The td_pmml_predict_sqle() function allows users to use external PMML models for scoring through tdplyr.
Required arguments:
- modeldata specifies the model tbl_teradata to be used for scoring.
- newdata specifies the input tbl_teradata that contains the data to be scored.
- accumulate specifies the names of newdata columns to copy to the output tbl_teradata.
Optional arguments:
- modeldata.order.column specifies Order By columns for modeldata.
- newdata.partition.column specifies Partition By columns for newdata.
- newdata.order.column specifies Order By columns for newdata.
- model.output.fields specifies the columns of the json output that the user wants to specify as individual columns instead of the entire json report.
- overwrite.cached.models specifies the model name that needs to be removed from the cache.
Use * to remove all cached models.