H2OPredict Output | Vantage BYOM - H2OPredict Output - Teradata Vantage

Teradata Vantageā„¢ - Bring Your Own Model User Guide

Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
Lake
VMware
Product
Teradata Vantage
Release Number
5.0
Published
October 2023
Language
English (United States)
Last Update
2023-12-19
dita:mapPath
fee1607120608274.ditamap
dita:ditavalPath
ayr1485454803741.ditaval
dita:id
fee1607120608274
Column Data Type Description
accumulate_column Same as in InputTable. One column each for the column names specified in accumulate_column.

Use an asterisk to specify all columns.

prediction VARCHAR The prediction value. Appears when the JSON has only one entry.

Often occurs during regression for both H2O Open Source and DAI models. If a classification, the probabilities of the classes are included in the JSON report.

json_report VARCHAR All output fields specific to the model, except for prediction. If EnableOptions is used, those fields are included. Appears only if you omit ModelOutputFields.
model_output_field VARCHAR or DOUBLE PRECISION The model-specific output fields such as probability, predicted, and value. Appears once for each specified model_output_field.

If EnableOptions is set, an extra field for the option is added to the JSON report. If any of the options are to be a separate column outside of the JSON, the option needs to also be included in the ModelOutputFields parameter.