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.
Usage
fill(data, ..., .direction = c("down", "up", "downup", "updown"))Arguments
- data
A
data.frame.- ...
Columns to fill.
- .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).
Examples
# Value (year) is recorded only when it changes
sales <- data.frame(
quarter = c(
"Q1", "Q2", "Q3", "Q4", "Q1", "Q2", "Q3", "Q4", "Q1", "Q2",
"Q3", "Q4", "Q1", "Q2", "Q3", "Q4"
),
year = c(2000, NA, NA, NA, 2001, NA, NA, NA, 2002, NA, NA, NA, 2004, NA, NA, NA),
sales = c(
66013, 69182, 53175, 21001, 46036, 58842, 44568, 50197, 39113, 41668, 30144,
52897, 32129, 67686, 31768, 49094
)
)
# `fill()` defaults to replacing missing data from top to bottom
sales %>% fill(year)
#> quarter year sales
#> 1 Q1 2000 66013
#> 2 Q2 2000 69182
#> 3 Q3 2000 53175
#> 4 Q4 2000 21001
#> 5 Q1 2001 46036
#> 6 Q2 2001 58842
#> 7 Q3 2001 44568
#> 8 Q4 2001 50197
#> 9 Q1 2002 39113
#> 10 Q2 2002 41668
#> 11 Q3 2002 30144
#> 12 Q4 2002 52897
#> 13 Q1 2004 32129
#> 14 Q2 2004 67686
#> 15 Q3 2004 31768
#> 16 Q4 2004 49094
# Value (pet_type) is missing above
tidy_pets <- data.frame(
rank = c(1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L),
pet_type = c(NA, NA, NA, NA, NA, "Dog", NA, NA, NA, NA, NA, "Cat"),
breed = c(
"Boston Terrier", "Retrievers (Labrador)", "Retrievers (Golden)",
"French Bulldogs", "Bulldogs", "Beagles", "Persian", "Maine Coon",
"Ragdoll", "Exotic", "Siamese", "American Short"
)
)
# For values that are missing above you can use `.direction = "up"`
tidy_pets %>%
fill(pet_type, .direction = "up")
#> rank pet_type breed
#> 1 1 Dog Boston Terrier
#> 2 2 Dog Retrievers (Labrador)
#> 3 3 Dog Retrievers (Golden)
#> 4 4 Dog French Bulldogs
#> 5 5 Dog Bulldogs
#> 6 6 Dog Beagles
#> 7 1 Cat Persian
#> 8 2 Cat Maine Coon
#> 9 3 Cat Ragdoll
#> 10 4 Cat Exotic
#> 11 5 Cat Siamese
#> 12 6 Cat American Short
# Value (n_squirrels) is missing above and below within a group
squirrels <- data.frame(
group = c(1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3),
name = c(
"Sam", "Mara", "Jesse", "Tom", "Mike", "Rachael", "Sydekea",
"Gabriela", "Derrick", "Kara", "Emily", "Danielle"
),
role = c(
"Observer", "Scorekeeper", "Observer", "Observer", "Observer",
"Observer", "Scorekeeper", "Observer", "Observer", "Scorekeeper",
"Observer", "Observer"
),
n_squirrels = c(NA, 8, NA, NA, NA, NA, 14, NA, NA, 9, NA, NA)
)
# The values are inconsistently missing by position within the group
# Use .direction = "downup" to fill missing values in both directions
squirrels %>%
group_by(group) %>%
fill(n_squirrels, .direction = "downup") %>%
ungroup()
#> Adding missing grouping variables: `group`
#> Adding missing grouping variables: `group`
#> Adding missing grouping variables: `group`
#> group name role n_squirrels
#> 1 1 Sam Observer 8
#> 2 1 Mara Scorekeeper 8
#> 3 1 Jesse Observer 8
#> 4 1 Tom Observer 8
#> 5 2 Mike Observer 14
#> 6 2 Rachael Observer 14
#> 7 2 Sydekea Scorekeeper 14
#> 8 2 Gabriela Observer 14
#> 9 3 Derrick Observer 9
#> 10 3 Kara Scorekeeper 9
#> 11 3 Emily Observer 9
#> 12 3 Danielle Observer 9
# Using `.direction = "updown"` accomplishes the same goal in this example