[backport 2.3.x] BUG/TST (string dtype): raise proper TypeError in interpolate (#60637) (#60652)

BUG/TST (string dtype): raise proper TypeError in interpolate (#60637)

* TST(string dtype): Resolve xfail for interpolate

* Adjust arrow tests

* Fixup for NumPyExtensionArray

* Use tm.shares_memory

(cherry picked from commit 5e50d3f)

Co-authored-by: Richard Shadrach <[email protected]>

Author: jorisvandenbossche

Diff for: pandas/core/arrays/arrow/array.py

@@ -2150,6 +2150,9 @@ def interpolate(
         See NDFrame.interpolate.__doc__.
         """
         # NB: we return type(self) even if copy=False
+        if not self.dtype._is_numeric:
+            raise TypeError(f"Cannot interpolate with {self.dtype} dtype")
+
         mask = self.isna()
         if self.dtype.kind == "f":
             data = self._pa_array.to_numpy()

Diff for: pandas/core/arrays/numpy_.py

@@ -287,6 +287,9 @@ def interpolate(
         See NDFrame.interpolate.__doc__.
         """
         # NB: we return type(self) even if copy=False
+        if not self.dtype._is_numeric:
+            raise TypeError(f"Cannot interpolate with {self.dtype} dtype")
+
         if not copy:
             out_data = self._ndarray
         else:

Diff for: pandas/tests/extension/test_arrow.py

@@ -3350,6 +3350,17 @@ def test_string_to_datetime_parsing_cast():
     tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.skipif(
+    pa_version_under13p0, reason="pairwise_diff_checked not implemented in pyarrow"
+)
+def test_interpolate_not_numeric(data):
+    if not data.dtype._is_numeric:
+        ser = pd.Series(data)
+        msg = re.escape(f"Cannot interpolate with {ser.dtype} dtype")
+        with pytest.raises(TypeError, match=msg):
+            pd.Series(data).interpolate()
+
+
 def test_string_to_time_parsing_cast():
     # GH 56463
     string_times = ["11:41:43.076160"]

Diff for: pandas/tests/frame/methods/test_interpolate.py

@@ -69,11 +69,7 @@ def test_interpolate_inplace(self, frame_or_series, using_array_manager, request
         assert np.shares_memory(orig, obj.values)
         assert orig.squeeze()[1] == 1.5
 
-    # TODO(infer_string) raise proper TypeError in case of string dtype
-    @pytest.mark.xfail(
-        using_string_dtype(), reason="interpolate doesn't work for string"
-    )
-    def test_interp_basic(self, using_copy_on_write):
+    def test_interp_basic(self, using_copy_on_write, using_infer_string):
         df = DataFrame(
             {
                 "A": [1, 2, np.nan, 4],
@@ -90,6 +86,13 @@ def test_interp_basic(self, using_copy_on_write):
                 "D": list("abcd"),
             }
         )
+        if using_infer_string:
+            dtype = "str" if using_infer_string else "object"
+            msg = f"[Cc]annot interpolate with {dtype} dtype"
+            with pytest.raises(TypeError, match=msg):
+                df.interpolate()
+            return
+
         msg = "DataFrame.interpolate with object dtype"
         with tm.assert_produces_warning(FutureWarning, match=msg):
             result = df.interpolate()
@@ -111,8 +114,8 @@ def test_interp_basic(self, using_copy_on_write):
         tm.assert_frame_equal(df, expected)
 
         # check we DID operate inplace
-        assert np.shares_memory(df["C"]._values, cvalues)
-        assert np.shares_memory(df["D"]._values, dvalues)
+        assert tm.shares_memory(df["C"]._values, cvalues)
+        assert tm.shares_memory(df["D"]._values, dvalues)
 
     @pytest.mark.xfail(
         using_string_dtype(), reason="interpolate doesn't work for string"