R group by aggregate

Question

In R (which I am relatively new to) I have a data frame consists of many column and a numeric column I need to aggregate according to groups determined by another column.

<

Answer 1

Using data.table package:

library(data.table)

dt = data.table(SessionID=c(1,1,1,7,7,7), Price=c(624,697,649,779,710,2679))

dt[, c("Min", "Max"):=list(min(Price),max(Price)), by=SessionID]
dt
#   SessionId Price Min  Max
#1:         1   624 624  697
#2:         1   697 624  697
#3:         1   649 624  697
#4:         7   779 710 2679
#5:         7   710 710 2679
#6:         7  2679 710 2679

In your case if you have a data.frame df, just do dt=as.data.table(df) and use the code above.

I am curious about the benchmark of the solutions on an average data.frame:

df = data.frame(SessionID=rep(1:1000, each=100), Price=runif(100000, 1, 2000))
dt = as.data.table(df)

algo1 <- function() 
{
    df %>% group_by(SessionID) %>% mutate(Min = min(Price), Max = max(Price))
}

algo2 <- function()
{
    dt[, c("Min", "Max"):=list(min(Price),max(Price)), by=SessionID]
}

algo3 <- function()
{
    tmp <- aggregate(Price ~ SessionID, df, function(x) c(Min = min(x), Max = max(x)))
    cbind(df, tmp[match(df$SessionID, tmp$SessionID), 2])
}

algo4 <- function()
{
    transform(df, Min = ave(Price, SessionID, FUN = min), Max = ave(Price, SessionID, FUN = max))
}   



#> system.time(algo1())
#   user  system elapsed 
#   0.03    0.00    0.19 

#> system.time(algo2())
#   user  system elapsed 
#   0.01    0.00    0.01 

#> system.time(algo3())
#   user  system elapsed 
#   0.77    0.01    0.78 

#> system.time(algo4())
#   user  system elapsed 
#   0.02    0.01    0.03