How to create 'Evaluation Result' directly from 'Table' data？

[xianglun918]

Many analysis widgets in Orange are expecting 'Evaluation Results' as inputs. I need to analyze on results of a complicated DNN, and find that it is hard to generate 'Evaluation Results' based on model's output csv files.

How can I transform 'Table' directly to 'Evaluation Results', say 'Table' already has categorical features including 'true lable' and 'predictions'?

Something Like:

[janezd]

You can't. Evaluation results is not just a table but a more complicated structure, which also contains other data like subset indices, models etc.

[xianglun918]

Understood. Maybe we can have a new widget which mocks 'Evaluation Results' with only 'Table data'? It would be great if Orange can be used to analyze on Pytorch or tensorflow model's results. Many evaluation widgets are verfy useful.

[xianglun918]

Something like this :)

[janezd]

@BlazZupan suggested that we could have a classifier that "predicts" based on values from a column. If the column is numeric, it can also apply logistic function.