[ci] [python-package] enforce 'pylint' checks (fixes #4308) (#6334)

python-package/lightgbm/basic.py

@@ -1215,7 +1215,7 @@ def predict(
             )
         if pred_leaf:
             preds = preds.astype(np.int32)
-        is_sparse = isinstance(preds, scipy.sparse.spmatrix) or isinstance(preds, list)
+        is_sparse = isinstance(preds, (list, scipy.sparse.spmatrix))
         if not is_sparse and preds.size != nrow:
             if preds.size % nrow == 0:
                 preds = preds.reshape(nrow, -1)
@@ -2681,7 +2681,10 @@ def set_field(
                     'In multiclass classification init_score can also be a list of lists, numpy 2-D array or pandas DataFrame.'
                 )
         else:
-            dtype = np.int32 if (field_name == 'group' or field_name == 'position') else np.float32
+            if field_name in {'group', 'position'}:
+                dtype = np.int32
+            else:
+                dtype = np.float32
             data = _list_to_1d_numpy(data, dtype=dtype, name=field_name)
 
         ptr_data: Union[_ctypes_float_ptr, _ctypes_int_ptr]
@@ -3106,7 +3109,7 @@ def get_data(self) -> Optional[_LGBM_TrainDataType]:
         if self._need_slice and self.used_indices is not None and self.reference is not None:
             self.data = self.reference.data
             if self.data is not None:
-                if isinstance(self.data, np.ndarray) or isinstance(self.data, scipy.sparse.spmatrix):
+                if isinstance(self.data, (np.ndarray, scipy.sparse.spmatrix)):
                     self.data = self.data[self.used_indices, :]
                 elif isinstance(self.data, pd_DataFrame):
                     self.data = self.data.iloc[self.used_indices].copy()
@@ -3284,7 +3287,7 @@ def add_features_from(self, other: "Dataset") -> "Dataset":
                     self.data = None
             elif isinstance(self.data, scipy.sparse.spmatrix):
                 sparse_format = self.data.getformat()
-                if isinstance(other.data, np.ndarray) or isinstance(other.data, scipy.sparse.spmatrix):
+                if isinstance(other.data, (np.ndarray, scipy.sparse.spmatrix)):
                     self.data = scipy.sparse.hstack((self.data, other.data), format=sparse_format)
                 elif isinstance(other.data, pd_DataFrame):
                     self.data = scipy.sparse.hstack((self.data, other.data.values), format=sparse_format)

python-package/lightgbm/plotting.py

@@ -393,8 +393,8 @@ def plot_metric(
     for name in dataset_names_iter:
         metrics_for_one = eval_results[name]
         results = metrics_for_one[metric]
-        max_result = max(max(results), max_result)
-        min_result = min(min(results), min_result)
+        max_result = max(*results, max_result)
+        min_result = min(*results, min_result)
         ax.plot(x_, results, label=name)
 
     ax.legend(loc='best')
@@ -804,7 +804,7 @@ def plot_tree(
         The plot with single tree.
     """
     if MATPLOTLIB_INSTALLED:
-        import matplotlib.image as image
+        import matplotlib.image
         import matplotlib.pyplot as plt
     else:
         raise ImportError('You must install matplotlib and restart your session to plot tree.')
@@ -821,7 +821,7 @@ def plot_tree(
     s = BytesIO()
     s.write(graph.pipe(format='png'))
     s.seek(0)
-    img = image.imread(s)
+    img = matplotlib.image.imread(s)
 
     ax.imshow(img)
     ax.axis('off')

python-package/pyproject.toml

@@ -125,7 +125,21 @@ ignore = [
     # (pydocstyle) Missing docstring in magic method
     "D105",
     # (pycodestyle) Line too long
-    "E501"
+    "E501",
+    # (pylint) Too many branches
+    "PLR0912",
+    # (pylint) Too many arguments in function definition
+    "PLR0913",
+    # (pylint) Too many statements
+    "PLR0915",
+    # (pylint) Consider merging multiple comparisons
+    "PLR1714",
+    # (pylint) Magic value used in comparison
+    "PLR2004",
+    # (pylint) for loop veriable overwritten by assignment target
+    "PLW2901",
+    # (pylint) use 'elif' instead of 'else' then 'if', to reduce indentation
+    "PLR5501"
 ]
 select = [
     # flake8-bugbear
@@ -138,6 +152,8 @@ select = [
     "E",
     # pyflakes
     "F",
+    # pylint
+    "PL",
     # flake8-return: unnecessary assignment before return
     "RET504",
     # flake8-simplify: use dict.get() instead of an if-else block
@@ -159,6 +175,10 @@ select = [
     # flake8-print
     "T"
 ]
+"python-package/lightgbm/basic.py" = [
+    # (pylint) Using the global statement is discouraged
+    "PLW0603"
+]
 "tests/*" = [
     # (flake8-bugbear) Found useless expression
     "B018",

tests/distributed/_test_distributed.py

@@ -79,7 +79,7 @@ def worker_train(self, i: int) -> subprocess.CompletedProcess:
         """Start the training process on the `i`-th worker."""
         config_path = TESTS_DIR / f"train{i}.conf"
         cmd = [self.executable, f"config={config_path}"]
-        return subprocess.run(cmd)
+        return subprocess.run(cmd, check=True)
 
     def _set_ports(self) -> None:
         """Randomly assign a port for training to each worker and save all ports to mlist.txt."""
@@ -145,7 +145,7 @@ def predict(self, predict_config: Dict[str, Any]) -> np.ndarray:
         with open(config_path, "wt") as file:
             _write_dict(self.predict_config, file)
         cmd = [self.executable, f"config={config_path}"]
-        result = subprocess.run(cmd)
+        result = subprocess.run(cmd, check=True)
         if result.returncode != 0:
             raise RuntimeError("Error in prediction")
         return np.loadtxt(str(TESTS_DIR / "predictions.txt"))