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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
|
#' Add new variables using `mutate`
#'
#' `step_mutate` creates a *specification* of a recipe step
#' that will add variables using [dplyr::mutate()].
#'
#' @inheritParams step_center
#' @param ... Name-value pairs of expressions. See [dplyr::mutate()].
#' If the argument is not named, the expression is converted to
#' a column name.
#' @param role For model terms created by this step, what analysis
#' role should they be assigned? By default, the function assumes
#' that the new dimension columns created by the original variables
#' will be used as predictors in a model.
#' @param inputs Quosure(s) of `...`.
#' @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 `values` which
#' contains the `mutate` expressions as character strings
#' (and are not reparsable).
#' @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
#' @concept transformation_methods
#' @export
#' @examples
#' rec <-
#' recipe( ~ ., data = iris) %>%
#' step_mutate(
#' dbl_width = Sepal.Width * 2,
#' half_length = Sepal.Length / 2
#' )
#'
#' prepped <- prep(rec, training = iris %>% slice(1:75))
#'
#' library(dplyr)
#'
#' dplyr_train <-
#' iris %>%
#' as_tibble() %>%
#' slice(1:75) %>%
#' mutate(
#' dbl_width = Sepal.Width * 2,
#' half_length = Sepal.Length / 2
#' )
#'
#' rec_train <- bake(prepped, new_data = NULL)
#' all.equal(dplyr_train, rec_train)
#'
#' dplyr_test <-
#' iris %>%
#' as_tibble() %>%
#' slice(76:150) %>%
#' mutate(
#' dbl_width = Sepal.Width * 2,
#' half_length = Sepal.Length / 2
#' )
#' rec_test <- bake(prepped, iris %>% slice(76:150))
#' all.equal(dplyr_test, rec_test)
#'
#' # Embedding objects:
#' const <- 1.414
#'
#' qq_rec <-
#' recipe( ~ ., data = iris) %>%
#' step_mutate(
#' bad_approach = Sepal.Width * const,
#' best_approach = Sepal.Width * !!const
#' ) %>%
#' prep(training = iris)
#'
#' bake(qq_rec, new_data = NULL, contains("appro")) %>% slice(1:4)
#'
#' # The difference:
#' tidy(qq_rec, number = 1)
step_mutate <- function(
recipe, ...,
role = "predictor",
trained = FALSE,
inputs = NULL,
skip = FALSE,
id = rand_id("mutate")
) {
inputs <- enquos(..., .named = TRUE)
add_step(
recipe,
step_mutate_new(
terms = terms,
trained = trained,
role = role,
inputs = inputs,
skip = skip,
id = id
)
)
}
step_mutate_new <-
function(terms, role, trained, inputs, skip, id) {
step(
subclass = "mutate",
terms = terms,
role = role,
trained = trained,
inputs = inputs,
skip = skip,
id = id
)
}
#' @export
prep.step_mutate <- function(x, training, info = NULL, ...) {
step_mutate_new(
terms = x$terms,
trained = TRUE,
role = x$role,
inputs = x$inputs,
skip = x$skip,
id = x$id
)
}
#' @export
bake.step_mutate <- function(object, new_data, ...) {
dplyr::mutate(new_data, !!!object$inputs)
}
print.step_mutate <-
function(x, width = max(20, options()$width - 35), ...) {
cat("Variable mutation for ",
paste0(names(x$inputs), collapse = ", "),
sep = "")
if (x$trained) {
cat(" [trained]\n")
} else {
cat("\n")
}
invisible(x)
}
#' @rdname step_mutate
#' @param x A `step_mutate` object
#' @export
tidy.step_mutate <- function(x, ...) {
var_expr <- map(x$inputs, quo_get_expr)
var_expr <- map_chr(var_expr, quo_text, width = options()$width, nlines = 1)
tibble(
terms = names(x$inputs),
value = var_expr,
id = rep(x$id, length(x$inputs))
)
}
|
