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
|
#' Impute Nominal Data Using the Most Common Value
#'
#' `step_modeimpute` creates a *specification* of a
#' recipe step that will substitute missing values of nominal
#' variables by the training set mode of those variables.
#'
#' @inheritParams step_center
#' @param ... One or more selector functions to choose which
#' variables are affected by the step. See [selections()]
#' for more details. For the `tidy` method, these are not
#' currently used.
#' @param role Not used by this step since no new variables are
#' created.
#' @param modes A named character vector of modes. This is
#' `NULL` until computed by [prep.recipe()].
#' @return An updated version of `recipe` with the new step
#' added to the sequence of existing steps (if any). For the
#' `tidy` method, a tibble with columns `terms` (the
#' selectors or variables selected) and `model` (the mode
#' value).
#' @keywords datagen
#' @concept preprocessing
#' @concept imputation
#' @export
#' @details `step_modeimpute` estimates the variable modes
#' from the data used in the `training` argument of
#' `prep.recipe`. `bake.recipe` then applies the new
#' values to new data sets using these values. If the training set
#' data has more than one mode, one is selected at random.
#' @examples
#' library(modeldata)
#' data("credit_data")
#'
#' ## missing data per column
#' vapply(credit_data, function(x) mean(is.na(x)), c(num = 0))
#'
#' set.seed(342)
#' in_training <- sample(1:nrow(credit_data), 2000)
#'
#' credit_tr <- credit_data[ in_training, ]
#' credit_te <- credit_data[-in_training, ]
#' missing_examples <- c(14, 394, 565)
#'
#' rec <- recipe(Price ~ ., data = credit_tr)
#'
#' impute_rec <- rec %>%
#' step_modeimpute(Status, Home, Marital)
#'
#' imp_models <- prep(impute_rec, training = credit_tr)
#'
#' imputed_te <- bake(imp_models, new_data = credit_te, everything())
#'
#' table(credit_te$Home, imputed_te$Home, useNA = "always")
#'
#' tidy(impute_rec, number = 1)
#' tidy(imp_models, number = 1)
step_modeimpute <-
function(recipe,
...,
role = NA,
trained = FALSE,
modes = NULL,
skip = FALSE,
id = rand_id("modeimpute")) {
add_step(
recipe,
step_modeimpute_new(
terms = ellipse_check(...),
role = role,
trained = trained,
modes = modes,
skip = skip,
id = id
)
)
}
step_modeimpute_new <-
function(terms, role, trained, modes, skip, id) {
step(
subclass = "modeimpute",
terms = terms,
role = role,
trained = trained,
modes = modes,
skip = skip,
id = id
)
}
#' @export
prep.step_modeimpute <- function(x, training, info = NULL, ...) {
col_names <- eval_select_recipes(x$terms, training, info)
modes <- vapply(training[, col_names], mode_est, c(mode = ""))
step_modeimpute_new(
terms = x$terms,
role = x$role,
trained = TRUE,
modes = modes,
skip = x$skip,
id = x$id
)
}
#' @export
bake.step_modeimpute <- function(object, new_data, ...) {
for (i in names(object$modes)) {
if (any(is.na(new_data[, i]))) {
mode_val <- cast(object$modes[[i]], new_data[[i]])
new_data[is.na(new_data[[i]]), i] <- mode_val
}
}
as_tibble(new_data)
}
print.step_modeimpute <-
function(x, width = max(20, options()$width - 30), ...) {
cat("Mode Imputation for ", sep = "")
printer(names(x$modes), x$terms, x$trained, width = width)
invisible(x)
}
mode_est <- function(x) {
if (!is.character(x) & !is.factor(x))
rlang::abort("The data should be character or factor to compute the mode.")
tab <- table(x)
modes <- names(tab)[tab == max(tab)]
sample(modes, size = 1)
}
#' @rdname step_modeimpute
#' @param x A `step_modeimpute` object.
#' @export
tidy.step_modeimpute <- function(x, ...) {
if (is_trained(x)) {
res <- tibble(terms = names(x$modes),
model = x$modes)
} else {
term_names <- sel2char(x$terms)
res <- tibble(terms = term_names, model = na_chr)
}
res$id <- x$id
res
}
|
