[R-package] CRAN fixes (#1499)

* Fixed typos in docs

* Fixed inconsistencies in documentation

* Updated strategy for registering routines

* Fixed issues caused by smashing multiple functions into one Rd

* Fixed issues with documentation

* Removed VignetteBuilder and updated Rbuildignore

* Added R build artefacts to gitignore

* Added namespacing on data.table set function. Updated handling of CMakeLists file to get around CRAN check.

* Updated build instructions

* Added R build script

* Removed build_r.sh script and updated R-package install instructions

R-package/man/lgb.cv.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/lgb.cv.R
+\name{lgb.cv}
+\alias{lgb.cv}
+\title{Main CV logic for LightGBM}
+\usage{
+lgb.cv(params = list(), data, nrounds = 10, nfold = 3, label = NULL,
+  weight = NULL, obj = NULL, eval = NULL, verbose = 1, record = TRUE,
+  eval_freq = 1L, showsd = TRUE, stratified = TRUE, folds = NULL,
+  init_model = NULL, colnames = NULL, categorical_feature = NULL,
+  early_stopping_rounds = NULL, callbacks = list(), ...)
+}
+\arguments{
+\item{params}{List of parameters}
+
+\item{data}{a \code{lgb.Dataset} object, used for training}
+
+\item{nrounds}{number of training rounds}
+
+\item{nfold}{the original dataset is randomly partitioned into \code{nfold} equal size subsamples.}
+
+\item{label}{vector of response values. Should be provided only when data is an R-matrix.}
+
+\item{weight}{vector of response values. If not NULL, will set to dataset}
+
+\item{obj}{objective function, can be character or custom objective function. Examples include 
+\code{regression}, \code{regression_l1}, \code{huber},
+\code{binary}, \code{lambdarank}, \code{multiclass}, \code{multiclass}}
+
+\item{eval}{evaluation function, can be (list of) character or custom eval function}
+
+\item{verbose}{verbosity for output, if <= 0, also will disable the print of evaluation during training}
+
+\item{record}{Boolean, TRUE will record iteration message to \code{booster$record_evals}}
+
+\item{eval_freq}{evaluation output frequency, only effect when verbose > 0}
+
+\item{showsd}{\code{boolean}, whether to show standard deviation of cross validation}
+
+\item{stratified}{a \code{boolean} indicating whether sampling of folds should be stratified
+by the values of outcome labels.}
+
+\item{folds}{\code{list} provides a possibility to use a list of pre-defined CV folds
+(each element must be a vector of test fold's indices). When folds are supplied,
+the \code{nfold} and \code{stratified} parameters are ignored.}
+
+\item{init_model}{path of model file of \code{lgb.Booster} object, will continue training from this model}
+
+\item{colnames}{feature names, if not null, will use this to overwrite the names in dataset}
+
+\item{categorical_feature}{list of str or int
+type int represents index,
+type str represents feature names}
+
+\item{early_stopping_rounds}{int
+Activates early stopping.
+Requires at least one validation data and one metric
+If there's more than one, will check all of them except the training data
+Returns the model with (best_iter + early_stopping_rounds)
+If early stopping occurs, the model will have 'best_iter' field}
+
+\item{callbacks}{list of callback functions
+List of callback functions that are applied at each iteration.}
+
+\item{...}{other parameters, see Parameters.rst for more information. A few key parameters:
+\itemize{
+    \item{boosting}{Boosting type. \code{"gbdt"} or \code{"dart"}}
+    \item{num_leaves}{number of leaves in one tree. defaults to 127}
+    \item{max_depth}{Limit the max depth for tree model. This is used to deal with 
+                     overfit when #data is small. Tree still grow by leaf-wise.}
+    \item{num_threads}{Number of threads for LightGBM. For the best speed, set this to
+                       the number of real CPU cores, not the number of threads (most 
+                       CPU using hyper-threading to generate 2 threads per CPU core).}
+}}
+}
+\value{
+a trained model \code{lgb.CVBooster}.
+}
+\description{
+Cross validation logic used by LightGBM
+}
+\examples{
+\dontrun{
+library(lightgbm)
+data(agaricus.train, package = "lightgbm")
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+params <- list(objective = "regression", metric = "l2")
+model <- lgb.cv(params,
+                dtrain,
+                10,
+                nfold = 5,
+                min_data = 1,
+                learning_rate = 1,
+                early_stopping_rounds = 10)
+}
+}

