{ "fetched_at": "2026-10-24T17:28:09Z", "source_url": "https://www.kaggle.com/competitions/che609/data", "pages": [ { "name": "rules", "content": " - Don't cheat! \n - Play around!\n - Have fun!\n\n\nYou have a maximum of 10 daily submissions. ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "# File description \n* `features.csv` : contains all feature columns and is in the same format as the files we used for training the models\n* `submission.csv`: example of a submission file ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "This is the competition for the CHE609 machine learning workshop. \n\nYou can team up and build the best models to predict the high-pressure carbon dioxide uptake in MOFs!\nWe didn't provide you with all the data---we use this data to test the generalization performance of the model. \n\n## Getting started\n1. Download the file with the features (they are also in the `data` folder on GitHub) \n2. Use your model to make predictions and create a submission `.csv`\n3. Upload your prediction\n\nYour 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). \n\nFeel free to explore any model architecture you wish---the only goal here is to get the best prediction with the given features. \n\n## Acknowledgment\nWe thank Leopold Talirz for incredibly valuable feedback on the exercises.\nThe 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", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "

The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:

\r\n
\r\n

The evaluation metric for this competition is Mean F1-Score. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:

\r\n

\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]

\r\n

The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.

\r\n

Submission Format

\r\n

For every author in the dataset, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).

\r\n

The file should contain a header and have the following format:

\r\n
AuthorId,DuplicateAuthorIds
1,1
8,8
9,9 10
10,10 9
etc.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }