Merge branch 'main' into PR02-fix

Author: sanrishi

.github/actions/build_pandas/action.yml

@@ -6,8 +6,7 @@ inputs:
     default: true
   werror:
     description: Enable werror flag for build
-    # TMP disable werror until we fix all warnings with more recent meson
-    default: false
+    default: true
 runs:
   using: composite
   steps:

.github/workflows/code-checks.yml

@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.3.x
+      - 3.0.x
   pull_request:
     branches:
       - main
-      - 2.3.x
+      - 3.0.x
 
 env:
   ENV_FILE: environment.yml

.github/workflows/docbuild-and-upload.yml

@@ -4,13 +4,13 @@ on:
   push:
     branches:
       - main
-      - 2.3.x
+      - 3.0.x
     tags:
       - '*'
   pull_request:
     branches:
       - main
-      - 2.3.x
+      - 3.0.x
   workflow_dispatch:
     inputs:
       version:

.github/workflows/package-checks.yml

@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.3.x
+      - 3.0.x
   pull_request:
     branches:
       - main
-      - 2.3.x
+      - 3.0.x
     types: [ labeled, opened, synchronize, reopened ]
 
 permissions:

.github/workflows/unit-tests.yml

@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.3.x
+      - 3.0.x
   pull_request:
     branches:
       - main
-      - 2.3.x
+      - 3.0.x
     paths-ignore:
       - "doc/**"
       - "web/**"
@@ -166,10 +166,11 @@ jobs:
     - name: Build Pandas
       id: build
       uses: ./.github/actions/build_pandas
-      # TMP disable werror until we fix all warnings with more recent meson
-      # with:
-      #   # xref https://github.com/cython/cython/issues/6870
-      #   werror: ${{ matrix.name != 'Freethreading' }}
+      with:
+        # python3.14t/cpython/pyatomic_gcc.h:63:10:
+        #   error: ‘__atomic_fetch_add_8’
+        #   writing 8 bytes into a region of size 0 overflows the destination [-Werror=stringop-overflow=]
+        werror: ${{ matrix.name != 'Freethreading' }}
 
     - name: Test (not single_cpu)
       uses: ./.github/actions/run-tests
@@ -242,14 +243,12 @@ jobs:
           fi
       - name: Build environment and Run Tests
         # https://github.com/numpy/numpy/issues/24703#issuecomment-1722379388
-        # Note: Pinned to Cython 3.0.10 to avoid numerical instability in 32-bit environments
-        # https://github.com/pandas-dev/pandas/pull/61423
         run: |
           /opt/python/cp313-cp313/bin/python -m venv ~/virtualenvs/pandas-dev
           . ~/virtualenvs/pandas-dev/bin/activate
           python -m pip install --no-cache-dir -U pip wheel setuptools meson[ninja]==1.2.1 meson-python==0.13.1
           python -m pip install numpy -Csetup-args="-Dallow-noblas=true"
-          python -m pip install --no-cache-dir versioneer[toml] cython==3.0.10 python-dateutil pytest>=8.3.4 pytest-xdist>=3.6.1 hypothesis>=6.116.0
+          python -m pip install --no-cache-dir versioneer[toml] cython python-dateutil pytest>=8.3.4 pytest-xdist>=3.6.1 hypothesis>=6.116.0
           python -m pip install --no-cache-dir --no-build-isolation -e . -Csetup-args="--werror"
           python -m pip list --no-cache-dir
           PANDAS_CI=1 python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml

asv_bench/benchmarks/categoricals.py

@@ -29,7 +29,7 @@ def setup(self):
         self.datetimes_with_nat = self.datetimes.copy()
         self.datetimes_with_nat.iloc[-1] = pd.NaT
 
