This is the competition for the CHE609 machine learning workshop. 

You can team up and build the best models to predict the high-pressure carbon dioxide uptake in MOFs!
We didn't provide you with all the data---we use this data to test the generalization performance of the model. 

## Getting started
1. Download the file with the features (they are also in the `data` folder on GitHub) 
2. Use your model to make predictions and create a submission `.csv`
3. Upload your prediction

Your submissions will be evaluated based on the mean absolute error on the subset from the same [database you used for training](https://www.nature.com/articles/s41586-019-1798-7#article-comments). 

Feel free to explore any model architecture you wish---the only goal here is to get the best prediction with the given features. 

## Acknowledgment
We thank Leopold Talirz for incredibly valuable feedback on the exercises.
The ChE609 course is supported by the ACT-funded project [PrISMa](https://prisma.hw.ac.uk/outreach-2/), in which we focus on the use of adsorption to capture CO2