more xfails

Author: jorisvandenbossche

pandas/tests/apply/test_frame_apply.py

@@ -4,6 +4,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.core.dtypes.dtypes import CategoricalDtype
 
 import pandas as pd
@@ -61,6 +63,7 @@ def test_apply(float_frame, engine, request):
         assert result.index is float_frame.index
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("axis", [0, 1])
 @pytest.mark.parametrize("raw", [True, False])
 @pytest.mark.parametrize("nopython", [True, False])
@@ -1213,6 +1216,7 @@ def test_agg_with_name_as_column_name():
     tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_agg_multiple_mixed():
     # GH 20909
     mdf = DataFrame(
@@ -1338,6 +1342,7 @@ def test_named_agg_reduce_axis1_raises(float_frame):
             float_frame.agg(row1=(name1, "sum"), row2=(name2, "max"), axis=axis)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_nuiscance_columns():
     # GH 15015
     df = DataFrame(
@@ -1514,6 +1519,7 @@ def test_apply_datetime_tz_issue(engine, request):
     tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("df", [DataFrame({"A": ["a", None], "B": ["c", "d"]})])
 @pytest.mark.parametrize("method", ["min", "max", "sum"])
 def test_mixed_column_raises(df, method, using_infer_string):

pandas/tests/apply/test_str.py

@@ -4,6 +4,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.compat import WASM
 
 from pandas.core.dtypes.common import is_number
@@ -79,6 +81,7 @@ def test_apply_np_transformer(float_frame, op, how):
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "series, func, expected",
     chain(
@@ -137,6 +140,7 @@ def test_agg_cython_table_series(series, func, expected):
         assert result == expected
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "series, func, expected",
     chain(

pandas/tests/arrays/categorical/test_analytics.py

@@ -4,6 +4,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.compat import PYPY
 
 from pandas import (
@@ -294,6 +296,7 @@ def test_nbytes(self):
         exp = 3 + 3 * 8  # 3 int8s for values + 3 int64s for categories
         assert cat.nbytes == exp
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_memory_usage(self):
         cat = Categorical([1, 2, 3])
 

pandas/tests/arrays/categorical/test_api.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.compat import PY311
 
 from pandas import (
@@ -149,6 +151,7 @@ def test_reorder_categories_raises(self, new_categories):
         with pytest.raises(ValueError, match=msg):
             cat.reorder_categories(new_categories)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_add_categories(self):
         cat = Categorical(["a", "b", "c", "a"], ordered=True)
         old = cat.copy()

pandas/tests/arrays/categorical/test_constructors.py

@@ -735,6 +735,7 @@ def test_interval(self):
         tm.assert_numpy_array_equal(cat.codes, expected_codes)
         tm.assert_index_equal(cat.categories, idx)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_categorical_extension_array_nullable(self, nulls_fixture):
         # GH:
         arr = pd.arrays.StringArray._from_sequence(

pandas/tests/arrays/masked/test_function.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.core.dtypes.common import is_integer_dtype
 
 import pandas as pd
@@ -58,6 +60,7 @@ def test_tolist(data):
     tm.assert_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_to_numpy():
     # GH#56991
 

pandas/tests/dtypes/test_dtypes.py

@@ -4,6 +4,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas._libs.tslibs.dtypes import NpyDatetimeUnit
 
 from pandas.core.dtypes.base import _registry as registry
@@ -959,6 +961,7 @@ def test_same_categories_different_order(self):
         c2 = CategoricalDtype(["b", "a"], ordered=True)
         assert c1 is not c2
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("ordered2", [True, False, None])
     def test_categorical_equality(self, ordered, ordered2):
         # same categories, same order

pandas/tests/extension/test_string.py

@@ -22,13 +22,19 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 import pandas._testing as tm
 from pandas.api.types import is_string_dtype
 from pandas.core.arrays import ArrowStringArray
 from pandas.core.arrays.string_ import StringDtype
 from pandas.tests.extension import base
 
+pytestmark = pytest.mark.xfail(
+    using_string_dtype(), reason="TODO(infer_string)", strict=False
+)
+
 
 def maybe_split_array(arr, chunked):
     if not chunked:

pandas/tests/frame/indexing/test_coercion.py

@@ -8,6 +8,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -82,6 +84,7 @@ def test_6942(indexer_al):
     assert df.iloc[0, 0] == t2
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_26395(indexer_al):
     # .at case fixed by GH#45121 (best guess)
     df = DataFrame(index=["A", "B", "C"])

pandas/tests/frame/indexing/test_indexing.py

@@ -9,6 +9,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas._libs import iNaT
 from pandas.errors import InvalidIndexError
 
@@ -174,6 +176,7 @@ def test_getitem_boolean(self, mixed_float_frame, mixed_int_frame, datetime_fram
                 if bif[c].dtype != bifw[c].dtype:
                     assert bif[c].dtype == df[c].dtype
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_getitem_boolean_casting(self, datetime_frame):
         # don't upcast if we don't need to
         df = datetime_frame.copy()
@@ -501,6 +504,7 @@ def test_setitem_ambig(self, using_infer_string):
         else:
             assert dm[2].dtype == np.object_
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_setitem_None(self, float_frame, using_infer_string):
         # GH #766
         float_frame[None] = float_frame["A"]
@@ -1121,6 +1125,7 @@ def test_setitem_with_unaligned_tz_aware_datetime_column(self):
         df.loc[[0, 1, 2], "dates"] = column[[1, 0, 2]]
         tm.assert_series_equal(df["dates"], column)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_loc_setitem_datetimelike_with_inference(self):
         # GH 7592
         # assignment of timedeltas with NaT
@@ -1143,6 +1148,7 @@ def test_loc_setitem_datetimelike_with_inference(self):
         )
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_getitem_boolean_indexing_mixed(self):
         df = DataFrame(
             {
@@ -1871,6 +1877,7 @@ def test_adding_new_conditional_column_with_string(dtype, infer_string) -> None:
     tm.assert_frame_equal(df, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_add_new_column_infer_string():
     # GH#55366
     pytest.importorskip("pyarrow")

