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
136
137
138
139
140
141
142
143
|
#' Sort rows using dplyr
#'
#' `step_arrange` creates a *specification* of a recipe step
#' that will sort rows using [dplyr::arrange()].
#'
#' @inheritParams step_center
#' @param ... Comma separated list of unquoted variable names.
#' Use `desc()`` to sort a variable in descending order. See
#' [dplyr::arrange()] for more details. For the `tidy`
#' method, these are not currently used.
#' @param role Not used by this step since no new variables are
#' created.
#' @param inputs Quosure of values given by `...`.
#' @return An updated version of `recipe` with the new step
#' added to the sequence of existing steps (if any). For the
#' `tidy` method, a tibble with columns `terms` which
#' contains the sorting variable(s) or expression(s). The
#' expressions are text representations and are not parsable.
#' @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.
#' @keywords datagen
#' @concept preprocessing
#' @export
#' @examples
#' rec <- recipe( ~ ., data = iris) %>%
#' step_arrange(desc(Sepal.Length), 1/Petal.Length)
#'
#' prepped <- prep(rec, training = iris %>% slice(1:75))
#' tidy(prepped, number = 1)
#'
#' library(dplyr)
#'
#' dplyr_train <-
#' iris %>%
#' as_tibble() %>%
#' slice(1:75) %>%
#' dplyr::arrange(desc(Sepal.Length), 1/Petal.Length)
#'
#' rec_train <- bake(prepped, new_data = NULL)
#' all.equal(dplyr_train, rec_train)
#'
#' dplyr_test <-
#' iris %>%
#' as_tibble() %>%
#' slice(76:150) %>%
#' dplyr::arrange(desc(Sepal.Length), 1/Petal.Length)
#' rec_test <- bake(prepped, iris %>% slice(76:150))
#' all.equal(dplyr_test, rec_test)
#'
#' # When you have variables/expressions, you can create a
#' # list of symbols with `rlang::syms()`` and splice them in
#' # the call with `!!!`. See https://tidyeval.tidyverse.org
#'
#' sort_vars <- c("Sepal.Length", "Petal.Length")
#'
#' qq_rec <-
#' recipe( ~ ., data = iris) %>%
#' # Embed the `values` object in the call using !!!
#' step_arrange(!!!syms(sort_vars)) %>%
#' prep(training = iris)
#'
#' tidy(qq_rec, number = 1)
step_arrange <- function(
recipe, ...,
role = NA,
trained = FALSE,
inputs = NULL,
skip = FALSE,
id = rand_id("arrange")
) {
inputs <- enquos(...)
add_step(
recipe,
step_arrange_new(
terms = terms,
trained = trained,
role = role,
inputs = inputs,
skip = skip,
id = id
)
)
}
step_arrange_new <-
function(terms, role, trained, inputs, skip, id) {
step(
subclass = "arrange",
terms = terms,
role = role,
trained = trained,
inputs = inputs,
skip = skip,
id = id
)
}
#' @export
prep.step_arrange <- function(x, training, info = NULL, ...) {
step_arrange_new(
terms = x$terms,
trained = TRUE,
role = x$role,
inputs = x$inputs,
skip = x$skip,
id = x$id
)
}
#' @export
bake.step_arrange <- function(object, new_data, ...) {
dplyr::arrange(new_data, !!!object$inputs)
}
print.step_arrange <-
function(x, width = max(20, options()$width - 35), ...) {
cat("Row arrangement")
if (x$trained) {
cat(" [trained]\n")
} else {
cat("\n")
}
invisible(x)
}
#' @rdname step_arrange
#' @param x A `step_arrange` object
#' @export
tidy.step_arrange <- 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 = cond_expr,
id = rep(x$id, length(x$inputs))
)
}
|
