BUG: DTI/TDI.insert doing invalid casting (#33703)

Author: jbrockmendel

pandas/core/arrays/datetimelike.py

@@ -857,10 +857,13 @@ def _validate_setitem_value(self, value):
     def _validate_insert_value(self, value):
         if isinstance(value, self._recognized_scalars):
             value = self._scalar_type(value)
+            self._check_compatible_with(value, setitem=True)
+            # TODO: if we dont have compat, should we raise or astype(object)?
+            #  PeriodIndex does astype(object)
         elif is_valid_nat_for_dtype(value, self.dtype):
             # GH#18295
             value = NaT
-        elif lib.is_scalar(value) and isna(value):
+        else:
             raise TypeError(
                 f"cannot insert {type(self).__name__} with incompatible label"
             )

pandas/core/indexes/datetimelike.py

@@ -966,37 +966,30 @@ def insert(self, loc, item):
         -------
         new_index : Index
         """
+        if isinstance(item, str):
+            # TODO: Why are strings special?
+            # TODO: Should we attempt _scalar_from_string?
+            return self.astype(object).insert(loc, item)
+
         item = self._data._validate_insert_value(item)
 
         freq = None
-        if isinstance(item, self._data._scalar_type) or item is NaT:
-            self._data._check_compatible_with(item, setitem=True)
-
-            # check freq can be preserved on edge cases
-            if self.size and self.freq is not None:
+        # check freq can be preserved on edge cases
+        if self.freq is not None:
+            if self.size:
                 if item is NaT:
                     pass
                 elif (loc == 0 or loc == -len(self)) and item + self.freq == self[0]:
                     freq = self.freq
                 elif (loc == len(self)) and item - self.freq == self[-1]:
                     freq = self.freq
-            elif self.freq is not None:
+            else:
                 # Adding a single item to an empty index may preserve freq
                 if self.freq.is_on_offset(item):
                     freq = self.freq
-            item = item.asm8
 
-        try:
-            new_i8s = np.concatenate(
-                (self[:loc].asi8, [item.view(np.int64)], self[loc:].asi8)
-            )
-            arr = type(self._data)._simple_new(new_i8s, dtype=self.dtype, freq=freq)
-            return type(self)._simple_new(arr, name=self.name)
-        except (AttributeError, TypeError) as err:
+        item = self._data._unbox_scalar(item)
 
-            # fall back to object index
-            if isinstance(item, str):
-                return self.astype(object).insert(loc, item)
-            raise TypeError(
-                f"cannot insert {type(self).__name__} with incompatible label"
-            ) from err
+        new_i8s = np.concatenate([self[:loc].asi8, [item], self[loc:].asi8])
+        arr = type(self._data)._simple_new(new_i8s, dtype=self.dtype, freq=freq)
+        return type(self)._simple_new(arr, name=self.name)

pandas/tests/indexes/datetimes/test_insert.py

@@ -165,3 +165,26 @@ def test_insert(self):
                 assert result.name == expected.name
                 assert result.tz == expected.tz
                 assert result.freq is None
+
+    @pytest.mark.parametrize(
+        "item", [0, np.int64(0), np.float64(0), np.array(0), np.timedelta64(456)]
+    )
+    def test_insert_mismatched_types_raises(self, tz_aware_fixture, item):
+        # GH#33703 dont cast these to dt64
+        tz = tz_aware_fixture
+        dti = date_range("2019-11-04", periods=9, freq="-1D", name=9, tz=tz)
+
+        msg = "incompatible label"
+        with pytest.raises(TypeError, match=msg):
+            dti.insert(1, item)
+
+    def test_insert_object_casting(self, tz_aware_fixture):
+        # GH#33703
+        tz = tz_aware_fixture
+        dti = date_range("2019-11-04", periods=3, freq="-1D", name=9, tz=tz)
+
+        # ATM we treat this as a string, but we could plausibly wrap it in Timestamp
+        value = "2019-11-05"
+        result = dti.insert(0, value)
+        expected = Index(["2019-11-05"] + list(dti), dtype=object, name=9)
+        tm.assert_index_equal(result, expected)

pandas/tests/indexes/timedeltas/test_insert.py

@@ -82,6 +82,17 @@ def test_insert_invalid_na(self):
         with pytest.raises(TypeError, match="incompatible label"):
             idx.insert(0, np.datetime64("NaT"))
 
+    @pytest.mark.parametrize(
+        "item", [0, np.int64(0), np.float64(0), np.array(0), np.datetime64(456, "us")]
+    )
+    def test_insert_mismatched_types_raises(self, item):
+        # GH#33703 dont cast these to td64
+        tdi = TimedeltaIndex(["4day", "1day", "2day"], name="idx")
+
+        msg = "incompatible label"
+        with pytest.raises(TypeError, match=msg):
+            tdi.insert(1, item)
+
     def test_insert_dont_cast_strings(self):
         # To match DatetimeIndex and PeriodIndex behavior, dont try to
         #  parse strings to Timedelta

pandas/tests/indexing/test_coercion.py

@@ -448,7 +448,7 @@ def test_insert_index_datetimes(self, fill_val, exp_dtype):
             with pytest.raises(TypeError, match=msg):
                 obj.insert(1, pd.Timestamp("2012-01-01", tz="Asia/Tokyo"))
 
-        msg = "cannot insert DatetimeIndex with incompatible label"
+        msg = "cannot insert DatetimeArray with incompatible label"
         with pytest.raises(TypeError, match=msg):
             obj.insert(1, 1)
 
@@ -465,12 +465,12 @@ def test_insert_index_timedelta64(self):
         )
 
         # ToDo: must coerce to object
-        msg = "cannot insert TimedeltaIndex with incompatible label"
+        msg = "cannot insert TimedeltaArray with incompatible label"
         with pytest.raises(TypeError, match=msg):
             obj.insert(1, pd.Timestamp("2012-01-01"))
 
         # ToDo: must coerce to object
-        msg = "cannot insert TimedeltaIndex with incompatible label"
+        msg = "cannot insert TimedeltaArray with incompatible label"
         with pytest.raises(TypeError, match=msg):
             obj.insert(1, 1)
 

pandas/tests/indexing/test_partial.py

@@ -335,7 +335,7 @@ def test_partial_set_invalid(self):
         df = orig.copy()
 
         # don't allow not string inserts
-        msg = "cannot insert DatetimeIndex with incompatible label"
+        msg = "cannot insert DatetimeArray with incompatible label"
 
         with pytest.raises(TypeError, match=msg):
             df.loc[100.0, :] = df.iloc[0]