rebase

R-package/R/utils.R

@@ -193,20 +193,20 @@ xgb.iter.update <- function(bst, dtrain, iter, obj) {
 # Evaluate one iteration.
 # Returns a named vector of evaluation metrics
 # with the names in a 'datasetname-metricname' format.
-xgb.iter.eval <- function(bst, watchlist, iter, feval) {
+xgb.iter.eval <- function(bst, evals, iter, feval) {
   handle <- xgb.get.handle(bst)
 
-  if (length(watchlist) == 0)
+  if (length(evals) == 0)
     return(NULL)
 
-  evnames <- names(watchlist)
+  evnames <- names(evals)
   if (is.null(feval)) {
-    msg <- .Call(XGBoosterEvalOneIter_R, handle, as.integer(iter), watchlist, as.list(evnames))
+    msg <- .Call(XGBoosterEvalOneIter_R, handle, as.integer(iter), evals, as.list(evnames))
     mat <- matrix(strsplit(msg, '\\s+|:')[[1]][-1], nrow = 2)
     res <- structure(as.numeric(mat[2, ]), names = mat[1, ])
   } else {
-    res <- sapply(seq_along(watchlist), function(j) {
-      w <- watchlist[[j]]
+    res <- sapply(seq_along(evals), function(j) {
+      w <- evals[[j]]
       ## predict using all trees
       preds <- predict(bst, w, outputmargin = TRUE, iterationrange = "all")
       eval_res <- feval(preds, w)

R-package/R/xgb.create.features.R

@@ -71,7 +71,6 @@
 #' new.dtest <- xgb.DMatrix(
 #'   data = new.features.test, label = agaricus.test$label, nthread = 2
 #' )
-#' watchlist <- list(train = new.dtrain)
 #' bst <- xgb.train(params = param, data = new.dtrain, nrounds = nrounds, nthread = 2)
 #'
 #' # Model accuracy with new features

R-package/R/xgb.cv.R

@@ -215,7 +215,7 @@ xgb.cv <- function(params = list(), data, nrounds, nfold, label = NULL, missing
       modelfile = NULL
     )
     bst <- bst$bst
-    list(dtrain = dtrain, bst = bst, watchlist = list(train = dtrain, test = dtest), index = folds[[k]])
+    list(dtrain = dtrain, bst = bst, evals = list(train = dtrain, test = dtest), index = folds[[k]])
   })
 
   # extract parameters that can affect the relationship b/w #trees and #iterations
@@ -254,7 +254,7 @@ xgb.cv <- function(params = list(), data, nrounds, nfold, label = NULL, missing
       )
       xgb.iter.eval(
         bst = fd$bst,
-        watchlist = fd$watchlist,
+        evals = fd$evals,
         iter = iteration - 1,
         feval = feval
       )

