Expand description
Evaluation metrics for ML models.
Includes regression metrics (R², MSE, MAE), clustering metrics (inertia, silhouette score), classification metrics (accuracy, precision, recall, F1-score, confusion matrix), ranking metrics (Hit@K, MRR, NDCG), model evaluation framework, and drift detection.
Modules§
- classification
- Classification metrics for evaluating classifier performance.
- drift
- Data drift detection for model retraining triggers.
- evaluator
- Model evaluation framework for comparing multiple models.
- ranking
- Ranking metrics for recommendation and retrieval systems.
Functions§
- inertia
- Computes the inertia (within-cluster sum of squares).
- mae
- Computes the Mean Absolute Error (MAE).
- mse
- Computes the Mean Squared Error (MSE).
- r_
squared - Computes the coefficient of determination (R²).
- rmse
- Computes the Root Mean Squared Error (RMSE).
- silhouette_
score - Computes the silhouette score for clustering quality.