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

@@ -16,3 +16,9 @@ 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"],