---
tags: HCMUT
---
Assignment AA202
===

## TODO
---
1. Cleaning and generate test data (label) (**Khanh Nguyen**)

• sv1 = {6, 5, 4}
• sv2 = {1, 7, 8}

- Group data for each class
- Remove duplicate data
- 2 options to encode score:
- Each of columns is score for a week
- Each of columns is score for a question
- **Define test case??**
2. Choose solve (**Nhut Nguyen**)
> Nhut Nguyen:
> All: Please let me know if you have other solver which is the best for us
> Easy to learn and use
> Community

- glpk
- pros:
- free
- Big community support
- cons:
- Using python to generate data following format support by glpk
- cplex (IBM) using student email to download
- pros:
- rich feature support
- cons:
- Hard to find example
- Has higher learning curve
- Gurobi
3. write cplex/glpk model
- model 1 (**Nhut Nguyen**)
- model 2 (**Kenz, Minh Pham**)
4. Apply heristric algorithm (**ALL**)
- Is there any way to optimize? Any ideal, approach?

5. Write report