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

@@ -9,7 +9,7 @@ lgb.model.dt.tree(model, num_iteration = NULL)
 \arguments{
 \item{model}{object of class \code{lgb.Booster}}
 
-\item{num_iteration}{number of iterations you want to predict with. NULL or 
+\item{num_iteration}{number of iterations you want to predict with. NULL or
 <= 0 means use best iteration}
 }
 \value{
@@ -26,7 +26,7 @@ The columns of the \code{data.table} are:
  \item \code{leaf_index}: ID of a leaf in a tree (integer)
  \item \code{leaf_parent}: ID of the parent node for current leaf (integer)
  \item \code{split_gain}: Split gain of a node
- \item \code{threshold}: Spliting threshold value of a node
+ \item \code{threshold}: Splitting threshold value of a node
  \item \code{decision_type}: Decision type of a node
  \item \code{default_left}: Determine how to handle NA value, TRUE -> Left, FALSE -> Right
  \item \code{internal_value}: Node value

R-package/man/lgb.train.Rd

 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/lgb.cv.R, R/lgb.train.R, R/lightgbm.R
-\name{lgb.cv}
-\alias{lgb.cv}
+% Please edit documentation in R/lgb.train.R
+\name{lgb.train}
 \alias{lgb.train}
-\alias{lightgbm}
-\title{Main CV logic for LightGBM}
+\title{Main training logic for LightGBM}
 \usage{
-lgb.cv(params = list(), data, nrounds = 10, nfold = 3, label = NULL,
-  weight = NULL, obj = NULL, eval = NULL, verbose = 1, record = TRUE,
-  eval_freq = 1L, showsd = TRUE, stratified = TRUE, folds = NULL,
-  init_model = NULL, colnames = NULL, categorical_feature = NULL,
-  early_stopping_rounds = NULL, callbacks = list(), ...)
-
 lgb.train(params = list(), data, nrounds = 10, valids = list(),
   obj = NULL, eval = NULL, verbose = 1, record = TRUE, eval_freq = 1L,
   init_model = NULL, colnames = NULL, categorical_feature = NULL,
   early_stopping_rounds = NULL, callbacks = list(), reset_data = FALSE,
   ...)
-
-lightgbm(data, label = NULL, weight = NULL, params = list(),
-  nrounds = 10, verbose = 1, eval_freq = 1L,
-  early_stopping_rounds = NULL, save_name = "lightgbm.model",
-  init_model = NULL, callbacks = list(), ...)
 }
 \arguments{
 \item{params}{List of parameters}
 
