merge conflict

R-package/demo/00Index

@@ -2,3 +2,4 @@ basic_walkthrough               Basic feature walkthrough
 boost_from_prediction           Boosting from existing prediction
 early_stopping                  Early Stop in training
 cross_validation                Cross Validation
+multiclass                      Multiclass training/prediction

R-package/demo/README.md

@@ -4,3 +4,4 @@ LightGBM R examples
 * [Boosting from existing prediction](boost_from_prediction.R)
 * [Early Stopping](early_stopping.R)
 * [Cross Validation](cross_validation.R)
+* [Multiclass Training/Prediction](multiclass.R)

R-package/demo/multiclass.R

+require(lightgbm)
+
+# we load the default iris dataset shipped with R
+data(iris)
+
+# we must convert factors to numeric
+# they must be starting from number 0 to use multiclass
+# for instance: 0, 1, 2, 3, 4, 5...
+iris$Species <- as.numeric(as.factor(iris$Species))-1
+
+# we cut the data set into 80% train and 20% validation
+# the 10 last samples of each class are for validation
+
+train <- as.matrix(iris[c(1:40, 51:90, 101:140), ])
+test <- as.matrix(iris[c(41:50, 91:100, 141:150), ])
+dtrain <- lgb.Dataset(data=train[, 1:4], label=train[, 5])
+dtest <- lgb.Dataset.create.valid(dtrain, data=test[, 1:4], label=test[, 5])
+valids <- list(test=dtest)
+
+# method 1 of training
+params <- list(objective="multiclass", metric="multi_error", num_class=3)
+model <- lgb.train(params, dtrain, 100, valids, min_data=1, learning_rate=1, early_stopping_rounds=10)
+
+# we can predict on test data, outputs a 90-length vector
+# order: obs1 class1, obs1 class2, obs1 class3, obs2 class1, obs2 class2, obs2 class3...
+my_preds <- predict(model, test[, 1:4])
+
+# method 2 of training, identical
+model <- lgb.train(list(), dtrain, 100, valids, min_data=1, learning_rate=1, early_stopping_rounds=10, objective="multiclass", metric="multi_error", num_class=3)
+
+# we can predict on test data, identical
+my_preds <- predict(model, test[, 1:4])
+
+# a (30x3) matrix with the predictions, use parameter reshape
+# class1 class2 class3
+#   obs1   obs1   obs1
+#   obs2   obs2   obs2
+#   ....   ....   ....
+my_preds <- predict(model, test[, 1:4], reshape=TRUE)
+
+# we can also get the predicted scores before the Sigmoid/Softmax application
+my_preds <- predict(model, test[, 1:4], rawscore=TRUE)
+
+# raw score predictions as matrix instead of vector
+my_preds <- predict(model, test[, 1:4], rawscore=TRUE, reshape=TRUE)
+
+# we can also get the leaf index
+my_preds <- predict(model, test[, 1:4], predleaf=TRUE)
+
+# preddict leaf index as matrix instead of vector
+my_preds <- predict(model, test[, 1:4], predleaf=TRUE, reshape=TRUE)

R-package/man/lgb.Dataset.Rd

@@ -2,7 +2,7 @@
 % Please edit documentation in R/lgb.Dataset.R
 \name{lgb.Dataset}
 \alias{lgb.Dataset}
-\title{Contruct lgb.Dataset object}
+\title{Construct lgb.Dataset object}
 \usage{
 lgb.Dataset(data, params = list(), reference = NULL, colnames = NULL,
   categorical_feature = NULL, free_raw_data = TRUE, info = list(), ...)
@@ -28,7 +28,7 @@ lgb.Dataset(data, params = list(), reference = NULL, colnames = NULL,
 constructed dataset
 }
 \description{
-Contruct lgb.Dataset object from dense matrix, sparse matrix
+Construct lgb.Dataset object from dense matrix, sparse matrix
 or local file (that was created previously by saving an \code{lgb.Dataset}).
 }
 \examples{

