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
|
#' Inverse Logit Transformation
#'
#' `step_invlogit` creates a *specification* of a recipe
#' step that will transform the data from real values to be between
#' zero and one.
#'
#' @inheritParams step_center
#' @param columns A character string of variable names that will
#' be populated (eventually) by the `terms` argument.
#' @template step-return
#' @family individual transformation steps
#' @export
#' @details The inverse logit transformation takes values on the
#' real line and translates them to be between zero and one using
#' the function `f(x) = 1/(1+exp(-x))`.
#'
#' # Tidying
#'
#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns
#' `terms` (the columns that will be affected) is returned.
#'
#' @template case-weights-not-supported
#'
#' @examplesIf rlang::is_installed("modeldata")
#' data(biomass, package = "modeldata")
#'
#' biomass_tr <- biomass[biomass$dataset == "Training", ]
#' biomass_te <- biomass[biomass$dataset == "Testing", ]
#'
#' rec <- recipe(
#' HHV ~ carbon + hydrogen + oxygen + nitrogen + sulfur,
#' data = biomass_tr
#' )
#'
#' ilogit_trans <- rec %>%
#' step_center(carbon, hydrogen) %>%
#' step_scale(carbon, hydrogen) %>%
#' step_invlogit(carbon, hydrogen)
#'
#' ilogit_obj <- prep(ilogit_trans, training = biomass_tr)
#'
#' transformed_te <- bake(ilogit_obj, biomass_te)
#' plot(biomass_te$carbon, transformed_te$carbon)
step_invlogit <-
function(recipe, ..., role = NA, trained = FALSE, columns = NULL,
skip = FALSE, id = rand_id("invlogit")) {
add_step(
recipe,
step_invlogit_new(
terms = enquos(...),
role = role,
trained = trained,
columns = columns,
skip = skip,
id = id
)
)
}
step_invlogit_new <-
function(terms, role, trained, columns, skip, id) {
step(
subclass = "invlogit",
terms = terms,
role = role,
trained = trained,
columns = columns,
skip = skip,
id = id
)
}
#' @export
prep.step_invlogit <- function(x, training, info = NULL, ...) {
col_names <- recipes_eval_select(x$terms, training, info)
check_type(training[, col_names], types = c("double", "integer"))
step_invlogit_new(
terms = x$terms,
role = x$role,
trained = TRUE,
columns = col_names,
skip = x$skip,
id = x$id
)
}
#' @export
bake.step_invlogit <- function(object, new_data, ...) {
check_new_data(names(object$columns), object, new_data)
for (i in seq_along(object$columns)) {
new_data[, object$columns[i]] <-
binomial()$linkinv(unlist(getElement(new_data, object$columns[i]),
use.names = FALSE
))
}
new_data
}
print.step_invlogit <-
function(x, width = max(20, options()$width - 26), ...) {
title <- "Inverse logit on "
print_step(x$columns, x$terms, x$trained, title, width)
invisible(x)
}
#' @rdname tidy.recipe
#' @export
tidy.step_invlogit <- function(x, ...) {
res <- simple_terms(x, ...)
res$id <- x$id
res
}
|
