There will be an optional Kaggle leader board where we test your predictions against a secret dataset. This is to help you to see how well your models are doing compared with others in the class. 

In the  [`Data`](https://www.kaggle.com/competitions/1dl034-project-vt24/data) section, there is a secondary dataset [`evaluation_dataset.csv`](https://www.kaggle.com/competitions/1dl034-project-vt24/data?select=evaluation_dataset.csv). This dataset does not contain any forest type classes.
Each row has a unique ID. Your task is to categorise this dataset using your trained, tuned model and predict the forest type for each row.
Once done, prepare a CSV file with two columns, first column being the unique ID as it is and the corresponding forest cover category. The file should have 10982 entries.

### Example CSV file for submission
```
ID, Category
nnn, N
nnn, N
....
```

Submit the CSV file and it will be graded automatically.

## Important!
Performance in the Kaggle leader board does not affect your mark of your project. The Kaggle competition is for motivation only, and your goal should not be just to score well on the Kaggle leader board.