diff --git a/pandas/core/arrays/_mixins.py b/pandas/core/arrays/_mixins.py
index cf9820c3aa8f8..848e724949bc5 100644
--- a/pandas/core/arrays/_mixins.py
+++ b/pandas/core/arrays/_mixins.py
@@ -197,8 +197,8 @@ def shift(self, periods=1, fill_value=None, axis=0):
         return self._from_backing_data(new_values)
 
     def _validate_shift_value(self, fill_value):
-        # TODO: after deprecation in datetimelikearraymixin is enforced,
-        #  we can remove this and ust validate_fill_value directly
+        # TODO(2.0): after deprecation in datetimelikearraymixin is enforced,
+        #  we can remove this and use validate_fill_value directly
         return self._validate_scalar(fill_value)
 
     def __setitem__(self, key, value):
diff --git a/pandas/core/arrays/categorical.py b/pandas/core/arrays/categorical.py
index 35e2dd25678e5..107cefdf31188 100644
--- a/pandas/core/arrays/categorical.py
+++ b/pandas/core/arrays/categorical.py
@@ -524,7 +524,6 @@ def astype(self, dtype: AstypeArg, copy: bool = True) -> ArrayLike:
             self = self.copy() if copy else self
             result = self._set_dtype(dtype)
 
-        # TODO: consolidate with ndarray case?
         elif isinstance(dtype, ExtensionDtype):
             return super().astype(dtype, copy=copy)
 
diff --git a/pandas/core/arrays/sparse/dtype.py b/pandas/core/arrays/sparse/dtype.py
index 6684e559b6f88..915e13bc3bbb2 100644
--- a/pandas/core/arrays/sparse/dtype.py
+++ b/pandas/core/arrays/sparse/dtype.py
@@ -371,7 +371,7 @@ def _subtype_with_str(self):
 
     def _get_common_dtype(self, dtypes: list[DtypeObj]) -> DtypeObj | None:
         # TODO for now only handle SparseDtypes and numpy dtypes => extend
-        # with other compatibtle extension dtypes
+        # with other compatible extension dtypes
         if any(
             isinstance(x, ExtensionDtype) and not isinstance(x, SparseDtype)
             for x in dtypes
diff --git a/pandas/core/computation/expr.py b/pandas/core/computation/expr.py
index 51af2cd732d09..f8716ca1bafe0 100644
--- a/pandas/core/computation/expr.py
+++ b/pandas/core/computation/expr.py
@@ -253,7 +253,6 @@ def _filter_nodes(superclass, all_nodes=_all_nodes):
 assert not intersection, _msg
 
 
-# TODO: Python 3.6.2: replace Callable[..., None] with Callable[..., NoReturn]
 def _node_not_implemented(node_name: str) -> Callable[..., None]:
     """
     Return a function that raises a NotImplementedError with a passed node name.
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 5afb19f1d91fe..2488048e30ccb 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -5356,7 +5356,6 @@ def _replace_columnwise(
         """
         Dispatch to Series.replace column-wise.
 
-
         Parameters
         ----------
         mapping : dict
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
index 6895455a43160..8b2774fd0f1b3 100644
--- a/pandas/core/generic.py
+++ b/pandas/core/generic.py
@@ -4974,7 +4974,7 @@ def _reindex_with_indexers(
             if indexer is not None:
                 indexer = ensure_platform_int(indexer)
 
-            # TODO: speed up on homogeneous DataFrame objects
+            # TODO: speed up on homogeneous DataFrame objects (see _reindex_multi)
             new_data = new_data.reindex_indexer(
                 index,
                 indexer,
@@ -6420,7 +6420,7 @@ def fillna(
                     )
             elif isinstance(value, ABCDataFrame) and self.ndim == 2:
 
-                new_data = self.where(self.notna(), value)._data
+                new_data = self.where(self.notna(), value)._mgr
             else:
                 raise ValueError(f"invalid fill value with a {type(value)}")
 
diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py
index 8a2ba69a61ed9..77281441c2ed2 100644
--- a/pandas/core/groupby/groupby.py
+++ b/pandas/core/groupby/groupby.py
@@ -1797,7 +1797,7 @@ def count(self) -> Series | DataFrame:
         is_series = data.ndim == 1
 
         def hfunc(bvalues: ArrayLike) -> ArrayLike:
-            # TODO(2DEA): reshape would not be necessary with 2D EAs
+            # TODO(EA2D): reshape would not be necessary with 2D EAs
             if bvalues.ndim == 1:
                 # EA
                 masked = mask & ~isna(bvalues).reshape(1, -1)
diff --git a/pandas/core/internals/blocks.py b/pandas/core/internals/blocks.py
index 7e533233d5ecf..bc9f5c3243705 100644
--- a/pandas/core/internals/blocks.py
+++ b/pandas/core/internals/blocks.py
@@ -917,7 +917,7 @@ def setitem(self, indexer, value):
                 value = np.nan
 
         # coerce if block dtype can store value
-        values = self.values
+        values = cast(np.ndarray, self.values)
         if not self._can_hold_element(value):
             # current dtype cannot store value, coerce to common dtype
             return self.coerce_to_target_dtype(value).setitem(indexer, value)
@@ -946,11 +946,7 @@ def setitem(self, indexer, value):
             values[indexer] = value
 
         else:
-            # error: Argument 1 to "setitem_datetimelike_compat" has incompatible type
-            # "Union[ndarray, ExtensionArray]"; expected "ndarray"
-            value = setitem_datetimelike_compat(
-                values, len(values[indexer]), value  # type: ignore[arg-type]
-            )
+            value = setitem_datetimelike_compat(values, len(values[indexer]), value)
             values[indexer] = value
 
         if transpose:
@@ -1729,8 +1725,7 @@ def is_view(self) -> bool:
 
     def setitem(self, indexer, value):
         if not self._can_hold_element(value):
-            # TODO: general case needs casting logic.
-            return self.astype(_dtype_obj).setitem(indexer, value)
+            return self.coerce_to_target_dtype(value).setitem(indexer, value)
 
         values = self.values
         if self.ndim > 1:
@@ -1751,7 +1746,6 @@ def putmask(self, mask, new) -> list[Block]:
         return [self]
 
     def where(self, other, cond, errors="raise") -> list[Block]:
-        # TODO(EA2D): reshape unnecessary with 2D EAs
         arr = self.values
 
         cond = extract_bool_array(cond)
diff --git a/pandas/core/series.py b/pandas/core/series.py
index 9795e1f7141ee..65592be32b5ef 100644
--- a/pandas/core/series.py
+++ b/pandas/core/series.py
@@ -4528,6 +4528,9 @@ def rename(
         5    3
         dtype: int64
         """
+        if axis is not None:
+            axis = self._get_axis_number(axis)
+
         if callable(index) or is_dict_like(index):
             return super().rename(
                 index, copy=copy, inplace=inplace, level=level, errors=errors
diff --git a/pandas/tests/arithmetic/common.py b/pandas/tests/arithmetic/common.py
index 649ad562307c0..6f4e35ad4dfb2 100644
--- a/pandas/tests/arithmetic/common.py
+++ b/pandas/tests/arithmetic/common.py
@@ -34,9 +34,18 @@ def assert_invalid_addsub_type(left, right, msg=None):
         right - left
 
 
+def get_expected_box(box):
+    """
+    Get the box to use for 'expected' in a comparison operation.
+    """
+    if box in [Index, array]:
+        return np.ndarray
+    return box
+
+
 def get_upcast_box(box, vector):
     """
-    Given two box-types, find the one that takes priority
+    Given two box-types, find the one that takes priority.
     """
     if box is DataFrame or isinstance(vector, DataFrame):
         return DataFrame
diff --git a/pandas/tests/arithmetic/test_datetime64.py b/pandas/tests/arithmetic/test_datetime64.py
index 0d3f7dcaaf65b..e511c1bdaca9c 100644
--- a/pandas/tests/arithmetic/test_datetime64.py
+++ b/pandas/tests/arithmetic/test_datetime64.py
@@ -43,6 +43,7 @@
 from pandas.tests.arithmetic.common import (
     assert_invalid_addsub_type,
     assert_invalid_comparison,
+    get_expected_box,
     get_upcast_box,
 )
 
@@ -59,9 +60,7 @@ def test_compare_zerodim(self, tz_naive_fixture, box_with_array):
         # Test comparison with zero-dimensional array is unboxed
         tz = tz_naive_fixture
         box = box_with_array
-        xbox = (
-            box_with_array if box_with_array not in [pd.Index, pd.array] else np.ndarray
-        )
+        xbox = get_expected_box(box)
         dti = date_range("20130101", periods=3, tz=tz)
 
         other = np.array(dti.to_numpy()[0])
@@ -148,7 +147,7 @@ def test_dt64arr_nat_comparison(self, tz_naive_fixture, box_with_array):
         # GH#22242, GH#22163 DataFrame considered NaT == ts incorrectly
         tz = tz_naive_fixture
         box = box_with_array
-        xbox = box if box not in [pd.Index, pd.array] else np.ndarray
+        xbox = get_expected_box(box)
 
         ts = Timestamp.now(tz)
         ser = Series([ts, NaT])
@@ -245,7 +244,7 @@ def test_nat_comparisons_scalar(self, dtype, data, box_with_array):
             #  on older numpys (since they check object identity)
             return
 
-        xbox = box if box not in [pd.Index, pd.array] else np.ndarray
+        xbox = get_expected_box(box)
 
         left = Series(data, dtype=dtype)
         left = tm.box_expected(left, box)
@@ -324,9 +323,7 @@ def test_timestamp_compare_series(self, left, right):
 
     def test_dt64arr_timestamp_equality(self, box_with_array):
         # GH#11034
-        xbox = (
-            box_with_array if box_with_array not in [pd.Index, pd.array] else np.ndarray
-        )
+        xbox = get_expected_box(box_with_array)
 
         ser = Series([Timestamp("2000-01-29 01:59:00"), Timestamp("2000-01-30"), NaT])
         ser = tm.box_expected(ser, box_with_array)
@@ -424,9 +421,7 @@ def test_dti_cmp_nat(self, dtype, box_with_array):
             #  on older numpys (since they check object identity)
             return
 
-        xbox = (
-            box_with_array if box_with_array not in [pd.Index, pd.array] else np.ndarray
-        )
+        xbox = get_expected_box(box_with_array)
 
         left = DatetimeIndex([Timestamp("2011-01-01"), NaT, Timestamp("2011-01-03")])
         right = DatetimeIndex([NaT, NaT, Timestamp("2011-01-03")])
@@ -662,7 +657,7 @@ def test_scalar_comparison_tzawareness(
         box = box_with_array
         tz = tz_aware_fixture
         dti = date_range("2016-01-01", periods=2, tz=tz)
-        xbox = box if box not in [pd.Index, pd.array] else np.ndarray
+        xbox = get_expected_box(box)
 
         dtarr = tm.box_expected(dti, box_with_array)
         if op in [operator.eq, operator.ne]:
@@ -2283,7 +2278,7 @@ def test_sub_dti_dti(self):
     # cleanup, box-parametrization, and de-duplication
 
     @pytest.mark.parametrize("op", [operator.add, operator.sub])
-    def test_timedelta64_equal_timedelta_supported_ops(self, op):
+    def test_timedelta64_equal_timedelta_supported_ops(self, op, box_with_array):
         ser = Series(
             [
                 Timestamp("20130301"),
@@ -2292,6 +2287,7 @@ def test_timedelta64_equal_timedelta_supported_ops(self, op):
                 Timestamp("20130228 21:00:00"),
             ]
         )
+        obj = box_with_array(ser)
 
         intervals = ["D", "h", "m", "s", "us"]
 
@@ -2302,10 +2298,10 @@ def timedelta64(*args):
         for d, h, m, s, us in product(*([range(2)] * 5)):
             nptd = timedelta64(d, h, m, s, us)
             pytd = timedelta(days=d, hours=h, minutes=m, seconds=s, microseconds=us)
-            lhs = op(ser, nptd)
-            rhs = op(ser, pytd)
+            lhs = op(obj, nptd)
+            rhs = op(obj, pytd)
 
-            tm.assert_series_equal(lhs, rhs)
+            tm.assert_equal(lhs, rhs)
 
     def test_ops_nat_mixed_datetime64_timedelta64(self):
         # GH#11349
diff --git a/pandas/tests/arithmetic/test_period.py b/pandas/tests/arithmetic/test_period.py
index 7d215c940c031..0c42be517b798 100644
--- a/pandas/tests/arithmetic/test_period.py
+++ b/pandas/tests/arithmetic/test_period.py
@@ -25,7 +25,10 @@
 import pandas._testing as tm
 from pandas.core import ops
 from pandas.core.arrays import TimedeltaArray
-from pandas.tests.arithmetic.common import assert_invalid_comparison
+from pandas.tests.arithmetic.common import (
+    assert_invalid_comparison,
+    get_expected_box,
+)
 
 # ------------------------------------------------------------------
 # Comparisons
@@ -38,9 +41,7 @@ class TestPeriodArrayLikeComparisons:
 
     def test_compare_zerodim(self, box_with_array):
         # GH#26689 make sure we unbox zero-dimensional arrays
-        xbox = (
-            box_with_array if box_with_array not in [pd.Index, pd.array] else np.ndarray
-        )
+        xbox = get_expected_box(box_with_array)
 
         pi = period_range("2000", periods=4)
         other = np.array(pi.to_numpy()[0])
@@ -77,11 +78,10 @@ def test_compare_invalid_listlike(self, box_with_array, other):
 
     @pytest.mark.parametrize("other_box", [list, np.array, lambda x: x.astype(object)])
     def test_compare_object_dtype(self, box_with_array, other_box):
+        xbox = get_expected_box(box_with_array)
         pi = period_range("2000", periods=5)
         parr = tm.box_expected(pi, box_with_array)
 
-        xbox = np.ndarray if box_with_array in [pd.Index, pd.array] else box_with_array
-
         other = other_box(pi)
 
         expected = np.array([True, True, True, True, True])
@@ -187,9 +187,7 @@ def test_pi_cmp_period(self):
 
     # TODO: moved from test_datetime64; de-duplicate with version below
     def test_parr_cmp_period_scalar2(self, box_with_array):
-        xbox = (
-            box_with_array if box_with_array not in [pd.Index, pd.array] else np.ndarray
-        )
+        xbox = get_expected_box(box_with_array)
 
         pi = period_range("2000-01-01", periods=10, freq="D")
 
@@ -210,7 +208,7 @@ def test_parr_cmp_period_scalar2(self, box_with_array):
     @pytest.mark.parametrize("freq", ["M", "2M", "3M"])
     def test_parr_cmp_period_scalar(self, freq, box_with_array):
         # GH#13200
-        xbox = np.ndarray if box_with_array in [pd.Index, pd.array] else box_with_array
+        xbox = get_expected_box(box_with_array)
 
         base = PeriodIndex(["2011-01", "2011-02", "2011-03", "2011-04"], freq=freq)
         base = tm.box_expected(base, box_with_array)
@@ -249,7 +247,7 @@ def test_parr_cmp_period_scalar(self, freq, box_with_array):
     @pytest.mark.parametrize("freq", ["M", "2M", "3M"])
     def test_parr_cmp_pi(self, freq, box_with_array):
         # GH#13200
-        xbox = np.ndarray if box_with_array in [pd.Index, pd.array] else box_with_array
+        xbox = get_expected_box(box_with_array)
 
         base = PeriodIndex(["2011-01", "2011-02", "2011-03", "2011-04"], freq=freq)
         base = tm.box_expected(base, box_with_array)
diff --git a/pandas/tests/arithmetic/test_timedelta64.py b/pandas/tests/arithmetic/test_timedelta64.py
index a2b7d93884a4e..7765c29ee59c8 100644
--- a/pandas/tests/arithmetic/test_timedelta64.py
+++ b/pandas/tests/arithmetic/test_timedelta64.py
@@ -1198,7 +1198,7 @@ def test_td64arr_addsub_integer_array_no_freq(self, box_with_array):
     # ------------------------------------------------------------------
     # Operations with timedelta-like others
 
-    def test_td64arr_add_td64_array(self, box_with_array):
+    def test_td64arr_add_sub_td64_array(self, box_with_array):
         box = box_with_array
         dti = pd.date_range("2016-01-01", periods=3)
         tdi = dti - dti.shift(1)
@@ -1213,20 +1213,11 @@ def test_td64arr_add_td64_array(self, box_with_array):
         result = tdarr + tdi
         tm.assert_equal(result, expected)
 
-    def test_td64arr_sub_td64_array(self, box_with_array):
-        box = box_with_array
-        dti = pd.date_range("2016-01-01", periods=3)
-        tdi = dti - dti.shift(1)
-        tdarr = tdi.values
-
-        expected = 0 * tdi
-        tdi = tm.box_expected(tdi, box)
-        expected = tm.box_expected(expected, box)
-
+        expected_sub = 0 * tdi
         result = tdi - tdarr
-        tm.assert_equal(result, expected)
+        tm.assert_equal(result, expected_sub)
         result = tdarr - tdi
-        tm.assert_equal(result, expected)
+        tm.assert_equal(result, expected_sub)
 
     def test_td64arr_add_sub_tdi(self, box_with_array, names):
         # GH#17250 make sure result dtype is correct
@@ -1263,37 +1254,25 @@ def test_td64arr_add_sub_tdi(self, box_with_array, names):
         tm.assert_equal(result, -expected)
         assert_dtype(result, "timedelta64[ns]")
 
-    def test_td64arr_add_sub_td64_nat(self, box_with_array):
-        # GH#23320 special handling for timedelta64("NaT")
+    @pytest.mark.parametrize("tdnat", [np.timedelta64("NaT"), NaT])
+    def test_td64arr_add_sub_td64_nat(self, box_with_array, tdnat):
+        # GH#18808, GH#23320 special handling for timedelta64("NaT")
         box = box_with_array
         tdi = TimedeltaIndex([NaT, Timedelta("1s")])
-        other = np.timedelta64("NaT")
         expected = TimedeltaIndex(["NaT"] * 2)
 
         obj = tm.box_expected(tdi, box)
         expected = tm.box_expected(expected, box)
 
