v4 refactor for GP module

RELEASE-NOTES.md

@@ -45,8 +45,14 @@ All of the above apply to:
 - Changes to the BART implementation:
   - A BART variable can be combined with other random variables. The `inv_link` argument has been removed (see [4914](https://github.com/pymc-devs/pymc3/pull/4914)).
   - Moved BART to its own module (see [5058](https://github.com/pymc-devs/pymc3/pull/5058)).
-- ...
-
+- Changes to the Gaussian Process (GP) submodule:
+  - For all implementations, `gp.Latent`, `gp.Marginal` etc., `cov_func` and `mean_func` are required kwargs.
+  - In Windows test conda environment the `mkl` version is fixed to verison 2020.4, and `mkl-service` is fixed to `2.3.0`.  This was required for `gp.MarginalKron` to function properly.
+  - `gp.MvStudentT` uses rotated samples from `StudentT` directly now, instead of sampling from `pm.Chi2` and then from `pm.Normal`.
+  - The "jitter" parameter, or the diagonal noise term added to Gram matrices such that the Cholesky is numerically stable, is now exposed to the user instead of hard-coded.  See the function `gp.util.stabilize`.
+  - The `is_observed` arguement for `gp.Marginal*` implementations has been deprecated.
+  - In the gp.utils file, the `kmeans_inducing_points` function now passes through `kmeans_kwargs` to scipy's k-means function.
+  - The function `replace_with_values` function has been added to `gp.utils`.
 
 ### Expected breaks
 + New API was already available in `v3`.

conda-envs/windows-environment-test-py38.yml

@@ -12,7 +12,8 @@ dependencies:
 - fastprogress>=0.2.0
 - h5py>=2.7
 - libpython
-- mkl-service
+- mkl==2020.4
+- mkl-service==2.3.0
 - m2w64-toolchain
 - numpy>=1.15.0
 - pandas

pymc/gp/cov.py

@@ -64,7 +64,7 @@ def __init__(self, input_dim, active_dims=None):
         if active_dims is None:
             self.active_dims = np.arange(input_dim)
         else:
-            self.active_dims = np.asarray(active_dims, np.int)
+            self.active_dims = np.asarray(active_dims, int)
 
     def __call__(self, X, Xs=None, diag=False):
         r"""
@@ -152,7 +152,9 @@ def __array_wrap__(self, result):
         elif isinstance(result[0][0], Prod):
             return result[0][0].factor_list[0] * A
         else:
-            raise RuntimeError
+            raise TypeError(
+                f"Unknown Covariance combination type {result[0][0]}.  Known types are `Add` or `Prod`."
+            )
 
 
 class Combination(Covariance):