2b5b96d760
* [R] xgb.save must work when handle in nil but raw exists * [R] print.xgb.Booster should still print other info when handle is nil * [R] rename internal function xgb.Booster to xgb.Booster.handle to make its intent clear * [R] rename xgb.Booster.check to xgb.Booster.complete and make it visible; more docs * [R] storing evaluation_log should depend only on watchlist, not on verbose * [R] reduce the excessive chattiness of unit tests * [R] only disable some tests in windows when it's not 64-bit * [R] clean-up xgb.DMatrix * [R] test xgb.DMatrix loading from libsvm text file * [R] store feature_names in xgb.Booster, use them from utility functions * [R] remove non-functional co-occurence computation from xgb.importance * [R] verbose=0 is enough without a callback * [R] added forgotten xgb.Booster.complete.Rd; cran check fixes * [R] update installation instructions
110 lines
3.6 KiB
R
110 lines
3.6 KiB
R
# Simple interface for training an xgboost model that wraps \code{xgb.train}
|
|
# Its documentation is combined with xgb.train.
|
|
#
|
|
#' @rdname xgb.train
|
|
#' @export
|
|
xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
|
|
params = list(), nrounds,
|
|
verbose = 1, print_every_n = 1L,
|
|
early_stopping_rounds = NULL, maximize = NULL,
|
|
save_period = 0, save_name = "xgboost.model",
|
|
xgb_model = NULL, callbacks = list(), ...) {
|
|
|
|
dtrain <- xgb.get.DMatrix(data, label, missing, weight)
|
|
|
|
watchlist <- list(train = dtrain)
|
|
|
|
bst <- xgb.train(params, dtrain, nrounds, watchlist, verbose = verbose, print_every_n = print_every_n,
|
|
early_stopping_rounds = early_stopping_rounds, maximize = maximize,
|
|
save_period = save_period, save_name = save_name,
|
|
xgb_model = xgb_model, callbacks = callbacks, ...)
|
|
return(bst)
|
|
}
|
|
|
|
#' Training part from Mushroom Data Set
|
|
#'
|
|
#' This data set is originally from the Mushroom data set,
|
|
#' UCI Machine Learning Repository.
|
|
#'
|
|
#' This data set includes the following fields:
|
|
#'
|
|
#' \itemize{
|
|
#' \item \code{label} the label for each record
|
|
#' \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
|
|
#' }
|
|
#'
|
|
#' @references
|
|
#' https://archive.ics.uci.edu/ml/datasets/Mushroom
|
|
#'
|
|
#' Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
|
|
#' [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
|
|
#' School of Information and Computer Science.
|
|
#'
|
|
#' @docType data
|
|
#' @keywords datasets
|
|
#' @name agaricus.train
|
|
#' @usage data(agaricus.train)
|
|
#' @format A list containing a label vector, and a dgCMatrix object with 6513
|
|
#' rows and 127 variables
|
|
NULL
|
|
|
|
#' Test part from Mushroom Data Set
|
|
#'
|
|
#' This data set is originally from the Mushroom data set,
|
|
#' UCI Machine Learning Repository.
|
|
#'
|
|
#' This data set includes the following fields:
|
|
#'
|
|
#' \itemize{
|
|
#' \item \code{label} the label for each record
|
|
#' \item \code{data} a sparse Matrix of \code{dgCMatrix} class, with 126 columns.
|
|
#' }
|
|
#'
|
|
#' @references
|
|
#' https://archive.ics.uci.edu/ml/datasets/Mushroom
|
|
#'
|
|
#' Bache, K. & Lichman, M. (2013). UCI Machine Learning Repository
|
|
#' [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California,
|
|
#' School of Information and Computer Science.
|
|
#'
|
|
#' @docType data
|
|
#' @keywords datasets
|
|
#' @name agaricus.test
|
|
#' @usage data(agaricus.test)
|
|
#' @format A list containing a label vector, and a dgCMatrix object with 1611
|
|
#' rows and 126 variables
|
|
NULL
|
|
|
|
# Various imports
|
|
#' @importClassesFrom Matrix dgCMatrix dgeMatrix
|
|
#' @importFrom Matrix cBind
|
|
#' @importFrom Matrix colSums
|
|
#' @importFrom Matrix sparse.model.matrix
|
|
#' @importFrom Matrix sparseVector
|
|
#' @importFrom data.table data.table
|
|
#' @importFrom data.table is.data.table
|
|
#' @importFrom data.table as.data.table
|
|
#' @importFrom data.table :=
|
|
#' @importFrom data.table rbindlist
|
|
#' @importFrom data.table setkey
|
|
#' @importFrom data.table setkeyv
|
|
#' @importFrom data.table setnames
|
|
#' @importFrom magrittr %>%
|
|
#' @importFrom stringi stri_detect_regex
|
|
#' @importFrom stringi stri_match_first_regex
|
|
#' @importFrom stringi stri_replace_first_regex
|
|
#' @importFrom stringi stri_replace_all_regex
|
|
#' @importFrom stringi stri_split_regex
|
|
#' @importFrom utils object.size str tail
|
|
#' @importFrom stats predict
|
|
#' @importFrom stats median
|
|
#' @importFrom utils head
|
|
#' @importFrom graphics barplot
|
|
#' @importFrom graphics grid
|
|
#' @importFrom graphics par
|
|
#' @importFrom graphics title
|
|
#'
|
|
#' @import methods
|
|
#' @useDynLib xgboost
|
|
NULL
|