Benchmarking fastDummies::dummy_cols() against modeldb::add_dummy_variables()

benchmarking_dummy_functions

# Compare the performance of two purportedly-fast ways of generating dummy variables from character vector.
# NOTE: fastDummies retains the original variable by default while modeldb does not

# Dependencies
library(microbenchmark)
library(fastDummies)
library(modeldb)
library(dplyr)

# Simulate data: 1 million rows, 1 variable with 26 unique values
set.seed(123)
df <- data.frame(x = sample(LETTERS, size = 1000000, replace = TRUE))

# Benchmarks
t <- 1000

result_modeldb <- microbenchmark(
        z <- df %>% modeldb::add_dummy_variables(x = x, auto_values = T),
        times = t)

result_fastdums <- microbenchmark::microbenchmark(
         z <- df %>% fastDummies::dummy_cols(remove_first_dummy = TRUE),
         times = t)

# Compare
result_modeldb %>% bind_rows(result_fastdums)