chronax.data_loader

Data Loader for loading and preprocessing time series data.

DataLoader

chronax.data_loader.DataLoader

Loads and processes complete time series datasets into Dataset objects.

The DataLoader handles CSV-based time series data, loading entire datasets into memory and creating rolling windows for training. It works with a single dataset at a time, suitable for the task-based execution model.

All data is treated as multivariate where univariate is simply num_targets == 1. Targets are inferred from data structure and kept as raw arrays without artificial column naming for maximum flexibility.

__init__(self, task_config: TaskConfig, evaluation_config: EvaluationConfig, *, force_no_normalize: bool = False)

Initialize the loader for a specific task and evaluation configuration.

Parameter	Type	Default	Description
task_config	TaskConfig	-	Task configuration object that includes dataset metadata and preprocessing directives for the active task.
evaluation_config	EvaluationConfig	-	Evaluation configuration object that includes benchmark settings for evaluation.
force_no_normalize	bool	False	If True, skip StandardScaler on targets (same missing-value handling as training). Used to export UI display series in raw units.