-        self.values_some_nan = list(np.tile(self.categories + [np.nan], N))
+        self.values_some_nan = list(np.tile([*self.categories, np.nan], N))
         self.values_all_nan = [np.nan] * len(self.values)
         self.values_all_int8 = np.ones(N, "int8")
         self.categorical = pd.Categorical(self.values, self.categories)

asv_bench/benchmarks/ctors.py

@@ -39,11 +39,11 @@ def list_of_lists(arr):
 
 
 def list_of_tuples_with_none(arr):
-    return [(i, -i) for i in arr][:-1] + [None]
+    return [*[(i, -i) for i in arr][:-1], None]
 
 
 def list_of_lists_with_none(arr):
-    return [[i, -i] for i in arr][:-1] + [None]
+    return [*[[i, -i] for i in arr][:-1], None]
 
 
 class SeriesConstructors:

asv_bench/benchmarks/hash_functions.py

@@ -44,8 +44,8 @@ class Unique:
     param_names = ["dtype"]
 
     def setup(self, dtype):
-        self.ser = pd.Series(([1, pd.NA, 2] + list(range(100_000))) * 3, dtype=dtype)
-        self.ser_unique = pd.Series(list(range(300_000)) + [pd.NA], dtype=dtype)
+        self.ser = pd.Series(([1, pd.NA, 2, *range(100000)]) * 3, dtype=dtype)
+        self.ser_unique = pd.Series([*range(300000), pd.NA], dtype=dtype)
 
     def time_unique_with_duplicates(self, exponent):
         pd.unique(self.ser)
@@ -62,7 +62,7 @@ class NumericSeriesIndexing:
     param_names = ["dtype", "N"]
 
     def setup(self, dtype, N):
-        vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype)
+        vals = np.array([*range(55), 54, *range(55, N - 1)], dtype=dtype)
         indices = pd.Index(vals)
         self.data = pd.Series(np.arange(N), index=indices)
 
@@ -79,7 +79,7 @@ class NumericSeriesIndexingShuffled:
     param_names = ["dtype", "N"]
 
     def setup(self, dtype, N):
-        vals = np.array(list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype)
+        vals = np.array([*range(55), 54, *range(55, N - 1)], dtype=dtype)
         np.random.shuffle(vals)
         indices = pd.Index(vals)
         self.data = pd.Series(np.arange(N), index=indices)

asv_bench/benchmarks/indexing.py

@@ -36,7 +36,7 @@ def setup(self, dtype, index_structure):
         indices = {
             "unique_monotonic_inc": Index(range(N), dtype=dtype),
             "nonunique_monotonic_inc": Index(
-                list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype
+                [*list(range(55)), 54, *list(range(55, N - 1))], dtype=dtype
             ),
         }
         self.data = Series(np.random.rand(N), index=indices[index_structure])
@@ -85,7 +85,7 @@ def time_loc_slice(self, index, index_structure):
 
 class NumericMaskedIndexing:
     monotonic_list = list(range(10**6))
-    non_monotonic_list = list(range(50)) + [54, 53, 52, 51] + list(range(55, 10**6 - 1))
+    non_monotonic_list = [*list(range(50)), 54, 53, 52, 51, *list(range(55, 10**6 - 1))]
 
     params = [
         ("Int64", "UInt64", "Float64"),
@@ -197,7 +197,7 @@ def setup(self, dtype, index_structure):
         indices = {
             "unique_monotonic_inc": Index(range(N), dtype=dtype),
             "nonunique_monotonic_inc": Index(
-                list(range(55)) + [54] + list(range(55, N - 1)), dtype=dtype
+                [*list(range(55)), 54, *list(range(55, N - 1))], dtype=dtype
             ),
         }
         self.idx_dupe = np.array(range(30)) * 99
@@ -452,7 +452,7 @@ def setup(self, unique_cols):
         if not unique_cols:
             # GH#33032 single-row lookups with non-unique columns were
             #  15x slower than with unique columns
-            df.columns = ["A", "A"] + list(df.columns[2:])
+            df.columns = ["A", "A", *list(df.columns[2:])]
 
         self.df = df
 

asv_bench/benchmarks/multiindex_object.py

@@ -328,7 +328,7 @@ class Unique:
 
     def setup(self, dtype_val):
         level = Series(
-            [1, 2, dtype_val[1], dtype_val[1]] + list(range(1_000_000)),
+            [1, 2, dtype_val[1], dtype_val[1], *list(range(1000000))],
             dtype=dtype_val[0],
         )
         self.midx = MultiIndex.from_arrays([level, level])