Merge branch 'na_infer_String' into string_dtype_tests_groupby

# Conflicts: # doc/source/whatsnew/v2.1.2.rst # pandas/tests/groupby/test_groupby.py
pandas-dev · Oct 23, 2023 · 5c58816 · 5c58816
2 parents d843320 + 479c4ec
commit 5c58816
Show file tree

Hide file tree

Showing 179 changed files with 12,395 additions and 11,318 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -70,19 +70,6 @@ repos:
     -   id: fix-encoding-pragma
         args: [--remove]
     -   id: trailing-whitespace
--   repo: https://github.com/cpplint/cpplint
-    rev: 1.6.1
-    hooks:
-    -   id: cpplint
-        exclude: ^pandas/_libs/include/pandas/vendored/klib
-        args: [
-            --quiet,
-            '--extensions=c,h',
-            '--headers=h',
-            --recursive,
-            --linelength=88,
-            '--filter=-readability/casting,-runtime/int,-build/include_subdir,-readability/fn_size'
-        ]
 -   repo: https://github.com/pylint-dev/pylint
     rev: v3.0.0b0
     hooks:
@@ -127,6 +114,13 @@ repos:
     rev: v0.6.8
     hooks:
     - id: sphinx-lint
+-   repo: https://github.com/pre-commit/mirrors-clang-format
+    rev: ea59a72
+    hooks:
+    - id: clang-format
+      files: ^pandas/_libs/src|^pandas/_libs/include
+      args: [-i]
+      types_or: [c, c++]
 -   repo: local
     hooks:
     -   id: pyright

diff --git a/ci/deps/actions-310.yaml b/ci/deps/actions-310.yaml
@@ -24,39 +24,41 @@ dependencies:
   - pytz
 
   # optional dependencies
-  - beautifulsoup4>=4.11.1
-  - blosc>=1.21.0
-  - bottleneck>=1.3.4
-  - fastparquet>=0.8.1
-  - fsspec>=2022.05.0
+  - beautifulsoup4>=4.11.2
+  - blosc>=1.21.3
+  - bottleneck>=1.3.6
+  - fastparquet>=2022.12.0
+  - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1
-  - gcsfs>=2022.05.0
+  - gcsfs>=2022.11.0
   - jinja2>=3.1.2
-  - lxml>=4.8.0
-  - matplotlib>=3.6.1, <3.8
-  - numba>=0.55.2
-  - numexpr>=2.8.0
+  - lxml>=4.9.2
+  - matplotlib>=3.6.3, <3.8
+  - numba>=0.56.4
+  - numexpr>=2.8.4
   - odfpy>=1.4.1
-  - qtpy>=2.2.0
-  - openpyxl>=3.0.10
-  - pandas-gbq>=0.17.5
-  - psycopg2>=2.9.3
-  - pyarrow>=7.0.0
+  - qtpy>=2.3.0
+  - openpyxl>=3.1.0
+  # Doesn't install well with pyarrow
+  # https://github.com/pandas-dev/pandas/issues/55525
+  # - pandas-gbq>=0.19.0
+  - psycopg2>=2.9.6
+  - pyarrow>=10.0.1
   - pymysql>=1.0.2
-  - pyreadstat>=1.1.5
-  - pytables>=3.7.0
+  - pyreadstat>=1.2.0
+  - pytables>=3.8.0
   - python-calamine>=0.1.6
-  - pyxlsb>=1.0.9
-  - s3fs>=2022.05.0
-  - scipy>=1.8.1
-  - sqlalchemy>=1.4.36
-  - tabulate>=0.8.10
-  - xarray>=2022.03.0
+  - pyxlsb>=1.0.10
+  - s3fs>=2022.11.0
+  - scipy>=1.10.0
+  - sqlalchemy>=2.0.0
+  - tabulate>=0.9.0
+  - xarray>=2022.12.0
   - xlrd>=2.0.1
-  - xlsxwriter>=3.0.3
-  - zstandard>=0.17.0
+  - xlsxwriter>=3.0.5
+  - zstandard>=0.19.0
 
