From 271e8202a7b077f9a5afab25eca3d67471303878 Mon Sep 17 00:00:00 2001
From: Vadim Khotilovich <khotilovich@gmail.com>
Date: Fri, 3 Apr 2015 12:20:34 -0500
Subject: [PATCH] force xgb.cv to return numeric performance values instead of
 character; update its docs

---
 R-package/R/xgb.cv.R    | 15 +++++++++++----
 R-package/man/xgb.cv.Rd | 10 ++++++++--
 2 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/R-package/R/xgb.cv.R b/R-package/R/xgb.cv.R
index 38f70b973..db2ecf103 100644
--- a/R-package/R/xgb.cv.R
+++ b/R-package/R/xgb.cv.R
@@ -50,12 +50,19 @@
 #' @param feval custimized evaluation function. Returns 
 #'   \code{list(metric='metric-name', value='metric-value')} with given 
 #'   prediction and dtrain.
-#' @param stratified \code{boolean}, whether the sampling of folds should be stratified by the values of labels in \code{data}
+#' @param stratified \code{boolean}, whether 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.
-#' 
+#' @return
+#' If \code{prediction = TRUE}, a list with the following elements is returned:
+#' \itemize{
+#'   \item \code{dt} a \code{data.table} with each mean and standard deviation stat for training set and test set
+#'   \item \code{pred} an array or matrix (for multiclass classification) with predictions for each CV-fold for the model having been trained on the data in all other folds.
+#' }
+#'
+#' If \code{prediction = FALSE}, just a \code{data.table} with each mean and standard deviation stat for training set and test set is returned.
+#'
 #' @details 
 #' The original sample is randomly partitioned into \code{nfold} equal size subsamples. 
 #' 
@@ -148,7 +155,7 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL, missing =
   dt <- read.table(text = "", colClasses = type, col.names = colnames) %>% as.data.table
   split <- str_split(string = history, pattern = "\t")
   
-  for(line in split) dt <- line[2:length(line)] %>% str_extract_all(pattern = "\\d*\\.+\\d*") %>% unlist %>% as.list %>% {vec <- .; rbindlist(list(dt, vec), use.names = F, fill = F)}
+  for(line in split) dt <- line[2:length(line)] %>% str_extract_all(pattern = "\\d*\\.+\\d*") %>% unlist %>% as.numeric %>% as.list %>% {rbindlist(list(dt, .), use.names = F, fill = F)}
   
   if (prediction) {
     return(list(dt = dt,pred = predictValues))
diff --git a/R-package/man/xgb.cv.Rd b/R-package/man/xgb.cv.Rd
index 6f8ee06cb..20423f76a 100644
--- a/R-package/man/xgb.cv.Rd
+++ b/R-package/man/xgb.cv.Rd
@@ -57,14 +57,20 @@ gradient with given prediction and dtrain.}
 \code{list(metric='metric-name', value='metric-value')} with given
 prediction and dtrain.}
 
-\item{stratified}{\code{boolean}, whether the sampling of folds should be stratified by the values of labels in \code{data}}
+\item{stratified}{\code{boolean}, whether sampling of folds should be stratified by the values of labels in \code{data}}
 
 \item{verbose}{\code{boolean}, print the statistics during the process}
 
 \item{...}{other parameters to pass to \code{params}.}
 }
 \value{
-A \code{data.table} with each mean and standard deviation stat for training set and test set.
+If \code{prediction = TRUE}, a list with the following elements is returned:
+\itemize{
+  \item \code{dt} a \code{data.table} with each mean and standard deviation stat for training set and test set
+  \item \code{pred} an array or matrix (for multiclass classification) with predictions for each CV-fold for the model having been trained on the data in all other folds.
+}
+
+If \code{prediction = FALSE}, just a \code{data.table} with each mean and standard deviation stat for training set and test set is returned.
 }
 \description{
 The cross valudation function of xgboost