[R] Redesigned xgboost() interface skeleton

R-package/DESCRIPTION

@@ -57,7 +57,8 @@ Suggests:
     igraph (>= 1.0.1),
     float,
     titanic,
-    RhpcBLASctl
+    RhpcBLASctl,
+    survival
 Depends:
     R (>= 4.3.0)
 Imports:
@@ -66,6 +67,6 @@ Imports:
     data.table (>= 1.9.6),
     jsonlite (>= 1.0)
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Encoding: UTF-8
 SystemRequirements: GNU make, C++17

R-package/NAMESPACE

@@ -13,6 +13,7 @@ S3method(predict,xgb.Booster)
 S3method(print,xgb.Booster)
 S3method(print,xgb.DMatrix)
 S3method(print,xgb.cv.synchronous)
+S3method(print,xgboost)
 S3method(setinfo,xgb.Booster)
 S3method(setinfo,xgb.DMatrix)
 S3method(variable.names,xgb.Booster)

R-package/R/utils.R

@@ -30,6 +30,40 @@ NVL <- function(x, val) {
   return(c('rank:pairwise', 'rank:ndcg', 'rank:map'))
 }
 
+.OBJECTIVES_NON_DEFAULT_MODE <- function() {
+  return(c("reg:logistic", "binary:logitraw", "multi:softmax"))
+}
+
+.BINARY_CLASSIF_OBJECTIVES <- function() {
+  return(c("binary:logistic", "binary:hinge"))
+}
+
+.MULTICLASS_CLASSIF_OBJECTIVES <- function() {
+  return("multi:softprob")
+}
+
+.SURVIVAL_RIGHT_CENSORING_OBJECTIVES <- function() { # nolint
+  return(c("survival:cox", "survival:aft"))
+}
+
+.SURVIVAL_ALL_CENSORING_OBJECTIVES <- function() { # nolint
+  return("survival:aft")
+}
+
+.REGRESSION_OBJECTIVES <- function() {
+  return(c(
+    "reg:squarederror", "reg:squaredlogerror", "reg:logistic", "reg:pseudohubererror",
+    "reg:absoluteerror", "reg:quantileerror", "count:poisson", "reg:gamma", "reg:tweedie"
+  ))
+}
+
+.MULTI_TARGET_OBJECTIVES <- function() {
+  return(c(
+    "reg:squarederror", "reg:squaredlogerror", "reg:logistic", "reg:pseudohubererror",
+    "reg:quantileerror", "reg:gamma"
+  ))
+}
+
 
 #
 # Low-level functions for boosting --------------------------------------------

R-package/R/xgb.Booster.R

@@ -663,9 +663,8 @@ validate.features <- function(bst, newdata) {
 #' data(agaricus.train, package = "xgboost")
 #' train <- agaricus.train
 #'
-#' bst <- xgboost(
-#'   data = train$data,
-#'   label = train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(train$data, label = train$label),
 #'   max_depth = 2,
 #'   eta = 1,
 #'   nthread = 2,
@@ -767,9 +766,8 @@ xgb.attributes <- function(object) {
 #' data.table::setDTthreads(nthread)
 #' train <- agaricus.train
 #'
-#' bst <- xgboost(
-#'   data = train$data,
-#'   label = train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(train$data, label = train$label),
 #'   max_depth = 2,
 #'   eta = 1,
 #'   nthread = nthread,
@@ -817,9 +815,8 @@ xgb.config <- function(object) {
 #' data(agaricus.train, package = "xgboost")
 #' train <- agaricus.train
 #'
-#' bst <- xgboost(
-#'   data = train$data,
-#'   label = train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(train$data, label = train$label),
 #'   max_depth = 2,
 #'   eta = 1,
 #'   nthread = 2,
@@ -1230,9 +1227,8 @@ xgb.is.same.Booster <- function(obj1, obj2) {
 #' data(agaricus.train, package = "xgboost")
 #' train <- agaricus.train
 #'
-#' bst <- xgboost(
-#'   data = train$data,
-#'   label = train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(train$data, label = train$label),
 #'   max_depth = 2,
 #'   eta = 1,
 #'   nthread = 2,