   - pip:
-    - pyqt5>=5.15.6
-    - tzdata>=2022.1
+    - pyqt5>=5.15.8
+    - tzdata>=2022.7
diff --git a/ci/deps/actions-311-downstream_compat.yaml b/ci/deps/actions-311-downstream_compat.yaml
@@ -25,38 +25,40 @@ dependencies:
   - pytz
 
   # optional dependencies
-  - beautifulsoup4>=4.11.1
-  - blosc>=1.21.0
-  - bottleneck>=1.3.4
-  - fastparquet>=0.8.1
-  - fsspec>=2022.05.0
+  - beautifulsoup4>=4.11.2
+  - blosc>=1.21.3
+  - bottleneck>=1.3.6
+  - fastparquet>=2022.12.0
+  - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1
-  - gcsfs>=2022.05.0
+  - gcsfs>=2022.11.0
   - jinja2>=3.1.2
-  - lxml>=4.8.0
-  - matplotlib>=3.6.1, <3.8
-  - numba>=0.55.2
-  - numexpr>=2.8.0
+  - lxml>=4.9.2
+  - matplotlib>=3.6.3, <3.8
+  - numba>=0.56.4
+  - numexpr>=2.8.4
   - odfpy>=1.4.1
-  - qtpy>=2.2.0
-  - openpyxl>=3.0.10
-  - pandas-gbq>=0.17.5
-  - psycopg2>=2.9.3
-  - pyarrow>=7.0.0
+  - qtpy>=2.3.0
+  - openpyxl>=3.1.0
+  # Doesn't install well with pyarrow
+  # https://github.com/pandas-dev/pandas/issues/55525
+  # - pandas-gbq>=0.19.0
+  - psycopg2>=2.9.6
+  - pyarrow>=10.0.1
   - pymysql>=1.0.2
-  - pyreadstat>=1.1.5
-  - pytables>=3.7.0
+  - pyreadstat>=1.2.0
+  - pytables>=3.8.0
   - python-calamine>=0.1.6
-  - pyxlsb>=1.0.9
-  - s3fs>=2022.05.0
-  - scipy>=1.8.1
-  - sqlalchemy>=1.4.36
-  - tabulate>=0.8.10
-  - xarray>=2022.03.0
+  - pyxlsb>=1.0.10
+  - s3fs>=2022.11.0
+  - scipy>=1.10.0
+  - sqlalchemy>=2.0.0
+  - tabulate>=0.9.0
+  - xarray>=2022.12.0
   - xlrd>=2.0.1
-  - xlsxwriter>=3.0.3
-  - zstandard>=0.17.0
+  - xlsxwriter>=3.0.5
+  - zstandard>=0.19.0
 
   # downstream packages
   - botocore
@@ -73,5 +75,5 @@ dependencies:
   - py
   - pip:
     - dataframe-api-compat>=0.1.7
-    - pyqt5>=5.15.6
-    - tzdata>=2022.1
+    - pyqt5>=5.15.8
+    - tzdata>=2022.7
diff --git a/ci/deps/actions-311-numpydev.yaml b/ci/deps/actions-311-numpydev.yaml
@@ -29,4 +29,4 @@ dependencies:
     - "--extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple"
     - "--pre"
     - "numpy"
-    - "tzdata>=2022.1"
+    - "tzdata>=2022.7"
diff --git a/ci/deps/actions-311-pyarrownightly.yaml b/ci/deps/actions-311-pyarrownightly.yaml
@@ -24,7 +24,7 @@ dependencies:
   - pip
 
   - pip:
-    - "tzdata>=2022.1"
+    - "tzdata>=2022.7"
     - "--extra-index-url https://pypi.fury.io/arrow-nightlies/"
     - "--prefer-binary"
     - "--pre"

diff --git a/ci/deps/actions-311.yaml b/ci/deps/actions-311.yaml
@@ -24,39 +24,41 @@ dependencies:
   - pytz
 