-\item{data}{a \code{lgb.Dataset} object, used for CV}
-
-\item{nrounds}{number of CV rounds}
-
-\item{nfold}{the original dataset is randomly partitioned into \code{nfold} equal size subsamples.}
-
-\item{label}{vector of response values. Should be provided only when data is an R-matrix.}
-
-\item{weight}{vector of response values. If not NULL, will set to dataset}
-
-\item{obj}{objective function, can be character or custom objective function. Examples include 
-\code{regression}, \code{regression_l1}, \code{huber},
-\code{binary}, \code{lambdarank}, \code{multiclass}, \code{multiclass}}
-
-\item{eval}{evaluation function, can be (list of) character or custom eval function}
-
-\item{verbose}{verbosity for output, if <= 0, also will disable the print of evalutaion during training}
-
-\item{record}{Boolean, TRUE will record iteration message to \code{booster$record_evals}}
-
-\item{eval_freq}{evalutaion output frequence, only effect when verbose > 0}
-
-\item{showsd}{\code{boolean}, whether to show standard deviation of cross validation}
-
-\item{stratified}{a \code{boolean} indicating whether sampling of folds should be stratified
-by the values of outcome labels.}
-
-\item{folds}{\code{list} provides a possibility to use a list of pre-defined CV folds
-(each element must be a vector of test fold's indices). When folds are supplied,
-the \code{nfold} and \code{stratified} parameters are ignored.}
-
-\item{init_model}{path of model file of \code{lgb.Booster} object, will continue train from this model}
-
-\item{colnames}{feature names, if not null, will use this to overwrite the names in dataset}
-
-\item{categorical_feature}{list of str or int
-type int represents index,
-type str represents feature names}
-
-\item{early_stopping_rounds}{int
-Activates early stopping.
-CV score needs to improve at least every early_stopping_rounds round(s) to continue.
-Requires at least one metric.
-If there's more than one, will check all of them.
-Returns the model with (best_iter + early_stopping_rounds).
-If early stopping occurs, the model will have 'best_iter' field}
-
-\item{callbacks}{list of callback functions
-List of callback functions that are applied at each iteration.}
-
-\item{...}{other parameters, see Parameters.rst for more informations}
-
-\item{valids}{a list of \code{lgb.Dataset} objects, used for validation}
-
-\item{reset_data}{Boolean, setting it to TRUE (not the default value) will transform the booster model into a predictor model which frees up memory and the original datasets}
-
-\item{boosting}{boosting type. \code{gbdt}, \code{dart}}
-
-\item{num_leaves}{number of leaves in one tree. defaults to 127}
-
-\item{max_depth}{Limit the max depth for tree model. This is used to deal with overfit when #data is small. 
-Tree still grow by leaf-wise.}
-
-\item{num_threads}{Number of threads for LightGBM. For the best speed, set this to the number of real CPU cores, not the number of threads (most CPU using hyper-threading to generate 2 threads per CPU core).}
-
-\item{params}{List of parameters}
-
 \item{data}{a \code{lgb.Dataset} object, used for training}
 
 \item{nrounds}{number of training rounds}
 
+\item{valids}{a list of \code{lgb.Dataset} objects, used for validation}
+
 \item{obj}{objective function, can be character or custom objective function. Examples include 
 \code{regression}, \code{regression_l1}, \code{huber},
 \code{binary}, \code{lambdarank}, \code{multiclass}, \code{multiclass}}
 
-\item{boosting}{boosting type. \code{gbdt}, \code{dart}}
-
-\item{num_leaves}{number of leaves in one tree. defaults to 127}
-
-\item{max_depth}{Limit the max depth for tree model. This is used to deal with overfit when #data is small. 
-Tree still grow by leaf-wise.}
-
-\item{num_threads}{Number of threads for LightGBM. For the best speed, set this to the number of real CPU cores, not the number of threads (most CPU using hyper-threading to generate 2 threads per CPU core).}
-
 \item{eval}{evaluation function, can be (a list of) character or custom eval function}
 
-\item{verbose}{verbosity for output, if <= 0, also will disable the print of evalutaion during training}
+\item{verbose}{verbosity for output, if <= 0, also will disable the print of evaluation during training}
 
 \item{record}{Boolean, TRUE will record iteration message to \code{booster$record_evals}}
 
-\item{eval_freq}{evalutaion output frequency, only effect when verbose > 0}
+\item{eval_freq}{evaluation output frequency, only effect when verbose > 0}
 
 \item{init_model}{path of model file of \code{lgb.Booster} object, will continue training from this model}
 
@@ -128,26 +41,32 @@ type str represents feature names}
 
 \item{early_stopping_rounds}{int
 Activates early stopping.
-The model will train until the validation score stops improving.
-Validation score needs to improve at least every early_stopping_rounds round(s) to continue training.
-Requires at least one validation data and one metric.
-If there's more than one, will check all of them. But the training data is ignored anyway.
-Returns the model with (best_iter + early_stopping_rounds).
+Requires at least one validation data and one metric
+If there's more than one, will check all of them except the training data
+Returns the model with (best_iter + early_stopping_rounds)
 If early stopping occurs, the model will have 'best_iter' field}
 
