Matrix containing training sample where each row is a d-dimensional object, and objects of each class are kept together so that the matrix can be thought of as containing blocks of objects representing classes.

Numerical vector of cardinalities of each class in data, each entry corresponds to one class.

The type of the used method. The default is exact=F, which leads to approximate computation of the halfspace depth. For exact=F, method="Sunif.1D" is used by default. If exact=T, the halfspace depth is computed exactly, with method="recursive" by default.

For exact=F, if method="Sunif.1D" (by default), the halfspace depth is computed approximately by being minimized over univariate projections (see details).

For exact=T, the halfspace depth is calculated as the minimum over all combinations of k points from data (see details). In this case parameter method specifies k, with possible values 1 for method="recursive" (by default), d-2 for method="plane", d-1 for method="line".

The name of the method may be given as well as just parameter exact, in which case the default method will be used.

Number of random directions to be generated. As the same direction set is used for all observations, the algorithmic complexity of calculating the depth of each single point in data is logarithmic in the number of observations in data, given the number of directions, see Mozharovskyi et al. (2015), Section 2.3 for discussion.

The random seed. The default value seed=0 makes no changes.