A Basic Set of Functions for Compositional Data Analysis
A minimum set of functions to perform compositional data analysis
using the log-ratio approach introduced by John Aitchison (1982) < http://www.jstor.org/stable/2345821>. Main functions
have been implemented in c++ for better performance.
coda.base 0.1.12 (Release date: 2018-04-15)
- coordinates function keeps row.names attribute (thank )
- Principal components calculations are done using svd function which is faster than princomp
- sbp_basis function does not need package to be loaded, can run as coda.base::sbp_basis()
coda.base 0.1.11 (Release date: 2018-12-23)
- Principal components coordinates uncentered.
- Sequential binary partition can be defined using a matrix with -1,0 and 1's.
- CoDaPack's basis included.
- A vignette explaining how to build coordinates has been included.
coda.base 0.1.10 (Release date: 2018-08-03)
- Principal Balances included as direct method in coordinates function.
- Coordinates function filters non-valid compositions.
coda.base 0.1.9 (Release date: 2018-05-03)
- Modifications included to rcran policies.
coda.base 0.1.8 (Release date: 2017-12-03)
- Exact algorithm for Principal Balances included.
- Bug in lsearch base in principal components solved.
coda.base 0.1.7 (Release date: 2017-08-25)
- Problem with function composition using 'clr' basis solved.
- 'coda.base.basis' option included to hide the basis when printing the coordinates.
- New method which uses the principal components included in pb_basis.
- Documentaion improved.