DATASET NORMALIZE (APPLY)¶
Applies a previously-fitted normalization (mean/std parameters from dataset_normalize_fit) to a new dataset WITHOUT refitting – the train/test discipline. Skips id/mid/*_id columns; columns with no saved parameters are left unchanged; missing cells are left as-is; std==0 is treated as 1.0.
When to use¶
Tagged: normalization, standardize, zscore, scaling, apply, transform, train_test, preprocessing.
Inputs¶
| Label | ID | Type | Default | Required | Description |
|---|---|---|---|---|---|
| Dataset | dataset | dataset | — | ✓ | Testing/new dataset to normalize with the saved parameters; 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 |
|---|---|---|---|
| Normalized Dataset | dataset | dataset | Input dataset normalized using the supplied saved parameters. |
| Status | status | string | Summary of how many columns were transformed vs left unchanged. |
Disciplines¶
- data.dataset.transform
- data.statistics
Auto-generated from platform schema. Worker id: dataset_normalize_apply. Schema hash: 8c5513df78c8. Hand-curated docs in workerexamples/ override this page when present.