Merge branch 'master' into macos-version

.ci/conda-envs/ci-core.txt

@@ -18,7 +18,7 @@
 
 # direct imports
 cffi>=1.16
-dask>=2023.5.0
+dask>=2023.5.0,<2024.12
 joblib>=1.3.2
 matplotlib-base>=3.7.3
 numpy>=1.24.4

.ci/test-r-package-windows.ps1

@@ -171,7 +171,7 @@ Write-Output "Done installing Rtools"
 Write-Output "Installing CMake"
 Add-Type -AssemblyName System.IO.Compression.FileSystem
 [System.IO.Compression.ZipFile]::ExtractToDirectory("$env:CMAKE_PATH/cmake.zip", "$env:CMAKE_PATH") ; Assert-Output $?
-# Remove old CMake shiped with RTools
+# Remove old CMake shipped with RTools
 Remove-Item "$env:RTOOLS_MINGW_BIN/cmake.exe" -Force -ErrorAction Ignore
 Write-Output "Done installing CMake"
 

.ci/test-r-package.sh

@@ -20,12 +20,7 @@ fi
 
 # Get details needed for installing R components
 R_MAJOR_VERSION="${R_VERSION%.*}"
-if [[ "${R_MAJOR_VERSION}" == "3" ]]; then
-    export R_MAC_VERSION=3.6.3
-    export R_MAC_PKG_URL=${CRAN_MIRROR}/bin/macosx/R-${R_MAC_VERSION}.nn.pkg
-    export R_LINUX_VERSION="3.6.3-1bionic"
-    export R_APT_REPO="bionic-cran35/"
-elif [[ "${R_MAJOR_VERSION}" == "4" ]]; then
+if [[ "${R_MAJOR_VERSION}" == "4" ]]; then
     export R_MAC_VERSION=4.3.1
     export R_MAC_PKG_URL=${CRAN_MIRROR}/bin/macosx/big-sur-${ARCH}/base/R-${R_MAC_VERSION}-${ARCH}.pkg
     export R_LINUX_VERSION="4.3.1-1.2204.0"
@@ -108,16 +103,10 @@ if [[ $OS_NAME == "macos" ]]; then
     export R_TIDYCMD=/usr/local/bin/tidy
 fi
 
-# fix for issue where CRAN was not returning {evaluate}, {lattice}, or {waldo} when using R 3.6
-# "Warning: dependency ‘lattice’ is not available"
-if [[ "${R_MAJOR_VERSION}" == "3" ]]; then
-    Rscript --vanilla ./.ci/install-old-r-packages.R
-else
-    # {Matrix} needs {lattice}, so this needs to run before manually installing {Matrix}.
-    # This should be unnecessary on R >=4.4.0
-    # ref: https://github.com/microsoft/LightGBM/issues/6433
-    Rscript --vanilla -e "install.packages('lattice', repos = '${CRAN_MIRROR}', lib = '${R_LIB_PATH}')"
-fi
+# {Matrix} needs {lattice}, so this needs to run before manually installing {Matrix}.
+# This should be unnecessary on R >=4.4.0
+# ref: https://github.com/microsoft/LightGBM/issues/6433
+Rscript --vanilla -e "install.packages('lattice', repos = '${CRAN_MIRROR}', lib = '${R_LIB_PATH}')"
 
 # manually install {Matrix}, as {Matrix}=1.7-0 raised its R floor all the way to R 4.4.0
 # ref: https://github.com/microsoft/LightGBM/issues/6433

.github/workflows/lock.yml

@@ -39,7 +39,7 @@ jobs:
             This pull request has been automatically locked since there has not been any recent activity since it was closed.
             To start a new related discussion, open a new issue at https://github.com/microsoft/LightGBM/issues
             including a reference to this.
-          # what shoulld the locking status be?
+          # what should the locking status be?
           issue-lock-reason: 'resolved'
           pr-lock-reason: 'resolved'
           process-only: 'issues, prs'