R-package/R/xgb.DMatrix.R

@@ -853,36 +853,6 @@ xgb.DMatrix.hasinfo <- function(object, info) {
 }
 
 
-# get dmatrix from data, label
-# internal helper method
-xgb.get.DMatrix <- function(data, label, missing, weight, nthread) {
-  if (inherits(data, "dgCMatrix") || is.matrix(data)) {
-    if (is.null(label)) {
-      stop("label must be provided when data is a matrix")
-    }
-    dtrain <- xgb.DMatrix(data, label = label, missing = missing, nthread = nthread)
-    if (!is.null(weight)) {
-      setinfo(dtrain, "weight", weight)
-    }
-  } else {
-    if (!is.null(label)) {
-      warning("xgboost: label will be ignored.")
-    }
-    if (is.character(data)) {
-      data <- path.expand(data)
-      dtrain <- xgb.DMatrix(data[1])
-    } else if (inherits(data, "xgb.DMatrix")) {
-      dtrain <- data
-    } else if (inherits(data, "data.frame")) {
-      stop("xgboost doesn't support data.frame as input. Convert it to matrix first.")
-    } else {
-      stop("xgboost: invalid input data")
-    }
-  }
-  return(dtrain)
-}
-
-
 #' Dimensions of xgb.DMatrix
 #'
 #' Returns a vector of numbers of rows and of columns in an \code{xgb.DMatrix}.

R-package/R/xgb.dump.R

@@ -29,8 +29,8 @@
 #' data(agaricus.test, package='xgboost')
 #' train <- agaricus.train
 #' test <- agaricus.test
-#' bst <- xgboost(data = train$data, label = train$label, max_depth = 2,
-#'                eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
+#' bst <- xgb.train(data = xgb.DMatrix(train$data, label = train$label), max_depth = 2,
+#'                  eta = 1, nthread = 2, nrounds = 2, objective = "binary:logistic")
 #' # save the model in file 'xgb.model.dump'
 #' dump_path = file.path(tempdir(), 'model.dump')
 #' xgb.dump(bst, dump_path, with_stats = TRUE)

R-package/R/xgb.importance.R

@@ -46,9 +46,8 @@
 #' # binomial classification using "gbtree":
 #' data(agaricus.train, package = "xgboost")
 #'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
 #'   max_depth = 2,
 #'   eta = 1,
 #'   nthread = 2,
@@ -59,9 +58,8 @@
 #' xgb.importance(model = bst)
 #'
 #' # binomial classification using "gblinear":
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
 #'   booster = "gblinear",
 #'   eta = 0.3,
 #'   nthread = 1,
@@ -73,9 +71,11 @@
 #' # multiclass classification using "gbtree":
 #' nclass <- 3
 #' nrounds <- 10
-#' mbst <- xgboost(
-#'   data = as.matrix(iris[, -5]),
-#'   label = as.numeric(iris$Species) - 1,
+#' mbst <- xgb.train(
+#'   data = xgb.DMatrix(
+#'     as.matrix(iris[, -5]),
+#'     label = as.numeric(iris$Species) - 1
+#'   ),
 #'   max_depth = 3,
 #'   eta = 0.2,
 #'   nthread = 2,
@@ -99,9 +99,11 @@
 #' )
 #'
 #' # multiclass classification using "gblinear":
-#' mbst <- xgboost(
-#'   data = scale(as.matrix(iris[, -5])),
-#'   label = as.numeric(iris$Species) - 1,
+#' mbst <- xgb.train(
+#'   data = xgb.DMatrix(
+#'     scale(as.matrix(iris[, -5])),
+#'     label = as.numeric(iris$Species) - 1
+#'   ),
 #'   booster = "gblinear",
 #'   eta = 0.2,
 #'   nthread = 1,

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

@@ -43,9 +43,8 @@
 #' nthread <- 1
 #' data.table::setDTthreads(nthread)
 #'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
 #'   max_depth = 2,
 #'   eta = 1,
 #'   nthread = nthread,

