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

…er_string (#59329) * TST (string dtype): xfail all currently failing tests with future.infer_string * more xfails * more xfails * add missing strict=False * also run slow and single cpu tests * fix single_cpu tests * xfail some slow tests * stop suppressing non-zero exit code from pytest on string CI build * remove accidentally added xlsx file --------- Co-authored-by: Matthew Roeschke <[email protected]>
pandas-dev · Jul 29, 2024 · 9c8c685 · 9c8c685
1 parent aa4dc71
commit 9c8c685
Show file tree

Hide file tree

Showing 132 changed files with 543 additions and 22 deletions.
diff --git a/.github/workflows/unit-tests.yml b/.github/workflows/unit-tests.yml
@@ -59,7 +59,6 @@ jobs:
             extra_loc: "zh_CN"
           - name: "Future infer strings"
             env_file: actions-311.yaml
-            pattern: "not slow and not network and not single_cpu"
             pandas_future_infer_string: "1"
           - name: "Pypy"
             env_file: actions-pypy-39.yaml

diff --git a/ci/run_tests.sh b/ci/run_tests.sh
@@ -16,11 +16,5 @@ if [[ "$PATTERN" ]]; then
   PYTEST_CMD="$PYTEST_CMD -m \"$PATTERN\""
 fi
 
-# temporarily let pytest always succeed (many tests are not yet passing in the
-# build enabling the future string dtype)
-if [[ "$PANDAS_FUTURE_INFER_STRING" == "1" ]]; then
-  PYTEST_CMD="$PYTEST_CMD || true"
-fi
-
 echo $PYTEST_CMD
 sh -c "$PYTEST_CMD"
diff --git a/pandas/tests/apply/test_frame_apply.py b/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):

diff --git a/pandas/tests/apply/test_numba.py b/pandas/tests/apply/test_numba.py
@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
 import pandas.util._test_decorators as td
 
 from pandas import (
@@ -17,6 +19,7 @@ def apply_axis(request):
     return request.param
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_numba_vs_python_noop(float_frame, apply_axis):
     func = lambda x: x
     result = float_frame.apply(func, engine="numba", axis=apply_axis)
@@ -40,6 +43,7 @@ def test_numba_vs_python_string_index():
     )
 
 
+@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_numba_vs_python_indexing():
     frame = DataFrame(
         {"a": [1, 2, 3], "b": [4, 5, 6], "c": [7.0, 8.0, 9.0]},

diff --git a/pandas/tests/apply/test_str.py b/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(

diff --git a/pandas/tests/arrays/categorical/test_analytics.py b/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])
 

diff --git a/pandas/tests/arrays/categorical/test_api.py b/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()

diff --git a/pandas/tests/arrays/categorical/test_constructors.py b/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(

diff --git a/pandas/tests/arrays/floating/test_arithmetic.py b/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)

diff --git a/pandas/tests/arrays/integer/test_arithmetic.py b/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)

diff --git a/pandas/tests/arrays/masked/test_function.py b/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
 

diff --git a/pandas/tests/copy_view/test_array.py b/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)

diff --git a/pandas/tests/copy_view/test_astype.py b/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()

diff --git a/pandas/tests/copy_view/test_constructors.py b/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)]
 )

diff --git a/pandas/tests/copy_view/test_functions.py b/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")
 

diff --git a/pandas/tests/copy_view/test_internals.py b/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",

diff --git a/pandas/tests/copy_view/test_interp_fillna.py b/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")