awsm-research / PyExplainer

PyExplainer: A Local Rule-Based Model-Agnostic Technique (Explainable AI)
MIT License
29 stars 9 forks source link

confused dataframe returned from instance generation function #2

Closed oathaha closed 3 years ago

oathaha commented 3 years ago

From the returned value of explain function

   pyExp_rule_obj = {'synthetic_data': synthetic_instances,
                      'synthetic_predictions': synthetic_predictions,
                      'X_explain': X_explain,
                      'y_explain': y_explain,
                      'indep': self.indep,
                      'dep': self.dep,
                      'top_k_positive_rules': top_k_positive_rules,
                      'top_k_negative_rules': top_k_negative_rules}

I found that there is label column ('defect') in synthetic_instances variable like this image

I think this column should not be included in this variable (or dataframe) because the label is already in synthetic_predictions variable.

What do you think about this?

MichaelFu1998-create commented 3 years ago

I agree with your point, let me double-check with my teammate.

MichaelFu1998-create commented 3 years ago

the source code has been modified and uploaded to the repo.