Closed DomMcOyle closed 1 year ago
Tests should be produced also on the multicultural split.
It is necessary to build a custom F1 function in order to obtain scores.
Custom function for producing results (both macro-aggregation and per-class) was implemented. Closing this issue.
scoring of the models must be done on basis of F1 score/precision/recall macro on the test and validation splits. Probably it will be useful to tune a threshold for discretization of labels if the model produces a different probablility for each class.