Stylistic changes r package (#184)

* src & callbacks

* lgb.Booster and utils

* cv

* wip lgb.Dataset

* lgb.Dataset

* lgb.Predictor

* lgb.train

* typos

* add flags to facilitate macosx compilation

* fix basic_string template error with clang

* most unfortunate mode of development

* fixup tests

* last test

* roxygen

* roxygen v5.x.x

R-package/man/lgb.Dataset.construct.Rd

@@ -2,7 +2,7 @@
 % Please edit documentation in R/lgb.Dataset.R
 \name{lgb.Dataset.construct}
 \alias{lgb.Dataset.construct}
-\title{Construct Dataset explicit}
+\title{Construct Dataset explicitly}
 \usage{
 lgb.Dataset.construct(dataset)
 }
@@ -10,12 +10,14 @@ lgb.Dataset.construct(dataset)
 \item{dataset}{Object of class \code{lgb.Dataset}}
 }
 \description{
-Construct Dataset explicit
+Construct Dataset explicitly
 }
 \examples{
-data(agaricus.train, package='lightgbm')
-train <- agaricus.train
-dtrain <- lgb.Dataset(train$data, label=train$label)
-lgb.Dataset.construct(dtrain)
+\dontrun{
+  data(agaricus.train, package='lightgbm')
+  train <- agaricus.train
+  dtrain <- lgb.Dataset(train$data, label=train$label)
+  lgb.Dataset.construct(dtrain)
+}
 }
 

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 a validation data}
+\title{Contruct validation data}
 \usage{
 lgb.Dataset.create.valid(dataset, data, info = list(), ...)
 }
@@ -19,14 +19,16 @@ lgb.Dataset.create.valid(dataset, data, info = list(), ...)
 constructed dataset
 }
 \description{
-Contruct a validation data according to training data
+Contruct validation data according to training data
 }
 \examples{
-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)
+\dontrun{
+  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.Dataset.save.Rd

@@ -2,7 +2,7 @@
 % Please edit documentation in R/lgb.Dataset.R
 \name{lgb.Dataset.save}
 \alias{lgb.Dataset.save}
-\title{save \code{lgb.Dataset} to binary file}
+\title{Save \code{lgb.Dataset} to a binary file}
 \usage{
 lgb.Dataset.save(dataset, fname)
 }
@@ -15,12 +15,14 @@ lgb.Dataset.save(dataset, fname)
 passed dataset
 }
 \description{
-save \code{lgb.Dataset} to binary file
+Save \code{lgb.Dataset} to a binary file
 }
 \examples{
-data(agaricus.train, package='lightgbm')
-train <- agaricus.train
-dtrain <- lgb.Dataset(train$data, label=train$label)
-lgb.Dataset.save(dtrain, "data.bin")
+\dontrun{
+  data(agaricus.train, package='lightgbm')
+  train <- agaricus.train
+  dtrain <- lgb.Dataset(train$data, label=train$label)
+  lgb.Dataset.save(dtrain, "data.bin")
+}
 }
 

R-package/man/lgb.Dataset.set.categorical.Rd

@@ -2,7 +2,7 @@
 % Please edit documentation in R/lgb.Dataset.R
 \name{lgb.Dataset.set.categorical}
 \alias{lgb.Dataset.set.categorical}
-\title{set categorical feature of \code{lgb.Dataset}}
+\title{Set categorical feature of \code{lgb.Dataset}}
 \usage{
 lgb.Dataset.set.categorical(dataset, categorical_feature)
 }
@@ -15,14 +15,16 @@ lgb.Dataset.set.categorical(dataset, categorical_feature)
 passed dataset
 }
 \description{
-set categorical feature of \code{lgb.Dataset}
+Set categorical feature of \code{lgb.Dataset}
 }
 \examples{
-data(agaricus.train, package='lightgbm')
-train <- agaricus.train
-dtrain <- lgb.Dataset(train$data, label=train$label)
-lgb.Dataset.save(dtrain, 'lgb.Dataset.data')
-dtrain <- lgb.Dataset('lgb.Dataset.data')
-lgb.Dataset.set.categorical(dtrain, 1:2)
+\dontrun{
+  data(agaricus.train, package='lightgbm')
+  train <- agaricus.train
+  dtrain <- lgb.Dataset(train$data, label=train$label)
+  lgb.Dataset.save(dtrain, 'lgb.Dataset.data')
+  dtrain <- lgb.Dataset('lgb.Dataset.data')
+  lgb.Dataset.set.categorical(dtrain, 1:2)
+}
 }
 

R-package/man/lgb.Dataset.set.reference.Rd

@@ -2,7 +2,7 @@
 % Please edit documentation in R/lgb.Dataset.R
 \name{lgb.Dataset.set.reference}
 \alias{lgb.Dataset.set.reference}
-\title{set reference of \code{lgb.Dataset}}
+\title{Set reference of \code{lgb.Dataset}}
 \usage{
 lgb.Dataset.set.reference(dataset, reference)
 }
@@ -15,16 +15,17 @@ lgb.Dataset.set.reference(dataset, reference)
 passed dataset
 }
 \description{
-set reference of \code{lgb.Dataset}. 
-If you want to use validation data, you should set its reference to training data
+If you want to use validation data, you should set reference to training data
 }
 \examples{
-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(test$data, test=train$label)
-lgb.Dataset.set.reference(dtest, dtrain)
+\dontrun{
+  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(test$data, test=train$label)
+  lgb.Dataset.set.reference(dtest, dtrain)
+}
 }
 

R-package/man/lgb.dump.Rd

@@ -18,16 +18,18 @@ json format of model
 Dump LightGBM model to json
 }
 \examples{
-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)
-json_model <- lgb.dump(model)
+\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)
+  json_model <- lgb.dump(model)
+}
 }
 

R-package/man/lgb.load.Rd

@@ -16,17 +16,19 @@ booster
 Load LightGBM model from saved model file
 }
 \examples{
-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)
-lgb.save(model, "model.txt")
-load_booster <- lgb.load("model.txt")
+\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)
+  lgb.save(model, "model.txt")
+  load_booster <- lgb.load("model.txt")
+}
 }
 

R-package/man/lgb.save.Rd

@@ -20,16 +20,18 @@ booster
 Save LightGBM model
 }
 \examples{
-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)
-lgb.save(model, "model.txt")
+\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)
+  lgb.save(model, "model.txt")
+}
 }
 

R-package/man/lgb.train.Rd

@@ -46,11 +46,11 @@ if verbose > 0 , also will record iteration message to booster$record_evals}
 
 \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 
+\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, 
+(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}
@@ -73,7 +73,7 @@ List of callback functions that are applied at each iteration.}
 
 \item{...}{other parameters, see parameters.md for more informations}
 
-\item{valids}{a list of \code{lgb.Dataset} object, used for validation}
+\item{valids}{a list of \code{lgb.Dataset} objects, used for validation}
 
 \item{params}{List of parameters}
 
@@ -83,14 +83,14 @@ List of callback functions that are applied at each iteration.}
 
 \item{obj}{objective function, can be character or custom objective function}
 
-\item{eval}{evaluation function, can be (list of) character or custom eval function}
+\item{eval}{evaluation function, can be (a list of) character or custom eval function}
 
 \item{verbose}{verbosity for output
-if verbose > 0 , also will record iteration message to booster$record_evals}
+if \code{verbose > 0}, also will record iteration message to \code{booster$record_evals}}
 
-\item{eval_freq}{evalutaion output frequence}
+\item{eval_freq}{evalutaion output frequency}
 
-\item{init_model}{path of model file of \code{lgb.Booster} object, will continue train from this model}
+\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}
 
@@ -119,25 +119,30 @@ a trained booster model \code{lgb.Booster}.
 Main CV logic for LightGBM
 
 Main training logic for LightGBM
+
+Simple interface for training an lightgbm model.
+Its documentation is combined with lgb.train.
 }
 \examples{
-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)
-
-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)
-
+\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)
+}
+\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)
+}
 }
 

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

@@ -14,41 +14,42 @@
 
 \item{num_iteration}{number of iteration want to predict with, NULL or <= 0 means use best iteration}
 
-\item{rawscore}{whether the prediction should be returned in the for of original untransformed 
-sum of predictions from boosting iterations' results. E.g., setting \code{rawscore=TRUE} for 
+\item{rawscore}{whether the prediction should be returned in the for of original untransformed
+sum of predictions from boosting iterations' results. E.g., setting \code{rawscore=TRUE} for
 logistic regression would result in predictions for log-odds instead of probabilities.}
 
 \item{predleaf}{whether predict leaf index instead.}
 
 \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 
+\item{reshape}{whether to reshape the vector of predictions to a matrix form when there are several
 prediction outputs per case.}
 }
 \value{
 For regression or binary classification, it returns a vector of length \code{nrows(data)}.
-For multiclass classification, either a \code{num_class * nrows(data)} vector or 
-a \code{(nrows(data), num_class)} dimension matrix is returned, depending on 
+For multiclass classification, either a \code{num_class * nrows(data)} vector or
+a \code{(nrows(data), num_class)} dimension matrix is returned, depending on
 the \code{reshape} value.
 
-When \code{predleaf = TRUE}, the output is a matrix object with the 
+When \code{predleaf = TRUE}, the output is a matrix object with the
 number of columns corresponding to the number of trees.
 }
 \description{
 Predicted values based on class \code{lgb.Booster}
 }
 \examples{
-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)
-preds <- predict(model, test$data)
-
+\dontrun{
+  library(lightgbm)
+  data(agaricus.train, package='lightgbm')
+  train <- agaricus.train
+  dtrain <- lgb.Dataset(train$data, label=train$label)
+  data(agaricus.test, package='lightgbm')
+  test <- agaricus.test
+  dtest <- lgb.Dataset.create.valid(dtrain, test$data, label=test$label)
+  params <- list(objective="regression", metric="l2")
+  valids <- list(test=dtest)
+  model <- lgb.train(params, dtrain, 100, valids, min_data=1, learning_rate=1, early_stopping_rounds=10)
+  preds <- predict(model, test$data)
+}
 }
 

R-package/man/setinfo.Rd

@@ -35,13 +35,15 @@ The \code{name} field can be one of the following:
 }
 }
 \examples{
-data(agaricus.train, package='lightgbm')
-train <- agaricus.train
-dtrain <- lgb.Dataset(train$data, label=train$label)
-lgb.Dataset.construct(dtrain)
-labels <- getinfo(dtrain, 'label')
-setinfo(dtrain, 'label', 1-labels)
-labels2 <- getinfo(dtrain, 'label')
-stopifnot(all.equal(labels2, 1-labels))
+\dontrun{
+  data(agaricus.train, package='lightgbm')
+  train <- agaricus.train
+  dtrain <- lgb.Dataset(train$data, label=train$label)
+  lgb.Dataset.construct(dtrain)
+  labels <- getinfo(dtrain, 'label')
+  setinfo(dtrain, 'label', 1-labels)
+  labels2 <- getinfo(dtrain, 'label')
+  stopifnot(all.equal(labels2, 1-labels))
+}
 }
 

R-package/man/slice.Rd

@@ -3,7 +3,7 @@
 \name{slice}
 \alias{slice}
 \alias{slice.lgb.Dataset}
-\title{Slice an dataset}
+\title{Slice a dataset}
 \usage{
 slice(dataset, ...)
 
@@ -20,16 +20,17 @@ slice(dataset, ...)
 constructed sub dataset
 }
 \description{
-Get a new Dataset containing the specified rows of
+Get a new \code{lgb.Dataset} containing the specified rows of
 orginal lgb.Dataset object
 }
 \examples{
-data(agaricus.train, package='lightgbm')
-train <- agaricus.train
-dtrain <- lgb.Dataset(train$data, label=train$label)
-
-dsub <- slice(dtrain, 1:42)
-labels1 <- getinfo(dsub, 'label')
+\dontrun{
+  data(agaricus.train, package='lightgbm')
+  train <- agaricus.train
+  dtrain <- lgb.Dataset(train$data, label=train$label)
 
