Project Information

This is the repository of EE660 final project.

• Final project report ------ see Project.pdf (Project.tex is generated from R)
• Programs for this project has two parts:

1. The first part (getting & cleaning data, explorotary research) is in Project.Rmd. After preprocessing, the data is saved as training.csv and test.csv in this reposotory. (Other .R files are functions write by myself for preprocessing data.)
2. The second part (classification, further analysis) is in Project.ipynb.

• Data and relevant paper are in http://www.hindawi.com/journals/bmri/2014/781670/.
• The downloaded data are diabetic_data.csv and IDs_mapping.csv in this repository. (asi.csv,ati.csv and ddi.csv are files generated from IDs_mapping.csv, since there are three different types of ID in the original IDs_maping.csv.)
• Project_cache and Project.Rdata are cache files for R to speed up.
• Other informations, please see Project.pdf.