Module aim
To investigate the properties of data, how to visualise data, and how pre-proposing can improve the information content of data.
Module learning outcomes
On successful completion of this module the learner will be able to:
- Discuss in depth a variety of data preparation techniques, and their applicability to various problem domains
- Research current trends in data visualisation, and select the appropriate graphical representation for data and results
- Understand the links between data and necessary pre-processing algorithms to improve as well as prepare the data for modelling purposes
- Evaluate appropriate techniques to improve data quality, and be aware of the limitations of such techniques
- Analyse a data set to assess what data preparation is required to both clean the data set and expose its information content
- Highlight information content using data visualisation techniques
- Independently research current trends and developments in data preparation techniques
Indicative module assessment
- Literature reviews and analysis covering a range of topics relevant to the module.
- Apply appropriate data exploration and preprocessing techniques on a dataset selected by the student; report on work done detailing decision made with justification.Practical work can be done using Rapidminer and R, both of which are opensource.