Krige unification

[MuellerSeb]

Closes #79
Fixes #89

Here comes the great unification of our krige submodule:

• Swiss Army Knife for kriging: The Krige class now provides everything in one place
• "Kriging the mean" is now possible with the switch only_mean in the call routine
• Simple/Ordinary/Universal/ExtDrift/Detrended are only shortcuts to Krige with limited input parameter list
• We now use the covariance function to build up the kriging matrix
• An unbiased switch was added to enable simple kriging (where the unbiased condition is not given)
• An exact switch was added to allow smother results, if a nugget is present in the model
• An cond_err parameter was added, where measurement error variances can be given for each conditional point
• pseudo-inverse matrix is now used to solve the kriging system (can be disabled by the new switch pseudo_inv), this is equal to solving the system with least-squares and prevents numerical errors
• New examples added
• New tests added

PS: I needed to create a new PR, since there were some commits in the branch, that weren't recognized by the last PR.

[MuellerSeb]

I still need to update the call signatures of the different kriging methods to include the pseudo_inv_type.

[MuellerSeb]

I still need to update the call signatures of the different kriging methods to include the pseudo_inv_type.

Done. @LSchueler you can start your review ;-)

[LSchueler]

As I already said in PR #95, great work!

Just a typo hint and a suggestion to think about. Functions are first class objects in Python, hurray!!