remove xfails

Author: jorisvandenbossche

pandas/core/arrays/string_arrow.py

@@ -418,8 +418,10 @@ def _reduce(
             return ArrowExtensionArray(arr)._reduce(
                 name, skipna=skipna, keepdims=keepdims, **kwargs
             )
-
-        result = self._reduce_calc(name, skipna=skipna, keepdims=keepdims, **kwargs)
+        if name in ("min", "max", "sum", "argmin", "argmax"):
+            result = self._reduce_calc(name, skipna=skipna, keepdims=keepdims, **kwargs)
+        else:
+            raise TypeError(f"Cannot perform reduction '{name}' with string dtype")
         if name in ("argmin", "argmax") and isinstance(result, pa.Array):
             return self._convert_int_result(result)
         elif isinstance(result, pa.Array):

pandas/tests/apply/test_frame_apply.py

@@ -6,8 +6,6 @@
 
 from pandas._config import using_string_dtype
 
-from pandas.compat import HAS_PYARROW
-
 from pandas.core.dtypes.dtypes import CategoricalDtype
 
 import pandas as pd
@@ -1218,7 +1216,6 @@ 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(
@@ -1247,9 +1244,6 @@ def test_agg_multiple_mixed():
     tm.assert_frame_equal(result, expected)
 
 
-@pytest.mark.xfail(
-    using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)"
-)
 def test_agg_multiple_mixed_raises():
     # GH 20909
     mdf = DataFrame(
@@ -1347,7 +1341,6 @@ 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(
@@ -1524,7 +1517,6 @@ 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/groupby/aggregate/test_cython.py

@@ -146,7 +146,6 @@ def test_cython_agg_return_dict():
     tm.assert_series_equal(ts, expected)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_cython_fail_agg():
     dr = bdate_range("1/1/2000", periods=50)
     ts = Series(["A", "B", "C", "D", "E"] * 10, index=dr)

pandas/tests/groupby/test_groupby.py

@@ -8,12 +8,9 @@
 
 from pandas._config import using_string_dtype
 
-from pandas.compat import HAS_PYARROW
 from pandas.errors import SpecificationError
 import pandas.util._test_decorators as td
 
-from pandas.core.dtypes.common import is_string_dtype
-
 import pandas as pd
 from pandas import (
     Categorical,
@@ -1408,23 +1405,15 @@ def g(group):
     tm.assert_series_equal(result, expected)
 
 
-# TODO harmonize error messages
-@pytest.mark.xfail(
-    using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)", strict=False
-)
 @pytest.mark.parametrize("grouper", ["A", ["A", "B"]])
-def test_set_group_name(df, grouper, using_infer_string):
+def test_set_group_name(df, grouper):
     def f(group):
         assert group.name is not None
         return group
 
     def freduce(group):
         assert group.name is not None
-        if using_infer_string and grouper == "A" and is_string_dtype(group.dtype):
-            with pytest.raises(TypeError, match="does not support"):
-                group.sum()
-        else:
-            return group.sum()
+        return group.sum()
 
     def freducex(x):
         return freduce(x)

pandas/tests/groupby/test_raises.py

@@ -208,7 +208,6 @@ def func(x):
         getattr(gb, how)(func)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize("how", ["agg", "transform"])
 @pytest.mark.parametrize("groupby_func_np", [np.sum, np.mean])
 def test_groupby_raises_string_np(
@@ -225,7 +224,8 @@ def test_groupby_raises_string_np(
         np.sum: (None, ""),
         np.mean: (
             TypeError,
-            "Could not convert string .* to numeric",
+            "Could not convert string .* to numeric|"
+            "Cannot perform reduction 'mean' with string dtype",
         ),
     }[groupby_func_np]
     _call_and_check(klass, msg, how, gb, groupby_func_np, ())