Mfcttrf

I am somewhat stuck. Is there a better way than the below to do value matching considering NAs as "real values" within mutate?

library(dplyr)

data_foo <- data.frame(A= c(1:2, NA, 4, NA), B = c(1, 3, NA, NA, 4))

Not the desired output:

data_foo %>% mutate(irr = A==B)

#> A B irr
#> 1 1 1 TRUE
#> 2 2 3 FALSE
#> 3 NA NA NA
#> 4 4 NA NA
#> 5 NA 4 NA

data_foo %>% rowwise() %>% mutate(irr = A%in%B)

#> Source: local data frame [5 x 3]
#> Groups: <by row>
#> 
#> # A tibble: 5 x 3
#> A B irr 
#> <dbl> <dbl> <lgl>
#> 1 1 1 TRUE 
#> 2 2 3 FALSE
#> 3 NA NA FALSE
#> 4 4 NA FALSE
#> 5 NA 4 FALSE

Desired output: The below shows the desired column, irr. I am using this somewhat cumbersome helper columns. Is there a shorter way?

data_foo %>% 
 mutate(NA_A = is.na(A), 
 NA_B = is.na(B), 
 irr = if_else(is.na(A)|is.na(B), NA_A == NA_B, A == B))

#> A B NA_A NA_B irr
#> 1 1 1 FALSE FALSE TRUE
#> 2 2 3 FALSE FALSE FALSE
#> 3 NA NA TRUE TRUE TRUE
#> 4 4 NA FALSE TRUE FALSE
#> 5 NA 4 TRUE FALSE FALSE

Maybe simpler than akrun's answer?

Any of the two ways below will produce the expected result. Note that as.character won't do it, because the return value of as.character(NA) is NA_character_.

data_foo %>%
 rowwise() %>%
 mutate(irr = paste(A) == paste(B))

data_foo %>%
 rowwise() %>%
 mutate(irr = sQuote(A) == sQuote(B))

#Source: local data frame [5 x 3]
#Groups: <by row>
#
## A tibble: 5 x 3
# A B irr 
# <dbl> <dbl> <lgl>
#1 1 1 TRUE 
#2 2 3 FALSE
#3 NA NA TRUE 
#4 4 NA FALSE
#5 NA 4 FALSE

Using map2

library(tidyverse)
data_foo %>%
 mutate(irr = map2_lgl(A, B, `%in%`))
# A B irr
#1 1 1 TRUE
#2 2 3 FALSE
#3 NA NA TRUE
#4 4 NA FALSE
#5 NA 4 FALSE

Or with setequal

data_foo %>% 
 rowwise %>%
 mutate(irr = setequal(A, B))

The above method is concise, but it is also loopy. We can replace the NA with a different value and then do the ==

data_foo %>%
 mutate_all(list(new = ~ replace_na(., -999))) %>%
 transmute(A, B, irr = A_new == B_new)
# A B irr
#1 1 1 TRUE
#2 2 3 FALSE
#3 NA NA TRUE
#4 4 NA FALSE
#5 NA 4 FALSE

Or with bind_cols and reduce

data_foo %>%
 mutate_all(replace_na, -999) %>% 
 reduce(`==`) %>% 
 bind_cols(data_foo, irr = .)

Could also be a possibility:

data_foo %>%
 rowwise() %>%
 mutate(irr = identical(A, B)) %>%
 ungroup()

 A B irr 
 <dbl> <dbl> <lgl>
1 1 1 TRUE 
2 2 3 FALSE
3 NA NA TRUE 
4 4 NA FALSE
5 NA 4 FALSE

The coalesce function is useful if you want to perform an action when a value is NA

data_foo %>% 
 mutate(irr = coalesce(A == B, is.na(A) & is.na(B)))

# A B irr
# 1 1 1 TRUE
# 2 2 3 FALSE
# 3 NA NA TRUE
# 4 4 NA FALSE
# 5 NA 4 FALSE

Same thing for > 2 columns

data_foo %>% 
 mutate(irr = coalesce(reduce(., `==`), rowMeans(is.na(.)) == 1))