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
160
161
162
163
164
165
166
167
168
169
170
|
#' Logarithmic Transformation
#'
#' `step_log` creates a *specification* of a recipe step
#' that will log transform data.
#'
#' @inheritParams step_center
#' @param ... One or more selector functions to choose which
#' variables are affected by the step. See [selections()]
#' 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 base A numeric value for the base.
#' @param offset An optional value to add to the data prior to
#' logging (to avoid `log(0)`).
#' @param columns A character string of variable names that will
#' be populated (eventually) by the `terms` argument.
#' @param signed A logical indicating whether to take the signed log.
#' This is sign(x) * abs(x) when abs(x) => 1 or 0 if abs(x) < 1.
#' If `TRUE` the `offset` argument will be ignored.
#' @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` (the
#' columns that will be affected) and `base`.
#' @keywords datagen
#' @concept preprocessing
#' @concept transformation_methods
#' @export
#' @examples
#' set.seed(313)
#' examples <- matrix(exp(rnorm(40)), ncol = 2)
#' examples <- as.data.frame(examples)
#'
#' rec <- recipe(~ V1 + V2, data = examples)
#'
#' log_trans <- rec %>%
#' step_log(all_predictors())
#'
#' log_obj <- prep(log_trans, training = examples)
#'
#' transformed_te <- bake(log_obj, examples)
#' plot(examples$V1, transformed_te$V1)
#'
#' tidy(log_trans, number = 1)
#' tidy(log_obj, number = 1)
#'
#' # using the signed argument with negative values
#'
#' examples2 <- matrix(rnorm(40, sd = 5), ncol = 2)
#' examples2 <- as.data.frame(examples2)
#'
#' recipe(~ V1 + V2, data = examples2) %>%
#' step_log(all_predictors()) %>%
#' prep(training = examples2) %>%
#' bake(examples2)
#'
#' recipe(~ V1 + V2, data = examples2) %>%
#' step_log(all_predictors(), signed = TRUE) %>%
#' prep(training = examples2) %>%
#' bake(examples2)
#'
#' @seealso [step_logit()] [step_invlogit()]
#' [step_hyperbolic()] [step_sqrt()]
#' [recipe()] [prep.recipe()]
#' [bake.recipe()]
step_log <-
function(recipe,
...,
role = NA,
trained = FALSE,
base = exp(1),
offset = 0,
columns = NULL,
skip = FALSE,
signed = FALSE,
id = rand_id("log")
) {
add_step(
recipe,
step_log_new(
terms = ellipse_check(...),
role = role,
trained = trained,
base = base,
offset = offset,
columns = columns,
skip = skip,
signed = signed,
id = id
)
)
}
step_log_new <-
function(terms, role, trained, base, offset, columns, skip, signed, id) {
step(
subclass = "log",
terms = terms,
role = role,
trained = trained,
base = base,
offset = offset,
columns = columns,
skip = skip,
signed = signed,
id = id
)
}
#' @export
prep.step_log <- function(x, training, info = NULL, ...) {
col_names <- eval_select_recipes(x$terms, training, info)
check_type(training[, col_names])
step_log_new(
terms = x$terms,
role = x$role,
trained = TRUE,
base = x$base,
offset = x$offset,
columns = col_names,
skip = x$skip,
signed = x$signed,
id = x$id
)
}
#' @export
bake.step_log <- function(object, new_data, ...) {
col_names <- object$columns
# for backward compat
if(all(names(object) != "offset"))
object$offset <- 0
if (!object$signed){
for (i in seq_along(col_names))
new_data[, col_names[i]] <-
log(new_data[[ col_names[i] ]] + object$offset, base = object$base)
} else {
if (object$offset != 0)
rlang::warn("When signed is TRUE, offset will be ignored")
for (i in seq_along(col_names))
new_data[, col_names[i]] <-
ifelse(abs(new_data[[ col_names[i] ]]) < 1,
0,
sign(new_data[[ col_names[i] ]]) *
log(abs(new_data[[ col_names[i] ]]), base = object$base ))
}
as_tibble(new_data)
}
print.step_log <-
function(x, width = max(20, options()$width - 31), ...) {
msg <- ifelse(x$signed, "Signed log ", "Log ")
cat(msg, "transformation on ", sep = "")
printer(x$columns, x$terms, x$trained, width = width)
invisible(x)
}
#' @rdname step_log
#' @param x A `step_log` object.
#' @export
tidy.step_log <- function(x, ...) {
out <- simple_terms(x, ...)
out$base <- x$base
out$id <- x$id
out
}
|