R-package/man/lgb.Dataset.create.valid.Rd

@@ -2,7 +2,7 @@
 % Please edit documentation in R/lgb.Dataset.R
 \name{lgb.Dataset.create.valid}
 \alias{lgb.Dataset.create.valid}
-\title{Contruct validation data}
+\title{Construct validation data}
 \usage{
 lgb.Dataset.create.valid(dataset, data, info = list(), ...)
 }
@@ -19,7 +19,7 @@ lgb.Dataset.create.valid(dataset, data, info = list(), ...)
 constructed dataset
 }
 \description{
-Contruct validation data according to training data
+Construct validation data according to training data
 }
 \examples{
 \dontrun{

R-package/man/lgb.importance.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/lgb.importance.R
+\name{lgb.importance}
+\alias{lgb.importance}
+\title{Compute feature importance in a model}
+\usage{
+lgb.importance(model, percentage = TRUE)
+}
+\arguments{
+\item{model}{object of class \code{lgb.Booster}.}
+
+\item{percentage}{whether to show importance in relative percentage.}
+}
+\value{
+For a tree model, a \code{data.table} with the following columns:
+\itemize{
+  \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.
+}
+}
+\description{
+Creates a \code{data.table} of feature importances in a model.
+}
+\examples{
+
+data(agaricus.train, package = 'lightgbm')
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+
+params = list(objective = "binary",
+              learning_rate = 0.01, num_leaves = 63, max_depth = -1,
+              min_data_in_leaf = 1, min_sum_hessian_in_leaf = 1)
+              model <- lgb.train(params, dtrain, 20)
+model <- lgb.train(params, dtrain, 20)
+
+tree_imp1 <- lgb.importance(model, percentage = TRUE)
+tree_imp2 <- lgb.importance(model, percentage = FALSE)
+
+}
+

R-package/man/lgb.interprete.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/lgb.interprete.R
+\name{lgb.interprete}
+\alias{lgb.interprete}
+\title{Compute feature contribution of prediction}
+\usage{
+lgb.interprete(model, data, idxset, num_iteration = NULL)
+}
+\arguments{
+\item{model}{object of class \code{lgb.Booster}.}
+
+\item{data}{a matrix object or a dgCMatrix object.}
+
+\item{idxset}{a integer vector of indices of rows needed.}
+
+\item{num_iteration}{number of iteration want to predict with, NULL or <= 0 means use best iteration.}
+}
+\value{
+For regression, binary classification and lambdarank model, a \code{list} of \code{data.table} with the following columns:
+\itemize{
+  \item \code{Feature} Feature names in the model.
+  \item \code{Contribution} The total contribution of this feature's splits.
+}
+For multiclass classification, a \code{list} of \code{data.table} with the Feature column and Contribution columns to each class.
+}
+\description{
+Computes feature contribution components of rawscore prediction.
+}
+\examples{
+
+Sigmoid <- function(x) 1 / (1 + exp(-x))
+Logit <- function(x) log(x / (1 - x))
+data(agaricus.train, package = 'lightgbm')
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+setinfo(dtrain, "init_score", rep(Logit(mean(train$label)), length(train$label)))
+data(agaricus.test, package = 'lightgbm')
+test <- agaricus.test
+
+params = list(objective = "binary",
+              learning_rate = 0.01, num_leaves = 63, max_depth = -1,
+              min_data_in_leaf = 1, min_sum_hessian_in_leaf = 1)
+              model <- lgb.train(params, dtrain, 20)
+model <- lgb.train(params, dtrain, 20)
+
+tree_interpretation <- lgb.interprete(model, test$data, 1:5)
+
+}
+

