R (programming language)

From Wikipedia, the free encyclopedia
  (Redirected from R Statistics)
Jump to: navigation, search
For other uses, see R (disambiguation).
R
Rlogo.png
Paradigm(s) multi-paradigm: array, object-oriented, imperative, functional, procedural, reflective
Designed by Ross Ihaka and Robert Gentleman
Developer R Development Core Team
Appeared in 1993[1]
Stable release 3.1.1 / July 10, 2014; 3 months ago (2014-07-10)
Preview release Through Subversion
Typing discipline Dynamic
Influenced by S, Scheme, XLispStat
OS Cross-platform
License GNU General Public License
Website www.r-project.org

R is a free software programming language and software environment for statistical computing and graphics. The R language is widely used among statisticians and data miners for developing statistical software[2][3] and data analysis.[3] Polls and surveys of data miners are showing R's popularity has increased substantially in recent years.[4][5][6]

R is an implementation of the S programming language combined with lexical scoping semantics inspired by Scheme. S was created by John Chambers while at Bell Labs. R was created by Ross Ihaka and Robert Gentleman[7] at the University of Auckland, New Zealand, and is currently developed by the R Development Core Team, of which Chambers is a member. R is named partly after the first names of the first two R authors and partly as a play on the name of S.[8]

R is a GNU project.[9][10] The source code for the R software environment is written primarily in C, Fortran, and R.[11] R is freely available under the GNU General Public License, and pre-compiled binary versions are provided for various operating systems. R uses a command line interface; however, several graphical user interfaces are available for use with R.

Statistical features[edit]

R provides a wide variety of statistical and graphical techniques, including linear and nonlinear modeling, classical statistical tests, time-series analysis, classification, clustering, and others. R is easily extensible through functions and extensions, and the R community is noted for its active contributions in terms of packages. There are some important differences, but much code written for S runs unaltered. Many of R's standard functions are written in R itself, which makes it easy for users to follow the algorithmic choices made. For computationally intensive tasks, C, C++, and Fortran code can be linked and called at run time. Advanced users can write C, C++,[12] Java,[13] .NET [14][15][16] or Python code to manipulate R objects directly.

R is highly extensible through the use of user-submitted packages for specific functions or specific areas of study. Due to its S heritage, R has stronger object-oriented programming facilities than most statistical computing languages. Extending R is also eased by its lexical scoping rules.[17]

Another strength of R is static graphics, which can produce publication-quality graphs, including mathematical symbols. Dynamic and interactive graphics are available through additional packages.[18]

R has its own LaTeX-like documentation format, which is used to supply comprehensive documentation, both on-line in a number of formats and in hard copy.

Programming features[edit]

R is an interpreted language; users typically access it through a command-line interpreter. If a user types "2+2" at the R command prompt and presses enter, the computer replies with "4", as shown below:

> 2+2
[1] 4

Like other similar languages such as APL and MATLAB, R supports matrix arithmetic. R's data structures include vectors, matrices, arrays, data frames (similar to tables in a relational database) and lists.[19] R's extensible object system includes objects for (among others): regression models, time-series and geo-spatial coordinates. The scalar data type was never a data structure of R.[20] A scalar is represented as a vector with length one in R.

R supports procedural programming with functions and, for some functions, object-oriented programming with generic functions. A generic function acts differently depending on the type of arguments passed to it. In other words, the generic function dispatches the function (method) specific to that type of object. For example, R has a generic print() function that can print almost every type of object in R with a simple "print(objectname)" syntax.

Although used mainly by statisticians and other practitioners requiring an environment for statistical computation and software development, R can also operate as a general matrix calculation toolbox – with performance benchmarks comparable to GNU Octave or MATLAB.[21]

Examples[edit]

Example 1[edit]

The following examples illustrate the basic syntax of the language and use of the command-line interface.

