aeon
aeon copied to clipboard
[ENH] Implement Mahalanobis Distance
Describe the feature or idea you want to propose
Mahalanobis Distance is the distance distance that takes Covariance into account. Mahalanobis distance is widely used in cluster analysis and classification techniques. It is also used for multivariate statistical testing and Fisher's Linear Discriminant Anlaysis that is used for supervised classification. You can take a look at the following wikipedia:
https://en.wikipedia.org/wiki/Mahalanobis_distance
Its applications in Time Series Analysis are described in the following papers:
https://sites.cs.ucsb.edu/~yfwang/papers/IEEE_cybernetics_2015.pdf https://link.springer.com/chapter/10.1007/978-3-319-13731-5_57
I think it would be a good idea to include this in aeon.distances
Describe your proposed solution
Implement it using numpy
and numba
(which is fairly simple) or wrap scipy.spatial.distance.mahalanobis
.
Describe alternatives you've considered, if relevant
No response
Additional context
No response