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

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/lgb.model.dt.tree.R
+\name{lgb.model.dt.tree}
+\alias{lgb.model.dt.tree}
+\title{Parse a LightGBM model json dump}
+\usage{
+lgb.model.dt.tree(model, num_iteration = NULL)
+}
+\arguments{
+\item{model}{object of class \code{lgb.Booster}}
+}
+\value{
+A \code{data.table} with detailed information about model trees' nodes and leafs.
+
+The columns of the \code{data.table} are:
+
+\itemize{
+ \item \code{tree_index}: ID of a tree in a model (integer)
+ \item \code{split_index}: ID of a node in a tree (integer)
+ \item \code{split_feature}: for a node, it's a feature name (character);
+                             for a leaf, it simply labels it as \code{'NA'}
+ \item \code{node_parent}: ID of the parent node for current node (integer)
+ \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{decision_type}: Decision type of a node
+ \item \code{internal_value}: Node value
+ \item \code{internal_count}: The number of observation collected by a node
+ \item \code{leaf_value}: Leaf value
+ \item \code{leaf_count}: The number of observation collected by a leaf
+}
+}
+\description{
+Parse a LightGBM model json dump into a \code{data.table} structure.
+}
+\examples{
+
+data(agaricus.train, package = 'lightgbm')
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+
+params = list(objective = "binary",
+              learning_rate = 0.01, num_leaves = 63, max_depth = -1,
+              min_data_in_leaf = 1, min_sum_hessian_in_leaf = 1)
+              model <- lgb.train(params, dtrain, 20)
+model <- lgb.train(params, dtrain, 20)
+
+tree_dt <- lgb.model.dt.tree(model)
+
+}
+

R-package/man/lgb.plot.importance.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/lgb.plot.importance.R
+\name{lgb.plot.importance}
+\alias{lgb.plot.importance}
+\title{Plot feature importance as a bar graph}
+\usage{
+lgb.plot.importance(tree_imp, top_n = 10, measure = "Gain",
+  left_margin = 10, cex = NULL)
+}
+\arguments{
+\item{tree_imp}{a \code{data.table} returned by \code{\link{lgb.importance}}.}
+
+\item{top_n}{maximal number of top features to include into the plot.}
+
+\item{measure}{the name of importance measure to plot, can be "Gain", "Cover" or "Frequency".}
+
+\item{left_margin}{(base R barplot) allows to adjust the left margin size to fit feature names.}
+
+\item{cex}{(base R barplot) passed as \code{cex.names} parameter to \code{barplot}.}
+}
+\value{
+The \code{lgb.plot.importance} function creates a \code{barplot}
+and silently returns a processed data.table with \code{top_n} features sorted by defined importance.
+}
+\description{
+Plot previously calculated feature importance: Gain, Cover and Frequency, as a bar graph.
+}
+\details{
+The graph represents each feature as a horizontal bar of length proportional to the defined importance of a feature.
+Features are shown ranked in a decreasing importance order.
+}
+\examples{
+
+data(agaricus.train, package = 'lightgbm')
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+
+params = list(objective = "binary",
+              learning_rate = 0.01, num_leaves = 63, max_depth = -1,
+              min_data_in_leaf = 1, min_sum_hessian_in_leaf = 1)
+              model <- lgb.train(params, dtrain, 20)
+model <- lgb.train(params, dtrain, 20)
+
+tree_imp <- lgb.importance(model, percentage = TRUE)
+lgb.plot.importance(tree_imp, top_n = 10, measure = "Gain")
+
+}
+

R-package/man/lgb.plot.interpretation.Rd

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/lgb.plot.interpretation.R
+\name{lgb.plot.interpretation}
+\alias{lgb.plot.interpretation}
+\title{Plot feature contribution as a bar graph}
+\usage{
+lgb.plot.interpretation(tree_interpretation_dt, top_n = 10, cols = 1,
+  left_margin = 10, cex = NULL)
+}
+\arguments{
+\item{tree_interpretation_dt}{a \code{data.table} returned by \code{\link{lgb.interprete}}.}
+
+\item{top_n}{maximal number of top features to include into the plot.}
+
+\item{cols}{the column numbers of layout, will be used only for multiclass classification feature contribution.}
+
+\item{left_margin}{(base R barplot) allows to adjust the left margin size to fit feature names.}
+
+\item{cex}{(base R barplot) passed as \code{cex.names} parameter to \code{barplot}.}
+}
+\value{
+The \code{lgb.plot.interpretation} function creates a \code{barplot}
+}
+\description{
+Plot previously calculated feature contribution as a bar graph.
+}
+\details{
+The graph represents each feature as a horizontal bar of length proportional to the defined contribution of a feature.
+Features are shown ranked in a decreasing contribution order.
+}
+\examples{
+
+Sigmoid <- function(x) 1 / (1 + exp(-x))
+Logit <- function(x) log(x / (1 - x))
+data(agaricus.train, package = 'lightgbm')
+train <- agaricus.train
+dtrain <- lgb.Dataset(train$data, label = train$label)
+setinfo(dtrain, "init_score", rep(Logit(mean(train$label)), length(train$label)))
+data(agaricus.test, package = 'lightgbm')
+test <- agaricus.test
+
+params = list(objective = "binary",
+              learning_rate = 0.01, num_leaves = 63, max_depth = -1,
+              min_data_in_leaf = 1, min_sum_hessian_in_leaf = 1)
+              model <- lgb.train(params, dtrain, 20)
+model <- lgb.train(params, dtrain, 20)
+
+tree_interpretation <- lgb.interprete(model, test$data, 1:5)
+lgb.plot.interpretation(tree_interpretation[[1]], top_n = 10)
+
+}
+

