DATASET NORMALIZE (INVERSE)¶
Inverts a normalization to recover raw values: raw = normalized * std + mean, using the mean/std parameters from dataset_normalize_fit. Only columns present in the parameters are inverted; all other columns pass through unchanged. Use after prediction (and after inverse PCA) to return predicted columns to their original physical scale.
When to use¶
Tagged: normalization, denormalize, inverse, scaling, postprocessing, prediction.
Inputs¶
| Label | ID | Type | Default | Required | Description |
|---|---|---|---|---|---|
| Dataset | dataset | dataset | — | ✓ | Normalized dataset to invert back to raw scale; array-of-row-objects. |
| Normalization Parameters | parameters | dataset | — | ✓ | Parameters dataset produced by dataset_normalize_fit; rows of {column, mean, std}. |
Outputs¶
| Label | ID | Type | Description |
|---|---|---|---|
| Raw Dataset | dataset | dataset | Input dataset with normalized columns converted back to raw scale (normalized * std + mean). |
| Status | status | string | Summary of how many columns were inverted. |
Disciplines¶
- data.dataset.transform
- data.statistics
Auto-generated from platform schema. Worker id: dataset_normalize_inverse. Schema hash: 7297d8eb67bb. Hand-curated docs in workerexamples/ override this page when present.