depth.space. {ddalpha}

Calculate Depth Space using the Given Depth

Description

Calculates the representation of the training classes in depth space.

The detailed descriptions are found in the corresponding topics.

Usage

depth.space.(data, cardinalities, notion, ...)

## Mahalanobis depth
# depth.space.Mahalanobis(data, cardinalities, mah.estimate = "moment", mah.parMcd = 0.75)

## projection depth
# depth.space.projection(data, cardinalities, method = "random", num.directions = 1000)

## Tukey depth
# depth.space.halfspace(data, cardinalities, exact, alg, num.directions = 1000)

## spatial depth
# depth.space.spatial(data, cardinalities)

## zonoid depth
# depth.space.zonoid(data, cardinalities)

# Potential
# depth.space.potential(data, cardinalities, pretransform = "NMom", 
#            kernel = "GKernel", kernel.bandwidth = NULL, mah.parMcd = 0.75)

Arguments

data

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.

cardinalities

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

notion

The name of the depth notion (shall also work with Custom Methods).

...

Additional parameters passed to the depth functions.

Value

Matrix of objects, each object (row) is represented via its depths (columns) w.r.t. each of the classes of the training sample; order of the classes in columns corresponds to the one in the argument cardinalities.

See Also

depth.space.Mahalanobis

depth.space.projection

depth.space.halfspace

depth.space.spatial

depth.space.zonoid

Examples

# Generate a bivariate normal location-shift classification task
# containing 20 training objects
class1 <- mvrnorm(10, c(0,0), 
                  matrix(c(1,1,1,4), nrow = 2, ncol = 2, byrow = TRUE))
class2 <- mvrnorm(10, c(2,2), 
                  matrix(c(1,1,1,4), nrow = 2, ncol = 2, byrow = TRUE))
data <- rbind(class1, class2)
# Get depth space using zonoid depth
depth.space.(data, c(10, 10), notion = "zonoid")