CLN/TST: skips -> xfails (#44744)

Author: jbrockmendel

pandas/_testing/__init__.py

@@ -1077,14 +1077,16 @@ def shares_memory(left, right) -> bool:
 
     if isinstance(left, NDArrayBackedExtensionArray):
         return shares_memory(left._ndarray, right)
-    if isinstance(left, pd.SparseArray):
+    if isinstance(left, pd.core.arrays.SparseArray):
         return shares_memory(left.sp_values, right)
 
     if isinstance(left, ExtensionArray) and left.dtype == "string[pyarrow]":
         # https://github.com/pandas-dev/pandas/pull/43930#discussion_r736862669
         if isinstance(right, ExtensionArray) and right.dtype == "string[pyarrow]":
-            left_pa_data = left._data
-            right_pa_data = right._data
+            # error: "ExtensionArray" has no attribute "_data"
+            left_pa_data = left._data  # type: ignore[attr-defined]
+            # error: "ExtensionArray" has no attribute "_data"
+            right_pa_data = right._data  # type: ignore[attr-defined]
             left_buf1 = left_pa_data.chunk(0).buffers()[1]
             right_buf1 = right_pa_data.chunk(0).buffers()[1]
             return left_buf1 == right_buf1

pandas/tests/apply/test_frame_transform.py

@@ -160,8 +160,6 @@ def test_transform_bad_dtype(op, frame_or_series, request):
 @pytest.mark.parametrize("op", frame_kernels_raise)
 def test_transform_partial_failure_typeerror(op):
     # GH 35964
-    if op == "rank":
-        pytest.skip("GH 40418: rank does not raise a TypeError")
 
     # Using object makes most transform kernels fail
     df = DataFrame({"A": 3 * [object], "B": [1, 2, 3]})

pandas/tests/extension/arrow/test_bool.py

@@ -41,8 +41,7 @@ class BaseArrowTests:
 
 
 class TestDtype(BaseArrowTests, base.BaseDtypeTests):
-    def test_array_type_with_arg(self, data, dtype):
-        pytest.skip("GH-22666")
+    pass
 
 
 class TestInterface(BaseArrowTests, base.BaseInterfaceTests):
@@ -63,9 +62,6 @@ def test_contains(self, data, data_missing):
 
 
 class TestConstructors(BaseArrowTests, base.BaseConstructorsTests):
-    def test_from_dtype(self, data):
-        pytest.skip("GH-22666")
-
     # seems like some bug in isna on empty BoolArray returning floats.
     @pytest.mark.xfail(reason="bad is-na for empty data")
     def test_from_sequence_from_cls(self, data):

pandas/tests/extension/test_boolean.py

@@ -208,13 +208,13 @@ def test_searchsorted(self, data_for_sorting, as_series):
         sorter = np.array([1, 0])
         assert data_for_sorting.searchsorted(a, sorter=sorter) == 0
 
-    @pytest.mark.skip(reason="uses nullable integer")
+    @pytest.mark.xfail(reason="uses nullable integer")
     def test_value_counts(self, all_data, dropna):
         return super().test_value_counts(all_data, dropna)
 
-    @pytest.mark.skip(reason="uses nullable integer")
+    @pytest.mark.xfail(reason="uses nullable integer")
     def test_value_counts_with_normalize(self, data):
-        pass
+        super().test_value_counts_with_normalize(data)
 
     def test_argmin_argmax(self, data_for_sorting, data_missing_for_sorting):
         # override because there are only 2 unique values

pandas/tests/extension/test_floating.py

@@ -169,7 +169,9 @@ class TestMissing(base.BaseMissingTests):
 
 
 class TestMethods(base.BaseMethodsTests):
+    # TODO(ExtensionIndex): re-enable
     @pytest.mark.skip(reason="uses nullable integer")
+    @pytest.mark.parametrize("dropna", [True, False])
     def test_value_counts(self, all_data, dropna):
         all_data = all_data[:10]
         if dropna:
@@ -183,9 +185,9 @@ def test_value_counts(self, all_data, dropna):
 
         self.assert_series_equal(result, expected)
 
