CLN: xfails, FIXMEs (#44804)

Author: jbrockmendel

pandas/_testing/_warnings.py

@@ -149,15 +149,14 @@ def _assert_caught_no_extra_warnings(
         if _is_unexpected_warning(actual_warning, expected_warning):
             # GH 44732: Don't make the CI flaky by filtering SSL-related
             # ResourceWarning from dependencies
+            # GH#38630 pytest.filterwarnings does not suppress these.
             unclosed_ssl = (
                 "unclosed transport <asyncio.sslproto._SSLProtocolTransport",
                 "unclosed <ssl.SSLSocket",
             )
             if actual_warning.category == ResourceWarning and any(
                 msg in str(actual_warning.message) for msg in unclosed_ssl
             ):
-                # FIXME(GH#38630): kludge because pytest.filterwarnings does not
-                #  suppress these
                 continue
 
             extra_warnings.append(

pandas/core/arraylike.py

@@ -367,10 +367,12 @@ def reconstruct(result):
         return result
 
     if "out" in kwargs:
+        # e.g. test_multiindex_get_loc
         result = dispatch_ufunc_with_out(self, ufunc, method, *inputs, **kwargs)
         return reconstruct(result)
 
     if method == "reduce":
+        # e.g. test.series.test_ufunc.test_reduce
         result = dispatch_reduction_ufunc(self, ufunc, method, *inputs, **kwargs)
         if result is not NotImplemented:
             return result

pandas/core/arrays/interval.py

@@ -800,10 +800,12 @@ def min(self, *, axis: int | None = None, skipna: bool = True):
         if mask.any():
             if not skipna:
                 return self._na_value
-            return self[~mask].min()
+            obj = self[~mask]
+        else:
+            obj = self
 
-        indexer = self.argsort()[0]
-        return self[indexer]
+        indexer = obj.argsort()[0]
+        return obj[indexer]
 
     def max(self, *, axis: int | None = None, skipna: bool = True):
         nv.validate_minmax_axis(axis, self.ndim)
@@ -815,10 +817,12 @@ def max(self, *, axis: int | None = None, skipna: bool = True):
         if mask.any():
             if not skipna:
                 return self._na_value
-            return self[~mask].max()
+            obj = self[~mask]
+        else:
+            obj = self
 
-        indexer = self.argsort()[-1]
-        return self[indexer]
+        indexer = obj.argsort()[-1]
+        return obj[indexer]
 
     def fillna(
         self: IntervalArrayT, value=None, method=None, limit=None

pandas/core/arrays/numpy_.py

@@ -137,23 +137,12 @@ def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
         # The primary modification is not boxing scalar return values
         # in PandasArray, since pandas' ExtensionArrays are 1-d.
         out = kwargs.get("out", ())
-        for x in inputs + out:
-            # Only support operations with instances of _HANDLED_TYPES.
-            # Use PandasArray instead of type(self) for isinstance to
-            # allow subclasses that don't override __array_ufunc__ to
-            # handle PandasArray objects.
-            if not isinstance(x, self._HANDLED_TYPES + (PandasArray,)):
-                return NotImplemented
-
-        if ufunc not in [np.logical_or, np.bitwise_or, np.bitwise_xor]:
-            # For binary ops, use our custom dunder methods
-            # We haven't implemented logical dunder funcs, so exclude these
-            #  to avoid RecursionError
-            result = ops.maybe_dispatch_ufunc_to_dunder_op(
-                self, ufunc, method, *inputs, **kwargs
-            )
-            if result is not NotImplemented:
-                return result
+
+        result = ops.maybe_dispatch_ufunc_to_dunder_op(
+            self, ufunc, method, *inputs, **kwargs
+        )
+        if result is not NotImplemented:
+            return result
 
         # Defer to the implementation of the ufunc on unwrapped values.
         inputs = tuple(x._ndarray if isinstance(x, PandasArray) else x for x in inputs)

pandas/core/indexes/period.py

@@ -230,6 +230,10 @@ def __new__(
 
         if data is None and ordinal is None:
             # range-based.
+            if not fields:
+                # test_pickle_compat_construction
+                raise cls._scalar_data_error(None)
+
             data, freq2 = PeriodArray._generate_range(None, None, None, freq, fields)
             # PeriodArray._generate range does validation that fields is
             # empty when really using the range-based constructor.

pandas/tests/frame/methods/test_fillna.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-import pandas.util._test_decorators as td
-
 from pandas import (
     Categorical,
     DataFrame,
@@ -281,7 +279,6 @@ def test_fillna_dtype_conversion_equiv_replace(self, val):
         result = df.fillna(val)
         tm.assert_frame_equal(result, expected)
 
-    @td.skip_array_manager_invalid_test
     def test_fillna_datetime_columns(self):
         # GH#7095
         df = DataFrame(

pandas/tests/indexes/datetimelike_/test_equals.py

@@ -166,12 +166,17 @@ def test_equals2(self):
         assert not idx.equals(pd.Series(idx2))
 
         # Check that we dont raise OverflowError on comparisons outside the
-        #  implementation range
+        #  implementation range GH#28532
         oob = Index([timedelta(days=10 ** 6)] * 3, dtype=object)
         assert not idx.equals(oob)
         assert not idx2.equals(oob)
 