pandas/tests/frame/indexing/test_insert.py

@@ -7,6 +7,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.errors import PerformanceWarning
 
 from pandas import (
@@ -61,6 +63,7 @@ def test_insert_column_bug_4032(self):
         expected = DataFrame([[1.3, 1, 1.1], [2.3, 2, 2.2]], columns=["c", "a", "b"])
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_insert_with_columns_dups(self):
         # GH#14291
         df = DataFrame()

pandas/tests/frame/indexing/test_setitem.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.core.dtypes.base import _registry as ea_registry
 from pandas.core.dtypes.common import is_object_dtype
 from pandas.core.dtypes.dtypes import (
@@ -144,6 +146,7 @@ def test_setitem_different_dtype(self):
         )
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_setitem_empty_columns(self):
         # GH 13522
         df = DataFrame(index=["A", "B", "C"])
@@ -159,6 +162,7 @@ def test_setitem_dt64_index_empty_columns(self):
         df["A"] = rng
         assert df["A"].dtype == np.dtype("M8[ns]")
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_setitem_timestamp_empty_columns(self):
         # GH#19843
         df = DataFrame(index=range(3))
@@ -198,6 +202,7 @@ def test_setitem_with_unaligned_sparse_value(self):
         expected = Series(SparseArray([1, 0, 0]), name="new_column")
         tm.assert_series_equal(df["new_column"], expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_setitem_period_preserves_dtype(self):
         # GH: 26861
         data = [Period("2003-12", "D")]
@@ -667,6 +672,7 @@ def test_setitem_iloc_two_dimensional_generator(self):
         expected = DataFrame({"a": [1, 2, 3], "b": [4, 1, 1]})
         tm.assert_frame_equal(df, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_setitem_dtypes_bytes_type_to_object(self):
         # GH 20734
         index = Series(name="id", dtype="S24")
@@ -699,6 +705,7 @@ def test_setitem_ea_dtype_rhs_series(self):
         expected = DataFrame({"a": [1, 2]}, dtype="Int64")
         tm.assert_frame_equal(df, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_setitem_npmatrix_2d(self):
         # GH#42376
         # for use-case df["x"] = sparse.random((10, 10)).mean(axis=1)
@@ -920,6 +927,7 @@ def test_setitem_with_expansion_categorical_dtype(self):
         ser.name = "E"
         tm.assert_series_equal(result2.sort_index(), ser.sort_index())
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_setitem_scalars_no_index(self):
         # GH#16823 / GH#17894
         df = DataFrame()

pandas/tests/frame/indexing/test_where.py

@@ -4,6 +4,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.core.dtypes.common import is_scalar
 
 import pandas as pd
@@ -46,6 +48,7 @@ def is_ok(s):
 
 
 class TestDataFrameIndexingWhere:
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     def test_where_get(self, where_frame, float_string_frame):
         def _check_get(df, cond, check_dtypes=True):
             other1 = _safe_add(df)
@@ -96,6 +99,7 @@ def test_where_upcasting(self):
 
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     def test_where_alignment(self, where_frame, float_string_frame):
         # aligning
         def _check_align(df, cond, other, check_dtypes=True):
@@ -170,6 +174,7 @@ def test_where_invalid(self):
         with pytest.raises(ValueError, match=msg):
             df.mask(0)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     def test_where_set(self, where_frame, float_string_frame, mixed_int_frame):
         # where inplace
 

pandas/tests/frame/indexing/test_xs.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas import (
     DataFrame,
     Index,
@@ -72,6 +74,7 @@ def test_xs_other(self, float_frame):
         tm.assert_series_equal(float_frame["A"], float_frame_orig["A"])
         assert not (expected == 5).all()
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_xs_corner(self):
         # pathological mixed-type reordering case
         df = DataFrame(index=[0])

pandas/tests/frame/methods/test_combine_first.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.core.dtypes.cast import find_common_type
 from pandas.core.dtypes.common import is_dtype_equal
 
@@ -30,6 +32,7 @@ def test_combine_first_mixed(self):
         combined = f.combine_first(g)
         tm.assert_frame_equal(combined, exp)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_combine_first(self, float_frame, using_infer_string):
         # disjoint
         head, tail = float_frame[:5], float_frame[5:]

pandas/tests/frame/methods/test_convert_dtypes.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 import pandas._testing as tm
 
@@ -180,6 +182,7 @@ def test_convert_dtypes_pyarrow_timestamp(self):
         result = expected.convert_dtypes(dtype_backend="pyarrow")
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_convert_dtypes_avoid_block_splitting(self):
         # GH#55341
         df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6], "c": "a"})
@@ -194,6 +197,7 @@ def test_convert_dtypes_avoid_block_splitting(self):
         tm.assert_frame_equal(result, expected)
         assert result._mgr.nblocks == 2
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_convert_dtypes_from_arrow(self):
         # GH#56581
         df = pd.DataFrame([["a", datetime.time(18, 12)]], columns=["a", "b"])