Alternative pivoting method for easily pivoting based on name pattern
Source:R/wide2long.R
wide2long.RdThis function requires and assumes a systematic naming of variables. For now only supports one level pivoting. Adding more levels would require an added "ignore" string pattern or similarly. Example 2.
Usage
wide2long(
data,
pattern,
type = c("prefix", "infix", "suffix"),
id.col = 1,
instance.name = "instance"
)Examples
data.frame(
1:20, sample(70:80, 20, TRUE),
sample(70:100, 20, TRUE),
sample(70:100, 20, TRUE),
sample(170:200, 20, TRUE)
) |>
setNames(c("id", "age", "weight_0", "weight_1", "height_1")) |>
wide2long(pattern = c("_0", "_1"), type = "suffix")
#> id age instance weight height
#> 1 1 76 0 93 NA
#> 2 1 NA 1 72 176
#> 3 2 71 0 91 NA
#> 4 2 NA 1 79 188
#> 5 3 72 0 70 NA
#> 6 3 NA 1 70 174
#> 7 4 77 0 98 NA
#> 8 4 NA 1 99 186
#> 9 5 71 0 79 NA
#> 10 5 NA 1 74 178
#> 11 6 76 0 82 NA
#> 12 6 NA 1 74 191
#> 13 7 74 0 88 NA
#> 14 7 NA 1 73 181
#> 15 8 76 0 77 NA
#> 16 8 NA 1 80 191
#> 17 9 79 0 81 NA
#> 18 9 NA 1 78 194
#> 19 10 79 0 80 NA
#> 20 10 NA 1 71 182
#> 21 11 74 0 85 NA
#> 22 11 NA 1 97 181
#> 23 12 75 0 80 NA
#> 24 12 NA 1 79 172
#> 25 13 70 0 90 NA
#> 26 13 NA 1 71 177
#> 27 14 70 0 75 NA
#> 28 14 NA 1 71 171
#> 29 15 75 0 93 NA
#> 30 15 NA 1 97 199
#> 31 16 75 0 95 NA
#> 32 16 NA 1 81 192
#> 33 17 79 0 97 NA
#> 34 17 NA 1 75 195
#> 35 18 75 0 77 NA
#> 36 18 NA 1 83 191
#> 37 19 78 0 90 NA
#> 38 19 NA 1 95 178
#> 39 20 70 0 76 NA
#> 40 20 NA 1 78 200
data.frame(
1:20, sample(70:80, 20, TRUE),
sample(70:100, 20, TRUE),
sample(70:100, 20, TRUE),
sample(170:200, 20, TRUE)
) |>
setNames(c("id", "age", "weight_0", "weight_a_1", "height_b_1")) |>
wide2long(pattern = c("_0", "_1"), type = "suffix")
#> id age instance weight weight_a height_b
#> 1 1 79 0 96 NA NA
#> 2 1 NA 1 NA 88 178
#> 3 2 76 0 90 NA NA
#> 4 2 NA 1 NA 93 188
#> 5 3 74 0 99 NA NA
#> 6 3 NA 1 NA 72 181
#> 7 4 76 0 85 NA NA
#> 8 4 NA 1 NA 76 179
#> 9 5 76 0 76 NA NA
#> 10 5 NA 1 NA 99 193
#> 11 6 76 0 94 NA NA
#> 12 6 NA 1 NA 91 181
#> 13 7 79 0 79 NA NA
#> 14 7 NA 1 NA 99 197
#> 15 8 71 0 88 NA NA
#> 16 8 NA 1 NA 92 194
#> 17 9 73 0 95 NA NA
#> 18 9 NA 1 NA 93 192
#> 19 10 73 0 72 NA NA
#> 20 10 NA 1 NA 81 175
#> 21 11 78 0 94 NA NA
#> 22 11 NA 1 NA 97 177
#> 23 12 72 0 82 NA NA
#> 24 12 NA 1 NA 77 192
#> 25 13 80 0 85 NA NA
#> 26 13 NA 1 NA 92 182
#> 27 14 78 0 88 NA NA
#> 28 14 NA 1 NA 82 199
#> 29 15 73 0 83 NA NA
#> 30 15 NA 1 NA 89 196
#> 31 16 77 0 88 NA NA
#> 32 16 NA 1 NA 90 180
#> 33 17 78 0 79 NA NA
#> 34 17 NA 1 NA 87 182
#> 35 18 72 0 71 NA NA
#> 36 18 NA 1 NA 79 171
#> 37 19 75 0 85 NA NA
#> 38 19 NA 1 NA 96 177
#> 39 20 74 0 80 NA NA
#> 40 20 NA 1 NA 71 181
# Optional filling of missing values by last observation carried forward
# Needed for mmrm analyses
long_missings |>
# Fills record ID assuming none are missing
tidyr::fill(record_id) |>
# Grouping by ID for the last step
dplyr::group_by(record_id) |>
# Filling missing data by ID
tidyr::fill(names(long_missings)[!names(long_missings) %in% new_names]) |>
# Remove grouping
dplyr::ungroup()
#> Error: object 'long_missings' not found