Explanation Dashboard for local explanation throwing KeyError - "intercept" about interpret-community HOT 3 CLOSED

I have the similar problem when trying to produce the local explanation based on Azure AutoML output. Dataset is the "orange juice store" sample data used in the forecasting notebook. I setup the MimicWrapper as per introduced in the AutoML explain page.
It works perfectly with the global explain, but not as expected for the local. Individual feature importance can be obtained in the json format, but I am not able to visualize it:

• If I try to call dashboard, I got the following error (it also throws error when I pass the fitted model parameter)

from interpret_community.widget import ExplanationDashboard
ExplanationDashboard(engineered_local_explainations, datasetX=automl_explainer_setup_obj.X_test_transform)

Full error message is:

ValueError: Unsupported local explanation type, inner error: Traceback (most recent call last):
  File "anaconda3/envs/xxx/lib/python3.6/site-packages/interpret_community/widget/explanation_dashboard_input.py", line 137, in __init__
    local_explanation["intercept"] = self._convert_to_list(local_explanation["intercept"])
KeyError: 'intercept'

• I also cannot call engineered_local_explainations.visualize() method since it doesn't support "DynamicLocalExplain`.

So, what is the best way of viz the local explanation?

from interpret-community.

@nagapavannukala sorry about the issue you are encountering, and sorry about the late reply. Could you give us more details about this issue? What explainer did you use that caused this error? If the dataset is not private, would you be able to share an example that reproduces this issue?

from interpret-community.

@nagapavannukala @xiaolul @saimachi @konabuta I've sent a PR to fix this issue here:
#387

from interpret-community.