[R-package] updated examples and removed dontrun guards on them in roxygen (#1626)

R-package/R/lgb.Booster.R

@@ -633,7 +633,6 @@ Booster <- R6::R6Class(
 #' number of columns corresponding to the number of trees.
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -651,7 +650,6 @@ Booster <- R6::R6Class(
 #'                    learning_rate = 1,
 #'                    early_stopping_rounds = 10)
 #' preds <- predict(model, test$data)
-#' }
 #' 
 #' @rdname predict.lgb.Booster
 #' @export
@@ -692,7 +690,6 @@ predict.lgb.Booster <- function(object,
 #' @return lgb.Booster
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -713,7 +710,6 @@ predict.lgb.Booster <- function(object,
 #' load_booster <- lgb.load(filename = "model.txt")
 #' model_string <- model$save_model_to_string(NULL) # saves best iteration
 #' load_booster_from_str <- lgb.load(model_str = model_string)
-#' }
 #' 
 #' @rdname lgb.load
 #' @export
@@ -752,7 +748,6 @@ lgb.load <- function(filename = NULL, model_str = NULL){
 #' @return lgb.Booster
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -770,7 +765,6 @@ lgb.load <- function(filename = NULL, model_str = NULL){
 #'                    learning_rate = 1,
 #'                    early_stopping_rounds = 10)
 #' lgb.save(model, "model.txt")
-#' }
 #' 
 #' @rdname lgb.save
 #' @export
@@ -801,7 +795,6 @@ lgb.save <- function(booster, filename, num_iteration = NULL){
 #' @return json format of model
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -819,7 +812,6 @@ lgb.save <- function(booster, filename, num_iteration = NULL){
 #'                    learning_rate = 1,
 #'                    early_stopping_rounds = 10)
 #' json_model <- lgb.dump(model)
-#' }
 #' 
 #' @rdname lgb.dump
 #' @export
@@ -847,7 +839,6 @@ lgb.dump <- function(booster, num_iteration = NULL){
 #' @return vector of evaluation result
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -865,7 +856,6 @@ lgb.dump <- function(booster, num_iteration = NULL){
 #'                    learning_rate = 1,
 #'                    early_stopping_rounds = 10)
 #' lgb.get.eval.result(model, "test", "l2")
-#' }
 #' 
 #' @rdname lgb.get.eval.result
 #' @export

R-package/R/lgb.Dataset.R

@@ -311,6 +311,7 @@ Dataset <- R6::R6Class(
       } else if (is.matrix(private$raw_data) || methods::is(private$raw_data, "dgCMatrix")) {
 
         # Check if dgCMatrix (sparse matrix column compressed)
+        # NOTE: requires Matrix package
         dim(private$raw_data)
 
