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
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
|
#' Ratio Variable Creation
#'
#' `step_ratio` creates a *specification* of a recipe
#' step that will create one or more ratios out of numeric
#' variables.
#'
#' @inheritParams step_date
#' @inheritParams step_pca
#' @inheritParams step_center
#' @param ... One or more selector functions to choose which
#' variables will be used in the *numerator* of the ratio.
#' When used with `denom_vars`, the dots indicate which
#' variables are used in the *denominator*. See
#' [selections()] for more details.
#' @param denom A call to `denom_vars` to specify which
#' variables are used in the denominator that can include specific
#' variable names separated by commas or different selectors (see
#' [selections()]). If a column is included in both lists
#' to be numerator and denominator, it will be removed from the
#' listing.
#' @param naming A function that defines the naming convention for
#' new ratio columns.
#' @param columns The column names used in the ratios. This
#' argument is not populated until [prep()] is
#' executed.
#' @template step-return
#' @details
#'
#' # Tidying
#'
#' When you [`tidy()`][tidy.recipe()] this step, a tibble with columns
#' `terms` (the selectors or variables selected) and `denom` is returned.
#'
#' @template case-weights-not-supported
#'
#' @family multivariate transformation steps
#' @export
#' @examplesIf rlang::is_installed("modeldata")
#' library(recipes)
#' data(biomass, package = "modeldata")
#'
#' biomass$total <- apply(biomass[, 3:7], 1, sum)
#' biomass_tr <- biomass[biomass$dataset == "Training", ]
#' biomass_te <- biomass[biomass$dataset == "Testing", ]
#'
#' rec <- recipe(HHV ~ carbon + hydrogen + oxygen + nitrogen +
#' sulfur + total,
#' data = biomass_tr
#' )
#'
#' ratio_recipe <- rec %>%
#' # all predictors over total
#' step_ratio(all_numeric_predictors(), denom = denom_vars(total)) %>%
#' # get rid of the original predictors
#' step_rm(all_predictors(), -ends_with("total"))
#'
#' ratio_recipe <- prep(ratio_recipe, training = biomass_tr)
#'
#' ratio_data <- bake(ratio_recipe, biomass_te)
#' ratio_data
step_ratio <-
function(recipe,
...,
role = "predictor",
trained = FALSE,
denom = denom_vars(),
naming = function(numer, denom) {
make.names(paste(numer, denom, sep = "_o_"))
},
columns = NULL,
keep_original_cols = TRUE,
skip = FALSE,
id = rand_id("ratio")) {
if (is_empty(denom)) {
rlang::abort(
paste0(
"Please supply at least one denominator variable specification. ",
"See ?selections."
)
)
}
add_step(
recipe,
step_ratio_new(
terms = enquos(...),
role = role,
trained = trained,
denom = denom,
naming = naming,
columns = columns,
keep_original_cols = keep_original_cols,
skip = skip,
id = id
)
)
}
step_ratio_new <-
function(terms, role, trained, denom, naming, columns,
keep_original_cols, skip, id) {
step(
subclass = "ratio",
terms = terms,
role = role,
trained = trained,
denom = denom,
naming = naming,
columns = columns,
keep_original_cols = keep_original_cols,
skip = skip,
id = id
)
}
#' @export
prep.step_ratio <- function(x, training, info = NULL, ...) {
col_names <- expand.grid(
top = recipes_eval_select(x$terms, training, info),
bottom = recipes_eval_select(x$denom, training, info),
stringsAsFactors = FALSE
)
col_names <- tibble::as_tibble(col_names)
col_names <- col_names[!(col_names$top == col_names$bottom), ]
check_type(
training[, c(col_names$top, col_names$bottom)],
types = c("double", "integer")
)
step_ratio_new(
terms = x$terms,
role = x$role,
trained = TRUE,
denom = x$denom,
naming = x$naming,
columns = col_names,
keep_original_cols = get_keep_original_cols(x),
skip = x$skip,
id = x$id
)
}
#' @export
bake.step_ratio <- function(object, new_data, ...) {
check_new_data(unname(object$columns$top), object, new_data)
res <- purrr::map2(
new_data[, object$columns$top],
new_data[, object$columns$bottom],
`/`
)
names(res) <- apply(
object$columns,
MARGIN = 1,
function(x) object$naming(x[1], x[2])
)
res <- tibble::new_tibble(res, nrow = nrow(new_data))
keep_original_cols <- get_keep_original_cols(object)
new_data <- bind_cols(new_data, res)
if (!keep_original_cols) {
union_cols <- union(object$columns$top, object$columns$bottom)
new_data <- new_data[, !(colnames(new_data) %in% union_cols), drop = FALSE]
}
new_data
}
print.step_ratio <-
function(x, width = max(20, options()$width - 30), ...) {
title <- "Ratios from "
vars <- c(unique(x$columns$top), unique(x$columns$bottom))
print_step(vars, c(x$terms, x$denom), x$trained, title, width)
invisible(x)
}
#' @export
#' @rdname step_ratio
denom_vars <- function(...) quos(...)
#' @rdname tidy.recipe
#' @export
tidy.step_ratio <- function(x, ...) {
if (is_trained(x)) {
res <- tibble(
terms = unname(x$columns$top),
denom = unname(x$columns$bottom)
)
} else {
res <- tidyr::crossing(
terms = sel2char(x$terms),
denom = sel2char(x$denom)
)
res <- as_tibble(res)
}
res$id <- x$id
arrange(res, terms, denom)
}
|
