search

scikit-learn-contrib / DESlib

A Python library for dynamic classifier and ensemble selection
BSD 3-Clause "New" or "Revised" License
479 stars 106 forks source link

For LCA, what if the samples with the class is not amongst the neighbour? #205

Closed jayahm closed 4 years ago

jayahm commented 4 years ago

I'm wondering for LCA.

Since the local accuracy is estimated in respect of output classes assigned by a particular classifier, what if the local region of a test sample does not have the validation sample with that class label in the region?

Is this possible to happen?

If yes, how your implementation for LCA can handle this?

Menelau commented 4 years ago

Yes, it is possible to happen. In this case, the competence level of this base classifier is set to zero

Em qui., 6 de ago. de 2020 às 21:48, jayahm notifications@github.com escreveu:

I'm wondering for LCA.

Since the local accuracy is estimated in respect of output classes assigned by a particular classifier, what if the local region of a test sample does not have the validation sample with that class label in the region?

Is this possible to happen?

If yes, how your implementation for LCA can handle this?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/scikit-learn-contrib/DESlib/issues/205, or unsubscribe https://github.com/notifications/unsubscribe-auth/AD6SFZCMDXOVGSETGS4B7WDR7NMPPANCNFSM4PXE2F2A .

jayahm commented 4 years ago

@Menelau

May I know which part of the library is doing so?

Menelau commented 4 years ago

In the estimate_competence function line 180:

https://github.com/scikit-learn-contrib/DESlib/blob/50e6ba4ddc8f04599937ac0b9913522798dd4b58/deslib/dcs/lca.py#L180