LinearComponentSplitter#

class openstef_models.models.component_splitting.linear_component_splitter.LinearComponentSplitter(config: LinearComponentSplitterConfig) → None[source]

Bases: ComponentSplitter

Linear component splitter for energy data.

Provides a linear component splitter that uses a simple linear model to split energy data into predefined components. The predefined components are:

  • Wind on shore

  • Solar

  • Other

The splitter applies a pre-trained model from OpenSTEF V3.4.24 to divide total energy consumption into three predefined components. Training is currently not supported.

Example

Basic usage

>>> from openstef_core.types import EnergyComponentType
>>> config = LinearComponentSplitterConfig(
...     source_column="total_load",
...     components=[EnergyComponentType.SOLAR, EnergyComponentType.WIND, EnergyComponentType.OTHER],
... )
>>> splitter = LinearComponentSplitter(config)
>>> components = splitter.predict(time_series_data)
Parameters:

config (LinearComponentSplitterConfig)

__init__(config: LinearComponentSplitterConfig) → None[source]

Initialize the linear component splitter.

Parameters:

  • config (LinearComponentSplitterConfig) – Configuration with model path and column names.

  • config

property config: LinearComponentSplitterConfig

Get the splitter configuration.

Returns:

Current configuration with component ratios and settings.

property is_fitted: bool

Check if the predictor has been fitted.

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

No training supported currently for linear component splitter.

The linear model is pre-trained and loaded from a file.

Parameters:
Return type:

None

predict(data: TimeSeriesDataset) → EnergyComponentDataset[source]

Predict energy components using the linear model.

Parameters:

  • data (TimeSeriesDataset) – Input time series dataset containing total load, radiation, and windspeed_100m.

  • data

Returns:

Energy component dataset with wind, solar, and other components.

Raises:

ValueError – If required columns are missing or model not loaded.

Return type:

EnergyComponentDataset