openstef_core.datasets#

Time series datasets and versioned data access.

This module provides core data structures for handling time series data in OpenSTEF forecasting. It includes both simple time series datasets and versioned datasets that track data availability over time, enabling realistic backtesting and training and forecasting.

The module supports:

  • Regular time series with consistent sampling intervals

  • Versioned time series that track when data became available

  • Validated datasets with domain-specific constraints

  • Data transformations and validation utilities

  • Feature concatenation and horizon restriction operations

Submodules#

openstef_core.datasets.mixins

Protocol definitions for time series dataset interfaces.

Functions#

validate_horizons_present(dataset, horizons)

Validate that the specified forecast horizons are present in the dataset.

Classes#

EnergyComponentDataset(data[, ...])

Time series dataset for energy generation by component type.

ForecastDataset(data[, sample_interval, ...])

Time series dataset containing probabilistic forecasts with quantile estimates.

ForecastInputDataset(data[, ...])

Time series dataset for forecasting with validated target column.

TimeSeriesDataset(data[, sample_interval, ...])

A time series dataset with regular sampling intervals and optional versioning.

VersionedTimeSeriesDataset(data_parts, *[, ...])

A versioned time series dataset composed of multiple data parts.