nirs4all.controllers.models.components.prediction_transformer module

Prediction Transformer - Handle scaling/unscaling of predictions

This component handles the transformation of predictions between different target spaces (scaled/unscaled, numeric/transformed).

Extracted from launch_training() lines 427-447 and _create_fold_averages() to eliminate duplicate logic.

class nirs4all.controllers.models.components.prediction_transformer.PredictionTransformer

Bases: object

Transforms predictions between scaled and unscaled spaces.

Handles:

• Classification tasks: Keep predictions in transformed space

• Regression tasks: Transform predictions back to numeric space

• Respects current y_processing from context

Example

>>> transformer = PredictionTransformer()
>>> y_pred_unscaled = transformer.transform_to_unscaled(
...     y_pred_scaled,
...     dataset,
...     context
... )

transform_batch_to_unscaled(predictions_dict: dict, dataset: SpectroDataset, context: ExecutionContext | None = None) → dict

Transform a dictionary of predictions to unscaled space.

Parameters:

• predictions_dict – Dictionary with keys like ‘train’, ‘val’, ‘test’ and values as prediction arrays

• dataset – Dataset with transformation info

• context – Execution context

Returns:

Dictionary with same keys but unscaled predictions

transform_to_unscaled(predictions_scaled: ndarray, dataset: SpectroDataset, context: ExecutionContext | None = None) → ndarray

Transform predictions from scaled/processed space to unscaled/numeric space.

Parameters:

• predictions_scaled – Predictions in scaled/processed space

• dataset – Dataset with task type and target transformation info

• context – Execution context with y processing info

Returns:

Predictions in unscaled/numeric space