R-package/R/xgb.train.R

@@ -114,13 +114,13 @@
 #' @param data training dataset. \code{xgb.train} accepts only an \code{xgb.DMatrix} as the input.
 #'        \code{xgboost}, in addition, also accepts \code{matrix}, \code{dgCMatrix}, or name of a local data file.
 #' @param nrounds max number of boosting iterations.
-#' @param watchlist named list of xgb.DMatrix datasets to use for evaluating model performance.
+#' @param evals Named list of `xgb.DMatrix` datasets to use for evaluating model performance.
 #'        Metrics specified in either \code{eval_metric} or \code{feval} will be computed for each
 #'        of these datasets during each boosting iteration, and stored in the end as a field named
 #'        \code{evaluation_log} in the resulting object. When either \code{verbose>=1} or
 #'        \code{\link{xgb.cb.print.evaluation}} callback is engaged, the performance results are continuously
 #'        printed out during the training.
-#'        E.g., specifying \code{watchlist=list(validation1=mat1, validation2=mat2)} allows to track
+#'        E.g., specifying \code{evals=list(validation1=mat1, validation2=mat2)} allows to track
 #'        the performance of each round's model on mat1 and mat2.
 #' @param obj customized objective function. Returns gradient and second order
 #'        gradient with given prediction and dtrain.
@@ -171,7 +171,7 @@
 #' @details
 #' These are the training functions for \code{xgboost}.
 #'
-#' The \code{xgb.train} interface supports advanced features such as \code{watchlist},
+#' The \code{xgb.train} interface supports advanced features such as \code{evals},
 #' customized objective and evaluation metric functions, therefore it is more flexible
 #' than the \code{xgboost} interface.
 #'
@@ -209,7 +209,7 @@
 #' \itemize{
 #'   \item \code{xgb.cb.print.evaluation} is turned on when \code{verbose > 0};
 #'         and the \code{print_every_n} parameter is passed to it.
-#'   \item \code{xgb.cb.evaluation.log} is on when \code{watchlist} is present.
+#'   \item \code{xgb.cb.evaluation.log} is on when \code{evals} is present.
 #'   \item \code{xgb.cb.early.stop}: when \code{early_stopping_rounds} is set.
 #'   \item \code{xgb.cb.save.model}: when \code{save_period > 0} is set.
 #' }
@@ -254,12 +254,12 @@
 #' dtest <- with(
 #'   agaricus.test, xgb.DMatrix(data, label = label, nthread = nthread)
 #' )
-#' watchlist <- list(train = dtrain, eval = dtest)
+#' evals <- list(train = dtrain, eval = dtest)
 #'
 #' ## A simple xgb.train example:
 #' param <- list(max_depth = 2, eta = 1, nthread = nthread,
 #'               objective = "binary:logistic", eval_metric = "auc")
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0)
+#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals, verbose = 0)
 #'
 #' ## An xgb.train example where custom objective and evaluation metric are
 #' ## used:
@@ -280,27 +280,27 @@
 #' #  as 'objective' and 'eval_metric' parameters in the params list:
 #' param <- list(max_depth = 2, eta = 1, nthread = nthread,
 #'               objective = logregobj, eval_metric = evalerror)
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0)
+#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals, verbose = 0)
 #'
 #' #  or through the ... arguments:
 #' param <- list(max_depth = 2, eta = 1, nthread = nthread)
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0,
+#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals, verbose = 0,
 #'                  objective = logregobj, eval_metric = evalerror)
 #'
 #' #  or as dedicated 'obj' and 'feval' parameters of xgb.train:
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist,
+#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals,
 #'                  obj = logregobj, feval = evalerror)
 #'
 #'
 #' ## An xgb.train example of using variable learning rates at each iteration:
 #' param <- list(max_depth = 2, eta = 1, nthread = nthread,
 #'               objective = "binary:logistic", eval_metric = "auc")
 #' my_etas <- list(eta = c(0.5, 0.1))
-#' bst <- xgb.train(param, dtrain, nrounds = 2, watchlist, verbose = 0,
+#' bst <- xgb.train(param, dtrain, nrounds = 2, evals = evals, verbose = 0,
 #'                  callbacks = list(xgb.cb.reset.parameters(my_etas)))
 #'
 #' ## Early stopping:
-#' bst <- xgb.train(param, dtrain, nrounds = 25, watchlist,
+#' bst <- xgb.train(param, dtrain, nrounds = 25, evals = evals,
 #'                  early_stopping_rounds = 3)
 #'
 #' ## An 'xgboost' interface example:
@@ -311,7 +311,7 @@
 #'
 #' @rdname xgb.train
 #' @export
-xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
+xgb.train <- function(params = list(), data, nrounds, evals = list(),
                       obj = NULL, feval = NULL, verbose = 1, print_every_n = 1L,
                       early_stopping_rounds = NULL, maximize = NULL,
                       save_period = NULL, save_name = "xgboost.model",
@@ -324,17 +324,17 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   check.custom.obj()
   check.custom.eval()
 
