TST/REF: collect indexing tests (#39661)

Author: jbrockmendel

pandas/core/indexes/base.py

@@ -115,7 +115,7 @@
 )
 
 if TYPE_CHECKING:
-    from pandas import IntervalIndex, MultiIndex, RangeIndex, Series
+    from pandas import CategoricalIndex, IntervalIndex, MultiIndex, RangeIndex, Series
     from pandas.core.indexes.datetimelike import DatetimeIndexOpsMixin
 
 
@@ -405,6 +405,7 @@ def _ensure_array(cls, data, dtype, copy: bool):
             data = data.copy()
         return data
 
+    @final
     @classmethod
     def _dtype_to_subclass(cls, dtype: DtypeObj):
         # Delay import for perf. https://github.com/pandas-dev/pandas/pull/31423
@@ -1013,8 +1014,8 @@ def _format_data(self, name=None) -> str_t:
         if self.inferred_type == "string":
             is_justify = False
         elif self.inferred_type == "categorical":
-            # error: "Index" has no attribute "categories"
-            if is_object_dtype(self.categories):  # type: ignore[attr-defined]
+            self = cast("CategoricalIndex", self)
+            if is_object_dtype(self.categories):
                 is_justify = False
 
         return format_object_summary(
@@ -1075,6 +1076,7 @@ def _format_with_header(
             result = trim_front(format_array(values, None, justify="left"))
         return header + result
 
+    @final
     def to_native_types(self, slicer=None, **kwargs):
         """
         Format specified values of `self` and return them.

pandas/tests/arrays/sparse/test_arithmetics.py

@@ -357,7 +357,7 @@ def test_mixed_array_float_int(self, kind, mix, all_arithmetic_functions, reques
 
         if not np_version_under1p20:
             if op in [operator.floordiv, ops.rfloordiv] and mix:
-                mark = pytest.mark.xfail(strict=True, reason="GH#38172")
+                mark = pytest.mark.xfail(reason="GH#38172")
                 request.node.add_marker(mark)
 
         rdtype = "int64"

pandas/tests/base/test_conversion.py

@@ -197,13 +197,13 @@ def test_iter_box(self):
             pd.DatetimeIndex(["2017", "2018"]),
             np.ndarray,
             "datetime64[ns]",
-            marks=[pytest.mark.xfail(reason="datetime _values", strict=True)],
+            marks=[pytest.mark.xfail(reason="datetime _values")],
         ),
         pytest.param(
             pd.TimedeltaIndex([10 ** 10]),
             np.ndarray,
             "m8[ns]",
-            marks=[pytest.mark.xfail(reason="timedelta _values", strict=True)],
+            marks=[pytest.mark.xfail(reason="timedelta _values")],
         ),
     ],
 )

pandas/tests/extension/test_boolean.py

@@ -106,16 +106,16 @@ def check_opname(self, s, op_name, other, exc=None):
         # overwriting to indicate ops don't raise an error
         super().check_opname(s, op_name, other, exc=None)
 
-    def _check_op(self, s, op, other, op_name, exc=NotImplementedError):
+    def _check_op(self, obj, op, other, op_name, exc=NotImplementedError):
         if exc is None:
             if op_name in self.implements:
                 msg = r"numpy boolean subtract"
                 with pytest.raises(TypeError, match=msg):
-                    op(s, other)
+                    op(obj, other)
                 return
 
