Regression Metrics From Scratch
ROC-AUC From Scratch With Tied Scores
Multi-Class Confusion Matrix and F1 Scores
Precision-Recall Curve and Average Precision
Matthews Correlation and Cohen's Kappa from Scratch
Multi-Label Classification Metrics
Ranking Retrieval Metrics
Dataset-Level MRR and Hit Rate@K
Precision@K and Recall@K for Recommendations
NDCG at K for a Single Query
Mean Average Precision at K
Brier Score and Brier Skill Score
Expected Calibration Error with Bin Statistics
Cost-Minimizing Fraud Decision Threshold
Temperature Scaling for Logit Calibration
Isotonic Regression Calibration via PAV
Significance Fairness Slicing
Bootstrap Confidence Interval for a Metric
Per-Slice Precision and Recall Evaluator
Paired Bootstrap CI for Metric Delta
Demographic Parity and Equalized Odds Metrics
Paired Permutation and McNemar Tests
DeLong Test for Correlated ROC-AUCs
SQuAD Exact Match and F1 Metrics
ROUGE-1, ROUGE-2 and ROUGE-L From Scratch
Word Error Rate with Error Breakdown
Dice and Mean IoU for Segmentation
Box IoU and Detection Average Precision