In R, the widely preferred[22][23][24][25] assignment operator is an arrow made from two characters "<-", although "=" can be used instead.[26]

> x <- c(1,2,3,4,5,6)   # Create ordered collection (vector)
> y <- x^2              # Square the elements of x
> print(y)              # print (vector) y
[1]  1  4  9 16 25 36
> mean(y)               # Calculate average (arithmetic mean) of (vector) y; result is scalar
[1] 15.16667
> var(y)                # Calculate sample variance
[1] 178.9667
> lm_1 <- lm(y ~ x)     # Fit a linear regression model "y = f(x)" or "y = B0 + (B1 * x)"
                        # store the results as lm_1
> print(lm_1)           # Print the model from the (linear model object) lm_1
 
Call:
lm(formula = y ~ x)
 
Coefficients:
(Intercept)            x
     -9.333        7.000
 
> summary(lm_1)          # Compute and print statistics for the fit
                         # of the (linear model object) lm_1
 
Call:
lm(formula = y ~ x)
 
Residuals:
1       2       3       4       5       6
3.3333 -0.6667 -2.6667 -2.6667 -0.6667  3.3333
 
Coefficients:
            Estimate Std. Error t value Pr(>|t|)
(Intercept)  -9.3333     2.8441  -3.282 0.030453 *
x             7.0000     0.7303   9.585 0.000662 ***
---
Signif. codes:  0***0.001**0.01*0.05 ‘.’ 0.1 ‘ ’ 1
 
Residual standard error: 3.055 on 4 degrees of freedom
Multiple R-squared: 0.9583,	Adjusted R-squared: 0.9478
F-statistic: 91.88 on 1 and 4 DF,  p-value: 0.000662
 
> par(mfrow=c(2, 2))     # Request 2x2 plot layout
> plot(lm_1)             # Diagnostic plot of regression model

Diagnostic graphs produced by plot.lm() function. Features include mathematical notation in axis labels, as at lower left.

Example 2[edit]

Short R code calculating Mandelbrot set through the first 20 iterations of equation z = z² + c plotted for different complex constants c. This example demonstrates:

  • use of community-developed external libraries (called packages), in this case caTools package
  • handling of complex numbers
  • multidimensional arrays of numbers used as basic data type, see variables C, Z and X.
library(caTools)         # external package providing write.gif function
jet.colors <- colorRampPalette(c("#00007F", "blue", "#007FFF", "cyan", "#7FFF7F",
                                 "yellow", "#FF7F00", "red", "#7F0000"))
m <- 1000                # define size
C <- complex( real=rep(seq(-1.8,0.6, length.out=m), each=m ),
              imag=rep(seq(-1.2,1.2, length.out=m), m ) )
C <- matrix(C,m,m)       # reshape as square matrix of complex numbers
Z <- 0                   # initialize Z to zero
X <- array(0, c(m,m,20)) # initialize output 3D array
for (k in 1:20) {        # loop with 20 iterations
  Z <- Z^2+C             # the central difference equation
  X[,,k] <- exp(-abs(Z)) # capture results
}
write.gif(X, "Mandelbrot.gif", col=jet.colors, delay=800)

"Mandelbrot.gif" – Graphics created in R with 14 lines of code in Example 2

Example 3[edit]

The ease of function creation by the user is one of the strengths of using R. Objects remain local to the function, which can be returned as any data type.[27] Below is an example of the structure of a function:

functionname <- function(arg1, arg2, ... ){ # declare name of function and function arguments
statements                                  # declare statements
return(object)                              # declare object data type
}
 
sumofsquares <- function(x){ # a user-created function 
  return(sum(x^2))           # return the sum of squares of the elements of vector x
}
> sumofsquares(1:3)
[1] 14

Packages[edit]

The capabilities of R are extended through user-created packages, which allow specialized statistical techniques, graphical devices (ggplot2), import/export capabilities, reporting tools (knitr, Sweave), etc. These packages are developed primarily in R, and sometimes in Java, C and Fortran. A core set of packages is included with the installation of R, with more than 5,800 additional packages and 120,000 functions (as of June 2014) available at the Comprehensive R Archive Network (CRAN), Bioconductor, and other repositories. [6][28]

The "Task Views" page (subject list) on the CRAN website[29] lists a wide range of tasks (in fields such as Finance, Genetics, High Performance Computing, Machine Learning, Medical Imaging, Social Sciences and Spatial Statistics) to which R has been applied and for which packages are available. R has also been identified by the FDA as suitable for interpreting data from clinical research.[30]

Other R package resources include Crantastic, a community site for rating and reviewing all CRAN packages, and R-Forge, a central platform for the collaborative development of R packages, R-related software, and projects. R-Forge also hosts many unpublished beta packages, and development versions of CRAN packages.

