ML - Data transfer when running a model in Vertica?

emichaudemichaud Vertica Employee Employee
edited April 2020 in General Discussion

Is it true that running the model still involves data transfer between compute and storage layers in Vertica?

Asked during the BDC session Model Management and Data Preparation.
@WD @Arash_Fard

Answers

  • An ML model is a catalog object backed by several files on Vertica's internal DFS. When an appropriate predict function is called to use a model for in-database scoring (prediction), its files are read from the DFS (storage layer) into memory, and then this information is employed for calculating the predicted values. The input data is fed to the function the same way it is fed into any other function in database.

Leave a Comment

BoldItalicStrikethroughOrdered listUnordered list
Emoji
Image
Align leftAlign centerAlign rightToggle HTML viewToggle full pageToggle lights
Drop image/file