 \item{callbacks}{list of callback functions
 List of callback functions that are applied at each iteration.}
 
-\item{...}{other parameters, see Parameters.rst for more informations}
+\item{reset_data}{Boolean, setting it to TRUE (not the default value) will transform the booster model into a predictor model which frees up memory and the original datasets}
+
+\item{...}{other parameters, see Parameters.rst for more information. A few key parameters:
+\itemize{
+    \item{boosting}{Boosting type. \code{"gbdt"} or \code{"dart"}}
+    \item{num_leaves}{number of leaves in one tree. defaults to 127}
+    \item{max_depth}{Limit the max depth for tree model. This is used to deal with 
+                     overfit when #data is small. Tree still grow by leaf-wise.}
+    \item{num_threads}{Number of threads for LightGBM. For the best speed, set this to
+                       the number of real CPU cores, not the number of threads (most 
+                       CPU using hyper-threading to generate 2 threads per CPU core).}
+}}
 }
 \value{
-a trained model \code{lgb.CVBooster}.
-
 a trained booster model \code{lgb.Booster}.
 }
 \description{
-Simple interface for training an lightgbm model.
-Its documentation is combined with lgb.train.
+Logic to train with LightGBM
 }
 \examples{
 \dontrun{
@@ -155,20 +74,6 @@ library(lightgbm)
 data(agaricus.train, package = "lightgbm")
 train <- agaricus.train
 dtrain <- lgb.Dataset(train$data, label = train$label)
-params <- list(objective = "regression", metric = "l2")
-model <- lgb.cv(params,
-                dtrain,
-                10,
-                nfold = 5,
-                min_data = 1,
-                learning_rate = 1,
-                early_stopping_rounds = 10)
-}
-\dontrun{
-library(lightgbm)
-data(agaricus.train, package = "lightgbm")
-train <- agaricus.train
-dtrain <- lgb.Dataset(train$data, label = train$label)
 data(agaricus.test, package = "lightgbm")
 test <- agaricus.test
 dtest <- lgb.Dataset.create.valid(dtrain, test$data, label = test$label)

R-package/man/lgb_shared_params.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/lightgbm.R
+\name{lgb_shared_params}
+\alias{lgb_shared_params}
+\title{Shared parameter docs}
+\arguments{
+\item{callbacks}{list of callback functions
+List of callback functions that are applied at each iteration.}
+
+\item{data}{a \code{lgb.Dataset} object, used for training}
+
+\item{early_stopping_rounds}{int
+Activates early stopping.
+Requires at least one validation data and one metric
+If there's more than one, will check all of them except the training data
+Returns the model with (best_iter + early_stopping_rounds)
+If early stopping occurs, the model will have 'best_iter' field}
+
+\item{eval_freq}{evaluation output frequency, only effect when verbose > 0}
+
+\item{init_model}{path of model file of \code{lgb.Booster} object, will continue training from this model}
+
+\item{nrounds}{number of training rounds}
+
+\item{params}{List of parameters}
+
+\item{verbose}{verbosity for output, if <= 0, also will disable the print of evaluation during training}
+}
+\description{
+Parameter docs shared by \code{lgb.train}, \code{lgb.cv}, and \code{lightgbm}
+}

