R dplyr join by range or virtual column

Question

I want to join two tibbles by a range or a virtual column. but it seems the by - parameter just allow to handle chr oder vector(chr) o

Answer 1

We can use mutate and case_when from dplyr.

library(dplyr)

d2 <- d %>%
  mutate(class = case_when(
    value >= 1 & value < 2 ~ "A",
    value >= 2 & value < 3 ~ "B",
    value >= 3 & value < 4 ~ "C",
    value >= 4 & value < 5 ~ "D",
    value >= 5 & value < 6 ~ "E",
    value >= 6             ~ "F"
  ))
d2
# A tibble: 26 x 2
   value class
    
 1   1.0     A
 2   1.2     A
 3   1.4     A
 4   1.6     A
 5   1.8     A
 6   2.0     B
 7   2.2     B
 8   2.4     B
 9   2.6     B
10   2.8     B
# ... with 16 more rows

Update

Here is a workaround by defining a function for this task.

d <- tibble(value = seq(1,6, by = 0.2))
r <- tibble(from = seq(1,6), to = c(seq(2,6),Inf), class = LETTERS[seq(1,6)])

library(dplyr)

# Define a function for dynamic join
dynamic_join <- function(d, r){

  if (!("class" %in% colnames(d))){
    d[["class"]] <- NA_character_
  }

  d <- d %>%
    mutate(class = ifelse(value >= r$from & value < r$to, r$class, class))
  return(d)
}

re_dynamic_join <- function(d, r){
  r_list <- split(r, r$class)
  for (i in 1:length(r_list)){
    d <- dynamic_join(d, r_list[[i]])
  }
  return(d)
}

# Apply the function
d2 <- d %>% re_dynamic_join(r)
d2
# A tibble: 26 x 2
   value class
    
 1   1.0     A
 2   1.2     A
 3   1.4     A
 4   1.6     A
 5   1.8     A
 6   2.0     B
 7   2.2     B
 8   2.4     B
 9   2.6     B
10   2.8     B
# ... with 16 more rows