bartolomeoMod: wrapper for bartMachine

In FoscoV/foreYield: forecasting yield result

Description

Supervisor of Bayesian Additive Regression Tree for yield previsions

Usage

bartolomeoMod(cpus,depthing=TRUE)

Details

• cpus bartMachine which handles the computations allow for heavy parallelization. You can here provide your number of cpus to speed up the processing (try num_cores+1).

• depthing on default doeas the CrossValidated version (what you are probably looking for: MY SUGGESTION IS NOT TO DO ANYTHING)

Please note that due to its own structure this function will work after the successful fullfillment of the data structure and collection granted by virgilio's guide.

Value

bartolomeoMod return a printed text and nothing else

Note

Only cpu's number for parallelization are required, whatever else will be self managed.

Please note that the Java implementation require rJava working as wrapper. Due to it's known issues on some platforms, this whole is switched to "suggestion" level. To use it adopt install_github("FoscoV/foreYield",dependencies=T) during install phase. You'll have to take care of your Java machine.

References

Adam Kapelner, Justin Bleich (2016). bartMachine: Machine Learning with Bayesian Additive Regression Trees. Journal of Statistical Software, 70(4), 1-40. doi:10.18637/jss.v070.i04

See Also

configure()

Examples

#to run the cross validated fit of the BART model on a quad(4) core cpus:
bartolomeoMod(4)

FoscoV/foreYield documentation built on June 20, 2021, 7:17 p.m.