-            result = op(s, other)
-            expected = s.combine(other, op)
+            result = op(obj, other)
+            expected = self._combine(obj, other, op)
 
             if op_name in (
                 "__floordiv__",
@@ -130,27 +130,20 @@ def _check_op(self, s, op, other, op_name, exc=NotImplementedError):
             elif op_name in ("__truediv__", "__rtruediv__"):
                 # combine with bools does not generate the correct result
                 #  (numpy behaviour for div is to regard the bools as numeric)
-                expected = s.astype(float).combine(other, op).astype("Float64")
+                expected = self._combine(obj.astype(float), other, op)
+                expected = expected.astype("Float64")
             if op_name == "__rpow__":
                 # for rpow, combine does not propagate NaN
                 expected[result.isna()] = np.nan
-            self.assert_series_equal(result, expected)
+            self.assert_equal(result, expected)
         else:
             with pytest.raises(exc):
-                op(s, other)
+                op(obj, other)
 
     def _check_divmod_op(self, s, op, other, exc=None):
         # override to not raise an error
         super()._check_divmod_op(s, op, other, None)
 
-    def test_arith_frame_with_scalar(self, data, all_arithmetic_operators, request):
-        # frame & scalar
-        op_name = all_arithmetic_operators
-        if op_name not in self.implements:
-            mark = pytest.mark.xfail(reason="_reduce needs implementation")
-            request.node.add_marker(mark)
-        super().test_arith_frame_with_scalar(data, all_arithmetic_operators)
-
 
 class TestComparisonOps(base.BaseComparisonOpsTests):
     def check_opname(self, s, op_name, other, exc=None):

pandas/tests/extension/test_sparse.py

@@ -450,7 +450,7 @@ def _compare_other(self, s, data, op_name, other):
 
 
 class TestPrinting(BaseSparseTests, base.BasePrintingTests):
-    @pytest.mark.xfail(reason="Different repr", strict=True)
+    @pytest.mark.xfail(reason="Different repr")
     def test_array_repr(self, data, size):
         super().test_array_repr(data, size)
 

pandas/tests/frame/indexing/test_getitem.py

@@ -6,6 +6,7 @@
     CategoricalDtype,
     CategoricalIndex,
     DataFrame,
+    Index,
     MultiIndex,
     Series,
     Timestamp,
@@ -174,3 +175,24 @@ def test_getitem_bool_mask_categorical_index(self):
             df4[df4.index < 2]
         with pytest.raises(TypeError, match=msg):
             df4[df4.index > 1]
+
+
+class TestGetitemSlice:
+    def test_getitem_slice_float64(self, frame_or_series):
+        values = np.arange(10.0, 50.0, 2)
+        index = Index(values)
+
+        start, end = values[[5, 15]]
+
+        data = np.random.randn(20, 3)
+        if frame_or_series is not DataFrame:
+            data = data[:, 0]
+
+        obj = frame_or_series(data, index=index)
+
+        result = obj[start:end]
+        expected = obj.iloc[5:16]
+        tm.assert_equal(result, expected)
+
+        result = obj.loc[start:end]
+        tm.assert_equal(result, expected)

pandas/tests/frame/methods/test_replace.py

@@ -1587,7 +1587,6 @@ def test_replace_value_category_type(self):
 
     @pytest.mark.xfail(
         reason="category dtype gets changed to object type after replace, see #35268",
-        strict=True,
     )
     def test_replace_dict_category_type(self, input_category_df, expected_category_df):
         """

pandas/tests/indexing/test_indexing.py

@@ -60,16 +60,22 @@ def test_getitem_ndarray_3d(self, index, frame_or_series, indexer_sli):
         idxr = indexer_sli(obj)
         nd3 = np.random.randint(5, size=(2, 2, 2))
 
