I want to score multiple models on a huge dataset. Is it possible to score these models in parallel?¶
The best way to score models in parallel is to use the in-H2O binary models. To do this:
Import the binary (non-POJO, previously exported) model into an H2O cluster
Import the datasets into H2O as well.
Call the predict endpoint either from R, Python, Flow, or the REST API directly.
Export the predictions to file or download them from the server.
You can also score models in parallel by downloading a POJO or MOJO for each model, and then embedding those within a HIVE UDF to score the large dataset stored on Hadoop. Tutorials on this process can be found in the Productionizing H2O section.
Which parameters are used with or for scoring?¶