.github/workflows/r_package.yml

@@ -14,10 +14,6 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  # https://github.com/actions/checkout/issues/1590#issuecomment-2207052044
-  #
-  # this could be removed (hopefully) when R 3.6 support is removed
-  ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
   # in CMake-driven builds, parallelize compilation
   CMAKE_BUILD_PARALLEL_LEVEL: 4
   # on Debian-based images, avoid interactive prompts
@@ -48,12 +44,6 @@ jobs:
           ################
           # CMake builds #
           ################
-          - os: ubuntu-latest
-            task: r-package
-            compiler: gcc
-            r_version: 3.6
-            build_type: cmake
-            container: 'ubuntu:18.04'
           - os: ubuntu-latest
             task: r-package
             compiler: gcc
@@ -174,19 +164,12 @@ jobs:
         run: |
           git config --global --add safe.directory "${GITHUB_WORKSPACE}"
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           fetch-depth: 5
           submodules: true
       - name: Install pandoc
         uses: r-lib/actions/setup-pandoc@v2
-        if: matrix.container != 'ubuntu:18.04'
-      # R 3.6 binary isn't easily available on Ubuntu 18.04,
-      # but setup-pandoc>=2.7.1 is uses a too-new glibc for it.
-      # ref: https://github.com/microsoft/LightGBM/issues/6298
-      - name: Install pandoc
-        uses: r-lib/actions/[email protected]
-        if: matrix.container == 'ubuntu:18.04'
       - name: Install tinytex
         if: startsWith(matrix.os, 'windows')
         uses: r-lib/actions/setup-tinytex@v2

.pre-commit-config.yaml

@@ -38,4 +38,10 @@ repos:
   - repo: https://github.com/shellcheck-py/shellcheck-py
     rev: v0.10.0.1
     hooks:
-    - id: shellcheck
+      - id: shellcheck
+  - repo: https://github.com/crate-ci/typos
+    rev: v1.23.2
+    hooks:
+      - id: typos
+        args: ["--force-exclude"]
+        exclude: (\.gitignore$)|(^\.editorconfig$)

.typos.toml

@@ -0,0 +1,21 @@
+default.extend-ignore-re = [
+  "/Ot",
+  "mis-alignment",
+  "mis-spelled",
+  "posix-seh-rt",
+]
+
+[default.extend-words]
+MAPE = "MAPE"
+datas = "datas"
+interprete = "interprete"
+mape = "mape"
+splitted = "splitted"
+
+[default.extend-identifiers]
+ERRORs = "ERRORs"
+GAM = "GAM"
+ND24s = "ND24s"
+WARNINGs = "WARNINGs"
+fullset = "fullset"
+thess = "thess"

CMakeLists.txt

@@ -5,7 +5,7 @@ option(USE_SWIG "Enable SWIG to generate Java API" OFF)
 option(USE_TIMETAG "Set to ON to output time costs" OFF)
 option(USE_CUDA "Enable CUDA-accelerated training " OFF)
 option(USE_DEBUG "Set to ON for Debug mode" OFF)
-option(USE_SANITIZER "Use santizer flags" OFF)
+option(USE_SANITIZER "Use sanitizer flags" OFF)
 set(
   ENABLED_SANITIZERS
   "address" "leak" "undefined"

R-package/R/lgb.Booster.R

@@ -1114,7 +1114,7 @@ predict.lgb.Booster <- function(object,
 #'
 #'          Requesting a different prediction type or passing parameters to \link{predict.lgb.Booster}
 #'          will cause it to ignore the fast-predict configuration and take the slow route instead
-#'          (but be aware that an existing configuration might not always be overriden by supplying
+#'          (but be aware that an existing configuration might not always be overridden by supplying
 #'          different parameters or prediction type, so make sure to check that the output is what
 #'          was expected when a prediction is to be made on a single row for something different than
 #'          what is configured).
@@ -1128,7 +1128,7 @@ predict.lgb.Booster <- function(object,
 #'          and as such, this function will produce an error if passing \code{csr=TRUE} and
 #'          \code{type = "contrib"} together.
 #' @inheritParams lgb_predict_shared_params
-#' @param model LighGBM model object (class \code{lgb.Booster}).
+#' @param model LightGBM model object (class \code{lgb.Booster}).
 #'
 #'              \bold{The object will be modified in-place}.
 #' @param csr Whether the prediction function is going to be called on sparse CSR inputs.

