Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| F1 moyen macro× | F1 pondéré× | |
|---|---|---|
| Domaine | Évaluation de modèles | Évaluation de modèles |
| Famille | MCDM | MCDM |
| Année d'origine | 2000s | 2000s |
| Auteur d'origine | Multi-class evaluation community | Multi-class evaluation community |
| Type | Evaluation metric | Evaluation metric |
| Source fondatrice | Powers, D. M. (2011). Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation. Journal of Machine Learning Technologies, 2(1), 37-63. link ↗ | Powers, D. M. (2011). Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation. Journal of Machine Learning Technologies, 2(1), 37-63. link ↗ |
| Alias≠ | Macro F1, Unweighted average F1 | Support-weighted F1 |
| Apparentées | 3 | 3 |
| Résumé≠ | Macro-averaged F1 computes the F1-score independently for each class and then takes the unweighted arithmetic mean. It treats all classes equally, regardless of their frequency in the dataset, making it useful for imbalanced multi-class problems. | Weighted F1 computes the F1-score for each class and then takes a weighted average, where weights are proportional to the number of samples in each class (support). It provides a middle ground between macro and micro-averaging. |
| ScholarGateJeu de données ↗ |
|
|