This is an early version of a package for extracting features from time series data. The main method implemented in this package is VEST (UnivariateVEST class) which is described in the paper Cerqueira et al., 2020.
The focus of this work is to use a set of statistic to summarise the recent dynamics of time series for forecasting.
Check examples directory for examples on how to use this package.
For citation purposes, please use:
Cerqueira, Vitor, Nuno Moniz, and Carlos Soares. "VEST: Automatic Feature Engineering for Forecasting." arXiv preprint arXiv:2010.07137 (2020).
This package will be uploaded to Python Package Index after some tests. Feedback is appreciated. You can install the package with pip using the source tar
Feel free to contact me at vitor.cerqueira@dal.ca