       } else {
@@ -392,9 +393,11 @@ Dataset <- R6::R6Class(
 
       # Check for info name and handle
       if (is.null(private$info[[name]])) {
+        
         if (lgb.is.null.handle(private$handle)){
-          stop("Cannot perform getinfo before construct Dataset.")
+          stop("Cannot perform getinfo before constructing Dataset.")
         }
+        
         # Get field size of info
         info_len <- 0L
         info_len <- lgb.call("LGBM_DatasetGetFieldSize_R",
@@ -646,7 +649,6 @@ Dataset <- R6::R6Class(
 #' @return constructed dataset
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -654,7 +656,6 @@ Dataset <- R6::R6Class(
 #' lgb.Dataset.save(dtrain, "lgb.Dataset.data")
 #' dtrain <- lgb.Dataset("lgb.Dataset.data")
 #' lgb.Dataset.construct(dtrain)
-#' }
 #'
 #' @export
 lgb.Dataset <- function(data,
@@ -692,7 +693,6 @@ lgb.Dataset <- function(data,
 #' @return constructed dataset
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -700,7 +700,6 @@ lgb.Dataset <- function(data,
 #' data(agaricus.test, package = "lightgbm")
 #' test <- agaricus.test
 #' dtest <- lgb.Dataset.create.valid(dtrain, test$data, label = test$label)
-#' }
 #'
 #' @export
 lgb.Dataset.create.valid <- function(dataset, data, info = list(), ...) {
@@ -720,13 +719,11 @@ lgb.Dataset.create.valid <- function(dataset, data, info = list(), ...) {
 #' @param dataset Object of class \code{lgb.Dataset}
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
 #' lgb.Dataset.construct(dtrain)
-#' }
 #'
 #' @export
 lgb.Dataset.construct <- function(dataset) {
@@ -754,7 +751,6 @@ lgb.Dataset.construct <- function(dataset) {
 #' be directly used with an \code{lgb.Dataset} object.
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -763,7 +759,6 @@ lgb.Dataset.construct <- function(dataset) {
 #' stopifnot(nrow(dtrain) == nrow(train$data))
 #' stopifnot(ncol(dtrain) == ncol(train$data))
 #' stopifnot(all(dim(dtrain) == dim(train$data)))
-#' }
 #'
 #' @rdname dim
 #' @export
@@ -793,7 +788,6 @@ dim.lgb.Dataset <- function(x, ...) {
 #' Since row names are irrelevant, it is recommended to use \code{colnames} directly.
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -803,7 +797,6 @@ dim.lgb.Dataset <- function(x, ...) {
 #' colnames(dtrain)
 #' colnames(dtrain) <- make.names(1:ncol(train$data))
 #' print(dtrain, verbose = TRUE)
-#' }
 #'
 #' @rdname dimnames.lgb.Dataset
 #' @export
@@ -864,15 +857,14 @@ dimnames.lgb.Dataset <- function(x) {
 #' @return constructed sub dataset
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
 #'
 #' dsub <- lightgbm::slice(dtrain, 1:42)
+#' lgb.Dataset.construct(dsub)
 #' labels <- lightgbm::getinfo(dsub, "label")
-#' }
 #'
 #' @export
 slice <- function(dataset, ...) {
@@ -911,7 +903,6 @@ slice.lgb.Dataset <- function(dataset, idxset, ...) {
 #' }
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -923,7 +914,6 @@ slice.lgb.Dataset <- function(dataset, idxset, ...) {
 #'
 #' labels2 <- lightgbm::getinfo(dtrain, "label")
 #' stopifnot(all(labels2 == 1 - labels))
-#' }
 #'
 #' @export
 getinfo <- function(dataset, ...) {
@@ -963,7 +953,6 @@ getinfo.lgb.Dataset <- function(dataset, name, ...) {
 #' }
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -975,7 +964,6 @@ getinfo.lgb.Dataset <- function(dataset, name, ...) {
 #'
 #' labels2 <- lightgbm::getinfo(dtrain, "label")
 #' stopifnot(all.equal(labels2, 1 - labels))
-#' }
 #'
 #' @export
 setinfo <- function(dataset, ...) {
@@ -1003,7 +991,6 @@ setinfo.lgb.Dataset <- function(dataset, name, info, ...) {
 #' @return passed dataset
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -1011,7 +998,6 @@ setinfo.lgb.Dataset <- function(dataset, name, info, ...) {
 #' lgb.Dataset.save(dtrain, "lgb.Dataset.data")
 #' dtrain <- lgb.Dataset("lgb.Dataset.data")
 #' lgb.Dataset.set.categorical(dtrain, 1:2)
-#' }
 #'
 #' @rdname lgb.Dataset.set.categorical
 #' @export
@@ -1037,7 +1023,6 @@ lgb.Dataset.set.categorical <- function(dataset, categorical_feature) {
 #' @return passed dataset
 #'
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package ="lightgbm")
 #' train <- agaricus.train
@@ -1046,7 +1031,6 @@ lgb.Dataset.set.categorical <- function(dataset, categorical_feature) {
 #' test <- agaricus.test
 #' dtest <- lgb.Dataset(test$data, test = train$label)
 #' lgb.Dataset.set.reference(dtest, dtrain)
-#' }
 #'
 #' @rdname lgb.Dataset.set.reference
 #' @export
@@ -1070,13 +1054,11 @@ lgb.Dataset.set.reference <- function(dataset, reference) {
 #'
 #' @examples
 #'
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
 #' lgb.Dataset.save(dtrain, "data.bin")
-#' }
 #'
 #' @rdname lgb.Dataset.save
 #' @export

R-package/R/lgb.cv.R

@@ -55,7 +55,6 @@ CVBooster <- R6::R6Class(
 #' @return a trained model \code{lgb.CVBooster}.
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -68,7 +67,6 @@ CVBooster <- R6::R6Class(
 #'                 min_data = 1,
 #'                 learning_rate = 1,
 #'                 early_stopping_rounds = 10)
-#' }
 #' @export
 lgb.cv <- function(params = list(),
                    data,

