H2OPredict Syntax Elements | Vantage BYOM - 3.0 - H2OPredict Syntax Elements - Teradata Vantage

Teradata Vantageā„¢ - Bring Your Own Model User Guide

Teradata Vantage
Release Number
Release Date
May 2022
Content Type
User Guide
Publication ID
English (United States)
Specify one or more column names to add to the output table. Use an asterisk to specify all columns.
An accumulate_column cannot specify column Ids as integers, ranges, or allow the data type BLOB or CLOB.
[Optional] Specify the output fields to add as individual columns instead of the entire JSON output. Specify fields with a comma-separated list.
[Optional] Valid values are: 'current_cached_model', '*', 'true', 't', 'yes', '1', 'false', 'f', 'no', 'n', or '0'. All of these values are equivalent as this argument applies only to the model specified in the model ON clause, which is assumed to be in the cache.
Important: Do not use the OverwriteCachedModel argument except when you are trying to replace a previously cached model. This applies to any model type (PMML, H2O Open Source, DAI, and ONNX). Using the argument in other cases, including in concurrent queries or multiple times within a short period of time, may lead to an OOM error from garbage collection not being fast enough.
If a model loaded into the memory of the node fits in the cache, it stays in the cache until being evicted to make space for another model that needs to be loaded. Therefore, a model can remain in the cache after the query that loaded it completes. Other queries that use the same model can use it, saving the cost of reloading it into memory.
You want to overwrite a cached model only when it has been updated, to make sure that the Predict function uses the updated model instead of the cached model.
Default behavior: The function does not overwrite cached models.
[Optional] Specify the type of model to use for scoring.
You can use either of the following values: Driverless AI (DAI) or OpenSource.
[Optional] Set the following feature option values to true to have the values appear in the JSON in the output:
  • contributions: The contribution of each input feature towards the prediction.
  • stageProbabilities: Prediction probabilities of trees in each stage or iteration.
  • leafNodeAssignments: The leaf placements of the row in all the trees in the tree-based model.
If the feature options are not specified, the features are considered false and the following values are not populated in the output JSON:
  • contributions (applies only to binomial or regression models)
  • leafNodeAssignments and stageProbabilities (applies to binomial, regression, multinomial, and AnomalyDetection models)