implement guniqueN

Start by reproducing the supplied R data.table and microbenchmark examples, then inspect the existing uniqueN behavior and the related Stack Overflow discussion. Define the intended guniqueN interface and verify that its grouped unique counts match the demonstrated cases while improving the reported performance.

Most recent data.table. Not always, but quite often...

library(data.table)
library(microbenchmark)
N <- 1e6
DT <- data.table(x = sample(1e5,N,TRUE), y = sample(1e2,N,TRUE))
microbenchmark(times=1L,
               DT[, length(unique(x)),y],
               DT[, uniqueN(x),y],
               DT[, uniqueN(.SD), by="y", .SDcols="x"])
# Unit: milliseconds
#                                         expr      min       lq     mean   median       uq      max neval
#                   DT[, length(unique(x)), y] 85.58602 85.58602 85.58602 85.58602 85.58602 85.58602     1
#                          DT[, uniqueN(x), y] 92.71877 92.71877 92.71877 92.71877 92.71877 92.71877     1
#  DT[, uniqueN(.SD), by = "y", .SDcols = "x"] 97.51024 97.51024 97.51024 97.51024 97.51024 97.51024     1
N <- 1e7
DT <- data.table(x = sample(1e5,N,TRUE), y = sample(1e2,N,TRUE))
microbenchmark(times=1L,
               DT[, length(unique(x)),y],
               DT[, uniqueN(x),y],
               DT[, uniqueN(.SD), by="y", .SDcols="x"])
# Unit: milliseconds
#                                         expr       min        lq      mean    median        uq       max neval
#                   DT[, length(unique(x)), y] 1642.5212 1642.5212 1642.5212 1642.5212 1642.5212 1642.5212     1
#                          DT[, uniqueN(x), y]  843.0670  843.0670  843.0670  843.0670  843.0670  843.0670     1
#  DT[, uniqueN(.SD), by = "y", .SDcols = "x"]  804.7881  804.7881  804.7881  804.7881  804.7881  804.7881     1
N <- 1e7
DT <- data.table(x = sample(1e6,N,TRUE), y = sample(1e5,N,TRUE))
microbenchmark(times=1L,
               DT[, length(unique(x)),y],
               DT[, uniqueN(x),y],
               DT[, uniqueN(.SD), by="y", .SDcols="x"])
# Unit: seconds
#                                         expr      min       lq     mean   median       uq      max neval
#                   DT[, length(unique(x)), y] 3.025365 3.025365 3.025365 3.025365 3.025365 3.025365     1
#                          DT[, uniqueN(x), y] 4.734323 4.734323 4.734323 4.734323 4.734323 4.734323     1
#  DT[, uniqueN(.SD), by = "y", .SDcols = "x"] 5.905721 5.905721 5.905721 5.905721 5.905721 5.905721     1
N <- 1e7
DT <- data.table(x = sample(1e3,N,TRUE), y = sample(1e5,N,TRUE))
microbenchmark(times=1L,
               DT[, length(unique(x)),y],
               DT[, uniqueN(x),y],
               DT[, uniqueN(.SD), by="y", .SDcols="x"])
# Unit: seconds
#                                         expr      min       lq     mean   median       uq      max neval
#                   DT[, length(unique(x)), y] 2.906589 2.906589 2.906589 2.906589 2.906589 2.906589     1
#                          DT[, uniqueN(x), y] 4.731925 4.731925 4.731925 4.731925 4.731925 4.731925     1
#  DT[, uniqueN(.SD), by = "y", .SDcols = "x"] 7.084020 7.084020 7.084020 7.084020 7.084020 7.084020     1
N <- 1e7
DT <- data.table(x = sample(1e6,N,TRUE), y = sample(1e2,N,TRUE))
microbenchmark(times=1L,
               DT[, length(unique(x)),y],
               DT[, uniqueN(x),y],
               DT[, uniqueN(.SD), by="y", .SDcols="x"])
# Unit: milliseconds
#                                         expr      min       lq     mean   median       uq      max neval
#                   DT[, length(unique(x)), y] 1331.244 1331.244 1331.244 1331.244 1331.244 1331.244     1
#                          DT[, uniqueN(x), y]  998.040  998.040  998.040  998.040  998.040  998.040     1
#  DT[, uniqueN(.SD), by = "y", .SDcols = "x"] 1096.867 1096.867 1096.867 1096.867 1096.867 1096.867     1
N <- 1e7
DT <- data.table(x = sample(letters,N,TRUE), y = sample(letters[1:10],N,TRUE))
microbenchmark(times=1L,
               DT[, length(unique(x)),y],
               DT[, uniqueN(x),y],
               DT[, uniqueN(.SD), by="y", .SDcols="x"])
# Unit: milliseconds
#                                         expr       min        lq      mean    median        uq       max neval
#                   DT[, length(unique(x)), y] 1304.4865 1304.4865 1304.4865 1304.4865 1304.4865 1304.4865     1
#                          DT[, uniqueN(x), y]  573.8628  573.8628  573.8628  573.8628  573.8628  573.8628     1
#  DT[, uniqueN(.SD), by = "y", .SDcols = "x"]  528.3269  528.3269  528.3269  528.3269  528.3269  528.3269     1

Related SO: http://stackoverflow.com/a/29684533/2490497

R version 3.1.3 (2015-03-09)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 14.04.2 LTS

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C               LC_TIME=en_DK.UTF-8        LC_COLLATE=en_US.UTF-8     LC_MONETARY=en_US.UTF-8    LC_MESSAGES=C             
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                  LC_ADDRESS=C               LC_TELEPHONE=C             LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] data.table_1.9.5     microbenchmark_1.4-2

loaded via a namespace (and not attached):
 [1] bitops_1.0-6     chron_2.3-45     colorspace_1.2-4 devtools_1.7.0   digest_0.6.8     evaluate_0.5.5   formatR_1.0      ggplot2_1.0.0    grid_3.1.3      
[10] gtable_0.1.2     httr_0.6.1       knitr_1.8        MASS_7.3-37      munsell_0.4.2    plyr_1.8.1       proto_0.3-10     Rcpp_0.11.4      RCurl_1.95-4.5  
[19] reshape2_1.4.1   scales_0.2.4     stringr_0.6.2    tools_3.1.3