Hi there, Is it not possible that the table contains a null header and sagemaker is reading that header as col1 instead thus giving you that shift in the data structure. If that is not the case then it is possible you already had an col0 and it is moving up the data a column when you append col1, col2 and so on.
Hopefully this gives you more to think about and puts you in the right direction.
Redshift: Slow read speedsasked 7 months ago
Redshift ML with multi-container Sagemaker modelasked 4 months ago
Redshift ML / SageMaker - Deploy an existing model artifact to a Redshift ClusterAccepted Answerasked 2 years ago
Using Glue for dimensional model ETL into RedshiftAccepted Answerasked 3 years ago
Sagemaker Endpoint is not created when deploying HuggingFace Model using it.asked 5 months ago
SageMaker Model Monitor Missing Columns Constraint ViolationAccepted Answerasked 3 years ago
import tables with large data columns from redshift federated schema into local tablesasked 2 months ago
How to replicate IF NOT EXISTS in redshiftAccepted Answerasked 8 months ago
Is Redshift mixing up my data columns when creating a model?asked 3 months ago
aws glue job fail for escaper charasked 7 months ago