CLN: TODOs/noqas/xfails (#44586)

Author: jbrockmendel

asv_bench/benchmarks/pandas_vb_common.py

@@ -17,7 +17,7 @@
 try:
     import pandas._testing as tm
 except ImportError:
-    import pandas.util.testing as tm  # noqa
+    import pandas.util.testing as tm  # noqa:F401
 
 
 numeric_dtypes = [

pandas/core/tools/datetimes.py

@@ -28,7 +28,7 @@
     nat_strings,
     parsing,
 )
-from pandas._libs.tslibs.parsing import (  # noqa
+from pandas._libs.tslibs.parsing import (  # noqa:F401
     DateParseError,
     format_is_iso,
     guess_datetime_format,

pandas/io/parquet.py

@@ -151,7 +151,7 @@ def __init__(self):
         import pyarrow.parquet
 
         # import utils to register the pyarrow extension types
-        import pandas.core.arrays._arrow_utils  # noqa
+        import pandas.core.arrays._arrow_utils  # noqa:F401
 
         self.api = pyarrow
 

pandas/tests/arrays/categorical/test_constructors.py

@@ -236,14 +236,14 @@ def test_constructor(self):
         #  - when the first is an integer dtype and the second is not
         #  - when the resulting codes are all -1/NaN
         with tm.assert_produces_warning(None):
-            c_old = Categorical([0, 1, 2, 0, 1, 2], categories=["a", "b", "c"])
+            Categorical([0, 1, 2, 0, 1, 2], categories=["a", "b", "c"])
 
         with tm.assert_produces_warning(None):
-            c_old = Categorical([0, 1, 2, 0, 1, 2], categories=[3, 4, 5])  # noqa
+            Categorical([0, 1, 2, 0, 1, 2], categories=[3, 4, 5])
 
         # the next one are from the old docs
         with tm.assert_produces_warning(None):
-            c_old2 = Categorical([0, 1, 2, 0, 1, 2], [1, 2, 3])  # noqa
+            Categorical([0, 1, 2, 0, 1, 2], [1, 2, 3])
             cat = Categorical([1, 2], categories=[1, 2, 3])
 
         # this is a legitimate constructor

pandas/tests/arrays/sparse/test_libsparse.py

@@ -460,11 +460,10 @@ def test_check_integrity(self):
         lengths = []
 
         # 0-length OK
-        # TODO: index variables are not used...is that right?
-        index = BlockIndex(0, locs, lengths)
+        BlockIndex(0, locs, lengths)
 
         # also OK even though empty
-        index = BlockIndex(1, locs, lengths)  # noqa
+        BlockIndex(1, locs, lengths)
 
         msg = "Block 0 extends beyond end"
         with pytest.raises(ValueError, match=msg):

pandas/tests/extension/base/dim2.py

@@ -4,6 +4,7 @@
 import numpy as np
 import pytest
 
+from pandas._libs.missing import is_matching_na
 from pandas.compat import (
     IS64,
     is_platform_windows,
@@ -175,7 +176,7 @@ def test_reductions_2d_axis_none(self, data, method, request):
             assert type(err_result) == type(err_expected)
             return
 
-        assert result == expected  # TODO: or matching NA
+        assert is_matching_na(result, expected) or result == expected
 
     @pytest.mark.parametrize("method", ["mean", "median", "var", "std", "sum", "prod"])
     def test_reductions_2d_axis0(self, data, method, request):
@@ -254,8 +255,5 @@ def test_reductions_2d_axis1(self, data, method, request):
         # not necessarily type/dtype-preserving, so weaker assertions
         assert result.shape == (1,)
         expected_scalar = getattr(data, method)()
-        if pd.isna(result[0]):
-            # TODO: require matching NA
-            assert pd.isna(expected_scalar), expected_scalar
-        else:
-            assert result[0] == expected_scalar
+        res = result[0]
+        assert is_matching_na(res, expected_scalar) or res == expected_scalar