R-package/R/lgb.importance.R

@@ -16,13 +16,12 @@
 #' }
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
 #'
-#' params = list(objective = "binary",
+#' 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)
@@ -30,7 +29,6 @@
 #'
 #' tree_imp1 <- lgb.importance(model, percentage = TRUE)
 #' tree_imp2 <- lgb.importance(model, percentage = FALSE)
-#' }
 #' 
 #' @importFrom magrittr %>% %T>%
 #' @importFrom data.table :=

R-package/R/lgb.interprete.R

@@ -17,8 +17,6 @@
 #' For multiclass classification, a \code{list} of \code{data.table} with the Feature column and Contribution columns to each class.
 #' 
 #' @examples
-#' \dontrun{
-#' library(lightgbm)
 #' Sigmoid <- function(x) 1 / (1 + exp(-x))
 #' Logit <- function(x) log(x / (1 - x))
 #' data(agaricus.train, package = "lightgbm")
@@ -27,15 +25,18 @@
 #' 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)
+#' 
+#' 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)
-#'
+#' 
 #' tree_interpretation <- lgb.interprete(model, test$data, 1:5)
-#' }
 #' 
 #' @importFrom magrittr %>% %T>%
 #' @export

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

@@ -30,21 +30,18 @@
 #' }
 #'
 #' @examples
-#' \dontrun{
-#' library(lightgbm)
 #'
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
 #' dtrain <- lgb.Dataset(train$data, label = train$label)
 #'
-#' params = list(objective = "binary",
+#' 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)
-#' }
 #'
 #' @importFrom magrittr %>%
 #' @importFrom data.table := data.table rbindlist

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

@@ -17,20 +17,23 @@
 #' and silently returns a processed data.table with \code{top_n} features sorted by defined importance.
 #' 
 #' @examples
-#' \dontrun{
-#' 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")
-#' }
+# 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)
+# 
+# tree_imp <- lgb.importance(model, percentage = TRUE)
+# lgb.plot.importance(tree_imp, top_n = 10, measure = "Gain")
 #' @importFrom graphics barplot par
 #' @export
 lgb.plot.importance <- function(tree_imp,

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

@@ -16,7 +16,6 @@
 #' The \code{lgb.plot.interpretation} function creates a \code{barplot}.
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' Sigmoid <- function(x) {1 / (1 + exp(-x))}
 #' Logit <- function(x) {log(x / (1 - x))}
@@ -27,7 +26,7 @@
 #' data(agaricus.test, package = "lightgbm")
 #' test <- agaricus.test
 #' 
-#' params = list(objective = "binary",
+#' 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)
@@ -35,7 +34,6 @@
 #' 
 #' tree_interpretation <- lgb.interprete(model, test$data, 1:5)
 #' lgb.plot.interpretation(tree_interpretation[[1]], top_n = 10)
-#' }
 #' @importFrom graphics barplot par
 #' @export
 lgb.plot.interpretation <- function(tree_interpretation_dt,

