dreamquark-ai / tabnet

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf
https://dreamquark-ai.github.io/tabnet/
MIT License
2.55k stars 470 forks source link

Adding sklearn Classification Report #496

Open rawanmahdi opened 1 year ago

rawanmahdi commented 1 year ago

Working with a skewed dataset, it may be helpful to view the precision and f1 scores of the model in addition to the other metrics nativley supported.

What kind of change does this PR introduce? This PR provides the option for the user to pass in "classification_report" as one of the metrics to select to view for their model.

Does this PR introduce a breaking change? I dont think so.

What needs to be documented once your changes are merged? That classification reports are one of the optional default metrics, and can be requested under the string "classification_report". Documentation in the 'metrics.py' file have been updated as part of this PR.

Closing issues closes #489