Backport PR #56174: CI: Add 3.12 builds (#56333)

* Backport PR #56174: CI: Add 3.12 builds

* Update test_arrow.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: Patrick Hoefler <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: 3 people

.github/workflows/unit-tests.yml

@@ -26,7 +26,7 @@ jobs:
     timeout-minutes: 180
     strategy:
       matrix:
-        env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml]
+        env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml, actions-312.yaml]
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
         include:
@@ -69,6 +69,22 @@ jobs:
             env_file: actions-311.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_copy_on_write: "1"
+          - name: "Copy-on-Write 3.12"
+            env_file: actions-312.yaml
+            pattern: "not slow and not network and not single_cpu"
+            pandas_copy_on_write: "1"
+          - name: "Copy-on-Write 3.11 (warnings)"
+            env_file: actions-311.yaml
+            pattern: "not slow and not network and not single_cpu"
+            pandas_copy_on_write: "warn"
+          - name: "Copy-on-Write 3.10 (warnings)"
+            env_file: actions-310.yaml
+            pattern: "not slow and not network and not single_cpu"
+            pandas_copy_on_write: "warn"
+          - name: "Copy-on-Write 3.9 (warnings)"
+            env_file: actions-39.yaml
+            pattern: "not slow and not network and not single_cpu"
+            pandas_copy_on_write: "warn"
           - name: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -177,7 +193,7 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest, windows-latest]
-        env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml]
+        env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml, actions-312.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}
     name: ${{ format('{0} {1}', matrix.os, matrix.env_file) }}
@@ -308,7 +324,7 @@ jobs:
     #    To freeze this file, uncomment out the ``if: false`` condition, and migrate the jobs
     #    to the corresponding posix/windows-macos/sdist etc. workflows.
     # Feel free to modify this comment as necessary.
-    #if: false # Uncomment this to freeze the workflow, comment it to unfreeze
+    if: false # Uncomment this to freeze the workflow, comment it to unfreeze
     defaults:
       run:
         shell: bash -eou pipefail {0}

ci/deps/actions-312.yaml

@@ -0,0 +1,63 @@
+name: pandas-dev-312
+channels:
+  - conda-forge
+dependencies:
+  - python=3.12
+
+  # build dependencies
+  - versioneer[toml]
+  - cython>=0.29.33
+  - meson[ninja]=1.2.1
+  - meson-python=0.13.1
+
+  # test dependencies
+  - pytest>=7.3.2
+  - pytest-cov
+  - pytest-xdist>=2.2.0
+  - pytest-localserver>=0.7.1
+  - pytest-qt>=4.2.0
+  - boto3
+
+  # required dependencies
+  - python-dateutil
+  - numpy<2
+  - pytz
+
+  # optional dependencies
+  - beautifulsoup4>=4.11.1
+  - blosc>=1.21.3
+  - bottleneck>=1.3.4
+  - fastparquet>=0.8.1
+  - fsspec>=2022.05.0
+  - html5lib>=1.1
+  - hypothesis>=6.46.1
+  - gcsfs>=2022.05.0
+  - jinja2>=3.1.2
+  - lxml>=4.8.0
+  - matplotlib>=3.6.1
+  # - numba>=0.56.4
+  - numexpr>=2.8.0
+  - odfpy>=1.4.1
+  - qtpy>=2.2.0
+  - pyqt>=5.15.9
+  - openpyxl>=3.0.10
+  - psycopg2>=2.9.3
+  - pyarrow>=7.0.0
+  - pymysql>=1.0.2
+  - pyreadstat>=1.1.5
+  # - pytables>=3.8.0
+  # - python-calamine>=0.1.6
+  - pyxlsb>=1.0.9
+  - s3fs>=2022.05.0
+  - scipy>=1.8.1
+  - sqlalchemy>=1.4.36
+  - tabulate>=0.8.10
+  - xarray>=2022.03.0
+  - xlrd>=2.0.1
+  - xlsxwriter>=3.0.3
+  - zstandard>=0.17.0
+
+  - pip:
+    - adbc-driver-postgresql>=0.8.0
+    - adbc-driver-sqlite>=0.8.0
+    - tzdata>=2022.7

pandas/tests/computation/test_eval.py

@@ -542,6 +542,9 @@ def test_series_pos(self, lhs, engine, parser):
 
     def test_scalar_unary(self, engine, parser):
         msg = "bad operand type for unary ~: 'float'"
+        warn = None
+        if PY312 and not (engine == "numexpr" and parser == "pandas"):
+            warn = DeprecationWarning
         with pytest.raises(TypeError, match=msg):
             pd.eval("~1.0", engine=engine, parser=parser)
 
@@ -550,8 +553,14 @@ def test_scalar_unary(self, engine, parser):
         assert pd.eval("~1", parser=parser, engine=engine) == ~1
         assert pd.eval("-1", parser=parser, engine=engine) == -1
         assert pd.eval("+1", parser=parser, engine=engine) == +1
-        assert pd.eval("~True", parser=parser, engine=engine) == ~True
-        assert pd.eval("~False", parser=parser, engine=engine) == ~False
+        with tm.assert_produces_warning(
+            warn, match="Bitwise inversion", check_stacklevel=False
+        ):
+            assert pd.eval("~True", parser=parser, engine=engine) == ~True
+        with tm.assert_produces_warning(
+            warn, match="Bitwise inversion", check_stacklevel=False
+        ):
+            assert pd.eval("~False", parser=parser, engine=engine) == ~False
         assert pd.eval("-True", parser=parser, engine=engine) == -True
         assert pd.eval("-False", parser=parser, engine=engine) == -False
         assert pd.eval("+True", parser=parser, engine=engine) == +True

pandas/tests/io/excel/test_readers.py

@@ -1446,7 +1446,9 @@ def test_deprecate_bytes_input(self, engine, read_ext):
             "byte string, wrap it in a `BytesIO` object."
         )
 
-        with tm.assert_produces_warning(FutureWarning, match=msg):
+        with tm.assert_produces_warning(
+            FutureWarning, match=msg, raise_on_extra_warnings=False
+        ):
             with open("test1" + read_ext, "rb") as f:
                 pd.read_excel(f.read(), engine=engine)
 

pandas/tests/io/excel/test_writers.py

@@ -271,7 +271,9 @@ def test_read_excel_parse_dates(self, ext):
 
             date_parser = lambda x: datetime.strptime(x, "%m/%d/%Y")
             with tm.assert_produces_warning(
-                FutureWarning, match="use 'date_format' instead"
+                FutureWarning,
+                match="use 'date_format' instead",
+                raise_on_extra_warnings=False,
             ):
                 res = pd.read_excel(
                     pth,