Merge branch 'master' into ci/cran-asan

CMakeLists.txt

@@ -485,7 +485,7 @@ if(BUILD_CPP_TEST)
     FetchContent_Declare(
       googletest
       GIT_REPOSITORY https://github.com/google/googletest.git
-      GIT_TAG        release-1.10.0
+      GIT_TAG        release-1.11.0
     )
     FetchContent_MakeAvailable(googletest)
     add_library(GTest::GTest ALIAS gtest)

R-package/R/lgb.Booster.R

@@ -76,6 +76,8 @@ Booster <- R6::R6Class(
             stop("lgb.Booster: Can only use a string as model file path")
           }
 
+          modelfile <- path.expand(modelfile)
+
           # Create booster from model
           handle <- .Call(
             LGBM_BoosterCreateFromModelfile_R
@@ -425,6 +427,8 @@ Booster <- R6::R6Class(
         num_iteration <- self$best_iter
       }
 
+      filename <- path.expand(filename)
+
       .Call(
         LGBM_BoosterSaveModel_R
         , private$handle
@@ -857,6 +861,7 @@ lgb.load <- function(filename = NULL, model_str = NULL) {
     if (!is.character(filename)) {
       stop("lgb.load: filename should be character")
     }
+    filename <- path.expand(filename)
     if (!file.exists(filename)) {
       stop(sprintf("lgb.load: file '%s' passed to filename does not exist", filename))
     }
@@ -917,6 +922,7 @@ lgb.save <- function(booster, filename, num_iteration = NULL) {
   if (!(is.character(filename) && length(filename) == 1L)) {
     stop("lgb.save: filename should be a string")
   }
+  filename <- path.expand(filename)
 
   # Store booster
   return(

R-package/R/lgb.Dataset.R

@@ -243,7 +243,7 @@ Dataset <- R6::R6Class(
 
           handle <- .Call(
             LGBM_DatasetCreateFromFile_R
-            , private$raw_data
+            , path.expand(private$raw_data)
             , params_str
             , ref_handle
           )
@@ -742,7 +742,7 @@ Dataset <- R6::R6Class(
       .Call(
         LGBM_DatasetSaveBinary_R
         , private$handle
-        , fname
+        , path.expand(fname)
       )
       return(invisible(self))
     }

R-package/R/lgb.Predictor.R

@@ -35,7 +35,7 @@ Predictor <- R6::R6Class(
         # Create handle on it
         handle <- .Call(
           LGBM_BoosterCreateFromModelfile_R
-          , modelfile
+          , path.expand(modelfile)
         )
         private$need_free_handle <- TRUE
 
@@ -96,6 +96,8 @@ Predictor <- R6::R6Class(
       # Check if data is a file name and not a matrix
       if (identical(class(data), "character") && length(data) == 1L) {
 
+        data <- path.expand(data)
+
         # Data is a filename, create a temporary file with a "lightgbm_" pattern in it
         tmp_filename <- tempfile(pattern = "lightgbm_")
         on.exit(unlink(tmp_filename), add = TRUE)

R-package/pkgdown/_pkgdown.yml

@@ -17,18 +17,21 @@ development:
   mode: unreleased
 
 authors:
+  Yu Shi:
+    href: https://github.com/shiyu1994
+    html: <img src="https://avatars.githubusercontent.com/u/14541765?s=400&v=4" height="48" /> Yu Shi
   Guolin Ke:
     href: https://github.com/guolinke
-    html: <img src="https://avatars0.githubusercontent.com/u/16040950?s=400&v=4" height="48" /> Guolin Ke
+    html: <img src="https://avatars.githubusercontent.com/u/16040950?s=400&v=4" height="48" /> Guolin Ke
   Damien Soukhavong:
     href: https://github.com/Laurae2
-    html: <img src="https://avatars1.githubusercontent.com/u/9083669?s=460&v=4" height="48" /> Damien Soukhavong
+    html: <img src="https://avatars.githubusercontent.com/u/9083669?s=400&v=4" height="48" /> Damien Soukhavong
   Yachen Yan:
     href: https://github.com/yanyachen
-    html: <img src="https://avatars1.githubusercontent.com/u/6893682?s=460&v=4" height="48" /> Yachen Yan
+    html: <img src="https://avatars.githubusercontent.com/u/6893682?s=400&v=4" height="48" /> Yachen Yan
   James Lamb:
     href: https://github.com/jameslamb
-    html: <img src="https://avatars1.githubusercontent.com/u/7608904?s=400&v=4" height="48" /> James Lamb
+    html: <img src="https://avatars.githubusercontent.com/u/7608904?s=400&v=4" height="48" /> James Lamb
 
