CLN/TST: address TODOs (#44211)

Author: jbrockmendel

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):

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)
 

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

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.

pandas/core/frame.py

@@ -5356,7 +5356,6 @@ def _replace_columnwise(
         """
         Dispatch to Series.replace column-wise.
 
-
         Parameters
         ----------
         mapping : dict

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)}")
 

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)

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)

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

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

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

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)