R-package/man/lgb.train.Rd

@@ -7,13 +7,13 @@
 \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, eval_freq = 1L,
-  showsd = TRUE, stratified = TRUE, folds = NULL, init_model = NULL,
-  colnames = NULL, categorical_feature = 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, eval_freq = 1L,
+  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(), ...)
 
@@ -35,14 +35,17 @@ lightgbm(data, label = NULL, weight = NULL, params = list(),
 
 \item{weight}{vector of response values. If not NULL, will set to dataset}
 
-\item{obj}{objective function, can be character or custom objective function}
+\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 verbose > 0 , also will record iteration message to booster$record_evals}
+\item{verbose}{verbosity for output, if <= 0, also will disable the print of evalutaion during training}
+
+\item{record}{Boolean, TRUE will record iteration message to \code{booster$record_evals}}
 
-\item{eval_freq}{evalutaion output frequence}
+\item{eval_freq}{evalutaion output frequence, only effect when verbose > 0}
 
 \item{showsd}{\code{boolean}, whether to show standard deviation of cross validation}
 
@@ -75,20 +78,41 @@ List of callback functions that are applied at each iteration.}
 
 \item{valids}{a list of \code{lgb.Dataset} objects, used for validation}
 
+\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{obj}{objective function, can be character or custom objective function}
+\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 \code{verbose > 0}, also will record iteration message to \code{booster$record_evals}}
+\item{verbose}{verbosity for output, if <= 0, also will disable the print of evalutaion during training}
+
+\item{record}{Boolean, TRUE will record iteration message to \code{booster$record_evals}}
 
-\item{eval_freq}{evalutaion output frequency}
+\item{eval_freq}{evalutaion 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}
 
@@ -111,7 +135,7 @@ List of callback functions that are applied at each iteration.}
 \item{...}{other parameters, see parameters.md for more informations}
 }
 \value{
-a trained booster model \code{lgb.Booster}.
+a trained model \code{lgb.CVBooster}.
 
 a trained booster model \code{lgb.Booster}.
 }

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

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/readRDS.lgb.Booster.R
+\name{readRDS.lgb.Booster}
+\alias{readRDS.lgb.Booster}
+\title{readRDS for lgb.Booster models}
+\usage{
+readRDS.lgb.Booster(file = "", refhook = NULL)
+}
+\arguments{
+\item{file}{a connection or the name of the file where the R object is saved to or read from.}
+
+\item{refhook}{a hook function for handling reference objects.}
+}
+\value{
+an R object.
+}
+\description{
+Attemps to load a model using RDS.
+}
+\examples{
+\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)
+  params <- list(objective="regression", metric="l2")
+  valids <- list(test=dtest)
+  model <- lgb.train(params, dtrain, 100, valids, min_data=1, learning_rate=1, early_stopping_rounds=10)
+  saveRDS.lgb.Booster(model, "model.rds")
+  new_model <- readRDS.lgb.Booster("model.rds")
+}
+}
+

