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
|
#' Check for Missing Values
#'
#' `check_missing` creates a *specification* of a recipe
#' operation that will check if variables contain missing values.
#'
#' @param recipe A recipe object. The check will be added to the
#' sequence of operations for this recipe.
#' @param ... One or more selector functions to choose variables
#' for this check. See [selections()] for more details.
#' @param role Not used by this check since no new variables are
#' created.
#' @param trained A logical for whether the selectors in `...`
#' have been resolved by [prep()].
#' @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 check to identify it.
#' @param skip A logical. Should the check be skipped when the
#' recipe is baked by [bake()]? While all operations are baked
#' when [prep()] 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 = TRUE` as it may affect
#' the computations for subsequent operations.
#' @template check-return
#' @family checks
#' @export
#' @details This check will break the `bake` function if any of the checked
#' columns does contain `NA` values. If the check passes, nothing is changed
#' to the data.
#'
#' # tidy() results
#'
#' When you [`tidy()`][tidy.recipe()] this check, a tibble with column
#' `terms` (the selectors or variables selected) is returned.
#'
#' @examplesIf rlang::is_installed("modeldata")
#' data(credit_data, package = "modeldata")
#' is.na(credit_data) %>% colSums()
#'
#' # If the test passes, `new_data` is returned unaltered
#' recipe(credit_data) %>%
#' check_missing(Age, Expenses) %>%
#' prep() %>%
#' bake(credit_data)
#'
#' # If your training set doesn't pass, prep() will stop with an error
#' \dontrun{
#' recipe(credit_data) %>%
#' check_missing(Income) %>%
#' prep()
#' }
#'
#' # If `new_data` contain missing values, the check will stop `bake()`
#'
#' train_data <- credit_data %>% dplyr::filter(Income > 150)
#' test_data <- credit_data %>% dplyr::filter(Income <= 150 | is.na(Income))
#'
#' rp <- recipe(train_data) %>%
#' check_missing(Income) %>%
#' prep()
#'
#' bake(rp, train_data)
#' \dontrun{
#' bake(rp, test_data)
#' }
check_missing <-
function(recipe,
...,
role = NA,
trained = FALSE,
columns = NULL,
skip = FALSE,
id = rand_id("missing")) {
add_check(
recipe,
check_missing_new(
terms = enquos(...),
role = role,
trained = trained,
columns = columns,
skip = skip,
id = id
)
)
}
check_missing_new <-
function(terms, role, trained, columns, skip, id) {
check(
subclass = "missing",
prefix = "check_",
terms = terms,
role = role,
trained = trained,
columns = columns,
skip = skip,
id = id
)
}
prep.check_missing <- function(x, training, info = NULL, ...) {
col_names <- recipes_eval_select(x$terms, training, info)
check_missing_new(
terms = x$terms,
role = x$role,
trained = TRUE,
columns = col_names,
skip = x$skip,
id = x$id
)
}
bake.check_missing <- function(object, new_data, ...) {
col_names <- object$columns
subset_to_check <- new_data[col_names]
nr_na <- colSums(is.na(subset_to_check))
if (any(nr_na > 0)) {
with_na <- names(nr_na[nr_na > 0])
with_na_str <- paste(paste0("`", with_na, "`"), collapse = ", ")
rlang::abort(paste0(
"The following columns contain missing values: ",
with_na_str, "."
))
}
new_data
}
print.check_missing <-
function(x, width = max(20, options()$width - 30), ...) {
title <- "Check missing values for "
print_step(x$columns, x$terms, x$trained, title, width)
invisible(x)
}
#' @rdname tidy.recipe
#' @export
tidy.check_missing <- function(x, ...) {
if (is_trained(x)) {
res <- tibble(terms = unname(x$columns))
} else {
res <- tibble(terms = sel2char(x$terms))
}
res$id <- x$id
res
}
|
