Updating to latest

Author: astronights

.circleci/config.yml

@@ -3,7 +3,7 @@ version: 2.1
 jobs:
   test-arm:
     machine:
-      image: ubuntu-2004:2022.04.1
+      image: default
     resource_class: arm.large
     environment:
       ENV_FILE: ci/deps/circle-310-arm64.yaml
@@ -46,7 +46,7 @@ jobs:
       cibw-build:
         type: string
     machine:
-      image: ubuntu-2004:2022.04.1
+      image: default
     resource_class: arm.large
     environment:
       TRIGGER_SOURCE: << pipeline.trigger_source >>

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

@@ -20,11 +20,6 @@ runs:
         path: test-data.xml
       if: failure()
 
-    - name: Report Coverage
-      run: coverage report -m
-      shell: bash -el {0}
-      if: failure()
-
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v3
       with:

.github/workflows/code-checks.yml

@@ -86,7 +86,7 @@ jobs:
       if: ${{ steps.build.outcome == 'success' && always() }}
 
     - name: Typing + pylint
-      uses: pre-commit/[email protected].0
+      uses: pre-commit/[email protected].1
       with:
         extra_args: --verbose --hook-stage manual --all-files
       if: ${{ steps.build.outcome == 'success' && always() }}

.github/workflows/comment-commands.yml

@@ -24,7 +24,7 @@ jobs:
     concurrency:
       group: ${{ github.actor }}-preview-docs
     steps:
-      - uses: pandas-dev/[email protected].1
+      - uses: pandas-dev/[email protected].2
         with:
           previewer-server: "https://pandas.pydata.org/preview"
           artifact-job: "Doc Build and Upload"

.github/workflows/package-checks.yml

@@ -24,7 +24,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        extra: ["test", "performance", "computation", "fss", "aws", "gcp", "excel", "parquet", "feather", "hdf5", "spss", "postgresql", "mysql", "sql-other", "html", "xml", "plot", "output-formatting", "clipboard", "compression", "consortium-standard", "all"]
+        extra: ["test", "pyarrow", "performance", "computation", "fss", "aws", "gcp", "excel", "parquet", "feather", "hdf5", "spss", "postgresql", "mysql", "sql-other", "html", "xml", "plot", "output-formatting", "clipboard", "compression", "all"]
       fail-fast: false
     name: Install Extras - ${{ matrix.extra }}
     concurrency:

.github/workflows/unit-tests.yml

@@ -57,33 +57,14 @@ jobs:
             # Also install zh_CN (its encoding is gb2312) but do not activate it.
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "zh_CN"
-          - name: "Copy-on-Write 3.9"
-            env_file: actions-39.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "1"
-          - name: "Copy-on-Write 3.10"
-            env_file: actions-310.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "1"
-          - name: "Copy-on-Write 3.11"
-            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: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "--max-worker-restart 0"
           - name: "Numpy Dev"
             env_file: actions-311-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
-            # Currently restricted the warnings that error to Deprecation Warnings from numpy
-            # done since pyarrow isn't compatible with numpydev always
-            # TODO: work with pyarrow to revert this?
-            test_args: "-W error::DeprecationWarning:numpy -W error::FutureWarning:numpy"
+            test_args: "-W error::DeprecationWarning -W error::FutureWarning"
           - name: "Pyarrow Nightly"
             env_file: actions-311-pyarrownightly.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -101,7 +82,6 @@ jobs:
       PATTERN: ${{ matrix.pattern }}
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
-      PANDAS_COPY_ON_WRITE: ${{ matrix.pandas_copy_on_write || '0' }}
       PANDAS_CI: ${{ matrix.pandas_ci || '1' }}
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: ${{ matrix.pytest_workers || 'auto' }}
@@ -111,7 +91,7 @@ jobs:
       QT_QPA_PLATFORM: offscreen
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_copy_on_write || '' }}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}}
       cancel-in-progress: true
 
     services:

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pylint, pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.6
+    rev: v0.3.1
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -30,9 +30,14 @@ 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
-        # TODO: "." not needed in ruff 0.1.8
-        args: ["."]
+        exclude: ^scripts
 -   repo: https://github.com/jendrikseipp/vulture
     rev: 'v2.10'
     hooks:
@@ -54,13 +59,11 @@ repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.5.0
     hooks:
-    -   id: check-ast
     -   id: check-case-conflict
     -   id: check-toml
     -   id: check-xml
     -   id: check-yaml
         exclude: ^ci/meta.yaml$
-    -   id: debug-statements
     -   id: end-of-file-fixer
         exclude: \.txt$
     -   id: mixed-line-ending
@@ -130,7 +133,7 @@ repos:
         types: [python]
         stages: [manual]
         additional_dependencies: &pyright_dependencies
-        - [email protected].347
+        - [email protected].351
     -   id: pyright
         # note: assumes python env is setup and activated
         name: pyright reportGeneralTypeIssues
@@ -209,39 +212,22 @@ repos:
         language: pygrep
         entry: |
             (?x)
-            # pytest.xfail instead of pytest.mark.xfail
-            pytest\.xfail
-
             # imports from pandas._testing instead of `import pandas._testing as tm`
-            |from\ pandas\._testing\ import
+            from\ pandas\._testing\ import
             |from\ pandas\ import\ _testing\ as\ tm
 
-            # No direct imports from conftest
-            |conftest\ import
-            |import\ conftest
-
             # pandas.testing instead of tm
             |pd\.testing\.
 
             # pd.api.types instead of from pandas.api.types import ...
             |(pd|pandas)\.api\.types\.
 
-            # np.testing, np.array_equal
-            |(numpy|np)(\.testing|\.array_equal)
-
-            # unittest.mock (use pytest builtin monkeypatch fixture instead)
-            |(unittest(\.| import )mock|mock\.Mock\(\)|mock\.patch)
+            # np.array_equal
+            |(numpy|np)\.array_equal
 
             # pytest raises without context
             |\s\ pytest.raises
 
-            # TODO
-            # pytest.warns (use tm.assert_produces_warning instead)
-            # |pytest\.warns
-
-            # os.remove
-            |os\.remove
-
             # Unseeded numpy default_rng
             |default_rng\(\)
         files: ^pandas/tests/
@@ -292,25 +278,6 @@ repos:
         language: python
         entry: python scripts/validate_unwanted_patterns.py --validation-type="nodefault_used_not_only_for_typing"
         types: [python]
-    -   id: use-pd_array-in-core
-        name: Import pandas.array as pd_array in core
-        language: python
-        entry: python scripts/use_pd_array_in_core.py
-        files: ^pandas/core/
-        exclude: ^pandas/core/api\.py$
-        types: [python]
-    -   id: use-io-common-urlopen
-        name: Use pandas.io.common.urlopen instead of urllib.request.urlopen
-        language: python
-        entry: python scripts/use_io_common_urlopen.py
-        files: ^pandas/
-        exclude: ^pandas/tests/
-        types: [python]
-    -   id: no-bool-in-core-generic
-        name: Use bool_t instead of bool in pandas/core/generic.py
-        entry: python scripts/no_bool_in_generic.py
-        language: python
-        files: ^pandas/core/generic\.py$
     -   id: no-return-exception
         name: Use raise instead of return for exceptions
         language: pygrep

README.md

@@ -1,6 +1,7 @@
-<div align="center">
-  <img src="https://pandas.pydata.org/static/img/pandas.svg"><br>
-</div>
+<picture align="center">
+  <source media="(prefers-color-scheme: dark)" srcset="https://pandas.pydata.org/static/img/pandas_white.svg">
+  <img alt="Pandas Logo" src="https://pandas.pydata.org/static/img/pandas.svg">
+</picture>
 
 -----------------
 

asv_bench/benchmarks/frame_methods.py

@@ -159,12 +159,6 @@ def setup(self):
 
     def time_items(self):
         # (monitor no-copying behaviour)
-        if hasattr(self.df, "_item_cache"):
-            self.df._item_cache.clear()
-        for name, col in self.df.items():
-            pass
-
-    def time_items_cached(self):
         for name, col in self.df.items():
             pass
 

asv_bench/benchmarks/index_object.py

@@ -136,10 +136,14 @@ def setup(self):
             self.int_idxs.append(i_idx)
             o_idx = i_idx.astype(str)
             self.object_idxs.append(o_idx)
+        self.same_range_idx = [self.range_idx] * N
 
     def time_append_range_list(self):
         self.range_idx.append(self.range_idxs)
 
+    def time_append_range_list_same(self):
+        self.range_idx.append(self.same_range_idx)
+
     def time_append_int_list(self):
         self.int_idx.append(self.int_idxs)