The Bioconductor project provides R packages for the analysis of genomic data, such as Affymetrix and cDNA microarray object-oriented data-handling and analysis tools, and has started to provide tools for analysis of data from next-generation high-throughput sequencing methods.

Reproducible research and automated report generation can be accomplished with packages that support execution of R code embedded within LaTeX, OpenDocument format and other markups.[31]

Milestones[edit]

The full list of changes is maintained in the "R News" file at CRAN.[32] Some highlights are listed below.

  • Version 0.16 – This is the last alpha version developed primarily by Ihaka and Gentleman. Much of the basic functionality from the "White Book" (see S history) was implemented. The mailing lists commenced on April 1, 1997.
  • Version 0.49 – April 23, 1997 – This is the oldest available source release, and compiles on a limited number of Unix-like platforms. CRAN is started on this date, with 3 mirrors that initially hosted 12 packages. Alpha versions of R for Microsoft Windows and Mac OS are made available shortly after this version.
  • Version 0.60 – December 5, 1997 – R becomes an official part of the GNU Project. The code is hosted and maintained on CVS.
  • Version 1.0.0 – February 29, 2000 – Considered by its developers stable enough for production use.[33]
  • Version 1.4.0 – S4 methods are introduced and the first version for Mac OS X is made available soon after.
  • Version 2.0.0 – October 4, 2004 – Introduced lazy loading, which enables fast loading of data with minimal expense of system memory.
  • Version 2.1.0 – Support for UTF-8 encoding, and the beginnings of internationalization and localization for different languages.
  • Version 2.11.0 – April 22, 2010 – Support for Windows 64 bit systems.
  • Version 2.13.0 – April 14, 2011 – Adding a new compiler function that allows speeding up functions by converting them to byte-code.
  • Version 2.14.0 – October 31, 2011 – Added mandatory namespaces for packages. Added a new parallel package.
  • Version 2.15.0 – March 30, 2012 – New load balancing functions. Improved serialization speed for long vectors.
  • Version 3.0.0 – April 3, 2013 – Support for numeric index values 231 and larger on 64 bit systems.

Interfaces[edit]

Graphical user interfaces[edit]

  • RStudio – cross-platform open source IDE (which can also be run on a remote linux server).
  • Deducer[34] – GUI for menu driven data analysis (similar to SPSS/JMP/Minitab).
  • Java GUI for R – cross-platform stand-alone R terminal and editor based on Java (also known as JGR).
  • Rattle GUI – cross-platform GUI based on RGtk2 and specifically designed for data mining.
  • R Commander – cross-platform menu-driven GUI based on tcltk (several plug-ins to Rcmdr are also available).
  • Revolution Analytics provides a Visual Studio based IDE and has plans for web based point and click interface.
  • RGUI – comes with the pre-compiled version of R for Microsoft Windows.
  • RKWard – extensible GUI and IDE for R.
  • RWeka[35] – allows for the use of the data mining capabilities in Weka and statistical analysis in R.

There is a special issue of the Journal of Statistical Software that discusses GUIs for R.[36]

Editors and IDEs[edit]

Text editors and Integrated development environments (IDEs) with some support for R include: ConTEXT, Eclipse (StatET),[37] Emacs (Emacs Speaks Statistics), LyX (modules for knitr and Sweave), Vim, jEdit,[38] Kate,[39] Revolution R Enterprise DevelopR (part of Revolution R Enterprise),[40] RStudio,[41] Sublime Text, TextMate, WinEdt (R Package RWinEdt), Tinn-R and Notepad++.[42]

Scripting languages[edit]

R functionality has been made accessible from several scripting languages such as Python,[43] Perl,[44] Ruby,[45] and F#.[46] PL/R can be used alongside, or instead of, the PL/pgSQL scripting language in the PostgreSQL and Greenplum database management system. Scripting in R itself is possible via littler.[47]

useR! conferences[edit]

