## Metric
The evaluation metric for this competition is the Mean Column ROC AUC. This means we treat each column as its own binary classification problem, and calculate the area under curve (AUC) of the receiver operating curve (ROC). It allows us to measure a balance of the false positive and true positive rate. It is elaborated on [here](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html).

The equivalent [sklearn command](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html) used by the Kaggle grader would be: `sklearn.metrics.roc_auc_score(y_ground_truth, y_predicted_probabilities, multi_class='ovr')`

## Submission Format

For every row of data in WILDFIRES_TEST.csv, submission files should contain five columns:
* `id`: contains integers equal to the id's in the WILDFIRES_TEST.csv file
* `P1`: contains the probability (float from 0 to 1) that the label is 1 (natural cause of fire)
* `P2`: contains the probability (float from 0 to 1) that the label is 2 (accidental cause of fire)
* `P3`: contains the probability (float from 0 to 1) that the label is 3 (malicious cause of fire)
* `P4`: contains the probability  float from 0 to 1) that the label is 4 (other cause of fire)

The file should contain a header and have the following format:
```
id,P1,P2,P3,P4
285382,0.16,0.64,0.09,0.11
285383,0.17,0.2,0.411,0.219
...
358416,0.53,0.12,0.17,0.18
```