BUG: compare returning all nan columns when comparing ea and np dtypes

doc/source/whatsnew/v1.5.0.rst

@@ -908,6 +908,8 @@ Indexing
 - Bug in :meth:`DataFrame.mask` with ``inplace=True`` and ``ExtensionDtype`` columns incorrectly raising (:issue:`45577`)
 - Bug in getting a column from a DataFrame with an object-dtype row index with datetime-like values: the resulting Series now preserves the exact object-dtype Index from the parent DataFrame (:issue:`42950`)
 - Bug in :meth:`DataFrame.__getattribute__` raising ``AttributeError`` if columns have ``"string"`` dtype (:issue:`46185`)
+- Bug in :meth:`DataFrame.compare` returning all ``NaN`` column when comparing extension array dtype and numpy dtype (:issue:`44014`)
+- Bug in :meth:`DataFrame.where` setting wrong values with ``"boolean"`` mask for numpy dtype (:issue:`44014`)
 - Bug in indexing on a :class:`DatetimeIndex` with a ``np.str_`` key incorrectly raising (:issue:`45580`)
 - Bug in :meth:`CategoricalIndex.get_indexer` when index contains ``NaN`` values, resulting in elements that are in target but not present in the index to be mapped to the index of the NaN element, instead of -1 (:issue:`45361`)
 - Bug in setting large integer values into :class:`Series` with ``float32`` or ``float16`` dtype incorrectly altering these values instead of coercing to ``float64`` dtype (:issue:`45844`)

pandas/core/internals/blocks.py

@@ -1062,6 +1062,8 @@ def where(self, other, cond, _downcast="infer") -> list[Block]:
 
         transpose = self.ndim == 2
 
+        cond = extract_bool_array(cond)
+
         # EABlocks override where
         values = cast(np.ndarray, self.values)
         orig_other = other

pandas/tests/frame/indexing/test_where.py

@@ -1046,3 +1046,13 @@ def test_where_mask_deprecated(frame_or_series):
 
     with tm.assert_produces_warning(FutureWarning):
         obj.mask(mask, -1, errors="raise")
+
+
+def test_where_producing_ea_cond_for_np_dtype():
+    # GH#44014
+    df = DataFrame({"a": Series([1, pd.NA, 2], dtype="Int64"), "b": [1, 2, 3]})
+    result = df.where(lambda x: x.apply(lambda y: y > 1, axis=1))
+    expected = DataFrame(
+        {"a": Series([pd.NA, pd.NA, 2], dtype="Int64"), "b": [np.nan, 2, 3]}
+    )
+    tm.assert_frame_equal(result, expected)

pandas/tests/frame/methods/test_compare.py

@@ -236,3 +236,19 @@ def test_invalid_input_result_names(result_names):
         ),
     ):
         df1.compare(df2, result_names=result_names)
+
+
+def test_compare_ea_and_np_dtype():
+    # GH#44014
+    df1 = pd.DataFrame({"a": [4.0, 4], "b": [1.0, 2]})
+    df2 = pd.DataFrame({"a": pd.Series([1, pd.NA], dtype="Int64"), "b": [1.0, 2]})
+    result = df1.compare(df2, keep_shape=True)
+    expected = pd.DataFrame(
+        {
+            ("a", "self"): [4.0, np.nan],
+            ("a", "other"): pd.Series([1, pd.NA], dtype="Int64"),
+            ("b", "self"): np.nan,
+            ("b", "other"): np.nan,
+        }
+    )
+    tm.assert_frame_equal(result, expected)