 navbar:
   title: LightGBM

docs/conf.py

@@ -221,6 +221,7 @@ def generate_doxygen_xml(app: Sphinx) -> None:
         "MACRO_EXPANSION=YES",
         "EXPAND_ONLY_PREDEF=NO",
         "SKIP_FUNCTION_MACROS=NO",
+        "PREDEFINED=__cplusplus",
         "SORT_BRIEF_DOCS=YES",
         "WARN_AS_ERROR=YES",
     ]

include/LightGBM/c_api.h

@@ -1329,19 +1329,25 @@ LIGHTGBM_C_EXPORT int LGBM_NetworkInitWithFunctions(int num_machines,
                                                     void* allgather_ext_fun);
 
 #if !defined(__cplusplus) && (!defined(__STDC__) || (__STDC_VERSION__ < 199901L))
-#define INLINE_FUNCTION /*!< \brief inline specifier no-op in C using standards before C99. */
+/*! \brief Inline specifier no-op in C using standards before C99. */
+#define INLINE_FUNCTION
 #else
-#define INLINE_FUNCTION inline /*!< \brief Inline specifier. */
+/*! \brief Inline specifier. */
+#define INLINE_FUNCTION inline
 #endif
 
 #if !defined(__cplusplus) && (!defined(__STDC__) || (__STDC_VERSION__ < 201112L))
-#define THREAD_LOCAL  /*!< \brief Thread local specifier no-op in C using standards before C11. */
+/*! \brief Thread local specifier no-op in C using standards before C11. */
+#define THREAD_LOCAL
 #elif !defined(__cplusplus)
-#define THREAD_LOCAL _Thread_local  /*!< \brief Thread local specifier. */
+/*! \brief Thread local specifier. */
+#define THREAD_LOCAL _Thread_local
 #elif defined(_MSC_VER)
-#define THREAD_LOCAL __declspec(thread)  /*!< \brief Thread local specifier. */
+/*! \brief Thread local specifier. */
+#define THREAD_LOCAL __declspec(thread)
 #else
-#define THREAD_LOCAL thread_local  /*!< \brief Thread local specifier. */
+/*! \brief Thread local specifier. */
+#define THREAD_LOCAL thread_local
 #endif
 
 /*!

include/LightGBM/dataset_loader.h

@@ -67,7 +67,7 @@ class DatasetLoader {
   /*! \brief Random generator*/
   Random random_;
   /*! \brief prediction function for initial model */
-  const PredictFunction& predict_fun_;
+  const PredictFunction predict_fun_;
   /*! \brief number of classes */
   int num_class_;
   /*! \brief index of label column */

python-package/lightgbm/engine.py

@@ -188,12 +188,11 @@ def train(
 
     if num_boost_round <= 0:
         raise ValueError("num_boost_round should be greater than zero.")
+    predictor: Optional[_InnerPredictor] = None
     if isinstance(init_model, (str, Path)):
         predictor = _InnerPredictor(model_file=init_model, pred_parameter=params)
     elif isinstance(init_model, Booster):
         predictor = init_model._to_predictor(dict(init_model.params, **params))
-    else:
-        predictor = None
     init_iteration = predictor.num_total_iteration if predictor is not None else 0
     # check dataset
     if not isinstance(train_set, Dataset):

src/io/dataset_loader.cpp

@@ -1143,7 +1143,7 @@ void DatasetLoader::ExtractFeaturesFromMemory(std::vector<std::string>* text_dat
   double tmp_label = 0.0f;
   auto& ref_text_data = *text_data;
   std::vector<float> feature_row(dataset->num_features_);
-  if (predict_fun_ == nullptr) {
+  if (!predict_fun_) {
     OMP_INIT_EX();
     // if doesn't need to prediction with initial model
     #pragma omp parallel for schedule(static) private(oneline_features) firstprivate(tmp_label, feature_row)
@@ -1262,7 +1262,7 @@ void DatasetLoader::ExtractFeaturesFromMemory(std::vector<std::string>* text_dat
 void DatasetLoader::ExtractFeaturesFromFile(const char* filename, const Parser* parser,
                                             const std::vector<data_size_t>& used_data_indices, Dataset* dataset) {
   std::vector<double> init_score;
-  if (predict_fun_ != nullptr) {
+  if (predict_fun_) {
     init_score = std::vector<double>(dataset->num_data_ * num_class_);
   }
   std::function<void(data_size_t, const std::vector<std::string>&)> process_fun =