-        msg = "|".join(
-            [
-                r"Buffer has wrong number of dimensions \(expected 1, got 3\)",
-                "Cannot index with multidimensional key",
-                r"Wrong number of dimensions. values.ndim != ndim \[3 != 1\]",
-                "Index data must be 1-dimensional",
-                "positional indexers are out-of-bounds",
-                "Indexing a MultiIndex with a multidimensional key is not implemented",
-            ]
-        )
+        msgs = []
+        if frame_or_series is Series and indexer_sli in [tm.setitem, tm.iloc]:
+            msgs.append(r"Wrong number of dimensions. values.ndim != ndim \[3 != 1\]")
+        if frame_or_series is Series or indexer_sli is tm.iloc:
+            msgs.append(r"Buffer has wrong number of dimensions \(expected 1, got 3\)")
+        if indexer_sli is tm.loc or (
+            frame_or_series is Series and indexer_sli is tm.setitem
+        ):
+            msgs.append("Cannot index with multidimensional key")
+        if frame_or_series is DataFrame and indexer_sli is tm.setitem:
+            msgs.append("Index data must be 1-dimensional")
+        if isinstance(index, pd.IntervalIndex) and indexer_sli is tm.iloc:
+            msgs.append("Index data must be 1-dimensional")
+        if len(index) == 0 or isinstance(index, pd.MultiIndex):
+            msgs.append("positional indexers are out-of-bounds")
+        msg = "|".join(msgs)
 
         potential_errors = (IndexError, ValueError, NotImplementedError)
         with pytest.raises(potential_errors, match=msg):

pandas/tests/series/indexing/test_getitem.py

@@ -222,6 +222,24 @@ def test_getitem_slice_float_raises(self, datetime_series):
         with pytest.raises(TypeError, match=msg.format(key=r"4\.5")):
             datetime_series[4.5:10.0]
 
+    def test_getitem_slice_bug(self):
+        ser = Series(range(10), index=list(range(10)))
+        result = ser[-12:]
+        tm.assert_series_equal(result, ser)
+
+        result = ser[-7:]
+        tm.assert_series_equal(result, ser[3:])
+
+        result = ser[:-12]
+        tm.assert_series_equal(result, ser[:0])
+
+    def test_getitem_slice_integers(self):
+        ser = Series(np.random.randn(8), index=[2, 4, 6, 8, 10, 12, 14, 16])
+
+        result = ser[:4]
+        expected = Series(ser.values[:4], index=[2, 4, 6, 8])
+        tm.assert_series_equal(result, expected)
+
 
 class TestSeriesGetitemListLike:
     @pytest.mark.parametrize("box", [list, np.array, Index, pd.Series])

pandas/tests/series/indexing/test_numeric.py

@@ -113,6 +113,21 @@ def test_setitem_slice_float_raises(self, datetime_series):
         with pytest.raises(TypeError, match=msg.format(key=r"4\.5")):
             datetime_series[4.5:10.0] = 0
 
+    def test_setitem_slice(self):
+        ser = Series(range(10), index=list(range(10)))
+        ser[-12:] = 0
+        assert (ser == 0).all()
+
+        ser[:-12] = 5
+        assert (ser == 0).all()
+
+    def test_setitem_slice_integers(self):
+        ser = Series(np.random.randn(8), index=[2, 4, 6, 8, 10, 12, 14, 16])
+
+        ser[:4] = 0
+        assert (ser[:4] == 0).all()
+        assert not (ser[4:] == 0).any()
+
 
 class TestSetitemBooleanMask:
     def test_setitem_boolean(self, string_series):

pandas/tests/series/indexing/test_setitem.py

@@ -174,6 +174,6 @@ def test_attrs(self):
     @skip_if_no("jinja2")
     def test_inspect_getmembers(self):
         # GH38782
-        ser = Series()
+        ser = Series(dtype=object)
         with tm.assert_produces_warning(None):
             inspect.getmembers(ser)

pandas/tests/series/test_api.py

@@ -286,15 +286,13 @@ def test_reversed_xor_with_index_returns_index(self):
                 marks=pytest.mark.xfail(
                     reason="GH#22092 Index __and__ returns Index intersection",
                     raises=AssertionError,
-                    strict=True,
                 ),
             ),
             pytest.param(
                 ops.ror_,
                 marks=pytest.mark.xfail(
                     reason="GH#22092 Index __or__ returns Index union",
                     raises=AssertionError,
-                    strict=True,
                 ),
             ),
         ],