+  dsub <- slice(dtrain, 1:42)
+  labels1 <- getinfo(dsub, 'label')
+}
 }
 

R-package/src/Makevars

@@ -4,9 +4,9 @@ PKGROOT=../../
 ENABLE_STD_THREAD=1
 CXX_STD = CXX11
 
-LGBM_RFLAGS = -DUSE_SOCKET 
+LGBM_RFLAGS = -DUSE_SOCKET
 
-PKG_CPPFLAGS= -I$(PKGROOT)/include $(LGBM_RFLAGS) 
+PKG_CPPFLAGS= -I$(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-all.o ./lightgbm_R.o 
+PKG_LIBS = $(SHLIB_OPENMP_CFLAGS) $(SHLIB_PTHREAD_FLAGS)
+OBJECTS = ./lightgbm-all.o ./lightgbm_R.o

R-package/src/R_object_helper.h

 /*
-* A simple wrapper for access data in R object.
+* A simple wrapper for accessing data in R object.
 * Due to license issue(GPLv2), we cannot include R's header file, so use this simple wrapper instead.
-* However, If R change its define of object, this file need to be updated as well.
+* However, if R changes the way it defines objects, this file will need to be updated as well.
 */
 #ifndef R_OBJECT_HELPER_H_
 #define R_OBJECT_HELPER_H_

R-package/src/lightgbm_R.h

@@ -8,11 +8,10 @@
 #include "R_object_helper.h"
 
 
-
 /*!
 * \brief get string message of the last error
-*  all function in this file will return 0 when succeed
-*  and -1 when an error occured,
+*  all functions in this file will return 0 on success
+*  and -1 when an error occured
 * \return err_msg error inforomation
 * \return error inforomation
 */
@@ -21,10 +20,10 @@ DllExport SEXP LGBM_GetLastError_R(SEXP buf_len, SEXP actual_len, SEXP err_msg);
 // --- start Dataset interface
 
 /*!
-* \brief load data set from file like the command_line LightGBM do
+* \brief load data set from file like the command_line LightGBM does
 * \param filename the name of the file
 * \param parameters additional parameters
-* \param reference used to align bin mapper with other dataset, nullptr means don't used
+* \param reference used to align bin mapper with other dataset, nullptr means not used
 * \param out created dataset
 * \return 0 when succeed, -1 when failure happens
 */
@@ -43,7 +42,7 @@ DllExport SEXP LGBM_DatasetCreateFromFile_R(SEXP filename,
 * \param nelem number of nonzero elements in the matrix
 * \param num_row number of rows
 * \param parameters additional parameters
-* \param reference used to align bin mapper with other dataset, nullptr means don't used
+* \param reference used to align bin mapper with other dataset, nullptr means not used
 * \param out created dataset
 * \return 0 when succeed, -1 when failure happens
 */
@@ -65,7 +64,7 @@ DllExport SEXP LGBM_DatasetCreateFromCSC_R(SEXP indptr,
 * \param nrow number of rows
 * \param ncol number columns
 * \param parameters additional parameters
-* \param reference used to align bin mapper with other dataset, nullptr means don't used
+* \param reference used to align bin mapper with other dataset, nullptr means not used
 * \param out created dataset
 * \return 0 when succeed, -1 when failure happens
 */
@@ -117,7 +116,7 @@ DllExport SEXP LGBM_DatasetGetFeatureNames_R(SEXP handle,
 
 /*!
 * \brief save dateset to binary file
-* \param handle a instance of dataset
+* \param handle an instance of dataset
 * \param filename file name
 * \return 0 when succeed, -1 when failure happens
 */
@@ -127,7 +126,7 @@ DllExport SEXP LGBM_DatasetSaveBinary_R(SEXP handle,
 
 /*!
 * \brief free dataset
-* \param handle a instance of dataset
+* \param handle an instance of dataset
 * \return 0 when succeed, -1 when failure happens
 */
 DllExport SEXP LGBM_DatasetFree_R(SEXP handle,
@@ -135,9 +134,9 @@ DllExport SEXP LGBM_DatasetFree_R(SEXP handle,
 
 /*!
 * \brief set vector to a content in info
-*        Note: group and group only work for C_API_DTYPE_INT32
+*        Note: group and group_id only work for C_API_DTYPE_INT32
 *              label and weight only work for C_API_DTYPE_FLOAT32
-* \param handle a instance of dataset
+* \param handle an instance of dataset
 * \param field_name field name, can be label, weight, group, group_id
 * \param field_data pointer to vector
 * \param num_element number of element in field_data
@@ -151,7 +150,7 @@ DllExport SEXP LGBM_DatasetSetField_R(SEXP handle,
 
 /*!
 * \brief get size of info vector from dataset
-* \param handle a instance of dataset
+* \param handle an instance of dataset
 * \param field_name field name
 * \param out size of info vector from dataset
 * \return 0 when succeed, -1 when failure happens
@@ -163,7 +162,7 @@ DllExport SEXP LGBM_DatasetGetFieldSize_R(SEXP handle,
 
 /*!
 * \brief get info vector from dataset
-* \param handle a instance of dataset
+* \param handle an instance of dataset
 * \param field_name field name
 * \param field_data pointer to vector
 * \return 0 when succeed, -1 when failure happens
@@ -226,7 +225,7 @@ DllExport SEXP LGBM_BoosterCreateFromModelfile_R(SEXP filename,
   SEXP call_state);
 
 /*!
-* \brief Merge model in two booster to first handle
+* \brief Merge model in two boosters to first handle
 * \param handle handle, will merge other handle to this
 * \param other_handle
 * \return 0 when succeed, -1 when failure happens
@@ -266,12 +265,12 @@ DllExport SEXP LGBM_BoosterResetParameter_R(SEXP handle,
   SEXP call_state);
 
 /*!
-* \brief Get number of class
+* \brief Get number of classes
 * \param handle handle
 * \param out number of classes
 * \return 0 when succeed, -1 when failure happens
 */
-DllExport SEXP LGBM_BoosterGetNumClasses_R(SEXP handle, 
+DllExport SEXP LGBM_BoosterGetNumClasses_R(SEXP handle,
   SEXP out,
   SEXP call_state);
 
@@ -311,7 +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, 
+DllExport SEXP LGBM_BoosterGetCurrentIteration_R(SEXP handle,
   SEXP out,
   SEXP call_state);
 
@@ -320,7 +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, 
+DllExport SEXP LGBM_BoosterGetEvalNames_R(SEXP handle,
   SEXP buf_len,
   SEXP actual_len,
   SEXP eval_names,
@@ -351,8 +350,8 @@ DllExport SEXP LGBM_BoosterGetNumPredict_R(SEXP handle,
   SEXP call_state);
 
 /*!
-* \brief Get prediction for training data and validation data
-this can be used to support customized eval function
+* \brief Get prediction for training data and validation data.
+*        This can be used to support customized eval function
 * \param handle handle
 * \param data_idx 0:training data, 1: 1st valid data, 2:2nd valid data ...
 * \param out_result, used to store predict result, should pre-allocate memory
@@ -404,14 +403,14 @@ DllExport SEXP LGBM_BoosterCalcNumPredict_R(SEXP handle,
 /*!
 * \brief make prediction for an new data set
 *        Note:  should pre-allocate memory for out_result,
-*               for noraml and raw score: its length is equal to num_class * num_data
+*               for normal and raw score: its length is equal to num_class * num_data
 *               for leaf index, its length is equal to num_class * num_data * num_iteration
 * \param handle handle
 * \param indptr pointer to row headers
 * \param indices findex
 * \param data fvalue
 * \param nindptr number of cols in the matrix + 1
-* \param nelem number of nonzero elements in the matrix
+* \param nelem number of non-zero elements in the matrix
 * \param num_row number of rows
 * \param is_rawscore
 * \param is_leafidx
@@ -433,9 +432,9 @@ DllExport SEXP LGBM_BoosterPredictForCSC_R(SEXP handle,
   SEXP call_state);
 
 /*!
-* \brief make prediction for an new data set
+* \brief make prediction for a new data set
 *        Note:  should pre-allocate memory for out_result,
-*               for noraml and raw score: its length is equal to num_class * num_data
+*               for normal and raw score: its length is equal to num_class * num_data
 *               for leaf index, its length is equal to num_class * num_data * num_iteration
 * \param handle handle
 * \param data pointer to the data space
@@ -483,4 +482,4 @@ DllExport SEXP LGBM_BoosterDumpModel_R(SEXP handle,
   SEXP out_str,
   SEXP call_state);
 