R-package/R/lgb.importance.R

@@ -9,7 +9,7 @@
 #'   \item{\code{Feature}: Feature names in the model.}
 #'   \item{\code{Gain}: The total gain of this feature's splits.}
 #'   \item{\code{Cover}: The number of observation related to this feature.}
-#'   \item{\code{Frequency}: The number of times a feature splited in trees.}
+#'   \item{\code{Frequency}: The number of times a feature split in trees.}
 #' }
 #'
 #' @examples

R-package/R/lgb.model.dt.tree.R

@@ -10,7 +10,7 @@
 #'        \emph{New in version 4.4.0}
 #'
 #' @return
-#' A \code{data.table} with detailed information about model trees' nodes and leafs.
+#' A \code{data.table} with detailed information about model trees' nodes and leaves.
 #'
 #' The columns of the \code{data.table} are:
 #'

R-package/R/lightgbm.R

@@ -139,7 +139,7 @@ NULL
 #'                    system, but be aware that getting the number of cores detected correctly requires package
 #'                    \code{RhpcBLASctl} to be installed.
 #'
-#'                    This parameter gets overriden by \code{num_threads} and its aliases under \code{params}
+#'                    This parameter gets overridden by \code{num_threads} and its aliases under \code{params}
 #'                    if passed there.
 #'
 #'                    \emph{New in version 4.0.0}

R-package/demo/cross_validation.R

@@ -51,7 +51,7 @@ logregobj <- function(preds, dtrain) {
 
 # User-defined evaluation function returns a pair (metric_name, result, higher_better)
 # NOTE: when you do customized loss function, the default prediction value is margin
-# This may make built-in evalution metric calculate wrong results
+# This may make built-in evaluation metric calculate wrong results
 # For example, we are doing logistic loss, the prediction is score before logistic transformation
 # Keep this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {

R-package/demo/early_stopping.R

@@ -29,7 +29,7 @@ logregobj <- function(preds, dtrain) {
 
 # User-defined evaluation function returns a pair (metric_name, result, higher_better)
 # NOTE: when you do customized loss function, the default prediction value is margin
-# This may make built-in evalution metric calculate wrong results
+# This may make built-in evaluation metric calculate wrong results
 # For example, we are doing logistic loss, the prediction is score before logistic transformation
 # The built-in evaluation error assumes input is after logistic transformation
 # Keep this in mind when you use the customization, and maybe you need write customized evaluation function

R-package/tests/testthat/test_basic.R

@@ -9,7 +9,7 @@ set.seed(708L)
 #               to an accumulator then returns the current value.
 #               This is used to mock the situation where an evaluation
 #               metric increases every iteration
-ACCUMULATOR_NAME <- "INCREASING_METRIC_ACUMULATOR"
+ACCUMULATOR_NAME <- "INCREASING_METRIC_ACCUMULATOR"
 assign(x = ACCUMULATOR_NAME, value = 0.0, envir = .GlobalEnv)
 
 .increasing_metric <- function(preds, dtrain) {
@@ -1777,7 +1777,7 @@ test_that("lgb.train() works with early stopping for regression with a metric th
     , early_stopping_rounds + 1L
   )
 
-  # Booster should understand thatt all three of these metrics should be minimized
+  # Booster should understand that all three of these metrics should be minimized
   eval_info <- bst$.__enclos_env__$private$get_eval_info()
   expect_identical(eval_info, c("mape", "rmse", "l1"))
   expect_identical(

R-package/tests/testthat/test_custom_objective.R

@@ -14,7 +14,7 @@ logregobj <- function(preds, dtrain) {
 
 # User-defined evaluation function returns a pair (metric_name, result, higher_better)
 # NOTE: when you do customized loss function, the default prediction value is margin
-# This may make built-in evalution metric calculate wrong results
+# This may make built-in evaluation metric calculate wrong results
 # Keep this in mind when you use the customization, and maybe you need write customized evaluation function
 evalerror <- function(preds, dtrain) {
   labels <- get_field(dtrain, "label")

R-package/tests/testthat/test_lgb.interprete.R

@@ -5,7 +5,7 @@
     log(x / (1.0 - x))
 }
 
-test_that("lgb.intereprete works as expected for binary classification", {
+test_that("lgb.interprete works as expected for binary classification", {
     data(agaricus.train, package = "lightgbm")
     train <- agaricus.train
     dtrain <- lgb.Dataset(train$data, label = train$label)

R-package/tests/testthat/test_lgb.plot.interpretation.R

@@ -5,7 +5,7 @@
     log(x / (1.0 - x))
 }
 
-test_that("lgb.plot.interepretation works as expected for binary classification", {
+test_that("lgb.plot.interpretation works as expected for binary classification", {
     data(agaricus.train, package = "lightgbm")
     train <- agaricus.train
     dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -57,7 +57,7 @@ test_that("lgb.plot.interepretation works as expected for binary classification"
     expect_null(plot_res)
 })
 
-test_that("lgb.plot.interepretation works as expected for multiclass classification", {
+test_that("lgb.plot.interpretation works as expected for multiclass classification", {
     data(iris)
 
     # We must convert factors to numeric