R Programming Language

R is one of the popular languages for reporting, statistical analysis and graphical representation (Tutorials Point, 2019). R offers loops, user defined functions, conditions and I/O facilities like other effective programming languages with efficient data handling and storage capabilities. Calculations can be performed on data structures, arrays, metrics, lists and vectors in R. Large collection of R tools offer strong data analytical and display capabilities (2019). Krill (2015) highlighted the two packages, namely dplyr and ggplot2 for data manipulation and plotting respectively which are very popular and efficient for data representation. R has strong machine learning capabilities as well (Krill, 2015). On the other hand, R being an interpreted language which is why execution speed is slower compared to compiler-based programming languages (2015).

Smith (2012) highlighted that R excels as a programming language due to features like object-oriented programming, input/output support, distributed computing and support of thousands of packages. For data analytics, R offers basic mathematics, statistical modeling and tests, signal processing, probability distributions, data mining, and machine learning capabilities. Both dynamic and static graphics are supported by R (Smith, 2012). For machine learning and predictive analysis, R has various packages for decision trees, linear and non-linear regression, linear and non-linear classification and so on (Data Mentor, 2019)

R reads data into memory, which is why very large data sets can become problematic for R (Pradeep & Moy, 2015). However, R offers solutions to handle very large data set by reducing the input file using fewer number of rows and columns, parallel processing. For datasets greater than 10GB, variants of R like RHadoop and Rhipe leverage Hadoop distributed and MapReduce framework respectively for processing (Pradeep & Moy, 2015). Data wrangling, that is preparation of data for analysis is relatively easy in R as it supports input data in the .csv, excel and database tables (Edanz, 2018). Support of deep learning methods like neural networks, Keras and Tensorflow as well as Time series besides several machine learning algorithms, R provides a strong big data analytical environment for data processing, analysis, and graphical representation (University of Cincinnati, 2019).

References:

Edanz (2018). Powerful benefits of using R to analyze your research data (and a few limitations). Retrieved from https://www.edanzediting.com/blogs/powerful-benefits-using-r-analyze-your-research-data-and-few-limitations

University of Cincinnati (2019). UC Business analytics R programming guide – predictive analytics. Retrieved from http://uc-r.github.io/predictive

Pradeep & Moy (2015). Handling large data sets in R. Retrieved from https://rpubs.com/msundar/large_data_analysis

Data Mentor (2019). Learning R Programming – The Definitive Guide. Retrieved from https://www.datamentor.io/r-programming/

Krill, P. (2015) Why R? The pros and cons of the R language. Retrieved from https://www.infoworld.com/article/2940864/application-development/r-programming-language-statistical-data-analysis.html

Tutorials Point (2019). R – Overview. Retrieved from https://www.tutorialspoint.com/r/r_overview.htm