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
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
|
#' Filter rows by position using dplyr
#'
#' `step_slice` creates a *specification* of a recipe step
#' that will filter rows using [dplyr::slice()].
#'
#' @template row-ops
#' @inheritParams step_center
#' @param ... Integer row values. See
#' [dplyr::slice()] for more details.
#' @param inputs Quosure of values given by `...`.
#' @template step-return
#' @details When an object in the user's global environment is
#' referenced in the expression defining the new variable(s),
#' it is a good idea to use quasiquotation (e.g. `!!`)
#' to embed the value of the object in the expression (to
#' be portable between sessions). See the examples.
#'
#' # Tidying
#'
#' When you [`tidy()`][tidy.recipe()] this step, a tibble with column
#' `terms` which contains the filtering indices is returned.
#'
#' @template case-weights-not-supported
#'
#' @family row operation steps
#' @family dplyr steps
#' @export
#' @examples
#' rec <- recipe(~., data = iris) %>%
#' step_slice(1:3)
#'
#' prepped <- prep(rec, training = iris %>% slice(1:75))
#' tidy(prepped, number = 1)
#'
#' library(dplyr)
#'
#' dplyr_train <-
#' iris %>%
#' as_tibble() %>%
#' slice(1:75) %>%
#' slice(1:3)
#'
#' rec_train <- bake(prepped, new_data = NULL)
#' all.equal(dplyr_train, rec_train)
#'
#' dplyr_test <-
#' iris %>%
#' as_tibble() %>%
#' slice(76:150) %>%
#' slice(1:3)
#' rec_test <- bake(prepped, iris %>% slice(76:150))
#' all.equal(dplyr_test, rec_test)
#'
#' # Embedding the integer expression (or vector) into the
#' # recipe:
#'
#' keep_rows <- 1:6
#'
#' qq_rec <-
#' recipe(~., data = iris) %>%
#' # Embed `keep_rows` in the call using !!
#' step_slice(!!keep_rows) %>%
#' prep(training = iris)
#'
#' tidy(qq_rec, number = 1)
step_slice <- function(recipe, ...,
role = NA,
trained = FALSE,
inputs = NULL,
skip = TRUE,
id = rand_id("slice")) {
inputs <- enquos(...)
add_step(
recipe,
step_slice_new(
terms = terms,
trained = trained,
role = role,
inputs = inputs,
skip = skip,
id = id
)
)
}
step_slice_new <-
function(terms, role, trained, inputs, skip, id) {
step(
subclass = "slice",
terms = terms,
role = role,
trained = trained,
inputs = inputs,
skip = skip,
id = id
)
}
#' @export
prep.step_slice <- function(x, training, info = NULL, ...) {
step_slice_new(
terms = x$terms,
trained = TRUE,
role = x$role,
inputs = x$inputs,
skip = x$skip,
id = x$id
)
}
#' @export
bake.step_slice <- function(object, new_data, ...) {
dplyr::slice(new_data, !!!object$inputs)
}
print.step_slice <-
function(x, width = max(20, options()$width - 35), ...) {
title <- "Row filtering via position "
tr_obj <- format_selectors(x$inputs, width)
print_step(tr_obj, x$inputs, x$trained, title, width)
invisible(x)
}
#' @rdname tidy.recipe
#' @export
tidy.step_slice <- function(x, ...) {
cond_expr <- map(x$inputs, quo_get_expr)
cond_expr <- map_chr(cond_expr, quo_text, width = options()$width, nlines = 1)
tibble(
terms = unname(cond_expr),
id = rep(x$id, length(x$inputs))
)
}
|
