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
|
#' Convert Ordered Factors to Unordered Factors
#'
#' `step_unorder` creates a *specification* of a recipe
#' step that will transform the data.
#'
#' @inheritParams step_center
#' @param columns A character string of variable names that will
#' be populated (eventually) by the `terms` argument.
#' @template step-return
#' @family dummy variable and encoding steps
#' @export
#' @details The factors level order is preserved during the transformation.
#'
#' # Tidying
#'
#' When you [`tidy()`][tidy.recipe()] this step, a tibble with column
#' `terms` (the columns that will be affected) is returned.
#'
#' @template case-weights-not-supported
#'
#' @examples
#' lmh <- c("Low", "Med", "High")
#'
#' examples <- data.frame(
#' X1 = factor(rep(letters[1:4], each = 3)),
#' X2 = ordered(rep(lmh, each = 4),
#' levels = lmh
#' )
#' )
#'
#' rec <- recipe(~ X1 + X2, data = examples)
#'
#' factor_trans <- rec %>%
#' step_unorder(all_nominal_predictors())
#'
#' factor_obj <- prep(factor_trans, training = examples)
#'
#' transformed_te <- bake(factor_obj, examples)
#' table(transformed_te$X2, examples$X2)
#'
#' tidy(factor_trans, number = 1)
#' tidy(factor_obj, number = 1)
step_unorder <-
function(recipe,
...,
role = NA,
trained = FALSE,
columns = NULL,
skip = FALSE,
id = rand_id("unorder")) {
add_step(
recipe,
step_unorder_new(
terms = enquos(...),
role = role,
trained = trained,
columns = columns,
skip = skip,
id = id
)
)
}
step_unorder_new <-
function(terms, role, trained, columns, skip, id) {
step(
subclass = "unorder",
terms = terms,
role = role,
trained = trained,
columns = columns,
skip = skip,
id = id
)
}
#' @export
prep.step_unorder <- function(x, training, info = NULL, ...) {
col_names <- recipes_eval_select(x$terms, training, info)
check_type(training[, col_names], types = c("string", "factor", "ordered"))
step_unorder_new(
terms = x$terms,
role = x$role,
trained = TRUE,
columns = col_names,
skip = x$skip,
id = x$id
)
}
#' @export
bake.step_unorder <- function(object, new_data, ...) {
check_new_data(names(object$columns), object, new_data)
for (i in seq_along(object$columns)) {
new_data[, object$columns[i]] <-
factor(as.character(getElement(new_data, object$columns[i])),
levels = levels(getElement(new_data, object$columns[i]))
)
}
new_data
}
print.step_unorder <-
function(x, width = max(20, options()$width - 33), ...) {
title <- "Unordered variables "
print_step(x$columns, x$terms, x$trained, title, width)
invisible(x)
}
#' @rdname tidy.recipe
#' @export
tidy.step_unorder <- function(x, ...) {
res <- simple_terms(x, ...)
res$id <- x$id
res
}
|
