Merge branch 'master' into googletest-version

microsoft · Dec 28, 2023 · 83b4fb4 · 83b4fb4
2 parents 2fc28d1 + 4588d64
commit 83b4fb4
Show file tree

Hide file tree

Showing 90 changed files with 1,031 additions and 554 deletions.
diff --git a/.appveyor.yml b/.appveyor.yml
@@ -1,4 +1,4 @@
-version: 4.1.0.99.{build}
+version: 4.2.0.99.{build}
 
 image: Visual Studio 2015
 platform: x64

diff --git a/.ci/lint-cpp.sh b/.ci/lint-cpp.sh
@@ -30,8 +30,7 @@ get_omp_pragmas_without_num_threads() {
         --include='*.h' \
         --include='*.hpp' \
         'pragma omp parallel' \
-    | grep -v ' num_threads' \
-    | grep -v 'openmp_wrapper.h'
+    | grep -v ' num_threads'
 }
 PROBLEMATIC_LINES=$(
     get_omp_pragmas_without_num_threads

diff --git a/.ci/setup.sh b/.ci/setup.sh
@@ -54,6 +54,14 @@ else  # Linux
             sudo apt-get install --no-install-recommends -y \
                 clang \
                 libomp-dev
+        elif [[ $COMPILER == "clang-17" ]]; then
+            sudo apt-get install wget
+            wget -qO- https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc
+            sudo apt-add-repository deb http://apt.llvm.org/jammy/ llvm-toolchain-jammy-17 main
+            sudo apt-add-repository deb-src http://apt.llvm.org/jammy/ llvm-toolchain-jammy-17 main
+            sudo apt-get update
+            sudo apt-get install -y clang-17
+            sudo apt-get install --no-install-recommends -y libomp-17-dev
         fi
 
         export LANG="en_US.UTF-8"

diff --git a/.ci/test.sh b/.ci/test.sh
@@ -6,6 +6,9 @@ if [[ $OS_NAME == "macos" ]] && [[ $COMPILER == "gcc" ]]; then
 elif [[ $OS_NAME == "linux" ]] && [[ $COMPILER == "clang" ]]; then
     export CXX=clang++
     export CC=clang
+elif [[ $OS_NAME == "linux" ]] && [[ $COMPILER == "clang-17" ]]; then
+    export CXX=clang++-17
+    export CC=clang-17
 fi
 
 if [[ $IN_UBUNTU_BASE_CONTAINER == "true" ]]; then

diff --git a/.ci/test_r_package_valgrind.sh b/.ci/test_r_package_valgrind.sh
@@ -1,9 +1,11 @@
 #!/bin/bash
 
-RDscriptvalgrind -e "install.packages(c('R6', 'data.table', 'jsonlite', 'knitr', 'Matrix', 'RhpcBLASctl', 'rmarkdown', 'testthat'), repos = 'https://cran.rstudio.com', Ncpus = parallel::detectCores())" || exit -1
+RDscriptvalgrind -e "install.packages(c('R6', 'data.table', 'jsonlite', 'Matrix', 'RhpcBLASctl', 'testthat'), repos = 'https://cran.rstudio.com')" || exit -1
 sh build-cran-package.sh \
   --r-executable=RDvalgrind \
+  --no-build-vignettes \
   || exit -1
+
 RDvalgrind CMD INSTALL --preclean --install-tests lightgbm_*.tar.gz || exit -1
 
 cd R-package/tests
@@ -68,7 +70,7 @@ bytes_possibly_lost=$(
     | tr -d ","
 )
 echo "valgrind found ${bytes_possibly_lost} bytes possibly lost"
-if [[ ${bytes_possibly_lost} -gt 352 ]]; then
+if [[ ${bytes_possibly_lost} -gt 1056 ]]; then
     exit -1
 fi
 

diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS
@@ -7,4 +7,4 @@
 # offer a reasonable automatic best-guess
 
 # catch-all rule (this only gets matched if no rules below match)
-*    @guolinke @jameslamb @shiyu1994 @jmoralez
+*    @guolinke @jameslamb @shiyu1994 @jmoralez @borchero
diff --git a/.vsts-ci.yml b/.vsts-ci.yml
@@ -34,7 +34,7 @@ jobs:
     SETUP_CONDA: 'false'
     OS_NAME: 'linux'
     PRODUCES_ARTIFACTS: 'true'
-  pool: sh-ubuntu
+  pool: sh-mariner
   container: linux-artifact-builder
   strategy:
     matrix:
@@ -82,12 +82,12 @@ jobs:
 - job: Linux_latest
 ###########################################
   variables:
-    COMPILER: clang
+    COMPILER: clang-17
     DEBIAN_FRONTEND: 'noninteractive'
     IN_UBUNTU_BASE_CONTAINER: 'true'
     OS_NAME: 'linux'
     SETUP_CONDA: 'true'
-  pool: sh-ubuntu
+  pool: sh-mariner
   container: ubuntu-latest
   strategy:
     matrix:

diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -439,6 +439,7 @@ file(
       src/objective/*.cpp
       src/network/*.cpp
       src/treelearner/*.cpp
+      src/utils/*.cpp
 if(USE_CUDA)
       src/treelearner/*.cu
       src/boosting/cuda/*.cpp
@@ -647,6 +648,7 @@ if(BUILD_CPP_TEST)
 
   file(GLOB CPP_TEST_SOURCES tests/cpp_tests/*.cpp)
   if(MSVC)
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /permissive-")
     set(
       CompilerFlags
         CMAKE_CXX_FLAGS

