Merge remote-tracking branch 'upstream/main' into factorize-preserve-dtype

Author: jorisvandenbossche

.github/workflows/unit-tests.yml

@@ -86,7 +86,6 @@ jobs:
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}
-      NPY_PROMOTION_STATE: ${{ matrix.env_file == 'actions-311-numpydev.yaml' && 'weak' || 'legacy' }}
       # Clipboard tests
       QT_QPA_PLATFORM: offscreen
       REMOVE_PYARROW: ${{ matrix.name == 'Future infer strings (without pyarrow)' && '1' || '0' }}

.github/workflows/wheels.yml

@@ -156,7 +156,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.21.0
+        uses: pypa/cibuildwheel@v2.21.3
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

ci/code_checks.sh

@@ -85,8 +85,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.year GL08" \
-        -i "pandas.api.types.is_integer PR01,SA01" \
-        -i "pandas.api.types.is_iterator PR07,SA01" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
@@ -123,11 +121,9 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.resample.Resampler.quantile PR01,PR07" \
         -i "pandas.core.resample.Resampler.sem SA01" \
         -i "pandas.core.resample.Resampler.std SA01" \
-        -i "pandas.core.resample.Resampler.sum SA01" \
         -i "pandas.core.resample.Resampler.transform PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.var SA01" \
         -i "pandas.errors.AttributeConflictWarning SA01" \
-        -i "pandas.errors.CSSWarning SA01" \
         -i "pandas.errors.ChainedAssignmentError SA01" \
         -i "pandas.errors.DataError SA01" \
         -i "pandas.errors.DuplicateLabelError SA01" \
@@ -136,21 +132,17 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.errors.NullFrequencyError SA01" \
         -i "pandas.errors.NumExprClobberingError SA01" \
         -i "pandas.errors.NumbaUtilError SA01" \
-        -i "pandas.errors.OptionError SA01" \
         -i "pandas.errors.OutOfBoundsTimedelta SA01" \
         -i "pandas.errors.PerformanceWarning SA01" \
         -i "pandas.errors.PossibleDataLossError SA01" \
         -i "pandas.errors.UndefinedVariableError PR01,SA01" \
         -i "pandas.errors.UnsortedIndexError SA01" \
-        -i "pandas.errors.UnsupportedFunctionCall SA01" \
         -i "pandas.errors.ValueLabelTypeMismatch SA01" \
         -i "pandas.infer_freq SA01" \
         -i "pandas.io.json.build_table_schema PR07,RT03,SA01" \
         -i "pandas.io.stata.StataWriter.write_file SA01" \
-        -i "pandas.json_normalize RT03,SA01" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
         -i "pandas.plotting.scatter_matrix PR07,SA01" \
-        -i "pandas.set_eng_float_format RT03,SA01" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
         -i "pandas.tseries.offsets.BQuarterBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.n GL08" \
@@ -296,7 +288,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.Second.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Second.n GL08" \
         -i "pandas.tseries.offsets.Second.normalize GL08" \
-        -i "pandas.tseries.offsets.SemiMonthBegin SA01" \
         -i "pandas.tseries.offsets.SemiMonthBegin.day_of_month GL08" \
         -i "pandas.tseries.offsets.SemiMonthBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.SemiMonthBegin.n GL08" \

ci/deps/actions-311-pyarrownightly.yaml

@@ -18,7 +18,7 @@ dependencies:
 
   # required dependencies
   - python-dateutil
-  - numpy<2
+  - numpy
   - pip
 
   - pip:

doc/source/development/contributing_codebase.rst

@@ -298,6 +298,12 @@ So, before actually writing any code, you should write your tests.  Often the te
 taken from the original GitHub issue.  However, it is always worth considering additional
 use cases and writing corresponding tests.
 
+We use `code coverage <https://en.wikipedia.org/wiki/Code_coverage>`_ to help understand
+the amount of code which is covered by a test. We recommend striving to ensure code
+you add or change within Pandas is covered by a test. Please see our
+`code coverage dashboard through Codecov <https://app.codecov.io/github/pandas-dev/pandas>`_
+for more information.
+
 Adding tests is one of the most common requests after code is pushed to pandas.  Therefore,
 it is worth getting in the habit of writing tests ahead of time so this is never an issue.
 

doc/source/user_guide/cookbook.rst

@@ -35,7 +35,7 @@ These are some neat pandas ``idioms``
    )
    df
 
-if-then...
+If-then...
 **********
 
 An if-then on one column
@@ -176,7 +176,7 @@ One could hard code:
 Selection
 ---------
 
-Dataframes
+DataFrames
 **********
 
 The :ref:`indexing <indexing>` docs.
@@ -1489,7 +1489,7 @@ of the data values:
    )
    df
 
-Constant series
+Constant Series
 ---------------
 
 To assess if a series has a constant value, we can check if ``series.nunique() <= 1``.

doc/source/user_guide/gotchas.rst

@@ -121,7 +121,7 @@ Below is how to check if any of the values are ``True``:
     if pd.Series([False, True, False]).any():
         print("I am any")
 
-Bitwise boolean
+Bitwise Boolean
 ~~~~~~~~~~~~~~~
 
 Bitwise boolean operators like ``==`` and ``!=`` return a boolean :class:`Series`

doc/source/user_guide/groupby.rst

@@ -618,7 +618,7 @@ this will make an extra copy.
 
 .. _groupby.aggregate.udf:
 
-Aggregation with User-Defined Functions
+Aggregation with user-defined functions
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Users can also provide their own User-Defined Functions (UDFs) for custom aggregations.
@@ -1261,7 +1261,7 @@ with
     df.groupby("A", group_keys=False).apply(lambda x: x, include_groups=False)
 
 
-Numba Accelerated Routines
+Numba accelerated routines
 --------------------------
 
 .. versionadded:: 1.1
@@ -1696,7 +1696,7 @@ introduction <categorical>` and the
 
     dfg.groupby(["A", [0, 0, 0, 1, 1]]).ngroup()
 
-Groupby by indexer to 'resample' data
+GroupBy by indexer to 'resample' data
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Resampling produces new hypothetical samples (resamples) from already existing observed data or from a model that generates data. These new samples are similar to the pre-existing samples.

doc/source/user_guide/integer_na.rst

@@ -147,7 +147,7 @@ Reduction and groupby operations such as :meth:`~DataFrame.sum` work as well.
    df.sum()
    df.groupby("B").A.sum()
 
-Scalar NA Value
+Scalar NA value
 ---------------
 
 :class:`arrays.IntegerArray` uses :attr:`pandas.NA` as its scalar

doc/source/user_guide/io.rst

@@ -5996,7 +5996,7 @@ Full documentation can be found `here <https://pandas-gbq.readthedocs.io/en/late
 
 .. _io.stata:
 
-Stata format
+STATA format
 ------------
 
 .. _io.stata_writer: