DATA MINING Desktop Survival Guide by Graham Williams
Desktop Survival Project Home List of Figures List of Tables Data Mining Data Mining Data Mining with Rattle Introduction Data Transform Explore A Model Building Framework Unsupervised Modelling Two Class Models Multi Class Models Regression Models Text Mining Evaluation and Deployment Moving into R Troubleshooting R for the Data Miner R Data Graphics in R Understanding Data Preparing Data Building Models Evaluating Models Algorithms Apriori Bagging Bayes Classifier Boosting Cluster Analysis Conditional Trees Hierarchical Clustering K-Means K-Nearest Neighbours Linear Models Logistic Regression Neural Networks Support Vector Machines Text Mining Open Products AlphaMiner Borgelt Data Mining Suite KNime R Rattle Weka Closed Products C4.5 Clementine Equbits Foresight GhostMiner InductionEngine ODM Enterprise Miner Statistica Data Miner TreeNet Virtual Predict Appendicies Glossary Bibliography Index

R: An Introduction to the Language

R is a statistical and data mining package consisting of a programming language and a graphics system. It is used throughout this book to illustrate data mining procedures. It is the programming language used to implement the Rattle graphical user interface for data mining in See Chapter 2. If you are moving to R from SAS or SPSS, then you may find the document http://oit.utk.edu/scc/RforSAS&SPSSusers.doc helpful.

In the following sections of this chapter we introduce the basics of R. We will find many examples presented which can be readily copied into an R console to facilitate learning. You will also find many examples on the R-help mailing list at https://stat.ethz.ch/mailman/listinfo/r-help.

Learning by example is a powerful learning paradigm. Motivated by the programming paradigm of ``programming by example'' cypher:1993:watch_what_i_do, the intention is that you will be able to replicate the examples from the book, and then fine tune them to suit your own needs. This, of course, is also one of the underlying principles of Rattle, as described in See Chapter 2, where all of the R commands that are used under the graphical user interface are exposed to the user. This makes it a useful teaching tool in learning R for the specific task of data mining, and also a good memory aid!

So R is a language. The basic modus operandi is to write sentences expressed in this language. After a while you will want to do more than to issue single, simple, commands (sentences), but to write sentences and paragraphs and full novels in the language! R script files (often with the R filename extension) are the place to write scripts. You can re-run your scripts to transform, at will and automatically, your source data into information and knowledge.

This chapter begins with an overview of some of the key advantages (and disadvantages) of using R and continues with a guide to interacting with R. For data mining purposes the recommended interface is the simple to use Rattle (Chapter 2), although more advanced users will prefer the powerful Emacs editor, augmented with the ESS package. Both run under GNU/Linux, Mac/OSX, and MS/Windows. This is a personal preference and you may prefer some of the alternatives we discuss--this freedom of choice is yours.

Direct interaction with R has a steeper learning curve than using GUI based systems, but once into R, performing operations over the same or similar datasets becomes very easy using its programming language interface. For the R beginner, using a GUI like Rattle, where all underlying R commands are available for your perusal and direct pasting into R itself, may be a good first step.

Let's start with some of the advantages with using R:

• R is licensed under the GNU General Public License, with Copyright held by The R Foundation for Statistical Computing. Thus, it is Free Open Source Software, freely available, so that anyone can freely download and install the software and even freely modify the software, or look at the code behind the software to learn how things can be done. Indeed, anyone is welcome to provide bug fixes, code enhancements, and new packages, and the wealth of quality packages available for R is a testament to this approach to software development and sharing.
• R probably has the most complete collection of statistical functions of any statistical or data mining package. New technology and ideas often appear first in R.
• The graphic capabilities of R are outstanding, providing a fully programmable graphics language which surpasses most other statistical and graphical packages.
• A very active email list, with some of the worlds leading statisticians actively responding, is available for anyone to join. Questions are quickly answered and the archive provides a wealth of user solutions and examples. Be sure to read the http://www.R-project.org/posting-guide.htmlPosting Guide first.
• Being open source the R source code is peer reviewed, and anyone is welcome to review it and suggest improvements. Bugs are fixed very quickly. Consequently, R is a rock solid product. New packages provided with R do go through a life cycle, often beginning as somewhat less quality tools, but usually quickly evolving into top quality products.
• R plays well with many other tools, importing data, for example, from CSV files, SAS, and SPSS, or directly from MS/Excel, MS/Access, Oracle, MySQL, and SQLite. It can also produce graphics output in PDF, JPG, PNG, and SVG formats, and table output for L^ATEX and HTML.

Whilst the advantages might flow from the pen with a great deal of enthusiasm, it is useful to note some of the disadvantages or weaknesses of R, even if they are perhaps transitory!

• R is not so easy to use for the novice. There are several simple to use graphical user interfaces (GUIs) for R that encompass point and click interactions, but they generally do not have the polish of the commercial offerings of Clementine (See Chapter ) and SAS/Enterprise Miner (See Chapter ).
• Documentation is sometimes patchy. Whilst there are extensive documents on line and available in books and throughout the Internet, it can sometimes be terse and even impenetrable to the non-statistician. On the other hand, for example, SAS has extensive, self-contained, and often well explained, documentation, readily available to the user. Nonetheless, users do comment that the R documentation is to the point and easy to consult.
• The quality of some packages is less than perfect, although if a package is useful to many people, it will quickly evolve into a very robust product through collaborative efforts.
• There is no one to complain to if something doesn't work - at least no one who has a financial interest in keeping you, the user, as a satisfied customer. Organisations are quite happy to pay major premiums for that apparent peace of mind! Nonetheless, problems are usually dealt with quickly on the mailing list, and bugs disappear with lightning speed.

The remaining sections of this chapter can generally be skipped on a reading through the book, particularly if you are using Rattle. They provide a basic reference guide to using R, and in particular some of its programming capabilities. While chapter  deals in detail with creating data in R, we introduce some of the basics here. The most basic needs include creating simple datasets, and being familiar with the basic data types and programming concepts, and how to get help.

Support further development through the purchase of the PDF version of the book.
Brought to you by Togaware.