-        result = obj + other
+        result = obj + tdnat
         tm.assert_equal(result, expected)
-        result = other + obj
+        result = tdnat + obj
         tm.assert_equal(result, expected)
-        result = obj - other
+        result = obj - tdnat
         tm.assert_equal(result, expected)
-        result = other - obj
+        result = tdnat - obj
         tm.assert_equal(result, expected)
 
-    def test_td64arr_sub_NaT(self, box_with_array):
-        # GH#18808
-        box = box_with_array
-        ser = Series([NaT, Timedelta("1s")])
-        expected = Series([NaT, NaT], dtype="timedelta64[ns]")
-
-        ser = tm.box_expected(ser, box)
-        expected = tm.box_expected(expected, box)
-
-        res = ser - NaT
-        tm.assert_equal(res, expected)
-
     def test_td64arr_add_timedeltalike(self, two_hours, box_with_array):
         # only test adding/sub offsets as + is now numeric
         # GH#10699 for Tick cases
@@ -1328,7 +1307,7 @@ def test_td64arr_sub_timedeltalike(self, two_hours, box_with_array):
     # ------------------------------------------------------------------
     # __add__/__sub__ with DateOffsets and arrays of DateOffsets
 
-    def test_td64arr_add_offset_index(self, names, box_with_array):
+    def test_td64arr_add_sub_offset_index(self, names, box_with_array):
         # GH#18849, GH#19744
         box = box_with_array
         exname = get_expected_name(box, names)
@@ -1340,8 +1319,13 @@ def test_td64arr_add_offset_index(self, names, box_with_array):
         expected = TimedeltaIndex(
             [tdi[n] + other[n] for n in range(len(tdi))], freq="infer", name=exname
         )
+        expected_sub = TimedeltaIndex(
+            [tdi[n] - other[n] for n in range(len(tdi))], freq="infer", name=exname
+        )
+
         tdi = tm.box_expected(tdi, box)
         expected = tm.box_expected(expected, box)
+        expected_sub = tm.box_expected(expected_sub, box)
 
         with tm.assert_produces_warning(PerformanceWarning):
             res = tdi + other
@@ -1351,10 +1335,12 @@ def test_td64arr_add_offset_index(self, names, box_with_array):
             res2 = other + tdi
         tm.assert_equal(res2, expected)
 
-    # TODO: combine with test_td64arr_add_offset_index by parametrizing
-    # over second box?
-    def test_td64arr_add_offset_array(self, box_with_array):
-        # GH#18849
+        with tm.assert_produces_warning(PerformanceWarning):
+            res_sub = tdi - other
+        tm.assert_equal(res_sub, expected_sub)
+
+    def test_td64arr_add_sub_offset_array(self, box_with_array):
+        # GH#18849, GH#18824
         box = box_with_array
         tdi = TimedeltaIndex(["1 days 00:00:00", "3 days 04:00:00"])
         other = np.array([offsets.Hour(n=1), offsets.Minute(n=-2)])
@@ -1362,6 +1348,9 @@ def test_td64arr_add_offset_array(self, box_with_array):
         expected = TimedeltaIndex(
             [tdi[n] + other[n] for n in range(len(tdi))], freq="infer"
         )
+        expected_sub = TimedeltaIndex(
+            [tdi[n] - other[n] for n in range(len(tdi))], freq="infer"
+        )
 
         tdi = tm.box_expected(tdi, box)
         expected = tm.box_expected(expected, box)
@@ -1374,41 +1363,10 @@ def test_td64arr_add_offset_array(self, box_with_array):
             res2 = other + tdi
         tm.assert_equal(res2, expected)
 
