DataverseLabs / pyinterpolate

Kriging | Poisson Kriging | Variogram Analysis
https://pyinterpolate.readthedocs.io/en/stable/
BSD 3-Clause "New" or "Revised" License
151 stars 26 forks source link

[Feature] [Experimental Variogram] Variance should be calculated ALWAYS when experimental variogram is created #379

Closed SimonMolinsky closed 1 year ago

SimonMolinsky commented 1 year ago

Is your feature request related to a problem? Please describe. The ExperimentalVariogram class allows the user to choose if variance should be calculated. The problem is that variance is needed for multiple modeling tasks, especially to assign the sill in the search for the optimal theoretical variogram model.

Describe the solution you'd like Remove the is_variance parameter from the ExperimentalVariogram class, the __c_var attribute, and all related parameters in functions and classes depended on ExperimentalVariogram, force algorithm to calculate variance (always). Perform tests to check if everything works fine after this change.