more xfails

Author: jorisvandenbossche

pandas/tests/copy_view/test_array.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas import (
     DataFrame,
     Series,
@@ -117,6 +119,7 @@ def test_dataframe_array_ea_dtypes():
     assert arr.flags.writeable is False
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_dataframe_array_string_dtype():
     df = DataFrame({"a": ["a", "b"]}, dtype="string")
     arr = np.asarray(df)

pandas/tests/copy_view/test_astype.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.compat.pyarrow import pa_version_under12p0
 import pandas.util._test_decorators as td
 
@@ -82,6 +84,7 @@ def test_astype_numpy_to_ea():
     assert np.shares_memory(get_array(ser), get_array(result))
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize(
     "dtype, new_dtype", [("object", "string"), ("string", "object")]
 )
@@ -95,6 +98,7 @@ def test_astype_string_and_object(dtype, new_dtype):
     tm.assert_frame_equal(df, df_orig)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize(
     "dtype, new_dtype", [("object", "string"), ("string", "object")]
 )
@@ -195,6 +199,7 @@ def test_astype_arrow_timestamp():
         assert np.shares_memory(get_array(df, "a"), get_array(result, "a")._pa_array)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_convert_dtypes_infer_objects():
     ser = Series(["a", "b", "c"])
     ser_orig = ser.copy()
@@ -210,6 +215,7 @@ def test_convert_dtypes_infer_objects():
     tm.assert_series_equal(ser, ser_orig)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_convert_dtypes():
     df = DataFrame({"a": ["a", "b"], "b": [1, 2], "c": [1.5, 2.5], "d": [True, False]})
     df_orig = df.copy()

pandas/tests/copy_view/test_constructors.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -207,6 +209,7 @@ def test_dataframe_from_dict_of_series_with_reindex(dtype):
     assert np.shares_memory(arr_before, arr_after)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "data, dtype", [([1, 2], None), ([1, 2], "int64"), (["a", "b"], None)]
 )

pandas/tests/copy_view/test_functions.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas import (
     DataFrame,
     Index,
@@ -12,6 +14,7 @@
 from pandas.tests.copy_view.util import get_array
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_concat_frames():
     df = DataFrame({"b": ["a"] * 3})
     df2 = DataFrame({"a": ["a"] * 3})
@@ -30,6 +33,7 @@ def test_concat_frames():
     tm.assert_frame_equal(df, df_orig)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_concat_frames_updating_input():
     df = DataFrame({"b": ["a"] * 3})
     df2 = DataFrame({"a": ["a"] * 3})
@@ -149,6 +153,7 @@ def test_concat_copy_keyword():
     assert np.shares_memory(get_array(df2, "b"), get_array(result, "b"))
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize(
     "func",
     [
@@ -200,6 +205,7 @@ def test_merge_on_index():
     tm.assert_frame_equal(df2, df2_orig)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "func, how",
     [
@@ -243,6 +249,7 @@ def test_merge_copy_keyword():
     assert np.shares_memory(get_array(df2, "b"), get_array(result, "b"))
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_join_on_key():
     df_index = Index(["a", "b", "c"], name="key")
 
@@ -270,6 +277,7 @@ def test_join_on_key():
     tm.assert_frame_equal(df2, df2_orig)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_join_multiple_dataframes_on_key():
     df_index = Index(["a", "b", "c"], name="key")
 

pandas/tests/copy_view/test_internals.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas import DataFrame
 import pandas._testing as tm
 from pandas.tests.copy_view.util import get_array
@@ -40,6 +42,7 @@ def test_consolidate():
     assert df.loc[0, "b"] == 0.1
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("dtype", [np.intp, np.int8])
 @pytest.mark.parametrize(
     "locs, arr",

pandas/tests/copy_view/test_interp_fillna.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas import (
     NA,
     DataFrame,
@@ -110,6 +112,7 @@ def test_interp_fill_functions_inplace(func, dtype):
     assert view._mgr._has_no_reference(0)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_interpolate_cannot_with_object_dtype():
     df = DataFrame({"a": ["a", np.nan, "c"], "b": 1})
 
@@ -118,6 +121,7 @@ def test_interpolate_cannot_with_object_dtype():
         df.interpolate()
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_interpolate_object_convert_no_op():
     df = DataFrame({"a": ["a", "b", "c"], "b": 1})
     arr_a = get_array(df, "a")

pandas/tests/copy_view/test_methods.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -712,6 +714,7 @@ def test_head_tail(method):
     tm.assert_frame_equal(df, df_orig)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_infer_objects():
     df = DataFrame({"a": [1, 2], "b": "c", "c": 1, "d": "x"})
     df_orig = df.copy()
@@ -896,6 +899,7 @@ def test_sort_values_inplace(obj, kwargs):
     tm.assert_equal(view, obj_orig)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize("decimals", [-1, 0, 1])
 def test_round(decimals):
     df = DataFrame({"a": [1, 2], "b": "c"})

