features.remap_waveform_shape_features_volume
features.remap_waveform_shape_features_volume(ephys_atlas_vol, feature_names)Same transform as remap_waveform_shape_features, for a download_encoding_volume array.
Values there are unnormalised already, so no de-z-scoring is needed. Does not derive mean_per_feature/std_per_feature for the new columns – those come from the original per-channel dataset, not the volume itself.
Parameters
| Name | Type | Description | Default |
|---|---|---|---|
| ephys_atlas_vol | numpy.ndarray | Shape (nx, ny, nz, n_features). |
required |
| feature_names | numpy.ndarray or sequence of str | Length n_features, naming ephys_atlas_vol’s last axis; must include the 18 raw columns of ModelSpikeFeatures. |
required |
Returns
| Name | Type | Description |
|---|---|---|
| remapped_vol | numpy.ndarray | Shape (nx, ny, nz, 16), dtype float32. |
| remapped_feature_names | numpy.ndarray | Length 16, naming remapped_vol’s last axis (ModelSpikeShapeFeatures column order). |
Raises
| Name | Type | Description |
|---|---|---|
| KeyError | If a required raw feature name is absent from feature_names (except slowness_s_per_m/spatial_spread_um, #123, and their _std counterparts, #127, all nullable: treated as all-NaN if altogether absent, so volumes computed before they existed can still be remapped). |