   # optional dependencies
-  - beautifulsoup4>=4.11.1
-  - blosc>=1.21.0
-  - bottleneck>=1.3.4
-  - fastparquet>=0.8.1
-  - fsspec>=2022.05.0
+  - beautifulsoup4>=4.11.2
+  - blosc>=1.21.3
+  - bottleneck>=1.3.6
+  - fastparquet>=2022.12.0
+  - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1
-  - gcsfs>=2022.05.0
+  - gcsfs>=2022.11.0
   - jinja2>=3.1.2
-  - lxml>=4.8.0
-  - matplotlib>=3.6.1, <3.8
-  - numba>=0.55.2
-  - numexpr>=2.8.0
+  - lxml>=4.9.2
+  - matplotlib>=3.6.3, <3.8
+  - numba>=0.56.4
+  - numexpr>=2.8.4
   - odfpy>=1.4.1
-  - qtpy>=2.2.0
-  - openpyxl>=3.0.10
-  - pandas-gbq>=0.17.5
-  - psycopg2>=2.9.3
-  - pyarrow>=7.0.0
+  - qtpy>=2.3.0
+  - openpyxl>=3.1.0
+  # Doesn't install well with pyarrow
+  # https://github.com/pandas-dev/pandas/issues/55525
+  # - pandas-gbq>=0.19.0
+  - psycopg2>=2.9.6
+  - pyarrow>=10.0.1
   - pymysql>=1.0.2
-  - pyreadstat>=1.1.5
-  # - pytables>=3.7.0, 3.8.0 is first version that supports 3.11
+  - pyreadstat>=1.2.0
+  - pytables>=3.8.0
   - python-calamine>=0.1.6
-  - pyxlsb>=1.0.9
-  - s3fs>=2022.05.0
-  - scipy>=1.8.1
-  - sqlalchemy>=1.4.36
-  - tabulate>=0.8.10
-  - xarray>=2022.03.0
+  - pyxlsb>=1.0.10
+  - s3fs>=2022.11.0
+  - scipy>=1.10.0
+  - sqlalchemy>=2.0.0
+  - tabulate>=0.9.0
+  - xarray>=2022.12.0
   - xlrd>=2.0.1
-  - xlsxwriter>=3.0.3
-  - zstandard>=0.17.0
+  - xlsxwriter>=3.0.5
+  - zstandard>=0.19.0
 
   - pip:
-    - pyqt5>=5.15.6
-    - tzdata>=2022.1
+    - pyqt5>=5.15.8
+    - tzdata>=2022.7
diff --git a/ci/deps/actions-39-minimum_versions.yaml b/ci/deps/actions-39-minimum_versions.yaml
@@ -26,40 +26,40 @@ dependencies:
   - pytz=2020.1
 
   # optional dependencies
-  - beautifulsoup4=4.11.1
-  - blosc=1.21.0
-  - bottleneck=1.3.4
-  - fastparquet=0.8.1
-  - fsspec=2022.05.0
+  - beautifulsoup4=4.11.2
+  - blosc=1.21.3
+  - bottleneck=1.3.6
+  - fastparquet=2022.12.0
+  - fsspec=2022.11.0
   - html5lib=1.1
   - hypothesis=6.46.1
-  - gcsfs=2022.05.0
+  - gcsfs=2022.11.0
   - jinja2=3.1.2
-  - lxml=4.8.0
-  - matplotlib=3.6.1
-  - numba=0.55.2
-  - numexpr=2.8.0
+  - lxml=4.9.2
+  - matplotlib=3.6.3
+  - numba=0.56.4
+  - numexpr=2.8.4
   - odfpy=1.4.1
-  - qtpy=2.2.0
-  - openpyxl=3.0.10
-  - pandas-gbq=0.17.5
-  - psycopg2=2.9.3
-  - pyarrow=7.0.0
+  - qtpy=2.3.0
+  - openpyxl=3.1.0
+  #- pandas-gbq=0.19.0
+  - psycopg2=2.9.6
+  - pyarrow=10.0.1
   - pymysql=1.0.2
-  - pyreadstat=1.1.5
-  - pytables=3.7.0
+  - pyreadstat=1.2.0
+  - pytables=3.8.0
   - python-calamine=0.1.6
-  - pyxlsb=1.0.9
-  - s3fs=2022.05.0
-  - scipy=1.8.1
-  - sqlalchemy=1.4.36
-  - tabulate=0.8.10
-  - xarray=2022.03.0
+  - pyxlsb=1.0.10
+  - s3fs=2022.11.0
+  - scipy=1.10.0
+  - sqlalchemy=2.0.0
+  - tabulate=0.9.0
+  - xarray=2022.12.0
   - xlrd=2.0.1
-  - xlsxwriter=3.0.3
-  - zstandard=0.17.0
+  - xlsxwriter=3.0.5
+  - zstandard=0.19.0
 
