A function to make it easier to create functions like filter

create_chunk_mapper(chunk_fn, warning_msg = NULL, as.data.frame = TRUE)

Arguments

chunk_fn

The dplyr function to create a mapper for

warning_msg

The warning message to display when invoking the mapper

as.data.frame

force the input chunk of a data.frame; needed for dtplyr

Examples

filter = create_chunk_mapper(dplyr::filter) #' example: creating a function that keeps only the first and last n row first_and_last <- function(chunk, n, ...) { nr = nrow(chunk) print(nr-n+1:nr) chunk[c(1:n, (nr-n+1):nr), ] } #' create the function for use with disk.frame first_and_last_df = create_chunk_mapper(first_and_last) mtcars.df = as.disk.frame(mtcars) #' the operation is lazy lazy_mtcars.df = mtcars.df %>% first_and_last_df(2) #' bring into R collect(lazy_mtcars.df)
#> [1] 5 6 7 8 9 10 #> [1] 5 6 7 8 9 10 #> [1] 5 6 7 8 9 10 #> [1] 5 6 7 8 9 10 #> [1] 5 6 7 8 9 10 #> [1] 1 2
#> mpg cyl disp hp drat wt qsec vs am gear carb #> ...1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4 #> ...2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4 #> ...3 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2 #> ...4 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1 #> ...5 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 #> ...6 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2 #> ...7 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4 #> ...8 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3 #> ...9 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3 #> ...10 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3 #> ...11 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4 #> ...12 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1 #> ...13 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2 #> ...14 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1 #> ...15 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2 #> ...16 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4 #> ...17 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2 #> ...18 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1 #> ...19 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4 #> ...20 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6 #> 1 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8 #> 2 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2 #> 1.1 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8 #> 2.1 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2
#' clean up delete(mtcars.df)