Support imputations with ndarray data

closes #4437

RELEASE-NOTES.md

@@ -1,10 +1,11 @@
 # Release Notes
 
-## PyMC3 vNext (on deck)
+## PyMC3 vNext (3.11.1)
 
 ### Breaking Changes
 
 ### New Features
++ Automatic imputations now also work with `ndarray` data, not just `pd.Series` or `pd.DataFrame` (see[#4439](https://github.com/pymc-devs/pymc3/pull/4439)).
 
 ### Maintenance
 - `math.log1mexp_numpy` no longer raises RuntimeWarning when given very small inputs. These were commonly observed during NUTS sampling (see [#4428](https://github.com/pymc-devs/pymc3/pull/4428)).

pymc3/model.py

@@ -21,6 +21,7 @@
 from typing import TYPE_CHECKING, Any, List, Optional, Type, TypeVar, Union, cast
 
 import numpy as np
+import pandas as pd
 import scipy.sparse as sps
 import theano
 import theano.graph.basic
@@ -1695,16 +1696,29 @@ def pandas_to_array(data):
     XXX: When `data` is a generator, this will return a Theano tensor!
 
     """
-    if hasattr(data, "values"):  # pandas
-        if data.isnull().any().any():  # missing values
-            ret = np.ma.MaskedArray(data.values, data.isnull().values)
+    if isinstance(data, (pd.Series, pd.DataFrame)):
+        mask = data.isnull()
+        if mask.any().any():
+            # there are missing values
+            ret = np.ma.MaskedArray(data.values, mask.values)
         else:
             ret = data.values
-    elif hasattr(data, "mask"):
-        if data.mask.any():
-            ret = data
-        else:  # empty mask
-            ret = data.filled()
+    elif isinstance(data, np.ndarray):
+        if isinstance(data, np.ma.MaskedArray):
+            if not data.mask.any():
+                # empty mask
+                ret = data.filled()
+            else:
+                # already masked and rightly so
+                ret = data
+        else:
+            # already a ndarray, but not masked
+            mask = np.isnan(data)
+            if np.any(mask):
+                ret = np.ma.MaskedArray(data, mask)
+            else:
+                # no masking required
+                ret = data
     elif isinstance(data, theano.graph.basic.Variable):
         ret = data
     elif sps.issparse(data):