   - pip:
     - dataframe-api-compat==0.1.7
-    - pyqt5==5.15.6
-    - tzdata==2022.1
+    - pyqt5==5.15.8
+    - tzdata==2022.7
diff --git a/ci/deps/actions-39.yaml b/ci/deps/actions-39.yaml
@@ -24,39 +24,41 @@ dependencies:
   - pytz
 
   # optional dependencies
-  - beautifulsoup4>=4.11.1
-  - blosc>=1.21.0
-  - bottleneck>=1.3.4
-  - fastparquet>=0.8.1
-  - fsspec>=2022.05.0
+  - beautifulsoup4>=4.11.2
+  - blosc>=1.21.3
+  - bottleneck>=1.3.6
+  - fastparquet>=2022.12.0
+  - fsspec>=2022.11.0
   - html5lib>=1.1
   - hypothesis>=6.46.1
-  - gcsfs>=2022.05.0
+  - gcsfs>=2022.11.0
   - jinja2>=3.1.2
-  - lxml>=4.8.0
-  - matplotlib>=3.6.1, <3.8
-  - numba>=0.55.2
-  - numexpr>=2.8.0
+  - lxml>=4.9.2
+  - matplotlib>=3.6.3, <3.8
+  - numba>=0.56.4
+  - numexpr>=2.8.4
   - odfpy>=1.4.1
-  - qtpy>=2.2.0
-  - openpyxl>=3.0.10
-  - pandas-gbq>=0.17.5
-  - psycopg2>=2.9.3
-  - pyarrow>=7.0.0
+  - qtpy>=2.3.0
+  - openpyxl>=3.1.0
+  # Doesn't install well with pyarrow
+  # https://github.com/pandas-dev/pandas/issues/55525
+  # - pandas-gbq>=0.19.0
+  - psycopg2>=2.9.6
+  - pyarrow>=10.0.1
   - pymysql>=1.0.2
-  - pyreadstat>=1.1.5
-  - pytables>=3.7.0
+  - pyreadstat>=1.2.0
+  - pytables>=3.8.0
   - python-calamine>=0.1.6
-  - pyxlsb>=1.0.9
-  - s3fs>=2022.05.0
-  - scipy>=1.8.1
-  - sqlalchemy>=1.4.36
-  - tabulate>=0.8.10
-  - xarray>=2022.03.0
+  - pyxlsb>=1.0.10
+  - s3fs>=2022.11.0
+  - scipy>=1.10.0
+  - sqlalchemy>=2.0.0
+  - tabulate>=0.9.0
+  - xarray>=2022.12.0
   - xlrd>=2.0.1
-  - xlsxwriter>=3.0.3
-  - zstandard>=0.17.0
+  - xlsxwriter>=3.0.5
+  - zstandard>=0.19.0
 
   - pip:
-    - pyqt5>=5.15.6
-    - tzdata>=2022.1
+    - pyqt5>=5.15.8
+    - tzdata>=2022.7