client.trigger_pre_computation

Runs a variety of precomputation steps for a model.

🚧

Deprecated

This client method is being deprecated and will not be supported in future versions of the client. This method is called automatically now when calling client.add_model_surrogate() or client.add_model_artifact().

📘

Note

This method should be called after client.upload_model_package(). It is not necessary after calling client.register_model() as this step happens automatically when onboarding a model.

Input ParameterTypeDefaultDescription
project_idstrNoneThe unique identifier for the project.
model_idstrNoneA unique identifier for the model.
dataset_idstrNoneThe unique identifier for the dataset.
overwrite_cacheOptional [bool]TrueIf True, will overwrite existing cached information.
batch_sizeOptional [int]10The batch size used for global PDP calculations.
calculate_predictionsOptional [bool]TrueIf True, will precompute and store model predictions.
cache_global_impact_importanceOptional [bool]TrueIf True, global feature impact and global feature importance will be precomputed and cached when the model is registered.
cache_global_pdpsOptional [bool]TrueIf True, global partial dependence plots will be precomputed and cached when the model is registered.
cache_datasetOptional [bool]FalseIf True, histogram information for the baseline dataset will be precomputed and cached when the model is registered.
PROJECT_ID = 'example_project'
DATASET_ID = 'example_dataset'
MODEL_ID = 'example_model'

client.trigger_pre_computation(
    project_id=PROJECT_ID,
    dataset_id=DATASET_ID,
    model_id=MODEL_ID
)