[r] Select the top N values by group

# start with the mtcars data frame (included with your installation of R)
mtcars

# pick your 'group by' variable
gbv <- 'cyl'
# IMPORTANT NOTE: you can only include one group by variable here
# ..if you need more, the `order` function below will need
# one per inputted parameter: order( x$cyl , x$am )

# choose whether you want to find the minimum or maximum
find.maximum <- FALSE

# create a simple data frame with only two columns
x <- mtcars

# order it based on 
x <- x[ order( x[ , gbv ] , decreasing = find.maximum ) , ]

# figure out the ranks of each miles-per-gallon, within cyl columns
if ( find.maximum ){
    # note the negative sign (which changes the order of mpg)
    # *and* the `rev` function, which flips the order of the `tapply` result
    x$ranks <- unlist( rev( tapply( -x$mpg , x[ , gbv ] , rank ) ) )
} else {
    x$ranks <- unlist( tapply( x$mpg , x[ , gbv ] , rank ) )
}
# now just subset it based on the rank column
result <- x[ x$ranks <= 3 , ]

# look at your results
result

# done!

# but note only *two* values where cyl == 4 were kept,
# because there was a tie for third smallest, and the `rank` function gave both '3.5'
x[ x$ranks == 3.5 , ]

# ..if you instead wanted to keep all ties, you could change the
# tie-breaking behavior of the `rank` function.
# using the `min` *includes* all ties.  using `max` would *exclude* all ties
if ( find.maximum ){
    # note the negative sign (which changes the order of mpg)
    # *and* the `rev` function, which flips the order of the `tapply` result
    x$ranks <- unlist( rev( tapply( -x$mpg , x[ , gbv ] , rank , ties.method = 'min' ) ) )
} else {
    x$ranks <- unlist( tapply( x$mpg , x[ , gbv ] , rank , ties.method = 'min' ) )
}
# and there are even more options..
# see ?rank for more methods

# now just subset it based on the rank column
result <- x[ x$ranks <= 3 , ]

# look at your results
result
# and notice *both* cyl == 4 and ranks == 3 were included in your results
# because of the tie-breaking behavior chosen.