fisher_rao_phase_distance#
- skfda.misc.metrics.fisher_rao_phase_distance(fdata1, fdata2, *, lam=0, eval_points=None, _check=True)[source]#
Compute the Fisher-Rao phase distance between two functional objects.
Let \(f_i\) and \(f_j\) be two functional observations, and let \(\gamma_{ij}\) the corresponding warping used in the elastic registration to align \(f_i\) to \(f_j\) (see
elastic_registration()
). The Fisher-Rao phase distance between \(f_i\) and \(f_j\) is defined as\[d_{P}(f_i, f_j) = d_{FR}(\gamma_{ij}, \gamma_{id}) = arcos \left ( \int_0^1 \sqrt {\gamma_{ij}'(t)} dt \right )\]where \(\gamma_{id}\) is the identity warping.
See [1] for a detailed explanation.
If the observations are defined in a domain different than (0,1) their domains are normalized to this interval with an affine transformation.
- Parameters:
- Returns:
Phase distance between the objects.
- Raises:
ValueError – If the objects are not unidimensional.
- Return type:
References