Using external models with Vertica

To give you the utmost in machine learning flexibility and scalability, Vertica supports importing, exporting, and predicting with PMML and TensorFlow models.

The machine learning configuration parameter MaxModelSizeKB sets the maximum size of a model that can be imported into Vertica.

Support for PMML models

Vertica supports the import and export of K-means, linear regression, and logistic regression machine learning models in Predictive Model Markup Language (PMML) format. Support for this platform-independent model format allows you to use models trained on other platforms to predict on data stored in your Vertica database. You can also use Vertica as your model repository. Vertica supports PMML version 4.4.

With the PREDICT_PMML function, you can use a PMML model archived in Vertica to run prediction on data stored in the Vertica database.

For more information, see Using PMML models.

For details on the PMML attributes that Vertica does and does not currently support, see PMML features and attributes.

Support for TensorFlow models

Vertica now supports importing trained TensorFlow models, and using those models to do prediction in Vertica on data stored in the Vertica database. Vertica supports TensorFlow models trained in TensorFlow version 1.15.

The PREDICT_TENSORFLOW function lets you predict on data in Vertica with any TensorFlow model.

For additional information, see TensorFlow models.

Additional functions that support external models

The following functions support both PMML and TensorFlow models: