R use ddply or aggregate

Question

I have a data frame with 3 columns: custId, saleDate, DelivDateTime.

> head(events22)
     custId            saleDate      DelivDate
1 280356593 2012-11-1         


        

Answer 1

Here's a much faster data.table function:

DATATABLE <- function() { 
  dt <- data.table(events, key=c('custId', 'saleDate'))
  dt[, maxrow := 1:.N==.N, by = custId]
  return(dt[maxrow==TRUE, list(custId, DelivDate)])
}

Note that this function creates a data.table and sorts the data, which is a step you'd only need to perform once. If you remove this step (perhaps you have a multi-step data processing pipeline, and create the data.table once, as a first step), the function is more than twice as fast.

I also modified all the previous functions to return the result, for easier comparison:

DDPLY <- function() { 
  return(ddply(events, .(custId), .inform = T, 
               function(x) {
                 x[x$saleDate == max(x$saleDate),"DelivDate"]}))
}
AGG1 <- function() { 
  return(merge(events, aggregate(saleDate ~ custId, events, max)))}

SQLDF <- function() { 
  return(sqldf("select custId, DelivDate, max(saleDate) `saleDate` 
             from events group by custId"))}
DOCALL <- function() {
  return(do.call(rbind, 
                 lapply(split(events, events$custId), function(x){
                   x[which.max(x$saleDate), ]
                 })
  ))
}

Here's the results for 10k rows, repeated 10 times:

library(rbenchmark)
library(plyr)
library(data.table)
library(sqldf)
events <- do.call(rbind, lapply(1:500, function(x) events22))
events$custId <- sample(1:nrow(events), nrow(events))

benchmark(a <- DDPLY(), b <- DATATABLE(), c <- AGG1(), d <- SQLDF(),
 e <- DOCALL(), order = "elapsed", replications=10)[1:5]

              test replications elapsed relative user.self
2 b <- DATATABLE()           10    0.13    1.000      0.13
4     d <- SQLDF()           10    0.42    3.231      0.41
3      c <- AGG1()           10   12.11   93.154     12.03
1     a <- DDPLY()           10   32.17  247.462     32.01
5    e <- DOCALL()           10   56.05  431.154     55.85

Since all the functions return their results, we can verify they all return the same answer:

c <- c[order(c$custId),]
dim(a); dim(b); dim(c); dim(d); dim(e)
all(a$V1==b$DelivDate)
all(a$V1==c$DelivDate)
all(a$V1==d$DelivDate)
all(a$V1==e$DelivDate)

/Edit: On the smaller, 20 row dataset, data.table is still the fastest, but by a thinner margin:

              test replications elapsed relative user.self
2 b <- DATATABLE()          100    0.22    1.000      0.22
3      c <- AGG1()          100    0.42    1.909      0.42
5    e <- DOCALL()          100    0.48    2.182      0.49
1     a <- DDPLY()          100    0.55    2.500      0.55
4     d <- SQLDF()          100    1.00    4.545      0.98

/Edit2: If we remove the data.table creation from the function we get the following results:

dt <- data.table(events, key=c('custId', 'saleDate'))
DATATABLE2 <- function() { 
  dt[, maxrow := 1:.N==.N, by = custId]
  return(dt[maxrow==TRUE, list(custId, DelivDate)])
}
benchmark(a <- DDPLY(), b <- DATATABLE2(), c <- AGG1(), d <- SQLDF(),
           e <- DOCALL(), order = "elapsed", replications=10)[1:5]
              test replications elapsed relative user.self
2 b <- DATATABLE()           10    0.09    1.000      0.08
4     d <- SQLDF()           10    0.41    4.556      0.39
3      c <- AGG1()           10   11.73  130.333     11.67
1     a <- DDPLY()           10   31.59  351.000     31.50
5    e <- DOCALL()           10   55.05  611.667     54.91