left join data.frame list

left_join_list.R

library(dplyr)
library(data.table)
n <- 100

df <- data.frame(id=LETTERS[1:10],meta=letters[1:10])
other_dfs <- lapply(1:n,\(x) data.frame(id=LETTERS[1:10],values=rnorm(1:10)))

f <- function(n){
  for(i in 1:n){
    df <- left_join(df,other_dfs[[i]],by="id")
  }
}

g <- function(){
  df <- Reduce(function(x, y) left_join(x, y, by = "id"), 
             other_dfs, 
             init = df)
}

dt <- data.table(id=LETTERS[1:10],meta=letters[1:10])
other_dts <- lapply(1:n,\(x) data.table(id=LETTERS[1:10],values=rnorm(1:10)))

for (i in seq_along(other_dts)) {
  setnames(other_dts[[i]], "values", paste0("values_", i))
}

h <- function(){
  dt <- Reduce(function(x, y) merge(x, y, by = "id", all.x = TRUE), c(list(dt), other_dts))
}

microbenchmark::microbenchmark(
  f(n),g(),h(),times = 10
)

Unit: milliseconds
 expr     min      lq    mean  median      uq     max neval
 f(n) 71.2929 71.9764 77.5014 76.5651 81.6266 87.9712    10
  g() 69.3343 73.1557 76.3624 74.2622 81.0695 87.9320    10
  h() 35.4880 36.0954 37.1046 36.6920 38.0468 40.1230    10