Data sets and scripts for the publication in Energy and Buildings.
This is a repository for data for the publication:
Data driven prediction models of energy use of appliances in a low-energy house. Luis M. Candanedo, Véronique Feldheim, Dominique Deramaix. Energy and Buildings, Volume 140, 1 April 2017, Pages 81-97, ISSN 0378-7788, http://dx.doi.org/10.1016/j.enbuild.2017.01.083.
This repository hosts the experimental measurements for the energy use regression problem. It includes a clear description of the data files.
- Description of the data columns(units etc). See variables description.txt
- The scripts to reproduce exploratory figures.
- The scripts for model training.
- The commands for model testing.
- Also note that when training and testing the models you have to use the seed command to ensure reproducibility. There may be small variations in the reported accuracy.
- Some of the exploratory plots are provided.
Please read the commented lines in the model development file. Install all the packages dependencies before trying to train and test the models.
It is advised to execute each command one by one in case you find any errors/warnings about a missing package.
Please do not forget to cite the publication! Thank you!
Keywords: Appliances, energy, prediction, wireless sensor network, statistical learning models, data mining, random forest, GBM, SVM-radial,