DataVisualizations (version 1.1.12)

ShepardPDEscatter: Shepard PDE scatter

Description

Draws ein Shepard Diagram (scatterplot of distances) with an two-dimensional PDE density estimation .

Usage

ShepardPDEscatter(InputDists, OutputDists, Plotter = "native", 
xlab ="Input Distances", ylab = "Output Distances", 
main = "ProjectionMethod",sampleSize)

Arguments

InputDists

[1:n,1:n] with n cases of data in d variables/features: Matrix containing the distances of the inputspace.

OutputDists

[1:n,1:n] with n cases of data in d dimensionalites of the projection method variables/features: Matrix containing the distances of the outputspace.

xlab

Label of the x axis in the resulting Plot.

ylab

Label of the y axis in the resulting Plot.

Plotter

see PDEscatter for details

main

Title of the Shepard diagram

sampleSize

Optional, default(50000), reduces a.ount of data for density estimation, if too many distances given

Details

Introduced and described in [Thrun, 2018, p. 63] with examples in [Thrun, 2018, p. 71-72]

References

[Thrun, 2018] Thrun, M. C.: Projection Based Clustering through Self-Organization and Swarm Intelligence, doctoral dissertation 2017, Springer, ISBN: 978-3-658-20540-9, Heidelberg, 2018.

Examples

# NOT RUN {
data("Lsun3D")
Cls=Lsun3D$Cls
Data=Lsun3D$Data
InputDist=as.matrix(dist(Data))
res = stats::cmdscale(d = InputDist, k = 2, eig = TRUE, 
        add = FALSE, x.ret = FALSE)
ProjectedPoints = as.matrix(res$points)
# }
# NOT RUN {
ShepardPDEscatter(InputDist,as.matrix(dist(ProjectedPoints)),main = 'MDS')
# }