check if column values have 90 percent overlap in vlaues in r

main.r
library(dplyr)

# create sample data frame with three columns
df <- data.frame(col1 = c(1, 2, 3, 4, 5),
                 col2 = c(1, 2, 3, 4, 5),
                 col3 = c(1, 2, 3, 4, 6))

# calculate the percentage overlap in values for each pair of columns
overlap_percentages <- df %>%
  summarise(across(everything(), ~ sum(.x == col1 | .x == col2 | .x == col3) / n() * 100))

# check if any pair of columns has less than 90% overlap
if(any(overlap_percentages < 90)) {
  print("Columns do not have 90% overlap in values")
} else {
  print("Columns have 90% overlap in values")
}
584 chars
18 lines