Calculation of the OPTICS Cordillera

Functions for calculating the OPTICS Cordillera. The OPTICS Cordillera measures the amount of 'clusteredness' in a numeric data matrix within a distance-density based framework for a given minimum number of points comprising a cluster, as described in Rusch, Hornik, Mair (2017) . There is an R native version and a version that uses 'ELKI', with methods for printing, summarizing, and plotting the result. There also is an interface to the reference implementation of OPTICS in 'ELKI'.


Version 0.8-0

  • CRAN Release.

Version 0.7-2

  • Added possibility to not only center and scale X, but also to only scale X with no centering with rmsq and sd. TRUE and 1 is now center and scale, 2 is now scaling each column individually but no centering, 3 is now scaling all columns by the maximum column sd, 4 is now scaling all columns by maximum column rmsq. FALSE or 0 is no scaling.

Version 0.7-1

  • Fixed citation info and help file typos. Added another example.

Version 0.7-0

  • Included functionality for more distance measures: Either calculating different distances from a matrix (the ones in dist()) or supplying an object inheriting from dist or supplying a symmetric distance matrix (which is then coerced to a dist object). CRAN version.

Version 0.6-0

  • Updated version number to 0.6-0. Added dmax argument.

Version 0.1-0

  • Updated version number.

Version 0.0-35

  • Forked the cordillera infrastructure from stops into this package.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.8-0 by Thomas Rusch, 4 years ago

Browse source code at

Authors: Thomas Rusch [aut, cre] , Patrick Mair [ctb] , Kurt Hornik [ctb]

Documentation:   PDF Manual  

GPL-2 | GPL-3 license

Imports dbscan, yesno

Suggests cluster, scatterplot3d, MASS

System requirements: ELKI (>=0.6.0 if used)

Depended on by cops.

See at CRAN