TST (string dtype): xfail all currently failing tests with future.infer_string

Author: jorisvandenbossche

pandas/tests/arrays/floating/test_arithmetic.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
 from pandas.core.arrays import FloatingArray
@@ -122,6 +124,7 @@ def test_arith_zero_dim_ndarray(other):
 # -----------------------------------------------------------------------------
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 def test_error_invalid_values(data, all_arithmetic_operators, using_infer_string):
     op = all_arithmetic_operators
     s = pd.Series(data)

pandas/tests/arrays/integer/test_arithmetic.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
 from pandas.core import ops
@@ -172,6 +174,7 @@ def test_numpy_zero_dim_ndarray(other):
 # -----------------------------------------------------------------------------
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 def test_error_invalid_values(data, all_arithmetic_operators, using_infer_string):
     op = all_arithmetic_operators
     s = pd.Series(data)

pandas/tests/extension/test_arrow.py

@@ -32,6 +32,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas._libs import lib
 from pandas._libs.tslibs import timezones
 from pandas.compat import (
@@ -1993,6 +1995,7 @@ def test_str_find_large_start():
         tm.assert_series_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.skipif(
     pa_version_under13p0, reason="https://github.com/apache/arrow/issues/36311"
 )

pandas/tests/frame/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,
@@ -324,6 +326,7 @@ def test_quantile_multi_empty(self, interp_method):
         )
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_quantile_datetime(self, unit):
         dti = pd.to_datetime(["2010", "2011"]).as_unit(unit)
         df = DataFrame({"a": dti, "b": [0, 5]})
@@ -377,6 +380,7 @@ def test_quantile_datetime(self, unit):
         expected = DataFrame(index=[0.5], columns=[])
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     @pytest.mark.parametrize(
         "dtype",
         [
@@ -641,6 +645,7 @@ def test_quantile_nat(self, interp_method, unit):
         )
         tm.assert_frame_equal(res, exp)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_quantile_empty_no_rows_floats(self, interp_method):
         interpolation, method = interp_method
 
@@ -869,6 +874,7 @@ def test_quantile_ea_scalar(self, request, obj, index):
         else:
             tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize(
         "dtype, expected_data, expected_index, axis",
         [
@@ -887,6 +893,7 @@ def test_empty_numeric(self, dtype, expected_data, expected_index, axis):
         )
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize(
         "dtype, expected_data, expected_index, axis, expected_dtype",
         [
@@ -905,6 +912,7 @@ def test_empty_datelike(
         )
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize(
         "expected_data, expected_index, axis",
         [

pandas/tests/frame/test_query_eval.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.errors import (
     NumExprClobberingError,
     UndefinedVariableError,
@@ -759,6 +761,7 @@ def test_inf(self, op, f, engine, parser):
         result = df.query(q, engine=engine, parser=parser)
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_check_tz_aware_index_query(self, tz_aware_fixture):
         # https://github.com/pandas-dev/pandas/issues/29463
         tz = tz_aware_fixture

pandas/tests/groupby/methods/test_value_counts.py

@@ -7,6 +7,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas.util._test_decorators as td
 
 from pandas import (
@@ -273,6 +275,7 @@ def _frame_value_counts(df, keys, normalize, sort, ascending):
     return df[keys].value_counts(normalize=normalize, sort=sort, ascending=ascending)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("groupby", ["column", "array", "function"])
 @pytest.mark.parametrize("normalize, name", [(True, "proportion"), (False, "count")])
 @pytest.mark.parametrize(
@@ -356,6 +359,7 @@ def test_against_frame_and_seriesgroupby(
             tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize(
     "dtype",
     [

pandas/tests/groupby/test_grouping.py

@@ -10,6 +10,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas.errors import SpecificationError
 
 import pandas as pd
@@ -805,6 +807,7 @@ def test_groupby_empty(self):
         expected = ["name"]
         assert result == expected
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_groupby_level_index_value_all_na(self):
         # issue 20519
         df = DataFrame(
@@ -978,6 +981,7 @@ def test_groupby_with_empty(self):
         grouped = series.groupby(grouper)
         assert next(iter(grouped), None) is None
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_groupby_with_single_column(self):
         df = DataFrame({"a": list("abssbab")})
         tm.assert_frame_equal(df.groupby("a").get_group("a"), df.iloc[[0, 5]])

pandas/tests/groupby/test_raises.py

@@ -8,6 +8,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas import (
     Categorical,
     DataFrame,
@@ -104,6 +106,7 @@ def _call_and_check(klass, msg, how, gb, groupby_func, args, warn_msg=""):
                     gb.transform(groupby_func, *args)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
 @pytest.mark.parametrize("how", ["method", "agg", "transform"])
 def test_groupby_raises_string(
     how, by, groupby_series, groupby_func, df_with_string_col
@@ -205,6 +208,7 @@ 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(

pandas/tests/indexes/base_class/test_setops.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas as pd
 from pandas import (
     Index,
@@ -231,6 +233,7 @@ def test_tuple_union_bug(self, method, expected, sort):
         expected = Index(expected)
         tm.assert_index_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("first_list", [["b", "a"], []])
     @pytest.mark.parametrize("second_list", [["a", "b"], []])
     @pytest.mark.parametrize(

pandas/tests/io/json/test_pandas.py

@@ -189,6 +189,7 @@ def test_roundtrip_simple(self, orient, convert_axes, dtype, float_frame):
 
         assert_json_roundtrip_equal(result, expected, orient)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("dtype", [False, np.int64])
     @pytest.mark.parametrize("convert_axes", [True, False])
     def test_roundtrip_intframe(self, orient, convert_axes, dtype, int_frame):
@@ -274,6 +275,7 @@ def test_roundtrip_empty(self, orient, convert_axes):
 
