ROC AUC is displaying as none

shankarpandala / lazypredict

Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning

MIT License

2.87k stars 333 forks source link

ROC AUC is displaying as none #354

Open subho22 opened 3 years ago

subho22 commented 3 years ago

xjdeng commented 2 years ago

I struggled with this for a while.. basically, it's only relevant in a binary classification problem.

If your labels are already binary, then make them numbers or True/False. Don't make them strings. This took me a while to figure out until I enabled warnings and verbose=1 and found that the ROC calculation was failing due to failure to convert the labels to floats.