Watson Studio - model builder questions on feature evaluation and getting test/train data for a saved model

Question

I am using Watson Studio Model Builder to build a Linear Regression model.

1. Does it perform any feature evaluation/extraction ? Is there a way to look up this information ? I see some hyperparameters associated with the estimators, but nothing on features. I see something called
2. Is there a way to track/get the training/test data for a deployed model after it has been trained. I read up on lineage but did not see anything there.
3. When using WML to store and deploy a scikit-learn linear regression model, I get back learning_configuration_url, evaluation_metrics_url and feedback_url. Are these accessible using the REST API outside of WML ?

Thank you !

Answer 1

I would recommend checking out AutoAI, the graphical tool in Watson Studio automatically analyzes your data and generates candidate model pipelines customized for your predictive modeling problem and would be a perfect solution for building the Linear Regression Model you had in mind. To learn more check out our documentation: https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/autoai-build-from-sample.html?audience=wdp and demos: https://www.ibm.com/demos/collection/IBM-Watson-Studio-AutoAI/?lc=en about this exciting new feature.