hausdorff_error#

hausdorff_error(true_change_points: _SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes], pred_change_points: _SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes], symmetric: bool = True, seed: int = 0) float[source]#

Compute the Hausdorff distance between two sets of change points.

See also

This function wraps scipy.spatial.distance.directed_hausdorff

Parameters:
true_change_points: array_like

Integer indexes (positions) of true change points

pred_change_points: array_like

Integer indexes (positions) of predicted change points

symmetric: bool

If True symmetric Hausdorff distance will be used

seed: int, default=0

Local numpy.random.RandomState seed. Default is 0, a random shuffling of u and v that guarantees reproducibility.

Returns:
Hausdorff error.