Python Catboost: Multiclass F1 score custom metric

Question

How do you find the F1-score for each class of a multiclass Catboost Classifier? I've already read through the documentation and the github repo where someone asks the same question. However, I am unable to figure out the codesmithing to achieve this. I understand that I must use the custom_metric parameter in CatBoostClassifier() but I don't know what arguments are acceptable for custom_metric when I want F1 score for each class of my multiclass dataset.

Suppose you have a toy dataset (from the documentation):

from catboost import Pool
cat_features = [0, 1, 2]
data = [["a","b", 1, 4, 5, 6],
        ["a","b", 4, 5, 6, 7],
        ["c","d", 30, 40, 50, 60]]

label = [0, 1, 2]

from sklearn.model_selection import train_test_split    
X_train, X_test, y_train, y_test = train_test_split(data, labels, test_size=0.2)
train_pool = Pool(X_train, y_train, cat_features=categorical_features_indices)
validate_pool = Pool(X_test, y_test, cat_features=categorical_features_indices)
params = {"loss_function": "MultiClass",
          "depth": symmetric_tree_depth,
          "num_trees": 500,
#           "eval_metric": "F1", # this doesn't work
          "verbose": False}

model = CatBoostClassifier(**params)
model.fit(train_pool, eval_set=validate_pool)

Answer 1

you should use TotalF1

params = {
    'leaf_estimation_method': 'Gradient',
    'learning_rate': 0.01,
    'max_depth': 8,
    'bootstrap_type': 'Bernoulli',
    'objective': 'MultiClass',
    'subsample': 0.8,
    'random_state': 42,
    'verbose': 0,
    "eval_metric" : 'TotalF1',
    "early_stopping_rounds" : 100
    }

https://catboost.ai/docs/concepts/loss-functions-multiclassification.html