RnavGraph

RnavGraph is an open source R package (www.r-project.org) hosted on CRAN and written by Adrian Waddell and Professor Wayne Oldford. RnavGraph facilitates controlled exploration of high dimensional data space via (user determined) low dimensional trajectories through that space. The trajectories are paths on a navigation graph (navGraph), a graph whose nodes are plots and whose edges represent transitions from one plot to another (see Hurley and Oldford, 2011, Comp. Stat.). In RnavGraph, there are two primary display regions: the navigation graph (or navGraph) in one and some visualization of the data in the other. The navGraph display drives the data visualization. The user moves a "You are here" circle, or "bullet", from one node to another along defined edges, causing one data visualization to be smoothly morphed into the other.

Example Videos of RnavGraph

These following mute videos show how RnavGraph can be used.

Video of SSC 2012 slides Video of Olive Oil data Example Video of Frey Faces Example

Video of Scagnostics Example

Papers

  • Waddell, Adrian; Oldford, R. Wayne: Interactive Visual Clustering of High Dimensional Data by Exploring Low-Dimensional Subspaces. InfoVis 2012 in Seattle. paper, poster, 3d transition booklet, 4d transition booklet
  • Waddell, Adrian; Oldford, R. Wayne: RnavGraph: A visualization tool for navigating through high-dimensional data. ISI 2011, invited paper. pdf
  • Oldford, R. Wayne; Waddell, Adrian: Visual Clustering of High-dimensional Data by Navigating Low-dimensional Spaces. ISI 2011, invited paper. pdf
  • Hurley, C. B., and R. W. Oldford. "Graphs as Navigational Infrastructure for High Dimensional Data Spaces." Computational Statistics (February 2011).

Selected Talks

Speaker: item bullet color Oldford, item bullet color Waddell.

  • The Institute of Statistical Mathematics, Tokyo, Japan, 2011, "Graph-Theoretic Methods for Data Visualization 2: Navigating high-dimensional spaces and the RNavGraph R package". 7th Annual Japanese R-users meeting. slides, R code
  • World Statistics Conference, Dublin, Ireland, 2011, "Visual Clustering of High-Dimensional Data by Navigating Low-Dimensional Spaces". 58th Biennial Session of the International Statistical Institute. Special Topics Session: Visualisation of Complex Data Sets. video
  • World Statistics Conference, Dublin, Ireland, 2011, "RnavGraph: A Visualization Tool for Navigating through High-Dimensional Data Spaces". 58th Biennial Session of the International Statistical Institute. Invited Paper Session: Understanding Complex Data. Interface of North America, selection. slides, videos: 1 2 3 4 5 6
  • University of Warwick, Warwick, U.K., 2011, "RnavGraph and the tk canvas widget". useR! Annual Conference. slides, videos: 1 2 3 3a 5 6
  • Acadia University, Wolfville, NS, 2011, "RnavGraph: Interactive Visual Clustering". Annual Meeting of the Statistical Society of Canada. slides, videos

Video Manual

We have created a series of videos to help you getting started using RnavGraph. These videos, however, are not meant to replace the package vignette/manual which we update with every package build. If you experience any problems or have questions don't hesitate to email us.

Installing RnavGraph under Windows

Installation under Windows

If you want to import images from files such as jpg, png, etc..., you need the tcl Img extension installed. It is easiest to install ActiveTcl and then make R to use this tcl/tk build (see R mailing list entry).

Installing RnavGraph under OS X

Installation under Mac OS X

You need to make sure that you have the universal build of tcl/tk 8.5 for X11 installed.

Installing RnavGraph under Linux

Installation under Linux

Install the libtk-img-dev, tcl-dev and tk-dev system libraries before installing RnavGraph. The installation is shown for Ubuntu 11.10.