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

+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/saveRDS.lgb.Booster.R
+\name{saveRDS.lgb.Booster}
+\alias{saveRDS.lgb.Booster}
+\title{saveRDS for lgb.Booster models}
+\usage{
+saveRDS.lgb.Booster(object, file = "", ascii = FALSE, version = NULL,
+  compress = TRUE, refhook = NULL, raw = TRUE)
+}
+\arguments{
+\item{object}{R object to serialize.}
+
+\item{file}{a connection or the name of the file where the R object is saved to or read from.}
+
+\item{ascii}{a logical. If TRUE or NA, an ASCII representation is written; otherwise (default), a binary one is used. See the comments in the help for save.}
+
+\item{version}{the workspace format version to use. \code{NULL} specifies the current default version (2). Versions prior to 2 are not supported, so this will only be relevant when there are later versions.}
+
+\item{compress}{a logical specifying whether saving to a named file is to use "gzip" compression, or one of \code{"gzip"}, \code{"bzip2"} or \code{"xz"} to indicate the type of compression to be used. Ignored if file is a connection.}
+
+\item{refhook}{a hook function for handling reference objects.}
+
+\item{raw}{whether to save the model in a raw variable or not, recommended to leave it to \code{TRUE}.}
+}
+\value{
+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.
+}
+\examples{
+\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)
+  params <- list(objective="regression", metric="l2")
+  valids <- list(test=dtest)
+  model <- lgb.train(params, dtrain, 100, valids, min_data=1, learning_rate=1, early_stopping_rounds=10)
+  saveRDS.lgb.Booster(model, "model.rds")
+}
+}
+

R-package/src/Makevars_fullcode

+# package root
+PKGROOT=.
+
+ENABLE_STD_THREAD=1
+CXX_STD = CXX11
+
+LGBM_RFLAGS = -DUSE_SOCKET
+
+PKG_CPPFLAGS= -I$(PKGROOT)/include $(LGBM_RFLAGS) -Wno-deprecated-declarations
+PKG_CXXFLAGS= $(SHLIB_OPENMP_CFLAGS) $(SHLIB_PTHREAD_FLAGS) -std=c++11
+PKG_LIBS = $(SHLIB_OPENMP_CFLAGS) $(SHLIB_PTHREAD_FLAGS)
+OBJECTS = ./lightgbm-fullcode.o ./lightgbm_R.o

R-package/src/Makevars_fullcode.win

+# package root
+PKGROOT=.
+
+ENABLE_STD_THREAD=1
+CXX_STD = CXX11
+
+LGBM_RFLAGS = -DUSE_SOCKET 
+
+PKG_CPPFLAGS= -I$(PKGROOT)/include $(LGBM_RFLAGS) 
+PKG_CXXFLAGS= $(SHLIB_OPENMP_CFLAGS) $(SHLIB_PTHREAD_FLAGS) -std=c++11
+PKG_LIBS = $(SHLIB_OPENMP_CFLAGS) $(SHLIB_PTHREAD_FLAGS) -lws2_32 -liphlpapi 
+OBJECTS = ./lightgbm-fullcode.o ./lightgbm_R.o 

R-package/src/lightgbm-fullcode.cpp

+// application
+#include "./src/application/application.cpp"
+
+// boosting
+#include "./src/boosting/boosting.cpp"
+#include "./src/boosting/gbdt.cpp"
+
+// io
+#include "./src/io/bin.cpp"
+#include "./src/io/config.cpp"
+#include "./src/io/dataset.cpp"
+#include "./src/io/dataset_loader.cpp"
+#include "./src/io/metadata.cpp"
+#include "./src/io/parser.cpp"
+#include "./src/io/tree.cpp"
+
+// metric
+#include "./src/metric/dcg_calculator.cpp"
+#include "./src/metric/metric.cpp"
+
+// network
+#include "./src/network/linker_topo.cpp"
+#include "./src/network/linkers_socket.cpp"
+#include "./src/network/network.cpp"
+
+// objective
+#include "./src/objective/objective_function.cpp"
+
+// treelearner
+#include "./src/treelearner/data_parallel_tree_learner.cpp"
+#include "./src/treelearner/feature_parallel_tree_learner.cpp"
+#include "./src/treelearner/serial_tree_learner.cpp"
+#include "./src/treelearner/tree_learner.cpp"
+#include "./src/treelearner/voting_parallel_tree_learner.cpp"
+
+// c_api
+#include "./src/c_api.cpp"

R-package/src/lightgbm_R.cpp

@@ -4,7 +4,7 @@
 #include <cstring>
 #include <cstdio>
 #include <sstream>
-#include <omp.h>
+#include <LightGBM/utils/openmp_wrapper.h>
 #include <cstdint>
 #include <memory>
 

R-package/src/lightgbm_R.h

@@ -15,7 +15,7 @@
 * \return err_msg error inforomation
 * \return error inforomation
 */
-DllExport SEXP LGBM_GetLastError_R(SEXP buf_len, SEXP actual_len, SEXP err_msg);
+LIGHTGBM_C_EXPORT SEXP LGBM_GetLastError_R(SEXP buf_len, SEXP actual_len, SEXP err_msg);
 
 // --- start Dataset interface
 
@@ -27,7 +27,7 @@ DllExport SEXP LGBM_GetLastError_R(SEXP buf_len, SEXP actual_len, SEXP err_msg);
 * \param out created dataset
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetCreateFromFile_R(SEXP filename,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetCreateFromFile_R(SEXP filename,
   SEXP parameters,
   SEXP reference,
   SEXP out,
@@ -46,7 +46,7 @@ DllExport SEXP LGBM_DatasetCreateFromFile_R(SEXP filename,
 * \param out created dataset
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetCreateFromCSC_R(SEXP indptr,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetCreateFromCSC_R(SEXP indptr,
   SEXP indices,
   SEXP data,
   SEXP nindptr,
@@ -68,7 +68,7 @@ DllExport SEXP LGBM_DatasetCreateFromCSC_R(SEXP indptr,
 * \param out created dataset
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetCreateFromMat_R(SEXP data,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetCreateFromMat_R(SEXP data,
   SEXP nrow,
   SEXP ncol,
   SEXP parameters,
@@ -85,7 +85,7 @@ DllExport SEXP LGBM_DatasetCreateFromMat_R(SEXP data,
 * \param out created dataset
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetGetSubset_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetGetSubset_R(SEXP handle,
   SEXP used_row_indices,
   SEXP len_used_row_indices,
   SEXP parameters,
@@ -98,7 +98,7 @@ DllExport SEXP LGBM_DatasetGetSubset_R(SEXP handle,
 * \param feature_names feature names
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetSetFeatureNames_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetSetFeatureNames_R(SEXP handle,
   SEXP feature_names,
   SEXP call_state);
 
@@ -108,7 +108,7 @@ DllExport SEXP LGBM_DatasetSetFeatureNames_R(SEXP handle,
 * \param feature_names feature names
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetGetFeatureNames_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetGetFeatureNames_R(SEXP handle,
   SEXP buf_len,
   SEXP actual_len,
   SEXP feature_names,
@@ -120,7 +120,7 @@ DllExport SEXP LGBM_DatasetGetFeatureNames_R(SEXP handle,
 * \param filename file name
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetSaveBinary_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetSaveBinary_R(SEXP handle,
   SEXP filename,
   SEXP call_state);
 
@@ -129,7 +129,7 @@ DllExport SEXP LGBM_DatasetSaveBinary_R(SEXP handle,
 * \param handle an instance of dataset
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetFree_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetFree_R(SEXP handle,
   SEXP call_state);
 
