Merge remote-tracking branch 'upstream/main' into resample-long

Author: MarcoGorelli

.github/workflows/ubuntu.yml

@@ -29,7 +29,7 @@ jobs:
       matrix:
         env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml, actions-311.yaml]
         pattern: ["not single_cpu", "single_cpu"]
-        pyarrow_version: ["7", "8", "9", "10"]
+        pyarrow_version: ["8", "9", "10"]
         include:
           - name: "Downstream Compat"
             env_file: actions-38-downstream_compat.yaml
@@ -79,23 +79,17 @@ jobs:
             test_args: "-W error::DeprecationWarning -W error::FutureWarning"
             error_on_warnings: "0"
         exclude:
-          - env_file: actions-38.yaml
-            pyarrow_version: "7"
           - 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"
-          - env_file: actions-311.yaml
-            pyarrow_version: "7"
-          - env_file: actions-311.yaml
+          - env_file: actions-310.yaml
             pyarrow_version: "8"
-          - env_file: actions-311.yaml
+          - env_file: actions-310.yaml
             pyarrow_version: "9"
       fail-fast: false
     name: ${{ matrix.name || format('{0} pyarrow={1} {2}', matrix.env_file, matrix.pyarrow_version, matrix.pattern) }}

ci/code_checks.sh

@@ -266,6 +266,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.api.types.is_integer \
         pandas.api.types.pandas_dtype \
         pandas.read_clipboard \
+        pandas.ExcelFile \
         pandas.ExcelFile.parse \
         pandas.DataFrame.to_html \
         pandas.io.formats.style.Styler.to_html \
@@ -578,9 +579,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
     MSG='Partially validate docstrings (EX02)' ;  echo $MSG
     $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX02 --ignore_functions \
         pandas.DataFrame.plot.line \
-        pandas.Index.factorize \
         pandas.Period.strftime \
-        pandas.Series.factorize \
         pandas.Series.floordiv \
         pandas.Series.plot.line \
         pandas.Series.rfloordiv \
@@ -608,7 +607,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.api.types.is_unsigned_integer_dtype \
         pandas.core.groupby.DataFrameGroupBy.take \
         pandas.core.groupby.SeriesGroupBy.take \
-        pandas.factorize \
         pandas.io.formats.style.Styler.concat \
         pandas.io.formats.style.Styler.export \
         pandas.io.formats.style.Styler.set_td_classes \

ci/deps/actions-310.yaml

@@ -48,7 +48,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy<1.4.46
+  - sqlalchemy
   - tabulate
   - tzdata>=2022a
   - xarray

ci/deps/actions-311.yaml

@@ -18,7 +18,7 @@ dependencies:
 
   # required dependencies
   - python-dateutil
-  - numpy<1.24.0
+  - numpy
   - pytz
 
   # optional dependencies
@@ -48,7 +48,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy<1.4.46
+  - sqlalchemy
   - tabulate
   - tzdata>=2022a
   - xarray

ci/deps/actions-38-downstream_compat.yaml

@@ -48,7 +48,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy<1.4.46
+  - sqlalchemy
   - tabulate
   - xarray
   - xlrd

ci/deps/actions-38.yaml

@@ -48,7 +48,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy<1.4.46
+  - sqlalchemy
   - tabulate
   - xarray
   - xlrd

ci/deps/actions-39.yaml

@@ -48,7 +48,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy<1.4.46
+  - sqlalchemy
   - tabulate
   - tzdata>=2022a
   - xarray

ci/deps/circle-38-arm64.yaml

@@ -49,7 +49,7 @@ dependencies:
   - pyxlsb
   - s3fs>=2021.08.0
   - scipy
-  - sqlalchemy<1.4.46
+  - sqlalchemy
   - tabulate
   - xarray
   - xlrd

doc/source/reference/indexing.rst

@@ -299,6 +299,9 @@ MultiIndex components
    MultiIndex.reorder_levels
    MultiIndex.remove_unused_levels
    MultiIndex.drop
+   MultiIndex.copy
+   MultiIndex.append
+   MultiIndex.truncate
 
 MultiIndex selecting
 ~~~~~~~~~~~~~~~~~~~~

doc/source/reference/io.rst

@@ -40,6 +40,9 @@ Excel
 
    read_excel
    DataFrame.to_excel
+   ExcelFile
+   ExcelFile.book
+   ExcelFile.sheet_names
    ExcelFile.parse
 
 .. currentmodule:: pandas.io.formats.style

doc/source/user_guide/io.rst

@@ -5868,15 +5868,15 @@ If you have an SQLAlchemy description of your database you can express where con
        sa.Column("Col_3", sa.Boolean),
    )
 
-   pd.read_sql(sa.select([data_table]).where(data_table.c.Col_3 is True), engine)
+   pd.read_sql(sa.select(data_table).where(data_table.c.Col_3 is True), engine)
 
 You can combine SQLAlchemy expressions with parameters passed to :func:`read_sql` using :func:`sqlalchemy.bindparam`
 
 .. ipython:: python
 
     import datetime as dt
 
-    expr = sa.select([data_table]).where(data_table.c.Date > sa.bindparam("date"))
+    expr = sa.select(data_table).where(data_table.c.Date > sa.bindparam("date"))
     pd.read_sql(expr, engine, params={"date": dt.datetime(2010, 10, 18)})