
MREF package Version 0.2 (June, 2018) (Matlab code)

------------------------------------

Copyright (c) 2018 Liang Zhao
George Mason University
lzhao9@gmu.edu

Please cite the following paper in any work that uses this material:

Liang Zhao, Feng Chen, Chang-Tien Lu, and Naren Ramakrishnan. "Multi-resolution Spatial Event Forecasting in Social Media." in Proceedings of the IEEE International Conference on Data Mining (ICDM 2016), regular paper, (acceptance rate: 8.5%), pp. 689-698, Barcelona, Spain, Dec 2016.

@inproceedings{zhao2016multi,
  title={Multi-resolution spatial event forecasting in social media},
  author={Zhao, Liang and Chen, Feng and Lu, Chang-Tien and Ramakrishnan, Naren},
  booktitle={2016 IEEE 16th International Conference on Data Mining (ICDM)},
  pages={689--698},
  year={2016},
  organization={IEEE}
}

Together with this README file are the codes and part of the data.

---------------
ENVIRONMENT: 
---------------
Matlab (with version on or newer than 2011)


---------------
INSTALLATION: 
---------------

1. open Matlab, then set the package folder as the current path of Matlab.
2. Run in Matlab the following line:
>> addpath(genpath(pwd));

---------------
EXAMPLE RUN:
---------------
1. Train:

>> [W,P,Q] = tree_level_lasso_v02(XY_tr,1);

2. Test:

(Use the W as the optimized weight for your classification/regression on test set)


---------------
DATA FORMAT: 
---------------
Please refer to the comments in file 'tree_level_lasso_v02.m' for the format of the data in data_paraguay.mat

If any problem, please contact Liang Zhao via lzhao9@gmu.edu.
