Merge branch 'master' into ci/yamllint

.pre-commit-config.yaml

@@ -22,15 +22,9 @@ repos:
     hooks:
       - id: yamllint
         args: ["--strict"]
-  - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
-    hooks:
-      - id: isort
-        name: isort (python)
-        args: ["--settings-path", "python-package/pyproject.toml"]
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.7.0
+    rev: v0.8.3
     hooks:
       # Run the linter.
       - id: ruff
@@ -45,7 +39,7 @@ repos:
     hooks:
       - id: shellcheck
   - repo: https://github.com/crate-ci/typos
-    rev: v1.23.2
+    rev: v1.28.3
     hooks:
       - id: typos
         args: ["--force-exclude"]

R-package/tests/testthat/test_basic.R

@@ -2345,7 +2345,7 @@ test_that("early stopping works with lgb.cv()", {
   # never changes, its first iteration was the best oone
   expect_equal(bst$best_iter, 1L)
 
-  # best_score should be taken from the first metri
+  # best_score should be taken from the first metric
   expect_equal(bst$best_score, 0.2)
 
   # early stopping should have happened, since constant_metric was the first

examples/python-guide/notebooks/interactive_plot_example.ipynb

@@ -30,7 +30,7 @@
     "try:\n",
     "    # To enable interactive mode you should install ipywidgets\n",
     "    # https://github.com/jupyter-widgets/ipywidgets\n",
-    "    from ipywidgets import interact, SelectMultiple\n",
+    "    from ipywidgets import SelectMultiple, interact\n",
     "\n",
     "    INTERACTIVE = True\n",
     "except ImportError:\n",

python-package/lightgbm/basic.py

@@ -1291,10 +1291,7 @@ def __inner_predict_np2d(
         predict_type: int,
         preds: Optional[np.ndarray],
     ) -> Tuple[np.ndarray, int]:
-        if mat.dtype == np.float32 or mat.dtype == np.float64:
-            data = np.asarray(mat.reshape(mat.size), dtype=mat.dtype)
-        else:  # change non-float data to float data, need to copy
-            data = np.array(mat.reshape(mat.size), dtype=np.float32)
+        data, layout = _np2d_to_np1d(mat)
         ptr_data, type_ptr_data, _ = _c_float_array(data)
         n_preds = self.__get_num_preds(
             start_iteration=start_iteration,
@@ -1314,7 +1311,7 @@ def __inner_predict_np2d(
                 ctypes.c_int(type_ptr_data),
                 ctypes.c_int32(mat.shape[0]),
                 ctypes.c_int32(mat.shape[1]),
-                ctypes.c_int(_C_API_IS_ROW_MAJOR),
+                ctypes.c_int(layout),
                 ctypes.c_int(predict_type),
                 ctypes.c_int(start_iteration),
                 ctypes.c_int(num_iteration),
@@ -2507,13 +2504,13 @@ def _compare_params_for_warning(
         compare_result : bool
           Returns whether two dictionaries with params are equal.
         """
-        for k in other_params:
+        for k, v in other_params.items():
             if k not in ignore_keys:
-                if k not in params or params[k] != other_params[k]:
+                if k not in params or params[k] != v:
                     return False
-        for k in params:
+        for k, v in params.items():
             if k not in ignore_keys:
-                if k not in other_params or params[k] != other_params[k]:
+                if k not in other_params or v != other_params[k]:
                     return False
         return True
 

python-package/pyproject.toml

@@ -84,17 +84,6 @@ minimum-version = "build-system.requires"
 