 /*!
@@ -142,7 +142,7 @@ DllExport SEXP LGBM_DatasetFree_R(SEXP handle,
 * \param num_element number of element in field_data
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetSetField_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetSetField_R(SEXP handle,
   SEXP field_name,
   SEXP field_data,
   SEXP num_element,
@@ -155,7 +155,7 @@ DllExport SEXP LGBM_DatasetSetField_R(SEXP handle,
 * \param out size of info vector from dataset
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetGetFieldSize_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetGetFieldSize_R(SEXP handle,
   SEXP field_name,
   SEXP out,
   SEXP call_state);
@@ -167,7 +167,7 @@ DllExport SEXP LGBM_DatasetGetFieldSize_R(SEXP handle,
 * \param field_data pointer to vector
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetGetField_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetGetField_R(SEXP handle,
   SEXP field_name,
   SEXP field_data,
   SEXP call_state);
@@ -178,7 +178,7 @@ DllExport SEXP LGBM_DatasetGetField_R(SEXP handle,
 * \param out The address to hold number of data
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetGetNumData_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetGetNumData_R(SEXP handle,
   SEXP out,
   SEXP call_state);
 
@@ -188,7 +188,7 @@ DllExport SEXP LGBM_DatasetGetNumData_R(SEXP handle,
 * \param out The output of number of features
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_DatasetGetNumFeature_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_DatasetGetNumFeature_R(SEXP handle,
   SEXP out,
   SEXP call_state);
 
@@ -201,7 +201,7 @@ DllExport SEXP LGBM_DatasetGetNumFeature_R(SEXP handle,
 * \prama out handle of created Booster
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterCreate_R(SEXP train_data,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterCreate_R(SEXP train_data,
   SEXP parameters,
   SEXP out,
   SEXP call_state);
@@ -211,7 +211,7 @@ DllExport SEXP LGBM_BoosterCreate_R(SEXP train_data,
 * \param handle handle to be freed
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterFree_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterFree_R(SEXP handle,
   SEXP call_state);
 
 /*!
@@ -220,7 +220,7 @@ DllExport SEXP LGBM_BoosterFree_R(SEXP handle,
 * \prama out handle of created Booster
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterCreateFromModelfile_R(SEXP filename,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterCreateFromModelfile_R(SEXP filename,
   SEXP out,
   SEXP call_state);
 
@@ -230,7 +230,7 @@ DllExport SEXP LGBM_BoosterCreateFromModelfile_R(SEXP filename,
 * \param other_handle
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterMerge_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterMerge_R(SEXP handle,
   SEXP other_handle,
   SEXP call_state);
 
@@ -240,7 +240,7 @@ DllExport SEXP LGBM_BoosterMerge_R(SEXP handle,
 * \param valid_data validation data set
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterAddValidData_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterAddValidData_R(SEXP handle,
   SEXP valid_data,
   SEXP call_state);
 
@@ -250,7 +250,7 @@ DllExport SEXP LGBM_BoosterAddValidData_R(SEXP handle,
 * \param train_data training data set
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterResetTrainingData_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterResetTrainingData_R(SEXP handle,
   SEXP train_data,
   SEXP call_state);
 
@@ -260,7 +260,7 @@ DllExport SEXP LGBM_BoosterResetTrainingData_R(SEXP handle,
 * \param parameters format: 'key1=value1 key2=value2'
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterResetParameter_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterResetParameter_R(SEXP handle,
   SEXP parameters,
   SEXP call_state);
 
@@ -270,7 +270,7 @@ DllExport SEXP LGBM_BoosterResetParameter_R(SEXP handle,
 * \param out number of classes
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterGetNumClasses_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterGetNumClasses_R(SEXP handle,
   SEXP out,
   SEXP call_state);
 
@@ -279,7 +279,7 @@ DllExport SEXP LGBM_BoosterGetNumClasses_R(SEXP handle,
 * \param handle handle
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterUpdateOneIter_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterUpdateOneIter_R(SEXP handle,
   SEXP call_state);
 
 /*!
@@ -291,7 +291,7 @@ DllExport SEXP LGBM_BoosterUpdateOneIter_R(SEXP handle,
 * \param len length of grad/hess
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterUpdateOneIterCustom_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterUpdateOneIterCustom_R(SEXP handle,
   SEXP grad,
   SEXP hess,
   SEXP len,
@@ -302,7 +302,7 @@ DllExport SEXP LGBM_BoosterUpdateOneIterCustom_R(SEXP handle,
 * \param handle handle
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterRollbackOneIter_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterRollbackOneIter_R(SEXP handle,
   SEXP call_state);
 
