split benchmarks

gistfile1.txt

> test_df6  <- create_test_df(cols=4, rows=40, levels_per_var= 6)  # See appendix for 'create_test_df'
> g_test_df6  <- group_by(test_df6, a, b, c)
> 
> base_split <- function(df)split(test_df6 , test_df6[, c('a', 'b', 'c')])
> 
> microbenchmark::microbenchmark(
+   base_split(test_df6),
+   split(g_test_df6)
+ )
#Unit: milliseconds
#                 expr       min       lq      mean    median       uq       max neval
# base_split(test_df6) 17.671272 18.45257 20.843889 20.399100 22.14294 28.824846   100
#    split(g_test_df6)  1.466561  1.59341  1.910306  1.668386  1.87340  5.554186   100
> 
> microbenchmark::microbenchmark(
+   base_split(test_df6),
+   split(group_by(test_df6, a, b, c))
+ )
#Unit: milliseconds
#                               expr       min        lq     mean    median        uq       max neval
#               base_split(test_df6) 17.723653 18.409159 20.52208 19.996392 22.072682 35.195378   100
# split(group_by(test_df6, a, b, c))  2.212929  2.353382  2.60777  2.456671  2.615488  6.183901   100

## One Grouping Variable

> test_df6  <- create_test_df(cols=4, rows=40, levels_per_var= 6)  # See appendix for 'create_test_df'
> g_test_df6  <- group_by(test_df6, a)
> base_split <- function(df)split(test_df6 , test_df6[, c('a')])
> microbenchmark::microbenchmark(
+   base_split(test_df6),
+   split(g_test_df6)
+ )
#Unit: microseconds
#                 expr      min        lq      mean   median        uq      max neval
# base_split(test_df6) 1110.054 1175.8550 1386.9527 1242.724 1366.0990 3681.738   100
#    split(g_test_df6)  336.510  368.6955  436.1724  401.180  450.2485 1557.041   100
>