Azure automl model explanation using python code

Question

Can anyone please help me on the python code that would return the explanation of a trained model of azure automl? Usually after training a model in azure automl, i am getting the global and summery explanation of the best model from the training, but i want to implement a python code where i can get the other model's explanations using that models name and my compute as the passing parameter. Thank you in advance.

Answer 1

Please refer this article : https://learn.microsoft.com/en-us/azure/machine-learning/how-to-machine-learning-interpretability-automl

This details on how to get explanations

from azureml.train.automl.runtime.automl_explain_utilities import automl_setup_model_explanations

automl_explainer_setup_obj = automl_setup_model_explanations(fitted_model, X=X_train, 
                                                             X_test=X_test, y=y_train, 
                                                             task='classification')

You can get Snapshot of previous ML Run. Click on the Run Name -> Snapshot

Reference :

https://learn.microsoft.com/en-us/azure/machine-learning/concept-azure-machine-learning-architecture#snapshots

https://learn.microsoft.com/en-us/python/api/azureml-core/azureml.core.experiment.experiment?view=azure-ml-py#start-logging--args----kwargs-