R-package/R/lgb.prepare.R

-#' Data preparator for LightGBM datasets (numeric)
-#'
-#' Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric without integers. Please use \code{lgb.prepare_rules} if you want to apply this transformation to other datasets.
-#' 
-#' @param data A data.frame or data.table to prepare.
-#' 
-#' @return The cleaned dataset. It must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
-#' 
-#' @examples
-#' \dontrun{
-#' library(lightgbm)
-#' data(iris)
-#' 
-#' str(iris)
-#' # 'data.frame':	150 obs. of  5 variables:
-#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
-#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
-#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
-#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
-#' # $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
-#' 
-#' str(lgb.prepare(data = iris)) # Convert all factors/chars to numeric
-#' # 'data.frame':	150 obs. of  5 variables:
-#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
-#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
-#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
-#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
-#' # $ Species     : num  1 1 1 1 1 1 1 1 1 1 ...
-#' 
-#' # When lightgbm package is installed, and you do not want to load it
-#' # You can still use the function!
-#' lgb.unloader()
-#' str(lightgbm::lgb.prepare(data = iris))
-#' # 'data.frame':	150 obs. of  5 variables:
-#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
-#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
-#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
-#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
-#' # $ Species     : num  1 1 1 1 1 1 1 1 1 1 ...
-#' }
-#' 
-#' @export
-lgb.prepare <- function(data) {
-  
-  # data.table not behaving like data.frame
-  if ("data.table" %in% class(data)) {
-    
-    # Get data classes
-    list_classes <- sapply(data, class)
-    
-    # Convert characters to factors only (we can change them to numeric after)
-    is_char <- which(list_classes == "character")
-    if (length(is_char) > 0) {
-      data[, (is_char) := lapply(.SD, function(x) {as.numeric(as.factor(x))}), .SDcols = is_char]
-    }
-    
-    # Convert factors to numeric (integer is more efficient actually)
-    is_fact <- c(which(list_classes == "factor"), is_char)
-    if (length(is_fact) > 0) {
-      data[, (is_fact) := lapply(.SD, function(x) {as.numeric(x)}), .SDcols = is_fact]
-    }
-    
-  } else {
-    
-    # Default routine (data.frame)
-    if ("data.frame" %in% class(data)) {
-      
-      # Get data classes
-      list_classes <- sapply(data, class)
-      
-      # Convert characters to factors to numeric (integer is more efficient actually)
-      is_char <- which(list_classes == "character")
-      if (length(is_char) > 0) {
-        data[is_char] <- lapply(data[is_char], function(x) {as.numeric(as.factor(x))})
-      }
-      
-      # Convert factors to numeric (integer is more efficient actually)
-      is_fact <- which(list_classes == "factor")
-      if (length(is_fact) > 0) {
-        data[is_fact] <- lapply(data[is_fact], function(x) {as.numeric(x)})
-      }
-      
-    } else {
-      
-      # What do you think you are doing here? Throw error.
-      stop("lgb.prepare2: you provided ", paste(class(data), collapse = " & "), " but data should have class data.frame")
-      
-    }
-    
-  }
-  
-  return(data)
-  
-}
+#' Data preparator for LightGBM datasets (numeric)
+#'
+#' Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric without integers. Please use \code{lgb.prepare_rules} if you want to apply this transformation to other datasets.
+#' 
+#' @param data A data.frame or data.table to prepare.
+#' 
+#' @return The cleaned dataset. It must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
+#' 
+#' @examples
+#' library(lightgbm)
+#' data(iris)
+#' 
+#' str(iris)
+#' # 'data.frame':	150 obs. of  5 variables:
+#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
+#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
+#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
+#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
+#' # $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
+#' 
+#' str(lgb.prepare(data = iris)) # Convert all factors/chars to numeric
+#' # 'data.frame':	150 obs. of  5 variables:
+#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
+#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
+#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
+#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
+#' # $ Species     : num  1 1 1 1 1 1 1 1 1 1 ...
+#' 
+#' # When lightgbm package is installed, and you do not want to load it
+#' # You can still use the function!
+#' lgb.unloader()
+#' str(lightgbm::lgb.prepare(data = iris))
+#' # 'data.frame':	150 obs. of  5 variables:
+#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
+#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
+#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
+#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
+#' # $ Species     : num  1 1 1 1 1 1 1 1 1 1 ...
+#' 
+#' @export
+lgb.prepare <- function(data) {
+  
+  # data.table not behaving like data.frame
+  if ("data.table" %in% class(data)) {
+    
+    # Get data classes
+    list_classes <- sapply(data, class)
+    
+    # Convert characters to factors only (we can change them to numeric after)
+    is_char <- which(list_classes == "character")
+    if (length(is_char) > 0) {
+      data[, (is_char) := lapply(.SD, function(x) {as.numeric(as.factor(x))}), .SDcols = is_char]
+    }
+    
+    # Convert factors to numeric (integer is more efficient actually)
+    is_fact <- c(which(list_classes == "factor"), is_char)
+    if (length(is_fact) > 0) {
+      data[, (is_fact) := lapply(.SD, function(x) {as.numeric(x)}), .SDcols = is_fact]
+    }
+    
+  } else {
+    
+    # Default routine (data.frame)
+    if ("data.frame" %in% class(data)) {
+      
+      # Get data classes
+      list_classes <- sapply(data, class)
+      
+      # Convert characters to factors to numeric (integer is more efficient actually)
+      is_char <- which(list_classes == "character")
+      if (length(is_char) > 0) {
+        data[is_char] <- lapply(data[is_char], function(x) {as.numeric(as.factor(x))})
+      }
+      
+      # Convert factors to numeric (integer is more efficient actually)
+      is_fact <- which(list_classes == "factor")
+      if (length(is_fact) > 0) {
+        data[is_fact] <- lapply(data[is_fact], function(x) {as.numeric(x)})
+      }
+      
+    } else {
+      
+      # What do you think you are doing here? Throw error.
+      stop("lgb.prepare2: you provided ", paste(class(data), collapse = " & "), " but data should have class data.frame")
+      
+    }
+    
+  }
+  
+  return(data)
+  
+}

