Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added an option for stratified CV to xgb.cv

Browse Source
This commit is contained in:
Vadim Khotilovich
2015-04-02 19:48:23 -05:00
parent e9c95645a3
commit b8711226e2
2 changed files with 76 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
R-package/R/xgb.cv.R
View File

@@ -46,11 +46,12 @@
#' \item \code{merror} Exact matching error, used to evaluate multi-class classification
#' }
#' @param obj customized objective function. Returns gradient and second order
#' gradient with given prediction and dtrain,
#' gradient with given prediction and dtrain.
#' @param feval custimized evaluation function. Returns
#' \code{list(metric='metric-name', value='metric-value')} with given
#' prediction and dtrain,
#' @param verbose \code{boolean}, print the statistics during the process.
#' prediction and dtrain.
#' @param stratified \code{boolean}, whether the sampling of folds should be stratified by the values of labels in \code{data}
#' @param verbose \code{boolean}, print the statistics during the process
#' @param ... other parameters to pass to \code{params}.
#'
#' @return A \code{data.table} with each mean and standard deviation stat for training set and test set.
@@ -76,7 +77,7 @@
#'
xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing = NULL,
prediction = FALSE, showsd = TRUE, metrics=list(),
obj = NULL, feval = NULL, verbose = T,...) {
obj = NULL, feval = NULL, stratified = TRUE, verbose = T,...) {
if (typeof(params) != "list") {
stop("xgb.cv: first argument params must be list")
}
@@ -94,7 +95,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
params <- append(params, list("eval_metric"=mc))
}
folds <- xgb.cv.mknfold(dtrain, nfold, params)
folds <- xgb.cv.mknfold(dtrain, nfold, params, stratified)
obj_type = params[['objective']]
mat_pred = FALSE
if (!is.null(obj_type) && obj_type=='multi:softprob')