Merge branch 'main' into include-pyproject

Author: lithomas1

.github/actions/setup-conda/action.yml

@@ -18,7 +18,7 @@ runs:
     - name: Set Arrow version in ${{ inputs.environment-file }} to ${{ inputs.pyarrow-version }}
       run: |
         grep -q '  - pyarrow' ${{ inputs.environment-file }}
-        sed -i"" -e "s/  - pyarrow<10/  - pyarrow=${{ inputs.pyarrow-version }}/" ${{ inputs.environment-file }}
+        sed -i"" -e "s/  - pyarrow/  - pyarrow=${{ inputs.pyarrow-version }}/" ${{ inputs.environment-file }}
         cat ${{ inputs.environment-file }}
       shell: bash
       if: ${{ inputs.pyarrow-version }}

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

@@ -15,6 +15,7 @@ on:
 env:
   ENV_FILE: environment.yml
   PANDAS_CI: 1
+  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
 permissions:
   contents: read
@@ -45,6 +46,12 @@ jobs:
     - name: Build Pandas
       uses: ./.github/actions/build_pandas
 
+    - name: Set up maintainers cache
+      uses: actions/cache@v3
+      with:
+        path: maintainers.json
+        key: maintainers
+
     - name: Build website
       run: python web/pandas_web.py web/pandas --target-path=web/build
 

.github/workflows/macos-windows.yml

@@ -16,6 +16,7 @@ env:
   PANDAS_CI: 1
   PYTEST_TARGET: pandas
   PATTERN: "not slow and not db and not network and not single_cpu"
+  ERROR_ON_WARNINGS: "1"
 
 
 permissions:
@@ -52,7 +53,7 @@ jobs:
       uses: ./.github/actions/setup-conda
       with:
         environment-file: ci/deps/${{ matrix.env_file }}
-        pyarrow-version: ${{ matrix.os == 'macos-latest' && '6' || '' }}
+        pyarrow-version: ${{ matrix.os == 'macos-latest' && '9' || '' }}
 
     - name: Build Pandas
       uses: ./.github/actions/build_pandas

.github/workflows/ubuntu.yml

@@ -29,7 +29,7 @@ jobs:
       matrix:
         env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml]
         pattern: ["not single_cpu", "single_cpu"]
-        pyarrow_version: ["7", "8", "9"]
+        pyarrow_version: ["7", "8", "9", "10"]
         include:
           - name: "Downstream Compat"
             env_file: actions-38-downstream_compat.yaml
@@ -38,6 +38,7 @@ jobs:
           - name: "Minimum Versions"
             env_file: actions-38-minimum_versions.yaml
             pattern: "not slow and not network and not single_cpu"
+            error_on_warnings: "0"
           - name: "Locale: it_IT"
             env_file: actions-38.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -62,33 +63,42 @@ jobs:
             env_file: actions-310.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_copy_on_write: "1"
+            error_on_warnings: "0"
           - name: "Data Manager"
             env_file: actions-38.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_data_manager: "array"
+            error_on_warnings: "0"
           - name: "Pypy"
             env_file: actions-pypy-38.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "--max-worker-restart 0"
+            error_on_warnings: "0"
           - name: "Numpy Dev"
             env_file: actions-310-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "-W error::DeprecationWarning:numpy -W error::FutureWarning:numpy"
+            error_on_warnings: "0"
         exclude:
-          - env_file: actions-39.yaml
-            pyarrow_version: "6"
-          - env_file: actions-39.yaml
+          - env_file: actions-38.yaml
             pyarrow_version: "7"
-          - env_file: actions-310.yaml
-            pyarrow_version: "6"
-          - env_file: actions-310.yaml
+          - env_file: actions-38.yaml
+            pyarrow_version: "8"
+          - env_file: actions-38.yaml
+            pyarrow_version: "9"
+          - env_file: actions-39.yaml
             pyarrow_version: "7"
+          - env_file: actions-39.yaml
+            pyarrow_version: "8"
+          - env_file: actions-39.yaml
+            pyarrow_version: "9"
       fail-fast: false
     name: ${{ matrix.name || format('{0} pyarrow={1} {2}', matrix.env_file, matrix.pyarrow_version, matrix.pattern) }}
     env:
       ENV_FILE: ci/deps/${{ matrix.env_file }}
       PATTERN: ${{ matrix.pattern }}
       EXTRA_APT: ${{ matrix.extra_apt || '' }}
+      ERROR_ON_WARNINGS: ${{ matrix.error_on_warnings || '1' }}
       LANG: ${{ matrix.lang || '' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
       PANDAS_DATA_MANAGER: ${{ matrix.pandas_data_manager || 'block' }}

