CLN: address TODOs/FIXMEs (#44348)

Author: jbrockmendel

pandas/core/frame.py

@@ -3732,6 +3732,9 @@ def _setitem_array(self, key, value):
             self.iloc[indexer] = value
 
         else:
+            # Note: unlike self.iloc[:, indexer] = value, this will
+            #  never try to overwrite values inplace
+
             if isinstance(value, DataFrame):
                 check_key_length(self.columns, key, value)
                 for k1, k2 in zip(key, value.columns):

pandas/core/internals/managers.py

@@ -1045,8 +1045,7 @@ def iset(
             self._rebuild_blknos_and_blklocs()
 
         # Note: we exclude DTA/TDA here
-        vdtype = getattr(value, "dtype", None)
-        value_is_extension_type = is_1d_only_ea_dtype(vdtype)
+        value_is_extension_type = is_1d_only_ea_dtype(value.dtype)
 
         # categorical/sparse/datetimetz
         if value_is_extension_type:

pandas/core/series.py

@@ -4538,6 +4538,7 @@ def rename(
         dtype: int64
         """
         if axis is not None:
+            # Make sure we raise if an invalid 'axis' is passed.
             axis = self._get_axis_number(axis)
 
         if callable(index) or is_dict_like(index):

pandas/tests/frame/methods/test_quantile.py

@@ -617,7 +617,7 @@ def test_quantile_ea_with_na(self, obj, index):
         expected = type(obj)(expected)
         tm.assert_equal(result, expected)
 
-    # TODO: filtering can be removed after GH#39763 is fixed
+    # TODO(GH#39763): filtering can be removed after GH#39763 is fixed
     @pytest.mark.filterwarnings("ignore:Using .astype to convert:FutureWarning")
     def test_quantile_ea_all_na(self, obj, index, frame_or_series):
 

pandas/tests/frame/test_constructors.py

@@ -2585,6 +2585,19 @@ def test_error_from_2darray(self, col_a, col_b):
             DataFrame({"a": col_a, "b": col_b})
 
 
+class TestDataFrameConstructorIndexInference:
+    def test_frame_from_dict_of_series_overlapping_monthly_period_indexes(self):
+        rng1 = pd.period_range("1/1/1999", "1/1/2012", freq="M")
+        s1 = Series(np.random.randn(len(rng1)), rng1)
+
+        rng2 = pd.period_range("1/1/1980", "12/1/2001", freq="M")
+        s2 = Series(np.random.randn(len(rng2)), rng2)
+        df = DataFrame({"s1": s1, "s2": s2})
+
+        exp = pd.period_range("1/1/1980", "1/1/2012", freq="M")
+        tm.assert_index_equal(df.index, exp)
+
+
 class TestDataFrameConstructorWithDtypeCoercion:
     def test_floating_values_integer_dtype(self):
         # GH#40110 make DataFrame behavior with arraylike floating data and

pandas/tests/indexes/base_class/test_setops.py

@@ -90,15 +90,15 @@ def test_union_sort_other_incomparable(self):
 
     @pytest.mark.xfail(reason="GH#25151 need to decide on True behavior")
     def test_union_sort_other_incomparable_true(self):
-        # TODO decide on True behaviour
+        # TODO(GH#25151): decide on True behaviour
         # sort=True
         idx = Index([1, pd.Timestamp("2000")])
         with pytest.raises(TypeError, match=".*"):
             idx.union(idx[:1], sort=True)
 
     @pytest.mark.xfail(reason="GH#25151 need to decide on True behavior")
     def test_intersection_equal_sort_true(self):
-        # TODO decide on True behaviour
+        # TODO(GH#25151): decide on True behaviour
         idx = Index(["c", "a", "b"])
         sorted_ = Index(["a", "b", "c"])
         tm.assert_index_equal(idx.intersection(idx, sort=True), sorted_)

pandas/tests/indexes/datetimes/test_date_range.py

@@ -746,7 +746,7 @@ def test_cached_range_bug(self):
         assert len(rng) == 50
         assert rng[0] == datetime(2010, 9, 1, 5)
 
-    def test_timezone_comparaison_bug(self):
+    def test_timezone_comparison_bug(self):
         # smoke test
         start = Timestamp("20130220 10:00", tz="US/Eastern")
         result = date_range(start, periods=2, tz="US/Eastern")

pandas/tests/indexes/multi/test_setops.py

@@ -203,7 +203,7 @@ def test_difference_sort_special():
 
 @pytest.mark.xfail(reason="Not implemented.")
 def test_difference_sort_special_true():
-    # TODO decide on True behaviour
+    # TODO(GH#25151): decide on True behaviour
     idx = MultiIndex.from_product([[1, 0], ["a", "b"]])
     result = idx.difference([], sort=True)
     expected = MultiIndex.from_product([[0, 1], ["a", "b"]])
@@ -340,7 +340,7 @@ def test_intersect_equal_sort():
 
