Re-running case_studies/probabilistic_matrix_factorization, tag update

Author: Severin Hatt

examples/case_studies/probabilistic_matrix_factorization.ipynb

@@ -15,11 +15,17 @@ kernelspec:
 # Probabilistic Matrix Factorization for Making Personalized Recommendations
 
 :::{post} June 3, 2022
-:tags: case study
+:tags: case study, product recommendation, matrix factorization
 :category: intermediate
+:author: Ruslan Salakhutdinov, Andriy Mnih, Mack Sweeney, Colin Carroll, Rob Zinkov
 :::
 
 ```{code-cell} ipython3
+%load_ext autoreload
+```
+
+```{code-cell} ipython3
+%autoreload 2
 %matplotlib inline
 
 import arviz as az
@@ -361,14 +367,14 @@ class PMF:
                 mu=0,
                 tau=self.alpha_u * np.eye(dim),
                 dims=("users", "latent_factors"),
-                testval=rng.standard_normal(size=(n, dim)) * std,
+                initval=rng.standard_normal(size=(n, dim)) * std,
             )
             V = pm.MvNormal(
                 "V",
                 mu=0,
                 tau=self.alpha_v * np.eye(dim),
                 dims=("movies", "latent_factors"),
-                testval=rng.standard_normal(size=(m, dim)) * std,
+                initval=rng.standard_normal(size=(m, dim)) * std,
             )
             R = pm.Normal(
                 "R",
@@ -397,7 +403,7 @@ Since it is a reasonably complex model, we expect the MAP estimation to take som
 def _find_map(self):
     """Find mode of posterior using L-BFGS-B optimization."""
     tstart = time.time()
-    with self.model:
+    with self.model as m:
         logging.info("finding PMF MAP using L-BFGS-B optimization...")
         self._map = pm.find_MAP(method="L-BFGS-B")
 
@@ -757,6 +763,8 @@ If you made it this far, then congratulations! You now have some idea of how to
 
 +++
 
+## Authors
+
 The model discussed in this analysis was developed by Ruslan Salakhutdinov and Andriy Mnih. Code and supporting text are the original work of [Mack Sweeney](https://www.linkedin.com/in/macksweeney) with changes made to adapt the code and text for the MovieLens dataset by Colin Carroll and Rob Zinkov.
 
 +++
@@ -775,7 +783,7 @@ goldberg2001eigentaste
 
 ```{code-cell} ipython3
 %load_ext watermark
-%watermark -n -u -v -iv -w
+%watermark -n -u -v -iv -w -p aesara,aeppl,xarray
 ```
 
 :::{include} ../page_footer.md