R for data analytics (EN/NL/FR)

This 3 day ABIS course will give you hands-on practice with R, both as a data analytics and graphical tool, and as a programming and scripting environment where you can let the system give you any possible insight into your data that you may want.

Intended for whoever wants to start practising data analysis in a "big data" context: developers, data architects, marketeers, and anyone who needs to manipulate, visualize, or summarize their corporate data. This course is also a first introduction to the R programming language, so anyone who wants to start using R or one of its many packages is welcome.

Remark: Course description in English; Dutch and French versions are available on the ABIS website. Courses are planned in Dutch, English, and French. Consult the ABIS website for alternate course formats.

Main Topics - Content: 

Part I - R fundamentals

Getting started

• installing R (Linux / Windows / MAC)
• getting to learn the command line interface and the Rstudio GUI
• first steps with R: interactive commands; obtaining online help
• basic concepts: expressions (numeric, textual); commands & functions; variables & assignment

R basics

• "atomic" data types and how to write their constants: double (numeric), character, integer, logical
• numeric and logical operators
• the special values Inf, NaN, NA, and NULL
• the vector type; operator "c()"; so-called coercing; vector operators
• the "package" concept of R
• CRAN and www.r-project.org

More "structural" data types

• lists (hierarchical data) and matrices

Functions and attributes

• positional and named parameters
• creating your own functions
• R scripts; the startup script; scope of variables; writing comments
• dump, load, source and related commands
• dir, ls, getwd and setwd
• package loading, or using the "::" notation
• control flow: if, while, for
• the explicit "print" function; the "cat" function
• other useful functions: length, names, dimnames, unlist, cbind, rbind, c, as.<type>, is.<type>, order(vector), ...

Part II -- Data analytics with R

Structured data

• Objects and attributes
• lists, names(), dimnames(), factors
• reading / writing (structured) data from/to files: read.table; read.csv; readLines, write.csv, ...
• how to be memory-efficient with large volumes of data
• data frames
• how to use a database as "back store"

Packages

• how to install a (third party) R package
• examples: the "stats" package and the "ggplot2" package
• other useful packages: foreign (for reading/writing data of SAS, SPSS, dBase, etc.); XML; AER; tm; vcd; DBI; RODBC

Statistical techniques

• Random Number Generators
• sampling, summarizing: basic statistical terminology & techniques
• examples from the "stats" package; the lm functions
• plotting statistical graphs (scatter plots, histograms, trend lines, ...)

Audience: Everyone wanting to get some experience working with BigData environments - and R.

Background: Familiarity with the concepts of data stores and 'big data', as well as having notions of statistics. Familiarity with the concepts of a programming language.

Didactics: Classroom instruction with practical exercises.

Duration: 3 days.