pandas/tests/copy_view/test_replace.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas import (
     Categorical,
     DataFrame,
@@ -9,6 +11,7 @@
 from pandas.tests.copy_view.util import get_array
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize(
     "replace_kwargs",
     [
@@ -56,6 +59,7 @@ def test_replace_regex_inplace_refs():
     tm.assert_frame_equal(view, df_orig)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_replace_regex_inplace():
     df = DataFrame({"a": ["aaa", "bbb"]})
     arr = get_array(df, "a")
@@ -253,6 +257,7 @@ def test_replace_empty_list():
     assert not df2._mgr._has_no_reference(0)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize("value", ["d", None])
 def test_replace_object_list_inplace(value):
     df = DataFrame({"a": ["a", "b", "c"]})

pandas/tests/frame/methods/test_reset_index.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_float_dtype,
     is_integer_dtype,
@@ -642,6 +644,7 @@ def test_rest_index_multiindex_categorical_with_missing_values(self, codes):
         tm.assert_frame_equal(res, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize(
     "array, dtype",
     [

pandas/tests/frame/test_arithmetic.py

@@ -11,6 +11,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -1540,6 +1542,7 @@ def test_comparisons(self, simple_frame, float_frame, func):
         with pytest.raises(ValueError, match=msg):
             func(simple_frame, simple_frame[:2])
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_strings_to_numbers_comparisons_raises(self, compare_operators_no_eq_ne):
         # GH 11565
         df = DataFrame(

pandas/tests/frame/test_arrow_interface.py

@@ -2,13 +2,16 @@
 
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas.util._test_decorators as td
 
 import pandas as pd
 
 pa = pytest.importorskip("pyarrow")
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @td.skip_if_no("pyarrow", min_version="14.0")
 def test_dataframe_arrow_interface():
     df = pd.DataFrame({"a": [1, 2, 3], "b": ["a", "b", "c"]})
@@ -31,6 +34,7 @@ def test_dataframe_arrow_interface():
     assert table.equals(expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @td.skip_if_no("pyarrow", min_version="15.0")
 def test_dataframe_to_arrow():
     df = pd.DataFrame({"a": [1, 2, 3], "b": ["a", "b", "c"]})

pandas/tests/frame/test_constructors.py

@@ -1935,6 +1935,7 @@ def test_constructor_with_datetimes4(self):
         df = DataFrame({"value": dr})
         assert str(df.iat[0, 0].tz) == "US/Eastern"
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_constructor_with_datetimes5(self):
         # GH 7822
         # preserver an index with a tz on dict construction

pandas/tests/frame/test_reductions.py

@@ -606,6 +606,7 @@ def test_sem(self, datetime_frame):
             result = nanops.nansem(arr, axis=0)
             assert not (result < 0).any()
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize(
         "dropna, expected",
         [
@@ -1057,6 +1058,7 @@ def test_sum_bools(self):
     # ----------------------------------------------------------------------
     # Index of max / min
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     @pytest.mark.parametrize("axis", [0, 1])
     def test_idxmin(self, float_frame, int_frame, skipna, axis):
         frame = float_frame
@@ -1107,6 +1109,7 @@ def test_idxmin_axis_2(self, float_frame):
         with pytest.raises(ValueError, match=msg):
             frame.idxmin(axis=2)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("axis", [0, 1])
     def test_idxmax(self, float_frame, int_frame, skipna, axis):
         frame = float_frame
@@ -1346,6 +1349,7 @@ def test_any_all_extra(self):
         result = df[["C"]].all(axis=None).item()
         assert result is True
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("axis", [0, 1])
     def test_any_all_object_dtype(
         self, axis, all_boolean_reductions, skipna, using_infer_string

pandas/tests/groupby/methods/test_describe.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -71,6 +73,7 @@ def test_series_describe_as_index(as_index, keys):
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_frame_describe_multikey(tsframe):
     grouped = tsframe.groupby([lambda x: x.year, lambda x: x.month])
     result = grouped.describe()
@@ -246,6 +249,7 @@ def test_describe_non_cython_paths():
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("dtype", [int, float, object])
 @pytest.mark.parametrize(
     "kwargs",

pandas/tests/groupby/methods/test_nth.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -677,6 +679,7 @@ def test_first_multi_key_groupby_categorical():
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("method", ["first", "last", "nth"])
 def test_groupby_last_first_nth_with_none(method, nulls_fixture):
     # GH29645

pandas/tests/groupby/methods/test_quantile.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -156,6 +158,7 @@ def test_groupby_quantile_with_arraylike_q_and_int_columns(frame_size, groupby,
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_quantile_raises():
     df = DataFrame([["foo", "a"], ["foo", "b"], ["foo", "c"]], columns=["key", "val"])
 
@@ -238,6 +241,7 @@ def test_groupby_quantile_nullable_array(values, q):
     tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("q", [0.5, [0.0, 0.5, 1.0]])
 @pytest.mark.parametrize("numeric_only", [True, False])
 def test_groupby_quantile_raises_on_invalid_dtype(q, numeric_only):