-#endif // LIGHTGBM_R_H_
\ No newline at end of file
+#endif // LIGHTGBM_R_H_

R-package/tests/testthat/test_basic.R

-require(lightgbm)
-
 context("basic functions")
 
 data(agaricus.train, package='lightgbm')
@@ -11,17 +9,17 @@ windows_flag = grepl('Windows', Sys.info()[['sysname']])
 
 test_that("train and predict binary classification", {
   nrounds = 10
-  bst <- lightgbm(data = train$data, label = train$label, num_leaves = 5, 
+  bst <- lightgbm(data = train$data, label = train$label, num_leaves = 5,
     nrounds = nrounds, objective = "binary", metric="binary_error")
   expect_false(is.null(bst$record_evals))
   record_results <- lgb.get.eval.result(bst, "train", "binary_error")
   expect_lt(min(record_results), 0.02)
 
   pred <- predict(bst, test$data)
-  expect_length(pred, 1611)
-  
+  expect_equal(length(pred), 1611)
+
   pred1 <- predict(bst, train$data, num_iteration = 1)
-  expect_length(pred1, 6513)
+  expect_equal(length(pred1), 6513)
   err_pred1 <- sum((pred1 > 0.5) != train$label)/length(train$label)
   err_log <- record_results[1]
   expect_lt(abs(err_pred1 - err_log), 10e-6)
@@ -38,10 +36,9 @@ test_that("train and predict softmax", {
   expect_false(is.null(bst$record_evals))
   record_results <- lgb.get.eval.result(bst, "train", "multi_error")
   expect_lt(min(record_results), 0.03)
-  
-  pred <- predict(bst, as.matrix(iris[, -5]))
-  expect_length(pred, nrow(iris) * 3)
 
+  pred <- predict(bst, as.matrix(iris[, -5]))
+  expect_equal(length(pred), nrow(iris) * 3)
 })
 
 
@@ -82,4 +79,3 @@ test_that("cv works", {
   bst <- lgb.cv(params, dtrain, 10, nflod=5, min_data=1, learning_rate=1, early_stopping_rounds=10)
   expect_false(is.null(bst$record_evals))
 })
-

R-package/tests/testthat/test_custom_objective.R

 context('Test models with custom objective')
 
-require(lightgbm)
-
 data(agaricus.train, package='lightgbm')
 data(agaricus.test, package='lightgbm')
 dtrain <- lgb.Dataset(agaricus.train$data, label = agaricus.train$label)
@@ -27,10 +25,6 @@ param <- list(num_leaves=8, learning_rate=1,
 num_round <- 10
 
 test_that("custom objective works", {
-  bst <- lgb.train(param, dtrain, num_round, watchlist, eval=evalerror)
+  bst <- lgb.train(param, dtrain, num_round, watchlist, eval = evalerror)
   expect_false(is.null(bst$record_evals))
 })
-
-
-
-

include/LightGBM/utils/log.h

 #ifndef LIGHTGBM_UTILS_LOG_H_
 #define LIGHTGBM_UTILS_LOG_H_
 
+#include <iostream>
 #include <cstdio>
 #include <cstdlib>
 #include <cstdarg>
@@ -32,7 +33,7 @@ enum class LogLevel: int {
 
 
 /*!
-* \brief A static Log class 
+* \brief A static Log class
 */
 class Log {
 public:
@@ -87,14 +88,14 @@ private:
     }
   }
 
-  // a trick to use static variable in header file. 
+  // a trick to use static variable in header file.
   // May be not good, but avoid to use an additional cpp file
 #if defined(_MSC_VER)
   static LogLevel& GetLevel() { static __declspec(thread) LogLevel level = LogLevel::Info; return level; }
 #else
   static LogLevel& GetLevel() { static thread_local LogLevel level = LogLevel::Info; return level; }
 #endif
-  
+
 };
 
 }  // namespace LightGBM

src/application/application.cpp

@@ -120,7 +120,7 @@ void Application::LoadData() {
        GlobalSyncUpByMin<int>(config_.io_config.data_random_seed);
   }
 
-  DatasetLoader dataset_loader(config_.io_config, predict_fun, 
+  DatasetLoader dataset_loader(config_.io_config, predict_fun,
     boosting_->NumberOfClasses(), config_.io_config.data_filename.c_str());
   // load Training data
   if (config_.is_parallel_find_bin) {