-  # data & watchlist checks
+  # data & evals checks
   dtrain <- data
   if (!inherits(dtrain, "xgb.DMatrix"))
     stop("second argument dtrain must be xgb.DMatrix")
-  if (length(watchlist) > 0) {
-    if (typeof(watchlist) != "list" ||
-        !all(vapply(watchlist, inherits, logical(1), what = 'xgb.DMatrix')))
-      stop("watchlist must be a list of xgb.DMatrix elements")
-    evnames <- names(watchlist)
+  if (length(evals) > 0) {
+    if (typeof(evals) != "list" ||
+        !all(vapply(evals, inherits, logical(1), what = 'xgb.DMatrix')))
+      stop("'evals' must be a list of xgb.DMatrix elements")
+    evnames <- names(evals)
     if (is.null(evnames) || any(evnames == ""))
-      stop("each element of the watchlist must have a name tag")
+      stop("each element of 'evals' must have a name tag")
   }
   # Handle multiple evaluation metrics given as a list
   for (m in params$eval_metric) {
@@ -370,8 +370,8 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   if (verbose && !("print_evaluation" %in% cb_names)) {
     callbacks <- add.callback(callbacks, xgb.cb.print.evaluation(print_every_n))
   }
-  # evaluation log callback:  it is automatically enabled when watchlist is provided
-  if (length(watchlist) && !("evaluation_log" %in% cb_names)) {
+  # evaluation log callback:  it is automatically enabled when 'evals' is provided
+  if (length(evals) && !("evaluation_log" %in% cb_names)) {
     callbacks <- add.callback(callbacks, xgb.cb.evaluation.log())
   }
   # Model saving callback
@@ -385,7 +385,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
   # Construct a booster (either a new one or load from xgb_model)
   bst <- xgb.Booster(
     params = params,
-    cachelist = append(watchlist, dtrain),
+    cachelist = append(evals, dtrain),
     modelfile = xgb_model
   )
   niter_init <- bst$niter
@@ -407,7 +407,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
     callbacks,
     bst,
     dtrain,
-    watchlist,
+    evals,
     begin_iteration,
     end_iteration
   )
@@ -419,7 +419,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
       callbacks,
       bst,
       dtrain,
-      watchlist,
+      evals,
       iteration
     )
 
@@ -431,10 +431,10 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
     )
 
     bst_evaluation <- NULL
-    if (length(watchlist) > 0) {
+    if (length(evals) > 0) {
       bst_evaluation <- xgb.iter.eval(
         bst = bst,
-        watchlist = watchlist,
+        evals = evals,
         iter = iteration - 1,
         feval = feval
       )
@@ -444,7 +444,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
       callbacks,
       bst,
       dtrain,
-      watchlist,
+      evals,
       iteration,
       bst_evaluation
     )
@@ -456,7 +456,7 @@ xgb.train <- function(params = list(), data, nrounds, watchlist = list(),
     callbacks,
     bst,
     dtrain,
-    watchlist,
+    evals,
     iteration,
     bst_evaluation
   )

R-package/R/xgboost.R

@@ -18,9 +18,9 @@ xgboost <- function(data = NULL, label = NULL, missing = NA, weight = NULL,
     nthread = merged$nthread
   )
 
-  watchlist <- list(train = dtrain)
+  evals <- list(train = dtrain)
 
-  bst <- xgb.train(params, dtrain, nrounds, watchlist, verbose = verbose, print_every_n = print_every_n,
+  bst <- xgb.train(params, dtrain, nrounds, evals, 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, ...)

R-package/demo/basic_walkthrough.R

@@ -74,25 +74,25 @@ print(paste("sum(abs(pred3-pred))=", sum(abs(pred3 - pred))))
 # to use advanced features, we need to put data in xgb.DMatrix
 dtrain <- xgb.DMatrix(data = train$data, label = train$label)
 dtest <- xgb.DMatrix(data = test$data, label = test$label)
-#---------------Using watchlist----------------
-# watchlist is a list of xgb.DMatrix, each of them is tagged with name
-watchlist <- list(train = dtrain, test = dtest)
-# to train with watchlist, use xgb.train, which contains more advanced features
-# watchlist allows us to monitor the evaluation result on all data in the list
-print("Train xgboost using xgb.train with watchlist")
-bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
+#---------------Using an evaluation set----------------
+# 'evals' is a list of xgb.DMatrix, each of them is tagged with name
+evals <- list(train = dtrain, test = dtest)
+# to train with an evaluation set, use xgb.train, which contains more advanced features
+# 'evals' argument allows us to monitor the evaluation result on all data in the list
+print("Train xgboost using xgb.train with evaluation data")
+bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, evals = evals,
                  nthread = 2, objective = "binary:logistic")
 # we can change evaluation metrics, or use multiple evaluation metrics
-print("train xgboost using xgb.train with watchlist, watch logloss and error")
-bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
+print("train xgboost using xgb.train with evaluation data, watch logloss and error")
+bst <- xgb.train(data = dtrain, max_depth = 2, eta = 1, nrounds = 2, evals = evals,
                  eval_metric = "error", eval_metric = "logloss",
                  nthread = 2, objective = "binary:logistic")
 
 # xgb.DMatrix can also be saved using xgb.DMatrix.save
 xgb.DMatrix.save(dtrain, "dtrain.buffer")
 # to load it in, simply call xgb.DMatrix
 dtrain2 <- xgb.DMatrix("dtrain.buffer")
-bst <- xgb.train(data = dtrain2, max_depth = 2, eta = 1, nrounds = 2, watchlist = watchlist,
+bst <- xgb.train(data = dtrain2, max_depth = 2, eta = 1, nrounds = 2, evals = evals,
                  nthread = 2, objective = "binary:logistic")
 # information can be extracted from xgb.DMatrix using getinfo
 label <- getinfo(dtest, "label")

R-package/demo/boost_from_prediction.R

@@ -5,14 +5,14 @@ data(agaricus.test, package = 'xgboost')
 dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
-watchlist <- list(eval = dtest, train = dtrain)
+evals <- list(eval = dtest, train = dtrain)
 ###
 # advanced: start from a initial base prediction
 #
 print('start running example to start from a initial prediction')
 # train xgboost for 1 round
 param <- list(max_depth = 2, eta = 1, nthread = 2, objective = 'binary:logistic')
-bst <- xgb.train(param, dtrain, 1, watchlist)
+bst <- xgb.train(param, dtrain, 1, evals)
 # Note: we need the margin value instead of transformed prediction in set_base_margin
 # do predict with output_margin=TRUE, will always give you margin values before logistic transformation
 ptrain <- predict(bst, dtrain, outputmargin = TRUE)
@@ -23,4 +23,4 @@ setinfo(dtrain, "base_margin", ptrain)
 setinfo(dtest, "base_margin", ptest)
 
 print('this is result of boost from initial prediction')
-bst <- xgb.train(params = param, data = dtrain, nrounds = 1, watchlist = watchlist)
+bst <- xgb.train(params = param, data = dtrain, nrounds = 1, evals = evals)

R-package/demo/custom_objective.R

@@ -8,7 +8,7 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 # note: for customized objective function, we leave objective as default
 # note: what we are getting is margin value in prediction
 # you must know what you are doing
-watchlist <- list(eval = dtest, train = dtrain)
+evals <- list(eval = dtest, train = dtrain)
 num_round <- 2
 
 # user define objective function, given prediction, return gradient and second order gradient
@@ -38,7 +38,7 @@ param <- list(max_depth = 2, eta = 1, nthread  =  2, verbosity = 0,
 print('start training with user customized objective')
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train
-bst <- xgb.train(param, dtrain, num_round, watchlist)
+bst <- xgb.train(param, dtrain, num_round, evals)
 