"useR!" is the name given to the official annual gathering of R users. The first such event was useR! 2004 in May 2004, Vienna, Austria.[48] After skipping 2005, the useR conference has been held annually, usually alternating between locations in Europe and North America.[49] Subsequent conferences were:

  • useR! 2006, Vienna, Austria
  • useR! 2007, Ames, Iowa, USA
  • useR! 2008, Dortmund, Germany
  • useR! 2009, Rennes, France
  • useR! 2010, Gaithersburg, Maryland, USA
  • useR! 2011, Coventry, United Kingdom
  • useR! 2012, Nashville, Tennessee, USA
  • useR! 2013, Albacete, Spain
  • useR! 2014, Los Angeles, USA

Comparison with SAS, SPSS and Stata[edit]

The general consensus is that R compares well with other popular statistical packages, such as SAS, SPSS and Stata.[50] In January 2009, the New York Times ran an article about R gaining acceptance among data analysts and presenting a potential threat for the market share occupied by commercial statistical packages, such as SAS.[51][52]

Commercial support for R[edit]

In 2007, Revolution Analytics was founded to provide commercial support for Revolution R, its distribution of R, which also includes components developed by the company. Major additional components include: ParallelR, the R Productivity Environment IDE, RevoScaleR (for big data analysis), RevoDeployR, web services framework, and the ability for reading and writing data in the SAS file format.[53]

In October 2011, Oracle announced the Big Data Appliance, which integrates R, Apache Hadoop, Oracle Linux, and a NoSQL database with the Exadata hardware.[54][55][56] Oracle R Enterprise[57] is now one of two components of the "Oracle Advanced Analytics Option"[58] (the other component is Oracle Data Mining).

IBM offers support for in-Hadoop execution of R,[59] and provides a programming model for massively parallel in-database analytics in R.[60]

Other major commercial software systems supporting connections to or integration with R include: JMP,[61] Mathematica,[62] MATLAB,[63] Spotfire,[64] SPSS,[65] STATISTICA,[66] Platform Symphony,[67] and SAS.[68]

Tibco offers a runtime version R as a part of Spotfire.[69]

See also[edit]

References[edit]

