Merge branch 'rls-prep' of github.com:lithomas1/pandas into rls-prep

Author: lithomas1

.github/workflows/wheels.yml

@@ -102,9 +102,7 @@ jobs:
         python: [["cp310", "3.10"], ["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"]]
         include:
         # TODO: Remove this plus installing build deps in cibw_before_build.sh
-        # and test deps in cibw_before_test.sh after pandas can be built with a released NumPy/Cython
-        - python: ["cp313", "3.13"]
-          cibw_build_frontend: 'pip; args: --no-build-isolation'
+        # after pandas can be built with a released NumPy/Cython
         - python: ["cp313t", "3.13"]
           cibw_build_frontend: 'pip; args: --no-build-isolation'
         # Build Pyodide wheels and upload them to Anaconda.org
@@ -187,11 +185,9 @@ jobs:
       - name: Test Windows Wheels
         if: ${{ matrix.buildplat[1] == 'win_amd64' }}
         shell: pwsh
-        # TODO: Remove NumPy nightly install when there's a 3.13 wheel on PyPI
         run: |
           $TST_CMD = @"
           python -m pip install hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0;
-          ${{ matrix.python[1] == '3.13' && 'python -m pip install -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy;' }}
           python -m pip install `$(Get-Item pandas\wheelhouse\*.whl);
           python -c `'import pandas as pd; pd.test(extra_args=[`\"--no-strict-data-files`\", `\"-m not clipboard and not single_cpu and not slow and not network and not db`\"])`';
           "@

MANIFEST.in

@@ -65,4 +65,3 @@ graft pandas/_libs/include
 
 # Include cibw script in sdist since it's needed for building wheels
 include scripts/cibw_before_build.sh
-include scripts/cibw_before_test.sh

ci/code_checks.sh

@@ -383,7 +383,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.Week.n GL08" \
         -i "pandas.tseries.offsets.Week.normalize GL08" \
         -i "pandas.tseries.offsets.Week.weekday GL08" \
-        -i "pandas.tseries.offsets.WeekOfMonth SA01" \
         -i "pandas.tseries.offsets.WeekOfMonth.is_on_offset GL08" \
         -i "pandas.tseries.offsets.WeekOfMonth.n GL08" \
         -i "pandas.tseries.offsets.WeekOfMonth.normalize GL08" \

pandas/_libs/tslibs/np_datetime.pxd

@@ -89,7 +89,7 @@ cdef int string_to_dts(
     int* out_local,
     int* out_tzoffset,
     bint want_exc,
-    format: str | None = *,
+    str format = *,
     bint exact = *
 ) except? -1
 

pandas/_libs/tslibs/np_datetime.pyx

@@ -331,7 +331,7 @@ cdef int string_to_dts(
     int* out_local,
     int* out_tzoffset,
     bint want_exc,
-    format: str | None=None,
+    str format=None,
     bint exact=True,
 ) except? -1:
     cdef:

pandas/_libs/tslibs/offsets.pyx

@@ -3582,6 +3582,11 @@ cdef class WeekOfMonth(WeekOfMonthMixin):
     """
     Describes monthly dates like "the Tuesday of the 2nd week of each month".
 
+    This offset allows for generating or adjusting dates by specifying
+    a particular week and weekday within a month. The week is zero-indexed,
+    where 0 corresponds to the first week of the month, and weekday follows
+    a Monday=0 convention.
+
     Attributes
     ----------
     n : int, default 1
@@ -3602,6 +3607,12 @@ cdef class WeekOfMonth(WeekOfMonthMixin):
         - 5 is Saturday
         - 6 is Sunday.
 
+    See Also
+    --------
+    offsets.Week : Describes weekly frequency adjustments.
+    offsets.MonthEnd : Describes month-end frequency adjustments.
+    date_range : Generates a range of dates based on a specific frequency.
+
     Examples
     --------
     >>> ts = pd.Timestamp(2022, 1, 1)

pandas/core/computation/eval.py

@@ -14,7 +14,10 @@
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import validate_bool_kwarg
 
-from pandas.core.dtypes.common import is_extension_array_dtype
+from pandas.core.dtypes.common import (
+    is_extension_array_dtype,
+    is_string_dtype,
+)
 
 from pandas.core.computation.engines import ENGINES
 from pandas.core.computation.expr import (
@@ -345,10 +348,13 @@ def eval(
         parsed_expr = Expr(expr, engine=engine, parser=parser, env=env)
 
         if engine == "numexpr" and (
-            is_extension_array_dtype(parsed_expr.terms.return_type)
+            (
+                is_extension_array_dtype(parsed_expr.terms.return_type)
+                and not is_string_dtype(parsed_expr.terms.return_type)
+            )
             or getattr(parsed_expr.terms, "operand_types", None) is not None
             and any(
-                is_extension_array_dtype(elem)
+                (is_extension_array_dtype(elem) and not is_string_dtype(elem))
                 for elem in parsed_expr.terms.operand_types
             )
         ):

pandas/core/computation/expr.py

@@ -21,6 +21,8 @@
 
 from pandas.errors import UndefinedVariableError
 
+from pandas.core.dtypes.common import is_string_dtype
+
 import pandas.core.common as com
 from pandas.core.computation.ops import (
     ARITH_OPS_SYMS,
@@ -524,10 +526,12 @@ def _maybe_evaluate_binop(
         elif self.engine != "pytables":
             if (
                 getattr(lhs, "return_type", None) == object
+                or is_string_dtype(getattr(lhs, "return_type", None))
                 or getattr(rhs, "return_type", None) == object
+                or is_string_dtype(getattr(rhs, "return_type", None))
             ):
                 # evaluate "==" and "!=" in python if either of our operands
-                # has an object return type
+                # has an object or string return type
                 return self._maybe_eval(res, eval_in_python + maybe_eval_in_python)
         return res
 

pandas/tests/extension/test_sparse.py

@@ -340,11 +340,16 @@ def test_argmin_argmax_all_na(self, method, data, na_value):
         self._check_unsupported(data)
         super().test_argmin_argmax_all_na(method, data, na_value)
 
+    @pytest.mark.fails_arm_wheels
     @pytest.mark.parametrize("box", [pd.array, pd.Series, pd.DataFrame])
     def test_equals(self, data, na_value, as_series, box):
         self._check_unsupported(data)
         super().test_equals(data, na_value, as_series, box)
 
+    @pytest.mark.fails_arm_wheels
+    def test_equals_same_data_different_object(self, data):
+        super().test_equals_same_data_different_object(data)
+
     @pytest.mark.parametrize(
         "func, na_action, expected",
         [

pandas/tests/frame/test_query_eval.py

@@ -4,8 +4,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas.errors import (
     NumExprClobberingError,
     UndefinedVariableError,
@@ -762,7 +760,6 @@ def test_inf(self, op, f, engine, parser):
         result = df.query(q, engine=engine, parser=parser)
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_check_tz_aware_index_query(self, tz_aware_fixture):
         # https://github.com/pandas-dev/pandas/issues/29463
         tz = tz_aware_fixture
@@ -775,6 +772,7 @@ def test_check_tz_aware_index_query(self, tz_aware_fixture):
         tm.assert_frame_equal(result, expected)
 
         expected = DataFrame(df_index)
+        expected.columns = expected.columns.astype(object)
         result = df.reset_index().query('"2018-01-03 00:00:00+00" < time')
         tm.assert_frame_equal(result, expected)
 
@@ -1072,7 +1070,7 @@ def test_query_with_string_columns(self, parser, engine):
             with pytest.raises(NotImplementedError, match=msg):
                 df.query("a in b and c < d", parser=parser, engine=engine)
 
-    def test_object_array_eq_ne(self, parser, engine, using_infer_string):
+    def test_object_array_eq_ne(self, parser, engine):
         df = DataFrame(
             {
                 "a": list("aaaabbbbcccc"),
@@ -1081,14 +1079,11 @@ def test_object_array_eq_ne(self, parser, engine, using_infer_string):
                 "d": np.random.default_rng(2).integers(9, size=12),
             }
         )
-        warning = RuntimeWarning if using_infer_string and engine == "numexpr" else None
-        with tm.assert_produces_warning(warning):
-            res = df.query("a == b", parser=parser, engine=engine)
+        res = df.query("a == b", parser=parser, engine=engine)
         exp = df[df.a == df.b]
         tm.assert_frame_equal(res, exp)
 
-        with tm.assert_produces_warning(warning):
-            res = df.query("a != b", parser=parser, engine=engine)
+        res = df.query("a != b", parser=parser, engine=engine)
         exp = df[df.a != df.b]
         tm.assert_frame_equal(res, exp)
 
@@ -1128,15 +1123,13 @@ def test_query_with_nested_special_character(self, parser, engine):
         ],
     )
     def test_query_lex_compare_strings(
-        self, parser, engine, op, func, using_infer_string
+        self, parser, engine, op, func
     ):
         a = Series(np.random.default_rng(2).choice(list("abcde"), 20))
         b = Series(np.arange(a.size))
         df = DataFrame({"X": a, "Y": b})
 
-        warning = RuntimeWarning if using_infer_string and engine == "numexpr" else None
-        with tm.assert_produces_warning(warning):
-            res = df.query(f'X {op} "d"', engine=engine, parser=parser)
+        res = df.query(f'X {op} "d"', engine=engine, parser=parser)
         expected = df[func(df.X, "d")]
         tm.assert_frame_equal(res, expected)
 
@@ -1400,15 +1393,13 @@ def test_expr_with_column_name_with_backtick(self):
         expected = df[df["a`b"] < 2]
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_expr_with_string_with_backticks(self):
         # GH 59285
         df = DataFrame(("`", "`````", "``````````"), columns=["#backticks"])
         result = df.query("'```' < `#backticks`")
         expected = df["```" < df["#backticks"]]
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_expr_with_string_with_backticked_substring_same_as_column_name(self):
         # GH 59285
         df = DataFrame(("`", "`````", "``````````"), columns=["#backticks"])
@@ -1439,7 +1430,6 @@ def test_expr_with_column_names_with_special_characters(self, col1, col2, expr):
         expected = df[df[col1] < df[col2]]
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_expr_with_no_backticks(self):
         # GH 59285
         df = DataFrame(("aaa", "vvv", "zzz"), columns=["column_name"])
@@ -1483,15 +1473,13 @@ def test_expr_with_quote_opened_before_backtick_and_quote_is_unmatched(self):
         ):
             df.query("`column-name` < 'It`s that\\'s \"quote\" #hash")
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_expr_with_quote_opened_before_backtick_and_quote_is_matched_at_end(self):
         # GH 59285
         df = DataFrame(("aaa", "vvv", "zzz"), columns=["column-name"])
         result = df.query("`column-name` < 'It`s that\\'s \"quote\" #hash'")
         expected = df[df["column-name"] < 'It`s that\'s "quote" #hash']
         tm.assert_frame_equal(result, expected)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
     def test_expr_with_quote_opened_before_backtick_and_quote_is_matched_in_mid(self):
         # GH 59285
         df = DataFrame(("aaa", "vvv", "zzz"), columns=["column-name"])