CLN/TST: address/annotate TODOs (#44154)

Author: jbrockmendel

pandas/_libs/algos.pyx

@@ -947,7 +947,7 @@ def rank_1d(
 
     N = len(values)
     if labels is not None:
-        # TODO Cython 3.0: cast won't be necessary (#2992)
+        # TODO(cython3): cast won't be necessary (#2992)
         assert <Py_ssize_t>len(labels) == N
     out = np.empty(N)
     grp_sizes = np.ones(N, dtype=np.int64)
@@ -1086,7 +1086,7 @@ cdef void rank_sorted_1d(
     # array that we sorted previously, which gives us the location of
     # that sorted value for retrieval back from the original
     # values / masked_vals arrays
-    # TODO: de-duplicate once cython supports conditional nogil
+    # TODO(cython3): de-duplicate once cython supports conditional nogil
     if iu_64_floating_obj_t is object:
         with gil:
             for i in range(N):
@@ -1413,7 +1413,7 @@ ctypedef fused out_t:
 @cython.boundscheck(False)
 @cython.wraparound(False)
 def diff_2d(
-    ndarray[diff_t, ndim=2] arr,  # TODO(cython 3) update to "const diff_t[:, :] arr"
+    ndarray[diff_t, ndim=2] arr,  # TODO(cython3) update to "const diff_t[:, :] arr"
     ndarray[out_t, ndim=2] out,
     Py_ssize_t periods,
     int axis,
@@ -1422,7 +1422,7 @@ def diff_2d(
     cdef:
         Py_ssize_t i, j, sx, sy, start, stop
         bint f_contig = arr.flags.f_contiguous
-        # bint f_contig = arr.is_f_contig()  # TODO(cython 3)
+        # bint f_contig = arr.is_f_contig()  # TODO(cython3)
         diff_t left, right
 
     # Disable for unsupported dtype combinations,

pandas/_libs/groupby.pyx

@@ -963,7 +963,7 @@ def group_last(iu_64_floating_obj_t[:, ::1] out,
         ndarray[int64_t, ndim=2] nobs
         bint runtime_error = False
 
-    # TODO(cython 3.0):
+    # TODO(cython3):
     # Instead of `labels.shape[0]` use `len(labels)`
     if not len(values) == labels.shape[0]:
         raise AssertionError("len(index) != len(labels)")
@@ -978,7 +978,7 @@ def group_last(iu_64_floating_obj_t[:, ::1] out,
     N, K = (<object>values).shape
 
     if iu_64_floating_obj_t is object:
-        # TODO: De-duplicate once conditional-nogil is available
+        # TODO(cython3): De-duplicate once conditional-nogil is available
         for i in range(N):
             lab = labels[i]
             if lab < 0:
@@ -1057,7 +1057,7 @@ def group_nth(iu_64_floating_obj_t[:, ::1] out,
         ndarray[int64_t, ndim=2] nobs
         bint runtime_error = False
 
-    # TODO(cython 3.0):
+    # TODO(cython3):
     # Instead of `labels.shape[0]` use `len(labels)`
     if not len(values) == labels.shape[0]:
         raise AssertionError("len(index) != len(labels)")
@@ -1072,7 +1072,7 @@ def group_nth(iu_64_floating_obj_t[:, ::1] out,
     N, K = (<object>values).shape
 
     if iu_64_floating_obj_t is object:
-        # TODO: De-duplicate once conditional-nogil is available
+        # TODO(cython3): De-duplicate once conditional-nogil is available
         for i in range(N):
             lab = labels[i]
             if lab < 0:
@@ -1255,7 +1255,7 @@ cdef group_min_max(iu_64_floating_t[:, ::1] out,
         bint uses_mask = mask is not None
         bint isna_entry
 
-    # TODO(cython 3.0):
+    # TODO(cython3):
     # Instead of `labels.shape[0]` use `len(labels)`
     if not len(values) == labels.shape[0]:
         raise AssertionError("len(index) != len(labels)")

pandas/_libs/tslibs/nattype.pyx

@@ -166,7 +166,6 @@ cdef class _NaT(datetime):
 
         elif util.is_integer_object(other):
             # For Period compat
-            # TODO: the integer behavior is deprecated, remove it
             return c_NaT
 
         elif util.is_array(other):
@@ -201,7 +200,6 @@ cdef class _NaT(datetime):
 
         elif util.is_integer_object(other):
             # For Period compat
-            # TODO: the integer behavior is deprecated, remove it
             return c_NaT
 
         elif util.is_array(other):

pandas/_libs/tslibs/parsing.pyx

@@ -671,7 +671,7 @@ def try_parse_date_and_time(
         object[:] result
 
     n = len(dates)
-    # TODO(cython 3.0): Use len instead of `shape[0]`
+    # TODO(cython3): Use len instead of `shape[0]`
     if times.shape[0] != n:
         raise ValueError('Length of dates and times must be equal')
     result = np.empty(n, dtype='O')
@@ -709,7 +709,7 @@ def try_parse_year_month_day(
         object[:] result
 
     n = len(years)
-    # TODO(cython 3.0): Use len instead of `shape[0]`
+    # TODO(cython3): Use len instead of `shape[0]`
     if months.shape[0] != n or days.shape[0] != n:
         raise ValueError('Length of years/months/days must all be equal')
     result = np.empty(n, dtype='O')
@@ -735,7 +735,7 @@ def try_parse_datetime_components(object[:] years,
         double micros
 
     n = len(years)
-    # TODO(cython 3.0): Use len instead of `shape[0]`
+    # TODO(cython3): Use len instead of `shape[0]`
     if (
         months.shape[0] != n
         or days.shape[0] != n

pandas/core/window/rolling.py

@@ -136,7 +136,7 @@ def __init__(
         self.window = window
         self.min_periods = min_periods
         self.center = center
-        # TODO: Change this back to self.win_type once deprecation is enforced
+        # TODO(2.0): Change this back to self.win_type once deprecation is enforced
         self._win_type = win_type
         self.axis = obj._get_axis_number(axis) if axis is not None else None
         self.method = method
@@ -262,7 +262,7 @@ def _gotitem(self, key, ndim, subset=None):
         # we need to make a shallow copy of ourselves
         # with the same groupby
         with warnings.catch_warnings():
-            # TODO: Remove once win_type deprecation is enforced
+            # TODO(2.0): Remove once win_type deprecation is enforced
             warnings.filterwarnings("ignore", "win_type", FutureWarning)
             kwargs = {attr: getattr(self, attr) for attr in self._attributes}
 

pandas/io/parsers/readers.py

@@ -606,7 +606,7 @@ def read_csv(
     # Error Handling
     error_bad_lines=None,
     warn_bad_lines=None,
-    # TODO (2.0): set on_bad_lines to "error".
+    # TODO(2.0): set on_bad_lines to "error".
     # See _refine_defaults_read comment for why we do this.
     on_bad_lines=None,
     # Internal
@@ -704,7 +704,7 @@ def read_table(
     # Error Handling
     error_bad_lines=None,
     warn_bad_lines=None,
-    # TODO (2.0): set on_bad_lines to "error".
+    # TODO(2.0): set on_bad_lines to "error".
     # See _refine_defaults_read comment for why we do this.
     on_bad_lines=None,
     # Internal

pandas/io/stata.py

@@ -338,8 +338,8 @@ def convert_delta_safe(base, deltas, unit) -> Series:
         deltas = to_timedelta(deltas, unit=unit)
         return base + deltas
 
-    # TODO: If/when pandas supports more than datetime64[ns], this should be
-    # improved to use correct range, e.g. datetime[Y] for yearly
+    # TODO(non-nano): If/when pandas supports more than datetime64[ns], this
+    #  should be improved to use correct range, e.g. datetime[Y] for yearly
     bad_locs = np.isnan(dates)
     has_bad_values = False
     if bad_locs.any():

pandas/tests/arrays/sparse/test_array.py

@@ -1203,7 +1203,7 @@ def test_from_coo(self):
         row = [0, 3, 1, 0]
         col = [0, 3, 1, 2]
         data = [4, 5, 7, 9]
-        # TODO: Remove dtype when scipy is fixed
+        # TODO(scipy#13585): Remove dtype when scipy is fixed
         # https://github.com/scipy/scipy/issues/13585
         sp_array = scipy.sparse.coo_matrix((data, (row, col)), dtype="int")
         result = pd.Series.sparse.from_coo(sp_array)

pandas/tests/frame/methods/test_join.py

@@ -143,15 +143,14 @@ def test_join_index_more(float_frame):
 
 def test_join_index_series(float_frame):
     df = float_frame.copy()
-    s = df.pop(float_frame.columns[-1])
-    joined = df.join(s)
+    ser = df.pop(float_frame.columns[-1])
+    joined = df.join(ser)
 
-    # TODO should this check_names ?
-    tm.assert_frame_equal(joined, float_frame, check_names=False)
+    tm.assert_frame_equal(joined, float_frame)
 
-    s.name = None
+    ser.name = None
     with pytest.raises(ValueError, match="must have a name"):
-        df.join(s)
+        df.join(ser)
 
 
 def test_join_overlap(float_frame):
@@ -241,8 +240,7 @@ def test_join(self, multiindex_dataframe_random_data):
 
         assert not np.isnan(joined.values).all()
 
-        # TODO what should join do with names ?
-        tm.assert_frame_equal(joined, expected, check_names=False)
+        tm.assert_frame_equal(joined, expected)
 
     def test_join_segfault(self):
         # GH#1532

pandas/tests/frame/methods/test_reset_index.py

@@ -144,32 +144,31 @@ def test_reset_index(self, float_frame):
         df = float_frame.reset_index().set_index(["index", "A", "B"])
         rs = df.reset_index(["A", "B"])
 
-        # TODO should reset_index check_names ?
-        tm.assert_frame_equal(rs, float_frame, check_names=False)
+        tm.assert_frame_equal(rs, float_frame)
 
         rs = df.reset_index(["index", "A", "B"])
-        tm.assert_frame_equal(rs, float_frame.reset_index(), check_names=False)
+        tm.assert_frame_equal(rs, float_frame.reset_index())
 
         rs = df.reset_index(["index", "A", "B"])
-        tm.assert_frame_equal(rs, float_frame.reset_index(), check_names=False)
+        tm.assert_frame_equal(rs, float_frame.reset_index())
 
         rs = df.reset_index("A")
         xp = float_frame.reset_index().set_index(["index", "B"])
-        tm.assert_frame_equal(rs, xp, check_names=False)
+        tm.assert_frame_equal(rs, xp)
 
         # test resetting in place
         df = float_frame.copy()
         reset = float_frame.reset_index()
         return_value = df.reset_index(inplace=True)
         assert return_value is None
-        tm.assert_frame_equal(df, reset, check_names=False)
+        tm.assert_frame_equal(df, reset)
 
         df = float_frame.reset_index().set_index(["index", "A", "B"])
         rs = df.reset_index("A", drop=True)
         xp = float_frame.copy()
         del xp["A"]
         xp = xp.set_index(["B"], append=True)
-        tm.assert_frame_equal(rs, xp, check_names=False)
+        tm.assert_frame_equal(rs, xp)
 
     def test_reset_index_name(self):
         df = DataFrame(