geom_roc: Empirical Receiver Operating Characteristic Curve

View source: R/geom_roc.R

GeomRocR Documentation

Empirical Receiver Operating Characteristic Curve


Display the empirical ROC curve. Useful for characterizing the classification accuracy of continuous measurements for predicting binary states



  mapping = NULL,
  data = NULL,
  stat = "roc",
  n.cuts = 10,
  arrow = NULL,
  lineend = "butt",
  linejoin = "round",
  linemitre = 1,
  linealpha = 1,
  pointalpha = 1,
  pointsize = 0.5,
  labels = TRUE,
  labelsize = 3.88,
  labelround = 1,
  na.rm = TRUE, = NULL,
  cutoff.labels = NULL,
  position = "identity",
  show.legend = NA,
  inherit.aes = TRUE,



Set of aesthetic mappings created by aes() or aes_(). If specified and inherit.aes = TRUE (the default), it is combined with the default mapping at the top level of the plot. You must supply mapping if there is no plot mapping.


The data to be displayed in this layer. There are three options:

If NULL, the default, the data is inherited from the plot data as specified in the call to ggplot().

A data.frame, or other object, will override the plot data. All objects will be fortified to produce a data frame. See fortify() for which variables will be created.

A function will be called with a single argument, the plot data. The return value must be a data.frame, and will be used as the layer data. A function can be created from a formula (e.g. ~ head(.x, 10)).


Use to override the default connection between geom_roc and stat_roc.


Number of cutpoints to display along each curve


Arrow specification, as created by arrow


Line end style (round, butt, square)


Line join style (round, mitre, bevel)


Line mitre limit (number greater than 1)


Alpha level for the lines, alpha.line is deprecated


Alpha level for the cutoff points, alpha.point is deprecated


Size of cutoff points, size.point is deprecated


Logical, display cutoff text labels


Size of cutoff text labels


Integer, number of significant digits to round cutoff labels


Remove missing values from curve

Vector of user supplied cutoffs to plot as points. If non-NULL, it will override the values of n.cuts and plot the observed cutoffs closest to the user-supplied ones.


vector of user-supplied labels for the cutoffs. Must be a character vector of the same length as


Position adjustment, either as a string, or the result of a call to a position adjustment function.


logical. Should this layer be included in the legends? NA, the default, includes if any aesthetics are mapped. FALSE never includes, and TRUE always includes. It can also be a named logical vector to finely select the aesthetics to display.


If FALSE, overrides the default aesthetics, rather than combining with them. This is most useful for helper functions that define both data and aesthetics and shouldn't inherit behaviour from the default plot specification, e.g. borders().


Other arguments passed on to layer(). These are often aesthetics, used to set an aesthetic to a fixed value, like colour = "red" or size = 3. They may also be parameters to the paired geom/stat.


An object of class GeomRoc (inherits from Geom, ggproto, gg) of length 6.

Computed variables


estimate of false positive fraction


estimate of true positive fraction


values of m at which estimates are calculated


geom_roc understands the following aesthetics (required aesthetics are in bold):

  • x The FPF estimate. This is automatically mapped by stat_roc

  • y The TPF estimate. This is automatically mapped by stat_roc smallest level in sort order is assumed to be 0, with a warning

  • alpha

  • color

  • fill

  • linetype

  • size

See Also

See geom_rocci for displaying rectangular confidence regions for the empirical ROC curve, style_roc for adding guidelines and labels, and direct_label for adding direct labels to the curves. Also export_interactive_roc for creating interactive ROC curve plots for use in a web browser.


D.ex <- rbinom(50, 1, .5)
rocdata <- data.frame(D = c(D.ex, D.ex), 
                   M = c(rnorm(50, mean = D.ex, sd = .4), rnorm(50, mean = D.ex, sd = 1)), 
                   Z = c(rep("A", 50), rep("B", 50)))

ggplot(rocdata, aes(m = M, d = D)) + geom_roc()

ggplot(rocdata, aes(m = M, d = D, color = Z)) + geom_roc()
ggplot(rocdata, aes(m = M, d = D)) + geom_roc() + facet_wrap(~ Z)
ggplot(rocdata, aes(m = M, d = D)) + geom_roc(n.cuts = 20)
ggplot(rocdata, aes(m = M, d = D)) + geom_roc( = c(1.5, 1, .5, 0, -.5))
ggplot(rocdata, aes(m = M, d = D)) + geom_roc(labels = FALSE)
ggplot(rocdata, aes(m = M, d = D)) + geom_roc(size = 1.25)

plotROC documentation built on May 28, 2022, 1:11 a.m.