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     @pytest.mark.parametrize("convert_axes", [True, False])
     def test_roundtrip_timestamp(self, orient, convert_axes, datetime_frame):
         # TODO: improve coverage with date_format parameter
@@ -701,6 +703,7 @@ def test_series_roundtrip_simple(self, orient, string_series, using_infer_string
 
         tm.assert_series_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     @pytest.mark.parametrize("dtype", [False, None])
     def test_series_roundtrip_object(self, orient, dtype, object_series):
         data = StringIO(object_series.to_json(orient=orient))
@@ -810,6 +813,7 @@ def test_path(self, float_frame, int_frame, datetime_frame):
                 df.to_json(path)
                 read_json(path)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_axis_dates(self, datetime_series, datetime_frame):
         # frame
         json = StringIO(datetime_frame.to_json())
@@ -822,6 +826,7 @@ def test_axis_dates(self, datetime_series, datetime_frame):
         tm.assert_series_equal(result, datetime_series, check_names=False)
         assert result.name is None
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_convert_dates(self, datetime_series, datetime_frame):
         # frame
         df = datetime_frame
@@ -912,6 +917,7 @@ def test_convert_dates_infer(self, infer_word):
         result = read_json(StringIO(ujson_dumps(data)))[["id", infer_word]]
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     @pytest.mark.parametrize(
         "date,date_unit",
         [
@@ -972,6 +978,7 @@ def test_date_format_series_raises(self, datetime_series):
         with pytest.raises(ValueError, match=msg):
             ts.to_json(date_format="iso", date_unit="foo")
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_date_unit(self, unit, datetime_frame):
         df = datetime_frame
         df["date"] = Timestamp("20130101 20:43:42").as_unit("ns")
@@ -1112,6 +1119,7 @@ def test_round_trip_exception(self, datapath):
         res = res.fillna(np.nan)
         tm.assert_frame_equal(res, df)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     @pytest.mark.network
     @pytest.mark.single_cpu
     @pytest.mark.parametrize(
@@ -1414,6 +1422,7 @@ def test_read_inline_jsonl(self):
         expected = DataFrame([[1, 2], [1, 2]], columns=["a", "b"])
         tm.assert_frame_equal(result, expected)
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     @pytest.mark.single_cpu
     @td.skip_if_not_us_locale
     def test_read_s3_jsonl(self, s3_public_bucket_with_data, s3so):
@@ -2013,6 +2022,7 @@ def test_json_multiindex(self):
         result = series.to_json(orient="index")
         assert result == expected
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     @pytest.mark.single_cpu
     def test_to_s3(self, s3_public_bucket, s3so):
         # GH 28375
@@ -2134,6 +2144,7 @@ def test_json_uint64(self):
         result = df.to_json(orient="split")
         assert result == expected
 
+    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)", strict=False)
     def test_read_json_dtype_backend(
         self, string_storage, dtype_backend, orient, using_infer_string
     ):

pandas/tests/io/pytables/test_timezones.py

@@ -6,6 +6,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas._libs.tslibs.timezones import maybe_get_tz
 import pandas.util._test_decorators as td
 
@@ -42,6 +44,7 @@ def _compare_with_tz(a, b):
 gettz_pytz = lambda x: x
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize("gettz", [gettz_dateutil, gettz_pytz])
 def test_append_with_timezones(setup_path, gettz):
     # as columns
@@ -216,6 +219,7 @@ def test_tseries_select_index_column(setup_path):
         assert rng.tz == result.dt.tz
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_timezones_fixed_format_frame_non_empty(setup_path):
     with ensure_clean_store(setup_path) as store:
         # index
@@ -245,6 +249,7 @@ def test_timezones_fixed_format_frame_non_empty(setup_path):
         tm.assert_frame_equal(result, df)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_timezones_fixed_format_empty(setup_path, tz_aware_fixture, frame_or_series):
     # GH 20594
 
@@ -260,6 +265,7 @@ def test_timezones_fixed_format_empty(setup_path, tz_aware_fixture, frame_or_ser
         tm.assert_equal(result, obj)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_timezones_fixed_format_series_nonempty(setup_path, tz_aware_fixture):
     # GH 20594
 
@@ -312,6 +318,7 @@ def test_store_timezone(setup_path):
         tm.assert_frame_equal(result, df)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_dst_transitions(setup_path):
     # make sure we are not failing on transitions
     with ensure_clean_store(setup_path) as store:
@@ -332,6 +339,7 @@ def test_dst_transitions(setup_path):
             tm.assert_frame_equal(result, df)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_read_with_where_tz_aware_index(tmp_path, setup_path):
     # GH 11926
     periods = 10

pandas/tests/io/test_sql.py

@@ -18,6 +18,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 from pandas._libs import lib
 from pandas.compat import pa_version_under14p1
 from pandas.compat._optional import import_optional_dependency
@@ -1794,6 +1796,7 @@ def test_api_date_parsing(conn, request):
     ]
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize("conn", all_connectable_types)
 @pytest.mark.parametrize("error", ["raise", "coerce"])
 @pytest.mark.parametrize(
@@ -3183,6 +3186,7 @@ class DummyException(Exception):
         assert len(res2) == 1
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize("conn", sqlalchemy_connectable)
 def test_get_schema_create_table(conn, request, test_frame3):
     # Use a dataframe without a bool column, since MySQL converts bool to
@@ -3574,6 +3578,7 @@ def test_read_sql_dtype_backend(
             tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 @pytest.mark.parametrize("conn", all_connectable)
 @pytest.mark.parametrize("func", ["read_sql", "read_sql_table"])
 def test_read_sql_dtype_backend_table(