Feature names Mapping in Sagemaker

0

After create model in Redshift i can load the generated model in python via Sagemaker. The features are generated automatically e.g. f0, f1 and so on. Altough i have only 10 columns i get maybe 500 features. This comes from some categories but where can i see the mapping of the features to the original category names? For example f100 is the category "XY" of column 5.

1 réponse
0

Hi there!

Unfortunately there is no functionality to see the mapping of the features to the original category names. However, SageMaker provides auto-generated notebooks for the data exploration and feature engineering used during SageMaker Autopilot experiment.

As you may already know, Redshift's create model feature extracts the table into your S3 bucket, runs SageMaker Autopilot that does automatic data exploration, feature engineering and model creation.

A limitation of Redshift's create model feature is that there is no where to store these auto-generated notebooks made by SageMaker Autopilot. So to see these notebooks, you have to manually run a SageMaker Autopilot experiment using the SageMaker console.

You can find out more about it using below links:

https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-videos.html#autopilot-walkthrough

https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-automate-model-development.html

If you want more control during the data transformation/engineering process, you can have a look at SageMaker Data Wrangler:

https://aws.amazon.com/sagemaker/data-wrangler/

AWS
BenH
répondu il y a 2 ans

Vous n'êtes pas connecté. Se connecter pour publier une réponse.

Une bonne réponse répond clairement à la question, contient des commentaires constructifs et encourage le développement professionnel de la personne qui pose la question.

Instructions pour répondre aux questions