TST (string dtype): add test build with future strings enabled without pyarrow (pandas-dev#59437)

* TST (string dtype): add test build with future strings enabled without pyarrow

* ensure the build doesn't override the default ones

* uninstall -> remove

* avoid jobs with same env being cancelled

* use different python version for both future jobs

* add some xfails

* fixup xfails

* less strict

Author: WillAyd

.github/actions/setup-conda/action.yml

@@ -14,3 +14,9 @@ runs:
         condarc-file: ci/.condarc
         cache-environment: true
         cache-downloads: true
+
+    - name: Uninstall pyarrow
+      if: ${{ env.REMOVE_PYARROW == '1' }}
+      run: |
+        micromamba remove -y pyarrow
+      shell: bash -el {0}

.github/workflows/unit-tests.yml

@@ -29,6 +29,7 @@ jobs:
         env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml, actions-312.yaml]
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
+        pandas_future_infer_string: ["0"]
         include:
           - name: "Downstream Compat"
             env_file: actions-311-downstream_compat.yaml
@@ -86,6 +87,9 @@ jobs:
             pattern: "not slow and not network and not single_cpu"
             pandas_copy_on_write: "warn"
           - name: "Future infer strings"
+            env_file: actions-312.yaml
+            pandas_future_infer_string: "1"
+          - name: "Future infer strings (without pyarrow)"
             env_file: actions-311.yaml
             pandas_future_infer_string: "1"
           - name: "Pypy"
@@ -114,9 +118,10 @@ jobs:
       NPY_PROMOTION_STATE: ${{ matrix.env_file == 'actions-311-numpydev.yaml' && 'weak' || 'legacy' }}
       # Clipboard tests
       QT_QPA_PLATFORM: offscreen
+      REMOVE_PYARROW: ${{ matrix.name == 'Future infer strings (without pyarrow)' && '1' || '0' }}
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_copy_on_write || '' }}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_copy_on_write || '' }}-${{ matrix.pandas_future_infer_string }}
       cancel-in-progress: true
 
     services:

pandas/tests/apply/test_frame_apply.py

@@ -6,6 +6,8 @@
 
 from pandas._config import using_string_dtype
 
+from pandas.compat import HAS_PYARROW
+
 from pandas.core.dtypes.dtypes import CategoricalDtype
 
 import pandas as pd
@@ -1201,6 +1203,9 @@ 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(

pandas/tests/apply/test_invalid_arg.py

@@ -12,6 +12,9 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
+from pandas.compat import HAS_PYARROW
 from pandas.errors import SpecificationError
 
 from pandas import (
@@ -209,6 +212,10 @@ def transform(row):
         data.apply(transform, axis=1)
 
 
+# we should raise a proper TypeError instead of propagating the pyarrow error
+@pytest.mark.xfail(
+    using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)"
+)
 @pytest.mark.parametrize(
     "df, func, expected",
     tm.get_cython_table_params(
@@ -229,6 +236,10 @@ def test_agg_cython_table_raises_frame(df, func, expected, axis, using_infer_str
             df.agg(func, axis=axis)
 
 
+# we should raise a proper TypeError instead of propagating the pyarrow error
+@pytest.mark.xfail(
+    using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)"
+)
 @pytest.mark.parametrize(
     "series, func, expected",
     chain(

pandas/tests/apply/test_numba.py

@@ -104,6 +104,7 @@ def test_numba_nonunique_unsupported(apply_axis):
 
 
 def test_numba_unsupported_dtypes(apply_axis):
+    pytest.importorskip("pyarrow")
     f = lambda x: x
     df = DataFrame({"a": [1, 2], "b": ["a", "b"], "c": [4, 5]})
     df["c"] = df["c"].astype("double[pyarrow]")

pandas/tests/arithmetic/test_object.py

@@ -8,6 +8,9 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
+from pandas.compat import HAS_PYARROW
 import pandas.util._test_decorators as td
 
 import pandas as pd
@@ -315,6 +318,9 @@ def test_add(self):
         expected = pd.Index(["1a", "1b", "1c"])
         tm.assert_index_equal("1" + index, expected)
 
+    @pytest.mark.xfail(
+        using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)"
+    )
     def test_sub_fail(self, using_infer_string):
         index = pd.Index([str(i) for i in range(10)])
 

pandas/tests/arrays/boolean/test_arithmetic.py

@@ -3,6 +3,10 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
+from pandas.compat import HAS_PYARROW
+
 import pandas as pd
 import pandas._testing as tm
 
@@ -90,6 +94,9 @@ def test_op_int8(left_array, right_array, opname):
 # -----------------------------------------------------------------------------
 
 
+@pytest.mark.xfail(
+    using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)"
+)
 def test_error_invalid_values(data, all_arithmetic_operators, using_infer_string):
     # invalid ops
 

pandas/tests/arrays/categorical/test_analytics.py

@@ -6,7 +6,10 @@
 
 from pandas._config import using_string_dtype
 
-from pandas.compat import PYPY
+from pandas.compat import (
+    HAS_PYARROW,
+    PYPY,
+)
 
 from pandas import (
     Categorical,
@@ -298,7 +301,9 @@ 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)")
+    @pytest.mark.xfail(
+        using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)"
+    )
     def test_memory_usage(self):
         cat = Categorical([1, 2, 3])
 

pandas/tests/arrays/categorical/test_constructors.py

@@ -8,6 +8,8 @@
 
 from pandas._config import using_string_dtype
 
+from pandas.compat import HAS_PYARROW
+
 from pandas.core.dtypes.common import (
     is_float_dtype,
     is_integer_dtype,
@@ -449,7 +451,9 @@ def test_constructor_str_unknown(self):
         with pytest.raises(ValueError, match="Unknown dtype"):
             Categorical([1, 2], dtype="foo")
 
-    @pytest.mark.xfail(using_string_dtype(), reason="Can't be NumPy strings")
+    @pytest.mark.xfail(
+        using_string_dtype() and HAS_PYARROW, reason="Can't be NumPy strings"
+    )
     def test_constructor_np_strs(self):
         # GH#31499 Hashtable.map_locations needs to work on np.str_ objects
         cat = Categorical(["1", "0", "1"], [np.str_("0"), np.str_("1")])

pandas/tests/arrays/integer/test_reduction.py

@@ -1,6 +1,8 @@
 import numpy as np
 import pytest
 
+from pandas.compat import HAS_PYARROW
+
 import pandas as pd
 from pandas import (
     DataFrame,
@@ -102,9 +104,10 @@ def test_groupby_reductions(op, expected):
         ["all", Series([True, True, True], index=["A", "B", "C"], dtype="boolean")],
     ],
 )
-def test_mixed_reductions(op, expected, using_infer_string):
-    if op in ["any", "all"] and using_infer_string:
-        expected = expected.astype("bool")
+def test_mixed_reductions(request, op, expected, using_infer_string):
+    if op in ["any", "all"] and using_infer_string and HAS_PYARROW:
+        # TODO(infer_string) inconsistent result type
+        request.applymarker(pytest.mark.xfail(reason="TODO(infer_string)"))
     df = DataFrame(
         {
             "A": ["a", "b", "b"],

pandas/tests/base/test_conversion.py

@@ -1,6 +1,10 @@
 import numpy as np
 import pytest
 
+from pandas._config import using_string_dtype
+
+from pandas.compat import HAS_PYARROW
+
 from pandas.core.dtypes.dtypes import DatetimeTZDtype
 
 import pandas as pd
@@ -20,6 +24,7 @@
     SparseArray,
     TimedeltaArray,
 )
+from pandas.core.arrays.string_ import StringArrayNumpySemantics
 from pandas.core.arrays.string_arrow import ArrowStringArrayNumpySemantics
 
 
@@ -218,7 +223,9 @@ def test_iter_box_period(self):
 )
 def test_values_consistent(arr, expected_type, dtype, using_infer_string):
     if using_infer_string and dtype == "object":
-        expected_type = ArrowStringArrayNumpySemantics
+        expected_type = (
+            ArrowStringArrayNumpySemantics if HAS_PYARROW else StringArrayNumpySemantics
+        )
     l_values = Series(arr)._values
     r_values = pd.Index(arr)._values
     assert type(l_values) is expected_type
@@ -355,6 +362,9 @@ def test_to_numpy(arr, expected, index_or_series_or_array, request):
     tm.assert_numpy_array_equal(result, expected)
 
 
+@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)]

pandas/tests/copy_view/test_astype.py

@@ -5,6 +5,7 @@
 
 from pandas._config import using_string_dtype
 
+from pandas.compat import HAS_PYARROW
 from pandas.compat.pyarrow import pa_version_under12p0
 import pandas.util._test_decorators as td
 
