb_path, structure, "A", "B", 8.5)
 
     assert len(residue_pairs) > 0
@@ -64,7 +64,7 @@ def test_surrounding_residues() -> None:
     try:
         structure = get_structure(pdb, "101M")
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
 
     all_residues = structure.get_chain("A").residues
     # A nicely centered residue

tests/utils/test_graph.py

@@ -35,7 +35,7 @@ def graph() -> Graph:
     try:
         structure = get_structure(pdb, entry_id)
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
 
     # build a contact from two residues
     residue0 = structure.chains[0].residues[0]

tests/utils/test_pssmdata.py

@@ -10,7 +10,7 @@ def test_add_pssm() -> None:
     try:
         structure = get_structure(pdb, "1ATN")
     finally:
-        pdb._close()  # noqa: SLF001
+        pdb._close()
 
     for chain in structure.chains:
         with open(f"tests/data/pssm/1ATN/1ATN.{chain.id}.pdb.pssm", encoding="utf-8") as f: