merge

Author: jgarba

.github/workflows/32-bit-linux.yml

@@ -39,7 +39,7 @@ jobs:
           . ~/virtualenvs/pandas-dev/bin/activate && \
           python -m pip install --no-deps -U pip wheel 'setuptools<60.0.0' && \
           python -m pip install versioneer[toml] && \
-          python -m pip install cython numpy python-dateutil pytz pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17 hypothesis>=6.34.2 && \
+          python -m pip install cython numpy python-dateutil pytz pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17 hypothesis>=6.46.1 && \
           python setup.py build_ext -q -j$(nproc) && \
           python -m pip install --no-build-isolation --no-use-pep517 -e . && \
           python -m pip list && \

.github/workflows/assign.yml

@@ -1,19 +1,25 @@
-name: Preview docs
+name: Comment Commands
 on:
   issue_comment:
     types: created
 
 permissions:
   contents: read
+  issues: write
+  pull-requests: write
 
 jobs:
+  issue_assign:
+    runs-on: ubuntu-22.04
+    steps:
+    - if: (!github.event.issue.pull_request) && github.event.comment.body == 'take'
+      run: |
+        echo "Assigning issue ${{ github.event.issue.number }} to ${{ github.event.comment.user.login }}"
+        curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"assignees": ["${{ github.event.comment.user.login }}"]}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/assignees
   preview_docs:
-    permissions:
-      issues: write
-      pull-requests: write
     runs-on: ubuntu-22.04
     steps:
-    - if: github.event.comment.body == '/preview'
+    - if: github.event.issue.pull_request && github.event.comment.body == '/preview'
       run: |
         if curl --output /dev/null --silent --head --fail "https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"; then
           curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"body": "Website preview of this PR available at: https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/comments

.github/workflows/preview-docs.yml renamed to .github/workflows/comment-commands.yml

@@ -79,7 +79,7 @@ jobs:
         python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scipy-wheels-nightly/simple numpy
         python -m pip install git+https://github.com/nedbat/coveragepy.git
         python -m pip install versioneer[toml]
-        python -m pip install python-dateutil pytz cython hypothesis>=6.34.2 pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-cov pytest-asyncio>=0.17
+        python -m pip install python-dateutil pytz cython hypothesis>=6.46.1 pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-cov pytest-asyncio>=0.17
         python -m pip list
 
     - name: Build Pandas

.github/workflows/python-dev.yml

@@ -170,7 +170,7 @@ jobs:
           # (1. Generate sdist 2. Build wheels from sdist)
           # This tests the sdists, and saves some build time
           python -m pip install dist/*.gz
-          pip install hypothesis>=6.34.2 pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17
+          pip install hypothesis>=6.46.1 pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17
           cd .. # Not a good idea to test within the src tree
           python -c "import pandas; print(pandas.__version__);
           pandas.test(extra_args=['-m not clipboard and not single_cpu and not slow and not network and not db', '-n 2']);

.github/workflows/wheels.yml

@@ -90,14 +90,18 @@ Package Index (PyPI)](https://pypi.org/project/pandas) and on [Conda](https://do
 
 ```sh
 # conda
-conda install pandas
+conda install -c conda-forge pandas
 ```
 
 ```sh
 # or PyPI
 pip install pandas
 ```
 
+The list of changes to pandas between each release can be found
+[here](https://pandas.pydata.org/pandas-docs/stable/whatsnew/index.html). For full
+details, see the commit logs at https://github.com/pandas-dev/pandas.
+
 ## Dependencies
 - [NumPy - Adds support for large, multi-dimensional arrays, matrices and high-level mathematical functions to operate on these arrays](https://www.numpy.org)
 - [python-dateutil - Provides powerful extensions to the standard datetime module](https://dateutil.readthedocs.io/en/stable/index.html)

README.md

@@ -555,4 +555,19 @@ def time_read_csv_index_col(self):
         read_csv(self.StringIO_input, index_col="a")
 
 
+class ReadCSVDatePyarrowEngine(StringIORewind):
+    def setup(self):
+        count_elem = 100_000
+        data = "a\n" + "2019-12-31\n" * count_elem
+        self.StringIO_input = StringIO(data)
+
+    def time_read_csv_index_col(self):
+        read_csv(
+            self.StringIO_input,
+            parse_dates=["a"],
+            engine="pyarrow",
+            dtype_backend="pyarrow",
+        )
+
+
 from ..pandas_vb_common import setup  # noqa: F401 isort:skip

RELEASE.md

@@ -73,7 +73,14 @@ def time_f_ordered(self, axis, ignore_index):
 
 class ConcatIndexDtype:
     params = (
-        ["datetime64[ns]", "int64", "Int64", "string[python]", "string[pyarrow]"],
+        [
+            "datetime64[ns]",
+            "int64",
+            "Int64",
+            "int64[pyarrow]",
+            "string[python]",
+            "string[pyarrow]",
+        ],
         ["monotonic", "non_monotonic", "has_na"],
         [0, 1],
         [True, False],
@@ -84,7 +91,7 @@ def setup(self, dtype, structure, axis, sort):
         N = 10_000
         if dtype == "datetime64[ns]":
             vals = date_range("1970-01-01", periods=N)
-        elif dtype in ("int64", "Int64"):
+        elif dtype in ("int64", "Int64", "int64[pyarrow]"):
             vals = np.arange(N, dtype=np.int64)
         elif dtype in ("string[python]", "string[pyarrow]"):
             vals = tm.makeStringIndex(N)

asv_bench/benchmarks/io/csv.py

@@ -11,7 +11,7 @@ dependencies:
   - pytest>=7.0.0
   - pytest-cov
   - pytest-xdist>=2.2.0
-  - hypothesis>=6.34.2
+  - hypothesis>=6.46.1
   - pytest-asyncio>=0.17.0
 
   # pandas dependencies

asv_bench/benchmarks/join_merge.py

@@ -21,38 +21,40 @@ dependencies:
   - pytz
 
   # optional dependencies
-  - beautifulsoup4>=4.9.3
-  - blosc
-  - bottleneck>=1.3.2
+  - beautifulsoup4>=4.11.1
+  - blosc>=1.21.0
+  - bottleneck>=1.3.4
   - brotlipy>=0.7.0
-  - fastparquet>=0.6.3
-  - fsspec>=2021.07.0
+  - fastparquet>=0.8.1
+  - fsspec>=2022.05.0
   - html5lib>=1.1
-  - hypothesis>=6.34.2
-  - gcsfs>=2021.07.0
-  - jinja2>=3.0.0
-  - lxml>=4.6.3
+  - hypothesis>=6.46.1
+  - gcsfs>=2022.05.0
+  - jinja2>=3.1.2
+  - lxml>=4.8.0
   - matplotlib>=3.6.1, <3.7.0
-  - numba>=0.53.1
-  - numexpr>=2.7.3
-  - openpyxl<3.1.1, >=3.0.7
+  - numba>=0.55.2
+  - numexpr>=2.8.0
   - odfpy>=1.4.1
-  - pandas-gbq>=0.15.0
-  - psycopg2>=2.8.6
-  - pymysql>=1.0.2
-  - pytables>=3.6.1
+  - qtpy>=2.2.0
+  - openpyxl<3.1.1, >=3.0.10
+  - pandas-gbq>=0.17.5
+  - psycopg2>=2.9.3
   - pyarrow>=7.0.0
-  - pyreadstat>=1.1.2
-  - python-snappy>=0.6.0
-  - pyxlsb>=1.0.8
-  - s3fs>=2021.08.0
-  - scipy>=1.7.1
-  - sqlalchemy>=1.4.16
-  - tabulate>=0.8.9
-  - xarray>=0.21.0
+  - pymysql>=1.0.2
+  - pyreadstat>=1.1.5
+  - pytables>=3.7.0
+  - python-snappy>=0.6.1
+  - pyxlsb>=1.0.9
+  - s3fs>=2022.05.0
+  - scipy>=1.8.1
+  - sqlalchemy>=1.4.36
+  - tabulate>=0.8.10
+  - xarray>=2022.03.0
   - xlrd>=2.0.1
-  - xlsxwriter>=1.4.3
-  - zstandard>=0.15.2
+  - xlsxwriter>=3.0.3
+  - zstandard>=0.17.0
 
   - pip:
+    - pyqt5>=5.15.6
     - tzdata>=2022.1

ci/deps/actions-310-numpydev.yaml

@@ -12,7 +12,7 @@ dependencies:
   - pytest>=7.0.0
   - pytest-cov
   - pytest-xdist>=2.2.0
-  - hypothesis>=6.34.2
+  - hypothesis>=6.46.1
   - pytest-asyncio>=0.17.0
 
   # required dependencies

ci/deps/actions-310.yaml

@@ -21,38 +21,40 @@ dependencies:
   - pytz
 
   # optional dependencies
-  - beautifulsoup4>=4.9.3
-  - blosc
-  - bottleneck>=1.3.2
+  - beautifulsoup4>=4.11.1
+  - blosc>=1.21.0
+  - bottleneck>=1.3.4
   - brotlipy>=0.7.0
-  - fastparquet>=0.6.3
-  - fsspec>=2021.07.0
+  - fastparquet>=0.8.1
+  - fsspec>=2022.05.0
   - html5lib>=1.1
-  - hypothesis>=6.34.2
-  - gcsfs>=2021.07.0
-  - jinja2>=3.0.0
-  - lxml>=4.6.3
+  - hypothesis>=6.46.1
+  - gcsfs>=2022.05.0
+  - jinja2>=3.1.2
+  - lxml>=4.8.0
   - matplotlib>=3.6.1, <3.7.0
-  # - numba  not compatible with 3.11
-  - numexpr>=2.7.3
-  - openpyxl<3.1.1, >=3.0.7
+  # - numba>=0.55.2 not compatible with 3.11
+  - numexpr>=2.8.0
   - odfpy>=1.4.1
-  - pandas-gbq>=0.15.0
-  - psycopg2>=2.8.6
-  - pymysql>=1.0.2
-  # - pytables>=3.8.0  # first version that supports 3.11
+  - qtpy>=2.2.0
+  - openpyxl<3.1.1, >=3.0.10
+  - pandas-gbq>=0.17.5
+  - psycopg2>=2.9.3
   - pyarrow>=7.0.0
-  - pyreadstat>=1.1.2
-  - python-snappy>=0.6.0
-  - pyxlsb>=1.0.8
-  - s3fs>=2021.08.0
-  - scipy>=1.7.1
-  - sqlalchemy>=1.4.16
-  - tabulate>=0.8.9
-  - xarray>=0.21.0
+  - pymysql>=1.0.2
+  - pyreadstat>=1.1.5
+  # - pytables>=3.7.0, 3.8.0 is first version that supports 3.11
+  - python-snappy>=0.6.1
+  - pyxlsb>=1.0.9
+  - s3fs>=2022.05.0
+  - scipy>=1.8.1
+  - sqlalchemy>=1.4.36
+  - tabulate>=0.8.10
+  - xarray>=2022.03.0
   - xlrd>=2.0.1
-  - xlsxwriter>=1.4.3
-  - zstandard>=0.15.2
+  - xlsxwriter>=3.0.3
+  - zstandard>=0.17.0
 
   - pip:
+    - pyqt5>=5.15.6
     - tzdata>=2022.1

ci/deps/actions-311-pyarrownightly.yaml

@@ -22,37 +22,39 @@ dependencies:
   - pytz
 
   # optional dependencies
-  - beautifulsoup4>=4.9.3
-  - blosc
+  - beautifulsoup4>=4.11.1
+  - blosc>=1.21.0
+  - bottleneck>=1.3.4
   - brotlipy>=0.7.0
-  - bottleneck>=1.3.2
-  - fastparquet>=0.6.3
-  - fsspec>=2021.07.0
+  - fastparquet>=0.8.1
+  - fsspec>=2022.05.0
   - html5lib>=1.1
-  - hypothesis>=6.34.2
-  - gcsfs>=2021.07.0
-  - jinja2>=3.0.0
-  - lxml>=4.6.3
+  - hypothesis>=6.46.1
+  - gcsfs>=2022.05.0
+  - jinja2>=3.1.2
+  - lxml>=4.8.0
   - matplotlib>=3.6.1, <3.7.0
-  - numba>=0.53.1
-  - numexpr>=2.7.3
-  - openpyxl<3.1.1, >=3.0.7
+  - numba>=0.55.2
+  - numexpr>=2.8.0
   - odfpy>=1.4.1
-  - psycopg2>=2.8.6
+  - qtpy>=2.2.0
+  - openpyxl<3.1.1, >=3.0.10
+  - pandas-gbq>=0.17.5
+  - psycopg2>=2.9.3
   - pyarrow>=7.0.0
   - pymysql>=1.0.2
-  - pyreadstat>=1.1.2
-  - pytables>=3.6.1
-  - python-snappy>=0.6.0
-  - pyxlsb>=1.0.8
-  - s3fs>=2021.08.0
-  - scipy>=1.7.1
-  - sqlalchemy>=1.4.16
-  - tabulate>=0.8.9
-  - xarray>=0.21.0
+  - pyreadstat>=1.1.5
+  - pytables>=3.7.0
+  - python-snappy>=0.6.1
+  - pyxlsb>=1.0.9
+  - s3fs>=2022.05.0
+  - scipy>=1.8.1
+  - sqlalchemy>=1.4.36
+  - tabulate>=0.8.10
+  - xarray>=2022.03.0
   - xlrd>=2.0.1
-  - xlsxwriter>=1.4.3
-  - zstandard>=0.15.2
+  - xlsxwriter>=3.0.3
+  - zstandard>=0.17.0
 
   # downstream packages
   - botocore
@@ -65,9 +67,9 @@ dependencies:
   - statsmodels
   - coverage
   - pandas-datareader
-  - pandas-gbq>=0.15.0
   - pyyaml
   - py
 
   - pip:
+    - pyqt5>=5.15.6
     - tzdata>=2022.1