R-package/man/lightgbm.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/lightgbm.R
+\name{lightgbm}
+\alias{lightgbm}
+\title{Train a LightGBM model}
+\usage{
+lightgbm(data, label = NULL, weight = NULL, params = list(),
+  nrounds = 10, verbose = 1, eval_freq = 1L,
+  early_stopping_rounds = NULL, save_name = "lightgbm.model",
+  init_model = NULL, callbacks = list(), ...)
+}
+\arguments{
+\item{data}{a \code{lgb.Dataset} object, used for training}
+
+\item{label}{Vector of labels, used if \code{data} is not an \code{\link{lgb.Dataset}}}
+
+\item{weight}{vector of response values. If not NULL, will set to dataset}
+
+\item{params}{List of parameters}
+
+\item{nrounds}{number of training rounds}
+
+\item{verbose}{verbosity for output, if <= 0, also will disable the print of evaluation during training}
+
+\item{eval_freq}{evaluation output frequency, only effect when verbose > 0}
+
+\item{early_stopping_rounds}{int
+Activates early stopping.
+Requires at least one validation data and one metric
+If there's more than one, will check all of them except the training data
+Returns the model with (best_iter + early_stopping_rounds)
+If early stopping occurs, the model will have 'best_iter' field}
+
+\item{save_name}{File name to use when writing the trained model to disk. Should end in ".model".}
+
+\item{init_model}{path of model file of \code{lgb.Booster} object, will continue training from this model}
+
+\item{callbacks}{list of callback functions
+List of callback functions that are applied at each iteration.}
+
+\item{...}{Additional arguments passed to \code{\link{lgb.train}}. For example
+\itemize{
+   \item{valids}{a list of \code{lgb.Dataset} objects, used for validation}
+   \item{obj}{objective function, can be character or custom objective function. Examples include 
+              \code{regression}, \code{regression_l1}, \code{huber},
+               \code{binary}, \code{lambdarank}, \code{multiclass}, \code{multiclass}}
+   \item{eval}{evaluation function, can be (a list of) character or custom eval function}
+   \item{record}{Boolean, TRUE will record iteration message to \code{booster$record_evals}}
+   \item{colnames}{feature names, if not null, will use this to overwrite the names in dataset}
+   \item{categorical_feature}{list of str or int. type int represents index, type str represents feature names}
+   \item{reset_data}{Boolean, setting it to TRUE (not the default value) will transform the booster model 
+                     into a predictor model which frees up memory and the original datasets}
+    \item{boosting}{Boosting type. \code{"gbdt"} or \code{"dart"}}
+    \item{num_leaves}{number of leaves in one tree. defaults to 127}
+    \item{max_depth}{Limit the max depth for tree model. This is used to deal with 
+                     overfit when #data is small. Tree still grow by leaf-wise.}
+     \item{num_threads}{Number of threads for LightGBM. For the best speed, set this to
+                        the number of real CPU cores, not the number of threads (most 
+                        CPU using hyper-threading to generate 2 threads per CPU core).}
+}}
+}
+\description{
+Simple interface for training an LightGBM model.
+}

R-package/man/predict.lgb.Booster.Rd

@@ -5,8 +5,8 @@
 \title{Predict method for LightGBM model}
 \usage{
 \method{predict}{lgb.Booster}(object, data, num_iteration = NULL,
-  rawscore = FALSE, predleaf = FALSE, header = FALSE, reshape = FALSE,
-  ...)
+  rawscore = FALSE, predleaf = FALSE, predcontrib = FALSE,
+  header = FALSE, reshape = FALSE, ...)
 }
 \arguments{
 \item{object}{Object of class \code{lgb.Booster}}
@@ -21,6 +21,8 @@ logistic regression would result in predictions for log-odds instead of probabil
 
 \item{predleaf}{whether predict leaf index instead.}
 
+\item{predcontrib}{return per-feature contributions for each record.}
+
 \item{header}{only used for prediction for text file. True if text file has header}
 
 \item{reshape}{whether to reshape the vector of predictions to a matrix form when there are several

R-package/man/readRDS.lgb.Booster.Rd

@@ -15,7 +15,7 @@ readRDS.lgb.Booster(file = "", refhook = NULL)
 lgb.Booster.
 }
 \description{
-Attemps to load a model using RDS.
+Attempts to load a model using RDS.
 }
 \examples{
 \dontrun{

