Merge rows in a dataframe where the rows are disjoint and contain NAs

Question

I have a dataframe that has two rows:

| code | name  | v1 | v2 | v3 | v4 |
|------|-------|----|----|----|----|
| 345  | Yemen | NA | 2  | 3  | NA |
| 346  |         


        

Answer 1

Adding dplyr & data.table solutions for completeness

Using dplyr::coalesce()

library(dplyr)

sum_NA <- function(x) {if (all(is.na(x))) x[NA_integer_] else sum(x, na.rm = TRUE)}

df %>% 
  group_by(name) %>% 
  summarise_all(sum_NA)
#> # A tibble: 1 x 6
#>   name   code    v1    v2    v3    v4
#>        
#> 1 Yemen   691     4     2     3     5

# Ref: https://stackoverflow.com/a/45515491
# Supply lists by splicing them into dots:
coalesce_by_column <- function(df) {
  return(dplyr::coalesce(!!! as.list(df)))
}

df %>% 
  group_by(name) %>% 
  summarise_all(coalesce_by_column)
#> # A tibble: 1 x 6
#>   name   code    v1    v2    v3    v4
#>        
#> 1 Yemen   345     4     2     3     5

Using data.table

# Ref: https://stackoverflow.com/q/28036294/
library(data.table)
setDT(df)[, lapply(.SD, na.omit), by = name]
#>     name code v1 v2 v3 v4
#> 1: Yemen  345  4  2  3  5
#> 2: Yemen  346  4  2  3  5

setDT(df)[, code := NULL][, lapply(.SD, na.omit), by = name]    
#>     name v1 v2 v3 v4
#> 1: Yemen  4  2  3  5

setDT(df)[, code := NULL][, lapply(.SD, sum_NA), by = name]
#>     name v1 v2 v3 v4
#> 1: Yemen  4  2  3  5