-    @pytest.mark.skip(reason="uses nullable integer")
+    @pytest.mark.xfail(reason="uses nullable integer")
     def test_value_counts_with_normalize(self, data):
-        pass
+        super().test_value_counts_with_normalize(data)
 
 
 class TestCasting(base.BaseCastingTests):

pandas/tests/extension/test_integer.py

@@ -192,6 +192,7 @@ class TestMissing(base.BaseMissingTests):
 
 
 class TestMethods(base.BaseMethodsTests):
+    # TODO(ExtensionIndex): re-enable
     @pytest.mark.skip(reason="uses nullable integer")
     @pytest.mark.parametrize("dropna", [True, False])
     def test_value_counts(self, all_data, dropna):
@@ -207,9 +208,9 @@ def test_value_counts(self, all_data, dropna):
 
         self.assert_series_equal(result, expected)
 
-    @pytest.mark.skip(reason="uses nullable integer")
+    @pytest.mark.xfail(reason="uses nullable integer")
     def test_value_counts_with_normalize(self, data):
-        pass
+        super().test_value_counts_with_normalize(data)
 
 
 class TestCasting(base.BaseCastingTests):

pandas/tests/extension/test_interval.py

@@ -95,10 +95,7 @@ class TestGrouping(BaseInterval, base.BaseGroupbyTests):
 
 
 class TestInterface(BaseInterval, base.BaseInterfaceTests):
-    def test_view(self, data):
-        # __setitem__ incorrectly makes a copy (GH#27147), so we only
-        #  have a smoke-test
-        data.view()
+    pass
 
 
 class TestReduce(base.BaseNoReduceTests):

pandas/tests/extension/test_sparse.py

@@ -116,9 +116,6 @@ def test_array_type_with_arg(self, data, dtype):
 
 
 class TestInterface(BaseSparseTests, base.BaseInterfaceTests):
-    def test_no_values_attribute(self, data):
-        pytest.skip("We have values")
-
     def test_copy(self, data):
         # __setitem__ does not work, so we only have a smoke-test
         data.copy()

pandas/tests/frame/test_reductions.py

@@ -1492,7 +1492,7 @@ def test_reductions_deprecation_level_argument(
 
     def test_reductions_skipna_none_raises(self, frame_or_series, reduction_functions):
         if reduction_functions in ["count", "mad"]:
-            pytest.skip("Count does not accept skipna. Mad needs a depreaction cycle.")
+            pytest.skip("Count does not accept skipna. Mad needs a deprecation cycle.")
         obj = frame_or_series([1, 2, 3])
         msg = 'For argument "skipna" expected type bool, received type NoneType.'
         with pytest.raises(ValueError, match=msg):

pandas/tests/generic/test_to_xarray.py

@@ -30,9 +30,9 @@ def df(self):
             }
         )
 
-    def test_to_xarray_index_types(self, index, df):
-        if isinstance(index, MultiIndex):
-            pytest.skip("MultiIndex is tested separately")
+    def test_to_xarray_index_types(self, index_flat, df):
+        index = index_flat
+        # MultiIndex is tested in test_to_xarray_with_multiindex
         if len(index) == 0:
             pytest.skip("Test doesn't make sense for empty index")
 
@@ -86,9 +86,9 @@ def test_to_xarray_with_multiindex(self, df):
 
