1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
|
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/tidy.R
\name{tidy.rsplit}
\alias{tidy.rsplit}
\alias{tidy.rset}
\alias{tidy.vfold_cv}
\alias{tidy.nested_cv}
\title{Tidy Resampling Object}
\usage{
\method{tidy}{rsplit}(x, unique_ind = TRUE, ...)
\method{tidy}{rset}(x, ...)
\method{tidy}{vfold_cv}(x, ...)
\method{tidy}{nested_cv}(x, ...)
}
\arguments{
\item{x}{A \code{rset} or \code{rsplit} object}
\item{unique_ind}{Should unique row identifiers be returned? For example,
if \code{FALSE} then bootstrapping results will include multiple rows in the
sample for the same row in the original data.}
\item{...}{Not currently used.}
}
\value{
A tibble with columns \code{Row} and \code{Data}. The latter has possible
values "Analysis" or "Assessment". For \code{rset} inputs, identification columns
are also returned but their names and values depend on the type of
resampling. \code{vfold_cv} contains a column "Fold" and, if repeats are used,
another called "Repeats". \code{bootstraps} and \code{mc_cv} use the column
"Resample".
}
\description{
The \code{tidy} function from the \pkg{broom} package can be used on \code{rset} and
\code{rsplit} objects to generate tibbles with which rows are in the analysis and
assessment sets.
}
\details{
Note that for nested resampling, the rows of the inner resample,
named \code{inner_Row}, are \emph{relative} row indices and do not correspond to the
rows in the original data set.
}
\examples{
\dontshow{if (rlang::is_installed("ggplot2")) (if (getRversion() >= "3.4") withAutoprint else force)(\{ # examplesIf}
library(ggplot2)
theme_set(theme_bw())
set.seed(4121)
cv <- tidy(vfold_cv(mtcars, v = 5))
ggplot(cv, aes(x = Fold, y = Row, fill = Data)) +
geom_tile() +
scale_fill_brewer()
set.seed(4121)
rcv <- tidy(vfold_cv(mtcars, v = 5, repeats = 2))
ggplot(rcv, aes(x = Fold, y = Row, fill = Data)) +
geom_tile() +
facet_wrap(~Repeat) +
scale_fill_brewer()
set.seed(4121)
mccv <- tidy(mc_cv(mtcars, times = 5))
ggplot(mccv, aes(x = Resample, y = Row, fill = Data)) +
geom_tile() +
scale_fill_brewer()
set.seed(4121)
bt <- tidy(bootstraps(mtcars, time = 5))
ggplot(bt, aes(x = Resample, y = Row, fill = Data)) +
geom_tile() +
scale_fill_brewer()
dat <- data.frame(day = 1:30)
# Resample by week instead of day
ts_cv <- rolling_origin(dat,
initial = 7, assess = 7,
skip = 6, cumulative = FALSE
)
ts_cv <- tidy(ts_cv)
ggplot(ts_cv, aes(x = Resample, y = factor(Row), fill = Data)) +
geom_tile() +
scale_fill_brewer()
\dontshow{\}) # examplesIf}
}
|
