aggregate_voxel_means

Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the Habitat Guide and Python API guide (v2.0) for usage.

aggregate_voxel_means(field: VoxelFeatureField, label_array: ndarray) → DataFrame[source]

Average each voxel feature within each supervoxel.

This is the v0.1 calculate_supervoxel_means semantics on the v1 contracts: empty labels are skipped rather than filled with NaN, and the row order follows ascending supervoxel id.

Parameters:

  • field – Per-voxel features for one subject.

  • label_array – Supervoxel id per voxel over the full grid; 0 denotes voxels outside the ROI.

Returns:

One row per non-empty supervoxel, indexed by supervoxel id, with one column per voxel feature.