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -57,8 +57,6 @@ def test_agg_must_agg(df):
 
 
 def test_agg_ser_multi_key(df):
-    # TODO(wesm): unused
-    ser = df.C  # noqa
 
     f = lambda x: x.sum()
     results = df.C.groupby([df.A, df.B]).aggregate(f)

pandas/tests/indexing/test_coercion.py

@@ -780,7 +780,6 @@ def test_where_index_datetime(self, fill_val):
 
         self._assert_where_conversion(obj, cond, values, exp, exp_dtype)
 
-    @pytest.mark.xfail(reason="GH 22839: do not ignore timezone, must be object")
     def test_where_index_datetime64tz(self):
         fill_val = pd.Timestamp("2012-01-01", tz="US/Eastern")
         exp_dtype = object
@@ -795,9 +794,9 @@ def test_where_index_datetime64tz(self):
         assert obj.dtype == "datetime64[ns]"
         cond = pd.Index([True, False, True, False])
 
-        msg = "Index\\(\\.\\.\\.\\) must be called with a collection of some kind"
-        with pytest.raises(TypeError, match=msg):
-            obj.where(cond, fill_val)
+        res = obj.where(cond, fill_val)
+        expected = pd.Index([obj[0], fill_val, obj[2], fill_val], dtype=object)
+        tm.assert_index_equal(res, expected)
 
         values = pd.Index(pd.date_range(fill_val, periods=4))
         exp = pd.Index(

pandas/tests/io/pytables/test_append.py

@@ -896,9 +896,7 @@ def test_append_to_multiple_dropna(setup_path):
         tm.assert_index_equal(store.select("df1").index, store.select("df2").index)
 
 
-@pytest.mark.xfail(
-    run=False, reason="append_to_multiple_dropna_false is not raising as failed"
-)
+@pytest.mark.xfail(reason="append_to_multiple_dropna_false is not raising as failed")
 def test_append_to_multiple_dropna_false(setup_path):
     df1 = tm.makeTimeDataFrame()
     df2 = tm.makeTimeDataFrame().rename(columns="{}_2".format)

pandas/tests/io/pytables/test_select.py

@@ -265,7 +265,7 @@ def test_select_dtypes(setup_path):
         expected = df[df["A"] > 0]
 
         store.append("df", df, data_columns=True)
-        np_zero = np.float64(0)  # noqa
+        np_zero = np.float64(0)  # noqa:F841
         result = store.select("df", where=["A>np_zero"])
         tm.assert_frame_equal(expected, result)
 
@@ -683,17 +683,17 @@ def test_frame_select_complex2(setup_path):
         expected = read_hdf(hh, "df", where="l1=[2, 3, 4]")
 
         # scope with list like
-        l = selection.index.tolist()  # noqa
+        l0 = selection.index.tolist()  # noqa:F841
         store = HDFStore(hh)
-        result = store.select("df", where="l1=l")
+        result = store.select("df", where="l1=l0")
         tm.assert_frame_equal(result, expected)
         store.close()
 
-        result = read_hdf(hh, "df", where="l1=l")
+        result = read_hdf(hh, "df", where="l1=l0")
         tm.assert_frame_equal(result, expected)
 
         # index
-        index = selection.index  # noqa
+        index = selection.index  # noqa:F841
         result = read_hdf(hh, "df", where="l1=index")
         tm.assert_frame_equal(result, expected)
 
@@ -928,7 +928,7 @@ def test_query_compare_column_type(setup_path):
     with ensure_clean_store(setup_path) as store:
         store.append("test", df, format="table", data_columns=True)
 
-        ts = Timestamp("2014-01-01")  # noqa
+        ts = Timestamp("2014-01-01")  # noqa:F841
         result = store.select("test", where="real_date > ts")
         expected = df.loc[[1], :]
         tm.assert_frame_equal(expected, result)