  1. ^ Ihaka, Ross (1998). R : Past and Future History. Interface98 (Technical report). Statistics Department, The University of Auckland, Auckland, New Zealand. 
  2. ^ Fox, John and Andersen, Robert (January 2005). "Using the R Statistical Computing Environment to Teach Social Statistics Courses" (PDF). Department of Sociology, McMaster University. Retrieved 2006-08-03. 
  3. ^ a b Vance, Ashlee (2009-01-06). "Data Analysts Captivated by R's Power". New York Times. Retrieved 2009-04-28. "R is also the name of a popular programming language used by a growing number of data analysts inside corporations and academia. It is becoming their lingua franca..." 
  4. ^ David Smith (2012); R Tops Data Mining Software Poll, Java Developers Journal, May 31, 2012.
  5. ^ Karl Rexer, Heather Allen, & Paul Gearan (2011); 2011 Data Miner Survey Summary, presented at Predictive Analytics World, Oct. 2011.
  6. ^ a b Robert A. Muenchen (2012). "The Popularity of Data Analysis Software". 
  7. ^ Gentleman, Robert (9 December 2006). "Individual Expertise profile of Robert Gentleman". Archived from the original on 23 July 2011. Retrieved 2009-07-20. 
  8. ^ Kurt Hornik. The R FAQ: Why is R named R?. ISBN 3-900051-08-9. Retrieved 2008-01-29. 
  9. ^ "GNU R". Free Software Foundation (FSF) Free Software Directory. 19 July 2010. Retrieved 13 November 2012. 
  10. ^ R Project (n.d.). "What is R?". Retrieved 2009-04-28. 
  11. ^ "Wrathematics" (27 August 2011). "How Much of R Is Written in R". librestats. Retrieved 2011-12-01. 
  12. ^ Eddelbuettel, Dirk; Francois, Romain (2011). "Rcpp: Seamless R and C++ Integration". Journal of Statistical Software 40 (8). 
  13. ^ Temple Lang, Duncan (6 November 2010). "Calling R from Java". Nuiton. Retrieved 18 September 2013. 
  14. ^ "Making GUIs using C# and R with the help of R.NET". 
  15. ^ "R.NET homepage". 
  16. ^ "An Rserve Client Implementation for CLI/.NET". 
  17. ^ Jackman, Simon (Spring 2003). "R For the Political Methodologist" (PDF). The Political Methodologist (Political Methodology Section, American Political Science Association) 11 (1): 20–22. Archived from the original on 2006-07-21. Retrieved 2006-08-03. 
  18. ^ "CRAN Task View: Graphic Displays & Dynamic Graphics & Graphic Devices & Visualization". The Comprehensive R Archive Network. Retrieved 2011-08-01. 
  19. ^ Dalgaard, Peter (2002). Introductory Statistics with R. New York, Berlin, Heidelberg: Springer-Verlag. pp. 10–18, 34. ISBN 0387954759. 
  20. ^ Ihaka, Ross; Gentlman, Robert (Sep 1996). "R: A Language for Data Analysis and Graphics". Journal of Computational and Graphical Statistics (American Statistical Association) 5 (3): 299–314. doi:10.2307/1390807. Retrieved 12 May 2014. 
  21. ^ "Speed comparison of various number crunching packages (version 2)". SciView. 2003. Retrieved 2007-11-03. 
  22. ^ R Development Core Team. "Writing R Extensions". Retrieved 14 June 2012. "[...] we recommend the consistent use of the preferred assignment operator ‘<-’ (rather than ‘=’) for assignment." 
  23. ^ "Google's R Style Guide". Retrieved 14 June 2012. 
  24. ^ Wickham, Hadley. "Style Guide". Retrieved 14 June 2012. 
  25. ^ Bengtsson, Henrik (January 2009). "R Coding Conventions (RCC) – a draft". Retrieved 14 June 2012. 
  26. ^ R Development Core Team. "Assignments with the = Operator". Retrieved 14 June 2012. 
  27. ^ Kabacoff, Robert (2012). "Quick-R: User-Defined Functions". http://www.statmethods.net. Retrieved 28 October 2013. 
  28. ^ "Search all R packages and function manuals | Rdocumentation". Rdocumentation. 2014-06-16. Retrieved 2014-06-16. 
  29. ^ "CRAN Task Views". cran.r-project.org. Retrieved 2014-07-03. 
  30. ^ http://blog.revolutionanalytics.com/2012/06/fda-r-ok.html
  31. ^ CRAN Task View: Reproducible Research
  32. ^ "R News". cran.r-project.org. Retrieved 2014-07-03. 
  33. ^ Peter Dalgaard. "R-1.0.0 is released". Retrieved 2009-06-06. 
  34. ^ "Deducer Manual". www.deducer.org. Retrieved 2014-07-03. 
  35. ^ Hornik, Kurt. "RWeka: An R Interface to Weka. R package version 0.3–17". CRAN (by Kurt Hornik, Achim Zeileis, Torsten Hothorn and Christian Buchta). Retrieved 2009. 
