Catch positive definite error

[OriolAbril]

Even though the docstring from https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.multivariate_normal.html says

Symmetric positive (semi)definite covariance matrix of the distribution.

It also accepts matrices whose determinant is close to 0 but negative, generally due to numerical issues. It doesn't expect users to solve those numerical issues themselves before passing the covariance matrix to the multivariate_normal class or methods. This adds a try/except to catch the error related to this issue and checks if adding an identity matrix with 1e-10 to the provided covariance matrix solves the issue.

cc @symeneses

[codecov]

Codecov Report

Merging #24 (3d7a512) into main (72f0e42) will decrease coverage by 0.56%.
The diff coverage is 42.85%.

@@            Coverage Diff             @@
##             main      #24      +/-   ##
==========================================
- Coverage   91.83%   91.26%   -0.57%     
==========================================
  Files           6        6              
  Lines         612      618       +6     
==========================================
+ Hits          562      564       +2     
- Misses         50       54       +4     

Impacted Files	Coverage Δ
src/xarray_einstats/stats.py	89.47% <42.85%> (-1.52%)	⬇️

Help us with your feedback. Take ten seconds to tell us how you rate us.