forder
frankv
keyby
by
df[, .N,
keyby = .(cust_segment, cust_postal)
][order(-N), r := rowid(cust_segment)
][r <= 3, dcast(.SD, cust_segment ~ r, value.var ="cust_postal")]
cust_segment 1 2 3
1: A 51274 53440 55754
2: B 63590 69477 50380
3: C 60619 66249 52122
4: D 68107 50824 59305
5: E 51832 65249 52366
6: F 51401 55410 65046
library(microbenchmark)
microbenchmark(C8H10N4O2 = dcast(
df[,.(.N),
by = .(cust_segment, cust_postal)
][,.(cust_postal,
postal_rank = frankv(x=N, order=-1, ties.method = 'first')
), keyby=cust_segment
][postal_rank<=3],
cust_segment ~ paste0('postcode_rank_',postal_rank), value.var = 'cust_postal'
),
frank = df[, .N,
keyby = .(cust_segment, cust_postal)
][order(-N), r := rowid(cust_segment)
][r <= 3, dcast(.SD, cust_segment ~ r, value.var ="cust_postal")])
Unit: milliseconds
expr min lq mean median uq max neval
C8H10N4O2 136.3318 140.8096 156.2095 145.6099 170.4862 205.8457 100
frank 102.2789 110.0140 118.2148 112.6940 119.2105 192.2464 100