Graphics Group @ ISU

We develop methodologies for 3D radial visualization of high-dimensional datasets. Our display engine is called RadViz3D and extends the classic RadViz that visualizes multivariate data in the 2D plane by mapping every record to a point inside the unit circle. The classic RadViz display has equally-spaced anchor points on the unit circle, with each of them associated with an attribute or feature of the dataset. RadViz3D obtains equi-spaced anchor points exactly for the five Platonic solids and approximately for the other cases via a Fibonacci grid. We show that distributing anchor points at least approximately uniformly on the 3D unit sphere provides a better visualization %with less effects of ordering than in 2D. We also propose a Max-Ratio Projection (MRP) method that utilizes the group information in high dimensions to provide distinctive lower-dimensional projections that are then displayed using Radviz3D. Our methodology is extended to datasets with discrete and mixed features where a generalized distributional transform is used in conjunction with copula models before applying MRP and RadViz3D visualization.

The slides for the talk can be found here, and some example code is shown below.

library(devtools)

## Loading required package: usethis

library(rgl)
#install_github("fanne-stat/radviz3d")
library(radviz3d)

data("iris")
features = iris[,-5]
response = as.factor(iris[,5])
radialvis3d(data = features, 
            cl = response,
            domrp = F,
            doGtrans = F, 
            lwd = 2,
            alpha = 0.4, 
            pradius = 0.02, 
            class.labels = levels(response))

## Warning in rgl.texts(x = structure(c(0.666839560914018, 0.666839560914018, :
## "bitmap" family only supports font 1

rgl::rgl.viewpoint(zoom = 0.6)
rgl::rglwidget()