You can run post-processing tasks using the SpatialDataFrame class to interact with the database tables and files.

Also, OML4Py provides the functionality to save and load models into a datastore.

Post-processing tasks in the Spatial AI workflow include the following:

• Storing the model’s predictions or transformations as database tables or files.

  You can store data, such as features created as part of a feature engineering task or changes made as part of a preprocessing task, in a database using the write function in the SpatialDataFrame class.

• Saving a model to an OML4Py datastore.

  Your can store trained models, transformers, estimators, and Python objects in an OML4Py datastore.

• Loading a model from the OML4Py datastore.

  You can retrieve and use previously stored models, transformers, or Python objects that are available in an OML4Py datastore.

The post-processing tasks are explained in detail in the following sections: