Merge remote-tracking branch 'upstream/main' into cow/ser_array

Author: mroeschke

.circleci/config.yml

@@ -72,10 +72,6 @@ jobs:
           no_output_timeout: 30m # Sometimes the tests won't generate any output, make sure the job doesn't get killed by that
           command: |
             pip3 install cibuildwheel==2.15.0
-            # When this is a nightly wheel build, allow picking up NumPy 2.0 dev wheels:
-            if [[ "$IS_SCHEDULE_DISPATCH" == "true" || "$IS_PUSH" != 'true' ]]; then
-                export CIBW_ENVIRONMENT="PIP_EXTRA_INDEX_URL=https://pypi.anaconda.org/scientific-python-nightly-wheels/simple"
-            fi
             cibuildwheel --prerelease-pythons --output-dir wheelhouse
 
           environment:

.github/ISSUE_TEMPLATE/pdep_vote.yaml

@@ -0,0 +1,74 @@
+name: PDEP Vote
+description: Call for a vote on a PDEP
+title: "VOTE: "
+labels: [Vote]
+
+body:
+  - type: markdown
+    attributes:
+      value: >
+        As per [PDEP-1](https://pandas.pydata.org/pdeps/0001-purpose-and-guidelines.html), the following issue template should be used when a
+        maintainer has opened a PDEP discussion and is ready to call for a vote.
+  - type: checkboxes
+    attributes:
+      label: Locked issue
+      options:
+        - label: >
+            I locked this voting issue so that only voting members are able to cast their votes or
+            comment on this issue.
+          required: true
+  - type: input
+    id: PDEP-name
+    attributes:
+      label: PDEP number and title
+      placeholder: >
+        PDEP-1: Purpose and guidelines
+    validations:
+      required: true
+  - type: input
+    id: PDEP-link
+    attributes:
+      label: Pull request with discussion
+      description: e.g. https://github.com/pandas-dev/pandas/pull/47444
+    validations:
+      required: true
+  - type: input
+    id: PDEP-rendered-link
+    attributes:
+      label: Rendered PDEP for easy reading
+      description: e.g. https://github.com/pandas-dev/pandas/pull/47444/files?short_path=7c449e6#diff-7c449e698132205b235c501f7e47ebba38da4d2b7f9492c98f16745dba787041
+    validations:
+      required: true
+  - type: input
+    id: PDEP-number-of-discussion-participants
+    attributes:
+      label: Discussion participants
+      description: >
+        You may find it useful to list or total the number of participating members in the
+        PDEP discussion PR. This would be the maximum possible disapprove votes.
+      placeholder: >
+        14 voting members participated in the PR discussion thus far.
+  - type: input
+    id: PDEP-vote-end
+    attributes:
+      label: Voting will close in 15 days.
+      description: The voting period end date. ('Voting will close in 15 days.' will be automatically written)
+  - type: markdown
+    attributes:
+      value: ---
+  - type: textarea
+    id: Vote
+    attributes:
+      label: Vote
+      value: |
+        Cast your vote in a comment below.
+        * +1: approve.
+        * 0: abstain.
+            * Reason: A one sentence reason is required.
+        * -1: disapprove
+            * Reason: A one sentence reason is required.
+        A disapprove vote requires prior participation in the linked discussion PR.
+
+        @pandas-dev/pandas-core
+    validations:
+      required: true

.github/workflows/code-checks.yml

@@ -85,7 +85,7 @@ jobs:
         echo "PYTHONPATH=$PYTHONPATH" >> $GITHUB_ENV
       if: ${{ steps.build.outcome == 'success' && always() }}
 
-    - name: Typing + pylint
+    - name: Typing
       uses: pre-commit/[email protected]
       with:
         extra_args: --verbose --hook-stage manual --all-files

.github/workflows/wheels.yml

@@ -139,27 +139,14 @@ jobs:
         shell: bash -el {0}
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
-      - name: Build normal wheels
-        if: ${{ (env.IS_SCHEDULE_DISPATCH != 'true' || env.IS_PUSH == 'true') }}
+      - name: Build wheels
         uses: pypa/[email protected]
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
           CIBW_PRERELEASE_PYTHONS: True
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
 
-      - name: Build nightly wheels (with NumPy pre-release)
-        if: ${{ (env.IS_SCHEDULE_DISPATCH == 'true' && env.IS_PUSH != 'true') }}
-        uses: pypa/[email protected]
-        with:
-         package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
-        env:
-          # The nightly wheels should be build witht he NumPy 2.0 pre-releases
-          # which requires the additional URL.
-          CIBW_ENVIRONMENT: PIP_EXTRA_INDEX_URL=https://pypi.anaconda.org/scientific-python-nightly-wheels/simple
-          CIBW_PRERELEASE_PYTHONS: True
-          CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
-
       - name: Set up Python
         uses: mamba-org/setup-micromamba@v1
         with:

.pre-commit-config.yaml

@@ -16,10 +16,10 @@ ci:
     autofix_prs: false
     autoupdate_schedule: monthly
     # manual stage hooks
-    skip: [pylint, pyright, mypy]
+    skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.1
+    rev: v0.3.4
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -30,16 +30,10 @@ repos:
         files: ^pandas
         exclude: ^pandas/tests
         args: [--select, "ANN001,ANN2", --fix-only, --exit-non-zero-on-fix]
-    -   id: ruff
-        name: ruff-use-pd_array-in-core
-        alias: ruff-use-pd_array-in-core
-        files: ^pandas/core/
-        exclude: ^pandas/core/api\.py$
-        args: [--select, "ICN001", --exit-non-zero-on-fix]
     -   id: ruff-format
         exclude: ^scripts
 -   repo: https://github.com/jendrikseipp/vulture
-    rev: 'v2.10'
+    rev: 'v2.11'
     hooks:
       - id: vulture
         entry: python scripts/run_vulture.py
@@ -73,31 +67,12 @@ repos:
     -   id: fix-encoding-pragma
         args: [--remove]
     -   id: trailing-whitespace
--   repo: https://github.com/pylint-dev/pylint
-    rev: v3.0.1
-    hooks:
-    -   id: pylint
-        stages: [manual]
-        args: [--load-plugins=pylint.extensions.redefined_loop_name, --fail-on=I0021]
-    -   id: pylint
-        alias: redefined-outer-name
-        name: Redefining name from outer scope
-        files: ^pandas/
-        exclude: |
-            (?x)
-            ^pandas/tests  # keep excluded
-            |/_testing/  # keep excluded
-            |^pandas/util/_test_decorators\.py  # keep excluded
-            |^pandas/_version\.py  # keep excluded
-            |^pandas/conftest\.py  # keep excluded
-        args: [--disable=all, --enable=redefined-outer-name]
-        stages: [manual]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+    rev: 5.13.2
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.15.0
+    rev: v3.15.2
     hooks:
     -   id: pyupgrade
         args: [--py39-plus]
@@ -116,7 +91,7 @@ repos:
     hooks:
     - id: sphinx-lint
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v17.0.6
+    rev: v18.1.2
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

asv_bench/asv.conf.json

@@ -41,6 +41,7 @@
     // pip (with all the conda available packages installed first,
     // followed by the pip installed packages).
     "matrix": {
+        "pip+build": [],
         "Cython": ["3.0"],
         "matplotlib": [],
         "sqlalchemy": [],

asv_bench/benchmarks/categoricals.py

@@ -24,7 +24,7 @@ def setup(self):
         self.codes = np.tile(range(len(self.categories)), N)
 
         self.datetimes = pd.Series(
-            pd.date_range("1995-01-01 00:00:00", periods=N / 10, freq="s")
+            pd.date_range("1995-01-01 00:00:00", periods=N // 10, freq="s")
         )
         self.datetimes_with_nat = self.datetimes.copy()
         self.datetimes_with_nat.iloc[-1] = pd.NaT

asv_bench/benchmarks/frame_methods.py

@@ -862,4 +862,28 @@ def time_last_valid_index(self, dtype):
         self.df.last_valid_index()
 
 
+class Update:
+    def setup(self):
+        rng = np.random.default_rng()
+        self.df = DataFrame(rng.uniform(size=(1_000_000, 10)))
+
+        idx = rng.choice(range(1_000_000), size=1_000_000, replace=False)
+        self.df_random = DataFrame(self.df, index=idx)
+
+        idx = rng.choice(range(1_000_000), size=100_000, replace=False)
+        cols = rng.choice(range(10), size=2, replace=False)
+        self.df_sample = DataFrame(
+            rng.uniform(size=(100_000, 2)), index=idx, columns=cols
+        )
+
+    def time_to_update_big_frame_small_arg(self):
+        self.df.update(self.df_sample)
+
+    def time_to_update_random_indices(self):
+        self.df_random.update(self.df_sample)
+
+    def time_to_update_small_frame_big_arg(self):
+        self.df_sample.update(self.df)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/timeseries.py

@@ -29,7 +29,7 @@ def setup(self, index_type):
             "dst": date_range(
                 start="10/29/2000 1:00:00", end="10/29/2000 1:59:59", freq="s"
             ),
-            "repeated": date_range(start="2000", periods=N / 10, freq="s").repeat(10),
+            "repeated": date_range(start="2000", periods=N // 10, freq="s").repeat(10),
             "tz_aware": date_range(start="2000", periods=N, freq="s", tz="US/Eastern"),
             "tz_local": date_range(
                 start="2000", periods=N, freq="s", tz=dateutil.tz.tzlocal()