Apply the same function with multiple columns as inputs to multiple columns in R with tidyverse

user_7096959 0
Viewed 239

As an example, I have the following data frame:

df <- data.frame(a1=1,a2=2,a3=3,b1=1,b2=2,b3=3)

I have a function:

fn <- function(x,y,z) x^y+(z-x)^(y-x)

I want the following:

df <- df %>% mutate(a=fn(a1,a2,a3),b=fn(b1,b2,b3))

The problem is, I have tons of triplets in my dataset, so it is not ideal to write them out one by one.

dplyr tidyverse r
3 Answers

Here are base R options using:

  • split.default + lapply + do.call
cbind(
  df,
  lapply(
    split.default(df, gsub("\\d+", "", names(df))),
    function(x) do.call(fn, unname(x))
  )
)
  • reshape + lapply + do.call
cbind(
  df,
  lapply(
    subset(
      reshape(
        setNames(df, gsub("(\\d+)$", "\\.\\1", names(df))),
        direction = "long",
        varying = 1:length(df)
      ),
      select = -c(time, id)
    ),
    function(x) do.call(fn, as.list(x))
  )
)

Output

  a1 a2 a3 b1 b2 b3 a b
1  1  2  3  1  2  3 3 3
user_121587570

I would convert df to long format then use lag to create 3 columns then apply fn() on them

library(tidyverse)

df_long <- df %>% 
  pivot_longer(everything(),
               names_to = c(".value", "set"),
               names_pattern = "(.)(.)")

df_longer <- df_long %>% 
  pivot_longer(-c(set),
               names_to = "key",
               values_to = "val") %>% 
  arrange(key)
df_longer
#> # A tibble: 6 x 3
#>   set   key     val
#>   <chr> <chr> <dbl>
#> 1 1     a         1
#> 2 2     a         2
#> 3 3     a         3
#> 4 1     b         1
#> 5 2     b         2
#> 6 3     b         3

lag then apply fn(), keep only non-NA val_fn

df_longer <- df_longer %>% 
  group_by(key) %>% 
  mutate(val_lag1 = lag(val, n = 1),
         val_lag2 = lag(val, n = 2)) %>% 
  mutate(val_fn = fn(val_lag2, val_lag1, val)) %>% 
  filter(!is.na(val_fn))
df_longer
#> # A tibble: 2 x 6
#> # Groups:   key [2]
#>   set   key     val val_lag1 val_lag2 val_fn
#>   <chr> <chr> <dbl>    <dbl>    <dbl>  <dbl>
#> 1 3     a         3        2        1      3
#> 2 3     b         3        2        1      3

Created on 2020-12-03 by the reprex package (v0.3.0)

user_7865420

I think it would be easier/shorter to combine columns into their separate group and apply the function to each column.

library(dplyr)
library(tidyr)

df %>%
  pivot_longer(cols = everything(), 
               names_to = '.value', 
               names_pattern = '([a-z]+)') %>%
  summarise(across(.fns = ~do.call(fn, as.list(.)))) -> result
result

#     a     b
#  <dbl> <dbl>
#1     3     3

You can bind the result to your original dataset if needed.

bind_cols(df, result)
#  a1 a2 a3 b1 b2 b3 a b
#1  1  2  3  1  2  3 3 3
user_39629140
Related