use the stored rules and lists to actually prepare the data

apply the label encoding and other transformations stored in SQL code and the selected final column as RegEx string. Get the results back and export them to .parquet files so you could use them in a powerful R or Python environment. Of course you could also do the model building in Spark with a genuine Spark-ML model or H2O.ai Sparkling Water. All that matters is that the result is a MOJO file KNIME would be able to read and apply to Sparkling Water

External resources

• Combine Big Data, Spark and H2O.ai Sparkling Water