Computer Lab

The purpose of the practical assignments is to develop basic skills in the analysis of data with some of the techniques discussed in this course. You are going to write your own classification tree program, and use it to analyse a data set. All this will be done in R, a free software environment for statistical computing and graphics. During the lab sessions, you can work on the practical assignments. A staff member will be present during these sessions to provide help with R and the R language.

To start R on a computer in the computer lab, go to:
Start -> All Programs -> Standard Applications -> Science -> Biology ->
R for Windows 3.3.1 and then R for Windows or Rstudio

Short R tutorial to get started

  • If you never programmed in R before, we recommend you use the package "swirl" to learn the basics. To install swirl on your laptop, look here (Steps 3 and 4). To install and load swirl (and other packages) on the university machines, please specify a directory where you are allowed to write. For example (in R):
     > install.packages(pkgs="swirl",lib="U:/R/libraries")
     > library("swirl",lib.loc="U:/R/libraries")
    
    Start swirl, and choose the course "R Programming".
    You kan skip lessons 2: "Workspace and Files" and 14: "Dates and Times".
  • Getting started with the assignment in R.
  • The credit data.

Useful R links

  • To install R on your own laptop, go here.
  • R Studio is an IDE for R. It is warmly recommended.

Assignment 1: Classification Trees and Random Forests (deadline: Friday, October 13th, 2017)

The assignment should be handed in through EduCode.

  • The assignment.
  • Download the data for part 2 of the assignment here.
  • The accompanying article can be found here.

Assignment 2: Text Mining (deadline: Friday, November 3rd, 2017)

The assignment should be handed in through EduCode.