This repository contains the codes for feature generation, selection and model building. It is a MAC-MIGS extended project titled 'Data-driven Models for Battery life Prognostics' supervised by Dr Goncalo Dos Reis.
It makes use of the data used in the paper 'Data driven prediciton of battery cycle life before capacity degradation' by K.A. Severson, P.M. Attia, et al. The data is available at https://data.matr.io/1/. Additional information can also be found in more detail in the link.
There are basically four folders and Jupyter notebook files in this repository. They are analysed as follows:
- models contains the saved models (saved as pickle file) built on the combined dataset
- plots cosists of the plots generated from the feature selection and model building processes
- utils contains Python files for all the processes involved in the project
- Jupyter notebooks contains the implementations of various models and visualization of results