Merge pull request #624 from DeepRank/622_linting_dbodor

ci: update ruff and fix linting rules

Author: DaniBodor

deeprank2/tools/target.py

@@ -35,12 +35,9 @@ def add_target(  # noqa: C901
         1ATN_xxx-3 0
         1ATN_xxx-4 0
     """
-    target_dict = {}
-
     labels = np.loadtxt(target_list, delimiter=sep, usecols=[0], dtype=str)
     values = np.loadtxt(target_list, delimiter=sep, usecols=[1])
-    for label, value in zip(labels, values, strict=True):
-        target_dict[label] = value
+    target_dict = dict(zip(labels, values, strict=False))
 
     if os.path.isdir(graph_path):
         graphs = glob.glob(f"{graph_path}/*.hdf5")

deeprank2/trainer.py

@@ -348,8 +348,7 @@ def _precluster(self, dataset: GraphDataset) -> None:
             f5.close()
 
     def _put_model_to_device(self, dataset: GraphDataset | GridDataset) -> None:
-        """
-        Puts the model on the available device.
+        """Puts the model on the available device.
 
         Args:
             dataset (:class:`GraphDataset` | :class:`GridDataset`): GraphDataset object.
@@ -405,8 +404,7 @@ def configure_optimizers(
         lr: float = 0.001,
         weight_decay: float = 1e-05,
     ) -> None:
-        """
-        Configure optimizer and its main parameters.
+        """Configure optimizer and its main parameters.
 
         Args:
             optimizer (:class:`torch.optim`, optional): PyTorch optimizer object. If none, defaults to :class:`torch.optim.Adam`.
@@ -435,8 +433,7 @@ def set_lossfunction(  # noqa: C901
         lossfunction: nn.modules.loss._Loss | None = None,
         override_invalid: bool = False,
     ) -> None:
-        """
-        Set the loss function.
+        """Set the loss function.
 
         Args:
             lossfunction (optional): Make sure to use a loss function that is appropriate for
@@ -524,8 +521,7 @@ def train(  # noqa: PLR0915, C901
         best_model: bool = True,
         filename: str | None = "model.pth.tar",
     ) -> None:
-        """
-        Performs the training of the model.
+        """Performs the training of the model.
 
         Args:
             nepoch (int, optional): Maximum number of epochs to run.
@@ -685,8 +681,7 @@ def train(  # noqa: PLR0915, C901
         self.model.load_state_dict(self.model_load_state_dict)
 
     def _epoch(self, epoch_number: int, pass_name: str) -> float | None:
-        """
-        Runs a single epoch.
+        """Runs a single epoch.
 
         Args:
             epoch_number (int): the current epoch number
@@ -751,8 +746,7 @@ def _eval(
         epoch_number: int,
         pass_name: str,
     ) -> float | None:
-        """
-        Evaluates the model.
+        """Evaluates the model.
 
         Args:
             loader (Dataloader): Data to evaluate on.
@@ -818,8 +812,7 @@ def _eval(
 
     @staticmethod
     def _log_epoch_data(stage: str, loss: float, time: float) -> None:
-        """
-        Prints the data of each epoch.
+        """Prints the data of each epoch.
 
         Args:
             stage (str): Train or valid.
@@ -863,8 +856,7 @@ def test(
         batch_size: int = 32,
         num_workers: int = 0,
     ) -> None:
-        """
-        Performs the testing of the model.
+        """Performs the testing of the model.
 
         Args:
             batch_size (int, optional): Sets the size of the batch.
@@ -935,8 +927,7 @@ def _load_params(self) -> None:
         self.ngpu = state["ngpu"]
 
     def _save_model(self) -> dict[str, Any]:
-        """
-        Saves the model to a file.
+        """Saves the model to a file.
 
         Args:
             filename (str, optional): Name of the file. Defaults to None.

deeprank2/utils/parsing/residue.py

@@ -10,9 +10,7 @@ def __init__(
         absent_atom_names: list[str],
     ):
         self.class_name = class_name
-
         self.amino_acid_names = amino_acid_names
-
         self.present_atom_names = present_atom_names
         self.absent_atom_names = absent_atom_names
 
@@ -26,11 +24,7 @@ def matches(self, amino_acid_name: str, atom_names: list[str]) -> bool:
             return False
 
         # check the atom names that should be present
-        if not all(atom_name in atom_names for atom_name in self.present_atom_names):
-            return False
-
-        # all checks passed
-        return True
+        return all(atom_name in atom_names for atom_name in self.present_atom_names)
 
 
 class ResidueClassParser:  # noqa: D101

pyproject.toml

@@ -91,10 +91,12 @@ include = ["deeprank2*"]
 addopts = "-ra"  
 
 [tool.ruff]
+output-format = "concise"
 line-length = 159
 
 [tool.ruff.lint]
 select = ["ALL"]
+pydocstyle.convention = "google" # docstring settings
 ignore = [
     # Unrealistic for this code base
     "PTH",     # flake8-use-pathlib    
@@ -117,20 +119,6 @@ ignore = [
     "D104", # Missing public package docstring
     "D105", # Missing docstring in magic method
     "D107", # Missing docstring in `__init__`
-    # Docstring rules irrelevant to the Google style
-    "D203", # 1 blank line required before class docstring
-    "D204", # 1 blank line required after class docstring
-    "D212", # Multi-line docstring summary should start at the first line
-    "D213", # Multi-line docstring summary should start at the second line
-    "D215", # Section underline is over-indented 
-    "D400", # First line should end with a period (clashes with D415:First line should end with a period, question mark, or exclamation point) 
-    "D401", # First line of docstring should be in imperative mood
-    "D404", # First word of the docstring should not be This
-    "D406", # Section name should end with a newline
-    "D407", # Missing dashed underline after section 
-    "D408", # Section underline should be in the line following the section's name
-    "D409", # Section underline should match the length of its name
-    "D413", # Missing blank line after last section 
 ]
 
 # Autofix settings

tests/test_integration.py

@@ -32,8 +32,7 @@
 
 
 def test_cnn() -> None:
-    """
-    Tests processing several PDB files into their features representation HDF5 file.
+    """Tests processing several PDB files into their features representation HDF5 file.
 
     Then uses HDF5 generated files to train and test a CnnRegression network.
     """

tests/test_querycollection.py

@@ -22,8 +22,7 @@ def _querycollection_tester(
     cpu_count: int = 1,
     combine_output: bool = True,
 ) -> tuple[QueryCollection, str, list[str]]:
-    """
-    Generic function to test QueryCollection class.
+    """Generic function to test QueryCollection class.
 
     Args:
         query_type (str): query type to be generated. It accepts only 'ppi' (ProteinProteinInterface) or 'srv' (SingleResidueVariant).
@@ -203,15 +202,11 @@ def test_querycollection_process_combine_output_true() -> None:
         _, output_directory_f, output_paths_f = _querycollection_tester(query_type, feature_modules=modules, combine_output=False, cpu_count=2)
         assert len(output_paths_t) == 1
 
-        keys_t = {}
         with h5py.File(output_paths_t[0], "r") as file_t:
-            for key, value in file_t.items():
-                keys_t[key] = value
-        keys_f = {}
+            keys_t = dict(file_t.items())
         for output_path in output_paths_f:
             with h5py.File(output_path, "r") as file_f:
-                for key, value in file_f.items():
-                    keys_f[key] = value
+                keys_f = dict(file_f.items())
         assert keys_t == keys_f
 
         rmtree(output_directory_t)