Submissions are evaluated on [log loss](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html).

## Submission File
For each id in the test set, you must predict a probability for each ancestry label. The file should contain a header and have the following format:

|   id |       AFR |      AMR |      EAS |      EUR |       SAS |
|-----|----------|---------|---------|---------|----------|
|  689 | 0.177696  | 0.206956 | 0.211084 | 0.247305 | 0.156959  |
| 1196 | 0.230893  | 0.102298 | 0.24698  | 0.199245 | 0.220584  |
| 1766 | 0.0837201 | 0.478872 | 0.211402 | 0.156158 | 0.0698465 |
| 1898 | 0.051935  | 0.261239 | 0.273983 | 0.235532 | 0.177311  |
| 2071 | 0.0942584 | 0.222179 | 0.136058 | 0.244469 | 0.303035  |

Note that the table is truncated. The submission file should have 1 id column and 5 ancestry columns.