1
#' Sampling for the Apparent Error Rate
2
#'
3
#' When building a model on a data set and re-predicting the same data, the
4
#'   performance estimate from those predictions is often called the
5
#'   "apparent" performance of the model. This estimate can be wildly
6
#'   optimistic. "Apparent sampling" here means that the analysis and
7
#'   assessment samples are the same. These resamples are sometimes used in
8
#'   the analysis of bootstrap samples and should otherwise be
9
#'   avoided like old sushi.
10
#'
11
#' @inheritParams vfold_cv
12
#' @return  A tibble with a single row and classes `apparent`,
13
#'   `rset`, `tbl_df`, `tbl`, and `data.frame`. The
14
#'   results include a column for the data split objects and one column
15
#'   called `id` that has a character string with the resample identifier.
16
#' @examples
17
#' apparent(mtcars)
18
#' @export
19
apparent <- function(data, ...) {
20 1
  splits <- rsplit(data, in_id = 1:nrow(data), out_id = 1:nrow(data))
21
  # splits <- rm_out(splits)
22 1
  class(splits) <- c("rsplit", "apparent_split")
23 1
  split_objs <- tibble::tibble(splits = list(splits), id = "Apparent")
24

25 1
  new_rset(splits = split_objs$splits,
26 1
           ids = split_objs$id,
27 1
           attrib = NULL,
28 1
           subclass = c("apparent", "rset"))
29
}
30

31
#' @export
32
print.apparent <- function(x, ...) {
33 0
  cat("#", pretty(x), "\n")
34 0
  class(x) <- class(x)[!(class(x) %in% c("apparent", "rset"))]
35 0
  print(x, ...)
36
}
37

38

Read our documentation on viewing source code .

Loading