 # end:build-system
 
-[tool.isort]
-include_trailing_comma = true
-line_length = 120
-# "vertical hanging indent", to match what ruff-format does
-# ref: https://pycqa.github.io/isort/docs/configuration/multi_line_output_modes.html#3-vertical-hanging-indent
-multi_line_output = 3
-skip_glob = [
-    "*/external_libs/*",
-    "*/lightgbm-python/*",
-]
-
 [tool.mypy]
 disallow_untyped_defs = true
 exclude = 'build/*|compile/*|docs/*|examples/*|external_libs/*|lightgbm-python/*|tests/*'
@@ -140,7 +129,7 @@ ignore = [
     "PLR1714",
     # (pylint) Magic value used in comparison
     "PLR2004",
-    # (pylint) for loop veriable overwritten by assignment target
+    # (pylint) for loop variable overwritten by assignment target
     "PLW2901",
     # (pylint) use 'elif' instead of 'else' then 'if', to reduce indentation
     "PLR5501"
@@ -152,10 +141,12 @@ select = [
     "C4",
     # pydocstyle
     "D",
-    # pycodestyle
+    # pycodestyle (errors)
     "E",
     # pyflakes
     "F",
+    # isort
+    "I",
     # NumPy-specific rules
     "NPY",
     # pylint
@@ -166,11 +157,13 @@ select = [
     "SIM401",
     # flake8-print
     "T",
+    # pycodestyle (warnings)
+    "W",
 ]
 
 [tool.ruff.lint.per-file-ignores]
 "docs/conf.py" = [
-    # (flake8-bugbear) raise exceptions with "raise ... from errr"
+    # (flake8-bugbear) raise exceptions with "raise ... from err"
     "B904",
     # (flake8-print) flake8-print
     "T"
@@ -196,3 +189,6 @@ select = [
 
 [tool.ruff.lint.pydocstyle]
 convention = "numpy"
+
+[tool.ruff.lint.isort]
+known-first-party = ["lightgbm"]

src/objective/rank_objective.hpp

@@ -204,7 +204,7 @@ class LambdarankNDCG : public RankingObjective {
     }
     const double worst_score = score[sorted_idx[worst_idx]];
     double sum_lambdas = 0.0;
-    // start accmulate lambdas by pairs that contain at least one document above truncation level
+    // start accumulate lambdas by pairs that contain at least one document above truncation level
     for (data_size_t i = 0; i < cnt - 1 && i < truncation_level_; ++i) {
       if (score[sorted_idx[i]] == kMinScore) { continue; }
       for (data_size_t j = i + 1; j < cnt; ++j) {

src/treelearner/kernels/histogram_16_64_256.cu

@@ -150,7 +150,7 @@ __global__ void KERNEL_NAME(const uchar* feature_data_base,
     // size of threads that process this feature4
     const unsigned int subglobal_size = lsize * (1 << power_feature_workgroups);
 
-    // equavalent thread ID in this subgroup for this feature4
+    // equivalent thread ID in this subgroup for this feature4
     const unsigned int subglobal_tid  = gtid - feature_id * subglobal_size;
 
 

tests/python_package_test/test_engine.py

@@ -4611,3 +4611,18 @@ def test_bagging_by_query_in_lambdarank():
     ndcg_score_no_bagging_by_query = gbm_no_bagging_by_query.best_score["valid_0"]["ndcg@5"]
     assert ndcg_score_bagging_by_query >= ndcg_score - 0.1
     assert ndcg_score_no_bagging_by_query >= ndcg_score - 0.1
+
+
+def test_equal_predict_from_row_major_and_col_major_data():
+    X_row, y = make_synthetic_regression()
+    assert X_row.flags["C_CONTIGUOUS"] and not X_row.flags["F_CONTIGUOUS"]
+    ds = lgb.Dataset(X_row, y)
+    params = {"num_leaves": 8, "verbose": -1}
+    bst = lgb.train(params, ds, num_boost_round=5)
+    preds_row = bst.predict(X_row)
+
+    X_col = np.asfortranarray(X_row)
+    assert X_col.flags["F_CONTIGUOUS"] and not X_col.flags["C_CONTIGUOUS"]
+    preds_col = bst.predict(X_col)
+
+    np.testing.assert_allclose(preds_row, preds_col)