Submissions are evaluated on [Hamming Loss](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.hamming_loss.html) - the fraction of the wrong labels to the total number of labels. A lower score is better.

$$
\text{HammingLoss} = \frac{1}{N \cdot L} \sum_{i=1}^{N} \sum_{j=1}^{L} \mathbb{1}\left[ y_{ij} \ne \hat{y}_{ij} \right]
$$



## Submission File
For each ID in the test set, you must predict a binary value for each of the coral species classes (0=absent, 1=present).

 ```
id,species_Porites,species_Fungia,species_Favia...
7789,1,1,0...
6069,1,1,0...
```