 /*!
@@ -310,7 +310,7 @@ DllExport SEXP LGBM_BoosterRollbackOneIter_R(SEXP handle,
 * \param out iteration of boosting rounds
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterGetCurrentIteration_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterGetCurrentIteration_R(SEXP handle,
   SEXP out,
   SEXP call_state);
 
@@ -319,7 +319,7 @@ DllExport SEXP LGBM_BoosterGetCurrentIteration_R(SEXP handle,
 * \param eval_names eval names
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterGetEvalNames_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterGetEvalNames_R(SEXP handle,
   SEXP buf_len,
   SEXP actual_len,
   SEXP eval_names,
@@ -332,7 +332,7 @@ DllExport SEXP LGBM_BoosterGetEvalNames_R(SEXP handle,
 * \param out_result float arrary contains result
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterGetEval_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterGetEval_R(SEXP handle,
   SEXP data_idx,
   SEXP out_result,
   SEXP call_state);
@@ -344,7 +344,7 @@ DllExport SEXP LGBM_BoosterGetEval_R(SEXP handle,
 * \param out size of predict
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterGetNumPredict_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterGetNumPredict_R(SEXP handle,
   SEXP data_idx,
   SEXP out,
   SEXP call_state);
@@ -357,7 +357,7 @@ DllExport SEXP LGBM_BoosterGetNumPredict_R(SEXP handle,
 * \param out_result, used to store predict result, should pre-allocate memory
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterGetPredict_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterGetPredict_R(SEXP handle,
   SEXP data_idx,
   SEXP out_result,
   SEXP call_state);
@@ -373,7 +373,7 @@ DllExport SEXP LGBM_BoosterGetPredict_R(SEXP handle,
 * \return 0 when succeed, -1 when failure happens
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterPredictForFile_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterPredictForFile_R(SEXP handle,
   SEXP data_filename,
   SEXP data_has_header,
   SEXP is_rawscore,
@@ -392,7 +392,7 @@ DllExport SEXP LGBM_BoosterPredictForFile_R(SEXP handle,
 * \param out_len lenght of prediction
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterCalcNumPredict_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterCalcNumPredict_R(SEXP handle,
   SEXP num_row,
   SEXP is_rawscore,
   SEXP is_leafidx,
@@ -418,7 +418,7 @@ DllExport SEXP LGBM_BoosterCalcNumPredict_R(SEXP handle,
 * \param out prediction result
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterPredictForCSC_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterPredictForCSC_R(SEXP handle,
   SEXP indptr,
   SEXP indices,
   SEXP data,
@@ -446,7 +446,7 @@ DllExport SEXP LGBM_BoosterPredictForCSC_R(SEXP handle,
 * \param out prediction result
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterPredictForMat_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterPredictForMat_R(SEXP handle,
   SEXP data,
   SEXP nrow,
   SEXP ncol,
@@ -463,7 +463,7 @@ DllExport SEXP LGBM_BoosterPredictForMat_R(SEXP handle,
 * \param filename file name
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterSaveModel_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterSaveModel_R(SEXP handle,
   SEXP num_iteration,
   SEXP filename,
   SEXP call_state);
@@ -475,7 +475,7 @@ DllExport SEXP LGBM_BoosterSaveModel_R(SEXP handle,
 * \param out_str json format string of model
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterDumpModel_R(SEXP handle,
+LIGHTGBM_C_EXPORT SEXP LGBM_BoosterDumpModel_R(SEXP handle,
   SEXP num_iteration,
   SEXP buffer_len,
   SEXP actual_len,

R-package/unix_build_package.sh

+cp ../include ./src/include -rf
+cp ../src ./src/src -rf
+rm ./src/Makevars
+cp ./src/Makevars_fullcode ./src/Makevars -f
+R CMD build --no-build-vignettes .
\ No newline at end of file

R-package/win_build_package.cmd

+xcopy ..\include src\include /e /i /y
+xcopy ..\src src\src /e /i /y
+del .\src\Makevars.win
+copy .\src\Makevars_fullcode.win .\src\Makevars.win /y
+R CMD build --no-build-vignettes .
\ No newline at end of file