manager.multitask.PredictTask

manager.multitask.PredictTask(
    dataframe=None,
    data_test=None,
    data_frame_name='default',
    cache_home=None,
    agg_weights=None,
    index_name='DateTime',
    number_folds=10,
    predict_size=24,
    bounds=None,
    contamination=0.03,
    imputation_method='weighted',
    use_exogenous_features=True,
    n_trials_optuna=15,
    n_trials_spotoptim=10,
    n_initial_spotoptim=5,
    auto_save_models=True,
    train_days=365 * 2,
    val_days=7 * 2,
    log_level=logging.INFO,
    verbose=False,
    **config_overrides,
)

Task 5 — Predict-only using previously saved models.

Loads fitted forecasters that were persisted by a prior LazyTask, OptunaTask, or SpotOptimTask run and produces predictions for all configured targets. No training or tuning is performed.

If no saved models exist in the cache directory the run method raises RuntimeError with an informative message.

Examples

from spotforecast2.manager.multitask import PredictTask

task = PredictTask(data_frame_name="demo10", predict_size=24)
print(f"Task: {task.TASK}")
print(f"Predict size: {task.config.predict_size}")

Task: predict
Predict size: 24

Methods

Name	Description
run	Run prediction using previously saved models.

run

manager.multitask.PredictTask.run(
    show=True,
    task_name=None,
    max_age_days=None,
    **kwargs,
)

Run prediction using previously saved models.

Parameters

Name	Type	Description	Default
show	bool	If True, display prediction figures.	True
task_name	Optional[str]	Restrict model loading to a specific source task ("lazy", "optuna", or "spotoptim"). None loads the most recent model regardless of source.	None
max_age_days	Optional[float]	Maximum age in days for saved models. Models older than this are ignored. None accepts any age.	None

Returns

Name	Type	Description
	Dict[str, Any]	Aggregated prediction package. Per-target packages are stored
	Dict[str, Any]	on self.results["predict"].

Raises

Name	Type	Description
	RuntimeError	If no saved models are found in the cache directory, or if a target has no matching model.