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
|
#' Fill in missing values with previous or next value
#'
#' Fills missing values in selected columns using the next or previous entry.
#' This is useful in the common output format where values are not repeated,
#' and are only recorded when they change.
#'
#' Missing values are replaced in atomic vectors; `NULL`s are replaced in lists.
#'
#' @section Grouped data frames:
#' With grouped data frames created by [dplyr::group_by()], `fill()` will be
#' applied _within_ each group, meaning that it won't fill across group
#' boundaries.
#'
#' @param data A data frame.
#' @param ... <[`tidy-select`][tidyr_tidy_select]> Columns to fill.
#' @param .direction Direction in which to fill missing values. Currently
#' either "down" (the default), "up", "downup" (i.e. first down and then up)
#' or "updown" (first up and then down).
#' @export
#' @examples
#' # direction = "down" --------------------------------------------------------
#' # Value (year) is recorded only when it changes
#' sales <- tibble::tribble(
#' ~quarter, ~year, ~sales,
#' "Q1", 2000, 66013,
#' "Q2", NA, 69182,
#' "Q3", NA, 53175,
#' "Q4", NA, 21001,
#' "Q1", 2001, 46036,
#' "Q2", NA, 58842,
#' "Q3", NA, 44568,
#' "Q4", NA, 50197,
#' "Q1", 2002, 39113,
#' "Q2", NA, 41668,
#' "Q3", NA, 30144,
#' "Q4", NA, 52897,
#' "Q1", 2004, 32129,
#' "Q2", NA, 67686,
#' "Q3", NA, 31768,
#' "Q4", NA, 49094
#' )
#' # `fill()` defaults to replacing missing data from top to bottom
#' sales %>% fill(year)
#'
#' # direction = "up" ----------------------------------------------------------
#' # Value (pet_type) is missing above
#' tidy_pets <- tibble::tribble(
#' ~rank, ~pet_type, ~breed,
#' 1L, NA, "Boston Terrier",
#' 2L, NA, "Retrievers (Labrador)",
#' 3L, NA, "Retrievers (Golden)",
#' 4L, NA, "French Bulldogs",
#' 5L, NA, "Bulldogs",
#' 6L, "Dog", "Beagles",
#' 1L, NA, "Persian",
#' 2L, NA, "Maine Coon",
#' 3L, NA, "Ragdoll",
#' 4L, NA, "Exotic",
#' 5L, NA, "Siamese",
#' 6L, "Cat", "American Short"
#' )
#'
#' # For values that are missing above you can use `.direction = "up"`
#' tidy_pets %>%
#' fill(pet_type, .direction = "up")
#'
#' # direction = "downup" ------------------------------------------------------
#' # Value (n_squirrels) is missing above and below within a group
#' squirrels <- tibble::tribble(
#' ~group, ~name, ~role, ~n_squirrels,
#' 1, "Sam", "Observer", NA,
#' 1, "Mara", "Scorekeeper", 8,
#' 1, "Jesse", "Observer", NA,
#' 1, "Tom", "Observer", NA,
#' 2, "Mike", "Observer", NA,
#' 2, "Rachael", "Observer", NA,
#' 2, "Sydekea", "Scorekeeper", 14,
#' 2, "Gabriela", "Observer", NA,
#' 3, "Derrick", "Observer", NA,
#' 3, "Kara", "Scorekeeper", 9,
#' 3, "Emily", "Observer", NA,
#' 3, "Danielle", "Observer", NA
#' )
#'
#' # The values are inconsistently missing by position within the group
#' # Use .direction = "downup" to fill missing values in both directions
#' squirrels %>%
#' dplyr::group_by(group) %>%
#' fill(n_squirrels, .direction = "downup") %>%
#' dplyr::ungroup()
#'
#' # Using `.direction = "updown"` accomplishes the same goal in this example
fill <- function(data, ..., .direction = c("down", "up", "downup", "updown")) {
check_dots_unnamed()
UseMethod("fill")
}
#' @export
fill.data.frame <- function(data, ..., .direction = c("down", "up", "downup", "updown")) {
vars <- tidyselect::eval_select(expr(c(...)), data, allow_rename = FALSE)
.direction <- arg_match0(
arg = .direction,
values = c("down", "up", "downup", "updown"),
)
fn <- function(col) {
vec_fill_missing(col, direction = .direction)
}
dplyr::mutate_at(data, .vars = dplyr::vars(any_of(vars)), .funs = fn)
}
|