 #
 # there can be cases where you want additional information
@@ -62,4 +62,4 @@ param <- list(max_depth = 2, eta = 1, nthread  =  2, verbosity = 0,
 print('start training with user customized objective, with additional attributes in DMatrix')
 # training with customized objective, we can also do step by step training
 # simply look at xgboost.py's implementation of train
-bst <- xgb.train(param, dtrain, num_round, watchlist)
+bst <- xgb.train(param, dtrain, num_round, evals)

R-package/demo/early_stopping.R

@@ -8,7 +8,7 @@ dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 # note: what we are getting is margin value in prediction
 # you must know what you are doing
 param <- list(max_depth = 2, eta = 1, nthread = 2, verbosity = 0)
-watchlist <- list(eval = dtest)
+evals <- list(eval = dtest)
 num_round <- 20
 # user define objective function, given prediction, return gradient and second order gradient
 # this is log likelihood loss
@@ -32,7 +32,7 @@ evalerror <- function(preds, dtrain) {
 }
 print('start training with early Stopping setting')
 
-bst <- xgb.train(param, dtrain, num_round, watchlist,
+bst <- xgb.train(param, dtrain, num_round, evals,
                  objective = logregobj, eval_metric = evalerror, maximize = FALSE,
                  early_stopping_round = 3)
 bst <- xgb.cv(param, dtrain, num_round, nfold = 5,

R-package/demo/generalized_linear_model.R

@@ -25,9 +25,9 @@ param <- list(objective = "binary:logistic", booster = "gblinear",
 ##
 # the rest of settings are the same
 ##
-watchlist <- list(eval = dtest, train = dtrain)
+evals <- list(eval = dtest, train = dtrain)
 num_round <- 2
-bst <- xgb.train(param, dtrain, num_round, watchlist)
+bst <- xgb.train(param, dtrain, num_round, evals)
 ypred <- predict(bst, dtest)
 labels <- getinfo(dtest, 'label')
 cat('error of preds=', mean(as.numeric(ypred > 0.5) != labels), '\n')

R-package/demo/gpu_accelerated.R

@@ -23,7 +23,7 @@ y <- rbinom(N, 1, plogis(m))
 tr <- sample.int(N, N * 0.75)
 dtrain <- xgb.DMatrix(X[tr, ], label = y[tr])
 dtest <- xgb.DMatrix(X[-tr, ], label = y[-tr])
-wl <- list(train = dtrain, test = dtest)
+evals <- list(train = dtrain, test = dtest)
 
 # An example of running 'gpu_hist' algorithm
 # which is
@@ -35,11 +35,11 @@ wl <- list(train = dtrain, test = dtest)
 param <- list(objective = 'reg:logistic', eval_metric = 'auc', subsample = 0.5, nthread = 4,
               max_bin = 64, tree_method = 'gpu_hist')
 pt <- proc.time()
-bst_gpu <- xgb.train(param, dtrain, watchlist = wl, nrounds = 50)
+bst_gpu <- xgb.train(param, dtrain, evals = evals, nrounds = 50)
 proc.time() - pt
 
 # Compare to the 'hist' algorithm:
 param$tree_method <- 'hist'
 pt <- proc.time()
-bst_hist <- xgb.train(param, dtrain, watchlist = wl, nrounds = 50)
+bst_hist <- xgb.train(param, dtrain, evals = evals, nrounds = 50)
 proc.time() - pt

R-package/demo/predict_first_ntree.R

@@ -6,11 +6,11 @@ dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
 dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
 param <- list(max_depth = 2, eta = 1, objective = 'binary:logistic')
-watchlist <- list(eval = dtest, train = dtrain)
+evals <- list(eval = dtest, train = dtrain)
 nrounds <- 2
 
 # training the model for two rounds
-bst <- xgb.train(param, dtrain, nrounds, nthread = 2, watchlist)
+bst <- xgb.train(param, dtrain, nrounds, nthread = 2, evals = evals)
 cat('start testing prediction from first n trees\n')
 labels <- getinfo(dtest, 'label')