aggregate_panels

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_panels(panels: Sequence[DataFrame]) → DataFrame

Aggregate per-subject panels into the cohort-level panel.

The aggregation is the per-feature MEDIAN of value / lcl / ucl across subjects – the paper’s aggregation of per-lesion ICCs. A subject whose feature was unmeasurable (NaN) does not veto the feature; only a feature unmeasurable in EVERY subject comes out NaN.

Parameters:

panels – Per-subject panels from precision_panel(), all with the same feature index; at least one.

Returns:

The cohort-level panel, same columns as the input panels (n_voxels is the per-feature median across subjects).

Raises:

HABITAPIError – If no panel is given or the feature indices differ.

Examples using habit.precision.aggregate_panels

Precise voxel features

Precise voxel features