-        # FIXME: oob.apply(np.timedelta64) incorrectly overflows
         oob2 = Index([np.timedelta64(x) for x in oob], dtype=object)
+        assert (oob == oob2).all()
         assert not idx.equals(oob2)
         assert not idx2.equals(oob2)
+
+        oob3 = oob.map(np.timedelta64)
+        assert (oob3 == oob).all()
+        assert not idx.equals(oob3)
+        assert not idx2.equals(oob3)

pandas/tests/indexes/multi/test_setops.py

@@ -361,9 +361,7 @@ def test_union_sort_other_empty(slice_):
     # default, sort=None
     other = idx[slice_]
     tm.assert_index_equal(idx.union(other), idx)
-    # MultiIndex does not special case empty.union(idx)
-    # FIXME: don't leave commented-out
-    # tm.assert_index_equal(other.union(idx), idx)
+    tm.assert_index_equal(other.union(idx), idx)
 
     # sort=False
     tm.assert_index_equal(idx.union(other, sort=False), idx)

pandas/tests/indexes/period/test_period.py

@@ -34,10 +34,6 @@ def simple_index(self) -> Index:
     def index(self, request):
         return request.param
 
-    @pytest.mark.xfail(reason="Goes through a generate_range path")
-    def test_pickle_compat_construction(self):
-        super().test_pickle_compat_construction()
-
     def test_where(self):
         # This is handled in test_indexing
         pass

pandas/tests/indexes/test_base.py

@@ -816,14 +816,17 @@ def test_isin_nan_common_object(self, request, nulls_fixture, nulls_fixture2):
             )
 
     def test_isin_nan_common_float64(self, request, nulls_fixture):
-        if nulls_fixture is pd.NaT:
-            pytest.skip("pd.NaT not compatible with Float64Index")
 
-        # Float64Index overrides isin, so must be checked separately
-        if nulls_fixture is pd.NA:
-            request.node.add_marker(
-                pytest.mark.xfail(reason="Float64Index cannot contain pd.NA")
-            )
+        if nulls_fixture is pd.NaT or nulls_fixture is pd.NA:
+            # Check 1) that we cannot construct a Float64Index with this value
+            #  and 2) that with an NaN we do not have .isin(nulls_fixture)
+            msg = "data is not compatible with Float64Index"
+            with pytest.raises(ValueError, match=msg):
+                Float64Index([1.0, nulls_fixture])
+
+            idx = Float64Index([1.0, np.nan])
+            assert not idx.isin([nulls_fixture]).any()
+            return
 
         idx = Float64Index([1.0, nulls_fixture])
         res = idx.isin([np.nan])

pandas/tests/io/parser/common/test_chunksize.py

@@ -176,7 +176,7 @@ def test_chunks_have_consistent_numerical_type(all_parsers):
     assert result.a.dtype == float
 
 
-def test_warn_if_chunks_have_mismatched_type(all_parsers, request):
+def test_warn_if_chunks_have_mismatched_type(all_parsers):
     warning_type = None
     parser = all_parsers
     size = 10000
@@ -193,24 +193,8 @@ def test_warn_if_chunks_have_mismatched_type(all_parsers, request):
 
     buf = StringIO(data)
 
-    try:
-        with tm.assert_produces_warning(warning_type):
-            df = parser.read_csv(buf)
-    except AssertionError as err:
-        # 2021-02-21 this occasionally fails on the CI with an unexpected
-        #  ResourceWarning that we have been unable to track down,
-        #  see GH#38630
-        if "ResourceWarning" not in str(err) or parser.engine != "python":
-            raise
-
-        # Check the main assertion of the test before re-raising
-        assert df.a.dtype == object
-
-        mark = pytest.mark.xfail(
-            reason="ResourceWarning for unclosed SSL Socket, GH#38630"
-        )
-        request.node.add_marker(mark)
-        raise
+    with tm.assert_produces_warning(warning_type):
+        df = parser.read_csv(buf)
 
     assert df.a.dtype == object
 

pandas/tests/io/test_html.py

@@ -1166,6 +1166,10 @@ def test_displayed_only(self, displayed_only, exp0, exp1):
         else:
             assert len(dfs) == 1  # Should not parse hidden table
 
+    @pytest.mark.filterwarnings(
+        "ignore:You provided Unicode markup but also provided a value for "
+        "from_encoding.*:UserWarning"
+    )
     def test_encode(self, html_encoding_file):
         base_path = os.path.basename(html_encoding_file)
         root = os.path.splitext(base_path)[0]

pandas/tests/plotting/test_series.py

@@ -720,7 +720,7 @@ def test_custom_business_day_freq(self):
 
         _check_plot_works(s.plot)
 
-    @pytest.mark.xfail(reason="TODO: reason?")
+    @pytest.mark.xfail(reason="GH#24426")
     def test_plot_accessor_updates_on_inplace(self):
         ser = Series([1, 2, 3, 4])
         _, ax = self.plt.subplots()

pandas/tests/series/indexing/test_setitem.py

@@ -658,11 +658,6 @@ def test_index_where(self, obj, key, expected, val, request):
         mask = np.zeros(obj.shape, dtype=bool)
         mask[key] = True
 
-        if obj.dtype == bool:
-            msg = "Index/Series casting behavior inconsistent GH#38692"
-            mark = pytest.mark.xfail(reason=msg)
-            request.node.add_marker(mark)
-
         res = Index(obj).where(~mask, val)
         tm.assert_index_equal(res, Index(expected))