.pre-commit-config.yaml

@@ -333,3 +333,12 @@ repos:
         additional_dependencies:
         - autotyping==22.9.0
         - libcst==0.4.7
+    -   id: check-test-naming
+        name: check that test names start with 'test'
+        entry: python -m scripts.check_test_naming
+        types: [python]
+        files: ^pandas/tests
+        language: python
+        exclude: |
+            (?x)
+            ^pandas/tests/generic/test_generic.py  # GH50380

ci/deps/actions-310.yaml

@@ -42,7 +42,7 @@ dependencies:
   - psycopg2
   - pymysql
   - pytables
-  - pyarrow<10
+  - pyarrow
   - pyreadstat
   - python-snappy
   - pyxlsb

ci/deps/actions-38-downstream_compat.yaml

@@ -40,7 +40,7 @@ dependencies:
   - openpyxl
   - odfpy
   - psycopg2
-  - pyarrow<10
+  - pyarrow
   - pymysql
   - pyreadstat
   - pytables

ci/deps/actions-38.yaml

@@ -40,7 +40,7 @@ dependencies:
   - odfpy
   - pandas-gbq
   - psycopg2
-  - pyarrow<10
+  - pyarrow
   - pymysql
   - pyreadstat
   - pytables

ci/deps/actions-39.yaml

@@ -41,7 +41,7 @@ dependencies:
   - pandas-gbq
   - psycopg2
   - pymysql
-  - pyarrow<10
+  - pyarrow
   - pyreadstat
   - pytables
   - python-snappy

ci/deps/circle-38-arm64.yaml

@@ -40,7 +40,7 @@ dependencies:
   - odfpy
   - pandas-gbq
   - psycopg2
-  - pyarrow<10
+  - pyarrow
   - pymysql
   # Not provided on ARM
   #- pyreadstat

ci/run_tests.sh

@@ -30,6 +30,13 @@ if [[ "$PATTERN" ]]; then
   PYTEST_CMD="$PYTEST_CMD -m \"$PATTERN\""
 fi
 
+if [[ "$ERROR_ON_WARNINGS" == "1" ]]; then
+  for pth in $(find pandas -name '*.py' -not -path "pandas/tests/*" | sed -e 's/\.py//g' -e 's/\/__init__//g' -e 's/\//./g');
+    do
+        PYTEST_CMD="$PYTEST_CMD -W error:::$pth"
+    done
+fi
+
 echo $PYTEST_CMD
 sh -c "$PYTEST_CMD"
 

doc/source/reference/indexing.rst

@@ -298,6 +298,7 @@ MultiIndex components
    MultiIndex.swaplevel
    MultiIndex.reorder_levels
    MultiIndex.remove_unused_levels
+   MultiIndex.drop
 
 MultiIndex selecting
 ~~~~~~~~~~~~~~~~~~~~

doc/source/user_guide/io.rst

@@ -275,6 +275,9 @@ parse_dates : boolean or list of ints or names or list of lists or dict, default
 infer_datetime_format : boolean, default ``False``
   If ``True`` and parse_dates is enabled for a column, attempt to infer the
   datetime format to speed up the processing.
+
+  .. deprecated:: 2.0.0
+   A strict version of this argument is now the default, passing it has no effect.
 keep_date_col : boolean, default ``False``
   If ``True`` and parse_dates specifies combining multiple columns then keep the
   original columns.
@@ -916,12 +919,10 @@ an exception is raised, the next one is tried:
 
 Note that performance-wise, you should try these methods of parsing dates in order:
 
-1. Try to infer the format using ``infer_datetime_format=True`` (see section below).
-
-2. If you know the format, use ``pd.to_datetime()``:
+1. If you know the format, use ``pd.to_datetime()``:
    ``date_parser=lambda x: pd.to_datetime(x, format=...)``.
 
-3. If you have a really non-standard format, use a custom ``date_parser`` function.
+2. If you have a really non-standard format, use a custom ``date_parser`` function.
    For optimal performance, this should be vectorized, i.e., it should accept arrays
    as arguments.
 
@@ -1148,7 +1149,7 @@ To completely override the default values that are recognized as missing, specif
 .. _io.navaluesconst:
 
 The default ``NaN`` recognized values are ``['-1.#IND', '1.#QNAN', '1.#IND', '-1.#QNAN', '#N/A N/A', '#N/A', 'N/A',
-'n/a', 'NA', '<NA>', '#NA', 'NULL', 'null', 'NaN', '-NaN', 'nan', '-nan', '']``.
+'n/a', 'NA', '<NA>', '#NA', 'NULL', 'null', 'NaN', '-NaN', 'nan', '-nan', 'None', '']``.
 
 Let us consider some examples:
 
@@ -3832,7 +3833,7 @@ OpenDocument Spreadsheets
 The io methods for `Excel files`_ also support reading and writing OpenDocument spreadsheets
 using the `odfpy <https://pypi.org/project/odfpy/>`__ module. The semantics and features for reading and writing
 OpenDocument spreadsheets match what can be done for `Excel files`_ using
-``engine='odf'``.
+``engine='odf'``. The optional dependency 'odfpy' needs to be installed.
 
 The :func:`~pandas.read_excel` method can read OpenDocument spreadsheets