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
|
#' Remove observations with missing values
#'
#' `step_naomit` creates a *specification* of a recipe step that
#' will remove observations (rows of data) if they contain `NA`
#' or `NaN` values.
#'
#' @param recipe A recipe object. The step will be added to the sequence of
#' operations for this recipe.
#' @param ... One or more selector functions to choose which
#' variables will be used to remove observations containing `NA` or `NaN`
#' values. See [selections()] for more details.
#' @param role Unused, include for consistency with other steps.
#' @param trained A logical to indicate if the quantities for preprocessing
#' have been estimated. Again included for consistency.
#' @param columns A character string of variable names that will
#' be populated (eventually) by the `terms` argument.
#' @param id A character string that is unique to this step to identify it.
#' @param skip A logical. Should the step be skipped when the
#' recipe is baked by [bake.recipe()]? While all operations are baked
#' when [prep.recipe()] is run, some operations may not be able to be
#' conducted on new data (e.g. processing the outcome variable(s)).
#' Care should be taken when using `skip = FALSE`.
#'
#' @template row-ops
#' @rdname step_naomit
#' @return An updated version of `recipe` with the
#' new step added to the sequence of existing steps (if any).
#' @export
#'
#' @examples
#'
#' recipe(Ozone ~ ., data = airquality) %>%
#' step_naomit(Solar.R) %>%
#' prep(airquality, verbose = FALSE) %>%
#' bake(new_data = NULL)
#'
#' @seealso [step_filter()] [step_sample()] [step_slice()]
step_naomit <- function(recipe, ..., role = NA, trained = FALSE,
columns = NULL, skip = FALSE,
id = rand_id("naomit")) {
add_step(
recipe,
step_naomit_new(
terms = ellipse_check(...),
role = role,
trained = trained,
columns = columns,
skip = skip,
id = id
)
)
}
step_naomit_new <- function(terms, role, trained, columns, skip, id) {
step(
subclass = "naomit",
terms = terms,
role = role,
trained = trained,
columns = columns,
skip = skip,
id = id
)
}
#' @export
prep.step_naomit <- function(x, training, info = NULL, ...) {
step_naomit_new(
terms = x$terms,
role = x$role,
trained = TRUE,
columns = eval_select_recipes(x$terms, training, info),
skip = x$skip,
id = x$id
)
}
#' @export
bake.step_naomit <- function(object, new_data, ...) {
tibble::as_tibble(tidyr::drop_na(new_data, object$columns))
}
print.step_naomit <-
function(x, width = max(20, options()$width - 30), ...) {
cat("Removing rows with NA values in ", sep = "")
cat(format_selectors(x$terms, width = width))
cat("\n")
invisible(x)
}
#' @rdname step_naomit
#' @param x A `step_naomit` object.
#' @export
tidy.step_naomit <- function(x, ...) {
res <-simple_terms(x, ...)
res$id <- x$id
res
}
|