 @pytest.mark.xfail(reason="Not implemented.")
 def test_intersect_equal_sort_true():
-    # TODO decide on True behaviour
+    # TODO(GH#25151): decide on True behaviour
     idx = MultiIndex.from_product([[1, 0], ["a", "b"]])
     sorted_ = MultiIndex.from_product([[0, 1], ["a", "b"]])
     tm.assert_index_equal(idx.intersection(idx, sort=True), sorted_)
@@ -363,7 +363,7 @@ def test_union_sort_other_empty(slice_):
 
 @pytest.mark.xfail(reason="Not implemented.")
 def test_union_sort_other_empty_sort(slice_):
-    # TODO decide on True behaviour
+    # TODO(GH#25151): decide on True behaviour
     # # sort=True
     idx = MultiIndex.from_product([[1, 0], ["a", "b"]])
     other = idx[:0]
@@ -388,7 +388,7 @@ def test_union_sort_other_incomparable():
 
 @pytest.mark.xfail(reason="Not implemented.")
 def test_union_sort_other_incomparable_sort():
-    # TODO decide on True behaviour
+    # TODO(GH#25151): decide on True behaviour
     # # sort=True
     idx = MultiIndex.from_product([[1, pd.Timestamp("2000")], ["a", "b"]])
     with pytest.raises(TypeError, match="Cannot compare"):

pandas/tests/indexes/numeric/test_setops.py

@@ -155,7 +155,7 @@ def test_union_sort_other_special(self, slice_):
     @pytest.mark.xfail(reason="Not implemented")
     @pytest.mark.parametrize("slice_", [slice(None), slice(0)])
     def test_union_sort_special_true(self, slice_):
-        # TODO: decide on True behaviour
+        # TODO(GH#25151): decide on True behaviour
         # sort=True
         idx = Index([1, 0, 2])
         # default, sort=None

pandas/tests/indexes/period/test_setops.py

@@ -153,18 +153,6 @@ def test_union_misc(self, sort):
         expected = index.astype(object).union(index2.astype(object), sort=sort)
         tm.assert_index_equal(result, expected)
 
-    # TODO: belongs elsewhere
-    def test_union_dataframe_index(self):
-        rng1 = period_range("1/1/1999", "1/1/2012", freq="M")
-        s1 = pd.Series(np.random.randn(len(rng1)), rng1)
-
-        rng2 = period_range("1/1/1980", "12/1/2001", freq="M")
-        s2 = pd.Series(np.random.randn(len(rng2)), rng2)
-        df = pd.DataFrame({"s1": s1, "s2": s2})
-
-        exp = period_range("1/1/1980", "1/1/2012", freq="M")
-        tm.assert_index_equal(df.index, exp)
-
     def test_intersection(self, sort):
         index = period_range("1/1/2000", "1/20/2000", freq="D")
 

pandas/tests/indexes/ranges/test_range.py

@@ -204,10 +204,10 @@ def test_delete_preserves_rangeindex_list_middle(self):
         loc = [1, 2, 3, 4]
         result = idx.delete(loc)
         expected = RangeIndex(0, 6, 5)
-        tm.assert_index_equal(result, expected, exact="equiv")  # TODO: retain!
+        tm.assert_index_equal(result, expected, exact=True)
 
         result = idx.delete(loc[::-1])
-        tm.assert_index_equal(result, expected, exact="equiv")  # TODO: retain!
+        tm.assert_index_equal(result, expected, exact=True)
 
     def test_delete_all_preserves_rangeindex(self):
         idx = RangeIndex(0, 6, 1)

pandas/tests/indexes/test_base.py

@@ -525,20 +525,6 @@ def test_asof_numeric_vs_bool_raises(self):
         with pytest.raises(TypeError, match=msg):
             right.asof(left)
 
-    # TODO: this tests Series.asof
-    def test_asof_nanosecond_index_access(self):
-        s = Timestamp("20130101").value
-        r = DatetimeIndex([s + 50 + i for i in range(100)])
-        ser = Series(np.random.randn(100), index=r)
-
-        first_value = ser.asof(ser.index[0])
-
-        # this does not yet work, as parsing strings is done via dateutil
-        # assert first_value == x['2013-01-01 00:00:00.000000050+0000']
-
-        expected_ts = np_datetime64_compat("2013-01-01 00:00:00.000000050+0000", "ns")
-        assert first_value == ser[Timestamp(expected_ts)]
-
     @pytest.mark.parametrize("index", ["string"], indirect=True)
     def test_booleanindex(self, index):
         bool_index = np.ones(len(index), dtype=bool)