R-package/man/saveRDS.lgb.Booster.Rd

@@ -26,7 +26,7 @@ saveRDS.lgb.Booster(object, file = "", ascii = FALSE, version = NULL,
 NULL invisibly.
 }
 \description{
-Attemps to save a model using RDS. Has an additional parameter (\code{raw}) which decides whether to save the raw model or not.
+Attempts to save a model using RDS. Has an additional parameter (\code{raw}) which decides whether to save the raw model or not.
 }
 \examples{
 \dontrun{

R-package/man/slice.Rd

@@ -21,7 +21,7 @@ constructed sub dataset
 }
 \description{
 Get a new \code{lgb.Dataset} containing the specified rows of
-orginal lgb.Dataset object
+original lgb.Dataset object
 }
 \examples{
 \dontrun{

R-package/src/R_init.c

+
+// Register Dynamic Symbols
+
+#include <R.h>
+#include <Rinternals.h>
+#include <R_ext/Rdynload.h>
+#include "R_init.h"
+
+void R_init_lightgbm(DllInfo* info) {
+    R_registerRoutines(info, NULL, NULL, NULL, NULL);
+    R_useDynamicSymbols(info, TRUE);
+}

R-package/src/R_init.h

+// Register Dynamic Symbols
+#ifndef R_INIT_LIGHTGBM_H
+#define R_INIT_LIGHTGBM_H
+
+void R_init_lightgbm(DllInfo* info);
+
+#endif // R_INIT_LIGHTGBM_H

R-package/src/install.libs.R

@@ -14,6 +14,12 @@ if (!(R_int_UUID == "0310d4b8-ccb1-4bb8-ba94-d36a55f60262"
     || R_int_UUID == "2fdf6c18-697a-4ba7-b8ef-11c0d92f1327")){
   print("Warning: unmatched R_INTERNALS_UUID, may cannot run normally.")   
 }
+
+# Move in CMakeLists.txt
+if (!file.copy("../inst/bin/CMakeLists.txt", "CMakeLists.txt", overwrite = TRUE)){
+  stop("Copying CMakeLists failed")
+}
+
 # Check for precompilation
 if (!use_precompile) {
 
@@ -21,26 +27,6 @@ if (!use_precompile) {
   source_dir <- file.path(R_PACKAGE_SOURCE, "src", fsep = "/")
   setwd(source_dir)
   
-  if (!file.exists("_IS_FULL_PACKAGE")) {
-    unlink("./include", recursive = TRUE)
-    unlink("./src", recursive = TRUE)
-    unlink("./compute", recursive = TRUE)
-    unlink("./build", recursive = TRUE)
-    if (!file.copy("./../../include", "./", overwrite = TRUE, recursive = TRUE)) {
-      stop("Cannot find folder LightGBM/include")
-    }
-    if (!file.copy("./../../src", "./", overwrite = TRUE, recursive = TRUE)) {
-      stop("Cannot find folder LightGBM/src")
-    }
-    if (!file.copy("./../../compute", "./", overwrite = TRUE, recursive = TRUE)) {
-      print("Cannot find folder LightGBM/compute, disabling GPU build.")
-      use_gpu <- FALSE
-    }
-    if (!file.copy("./../../CMakeLists.txt", "./", overwrite = TRUE, recursive = TRUE)) {
-      stop("Cannot find file LightGBM/CMakeLists.txt")
-    }
-  }
-  
   # Prepare building package
   build_dir <- file.path(source_dir, "build", fsep = "/")
   dir.create(build_dir, recursive = TRUE, showWarnings = FALSE)