R-package/R/xgb.plot.deepness.R

@@ -48,9 +48,8 @@
 #' data.table::setDTthreads(nthread)
 #'
 #' ## Change max_depth to a higher number to get a more significant result
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
 #'   max_depth = 6,
 #'   nthread = nthread,
 #'   nrounds = 50,

R-package/R/xgb.plot.importance.R

@@ -51,9 +51,8 @@
 #' nthread <- 2
 #' data.table::setDTthreads(nthread)
 #'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
 #'   max_depth = 3,
 #'   eta = 1,
 #'   nthread = nthread,

R-package/R/xgb.plot.multi.trees.R

@@ -35,9 +35,8 @@
 #' nthread <- 2
 #' data.table::setDTthreads(nthread)
 #'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(agaricus.train$data, label = agaricus.train$label),
 #'   max_depth = 15,
 #'   eta = 1,
 #'   nthread = nthread,

R-package/R/xgb.plot.shap.R

@@ -82,9 +82,8 @@
 #' data.table::setDTthreads(nthread)
 #' nrounds <- 20
 #'
-#' bst <- xgboost(
-#'   agaricus.train$data,
-#'   agaricus.train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(agaricus.train$data, agaricus.train$label),
 #'   nrounds = nrounds,
 #'   eta = 0.1,
 #'   max_depth = 3,
@@ -108,9 +107,8 @@
 #' set.seed(123)
 #' is.na(x[sample(nrow(x) * 4, 30)]) <- TRUE # introduce some missing values
 #'
-#' mbst <- xgboost(
-#'   data = x,
-#'   label = as.numeric(iris$Species) - 1,
+#' mbst <- xgb.train(
+#'   data = xgb.DMatrix(x, label = as.numeric(iris$Species) - 1),
 #'   nrounds = nrounds,
 #'   max_depth = 2,
 #'   eta = 0.3,

R-package/R/xgb.plot.tree.R

@@ -68,9 +68,8 @@
 #' @examples
 #' data(agaricus.train, package = "xgboost")
 #'
-#' bst <- xgboost(
-#'   data = agaricus.train$data,
-#'   label = agaricus.train$label,
+#' bst <- xgb.train(
+#'   data = xgb.DMatrix(agaricus.train$data, agaricus.train$label),
 #'   max_depth = 3,
 #'   eta = 1,
 #'   nthread = 2,

R-package/R/xgb.train.R

@@ -170,12 +170,6 @@
 #'        as R attributes, and thus do not get saved when using XGBoost's own serializaters like
 #'        \link{xgb.save} (but are kept when using R serializers like \link{saveRDS}).
 #' @param ... other parameters to pass to \code{params}.
-#' @param label vector of response values. Should not be provided when data is
-#'        a local data file name or an \code{xgb.DMatrix}.
-#' @param missing by default is set to NA, which means that NA values should be considered as 'missing'
-#'        by the algorithm. Sometimes, 0 or other extreme value might be used to represent missing values.
-#'        This parameter is only used when input is a dense matrix.
-#' @param weight a vector indicating the weight for each row of the input.
 #'
 #' @return
 #' An object of class \code{xgb.Booster}.
@@ -316,12 +310,10 @@
 #'                  early_stopping_rounds = 3)
 #'
 #' ## An 'xgboost' interface example:
-#' bst <- xgboost(data = agaricus.train$data, label = agaricus.train$label,
-#'                max_depth = 2, eta = 1, nthread = nthread, nrounds = 2,
-#'                objective = "binary:logistic")
+#' bst <- xgboost(x = agaricus.train$data, y = factor(agaricus.train$label),
+#'                params = list(max_depth = 2, eta = 1), nthread = nthread, nrounds = 2)
 #' pred <- predict(bst, agaricus.test$data)
 #'
-#' @rdname xgb.train
 #' @export
 xgb.train <- function(params = list(), data, nrounds, evals = list(),
                       obj = NULL, feval = NULL, verbose = 1, print_every_n = 1L,