TST (string dtype): clean-up assorted xfails (#60345)

Author: jorisvandenbossche

pandas/tests/base/test_conversion.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.compat import HAS_PYARROW
 from pandas.compat.numpy import np_version_gt2
 
@@ -392,9 +390,6 @@ def test_to_numpy(arr, expected, zero_copy, index_or_series_or_array):
         assert np.may_share_memory(result_nocopy1, result_nocopy2)
 
 
-@pytest.mark.xfail(
-    using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)", strict=False
-)
 @pytest.mark.parametrize("as_series", [True, False])
 @pytest.mark.parametrize(
     "arr", [np.array([1, 2, 3], dtype="int64"), np.array(["a", "b", "c"], dtype=object)]
@@ -406,13 +401,13 @@ def test_to_numpy_copy(arr, as_series, using_infer_string):
 
     # no copy by default
     result = obj.to_numpy()
-    if using_infer_string and arr.dtype == object:
+    if using_infer_string and arr.dtype == object and obj.dtype.storage == "pyarrow":
         assert np.shares_memory(arr, result) is False
     else:
         assert np.shares_memory(arr, result) is True
 
     result = obj.to_numpy(copy=False)
-    if using_infer_string and arr.dtype == object:
+    if using_infer_string and arr.dtype == object and obj.dtype.storage == "pyarrow":
         assert np.shares_memory(arr, result) is False
     else:
         assert np.shares_memory(arr, result) is True

pandas/tests/indexes/multi/test_setops.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 import pandas as pd
 from pandas import (
     CategoricalIndex,
@@ -754,13 +752,12 @@ def test_intersection_keep_ea_dtypes(val, any_numeric_ea_dtype):
     tm.assert_index_equal(result, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_union_with_na_when_constructing_dataframe():
     # GH43222
     series1 = Series(
         (1,),
         index=MultiIndex.from_arrays(
-            [Series([None], dtype="string"), Series([None], dtype="string")]
+            [Series([None], dtype="str"), Series([None], dtype="str")]
         ),
     )
     series2 = Series((10, 20), index=MultiIndex.from_tuples(((None, None), ("a", "b"))))

pandas/tests/indexes/test_base.py

@@ -8,12 +8,7 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
-from pandas.compat import (
-    HAS_PYARROW,
-    IS64,
-)
+from pandas.compat import IS64
 from pandas.errors import InvalidIndexError
 import pandas.util._test_decorators as td
 
@@ -823,11 +818,6 @@ def test_isin(self, values, index, expected):
         expected = np.array(expected, dtype=bool)
         tm.assert_numpy_array_equal(result, expected)
 
-    @pytest.mark.xfail(
-        using_string_dtype() and not HAS_PYARROW,
-        reason="TODO(infer_string)",
-        strict=False,
-    )
     def test_isin_nan_common_object(
         self, nulls_fixture, nulls_fixture2, using_infer_string
     ):

pandas/tests/io/excel/test_readers.py

@@ -17,8 +17,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -625,7 +623,6 @@ def test_reader_dtype_str(self, read_ext, dtype, expected):
         expected = DataFrame(expected)
         tm.assert_frame_equal(actual, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     def test_dtype_backend(self, read_ext, dtype_backend, engine, tmp_excel):
         # GH#36712
         if read_ext in (".xlsb", ".xls"):

pandas/tests/io/excel/test_writers.py

@@ -13,8 +13,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.compat._optional import import_optional_dependency
 import pandas.util._test_decorators as td
 
@@ -1387,12 +1385,11 @@ def test_freeze_panes(self, tmp_excel):
         result = pd.read_excel(tmp_excel, index_col=0)
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_path_path_lib(self, engine, ext):
         df = DataFrame(
             1.1 * np.arange(120).reshape((30, 4)),
             columns=Index(list("ABCD")),
-            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+            index=Index([f"i-{i}" for i in range(30)]),
         )
         writer = partial(df.to_excel, engine=engine)
 

pandas/tests/io/test_stata.py

@@ -1719,7 +1719,6 @@ def test_date_parsing_ignores_format_details(self, column, datapath):
         formatted = df.loc[0, column + "_fmt"]
         assert unformatted == formatted
 
-    # @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     @pytest.mark.parametrize("byteorder", ["little", "big"])
     def test_writer_117(self, byteorder, temp_file, using_infer_string):
         original = DataFrame(

pandas/tests/reshape/test_union_categoricals.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.core.dtypes.concat import union_categoricals
 
 import pandas as pd
@@ -124,12 +122,15 @@ def test_union_categoricals_nan(self):
         exp = Categorical([np.nan, np.nan, np.nan, np.nan])
         tm.assert_categorical_equal(res, exp)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("val", [[], ["1"]])
     def test_union_categoricals_empty(self, val, request, using_infer_string):
         # GH 13759
         if using_infer_string and val == ["1"]:
-            request.applymarker(pytest.mark.xfail("object and strings dont match"))
+            request.applymarker(
+                pytest.mark.xfail(
+                    reason="TDOD(infer_string) object and strings dont match"
+                )
+            )
         res = union_categoricals([Categorical([]), Categorical(val)])
         exp = Categorical(val)
         tm.assert_categorical_equal(res, exp)