R-package/R/lgb.prepare2.R

-#' Data preparator for LightGBM datasets (integer)
-#'
-#' Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric (specifically: integer). Please use \code{lgb.prepare_rules2} if you want to apply this transformation to other datasets. This is useful if you have a specific need for integer dataset instead of numeric dataset. Note that there are programs which do not support integer-only input. Consider this as a half memory technique which is dangerous, especially for LightGBM.
-#' 
-#' @param data A data.frame or data.table to prepare.
-#' 
-#' @return The cleaned dataset. It must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
-#' 
-#' @examples
-#' \dontrun{
-#' library(lightgbm)
-#' data(iris)
-#' 
-#' str(iris)
-#' # 'data.frame':	150 obs. of  5 variables:
-#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
-#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
-#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
-#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
-#' # $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
-#' 
-#' str(lgb.prepare2(data = iris)) # Convert all factors/chars to integer
-#' # 'data.frame':	150 obs. of  5 variables:
-#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
-#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
-#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
-#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
-#' # $ Species     : int  1 1 1 1 1 1 1 1 1 1 ...
-#' 
-#' # When lightgbm package is installed, and you do not want to load it
-#' # You can still use the function!
-#' lgb.unloader()
-#' str(lightgbm::lgb.prepare2(data = iris))
-#' # 'data.frame':	150 obs. of  5 variables:
-#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
-#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
-#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
-#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
-#' # $ Species     : int  1 1 1 1 1 1 1 1 1 1 ...
-#' 
-#' }
-#' 
-#' @export
-lgb.prepare2 <- function(data) {
-  
-  # data.table not behaving like data.frame
-  if (inherits(data, "data.table")) {
-    
-    # Get data classes
-    list_classes <- vapply(data, class, character(1))
-    
-    # Convert characters to factors only (we can change them to numeric after)
-    is_char <- which(list_classes == "character")
-    if (length(is_char) > 0) {
-      data[, (is_char) := lapply(.SD, function(x) {as.integer(as.factor(x))}), .SDcols = is_char]
-    }
-    
-    # Convert factors to numeric (integer is more efficient actually)
-    is_fact <- c(which(list_classes == "factor"), is_char)
-    if (length(is_fact) > 0) {
-      data[, (is_fact) := lapply(.SD, function(x) {as.integer(x)}), .SDcols = is_fact]
-    }
-    
-  } else {
-    
-    # Default routine (data.frame)
-    if (inherits(data, "data.frame")) {
-      
-      # Get data classes
-      list_classes <- vapply(data, class, character(1))
-      
-      # Convert characters to factors to numeric (integer is more efficient actually)
-      is_char <- which(list_classes == "character")
-      if (length(is_char) > 0) {
-        data[is_char] <- lapply(data[is_char], function(x) {as.integer(as.factor(x))})
-      }
-      
-      # Convert factors to numeric (integer is more efficient actually)
-      is_fact <- which(list_classes == "factor")
-      if (length(is_fact) > 0) {
-        data[is_fact] <- lapply(data[is_fact], function(x) {as.integer(x)})
-      }
-      
-    } else {
-      
-      # What do you think you are doing here? Throw error.
-      stop("lgb.prepare: you provided ", paste(class(data), collapse = " & "), " but data should have class data.frame")
-      
-    }
-    
-  }
-  
-  return(data)
-  
-}