pandas/tests/indexes/test_setops.py

@@ -773,7 +773,7 @@ def test_difference_incomparable(self, opname):
     @pytest.mark.xfail(reason="Not implemented")
     @pytest.mark.parametrize("opname", ["difference", "symmetric_difference"])
     def test_difference_incomparable_true(self, opname):
-        # TODO: decide on True behaviour
+        # TODO(GH#25151): decide on True behaviour
         # # sort=True, raises
         a = Index([3, Timestamp("2000"), 1])
         b = Index([2, Timestamp("1999"), 1])

pandas/tests/indexing/test_iloc.py

@@ -96,10 +96,7 @@ def test_iloc_setitem_fullcol_categorical(self, indexer, key, using_array_manage
 
         # check we dont have a view on cat (may be undesired GH#39986)
         df.iloc[0, 0] = "gamma"
-        if overwrite:
-            assert cat[0] != "gamma"
-        else:
-            assert cat[0] != "gamma"
+        assert cat[0] != "gamma"
 
         # TODO with mixed dataframe ("split" path), we always overwrite the column
         frame = DataFrame({0: np.array([0, 1, 2], dtype=object), 1: range(3)})

pandas/tests/indexing/test_indexing.py

@@ -129,6 +129,21 @@ def test_setitem_ndarray_3d(self, index, frame_or_series, indexer_sli):
         with pytest.raises(err, match=msg):
             idxr[nd3] = 0
 
+    def test_getitem_ndarray_0d(self):
+        # GH#24924
+        key = np.array(0)
+
+        # dataframe __getitem__
+        df = DataFrame([[1, 2], [3, 4]])
+        result = df[key]
+        expected = Series([1, 3], name=0)
+        tm.assert_series_equal(result, expected)
+
+        # series __getitem__
+        ser = Series([1, 2])
+        result = ser[key]
+        assert result == 1
+
     def test_inf_upcast(self):
         # GH 16957
         # We should be able to use np.inf as a key

pandas/tests/indexing/test_loc.py

@@ -6,7 +6,6 @@
     time,
     timedelta,
 )
-from io import StringIO
 import re
 
 from dateutil.tz import gettz
@@ -558,15 +557,27 @@ def test_loc_setitem_consistency_empty(self):
     def test_loc_setitem_consistency_slice_column_len(self):
         # .loc[:,column] setting with slice == len of the column
         # GH10408
-        data = """Level_0,,,Respondent,Respondent,Respondent,OtherCat,OtherCat
-Level_1,,,Something,StartDate,EndDate,Yes/No,SomethingElse
-Region,Site,RespondentID,,,,,
-Region_1,Site_1,3987227376,A,5/25/2015 10:59,5/25/2015 11:22,Yes,
-Region_1,Site_1,3980680971,A,5/21/2015 9:40,5/21/2015 9:52,Yes,Yes
-Region_1,Site_2,3977723249,A,5/20/2015 8:27,5/20/2015 8:41,Yes,
-Region_1,Site_2,3977723089,A,5/20/2015 8:33,5/20/2015 9:09,Yes,No"""
-
-        df = pd.read_csv(StringIO(data), header=[0, 1], index_col=[0, 1, 2])
+        levels = [
+            ["Region_1"] * 4,
+            ["Site_1", "Site_1", "Site_2", "Site_2"],
+            [3987227376, 3980680971, 3977723249, 3977723089],
+        ]
+        mi = MultiIndex.from_arrays(levels, names=["Region", "Site", "RespondentID"])
+
+        clevels = [
+            ["Respondent", "Respondent", "Respondent", "OtherCat", "OtherCat"],
+            ["Something", "StartDate", "EndDate", "Yes/No", "SomethingElse"],
+        ]
+        cols = MultiIndex.from_arrays(clevels, names=["Level_0", "Level_1"])
+
+        values = [
+            ["A", "5/25/2015 10:59", "5/25/2015 11:22", "Yes", np.nan],
+            ["A", "5/21/2015 9:40", "5/21/2015 9:52", "Yes", "Yes"],
+            ["A", "5/20/2015 8:27", "5/20/2015 8:41", "Yes", np.nan],
+            ["A", "5/20/2015 8:33", "5/20/2015 9:09", "Yes", "No"],
+        ]
+        df = DataFrame(values, index=mi, columns=cols)
+
         df.loc[:, ("Respondent", "StartDate")] = to_datetime(
             df.loc[:, ("Respondent", "StartDate")]
         )

pandas/tests/indexing/test_scalar.py

@@ -74,8 +74,8 @@ def _check(f, func, values=False):
             _check(f, "at")
 