  36. ^ Valero-Mora, Pedro. "Graphical User Interfaces for R". Journal of Statistical Software (by Pedro M. Valero-Mora, and Ruben Ledesma). Retrieved 2014. 
  37. ^ Stephan Wahlbrink. "StatET: Eclipse based IDE for R". Retrieved 2009-09-26. 
  38. ^ Jose Claudio Faria. "R syntax". Retrieved 2007-11-03. 
  39. ^ "Syntax Highlighting". Kate Development Team. Archived from the original on 2008-07-07. Retrieved 2008-07-09. 
  40. ^ "R PEnterprise DevelopR". Revolution Analytics. Retrieved 2014-04-17. 
  41. ^ J. J. Alaire and colleagues. "RStudio: new IDE for R". Retrieved 2011-08-04. 
  42. ^ "NppToR: R in Notepad++". sourceforge.net. 8 May 2013. Retrieved 18 September 2013. 
  43. ^ Gautier, Laurent (21 October 2012). "A simple and efficient access to R from Python". Retrieved 18 September 2013. 
  44. ^ Statistics::R page on CPAN
  45. ^ RSRuby GitHub project
  46. ^ F# R Type Provider
  47. ^ Eddelbuettel, Dirk (14 July 2011). "littler: a scripting front-end for GNU R". Retrieved 18 September 2013. 
  48. ^ "useR! 2004 - The R User Conference". 27 May 2004. Retrieved 18 September 2013. 
  49. ^ R Project (9 August 2013). "R-related Conferences". Retrieved 18 September 2013. 
  50. ^ Burns, Patrick (27 February 2007). "Comparison of R to SAS, Stata and SPSS". Retrieved 18 September 2013. 
  51. ^ Vance, Ashlee (2009-01-07). "Data Analysts Are Mesmerized by the Power of Program R: [Business/Financial Desk]". The New York Times. 
  52. ^ Vance, Ashlee (2009-01-08). "R You Ready for R?". The New York Times. 
  53. ^ Timothy Prickett Morgan (2011); 'Red Hat for stats' goes toe-to-toe with SAS, The Register, February 7, 2011.
  54. ^ Doug Henschen (2012); Oracle Makes Big Data Appliance Move With Cloudera, InformationWeek, January 10, 2012.
  55. ^ Jaikumar Vijayan (2012); Oracle's Big Data Appliance brings focus to bundled approach, ComputerWorld, January 11, 2012.
  56. ^ Timothy Prickett Morgan (2011); Oracle rolls its own NoSQL and Hadoop Oracle rolls its own NoSQL and Hadoop, The Register, October 3, 2011.
  57. ^ Chris Kanaracus (2012); Oracle Stakes Claim in R With Advanced Analytics Launch, PC World, February 8, 2012.
  58. ^ Doug Henschen (2012); Oracle Stakes Claim in R With Advanced Analytics Launch, InformationWeek, April 4, 2012.
  59. ^ "What's New in IBM InfoSphere BigInsights v2.1.2". IBM. Retrieved 8 May 2014. 
  60. ^ "IBM PureData System for Analytics". IBM. Retrieved 8 May 2014. 
  61. ^ JMP (2013). "Analytical Application Development with JMP". SAS Institute Inc. Retrieved 19 September 2013. 
  62. ^ "New in Mathematica 9: Built-in Integration with R". Wolfram. 2013. Retrieved 19 September 2013. 
  63. ^ Henson, Robert (23 July 2013). "MATLAB R Link". The MathWorks, Inc. Retrieved 19 September 2013. 
  64. ^ Gibson, Brendan (8 March 2010). "Spotfire Integration with S+ and R". Spotfire. Retrieved 19 September 2013. 
  65. ^ Clark, Mike (October 2007). "Introduction to SPSS 16". University of North Texas Research and Statistical Support. Retrieved 19 September 2013. 
  66. ^ StatSoft (n.d.). "Using the R Language Platform". StatSoft Inc. Retrieved 20 September 2013. 
  67. ^ Parmar, Onkar (31 March 2011). ""R" integrated with Symphony". Platform Computing Corporation. Retrieved 20 September 2013. 
  68. ^ SAS (11 November 2010). "Calling Functions in the R Language (SAS/IML)". Retrieved 20 September 2013. 
  69. ^ Tibco. "Unleash the agility of R for the Enterprise". Retrieved 15 May 2014. 
  70. ^ Ostrouchov, G., Chen, W.-C., Schmidt, D., Patel, P. (2012). "Programming with Big Data in R". 

External links[edit]

  • Official website of the R project
  • The R wiki, a community wiki for R
  • R books, has extensive list (with brief comments) of R-related books
  • R-bloggers, a daily news site about R, with 10,000+ articles, tutorials and case-studies, contributed by over 450 R bloggers.
  • The R Graphical Manual, a collection of R graphics from all R packages, and an index to all functions in all R packages
  • R Graph Gallery, an extensive collection of examples demonstrating the graphing and graphical design capabilities of R, many with source code
  • R seek, a custom frontend to Google search engine, to assist in finding results related to the R language