CLN: address TODOs (#44305)

Author: jbrockmendel

pandas/_libs/hashtable.pyi

@@ -194,21 +194,6 @@ class StringHashTable(HashTable): ...
 class PyObjectHashTable(HashTable): ...
 class IntpHashTable(HashTable): ...
 
-def duplicated_int64(
-    values: np.ndarray,  # const int64_t[:] values
-    keep: Literal["last", "first", False] = ...,
-) -> npt.NDArray[np.bool_]: ...
-
-# TODO: Is it actually bool or is it uint8?
-
-def mode_int64(
-    values: np.ndarray,  # const int64_t[:] values
-    dropna: bool,
-) -> npt.NDArray[np.int64]: ...
-def value_count_int64(
-    values: np.ndarray,  # const int64_t[:]
-    dropna: bool,
-) -> tuple[npt.NDArray[np.int64], npt.NDArray[np.int64]]: ...
 def duplicated(
     values: np.ndarray,
     keep: Literal["last", "first", False] = ...,

pandas/_libs/tslibs/offsets.pyx

@@ -777,7 +777,7 @@ cdef class Tick(SingleConstructorOffset):
                 "Tick offset with `normalize=True` are not allowed."
             )
 
-    # FIXME: Without making this cpdef, we get AttributeError when calling
+    # Note: Without making this cpdef, we get AttributeError when calling
     #  from __mul__
     cpdef Tick _next_higher_resolution(Tick self):
         if type(self) is Day:

pandas/_libs/writers.pyi

@@ -1,8 +1,11 @@
+from __future__ import annotations
+
 import numpy as np
 
-# TODO: can make this more specific
+from pandas._typing import ArrayLike
+
 def write_csv_rows(
-    data: list,
+    data: list[ArrayLike],
     data_index: np.ndarray,
     nlevels: int,
     cols: np.ndarray,

pandas/_libs/writers.pyx

@@ -30,7 +30,7 @@ def write_csv_rows(
 
     Parameters
     ----------
-    data : list
+    data : list[ArrayLike]
     data_index : ndarray
     nlevels : int
     cols : ndarray

pandas/core/array_algos/putmask.py

@@ -65,7 +65,7 @@ def putmask_inplace(values: ArrayLike, mask: npt.NDArray[np.bool_], value: Any)
         np.putmask(values, mask, value)
 
 
-def putmask_smart(values: np.ndarray, mask: np.ndarray, new) -> np.ndarray:
+def putmask_smart(values: np.ndarray, mask: npt.NDArray[np.bool_], new) -> np.ndarray:
     """
     Return a new ndarray, try to preserve dtype if possible.
 
@@ -84,12 +84,11 @@ def putmask_smart(values: np.ndarray, mask: np.ndarray, new) -> np.ndarray:
 
     See Also
     --------
-    ndarray.putmask
+    np.putmask
     """
     # we cannot use np.asarray() here as we cannot have conversions
     # that numpy does when numeric are mixed with strings
 
-    # n should be the length of the mask or a scalar here
     if not is_list_like(new):
         new = np.broadcast_to(new, mask.shape)
 
@@ -139,15 +138,17 @@ def putmask_smart(values: np.ndarray, mask: np.ndarray, new) -> np.ndarray:
     return _putmask_preserve(values, new, mask)
 
 
-def _putmask_preserve(new_values: np.ndarray, new, mask: np.ndarray):
+def _putmask_preserve(new_values: np.ndarray, new, mask: npt.NDArray[np.bool_]):
     try:
         new_values[mask] = new[mask]
     except (IndexError, ValueError):
         new_values[mask] = new
     return new_values
 
 
-def putmask_without_repeat(values: np.ndarray, mask: np.ndarray, new: Any) -> None:
+def putmask_without_repeat(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], new: Any
+) -> None:
     """
     np.putmask will truncate or repeat if `new` is a listlike with
     len(new) != len(values).  We require an exact match.
@@ -181,7 +182,9 @@ def putmask_without_repeat(values: np.ndarray, mask: np.ndarray, new: Any) -> No
         np.putmask(values, mask, new)
 
