[Reduce number of categories] Reduce the number of categories by lumping some of them together into an "Other" category #R

lump.R

# Refs: https://forcats.tidyverse.org/reference/fct_lump.html

# A  test data frame
set.seed(2)
df <- tibble(cat = factor(sample(c("a", "b", "c", "d"), 10, replace = TRUE)), 
       val = sample(1:10))
df %>% head()
# A tibble: 6 x 2
#   cat     val
#   <fct> <int>
# 1 a         9
# 2 c         2
# 3 b         3
# 4 b         1
# 5 d         8
# 6 d        10

# Lumping by number of values -----

# Count the number of values by categories
df %>% 
    count(cat)
# A tibble: 4 x 2
#   cat       n
#   <fct> <int>
# 1 a         4
# 2 b         2
# 3 c         1
# 4 d         3

# Keep only the 2 most frequent categories, lumping together the remaining
# categories in the "Other" category
df %>%
    group_by(cat = forcats::fct_lump_n(cat, 2)) %>% 
    count(cat)
# A tibble: 3 x 2
# Groups:   cat [3]
#   cat       n
#   <fct> <int>
# 1 a         4
# 2 d         3
# 3 Other     3