radviz2d: Radial Coordinate Visualization
In dprep: Data Pre-Processing and Visualization Functions for Classification

Description Usage Arguments Details Value Note Author(s) References See Also Examples

Radviz is a radial spring-based visualization that permits the visualization of n-dimensional datasets. Data attributes are equidistantly distributed along the circumference of a circle. Each data item is virtually connected to a spring that starts at the circle perimeter and ends on the data item. Each spring pulls the item with a force proportional to the item attribute value. Depending on the value of each attribute, the forces of the springs project each data item to a position inside the circle where the sum of the spring forces is equal to zero.

1	radviz2d(dataset, name = "")

`dataset`	The dataset to be visualized.
`name`	The name of the dataset to be used in the graph title.

Some features of this visualization are: l) Points where all dimensional values have approximately the same value will lie close to the center. 2) If dimensional points lie opposite each other on the circle and have similar values than points will lie near the center. 3) If 1 or 2 dimensional values are greater, points will lie closer to those dimensional points. 4) Where a point will lie depends on the layout of the particular dimensions around the circle. 5) This is a non-linear projection from N-dimensions down to 2 dimensions 6) Certain symmetries of the data will be preserved.

The function assumes the class labels are in the last column. Class column may be either a numeric vector or a factor.

A Radviz visualization of the original dataset is returned.

Prior to visualizing, the values of each attribute are usually standardized to the interval [0, 1] to make all the attributes equally important in "pulling" the data point. If one attribute value is much larger than the values of the other attributes, then the point will lie close to the point on the circumference of the circle which corresponds to this attribute. The visualization of a given data set, and also its usefulness, largely depends on the selection of visualized attributes and their ordering around the circle perimeter. The total number of possible orderings of m attributes is factorial(m), but some of them are equivalent up to a rotation or image mirroring. Hence, it can be shown that the total number of different projections with m attributes is factorial(m-1)/2.

Caroline Rodriguez

Ankerst M., Keim D. A., Kriegel H.-P. Circle Segments: A Technique for Visually Exploring Large Multidimensional Data Sets, IEEE Visualization, 1996.

K.A. Olsen, R.R. Korfhage, K.M. Sochats, M.B. Spring and J.G. Williams. Visualisation of a Document Collection: The VIBE System, Information Processing and Management, Vol. 29, No. 1, pp. 69-81, Pergamon Press Ltd, 1993.

starcoord, surveyplot, parallelplot

1 2	data(iris) radviz2d(iris,"Iris")

Warning messages:
1: In rgl.init(initValue, onlyNULL) : RGL: unable to open X11 display
2: 'rgl_init' failed, running with rgl.useNULL = TRUE 
3: .onUnload failed in unloadNamespace() for 'rgl', details:
  call: fun(...)
  error: object 'rgl_quit' not found