across_and_tidyselect

across_and_tidyselect.R

library(tidyverse)

# GOAL: Center and standardize every numeric column but `year` (by species and island)

palmerpenguins::penguins
# # A tibble: 344 x 8
#    species island    bill_length_mm bill_depth_mm flipper_length_mm body_mass_g sex     year
#    <fct>   <fct>              <dbl>         <dbl>             <int>       <int> <fct>  <int>
#  1 Adelie  Torgersen           39.1          18.7               181        3750 male    2007
#  2 Adelie  Torgersen           39.5          17.4               186        3800 female  2007
# # ... with 342 more rows

# Helper function
center_and_standardize <- function(x) (x - mean(x, na.rm = T)) / sd(x, na.rm = T)

# THIS IS TEDIOUS
palmerpenguins::penguins |> 
  group_by(species, island) |> 
  mutate(
    bill_length_mm = center_and_standardize(bill_length_mm),
    bill_depth_mm = center_and_standardize(bill_depth_mm),
    flipper_length_mm = center_and_standardize(flipper_length_mm),
    body_mass_g = center_and_standardize(body_mass_g)
  )
# # A tibble: 344 x 8
# # Groups:   species, island [5]
#    species island    bill_length_mm bill_depth_mm flipper_length_mm body_mass_g sex     year
#    <fct>   <fct>              <dbl>         <dbl>             <dbl>       <dbl> <fct>  <int>
#  1 Adelie  Torgersen         0.0493         0.202            -1.64       0.0980 male    2007
#  2 Adelie  Torgersen         0.181         -0.769            -0.834      0.210  female  2007
# # ... with 342 more rows

# Same result, less typing
palmerpenguins::penguins |> 
  group_by(species, island) |> 
  mutate(
    across(
      .cols = c(bill_length_mm, bill_depth_mm, flipper_length_mm, body_mass_g),
      .fns = center_and_standardize
    )
  )


# Same result, even less typing (Alternative I)
palmerpenguins::penguins |> 
  group_by(species, island) |> 
  mutate(
    across(
      .cols = ends_with(c('_mm', '_g')),
      .fns = center_and_standardize
    )
  )

# Same result, even less typing (Alternative II)
palmerpenguins::penguins |> 
  group_by(species, island) |> 
  mutate(
    across(
      .cols = matches(c('bill', 'flipper', 'body')),
      .fns = center_and_standardize
    )
  )

# Same result, even less typing (Alternative III)
palmerpenguins::penguins |> 
  group_by(species, island) |> 
  mutate(
    across(
      .cols = c(where(is.numeric), -year),
      .fns = center_and_standardize
    )
  )
  
  
  
  # GOAL: Transform every character column to factor
  mpg
# A tibble: 234 x 11
#    manufacturer model      displ  year   cyl trans      drv     cty   hwy fl    class  
#    <chr>        <chr>      <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr>  
#  1 audi         a4           1.8  1999     4 auto(l5)   f        18    29 p     compact
#  2 audi         a4           1.8  1999     4 manual(m5) f        21    29 p     compact
#  3 audi         a4           2    2008     4 manual(m6) f        20    31 p     compact
#  4 audi         a4           2    2008     4 auto(av)   f        21    30 p     compact
#  5 audi         a4           2.8  1999     6 auto(l5)   f        16    26 p     compact
#  6 audi         a4           2.8  1999     6 manual(m5) f        18    26 p     compact
#  7 audi         a4           3.1  2008     6 auto(av)   f        18    27 p     compact
#  8 audi         a4 quattro   1.8  1999     4 manual(m5) 4        18    26 p     compact
#  9 audi         a4 quattro   1.8  1999     4 auto(l5)   4        16    25 p     compact
# 10 audi         a4 quattro   2    2008     4 manual(m6) 4        20    28 p     compact
# # ... with 224 more rows

# Doing it the tedious repetitive way
mpg |> 
  mutate(
    manufacturer = factor(manufacturer),
    model = factor(model),
    trans = factor(trans),
    drv = factor(drv),
    fl = factor(drv),
    class = factor(drv)
  )
# # A tibble: 234 x 11
#    manufacturer model      displ  year   cyl trans      drv     cty   hwy fl    class
#    <fct>        <chr>      <dbl> <int> <int> <fct>      <fct> <int> <int> <fct> <fct>
#  1 audi         a4           1.8  1999     4 auto(l5)   f        18    29 f     f    
#  2 audi         a4           1.8  1999     4 manual(m5) f        21    29 f     f    
#  3 audi         a4           2    2008     4 manual(m6) f        20    31 f     f    
#  4 audi         a4           2    2008     4 auto(av)   f        21    30 f     f    
#  5 audi         a4           2.8  1999     6 auto(l5)   f        16    26 f     f    
#  6 audi         a4           2.8  1999     6 manual(m5) f        18    26 f     f    
#  7 audi         a4           3.1  2008     6 auto(av)   f        18    27 f     f    
#  8 audi         a4 quattro   1.8  1999     4 manual(m5) 4        18    26 4     4    
#  9 audi         a4 quattro   1.8  1999     4 auto(l5)   4        16    25 4     4    
# 10 audi         a4 quattro   2    2008     4 manual(m6) 4        20    28 4     4    
# # ... with 224 more rows

# Same result, less typing
mpg |> 
  mutate(
    across(
      .cols = c(manufacturer, model, trans, drv, fl, class),
      .fns = factor
    )
  )

# Same result, even less typing
mpg |> 
  mutate(
    across(
      .cols = where(is.character),
      .fns = factor
    )
  )