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 73 0 82 NA
#> 2 1 NA 1 74 188
#> 3 2 72 0 75 NA
#> 4 2 NA 1 92 198
#> 5 3 74 0 88 NA
#> 6 3 NA 1 75 185
#> 7 4 71 0 85 NA
#> 8 4 NA 1 88 189
#> 9 5 74 0 96 NA
#> 10 5 NA 1 89 173
#> 11 6 74 0 81 NA
#> 12 6 NA 1 97 195
#> 13 7 72 0 99 NA
#> 14 7 NA 1 97 190
#> 15 8 79 0 79 NA
#> 16 8 NA 1 81 190
#> 17 9 71 0 99 NA
#> 18 9 NA 1 72 183
#> 19 10 76 0 70 NA
#> 20 10 NA 1 73 192
#> 21 11 77 0 75 NA
#> 22 11 NA 1 84 185
#> 23 12 71 0 86 NA
#> 24 12 NA 1 83 195
#> 25 13 79 0 97 NA
#> 26 13 NA 1 95 174
#> 27 14 76 0 82 NA
#> 28 14 NA 1 82 200
#> 29 15 80 0 91 NA
#> 30 15 NA 1 72 193
#> 31 16 70 0 95 NA
#> 32 16 NA 1 83 190
#> 33 17 80 0 71 NA
#> 34 17 NA 1 84 172
#> 35 18 78 0 84 NA
#> 36 18 NA 1 98 195
#> 37 19 77 0 73 NA
#> 38 19 NA 1 71 192
#> 39 20 75 0 81 NA
#> 40 20 NA 1 75 173
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 76 0 75 NA NA
#> 2 1 NA 1 NA 100 182
#> 3 2 70 0 85 NA NA
#> 4 2 NA 1 NA 81 188
#> 5 3 75 0 73 NA NA
#> 6 3 NA 1 NA 77 171
#> 7 4 72 0 94 NA NA
#> 8 4 NA 1 NA 92 177
#> 9 5 77 0 75 NA NA
#> 10 5 NA 1 NA 75 175
#> 11 6 73 0 89 NA NA
#> 12 6 NA 1 NA 94 184
#> 13 7 73 0 77 NA NA
#> 14 7 NA 1 NA 80 192
#> 15 8 79 0 91 NA NA
#> 16 8 NA 1 NA 88 191
#> 17 9 73 0 70 NA NA
#> 18 9 NA 1 NA 95 178
#> 19 10 74 0 77 NA NA
#> 20 10 NA 1 NA 74 198
#> 21 11 70 0 80 NA NA
#> 22 11 NA 1 NA 94 197
#> 23 12 74 0 80 NA NA
#> 24 12 NA 1 NA 71 197
#> 25 13 75 0 91 NA NA
#> 26 13 NA 1 NA 76 199
#> 27 14 74 0 90 NA NA
#> 28 14 NA 1 NA 95 170
#> 29 15 78 0 90 NA NA
#> 30 15 NA 1 NA 79 171
#> 31 16 80 0 86 NA NA
#> 32 16 NA 1 NA 77 178
#> 33 17 80 0 78 NA NA
#> 34 17 NA 1 NA 96 186
#> 35 18 79 0 91 NA NA
#> 36 18 NA 1 NA 91 174
#> 37 19 73 0 87 NA NA
#> 38 19 NA 1 NA 72 196
#> 39 20 80 0 88 NA NA
#> 40 20 NA 1 NA 80 179
# 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