Integrate an existing prediction model into an app workflow, effectively productionalizing the model. The model(s) will be able to be ran on schedule.
This process type requires two inputs, one being a dataset and then other being a model. It's typically used with the process type ML Engine Train, which outputs a model.
Location of the package of scripts in a cloud storage bucket.
Prediction File Name:
Name of the script file to execute.
Shell Script Arguments:
Arguments to pass to the script. "@fromDate" and "@toDate" variables can be used in this field. The "@fromDate" and "@toDate" will be replaced with the date range configured in the job execution.
The name of the output table that results from the execution of this process.
The name of the table icon in the workflow of the app.
Load to BQ:
Load the table to Big Query (enabled or disabled).
Event Store Name:
Information about the event store associated with this app.
Information about the database that this output table will be stored in.
Information about the cloud storage bucket location where the data will be stored.
The table result of the script executed in the Prediction File Name.