Interim report: By 9 am on 27 February you must email me (a.storkey ... Final due
date: Evaluation of the work on the mini project will be by a written report. This.
Data Mining and Exploration Instructions for Mini Project School of Informatics, University of Edinburgh
Instructor: Amos Storkey March 2009 Selection: You must have an ordered list of projects for the lecture on the 31st January. If you are doing this as a group, please also have organised the group. Interim report: By 9 am on 27 February you must email me (a.storkey @ ed.ac.uk) a 1-page ascii description of your progress so far and your plans for completion of the mini-project by the final deadline. Final due date: Evaluation of the work on the mini project will be by a written report. This is due by manual submission to ITO by 4pm on 27 March. Late penalties: The policy of the School of Informatics is that no late submissions are allowed except on valid ground agreed a priori with the year organiser. Computing resources The machines statler.inf, waldorf.inf, goshawk.inf and goldfinch.inf are available for DME students (as well as the usual computational resources you have access to). One these machines there are directories /disk/data1/workspace and /disk/data2/workspace; each can hold up to 65GB. However, not that these areas are not backed up. Important information such as programs to carry out tasks like data format conversions or results of computations should be stored in your usual, backed-up filespace areas. After students have made their selections, the allocation of datasets will be available from the DME webpage. For each dataset, the datasets webpage clearly gives a description of the task to be undertaken. I would expect the mini-project to take you around 30 hours work. The report. The report should be around 8-12 pages in length of single spaced text. The following headings are likely to be useful. • Abstract • Overview of the task • Previous work (literature review) • Data preparation • Exploratory Data Analysis • Supervised learning methods used 1
• Results, evaluation • Conclusions Marking Breakdown A Well explained description of points above plus extra achievement at understanding or analysis of results. Clear explanations, evidence of creative or deeper thought will contribute to a higher grade. B Well explained description of points above. C Good description of points above but significant deficiencies. D Evidence that the student has gained some understanding, but not addressed that specified task properly. E/F/G serious error or slack work. Plagiarism policy The projects are (usually) group projects. Hence you are welcome to discuss the work within the group you are working in. Furthermore you can work together on the project. The assessment is entirely on the write-up of the project. The project write-up must be entirely your own. You should write up the project as a whole, including the work of the others in your project. You should clearly state which members of the team did which parts of the work, and exactly how the work was distributed. You should not borrow written work from others, or base your written work on others written work, except in as much as the results of the work of other team members is written down (e.g. tables, figures). You should not claim the work of others as your own, and where you use a specific item (e.g. table/figure) from one of your coworkers you should mention it. See http://www.informatics.ed.ac.uk/admin/ITO/DivisionalGuidelinesPlagiarism.html for further information.