-    def test_td64arr_sub_offset_index(self, names, box_with_array):
-        # GH#18824, GH#19744
-        box = box_with_array
-        xbox = box if box not in [tm.to_array, pd.array] else pd.Index
-        exname = get_expected_name(box, names)
-
-        tdi = TimedeltaIndex(["1 days 00:00:00", "3 days 04:00:00"], name=names[0])
-        other = pd.Index([offsets.Hour(n=1), offsets.Minute(n=-2)], name=names[1])
-
-        expected = TimedeltaIndex(
-            [tdi[n] - other[n] for n in range(len(tdi))], freq="infer", name=exname
-        )
-
-        tdi = tm.box_expected(tdi, box)
-        expected = tm.box_expected(expected, xbox)
-
+        expected_sub = tm.box_expected(expected_sub, box_with_array)
         with tm.assert_produces_warning(PerformanceWarning):
-            res = tdi - other
-        tm.assert_equal(res, expected)
-
-    def test_td64arr_sub_offset_array(self, box_with_array):
-        # GH#18824
-        tdi = TimedeltaIndex(["1 days 00:00:00", "3 days 04:00:00"])
-        other = np.array([offsets.Hour(n=1), offsets.Minute(n=-2)])
-
-        expected = TimedeltaIndex(
-            [tdi[n] - other[n] for n in range(len(tdi))], freq="infer"
-        )
-
-        tdi = tm.box_expected(tdi, box_with_array)
-        expected = tm.box_expected(expected, box_with_array)
-
-        with tm.assert_produces_warning(PerformanceWarning):
-            res = tdi - other
-        tm.assert_equal(res, expected)
+            res_sub = tdi - other
+        tm.assert_equal(res_sub, expected_sub)
 
     def test_td64arr_with_offset_series(self, names, box_with_array):
         # GH#18849
@@ -1968,10 +1926,12 @@ def test_td64arr_mul_tdscalar_invalid(self, box_with_array, scalar_td):
     def test_td64arr_mul_too_short_raises(self, box_with_array):
         idx = TimedeltaIndex(np.arange(5, dtype="int64"))
         idx = tm.box_expected(idx, box_with_array)
-        msg = (
-            "cannot use operands with types dtype|"
-            "Cannot multiply with unequal lengths|"
-            "Unable to coerce to Series"
+        msg = "|".join(
+            [
+                "cannot use operands with types dtype",
+                "Cannot multiply with unequal lengths",
+                "Unable to coerce to Series",
+            ]
         )
         with pytest.raises(TypeError, match=msg):
             # length check before dtype check
@@ -2079,12 +2039,14 @@ def test_td64arr_div_numeric_array(
         result = tdser / vector
         tm.assert_equal(result, expected)
 
-        pattern = (
-            "true_divide'? cannot use operands|"
-            "cannot perform __div__|"
-            "cannot perform __truediv__|"
-            "unsupported operand|"
-            "Cannot divide"
+        pattern = "|".join(
+            [
+                "true_divide'? cannot use operands",
+                "cannot perform __div__",
+                "cannot perform __truediv__",
+                "unsupported operand",
+                "Cannot divide",
+            ]
         )
         with pytest.raises(TypeError, match=pattern):
             vector / tdser
diff --git a/pandas/tests/extension/base/getitem.py b/pandas/tests/extension/base/getitem.py
index ac181af7875b5..7efd3bdb6920a 100644
--- a/pandas/tests/extension/base/getitem.py
+++ b/pandas/tests/extension/base/getitem.py
@@ -233,9 +233,9 @@ def test_getitem_integer_with_missing_raises(self, data, idx):
         # FIXME: dont leave commented-out
         # TODO: this raises KeyError about labels not found (it tries label-based)
         # import pandas._testing as tm
-        # s = pd.Series(data, index=[tm.rands(4) for _ in range(len(data))])
+        # ser = pd.Series(data, index=[tm.rands(4) for _ in range(len(data))])
         # with pytest.raises(ValueError, match=msg):
-        #    s[idx]
+        #    ser[idx]
 
     def test_getitem_slice(self, data):
         # getitem[slice] should return an array
diff --git a/pandas/tests/extension/test_integer.py b/pandas/tests/extension/test_integer.py
index 344b0be20fc7b..c9c0a4de60a46 100644
--- a/pandas/tests/extension/test_integer.py
+++ b/pandas/tests/extension/test_integer.py
@@ -115,15 +115,16 @@ def check_opname(self, s, op_name, other, exc=None):
     def _check_op(self, s, op, other, op_name, exc=NotImplementedError):
         if exc is None:
             sdtype = tm.get_dtype(s)
-            if sdtype.is_unsigned_integer and (op_name == "__rsub__"):
-                # TODO see https://github.com/pandas-dev/pandas/issues/22023
-                pytest.skip("unsigned subtraction gives negative values")
 
             if (
                 hasattr(other, "dtype")
                 and not is_extension_array_dtype(other.dtype)
                 and is_integer_dtype(other.dtype)
+                and sdtype.is_unsigned_integer
             ):
+                # TODO: comment below is inaccurate; other can be int8, int16, ...
+                #  and the trouble is that e.g. if s is UInt8 and other is int8,
+                #  then result is UInt16
                 # other is np.int64 and would therefore always result in
                 # upcasting, so keeping other as same numpy_dtype
                 other = other.astype(sdtype.numpy_dtype)
@@ -133,20 +134,9 @@ def _check_op(self, s, op, other, op_name, exc=NotImplementedError):
 
