Evaluation Metric
The competition will use the Macro F1-Score as the evaluation metric. This metric ensures equal weight is given to all classes, regardless of any class imbalance in the dataset.

Why Macro F1-Score?
It evaluates the model's precision and recall for each class independently.
It provides a holistic view of model performance across all labels.
It is robust to class imbalances in multi-class classification tasks.

from sklearn.metrics import f1_score
# Compute Macro F1-Score
f1 = f1_score(y_true, y_pred, average='macro')
print("Macro F1-Score:", f1)