[ci] update pre-commit versions, add some pixi things to config files (#6986)

.gitignore

@@ -466,3 +466,6 @@ dask-worker-space/
 
 # hipify-perl -inplace leaves behind *.prehip files
 *.prehip
+
+# pixi environments
+.pixi

.pre-commit-config.yaml

@@ -18,13 +18,13 @@ repos:
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/adrienverge/yamllint
-    rev: v1.35.1
+    rev: v1.37.1
     hooks:
       - id: yamllint
         args: ["--strict"]
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.9.10
+    rev: v0.12.5
     hooks:
       # Run the linter.
       - id: ruff
@@ -39,13 +39,13 @@ repos:
     hooks:
       - id: shellcheck
   - repo: https://github.com/crate-ci/typos
-    rev: v1.30.2
+    rev: v1.34.0
     hooks:
       - id: typos
         args: ["--force-exclude"]
         exclude: (\.gitignore$)|(^\.editorconfig$)
   - repo: https://github.com/henryiii/validate-pyproject-schema-store
-    rev: 2025.03.10
+    rev: 2025.07.14
     hooks:
       - id: validate-pyproject
         files: python-package/pyproject.toml$

biome.json

 {
     "files": {
-        "ignore": [".mypy_cache/"]
+        "ignore": [".mypy_cache/", ".pixi/"]
     },
     "formatter": {
         "enabled": true,

docs/conf.py

@@ -67,7 +67,7 @@ class IgnoredDirective(Directive):
 
 # -- General configuration ------------------------------------------------
 
-os.environ["LIGHTGBM_BUILD_DOC"] = "1"
+os.environ["LIGHTGBM_BUILD_DOC"] = "True"
 C_API = os.environ.get("C_API", "").lower().strip() != "no"
 RTD = bool(os.environ.get("READTHEDOCS", ""))
 RTD_VERSION = os.environ.get("READTHEDOCS_VERSION", "stable")

python-package/lightgbm/basic.py

@@ -287,7 +287,7 @@ def _log_callback(msg: bytes) -> None:
 
 
 # connect the Python logger to logging in lib_lightgbm
-if not environ.get("LIGHTGBM_BUILD_DOC", False):
+if environ.get("LIGHTGBM_BUILD_DOC", "False") != "True":
     _LIB.LGBM_GetLastError.restype = ctypes.c_char_p
     callback = ctypes.CFUNCTYPE(None, ctypes.c_char_p)
     _LIB.callback = callback(_log_callback)  # type: ignore[attr-defined]
@@ -840,7 +840,7 @@ def _data_from_pandas(
         for col, category in zip(cat_cols, pandas_categorical):
             if list(data[col].cat.categories) != list(category):
                 data[col] = data[col].cat.set_categories(category)
-    if len(cat_cols):  # cat_cols is list
+    if cat_cols:  # cat_cols is list
         data[cat_cols] = data[cat_cols].apply(lambda x: x.cat.codes).replace({-1: np.nan})
 
     # use cat cols from DataFrame

python-package/lightgbm/callback.py

@@ -74,7 +74,7 @@ class CallbackEnv:
 def _is_using_cv(env: CallbackEnv) -> bool:
     """Check if model in callback env is a CVBooster."""
     # this import is here to avoid a circular import
-    from .engine import CVBooster
+    from .engine import CVBooster  # noqa: PLC0415
 
     return isinstance(env.model, CVBooster)
 

python-package/lightgbm/compat.py

@@ -52,7 +52,7 @@ try:
             #  * lightgbm cannot be used with scikit-learn versions older than that
             #  * this validate_data() re-implementation will not be called in scikit-learn>=1.6
             #
-            from sklearn.utils.validation import _num_features
+            from sklearn.utils.validation import _num_features  # noqa: PLC0415
 
             # _num_features() raises a TypeError on 1-dimensional input. That's a problem
             # because scikit-learn's 'check_fit1d' estimator check sets that expectation that

python-package/lightgbm/dask.py

@@ -769,7 +769,7 @@ def _train(
                 )
                 raise LightGBMError(msg)
 
-            worker_address_to_port = {address: local_listen_port for address in worker_addresses}
+            worker_address_to_port = dict.fromkeys(worker_addresses, local_listen_port)
         else:
             _log_info("Finding random open ports for workers")
             worker_to_socket_future, worker_address_to_port = _assign_open_ports_to_workers(

python-package/lightgbm/libpath.py

@@ -41,7 +41,7 @@ def _find_lib_path() -> List[str]:
 
 # we don't need lib_lightgbm while building docs
 _LIB: ctypes.CDLL
-if environ.get("LIGHTGBM_BUILD_DOC", False):
+if environ.get("LIGHTGBM_BUILD_DOC", "False") == "True":
     from unittest.mock import Mock  # isort: skip
 
     _LIB = Mock(ctypes.CDLL)  # type: ignore

python-package/lightgbm/plotting.py

@@ -104,7 +104,7 @@ def plot_importance(
         The plot with model's feature importances.
     """
     if MATPLOTLIB_INSTALLED:
-        import matplotlib.pyplot as plt
+        import matplotlib.pyplot as plt  # noqa: PLC0415
     else:
         raise ImportError("You must install matplotlib and restart your session to plot importance.")
 
@@ -235,8 +235,8 @@ def plot_split_value_histogram(
         The plot with specified model's feature split value histogram.
     """
     if MATPLOTLIB_INSTALLED:
-        import matplotlib.pyplot as plt
-        from matplotlib.ticker import MaxNLocator
+        import matplotlib.pyplot as plt  # noqa: PLC0415
+        from matplotlib.ticker import MaxNLocator  # noqa: PLC0415
     else:
         raise ImportError("You must install matplotlib and restart your session to plot split value histogram.")
 
@@ -342,7 +342,7 @@ def plot_metric(
         The plot with metric's history over the training.
     """
     if MATPLOTLIB_INSTALLED:
-        import matplotlib.pyplot as plt
+        import matplotlib.pyplot as plt  # noqa: PLC0415
     else:
         raise ImportError("You must install matplotlib and restart your session to plot metric.")
 
@@ -468,7 +468,7 @@ def _to_graphviz(
       - https://graphviz.readthedocs.io/en/stable/api.html#digraph
     """
     if GRAPHVIZ_INSTALLED:
-        from graphviz import Digraph
+        from graphviz import Digraph  # noqa: PLC0415
     else:
         raise ImportError("You must install graphviz and restart your session to plot tree.")
 
@@ -812,8 +812,8 @@ def plot_tree(
         The plot with single tree.
     """
     if MATPLOTLIB_INSTALLED:
-        import matplotlib.image
-        import matplotlib.pyplot as plt
+        import matplotlib.image  # noqa: PLC0415
+        import matplotlib.pyplot as plt  # noqa: PLC0415
     else:
         raise ImportError("You must install matplotlib and restart your session to plot tree.")
 

src/io/cuda/cuda_column_data.cpp

@@ -135,7 +135,7 @@ void CUDAColumnData::Init(const int num_columns,
         } else if (bit_type == 32) {
           InitOneColumnData<false, false, uint32_t>(column_data[column_index], nullptr, &data_by_column_[column_index]);
         } else {
-          Log::Fatal("Unknow column bit type %d", bit_type);
+          Log::Fatal("Unknown column bit type %d", bit_type);
         }
       } else {
         // is sparse column
@@ -146,7 +146,7 @@ void CUDAColumnData::Init(const int num_columns,
         } else if (bit_type == 32) {
           InitOneColumnData<true, false, uint32_t>(nullptr, column_bin_iterator[column_index], &data_by_column_[column_index]);
         } else {
-          Log::Fatal("Unknow column bit type %d", bit_type);
+          Log::Fatal("Unknown column bit type %d", bit_type);
         }
       }
       OMP_LOOP_EX_END();

src/io/cuda/cuda_row_data.cpp

@@ -105,7 +105,7 @@ void CUDARowData::Init(const Dataset* train_data, TrainingShareStates* train_sha
           &cuda_row_ptr_uint64_t_,
           &cuda_partition_ptr_uint64_t_);
       } else {
-        Log::Fatal("Unknow data ptr bit type %d", row_ptr_bit_type_);
+        Log::Fatal("Unknown data ptr bit type %d", row_ptr_bit_type_);
       }
     }
   } else if (bit_type_ == 16) {
@@ -136,7 +136,7 @@ void CUDARowData::Init(const Dataset* train_data, TrainingShareStates* train_sha
           &cuda_row_ptr_uint64_t_,
           &cuda_partition_ptr_uint64_t_);
       } else {
-        Log::Fatal("Unknow data ptr bit type %d", row_ptr_bit_type_);
+        Log::Fatal("Unknown data ptr bit type %d", row_ptr_bit_type_);
       }
     }
   } else if (bit_type_ == 32) {
@@ -167,11 +167,11 @@ void CUDARowData::Init(const Dataset* train_data, TrainingShareStates* train_sha
           &cuda_row_ptr_uint64_t_,
           &cuda_partition_ptr_uint64_t_);
       } else {
-        Log::Fatal("Unknow data ptr bit type %d", row_ptr_bit_type_);
+        Log::Fatal("Unknown data ptr bit type %d", row_ptr_bit_type_);
       }
     }
   } else {
-    Log::Fatal("Unknow bit type = %d", bit_type_);
+    Log::Fatal("Unknown bit type = %d", bit_type_);
   }
   SynchronizeCUDADevice(__FILE__, __LINE__);
 }

tests/python_package_test/test_sklearn.py

@@ -1730,12 +1730,13 @@ def test_training_succeeds_when_data_is_dataframe_and_label_is_column_array(task
     y_col_array = y.reshape(-1, 1)
     params = {"n_estimators": 1, "num_leaves": 3, "random_state": 0}
     model_factory = task_to_model_factory[task]
-    with pytest.warns(UserWarning, match="column-vector"):
-        if task == "ranking":
-            model_1d = model_factory(**params).fit(X, y, group=g)
+    if task == "ranking":
+        model_1d = model_factory(**params).fit(X, y, group=g)
+        with pytest.warns(UserWarning, match="column-vector"):
             model_2d = model_factory(**params).fit(X, y_col_array, group=g)
-        else:
-            model_1d = model_factory(**params).fit(X, y)
+    else:
+        model_1d = model_factory(**params).fit(X, y)
+        with pytest.warns(UserWarning, match="column-vector"):
             model_2d = model_factory(**params).fit(X, y_col_array)
 
     preds_1d = model_1d.predict(X)