[BUG] Segmentation method to_classification and to_clustering do not work as expected

[TonyBagnall]

Describe the bug

these two methods in BaseSegmenter are meant to convert change points into 0/1 series where change points occur , comment says
For example change points [2, 8] for a time series of length 10
would result in: [0, 0, 1, 0, 0, 0, 0, 0, 1, 0].

but I cant see how it can be correct without being told what the length is, and output is not as expected.

the actual code is simply

        return np.bincount(change_points[1:-1], minlength=change_points[-1])

similar for to_clustering. Also not keen on the function names and they should be static methods. I think these came from clasp? @patrickzib ring any bells?

Steps/Code to reproduce the bug

calling it

import numpy as np
from aeon.segmentation import ClaSPSegmenter
bs = ClaSPSegmenter()
labels=bs.to_classification([2, 8])

Expected results

[0, 0, 1, 0, 0, 0, 0, 0, 1, 0].

Actual results

[0 0 0 0 0 0 0 0]

Versions

No response