Share via

HTSInferenceParameters Class

  • Reference

Parameters for HTS inference pipeline.

Inheritance
azureml.train.automl.runtime._solution_accelorators.data_models.pipeline_parameters.InferencePipelineParameters
HTSInferenceParameters

Constructor

HTSInferenceParameters(hierarchy_forecast_level: str, allocation_method: str | None = 'proportions_of_historical_average', forecast_mode: str = 'recursive', step: int = 1, forecast_quantiles: float | List[float] | None = None)

Parameters

Name Description
hierarchy_forecast_level
Required

The hts forecast level.
allocation_method

The allocation methods. We currently support 'average_historical_proportions' and 'proportions_of_historical_average'.

Default value: proportions_of_historical_average
forecast_mode

The forecast mode; either recursive or rolling.

Default value: recursive
step

The step size when the forecast mode is rolling.

Default value: 1
forecast_quantiles

Optional list of quantiles to get forecasts for.

Default value: None

Methods

validate

Validates the supplied parameters.

validate

Validates the supplied parameters.

validate()