 
-class TestScalar2:
-    # TODO: Better name, just separating things that dont need Base class
+class TestAtAndiAT:
+    # at and iat tests that don't need Base class
 
     def test_at_iat_coercion(self):
 
@@ -214,19 +214,6 @@ def test_iat_setter_incompatible_assignment(self):
         expected = DataFrame({"a": [None, 1], "b": [4, 5]})
         tm.assert_frame_equal(result, expected)
 
-    def test_getitem_zerodim_np_array(self):
-        # GH24924
-        # dataframe __getitem__
-        df = DataFrame([[1, 2], [3, 4]])
-        result = df[np.array(0)]
-        expected = Series([1, 3], name=0)
-        tm.assert_series_equal(result, expected)
-
-        # series __getitem__
-        s = Series([1, 2])
-        result = s[np.array(0)]
-        assert result == 1
-
 
 def test_iat_dont_wrap_object_datetimelike():
     # GH#32809 .iat calls go through DataFrame._get_value, should not

pandas/tests/io/formats/test_console.py

@@ -5,7 +5,7 @@
 from pandas._config import detect_console_encoding
 
 
-class MockEncoding:  # TODO(py27): replace with mock
+class MockEncoding:
     """
     Used to add a side effect when accessing the 'encoding' property. If the
     side effect is a str in nature, the value will be returned. Otherwise, the

pandas/tests/plotting/test_backend.py

@@ -71,7 +71,7 @@ def test_register_entrypoint(restore_backend):
     result = pandas.plotting._core._get_plot_backend("my_backend")
     assert result is mod
 
-    # TODO: https://github.com/pandas-dev/pandas/issues/27517
+    # TODO(GH#27517): https://github.com/pandas-dev/pandas/issues/27517
     # Remove the td.skip_if_no_mpl
     with pandas.option_context("plotting.backend", "my_backend"):
         result = pandas.plotting._core._get_plot_backend()

pandas/tests/reshape/test_melt.py

@@ -671,13 +671,12 @@ def test_simple(self):
         tm.assert_frame_equal(result, expected)
 
     def test_stubs(self):
-        # GH9204
+        # GH9204 wide_to_long call should not modify 'stubs' list
         df = DataFrame([[0, 1, 2, 3, 8], [4, 5, 6, 7, 9]])
         df.columns = ["id", "inc1", "inc2", "edu1", "edu2"]
         stubs = ["inc", "edu"]
 
-        # TODO: unused?
-        df_long = wide_to_long(df, stubs, i="id", j="age")  # noqa
+        wide_to_long(df, stubs, i="id", j="age")
 
         assert stubs == ["inc", "edu"]
 

pandas/tests/scalar/period/test_asfreq.py

@@ -428,9 +428,6 @@ def test_conv_daily(self):
         ival_D_saturday = Period(freq="D", year=2007, month=1, day=6)
         ival_D_sunday = Period(freq="D", year=2007, month=1, day=7)
 
-        # TODO: unused?
-        # ival_D_monday = Period(freq='D', year=2007, month=1, day=8)
-
         ival_B_friday = Period(freq="B", year=2007, month=1, day=5)
         ival_B_monday = Period(freq="B", year=2007, month=1, day=8)
 

pandas/tests/series/methods/test_asof.py

@@ -2,8 +2,10 @@
 import pytest
 
 from pandas._libs.tslibs import IncompatibleFrequency
+from pandas.compat import np_datetime64_compat
 
 from pandas import (
+    DatetimeIndex,
     Series,
     Timestamp,
     date_range,
@@ -15,6 +17,20 @@
 
 
 class TestSeriesAsof:
+    def test_asof_nanosecond_index_access(self):
+        ts = Timestamp("20130101").value
+        dti = DatetimeIndex([ts + 50 + i for i in range(100)])
+        ser = Series(np.random.randn(100), index=dti)
+
+        first_value = ser.asof(ser.index[0])
+
+        # this used to not work bc parsing was done by dateutil that didn't
+        #  handle nanoseconds
+        assert first_value == ser["2013-01-01 00:00:00.000000050+0000"]
+
+        expected_ts = np_datetime64_compat("2013-01-01 00:00:00.000000050+0000", "ns")
+        assert first_value == ser[Timestamp(expected_ts)]
+
     def test_basic(self):
 
         # array or list or dates

pandas/tests/series/test_logical_ops.py

@@ -49,9 +49,6 @@ def test_logical_operators_bool_dtype_with_empty(self):
     def test_logical_operators_int_dtype_with_int_dtype(self):
         # GH#9016: support bitwise op for integer types
 
-        # TODO: unused
-        # s_0101 = Series([0, 1, 0, 1])
-
         s_0123 = Series(range(4), dtype="int64")
         s_3333 = Series([3] * 4)
         s_4444 = Series([4] * 4)