             if op_name in ("__rtruediv__", "__truediv__", "__div__"):
                 expected = expected.fillna(np.nan).astype("Float64")
-            elif op_name.startswith("__r"):
-                # TODO reverse operators result in object dtype
-                # see https://github.com/pandas-dev/pandas/issues/22024
-                expected = expected.astype(sdtype)
-                result = result.astype(sdtype)
             else:
                 # combine method result in 'biggest' (int64) dtype
                 expected = expected.astype(sdtype)
-                pass
-
-            if (op_name == "__rpow__") and isinstance(other, pd.Series):
-                # TODO pow on Int arrays gives different result with NA
-                # see https://github.com/pandas-dev/pandas/issues/22022
-                result = result.fillna(1)
 
             self.assert_equal(result, expected)
         else:
diff --git a/pandas/tests/frame/indexing/test_indexing.py b/pandas/tests/frame/indexing/test_indexing.py
index 1ea436520bf20..74460a75d7b63 100644
--- a/pandas/tests/frame/indexing/test_indexing.py
+++ b/pandas/tests/frame/indexing/test_indexing.py
@@ -1165,12 +1165,10 @@ def test_getitem_boolean_indexing_mixed(self):
 
     def test_type_error_multiindex(self):
         # See gh-12218
-        df = DataFrame(
-            columns=["i", "c", "x", "y"],
-            data=[[0, 0, 1, 2], [1, 0, 3, 4], [0, 1, 1, 2], [1, 1, 3, 4]],
+        mi = MultiIndex.from_product([["x", "y"], [0, 1]], names=[None, "c"])
+        dg = DataFrame(
+            [[1, 1, 2, 2], [3, 3, 4, 4]], columns=mi, index=Index([0, 1], name="i")
         )
-        dg = df.pivot_table(index="i", columns="c", values=["x", "y"])
-        # TODO: Is this test for pivot_table?
         with pytest.raises(TypeError, match="unhashable type"):
             dg[:, 0]
 
diff --git a/pandas/tests/indexes/test_any_index.py b/pandas/tests/indexes/test_any_index.py
index f68bde2188e67..2313afcae607a 100644
--- a/pandas/tests/indexes/test_any_index.py
+++ b/pandas/tests/indexes/test_any_index.py
@@ -1,7 +1,5 @@
 """
 Tests that can be parametrized over _any_ Index object.
-
-TODO: consider using hypothesis for these.
 """
 import re
 
diff --git a/pandas/tests/indexes/timedeltas/test_indexing.py b/pandas/tests/indexes/timedeltas/test_indexing.py
index 669bbe23af559..fc8abb83ed302 100644
--- a/pandas/tests/indexes/timedeltas/test_indexing.py
+++ b/pandas/tests/indexes/timedeltas/test_indexing.py
@@ -248,8 +248,7 @@ def test_take_invalid_kwargs(self):
         with pytest.raises(ValueError, match=msg):
             idx.take(indices, mode="clip")
 
-    # TODO: This method came from test_timedelta; de-dup with version above
-    def test_take2(self):
+    def test_take_equiv_getitem(self):
         tds = ["1day 02:00:00", "1 day 04:00:00", "1 day 10:00:00"]
         idx = timedelta_range(start="1d", end="2d", freq="H", name="idx")
         expected = TimedeltaIndex(tds, freq=None, name="idx")
diff --git a/pandas/tests/io/formats/test_format.py b/pandas/tests/io/formats/test_format.py
index 95da68510be6b..d9bd8f6809c73 100644
--- a/pandas/tests/io/formats/test_format.py
+++ b/pandas/tests/io/formats/test_format.py
@@ -239,7 +239,7 @@ def test_repr_truncation(self):
             assert "..." not in repr(df)
 
     def test_repr_deprecation_negative_int(self):
-        # FIXME: remove in future version after deprecation cycle
+        # TODO(2.0): remove in future version after deprecation cycle
         # Non-regression test for:
         # https://github.com/pandas-dev/pandas/issues/31532
         width = get_option("display.max_colwidth")
diff --git a/pandas/tests/plotting/test_datetimelike.py b/pandas/tests/plotting/test_datetimelike.py
index 6d269a27e2656..f74cab9ed04da 100644
--- a/pandas/tests/plotting/test_datetimelike.py
+++ b/pandas/tests/plotting/test_datetimelike.py
@@ -6,7 +6,6 @@
     timedelta,
 )
 import pickle
-import sys
 
 import numpy as np
 import pytest
@@ -1526,14 +1525,8 @@ def _check_plot_works(f, freq=None, series=None, *args, **kwargs):
         with tm.ensure_clean(return_filelike=True) as path:
             plt.savefig(path)
 
