TopviewTopographicMap: Top view of the topographic map in 2D

In GeneralizedUmatrix: Credible Visualization for Two-Dimensional Projections of Data

Top view of the topographic map in 2D

Description

Fast visualization of the generalized U-matrix in 2D which visualizes high-dimensional distance and density based structurs of the combination two-dimensional scatter plots (projections) with high-dimensional data.

Usage

TopviewTopographicMap(GeneralizedUmatrix, BestMatchingUnits,

Cls, ClsColors = NULL, Imx = NULL,

ClsNames = NULL, BmSize = 6, DotLineWidth = 2,

alpha = 1, ...)

Arguments

GeneralizedUmatrix	[1:Lines,1:Columns] U-matrix to be plotted, numerical matrix storing the U-heights, see [Thrun, 2018] for definition.
BestMatchingUnits	[1:n,1:2], Positions of bestmatches to be plotted onto the U-matrix
Cls	[1:n], numerical vector of classification defining the labels defined as digits of the [1:k] classes. See details
ClsColors	Optional, [1:k] character vector of colors that will be used to colorize the different classes, vector can have names that define the mapping of the k classes, see details
Imx	a mask (Imx) that will be used to cut out the U-matrix
ClsNames	Optional, [1:k] character vector naming the k classes for the legend. Vector can have names that define the mapping of the k classes, see details. In this case, further parameters with the possibility to adjust are: LegendCex: (size); NamesOrientation: Legend position "v" or "h"; NamesTitle: title of legend.
BmSize	size(diameter) of the points in the visualizations. The points represent the BestMatchingUnits
DotLineWidth	...
alpha	...
...	Tiled Should the U-matrix be drawn 4times? main set specific title in plot ExtendBorders scalar, extends U-matrix by toroidal continuation of the given U-matrix MainCex scalar, magnification to be used for legend LegendCex scalar, magnification to be used for main titles _ Further Arguments relevant for interactive shiny application

Details

In Cls each the bestmatch that will be visualized as a colored point gets one label, and the mappping is consecutive, i.e. first bestmatch in BestMatchingUnits gets first label stored in Cls. Please note, that the there will be k labels stored in Cls but depending on the user input the digits in the k-labels do not need to be consecutive. For example, if an algorithm find three clusters the labels do not need to be 1,2,3 but can also be 5,99,1.

if ClsColors or ClsNames is given but the vector is not named, than internally the mapping of names(ClsColors)=sort(unique(Cls)) is assumed, meaning that the lowest digit number of the k classes gets the first color stored in the first element of the ClsColors vector. The same is true for ClsNames. The user can specify antoher non-consecutive mapping between colors/names and labels with names(ClsColors)=.... In the above example, one could define the mapping between colors and classes with names(ClsColors)=c(5,99,1), after the vector is initialized with three colors for the three clusters.

Please see also plotTopographicMap.

Value

plotly handler

Note

Names are currently under development, Imx in testing phase.

Author(s)

Tim Schreier, Luis Winckelmann, Michael Thrun

References

[Thrun, 2018] Thrun, M. C.: Projection Based Clustering through Self-Organization and Swarm Intelligence, doctoral dissertation 2017, Springer, Heidelberg, ISBN: 978-3-658-20539-3, \Sexpr[results=rd]{tools:::Rd_expr_doi("10.1007/978-3-658-20540-9")}, 2018.

[Thrun et al., 2016] Thrun, M. C., Lerch, F., Loetsch, J., & Ultsch, A.: Visualization and 3D Printing of Multivariate Data of Biomarkers, in Skala, V. (Ed.), International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG), Vol. 24, Plzen, http://wscg.zcu.cz/wscg2016/short/A43-full.pdf, 2016.

See Also

plotTopographicMap

Examples

data("Chainlink")
Data=Chainlink$Data
Cls=Chainlink$Cls
InputDistances=as.matrix(dist(Data))
res=cmdscale(d=InputDistances, k = 2, eig = TRUE, add = FALSE, x.ret = FALSE)
ProjectedPoints=as.matrix(res$points)
#see also ProjectionBasedClustering package for other common projection methods

resUmatrix=GeneralizedUmatrix(Data,ProjectedPoints)
## visualization
TopviewTopographicMap(GeneralizedUmatrix = resUmatrix$Umatrix,resUmatrix$Bestmatches)

GeneralizedUmatrix documentation built on April 3, 2025, 8:56 p.m.