+#' Data preparator for LightGBM datasets (integer)
+#'
+#' Attempts to prepare a clean dataset to prepare to put in a lgb.Dataset. Factors and characters are converted to numeric (specifically: integer). Please use \code{lgb.prepare_rules2} if you want to apply this transformation to other datasets. This is useful if you have a specific need for integer dataset instead of numeric dataset. Note that there are programs which do not support integer-only input. Consider this as a half memory technique which is dangerous, especially for LightGBM.
+#' 
+#' @param data A data.frame or data.table to prepare.
+#' 
+#' @return The cleaned dataset. It must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
+#' 
+#' @examples
+#' library(lightgbm)
+#' data(iris)
+#' 
+#' str(iris)
+#' # 'data.frame':	150 obs. of  5 variables:
+#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
+#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
+#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
+#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
+#' # $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 ...
+#' 
+#' # Convert all factors/chars to integer
+#' str(lgb.prepare2(data = iris))
+#' # 'data.frame':	150 obs. of  5 variables:
+#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
+#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
+#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
+#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
+#' # $ Species     : int  1 1 1 1 1 1 1 1 1 1 ...
+#' 
+#' # When lightgbm package is installed, and you do not want to load it
+#' # You can still use the function!
+#' lgb.unloader()
+#' str(lightgbm::lgb.prepare2(data = iris))
+#' # 'data.frame':	150 obs. of  5 variables:
+#' # $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
+#' # $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
+#' # $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
+#' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
+#' # $ Species     : int  1 1 1 1 1 1 1 1 1 1 ...
+#' 
+#' @export
+lgb.prepare2 <- function(data) {
+  
+  # data.table not behaving like data.frame
+  if (inherits(data, "data.table")) {
+    
+    # Get data classes
+    list_classes <- vapply(data, class, character(1))
+    
+    # Convert characters to factors only (we can change them to numeric after)
+    is_char <- which(list_classes == "character")
+    if (length(is_char) > 0) {
+      data[, (is_char) := lapply(.SD, function(x) {as.integer(as.factor(x))}), .SDcols = is_char]
+    }
+    
+    # Convert factors to numeric (integer is more efficient actually)
+    is_fact <- c(which(list_classes == "factor"), is_char)
+    if (length(is_fact) > 0) {
+      data[, (is_fact) := lapply(.SD, function(x) {as.integer(x)}), .SDcols = is_fact]
+    }
+    
+  } else {
+    
+    # Default routine (data.frame)
+    if (inherits(data, "data.frame")) {
+      
+      # Get data classes
+      list_classes <- vapply(data, class, character(1))
+      
+      # Convert characters to factors to numeric (integer is more efficient actually)
+      is_char <- which(list_classes == "character")
+      if (length(is_char) > 0) {
+        data[is_char] <- lapply(data[is_char], function(x) {as.integer(as.factor(x))})
+      }
+      
+      # Convert factors to numeric (integer is more efficient actually)
+      is_fact <- which(list_classes == "factor")
+      if (length(is_fact) > 0) {
+        data[is_fact] <- lapply(data[is_fact], function(x) {as.integer(x)})
+      }
+      
+    } else {
+      
+      # What do you think you are doing here? Throw error.
+      stop("lgb.prepare: you provided ", paste(class(data), collapse = " & "), " but data should have class data.frame")
+      
+    }
+    
+  }
+  
+  return(data)
+  
+}