diff --git a/R-package/DESCRIPTION b/R-package/DESCRIPTION
@@ -4,10 +4,10 @@ Title: Light Gradient Boosting Machine
 Version: ~~VERSION~~
 Date: ~~DATE~~
 Authors@R: c(
-    person("Yu", "Shi", email = "[email protected]", role = c("aut", "cre")),
+    person("Yu", "Shi", email = "[email protected]", role = c("aut")),
     person("Guolin", "Ke", email = "[email protected]", role = c("aut")),
     person("Damien", "Soukhavong", email = "[email protected]", role = c("aut")),
-    person("James", "Lamb", email="[email protected]", role = c("aut")),
+    person("James", "Lamb", email="[email protected]", role = c("aut", "cre")),
     person("Qi", "Meng", role = c("aut")),
     person("Thomas", "Finley", role = c("aut")),
     person("Taifeng", "Wang", role = c("aut")),

diff --git a/R-package/NAMESPACE b/R-package/NAMESPACE
@@ -9,6 +9,7 @@ S3method(print,lgb.Booster)
 S3method(set_field,lgb.Dataset)
 S3method(slice,lgb.Dataset)
 S3method(summary,lgb.Booster)
+export(getLGBMthreads)
 export(get_field)
 export(lgb.Dataset)
 export(lgb.Dataset.construct)
@@ -33,8 +34,7 @@ export(lgb.restore_handle)
 export(lgb.save)
 export(lgb.train)
 export(lightgbm)
-export(readRDS.lgb.Booster)
-export(saveRDS.lgb.Booster)
+export(setLGBMthreads)
 export(set_field)
 export(slice)
 import(methods)

diff --git a/R-package/R/lgb.Booster.R b/R-package/R/lgb.Booster.R
@@ -917,6 +917,8 @@ NULL
 #'         the factor levels not being present in the output.
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1082,6 +1084,8 @@ predict.lgb.Booster <- function(object,
 #'         \link{predict.lgb.Booster}.
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' library(lightgbm)
 #' data(mtcars)
 #' X <- as.matrix(mtcars[, -1L])
@@ -1224,6 +1228,8 @@ summary.lgb.Booster <- function(object, ...) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1289,6 +1295,8 @@ lgb.load <- function(filename = NULL, model_str = NULL) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -1346,6 +1354,8 @@ lgb.save <- function(booster, filename, num_iteration = NULL) {
 #' @examples
 #' \donttest{
 #' library(lightgbm)
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1396,6 +1406,8 @@ lgb.dump <- function(booster, num_iteration = NULL) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' # train a regression model
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train

diff --git a/R-package/R/lgb.Dataset.R b/R-package/R/lgb.Dataset.R
@@ -780,6 +780,8 @@ Dataset <- R6::R6Class(
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -837,6 +839,8 @@ lgb.Dataset <- function(data,
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -913,6 +917,8 @@ lgb.Dataset.create.valid <- function(dataset,
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -942,6 +948,8 @@ lgb.Dataset.construct <- function(dataset) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -975,6 +983,8 @@ dim.lgb.Dataset <- function(x) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1045,6 +1055,8 @@ dimnames.lgb.Dataset <- function(x) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1089,6 +1101,8 @@ slice.lgb.Dataset <- function(dataset, idxset) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1138,6 +1152,8 @@ get_field.lgb.Dataset <- function(dataset, field_name) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1177,6 +1193,8 @@ set_field.lgb.Dataset <- function(dataset, field_name, data) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
@@ -1207,6 +1225,8 @@ lgb.Dataset.set.categorical <- function(dataset, categorical_feature) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' # create training Dataset
 #' data(agaricus.train, package ="lightgbm")
 #' train <- agaricus.train
@@ -1240,6 +1260,8 @@ lgb.Dataset.set.reference <- function(dataset, reference) {
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)

diff --git a/R-package/R/lgb.cv.R b/R-package/R/lgb.cv.R
@@ -51,6 +51,8 @@ CVBooster <- R6::R6Class(
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)

diff --git a/R-package/R/lgb.importance.R b/R-package/R/lgb.importance.R
@@ -14,6 +14,8 @@
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)

diff --git a/R-package/R/lgb.interprete.R b/R-package/R/lgb.interprete.R
@@ -17,6 +17,8 @@
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' Logit <- function(x) log(x / (1.0 - x))
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train

diff --git a/R-package/R/lgb.model.dt.tree.R b/R-package/R/lgb.model.dt.tree.R
@@ -29,6 +29,8 @@
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)

diff --git a/R-package/R/lgb.plot.importance.R b/R-package/R/lgb.plot.importance.R
@@ -19,6 +19,8 @@
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)

diff --git a/R-package/R/lgb.plot.interpretation.R b/R-package/R/lgb.plot.interpretation.R
@@ -16,6 +16,8 @@
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' Logit <- function(x) {
 #'   log(x / (1.0 - x))
 #' }

diff --git a/R-package/R/lgb.restore_handle.R b/R-package/R/lgb.restore_handle.R
@@ -16,7 +16,10 @@
 #' @return \code{lgb.Booster} (the same `model` object that was passed as input, invisibly).
 #' @seealso \link{lgb.make_serializable}, \link{lgb.drop_serialized}.
 #' @examples
+#' \donttest{
 #' library(lightgbm)
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data("agaricus.train")
 #' model <- lightgbm(
 #'   agaricus.train$data
@@ -33,6 +36,7 @@
 #' model_new$check_null_handle()
 #' lgb.restore_handle(model_new)
 #' model_new$check_null_handle()
+#' }
 #' @export
 lgb.restore_handle <- function(model) {
   if (!.is_Booster(x = model)) {

diff --git a/R-package/R/lgb.train.R b/R-package/R/lgb.train.R
@@ -19,6 +19,8 @@
 #'
 #' @examples
 #' \donttest{
+#' \dontshow{setLGBMthreads(2L)}
+#' \dontshow{data.table::setDTthreads(1L)}
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)