knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

This vignette attempts to give a documentation on how to use the package nlsCompare to compare the best parameter values and sum-of-squares involved in solving non-linear least squares (nls) problems with R's existing and new packages' nls functions viz. nls (base), nlsLM (minpack.lm), nlxb (nlsr) and nlsj (nlsj). The last one is a new package developed during the Google Summer of Code (GSoC), 2021 program.
The GSoC project titled Improvements to nls(). The project student was the author, mentored by Dr. John C. Nash (retired professor, Telfer School of Management, University of Ottawa) and Dr. Heather Turner (Department of Statistics, University of Warwick). nlsCompare is a product of the above project.

How to install nlsCompare

As of this writing, only a development version of the package is available on GitHub. The package can be downloaded from GitHub using devtoools :

# install.packages(devtools)  ## uncomment if devtools package is not installed
devtools::install_github("ArkaB-DS/nlsCompare")

How to use it

The following R code gives a template on how to use the package for testing:

library(nlsCompare)         ## load the library
machid <- machineId()       ## get your machine summary as a string 
## uncomment when running this r script
# setup_dir()               ## setup working directory to store the outputs
st <- create_db()           ## create dataframe to save the database of problems 
sr <- create_elog()         ## create dataframe to save the error log while solving the problems
csv_exists(st, sr)          ## see if nlsDatabase.csv and nlsErrorLog.csv already exists in the directory
logs <- run(machid, st, sr) ## run the tests
write_csvs(logs$database, logs$errorlog) ## write final outputs in the csv files created
rm_nls()                    ## delete objects created by the above functions 

Examples of the output csv files - nlsDatabase.csv and nlsErrorLog.csv - are present in https://github.com/ArkaB-DS/nlsCompare/blob/master/vignettes.



ArkaB-DS/nlsCompare documentation built on Jan. 1, 2022, 2 p.m.