-        # GH18439
-        # this is supported only in Python 3 pickle since
-        # pickle in Python2 doesn't support instancemethod pickling
-        # TODO(statsmodels 0.10.0): Remove the statsmodels check
-        # https://github.com/pandas-dev/pandas/issues/24088
-        # https://github.com/statsmodels/statsmodels/issues/4772
-        if "statsmodels" not in sys.modules:
-            with tm.ensure_clean(return_filelike=True) as path:
-                pickle.dump(fig, path)
+        # GH18439, GH#24088, statsmodels#4772
+        with tm.ensure_clean(return_filelike=True) as path:
+            pickle.dump(fig, path)
     finally:
         plt.close(fig)
diff --git a/pandas/tests/series/indexing/test_datetime.py b/pandas/tests/series/indexing/test_datetime.py
index 2c5c977624470..b8291471225d7 100644
--- a/pandas/tests/series/indexing/test_datetime.py
+++ b/pandas/tests/series/indexing/test_datetime.py
@@ -137,14 +137,14 @@ def test_getitem_setitem_datetimeindex():
     tm.assert_series_equal(result, expected)
 
     # But we do not give datetimes a pass on tzawareness compat
-    # TODO: do the same with Timestamps and dt64
     msg = "Cannot compare tz-naive and tz-aware datetime-like objects"
     naive = datetime(1990, 1, 1, 4)
-    with tm.assert_produces_warning(FutureWarning):
-        # GH#36148 will require tzawareness compat
-        result = ts[naive]
-    expected = ts[4]
-    assert result == expected
+    for key in [naive, Timestamp(naive), np.datetime64(naive, "ns")]:
+        with tm.assert_produces_warning(FutureWarning):
+            # GH#36148 will require tzawareness compat
+            result = ts[key]
+        expected = ts[4]
+        assert result == expected
 
     result = ts.copy()
     with tm.assert_produces_warning(FutureWarning):
diff --git a/pandas/tests/series/methods/test_between.py b/pandas/tests/series/methods/test_between.py
index 9c11b71e4bee6..d81017633ff76 100644
--- a/pandas/tests/series/methods/test_between.py
+++ b/pandas/tests/series/methods/test_between.py
@@ -11,8 +11,6 @@
 
 
 class TestBetween:
-
-    # TODO: redundant with test_between_datetime_values?
     def test_between(self):
         series = Series(date_range("1/1/2000", periods=10))
         left, right = series[[2, 7]]
@@ -21,7 +19,7 @@ def test_between(self):
         expected = (series >= left) & (series <= right)
         tm.assert_series_equal(result, expected)
 
-    def test_between_datetime_values(self):
+    def test_between_datetime_object_dtype(self):
         ser = Series(bdate_range("1/1/2000", periods=20).astype(object))
         ser[::2] = np.nan
 
diff --git a/pandas/tests/series/methods/test_rename.py b/pandas/tests/series/methods/test_rename.py
index 2930c657eb3b2..a78abfa63cff4 100644
--- a/pandas/tests/series/methods/test_rename.py
+++ b/pandas/tests/series/methods/test_rename.py
@@ -1,6 +1,7 @@
 from datetime import datetime
 
 import numpy as np
+import pytest
 
 from pandas import (
     Index,
@@ -65,10 +66,9 @@ def test_rename_axis_supported(self):
         ser = Series(range(5))
         ser.rename({}, axis=0)
         ser.rename({}, axis="index")
-        # FIXME: dont leave commented-out
-        # TODO: clean up shared index validation
-        # with pytest.raises(ValueError, match="No axis named 5"):
-        #     ser.rename({}, axis=5)
+
+        with pytest.raises(ValueError, match="No axis named 5"):
+            ser.rename({}, axis=5)
 
     def test_rename_inplace(self, datetime_series):
         renamer = lambda x: x.strftime("%Y%m%d")
diff --git a/pandas/tests/series/test_arithmetic.py b/pandas/tests/series/test_arithmetic.py
index 4d1c75da72399..103130484f0e1 100644
--- a/pandas/tests/series/test_arithmetic.py
+++ b/pandas/tests/series/test_arithmetic.py
@@ -251,6 +251,7 @@ def test_add_corner_cases(self, datetime_series):
         # deltas5 = deltas * 5
         # deltas = deltas + sub_deltas
 
+    def test_add_float_plus_int(self, datetime_series):
         # float + int
         int_ts = datetime_series.astype(int)[:-5]
         added = datetime_series + int_ts