 
-def validate_putmask(values: ArrayLike, mask: np.ndarray) -> tuple[np.ndarray, bool]:
+def validate_putmask(
+    values: ArrayLike, mask: np.ndarray
+) -> tuple[npt.NDArray[np.bool_], bool]:
     """
     Validate mask and check if this putmask operation is a no-op.
     """
@@ -193,7 +196,7 @@ def validate_putmask(values: ArrayLike, mask: np.ndarray) -> tuple[np.ndarray, b
     return mask, noop
 
 
-def extract_bool_array(mask: ArrayLike) -> np.ndarray:
+def extract_bool_array(mask: ArrayLike) -> npt.NDArray[np.bool_]:
     """
     If we have a SparseArray or BooleanArray, convert it to ndarray[bool].
     """

pandas/core/indexes/category.py

@@ -390,6 +390,7 @@ def fillna(self, value, downcast=None):
 
         return type(self)._simple_new(cat, name=self.name)
 
+    # TODO(2.0): remove reindex once non-unique deprecation is enforced
     def reindex(
         self, target, method=None, level=None, limit=None, tolerance=None
     ) -> tuple[Index, npt.NDArray[np.intp] | None]:

pandas/tests/arithmetic/test_timedelta64.py

@@ -2132,7 +2132,6 @@ def test_float_series_rdiv_td64arr(self, box_with_array, names):
 
         result = ser.__rtruediv__(tdi)
         if box is DataFrame:
-            # TODO: Should we skip this case sooner or test something else?
             assert result is NotImplemented
         else:
             tm.assert_equal(result, expected)

pandas/tests/arrays/categorical/test_replace.py

@@ -29,14 +29,14 @@
         ([1, 2, "3"], "5", ["5", "5", 3], True),
     ],
 )
-def test_replace(to_replace, value, expected, flip_categories):
+def test_replace_categorical_series(to_replace, value, expected, flip_categories):
     # GH 31720
     stays_categorical = not isinstance(value, list) or len(pd.unique(value)) == 1
 
-    s = pd.Series([1, 2, 3], dtype="category")
-    result = s.replace(to_replace, value)
+    ser = pd.Series([1, 2, 3], dtype="category")
+    result = ser.replace(to_replace, value)
     expected = pd.Series(expected, dtype="category")
-    s.replace(to_replace, value, inplace=True)
+    ser.replace(to_replace, value, inplace=True)
 
     if flip_categories:
         expected = expected.cat.set_categories(expected.cat.categories[::-1])
@@ -46,7 +46,7 @@ def test_replace(to_replace, value, expected, flip_categories):
         expected = pd.Series(np.asarray(expected))
 
     tm.assert_series_equal(expected, result, check_category_order=False)
-    tm.assert_series_equal(expected, s, check_category_order=False)
+    tm.assert_series_equal(expected, ser, check_category_order=False)
 
 
 @pytest.mark.parametrize(
@@ -59,8 +59,7 @@ def test_replace(to_replace, value, expected, flip_categories):
         ("b", None, ["a", None], "Categorical.categories length are different"),
     ],
 )
-def test_replace2(to_replace, value, result, expected_error_msg):
-    # TODO: better name
+def test_replace_categorical(to_replace, value, result, expected_error_msg):
     # GH#26988
     cat = Categorical(["a", "b"])
     expected = Categorical(result)

pandas/tests/arrays/timedeltas/test_reductions.py

@@ -84,19 +84,8 @@ def test_sum(self):
         assert isinstance(result, Timedelta)
         assert result == expected
 
-    # TODO: de-duplicate with test_npsum below
-    def test_np_sum(self):
-        # GH#25282
-        vals = np.arange(5, dtype=np.int64).view("m8[h]").astype("m8[ns]")
-        arr = TimedeltaArray(vals)
-        result = np.sum(arr)
-        assert result == vals.sum()
-
-        result = np.sum(pd.TimedeltaIndex(arr))
-        assert result == vals.sum()
-
     def test_npsum(self):
-        # GH#25335 np.sum should return a Timedelta, not timedelta64
+        # GH#25282, GH#25335 np.sum should return a Timedelta, not timedelta64
         tdi = pd.TimedeltaIndex(["3H", "3H", "2H", "5H", "4H"])
         arr = tdi.array
 

pandas/tests/extension/decimal/test_decimal.py

@@ -174,11 +174,12 @@ def test_series_repr(self, data):
         assert "Decimal: " in repr(ser)
 
 
-# TODO(extension)
 @pytest.mark.xfail(
     reason=(
-        "raising AssertionError as this is not implemented, though easy enough to do"
-    )
+        "DecimalArray constructor raises bc _from_sequence wants Decimals, not ints."
+        "Easy to fix, just need to do it."
+    ),
+    raises=TypeError,
 )
 def test_series_constructor_coerce_data_to_extension_dtype_raises():
     xpr = (

pandas/tests/indexes/categorical/test_indexing.py

@@ -300,8 +300,8 @@ def test_get_indexer_same_categories_different_order(self):
 
 
 class TestWhere:
-    def test_where(self, listlike_box_with_tuple):
-        klass = listlike_box_with_tuple
+    def test_where(self, listlike_box):
+        klass = listlike_box
 
         i = CategoricalIndex(list("aabbca"), categories=list("cab"), ordered=False)
         cond = [True] * len(i)

pandas/tests/indexes/common.py

@@ -375,8 +375,8 @@ def test_numpy_repeat(self, simple_index):
         with pytest.raises(ValueError, match=msg):
             np.repeat(idx, rep, axis=0)
 
-    def test_where(self, listlike_box_with_tuple, simple_index):
-        klass = listlike_box_with_tuple
+    def test_where(self, listlike_box, simple_index):
+        klass = listlike_box
 
         idx = simple_index
         if isinstance(idx, (DatetimeIndex, TimedeltaIndex)):

pandas/tests/indexes/conftest.py

@@ -33,19 +33,9 @@ def freq_sample(request):
     return request.param
 
 
-@pytest.fixture(params=[list, np.array, array, Series])
+@pytest.fixture(params=[list, tuple, np.array, array, Series])
 def listlike_box(request):
     """
     Types that may be passed as the indexer to searchsorted.
     """
     return request.param
-
-
-# TODO: not clear if this _needs_ to be different from listlike_box or
-#  if that is just a historical artifact
-@pytest.fixture(params=[list, tuple, np.array, Series])
-def listlike_box_with_tuple(request):
-    """
-    Types that may be passed as the indexer to searchsorted.
-    """
-    return request.param

pandas/tests/indexes/interval/test_base.py

@@ -43,8 +43,8 @@ def test_take(self, closed):
         expected = IntervalIndex.from_arrays([0, 0, 1], [1, 1, 2], closed=closed)
         tm.assert_index_equal(result, expected)
 
-    def test_where(self, simple_index, listlike_box_with_tuple):
-        klass = listlike_box_with_tuple
+    def test_where(self, simple_index, listlike_box):
+        klass = listlike_box
 
         idx = simple_index
         cond = [True] * len(idx)

pandas/tests/indexes/multi/test_indexing.py

@@ -720,12 +720,12 @@ def test_where(self):
         with pytest.raises(NotImplementedError, match=msg):
             i.where(True)
 
-    def test_where_array_like(self, listlike_box_with_tuple):
+    def test_where_array_like(self, listlike_box):
         mi = MultiIndex.from_tuples([("A", 1), ("A", 2)])
         cond = [False, True]
         msg = r"\.where is not supported for MultiIndex operations"
         with pytest.raises(NotImplementedError, match=msg):
-            mi.where(listlike_box_with_tuple(cond))
+            mi.where(listlike_box(cond))
 
 
 class TestContains:

pandas/tests/indexes/numeric/test_indexing.py

@@ -397,14 +397,14 @@ class TestWhere:
             UInt64Index(np.arange(5, dtype="uint64")),
         ],
     )
-    def test_where(self, listlike_box_with_tuple, index):
+    def test_where(self, listlike_box, index):
         cond = [True] * len(index)
         expected = index
-        result = index.where(listlike_box_with_tuple(cond))
+        result = index.where(listlike_box(cond))
 
         cond = [False] + [True] * (len(index) - 1)
         expected = Float64Index([index._na_value] + index[1:].tolist())
-        result = index.where(listlike_box_with_tuple(cond))
+        result = index.where(listlike_box(cond))
         tm.assert_index_equal(result, expected)
 
     def test_where_uint64(self):

pandas/tests/indexes/period/test_indexing.py

@@ -602,16 +602,16 @@ def test_get_indexer2(self):
 
 
 class TestWhere:
-    def test_where(self, listlike_box_with_tuple):
+    def test_where(self, listlike_box):
         i = period_range("20130101", periods=5, freq="D")
         cond = [True] * len(i)
         expected = i
-        result = i.where(listlike_box_with_tuple(cond))
+        result = i.where(listlike_box(cond))
         tm.assert_index_equal(result, expected)
 
         cond = [False] + [True] * (len(i) - 1)
         expected = PeriodIndex([NaT] + i[1:].tolist(), freq="D")
-        result = i.where(listlike_box_with_tuple(cond))
+        result = i.where(listlike_box(cond))
         tm.assert_index_equal(result, expected)
 
     def test_where_other(self):

pandas/tests/io/formats/style/test_html.py

@@ -488,8 +488,8 @@ def test_replaced_css_class_names(styler_mi):
         uuid_len=0,
     ).set_table_styles(css_class_names=css)
     styler_mi.index.names = ["n1", "n2"]
-    styler_mi.hide_index(styler_mi.index[1:])
-    styler_mi.hide_columns(styler_mi.columns[1:])
+    styler_mi.hide(styler_mi.index[1:], axis=0)
+    styler_mi.hide(styler_mi.columns[1:], axis=1)
     styler_mi.applymap_index(lambda v: "color: red;", axis=0)
     styler_mi.applymap_index(lambda v: "color: green;", axis=1)
     styler_mi.applymap(lambda v: "color: blue;")
@@ -611,9 +611,9 @@ def test_hiding_index_columns_multiindex_alignment():
     )
     df = DataFrame(np.arange(16).reshape(4, 4), index=midx, columns=cidx)
     styler = Styler(df, uuid_len=0)
-    styler.hide_index(level=1).hide_columns(level=0)
-    styler.hide_index([("j0", "i1", "j2")])
-    styler.hide_columns([("c0", "d1", "d2")])
+    styler.hide(level=1, axis=0).hide(level=0, axis=1)
+    styler.hide([("j0", "i1", "j2")], axis=0)
+    styler.hide([("c0", "d1", "d2")], axis=1)
     result = styler.to_html()
     expected = dedent(
         """\

pandas/tests/io/formats/style/test_style.py

@@ -1530,7 +1530,7 @@ def test_hiding_headers_over_index_no_sparsify():
     df = DataFrame(9, index=midx, columns=[0])
     ctx = df.style._translate(False, False)
     assert len(ctx["body"]) == 6
-    ctx = df.style.hide_index((1, "a"))._translate(False, False)
+    ctx = df.style.hide((1, "a"), axis=0)._translate(False, False)
     assert len(ctx["body"]) == 4
     assert "row2" in ctx["body"][0][0]["class"]
 

pandas/tests/io/formats/style/test_to_latex.py

@@ -803,7 +803,7 @@ def test_css_convert_apply_index(styler, axis):
 
 def test_hide_index_latex(styler):
     # GH 43637
-    styler.hide_index([0])
+    styler.hide([0], axis=0)
     result = styler.to_latex()
     expected = dedent(
         """\
@@ -826,9 +826,9 @@ def test_latex_hiding_index_columns_multiindex_alignment():
     )
     df = DataFrame(np.arange(16).reshape(4, 4), index=midx, columns=cidx)
     styler = Styler(df, uuid_len=0)
-    styler.hide_index(level=1).hide_columns(level=0)
-    styler.hide_index([("i0", "i1", "i2")])
-    styler.hide_columns([("c0", "c1", "c2")])
+    styler.hide(level=1, axis=0).hide(level=0, axis=1)
+    styler.hide([("i0", "i1", "i2")], axis=0)
+    styler.hide([("c0", "c1", "c2")], axis=1)
     styler.applymap(lambda x: "color:{red};" if x == 5 else "")
     styler.applymap_index(lambda x: "color:{blue};" if "j" in x else "")
     result = styler.to_latex()