multiclass problem

[BY-hash]

Hi,

1. How do I get LIME results for a multiclass problem?

When I operate the code from the examples (with y_test which are one-hot encoded vectors) the results I get seems of a binary classification dataset.

2. when I run the example code, I get the following warning:
   "X does not have valid feature names, but GaussianNB was fitted with feature names"
   what does it mean?

Thank you!

The example I'm refering to is :
from interpret.blackbox import LimeTabular
from interpret import show

#Blackbox explainers need a predict function, and optionally a dataset
lime = LimeTabular(predict_fn=blackbox_model.predict_proba, data=X_train, random_state=1)

#Pick the instances to explain, optionally pass in labels if you have them
lime_local = lime.explain_local(X_test[:5], y_test[:5], name='LIME')

show(lime_local)

[paularindam]

I face the same issue.