Multiply many columns by a specific other column in R with data.table?

Question

I have a large data.table in R with several columns with dollar values. In a different column I have an inflation adjustment number. I am trying to figure out how to update

Answer 1

This approach is also quite convenient, but likely slower than using set():

library(data.table); library(magrittr)
set.seed(42)
DT <- data.table(id=1:1000,year=round(runif(1000)*10),
          inc1 = runif(1000), inc2 = runif(1000), inc3 = runif(1000),
          deflator = rnorm(1000))
vars <- names(DT) %>% .[grepl("inc", .)]
DT[, (vars) := .SD * deflator, .SDcols = vars]
DT[]

        id year         inc1        inc2        inc3   deflator
   1:    1    9  0.212563676  0.24806366  0.06860638  0.2505781
   2:    2    9 -0.017438715 -0.12186792 -0.26241497 -0.2779240
   3:    3    3 -1.414016119 -1.20714809 -0.76920337 -1.7247357
   4:    4    8 -1.082336969 -1.78411512 -1.08720698 -2.0067049
   5:    5    6 -0.644638321 -1.07757416 -0.20895576 -1.2918083
  ---                                                          
 996:  996    1 -0.573551720 -1.93996157 -0.50171303 -2.1569621
 997:  997    5 -0.007899417 -0.01561619 -0.05708009 -0.0920275
 998:  998    1 -0.090975121 -0.30475714 -0.27291825 -0.3974001
 999:  999    5 -0.045984079 -0.01563942 -0.07868934 -0.1383273
1000: 1000    0 -0.785962308 -0.63266975 -0.29247974 -0.8257650

Answer 2

You could try

DT[, (inc_cols) := lapply(.SD, function(x) 
        x * DT[['deflator']] ), .SDcols = inc_cols]
head(DT1,2)
#   id year         inc1         inc2       inc3   deflator
#1:  1    3  0.614838304  0.009796974  0.3236051  0.7735552
#2:  2    2 -0.001583579 -0.082289606 -0.1365115 -0.6644330

Or if you need a loop

for(inc in inc_cols){
  nm1 <- as.symbol(inc)
  DT[,(inc):= eval(nm1)*deflator]
}

 head(DT,2)
 #  id year         inc1         inc2       inc3   deflator
 #1:  1    3  0.614838304  0.009796974  0.3236051  0.7735552
 #2:  2    2 -0.001583579 -0.082289606 -0.1365115 -0.6644330

Or a possible option using set which should be very fast as the overhead of [.data.table is avoided (suggested by @Arun)

indx <- grep('inc', colnames(DT))

for(j in indx){
 set(DT, i=NULL, j=j, value=DT[[j]]*DT[['deflator']])
}
head(DT,2)
#  id year         inc1         inc2       inc3   deflator
#1:  1    3  0.614838304  0.009796974  0.3236051  0.7735552
#2:  2    2 -0.001583579 -0.082289606 -0.1365115 -0.6644330

where

inc_cols <-  grep('^inc', colnames(DT), value=TRUE)

data

set.seed(24)
DT <- data.table(id=1:1000,year=round(runif(1000)*10), 
      inc1 = runif(1000), inc2 = runif(1000), inc3 = runif(1000),    
      deflator = rnorm(1000)) 

Answer 3

Since you can use dplyr on data.tables, you could also do:

library(dplyr)
DT %>% mutate_each(funs(.*deflator), starts_with("inc"))

Which will multiply each column of DT that starts with "inc" by the "deflator" column.