 @td.skip_if_no("xarray")
 class TestSeriesToXArray:
-    def test_to_xarray_index_types(self, index):
-        if isinstance(index, MultiIndex):
-            pytest.skip("MultiIndex is tested separately")
+    def test_to_xarray_index_types(self, index_flat):
+        index = index_flat
+        # MultiIndex is tested in test_to_xarray_with_multiindex
 
         from xarray import DataArray
 

pandas/tests/indexes/interval/test_constructors.py

@@ -178,9 +178,6 @@ def test_constructor_string(self, constructor, breaks):
     @pytest.mark.parametrize("cat_constructor", [Categorical, CategoricalIndex])
     def test_constructor_categorical_valid(self, constructor, cat_constructor):
         # GH 21243/21253
-        if isinstance(constructor, partial) and constructor.func is Index:
-            # Index is defined to create CategoricalIndex from categorical data
-            pytest.skip()
 
         breaks = np.arange(10, dtype="int64")
         expected = IntervalIndex.from_breaks(breaks)

pandas/tests/indexes/multi/test_analytics.py

@@ -187,9 +187,6 @@ def test_map(idx):
 )
 def test_map_dictlike(idx, mapper):
 
-    if isinstance(idx, (pd.CategoricalIndex, pd.IntervalIndex)):
-        pytest.skip(f"skipping tests for {type(idx)}")
-
     identity = mapper(idx.values, idx)
 
     # we don't infer to UInt64 for a dict

pandas/tests/io/excel/test_xlrd.py

@@ -15,24 +15,35 @@
 xlrd = pytest.importorskip("xlrd")
 xlwt = pytest.importorskip("xlwt")
 
+pytestmark = pytest.mark.filterwarnings(
+    "ignore:As the xlwt package is no longer maintained:FutureWarning"
+)
+
+
+# error: Unsupported operand types for <= ("Version" and "None")
+if xlrd_version >= Version("2"):  # type: ignore[operator]
+    exts = [".xls"]
+else:
+    exts = [".xls", ".xlsx", ".xlsm"]
+
+
+@pytest.fixture(params=exts)
+def read_ext_xlrd(request):
+    """
+    Valid extensions for reading Excel files with xlrd.
 
-@pytest.fixture(autouse=True)
-def skip_ods_and_xlsb_files(read_ext):
-    if read_ext == ".ods":
-        pytest.skip("Not valid for xlrd")
-    if read_ext == ".xlsb":
-        pytest.skip("Not valid for xlrd")
-    if read_ext in (".xlsx", ".xlsm") and xlrd_version >= Version("2"):
-        pytest.skip("Not valid for xlrd >= 2.0")
+    Similar to read_ext, but excludes .ods, .xlsb, and for xlrd>2 .xlsx, .xlsm
+    """
+    return request.param
 
 
-def test_read_xlrd_book(read_ext, frame):
+def test_read_xlrd_book(read_ext_xlrd, frame):
     df = frame
 
     engine = "xlrd"
     sheet_name = "SheetA"
 
-    with tm.ensure_clean(read_ext) as pth:
+    with tm.ensure_clean(read_ext_xlrd) as pth:
         df.to_excel(pth, sheet_name)
         book = xlrd.open_workbook(pth)
 

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

@@ -30,8 +30,6 @@ def test_scientific_no_exponent(all_parsers_all_precisions):
     df = DataFrame.from_dict({"w": ["2e"], "x": ["3E"], "y": ["42e"], "z": ["632E"]})
     data = df.to_csv(index=False)
     parser, precision = all_parsers_all_precisions
-    if parser == "pyarrow":
-        pytest.skip()
 
     df_roundtrip = parser.read_csv(StringIO(data), float_precision=precision)
     tm.assert_frame_equal(df_roundtrip, df)
@@ -41,8 +39,7 @@ def test_scientific_no_exponent(all_parsers_all_precisions):
 def test_very_negative_exponent(all_parsers_all_precisions, neg_exp):
     # GH#38753
     parser, precision = all_parsers_all_precisions
-    if parser == "pyarrow":
-        pytest.skip()
+
     data = f"data\n10E{neg_exp}"
     result = parser.read_csv(StringIO(data), float_precision=precision)
     expected = DataFrame({"data": [0.0]})

