8 Services from ml-metrics.x402tookit.com

Computes confusion matrix and derived classification metrics (accuracy, precision, recall, F1, MCC, Cohen's kappa, etc.) from true and predicted labels

Computes binary or multiclass log loss (cross entropy) with epsilon clipping, plus the no-skill uniform baseline and the worst-performing samples.

Sweeps every score threshold for binary classification and returns the best F1, Youden J, and accuracy thresholds with full confusion matrix metrics at each point.

Computes reliability bins, expected calibration error (ECE), maximum calibration error (MCE), and Brier score from binary labels and predicted probabilities.

Computes precision-recall curve points, average precision (step-wise sum), and the baseline for binary classification labels and model scores.

Computes a comprehensive suite of regression evaluation metrics (MAE, MSE, RMSE, R², adjusted R², MAPE, SMAPE, explained variance, median absolute error, max error) from arrays of actual and predicted values.

Computes sentence BLEU (1–4 gram with brevity penalty and optional smoothing) and ROUGE-1, ROUGE-2, ROUGE-L F1/precision/recall scores for a candidate text against one or more reference texts.

Computes ROC curve points and AUC from binary labels and model scores using the Mann-Whitney rank-sum identity, with tie-handling.