GAP is a java-designed software for generalized association plots (Chen, 2002) and exploratory data analysis. It is programmed for the java runtime environment 1.4, which is available for most operating systems. 

Author: Han-Ming Wu in Chen's Lab for Information Visualization
e-mail: hmwu@stat.sincia.edu.tw
Institute of Statistical Science, Academia Sinica
Official Website of GAP Software:  http://gap.stat.sinica.edu.tw/Software/GAP

[Current Version of GAP Software: v0.1, Build 2005-05-30]
[Last Updated of This Page: 2005/08/12]

Features | Download | Documentation | References | History | forum


Features

Generalized Association Plots
  • Various seriation algorithms (Clustering Analysis)

  • Various display conditions

  • GAP with a Covaraite Adjusted

    • Within And Between Analysis (WABA). 

    • Partial Correlation Analysis.

  • GAP with Nonlinear Association Analysis

    • ISOMAP

    • Kernel Transformation

  • GAP with Missing Value Imputation

    • Row means, Columns means

    • Regression methods

    • KNN (KNNImpute)

    • SVD  (SVDImpute)

    • Local Least Square (LLSImpute)

    • Global 2D loess imputation (GAPImpute)

Statistical Plots

  • Histogram, 2D Scatterplot, 3D Scatterplot (Rotatable)

more screenshots...

Downloads

  • Java 2 Platform, Enterprise Edition (J2EE)
  • GAP (version 0.1, build 2005-05-20)
    [
    Please Register Before You Download the Software]
    ***NOTE***
    The GAP software is expected to release on 15th Dec, 2005.
    If you are interested in using it, please
    e-mail me. You will be alerted when the software is available.
    • Windows 2000/XP: GAP_v0.1_windows.zip
    • Linux: GAP_v0.1_linux.zip 
    • Solaris: GAP_v0.1_solaris.zip
    • Mac OS X: GAP_v0.1_macosx.zip
      @
  • Test Data

Documentation

References

  • Chen, C. H. (2002), "Generalized Association Plots for Information Visualization: The applications of the convergence of iteratively formed correlation matrices.” Statistica Sinica 12, 1-23.
  • Wu, H. M. and Chen, C.H. (2005). Covariate Adjusted Matrix Visualization, Technical Report.
  • Wu, H. M. and Chen, C.H. (2005). Imputation of Missing Values by Clustered Matrix Visualization with a 2D Kernel Density Estimation.
  • Wu, H. M. and Chen, C.H. (2004). Matrix Visualization with Nonlinear Association. 

History

  • 2005/12/15 To be released (expected).
  • 2004/04/27 Project Begin.