Metrics

All registered Metric components in DashAI.

Name	Description
Accuracy	Fraction of correctly classified samples over all predictions.
Bleu	A class for calculating BLEU scores between source and target sentences.
Chrf	A class for calculating CHRF scores between source and target sentences.
CohenKappa	Agreement between classifier predictions and true labels beyond chance.
ExplainedVariance	Proportion of the target variance explained by the regression model.
F1	Harmonic mean of precision and recall.
HammingDistance	Fraction of labels that are incorrectly predicted (Hamming loss).
LogLoss	Negative log-likelihood of true labels under the predicted probability distribution.
MAE	Average of absolute differences between predicted and true values.
MSE	Average of squared differences between predicted and true values.
MedianAbsoluteError	Median of absolute differences between predicted and true values.
Precision	Fraction of positive predictions that are actually correct.
R2	Coefficient of determination — goodness of fit for regression models.
RMSE	Square root of the mean squared error between predicted and true values.
ROCAUC	Area under the Receiver Operating Characteristic curve.
Recall	Fraction of actual positives that are correctly identified.
Ter	A class for calculating TER scores between source and target sentences.