Merge branch 'main' into BUG-56994/pyarrow-assignment-unexpected-dtypes

Author: droussea2001

.github/actions/build_pandas/action.yml

@@ -4,12 +4,6 @@ inputs:
   editable:
     description: Whether to build pandas in editable mode (default true)
     default: true
-  meson_args:
-    description: Extra flags to pass to meson
-    required: false
-  cflags_adds:
-    description: Items to append to the CFLAGS variable
-    required: false
 runs:
   using: composite
   steps:
@@ -30,12 +24,11 @@ runs:
 
     - name: Build Pandas
       run: |
-        export CFLAGS="$CFLAGS ${{ inputs.cflags_adds }}"
         if [[ ${{ inputs.editable }} == "true" ]]; then
-          pip install -e . --no-build-isolation -v --no-deps ${{ inputs.meson_args }} \
+          pip install -e . --no-build-isolation -v --no-deps \
             --config-settings=setup-args="--werror"
         else
-          pip install . --no-build-isolation -v --no-deps ${{ inputs.meson_args }} \
+          pip install . --no-build-isolation -v --no-deps \
             --config-settings=setup-args="--werror"
         fi
       shell: bash -el {0}

.github/actions/run-tests/action.yml

@@ -7,14 +7,14 @@ runs:
       shell: bash -el {0}
 
     - name: Publish test results
-      uses: actions/upload-artifact@v3
+      uses: actions/upload-artifact@v4
       with:
         name: Test results
         path: test-data.xml
       if: failure()
 
     - name: Upload coverage to Codecov
-      uses: codecov/codecov-action@v3
+      uses: codecov/codecov-action@v4
       with:
         flags: unittests
         name: codecov-pandas

.github/workflows/unit-tests.yml

@@ -74,9 +74,9 @@ jobs:
       PATTERN: ${{ matrix.pattern }}
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
-      PANDAS_CI: ${{ matrix.pandas_ci || '1' }}
+      PANDAS_CI: '1'
       TEST_ARGS: ${{ matrix.test_args || '' }}
-      PYTEST_WORKERS: ${{ matrix.pytest_workers || 'auto' }}
+      PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}
       NPY_PROMOTION_STATE: ${{ matrix.env_file == 'actions-311-numpydev.yaml' && 'weak' || 'legacy' }}
       # Clipboard tests
@@ -88,7 +88,7 @@ jobs:
 
     services:
       mysql:
-        image: mysql:8.0.33
+        image: mysql:8
         env:
           MYSQL_ALLOW_EMPTY_PASSWORD: yes
           MYSQL_DATABASE: pandas
@@ -101,7 +101,7 @@ jobs:
           - 3306:3306
 
       postgres:
-        image: postgres:13
+        image: postgres:16
         env:
           PGUSER: postgres
           POSTGRES_USER: postgres
@@ -116,7 +116,7 @@ jobs:
           - 5432:5432
 
       moto:
-        image: motoserver/moto:4.1.13
+        image: motoserver/moto:5.0.0
         env:
           AWS_ACCESS_KEY_ID: foobar_key
           AWS_SECRET_ACCESS_KEY: foobar_secret
@@ -148,9 +148,6 @@ jobs:
       uses: ./.github/actions/build_pandas
       # TODO: Re-enable once Pypy has Pypy 3.10 on conda-forge
       if: ${{ matrix.name != 'Pypy' }}
-      with:
-        meson_args: ${{ matrix.meson_args }}
-        cflags_adds: ${{ matrix.cflags_adds }}
 
     - name: Test (not single_cpu)
       uses: ./.github/actions/run-tests
@@ -302,7 +299,7 @@ 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}
@@ -317,7 +314,7 @@ jobs:
 
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-${{ matrix.pytest_target }}-dev
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-python-dev
       cancel-in-progress: true
 
     env:
@@ -334,7 +331,7 @@ jobs:
       - name: Set up Python Dev Version
         uses: actions/setup-python@v5
         with:
-          python-version: '3.12-dev'
+          python-version: '3.13-dev'
 
       - name: Build Environment
         run: |

ci/deps/actions-311-pyarrownightly.yaml

@@ -18,7 +18,7 @@ dependencies:
 
   # required dependencies
   - python-dateutil
-  - numpy
+  - numpy<2
   - pytz
   - pip
 

pandas/_libs/src/vendored/ujson/python/objToJSON.c

@@ -410,8 +410,8 @@ static void NpyArr_iterBegin(JSOBJ _obj, JSONTypeContext *tc) {
   npyarr->type_num = PyArray_DESCR(obj)->type_num;
 
