Compute the Pareto Optimal Frontier

Extract the points that make up the Pareto frontier from a set of data.

get_frontier(data, x, y, quadrant = c("top.right", "bottom.right",
  "bottom.left", "top.left"), decreasing = TRUE)

Arguments

data	A data frame.
x	A numeric vector.
y	A numeric vector.
quadrant	Chararacter string specifying which quadrant the frontier should appear in. Default is "top.right".
decreasing	Logical value indicating whether the data returned is in decreasing or ascending order (ordered by x and then y). Default is decreasing order.

Value

A data frame containing the data points that make up the efficient frontier.

See also

geom_frontier for plotting the Pareto front

Examples

# default will find the Pareto optimal observations in top right quadrant
get_frontier(mtcars, mpg, wt)
#>                      mpg    wt
#> Toyota Corolla      33.9 1.835
#> Fiat 128            32.4 2.200
#> Merc 240D           24.4 3.190
#> Hornet 4 Drive      21.4 3.215
#> Pontiac Firebird    19.2 3.845
#> Merc 450SE          16.4 4.070
#> Chrysler Imperial   14.7 5.345
#> Lincoln Continental 10.4 5.424

# the output can be in descending or ascending order
get_frontier(mtcars, mpg, wt, decreasing = FALSE)
#>                      mpg    wt
#> Lincoln Continental 10.4 5.424
#> Chrysler Imperial   14.7 5.345
#> Merc 450SE          16.4 4.070
#> Pontiac Firebird    19.2 3.845
#> Hornet 4 Drive      21.4 3.215
#> Merc 240D           24.4 3.190
#> Fiat 128            32.4 2.200
#> Toyota Corolla      33.9 1.835

# use quadrant parameter to change how you define the efficient frontier
get_frontier(airquality, Ozone, Temp, quadrant = 'top.left')
#>     Ozone Temp
#> 120    76   97
#> 126    73   93
#> 40     71   90
#> 41     39   87
#> 97     35   85
#> 129    32   84
#> 95     16   82
#> 94      9   81
#> 76      7   80
#> 23      4   61
#> 21      1   59

get_frontier(airquality, Ozone, Temp, quadrant = 'bottom.right')
#>     Ozone Temp
#> 117   168   81
#> 30    115   79
#> 139    46   78
#> 1      41   67
#> 17     34   66
#> 24     32   61
#> 8      19   59
#> 15     18   58
#> 18      6   57