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

@@ -245,7 +245,7 @@ def test_open_file(all_parsers):
     # GH 39024
     parser = all_parsers
     if parser.engine == "c":
-        pytest.skip()
+        pytest.skip("'c' engine does not support sep=None with delim_whitespace=False")
 
     with tm.ensure_clean() as path:
         file = Path(path)

pandas/tests/io/parser/test_comment.py

@@ -30,7 +30,7 @@ def test_comment(all_parsers, na_values):
 @pytest.mark.parametrize(
     "read_kwargs", [{}, {"lineterminator": "*"}, {"delim_whitespace": True}]
 )
-def test_line_comment(all_parsers, read_kwargs):
+def test_line_comment(all_parsers, read_kwargs, request):
     parser = all_parsers
     data = """# empty
 A,B,C
@@ -42,7 +42,10 @@ def test_line_comment(all_parsers, read_kwargs):
         data = data.replace(",", " ")
     elif read_kwargs.get("lineterminator"):
         if parser.engine != "c":
-            pytest.skip("Custom terminator not supported with Python engine")
+            mark = pytest.mark.xfail(
+                reason="Custom terminator not supported with Python engine"
+            )
+            request.node.add_marker(mark)
 
         data = data.replace("\n", read_kwargs.get("lineterminator"))
 

pandas/tests/io/parser/test_encoding.py

@@ -202,9 +202,6 @@ def test_encoding_named_temp_file(all_parsers):
     parser = all_parsers
     encoding = "shift-jis"
 
-    if parser.engine == "python":
-        pytest.skip("NamedTemporaryFile does not work with Python engine")
-
     title = "てすと"
     data = "こむ"
 
@@ -302,11 +299,15 @@ def test_readcsv_memmap_utf8(all_parsers):
     tm.assert_frame_equal(df, dfr)
 
 
-def test_not_readable(all_parsers):
+def test_not_readable(all_parsers, request):
     # GH43439
     parser = all_parsers
     if parser.engine in ("python", "pyarrow"):
-        pytest.skip("SpooledTemporaryFile does only work with the c-engine")
+        mark = pytest.mark.xfail(
+            reason="SpooledTemporaryFile does only work with the c-engine"
+        )
+        request.node.add_marker(mark)
+
     with tempfile.SpooledTemporaryFile() as handle:
         handle.write(b"abcd")
         handle.seek(0)

pandas/tests/io/parser/test_parse_dates.py

@@ -1709,8 +1709,8 @@ def _helper_hypothesis_delimited_date(call, date_string, **kwargs):
 def test_hypothesis_delimited_date(date_format, dayfirst, delimiter, test_datetime):
     if date_format == "%m %Y" and delimiter == ".":
         pytest.skip(
-            "parse_datetime_string cannot reliably tell whether \
-        e.g. %m.%Y is a float or a date, thus we skip it"
+            "parse_datetime_string cannot reliably tell whether "
+            "e.g. %m.%Y is a float or a date, thus we skip it"
         )
     result, expected = None, None
     except_in_dateutil, except_out_dateutil = None, None

pandas/tests/io/test_parquet.py

@@ -595,13 +595,16 @@ def test_write_column_index_nonstring(self, pa):
         msg = r"parquet must have string column names"
         self.check_error_on_write(df, engine, ValueError, msg)
 
-    def test_use_nullable_dtypes(self, engine):
+    def test_use_nullable_dtypes(self, engine, request):
         import pyarrow.parquet as pq
 
         if engine == "fastparquet":
             # We are manually disabling fastparquet's
             # nullable dtype support pending discussion
-            pytest.skip("Fastparquet nullable dtype support is disabled")
+            mark = pytest.mark.xfail(
+                reason="Fastparquet nullable dtype support is disabled"
+            )
+            request.node.add_marker(mark)
 
         table = pyarrow.table(
             {