Chordalysis (original) (raw)

ChoR, a R package for Chordalysis

ChoR is a R package for the Chordalysis algorithm, developed at Monash University, Melbourne, Australia

Update Chordalysis jar 2017-07-10
Replace Apache Commons Mathematics by https://cran.r-project.org/package=commonsMath
- Post modification of NAMESPACE in the makefile
Update the example:
- flare.data2 URL now points to https://raw.githubusercontent.com/jeffheaton/proben1/master/flare/flare.data2
- Check for optional package "graph"

The Chordalysis algorithm is coded in Java and use commonsMath. This package contains an R layer allowing to use the java code through rJava.

The rJava and commonsMath packages can be install in R with:

install.packages('rJava') install.packages('commonsMath')

R may need to be reconfigure with Java support. In the shell (may require sudo):

If you need more memory for Java, use the following R line before loading a package performing a JVM initialization.

options( java.parameters = "-Xmx4g" )

install.packages('Rcpp') install.packages('roxygen2')

See the ChoR/inst/examples/script.R for some examples. The Rgraphviz package from bioconductor is needed to plot the obtained graphs.

source("https://bioconductor.org/biocLite.R") biocLite("Rgraphviz") library(Rgraphviz)

If you need to work with ARFF data, use the RWeka package:

library(RWeka) myARFFdata = read.arff("/path/to/myfile.arff")

https://cran.r-project.org/web/packages/policies.html
https://cran.r-project.org/doc/manuals/r-release/R-exts.html
"For Java .class and .jar files, the sources should be in a top-level java directory in the source package (or that directory should explain how they can be obtained)."