   if (GET_TC(tc)->transpose) {
-    npyarr->dim = PyArray_DIM(obj, npyarr->ndim);
-    npyarr->stride = PyArray_STRIDE(obj, npyarr->ndim);
+    npyarr->dim = PyArray_DIM(obj, (int)npyarr->ndim);
+    npyarr->stride = PyArray_STRIDE(obj, (int)npyarr->ndim);
     npyarr->stridedim = npyarr->ndim;
     npyarr->index[npyarr->ndim] = 0;
     npyarr->inc = -1;
@@ -452,8 +452,8 @@ static void NpyArrPassThru_iterEnd(JSOBJ obj, JSONTypeContext *tc) {
     return;
   }
   const PyArrayObject *arrayobj = (const PyArrayObject *)npyarr->array;
-  npyarr->dim = PyArray_DIM(arrayobj, npyarr->stridedim);
-  npyarr->stride = PyArray_STRIDE(arrayobj, npyarr->stridedim);
+  npyarr->dim = PyArray_DIM(arrayobj, (int)npyarr->stridedim);
+  npyarr->stride = PyArray_STRIDE(arrayobj, (int)npyarr->stridedim);
   npyarr->dataptr += npyarr->stride;
 
   NpyArr_freeItemValue(obj, tc);
@@ -524,8 +524,8 @@ static int NpyArr_iterNext(JSOBJ _obj, JSONTypeContext *tc) {
   }
   const PyArrayObject *arrayobj = (const PyArrayObject *)npyarr->array;
 
-  npyarr->dim = PyArray_DIM(arrayobj, npyarr->stridedim);
-  npyarr->stride = PyArray_STRIDE(arrayobj, npyarr->stridedim);
+  npyarr->dim = PyArray_DIM(arrayobj, (int)npyarr->stridedim);
+  npyarr->stride = PyArray_STRIDE(arrayobj, (int)npyarr->stridedim);
   npyarr->index[npyarr->stridedim] = 0;
 
   ((PyObjectEncoder *)tc->encoder)->npyCtxtPassthru = npyarr;

pandas/_libs/tslibs/offsets.pyx

@@ -4948,7 +4948,12 @@ cpdef to_offset(freq, bint is_period=False):
     if result is None:
         raise ValueError(INVALID_FREQ_ERR_MSG.format(freq))
 
-    if is_period and not hasattr(result, "_period_dtype_code"):
+    try:
+        has_period_dtype_code = hasattr(result, "_period_dtype_code")
+    except ValueError:
+        has_period_dtype_code = False
+
+    if is_period and not has_period_dtype_code:
         if isinstance(freq, str):
             raise ValueError(f"{result.name} is not supported as period frequency")
         else:

pandas/compat/__init__.py

@@ -31,6 +31,7 @@
     pa_version_under14p0,
     pa_version_under14p1,
     pa_version_under16p0,
+    pa_version_under17p0,
 )
 
 if TYPE_CHECKING:
@@ -154,6 +155,7 @@ def is_ci_environment() -> bool:
     "pa_version_under14p0",
     "pa_version_under14p1",
     "pa_version_under16p0",
+    "pa_version_under17p0",
     "IS64",
     "ISMUSL",
     "PY311",

pandas/compat/numpy/__init__.py

@@ -12,7 +12,7 @@
 np_version_gte1p24 = _nlv >= Version("1.24")
 np_version_gte1p24p3 = _nlv >= Version("1.24.3")
 np_version_gte1p25 = _nlv >= Version("1.25")
-np_version_gt2 = _nlv >= Version("2.0.0.dev0")
+np_version_gt2 = _nlv >= Version("2.0.0")
 is_numpy_dev = _nlv.dev is not None
 _min_numpy_ver = "1.23.5"
 

pandas/compat/pyarrow.py

@@ -16,6 +16,7 @@
     pa_version_under14p1 = _palv < Version("14.0.1")
     pa_version_under15p0 = _palv < Version("15.0.0")
     pa_version_under16p0 = _palv < Version("16.0.0")
+    pa_version_under17p0 = _palv < Version("17.0.0")
 except ImportError:
     pa_version_under10p1 = True
     pa_version_under11p0 = True
@@ -25,3 +26,4 @@
     pa_version_under14p1 = True
     pa_version_under15p0 = True
     pa_version_under16p0 = True
+    pa_version_under17p0 = True

pandas/core/dtypes/cast.py

@@ -39,7 +39,6 @@
     is_supported_dtype,
 )
 from pandas._libs.tslibs.timedeltas import array_to_timedelta64
-from pandas.compat.numpy import np_version_gt2
 from pandas.errors import (
     IntCastingNaNError,
     LossySetitemError,
@@ -1643,13 +1642,11 @@ def maybe_cast_to_integer_array(arr: list | np.ndarray, dtype: np.dtype) -> np.n
             with warnings.catch_warnings():
                 # We already disallow dtype=uint w/ negative numbers
                 # (test_constructor_coercion_signed_to_unsigned) so safe to ignore.
-                if not np_version_gt2:
-                    warnings.filterwarnings(
-                        "ignore",
-                        "NumPy will stop allowing conversion of "
-                        "out-of-bound Python int",
-                        DeprecationWarning,
-                    )
+                warnings.filterwarnings(
+                    "ignore",
+                    "NumPy will stop allowing conversion of " "out-of-bound Python int",
+                    DeprecationWarning,
+                )
                 casted = np.asarray(arr, dtype=dtype)
         else:
             with warnings.catch_warnings():