R-package/R/lgb.prepare_rules.R

@@ -8,7 +8,6 @@
 #' @return A list with the cleaned dataset (\code{data}) and the rules (\code{rules}). The data must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(iris)
 #' 
@@ -66,8 +65,6 @@
 #' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 #' # $ Species     : num  3 3 3 3 3 3 3 3 3 3 ...
 #' 
-#' }
-#' 
 #' @importFrom data.table set
 #' @export
 lgb.prepare_rules <- function(data, rules = NULL) {

R-package/R/lgb.prepare_rules2.R

@@ -8,7 +8,6 @@
 #' @return A list with the cleaned dataset (\code{data}) and the rules (\code{rules}). The data must be converted to a matrix format (\code{as.matrix}) for input in lgb.Dataset.
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(iris)
 #' 
@@ -66,8 +65,6 @@
 #' # $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 #' # $ Species     : int  3 3 3 3 3 3 3 3 3 3 ...
 #' 
-#' }
-#' 
 #' @importFrom data.table set
 #' @export
 lgb.prepare_rules2 <- function(data, rules = NULL) {

R-package/R/lgb.train.R

@@ -26,7 +26,6 @@
 #' @return a trained booster model \code{lgb.Booster}.
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -43,7 +42,6 @@
 #'                    min_data = 1,
 #'                    learning_rate = 1,
 #'                    early_stopping_rounds = 10)
-#' }
 #' 
 #' @export
 lgb.train <- function(params = list(),

R-package/R/lgb.unloader.R

@@ -9,7 +9,6 @@
 #' @return NULL invisibly.
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -32,7 +31,6 @@
 #' 
 #' library(lightgbm)
 #' # Do whatever you want again with LightGBM without object clashing
-#' }
 #' 
 #' @export
 lgb.unloader <- function(restore = TRUE, wipe = FALSE, envir = .GlobalEnv) {

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

@@ -8,7 +8,6 @@
 #' @return lgb.Booster.
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -27,7 +26,6 @@
 #'                    early_stopping_rounds = 10)
 #' saveRDS.lgb.Booster(model, "model.rds")
 #' new_model <- readRDS.lgb.Booster("model.rds")
-#' }
 #' 
 #' @export
 readRDS.lgb.Booster <- function(file = "", refhook = NULL) {

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

@@ -13,7 +13,6 @@
 #' @return NULL invisibly.
 #' 
 #' @examples
-#' \dontrun{
 #' library(lightgbm)
 #' data(agaricus.train, package = "lightgbm")
 #' train <- agaricus.train
@@ -23,16 +22,16 @@
 #' 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)
+#' model <- lgb.train(
+#'     params
+#'     , dtrain
+#'     , 100
+#'     , valids
+#'     , min_data = 1
+#'     , learning_rate = 1
+#'     , early_stopping_rounds = 10
+#' )
 #' saveRDS.lgb.Booster(model, "model.rds")
-#' }
-#' 
 #' @export
 saveRDS.lgb.Booster <- function(object,
                                 file = "",

R-package/man/dim.Rd

@@ -22,7 +22,6 @@ Note: since \code{nrow} and \code{ncol} internally use \code{dim}, they can also
 be directly used with an \code{lgb.Dataset} object.
 }
 \examples{
-\dontrun{
 library(lightgbm)
 data(agaricus.train, package = "lightgbm")
 train <- agaricus.train
@@ -31,6 +30,5 @@ dtrain <- lgb.Dataset(train$data, label = train$label)
 stopifnot(nrow(dtrain) == nrow(train$data))
 stopifnot(ncol(dtrain) == ncol(train$data))
 stopifnot(all(dim(dtrain) == dim(train$data)))
-}
 
 }

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

@@ -24,7 +24,6 @@ Generic \code{dimnames} methods are used by \code{colnames}.
 Since row names are irrelevant, it is recommended to use \code{colnames} directly.
 }
 \examples{
-\dontrun{
 library(lightgbm)
 data(agaricus.train, package = "lightgbm")
 train <- agaricus.train
@@ -34,6 +33,5 @@ dimnames(dtrain)
 colnames(dtrain)
 colnames(dtrain) <- make.names(1:ncol(train$data))
 print(dtrain, verbose = TRUE)
-}
 
 }

R-package/man/getinfo.Rd

@@ -33,7 +33,6 @@ The \code{name} field can be one of the following:
 }
 }
 \examples{
-\dontrun{
 library(lightgbm)
 data(agaricus.train, package = "lightgbm")
 train <- agaricus.train
@@ -45,6 +44,5 @@ lightgbm::setinfo(dtrain, "label", 1 - labels)
 
 labels2 <- lightgbm::getinfo(dtrain, "label")
 stopifnot(all(labels2 == 1 - labels))
-}
 
 }

R-package/man/lgb.Dataset.Rd

@@ -32,7 +32,6 @@ Construct lgb.Dataset object from dense matrix, sparse matrix
 or local file (that was created previously by saving an \code{lgb.Dataset}).
 }
 \examples{
-\dontrun{
 library(lightgbm)
 data(agaricus.train, package = "lightgbm")
 train <- agaricus.train
@@ -40,6 +39,5 @@ dtrain <- lgb.Dataset(train$data, label = train$label)
 lgb.Dataset.save(dtrain, "lgb.Dataset.data")
 dtrain <- lgb.Dataset("lgb.Dataset.data")
 lgb.Dataset.construct(dtrain)
-}
 
 }