[ENH] Implement the Proximity Forest classifier using aeon distances

[TonyBagnall]

Is your feature request related to a problem? Please describe.

Proximity Forest is a distance based ensemble of decision trees. We do not currently have a working version of PF in aeon, but would very much like to have one. This is moderately complicated

https://link.springer.com/article/10.1007/s10618-019-00617-3
https://arxiv.org/abs/1808.10594

The original java version is here
https://github.com/benjaminmlucas/proximity-forest

We have a java version here
https://github.com/time-series-machine-learning/tsml-java/blob/master/src/main/java/tsml/classifiers/distance_based/proximity/ProximityForest.java

There is a version in the old repo, but it is broken and uses dataframes
https://github.com/sktime/sktime/blob/main/sktime/classification/distance_based/_proximity_forest.py

Describe the solution you'd like
I would like an implementation optimised for speed, that uses our distance functions and that can achieve accuracy results that are not significantly different to those published

Additional context
We would be happy to help the development and test performance against other implementations.