ComponentSplittingModel#

class openstef_models.models.ComponentSplittingModel(**data: Any) → None[source]#

Bases: BaseModel, ComponentSplitter

Complete component splitting pipeline combining preprocessing, splitting, and postprocessing.

Orchestrates the full component splitting workflow by managing data preprocessing, component splitting algorithms, and result postprocessing. Provides a unified interface for splitting energy time series into different components while ensuring data consistency and validation throughout the pipeline.

Invariants

  • fit() must be called before predict()

  • Component splitter and preprocessing must be compatible

  • Output components must sum to match input source values

Example

Basic component splitting setup:

>>> from openstef_models.models.component_splitting.constant_component_splitter import (
...     ConstantComponentSplitter, ConstantComponentSplitterConfig
... )
>>> from openstef_core.mixins import TransformPipeline
>>> from openstef_core.types import EnergyComponentType
>>>
>>> # Create a component splitter with known energy ratios
>>> splitter = ConstantComponentSplitter(
...     ConstantComponentSplitterConfig(
...         source_column="total_load",
...         components=[EnergyComponentType.SOLAR, EnergyComponentType.WIND],
...         component_ratios={
...             EnergyComponentType.SOLAR: 0.6,
...             EnergyComponentType.WIND: 0.4
...         }
...     )
... )
>>> preprocessing = TransformPipeline()
>>>
>>> # Create and train model
>>> model = ComponentSplittingModel(
...     component_splitter=splitter,
...     preprocessing=preprocessing,
...     source_column="total_load"
... )
>>> model.fit(training_data)
>>>
>>> # Split components
>>> components = model.predict(new_data)
Parameters:

data (Any)

preprocessing: TransformPipeline[TimeSeriesDataset]#
component_splitter: ComponentSplitter#
postprocessing: TransformPipeline[EnergyComponentDataset]#
source_column: str#
property config: ComponentSplitterConfig#

Access the model’s configuration parameters.

Returns:

Configuration object containing fundamental model parameters.

property is_fitted: bool#

Check if the predictor has been fitted.

fit(data: TimeSeriesDataset, data_val: TimeSeriesDataset | None = None) → None[source]#

Fit the predictor to the input data.

This method should be called before generating predictions. It allows the predictor to learn parameters from the training data.

Parameters:

  • data (TimeSeriesDataset) – The training data to fit the predictor on.

  • data_val (TimeSeriesDataset | None) – The validation data to evaluate and tune the predictor on (optional).

  • data

  • data_val

Return type:

None

predict(data: TimeSeriesDataset) → EnergyComponentDataset[source]#

Generate predictions for the input data.

This method should use the fitted parameters to generate predictions.

Parameters:
Returns:

Predictions for the input data.

Raises:

NotFittedError – If the predictor has not been fitted yet.

Return type:

EnergyComponentDataset

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True, 'protected_namespaces': (), 'ser_json_inf_nan': 'null'}#

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].