README authors: Bijaya Adhikari, Xinfeng Xu, and B. Aditya Prakash.
Dated: July 1, 2019. 


This is a reference implementation of the EpiDeep algorithm described in the following paper.

EpiDeep: Exploiting Embeddings for Epidemic Forecasting
Bijaya Adhikari, Xinfeng Xu, Naren Ramakrishnan and B. Aditya Prakash
In the 25TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (KDD 2019), August 2019, Anchorage, Alaska - USA


Given a partially observed influenza season, EpiDeep forecasts the following
1) Next four influenza incidence
2) The peak intensity
3) The peak time
4) The onset

==========================================================================================================================================================================================

Requirement: pytorch and sklearn python packages


To see a Demo: 
   make demo
   
For help: 
   make help
   

Execute:
   python src/main.py 

Example: python src/main.py --start_week 20 --start_year 2000 --end_year 2017 --region National

==========================================================================================================================================================================================
Input:

A csv file with ILINet wILI incidence curve

================================================================================================================================================================================================
Output:

1) CSV file with forecast and evaluations
2) Embeddings of historical seasons


================================================================================================================================================================================================
Contact:

If you have any questions about the code, please contact Bijaya Adhikari at bijaya[at]cs[dot]vt[dot]edu and/or B. Aditya Prakash badityap[at]cs[dot]vt[dot]edu