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
|
#' Filter rows using dplyr
#'
#' `step_filter` creates a *specification* of a recipe step
#' that will remove rows using [dplyr::filter()].
#'
#' @template row-ops
#' @inheritParams step_center
#' @param ... Logical predicates defined in terms of the variables
#' in the data. Multiple conditions are combined with `&`. Only
#' rows where the condition evaluates to `TRUE` are kept. See
#' [dplyr::filter()] 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 inputs Quosure of values given by `...`.
#' @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`.
#' @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` which
#' contains the conditional statements. These
#' expressions are text representations and are not parsable.
#' @details When an object in the user's global environment is
#' referenced in the expression defining the new variable(s),
#' it is a good idea to use quasiquotation (e.g. `!!`) to embed
#' the value of the object in the expression (to be portable
#' between sessions). See the examples.
#' @keywords datagen
#' @concept preprocessing
#' @concept row_filters
#' @export
#' @examples
#' rec <- recipe( ~ ., data = iris) %>%
#' step_filter(Sepal.Length > 4.5, Species == "setosa")
#'
#' prepped <- prep(rec, training = iris %>% slice(1:75))
#'
#' library(dplyr)
#'
#' dplyr_train <-
#' iris %>%
#' as_tibble() %>%
#' slice(1:75) %>%
#' dplyr::filter(Sepal.Length > 4.5, Species == "setosa")
#'
#' rec_train <- bake(prepped, new_data = NULL)
#' all.equal(dplyr_train, rec_train)
#'
#' dplyr_test <-
#' iris %>%
#' as_tibble() %>%
#' slice(76:150) %>%
#' dplyr::filter(Sepal.Length > 4.5, Species != "setosa")
#' rec_test <- bake(prepped, iris %>% slice(76:150))
#' all.equal(dplyr_test, rec_test)
#'
#' values <- c("versicolor", "virginica")
#'
#' qq_rec <-
#' recipe( ~ ., data = iris) %>%
#' # Embed the `values` object in the call using !!
#' step_filter(Sepal.Length > 4.5, Species %in% !!values)
#'
#' tidy(qq_rec, number = 1)
#' @seealso [step_naomit()] [step_sample()] [step_slice()]
step_filter <- function(
recipe, ...,
role = NA,
trained = FALSE,
inputs = NULL,
skip = TRUE,
id = rand_id("filter")
) {
inputs <- enquos(...)
add_step(
recipe,
step_filter_new(
terms = terms,
trained = trained,
role = role,
inputs = inputs,
skip = skip,
id = id
)
)
}
step_filter_new <-
function(terms, role, trained, inputs, skip, id) {
step(
subclass = "filter",
terms = terms,
role = role,
trained = trained,
inputs = inputs,
skip = skip,
id = id
)
}
#' @export
prep.step_filter <- function(x, training, info = NULL, ...) {
step_filter_new(
terms = x$terms,
trained = TRUE,
role = x$role,
inputs = x$inputs,
skip = x$skip,
id = x$id
)
}
#' @export
bake.step_filter <- function(object, new_data, ...) {
dplyr::filter(new_data, !!!object$inputs)
}
print.step_filter <-
function(x, width = max(20, options()$width - 35), ...) {
cat("Row filtering")
if (x$trained) {
cat(" [trained]\n")
} else {
cat("\n")
}
invisible(x)
}
#' @rdname step_filter
#' @param x A `step_filter` object
#' @export
tidy.step_filter <- function(x, ...) {
cond_expr <- map(x$inputs, quo_get_expr)
cond_expr <- map_chr(cond_expr, quo_text, width = options()$width, nlines = 1)
tibble(
terms = cond_expr,
id = rep(x$id, length(x$inputs))
)
}
|
