R, as we have seen in prior chapters, is an environment originally designed for statistical programming. It emerged out of a project at the University of New Zealand, where Ross Ihanka and Robert Gentleman developed R as a variation of the S programming language developed by John Chambers in Bell Labs. Although R was initially intended for statistical programming, over the last 7 to 8 years it has evolved into a mature, multifaceted language with enhanced support for a diverse range of related disciplines such as machine learning, high performance computing, visualization, econometrics, TimeSeries analysis, and much more. Some of these areas are also described with accompanying information at https://cran.r-project.org/web/views/.

A commercial version of R with enterprise support was available from Revolution Analytics. In 2015, it was rebranded as Microsoft R Open (open-source version) and Microsoft R Server (commercial version).

Although marketed under the Microsoft brand, note that Microsoft R is also available for Linux and Mac OS.

Popular machine learning packages in R include e1071, randomForest, gbm, kernlab, arules, and many more. These are listed at https://cran.r-project.org/web/views/MachineLearning.html. Another popular package, called caret, acts as a wrapper around various algorithm packages and provides a useful unified interface to run algorithms without having to conform to the nuances of the packages individually.

R also supports multicore programming via packages such as multicore, doMC, and others. These are listed at https://cran.r-project.org/web/views/HighPerformanceComputing.html.