You are required to apply the following clustering techniques using the WEKA software on only 10 of the datasets you selected in task 1:
(2) Agglomeration method
Remove the class attribute before applying the above clustering methods.Once you have applied the clustering techniques on all the datasets, it is required to accomplish the following tasks:
- Use the clustering evaluation methods to compare the performance of the above algorithms
- Write a report of no longer than 500 words detailing the results you have reached in (1) and (2) with recommendations on the choice of the data mining technique according to the features of the datasets.
Deliverables of this component of the coursework are:
You are to write a report addressing the aforementioned tasks in no more than 1500 (1000 classification + 500 clustering) words excluding figures and tables. Your report must cover the following areas:
- A short summary of the datasets you used and the justification of choice.
- A detailed analysis of your results when comparing the different classification/clustering techniques.
The submission is online through Moodle (the submission details will be available on Moodle).
This component (task 1 and 2) of your coursework contributes 60% of the total mark (40% Task I and 20% Task 2) for the unit assessment. The marking criteria [in 100% breakup of marks] for this component are as follows:
20%Justification of choice and number of the datasets used
20%Appropriate use of tables and figures when reporting the results
30%Analysis of the results of the experiments you have conducted
20%Conclusion with recommendations on how to match a dataset to a technique
10%Organisation, language style and clarity
Last Updated on July 3, 2019 by EssayPro