R-package/tests/testthat/test_dataset.R

@@ -62,7 +62,7 @@ test_that("lgb.Dataset: colnames", {
 
 test_that("lgb.Dataset: nrow is correct for a very sparse matrix", {
   nr <- 1000
-  x <- rsparsematrix(nr, 100, density=0.0005)
+  x <- Matrix::rsparsematrix(nr, 100, density=0.0005)
   # we want it very sparse, so that last rows are empty
   expect_lt(max(x@i), nr)
   dtest <- lgb.Dataset(x)

build_r.R

+
+# for macOS (replace 7 with version of gcc installed on your machine)
+# NOTE: your gcc / g++ from Homebrew is probably in /usr/local/bin
+#export CXX=/usr/local/bin/g++-8 CC=/usr/local/bin/gcc-8
+# Sys.setenv("CXX" = "/usr/local/bin/g++-8")
+# Sys.setenv("CC" = "/usr/local/bin/gcc-8")
+
+# R returns FALSE (not a non-zero exit code) if a file copy operation
+# breaks. Let's fix that
+.handle_result <- function(res){
+    if (!res){
+        stop("Copying files failed!")
+    }
+}
+
+# Make a new temporary folder to work in
+unlink(x = "lightgbm_r", recursive = TRUE)
+dir.create("lightgbm_r")
+
+# copy in the relevant files
+result <- file.copy(
+    from = "R-package/./"
+    , to = "lightgbm_r/"
+    , recursive = TRUE
+    , overwrite = TRUE
+)
+.handle_result(result)
+
+result <- file.copy(
+    from = "include/"
+    , to = file.path("lightgbm_r", "src/")
+    , recursive = TRUE
+    , overwrite = TRUE
+)
+.handle_result(result)
+
+result <- file.copy(
+    from = "src/"
+    , to = file.path("lightgbm_r", "src/")
+    , recursive = TRUE
+    , overwrite = TRUE
+)
+.handle_result(result)
+
+result <- file.copy(
+    from = "CMakeLists.txt"
+    , to = file.path("lightgbm_r", "inst", "bin/")
+    , recursive = TRUE
+    , overwrite = TRUE
+)
+.handle_result(result)
+
+# rebuild documentation
+devtools::document(
+    pkg = "lightgbm_r/"
+)
+
+# Build the package
+# NOTE: --keep-empty-dirs is necessary to keep the deep paths expected
+#       by CMake while also meeting the CRAN req to create object files
+#       on demand
+devtools::build(
+    pkg = "lightgbm_r"
+    , args = c("--keep-empty-dirs")
+)
+
+# Install the package
+version <- gsub(
+    "Version: "
+    , ""
+    , grep(
+        "Version: "
+        , readLines(con = file.path("lightgbm_r", "DESCRIPTION"))
+        , value = TRUE
+    )
+)
+tarball <- file.path(getwd(), sprintf("lightgbm_%s.tar.gz", version))
+
+system(sprintf("R CMD INSTALL %s --no-multi-arch", tarball))
+
+# Run R CMD CHECK
+#R CMD CHECK lightgbm_2.1.2.tar.gz --as-cran | tee check.log | cat

src/treelearner/gpu_tree_learner.cpp

@@ -1096,7 +1096,7 @@ void GPUTreeLearner::FindBestSplits() {
 void GPUTreeLearner::Split(Tree* tree, int best_Leaf, int* left_leaf, int* right_leaf) {
   const SplitInfo& best_split_info = best_split_per_leaf_[best_Leaf];
 #if GPU_DEBUG >= 2
-  printf("Spliting leaf %d with feature %d thresh %d gain %f stat %f %f %f %f\n", best_Leaf, best_split_info.feature, best_split_info.threshold, best_split_info.gain, best_split_info.left_sum_gradient, best_split_info.right_sum_gradient, best_split_info.left_sum_hessian, best_split_info.right_sum_hessian);
+  printf("Splitting leaf %d with feature %d thresh %d gain %f stat %f %f %f %f\n", best_Leaf, best_split_info.feature, best_split_info.threshold, best_split_info.gain, best_split_info.left_sum_gradient, best_split_info.right_sum_gradient, best_split_info.left_sum_hessian, best_split_info.right_sum_hessian);
 #endif
   SerialTreeLearner::Split(tree, best_Leaf, left_leaf, right_leaf);
   if (Network::num_machines() == 1) {