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
|
#' Check for New Values
#'
#' `check_new_values` creates a *specification* of a recipe
#' operation that will check if variables contain new 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 which
#' variables are checked in the check. See [selections()]
#' for more details. For the `tidy` method, these are not
#' currently used.
#' @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 ignore_NA A logical that indicates if we should consider missing
#' values as value or not. Defaults to `TRUE`.
#' @param values A named list with the allowed values.
#' This is `NULL` until computed by prep.recipe().
#' @param id A character string that is unique to this step to identify it.
#' @param skip A logical. Should the check 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 = TRUE` as it may affect
#' the computations for subsequent operations.
#' @return An updated version of `recipe` with the new check
#' added to the sequence of existing operations (if any). For the
#' `tidy` method, a tibble with columns `terms` (the
#' selectors or variables selected).
#' @export
#' @details This check will break the `bake` function if any of the checked
#' columns does contain values it did not contain when `prep` was called
#' on the recipe. If the check passes, nothing is changed to the data.
#' @examples
#' library(modeldata)
#' data(credit_data)
#'
#' # If the test passes, `new_data` is returned unaltered
#' recipe(credit_data) %>%
#' check_new_values(Home) %>%
#' prep() %>%
#' bake(new_data = credit_data)
#'
#' # If `new_data` contains values not in `x` at the `prep()` function,
#' # the `bake()` function will break.
#' \dontrun{
#' recipe(credit_data %>% dplyr::filter(Home != "rent")) %>%
#' check_new_values(Home) %>%
#' prep() %>%
#' bake(new_data = credit_data)
#' }
#'
#' # By default missing values are ignored, so this passes.
#' recipe(credit_data %>% dplyr::filter(!is.na(Home))) %>%
#' check_new_values(Home) %>%
#' prep() %>%
#' bake(credit_data)
#'
#' # Use `ignore_NA = FALSE` if you consider missing values as a value,
#' # that should not occur when not observed in the train set.
#' \dontrun{
#' recipe(credit_data %>% dplyr::filter(!is.na(Home))) %>%
#' check_new_values(Home, ignore_NA = FALSE) %>%
#' prep() %>%
#' bake(credit_data)
#' }
check_new_values <-
function(recipe,
...,
role = NA,
trained = FALSE,
columns = NULL,
ignore_NA = TRUE,
values = NULL,
skip = FALSE,
id = rand_id("new_values")) {
add_check(
recipe,
check_new_values_new(
terms = ellipse_check(...),
role = role,
trained = trained,
columns = columns,
ignore_NA = ignore_NA,
values = values,
skip = skip,
id = id
)
)
}
check_new_values_new <-
function(terms, role, trained, columns, skip, id, values, ignore_NA) {
check(subclass = "new_values",
prefix = "check_",
terms = terms,
role = role,
trained = trained,
columns = columns,
skip = skip,
id = id,
values = values,
ignore_NA = ignore_NA)
}
new_values_func <- function(x,
allowed_values,
colname = "x",
ignore_NA = TRUE) {
new_vals <- setdiff(as.character(x), as.character(allowed_values))
if (length(new_vals) == 0) return()
if (all(is.na(new_vals)) && ignore_NA) return()
if (ignore_NA) new_vals <- new_vals[!is.na(new_vals)]
rlang::abort(paste0(
colname,
" contains the new value(s): ",
paste(new_vals, collapse = ",")
))
}
prep.check_new_values <- function(x, training, info = NULL, ...) {
col_names <- eval_select_recipes(x$terms, training, info)
values <- lapply(training[ ,col_names], unique)
check_new_values_new(
terms = x$terms,
role = x$role,
trained = TRUE,
columns = col_names,
skip = x$skip,
id = x$id,
values = values,
ignore_NA = x$ignore_NA
)
}
bake.check_new_values <- function(object,
new_data,
...) {
col_names <- names(object$values)
for (i in seq_along(col_names)) {
colname <- col_names[i]
new_values_func(new_data[[ colname ]],
object$values[[colname]],
colname,
ignore_NA = object$ignore_NA)
}
as_tibble(new_data)
}
print.check_new_values <-
function(x, width = max(20, options()$width - 30), ...) {
cat("Checking no new_values for ", sep = "")
printer(names(x$values), x$terms, x$trained, width = width)
invisible(x)
}
tidy.check_new_values <- function(x, ...) {
if (is_trained(x)) {
res <- tibble(terms = x$columns)
} else {
res <- tibble(terms = sel2char(x$terms))
}
res
}
|
