Table of Contents
Section: Numerical classification
TWINSPAN (hierarchical divisive classification)
library (twinspanR), David Zelený
I created an
twinspanR with the TWINSPAN algorithm - you may install it from GitHub repository https://github.com/zdealveindy/twinspanR (note: this library is currently in beta stage under development). To install any library from GitHub, you will need to first install the package
devtools written by Hadley Wickham, which contains a set of tools for the development of R packages. After installing
devtools, use the function
install_github. Note that the use of the library has some limitations: it can be installed only on Windows platform (since the engine of the library is based on running *.exe file externally) and you need permanent access to the folder where the library is installed (usually in Program Files/R/R-x.x.x/library, but could be also in some other personalized place). Without the access to this folder the function
twinspan cannot run correctly.
How to install: follow instructions at https://github.com/zdealveindy/twinspanR (note that you may need to install also
riojaExtra manually from GitHub - see the installation instructions).
For more details see also my blog post.
library (twinspan), Jari Oksanen
Jari Oksanen created
twinspan package by importing the original FORTRAN code into R - it can be installed from GitHub on https://github.com/jarioksa/twinspan. This has singificant advantage against the package
twinspanR in that it is portable across all platform (
twinspanR works only on Windows). Also, this library can plot the dendrogram. The only disadvantage is that it does not offer modified TWINSPAN algorithm (the main reason for which I created
twinspanR in 2015).