@@ -223,7 +224,7 @@ def test_astype_arrow_timestamp(using_copy_on_write):
             )
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_convert_dtypes_infer_objects(using_copy_on_write):
     ser = Series(["a", "b", "c"])
     ser_orig = ser.copy()
@@ -243,7 +244,7 @@ def test_convert_dtypes_infer_objects(using_copy_on_write):
     tm.assert_series_equal(ser, ser_orig)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_convert_dtypes(using_copy_on_write):
     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_functions.py

@@ -3,6 +3,8 @@
 
 from pandas._config import using_string_dtype
 
+from pandas.compat import HAS_PYARROW
+
 from pandas import (
     DataFrame,
     Index,
@@ -14,7 +16,7 @@
 from pandas.tests.copy_view.util import get_array
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_concat_frames(using_copy_on_write):
     df = DataFrame({"b": ["a"] * 3})
     df2 = DataFrame({"a": ["a"] * 3})
@@ -39,7 +41,7 @@ def test_concat_frames(using_copy_on_write):
     tm.assert_frame_equal(df, df_orig)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_concat_frames_updating_input(using_copy_on_write):
     df = DataFrame({"b": ["a"] * 3})
     df2 = DataFrame({"a": ["a"] * 3})
@@ -201,7 +203,7 @@ def test_concat_copy_keyword(using_copy_on_write, copy):
         assert not np.shares_memory(get_array(df2, "b"), get_array(result, "b"))
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 @pytest.mark.parametrize(
     "func",
     [
@@ -319,7 +321,7 @@ def test_merge_copy_keyword(using_copy_on_write, copy):
         assert not np.shares_memory(get_array(df2, "b"), get_array(result, "b"))
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_join_on_key(using_copy_on_write):
     df_index = Index(["a", "b", "c"], name="key")
 
@@ -353,7 +355,7 @@ def test_join_on_key(using_copy_on_write):
     tm.assert_frame_equal(df2, df2_orig)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_join_multiple_dataframes_on_key(using_copy_on_write):
     df_index = Index(["a", "b", "c"], name="key")
 

pandas/tests/copy_view/test_interp_fillna.py

@@ -3,6 +3,8 @@
 
 from pandas._config import using_string_dtype
 
+from pandas.compat import HAS_PYARROW
+
 from pandas import (
     NA,
     ArrowDtype,
@@ -159,7 +161,7 @@ def test_interpolate_cleaned_fill_method(using_copy_on_write):
     tm.assert_frame_equal(df, df_orig)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_interpolate_object_convert_no_op(using_copy_on_write):
     df = DataFrame({"a": ["a", "b", "c"], "b": 1})
     arr_a = get_array(df, "a")

pandas/tests/copy_view/test_methods.py

@@ -3,6 +3,7 @@
 
 from pandas._config import using_string_dtype
 
+from pandas.compat import HAS_PYARROW
 from pandas.errors import SettingWithCopyWarning
 
 import pandas as pd
@@ -952,7 +953,7 @@ def test_head_tail(method, using_copy_on_write, warn_copy_on_write):
     tm.assert_frame_equal(df, df_orig)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 def test_infer_objects(using_copy_on_write):
     df = DataFrame({"a": [1, 2], "b": "c", "c": 1, "d": "x"})
     df_orig = df.copy()
@@ -974,6 +975,9 @@ def test_infer_objects(using_copy_on_write):
     tm.assert_frame_equal(df, df_orig)
 
 
+@pytest.mark.xfail(
+    using_string_dtype() and not HAS_PYARROW, reason="TODO(infer_string)"
+)
 def test_infer_objects_no_reference(using_copy_on_write):
     df = DataFrame(
         {
@@ -1180,7 +1184,7 @@ def test_sort_values_inplace(using_copy_on_write, obj, kwargs, warn_copy_on_writ
         assert np.shares_memory(get_array(obj, "a"), get_array(view, "a"))
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
+@pytest.mark.xfail(using_string_dtype() and HAS_PYARROW, reason="TODO(infer_string)")
 @pytest.mark.parametrize("decimals", [-1, 0, 1])
 def test_round(using_copy_on_write, warn_copy_on_write, decimals):
     df = DataFrame({"a": [1, 2], "b": "c"})