Merge branch 'main' into enforce-match

Author: chaarvii

.github/workflows/unit-tests.yml

@@ -391,6 +391,7 @@ jobs:
         env:
           PYTHON_GIL: 0
 
+  # NOTE: this job must be kept in sync with the Pyodide build job in wheels.yml
   emscripten:
     # Note: the Python version, Emscripten toolchain version are determined
     # by the Pyodide version. The appropriate versions can be found in the

.github/workflows/wheels.yml

@@ -100,6 +100,13 @@ jobs:
         - [windows-2022, win_amd64]
         # TODO: support PyPy?
         python: [["cp310", "3.10"], ["cp311", "3.11"], ["cp312", "3.12"]]
+
+        # Build Pyodide wheels and upload them to Anaconda.org
+        # NOTE: this job is similar to the one in unit-tests.yml except for the fact
+        # that it uses cibuildwheel instead of a standard Pyodide xbuildenv setup.
+        include:
+          - buildplat: [ubuntu-22.04, pyodide_wasm32]
+            python: ["cp312", "3.12"]
     env:
       IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
       IS_SCHEDULE_DISPATCH: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -140,12 +147,13 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.19.1
+        uses: pypa/cibuildwheel@v2.19.2
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
           CIBW_PRERELEASE_PYTHONS: True
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
+          CIBW_PLATFORM: ${{ matrix.buildplat[1] == 'pyodide_wasm32' && 'pyodide' || 'auto' }}
 
       - name: Set up Python
         uses: mamba-org/setup-micromamba@v1

asv_bench/benchmarks/indexing.py

@@ -546,24 +546,17 @@ def time_chained_indexing(self, mode):
 
 
 class Block:
-    params = [
-        (True, "True"),
-        (np.array(True), "np.array(True)"),
-    ]
-
-    def setup(self, true_value, mode):
+    def setup(self):
         self.df = DataFrame(
             False,
             columns=np.arange(500).astype(str),
             index=date_range("2010-01-01", "2011-01-01"),
         )
 
-        self.true_value = true_value
-
-    def time_test(self, true_value, mode):
+    def time_test(self):
         start = datetime(2010, 5, 1)
         end = datetime(2010, 9, 1)
-        self.df.loc[start:end, :] = true_value
+        self.df.loc[start:end, :] = True
 
 
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

ci/code_checks.sh

@@ -70,10 +70,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
-        -i "pandas.DataFrame.max RT03" \
-        -i "pandas.DataFrame.mean RT03" \
-        -i "pandas.DataFrame.median RT03" \
-        -i "pandas.DataFrame.min RT03" \
         -i "pandas.DataFrame.plot PR02" \
         -i "pandas.Grouper PR02" \
         -i "pandas.MultiIndex.append PR07,SA01" \
@@ -95,7 +91,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.freqstr SA01" \
         -i "pandas.Period.month SA01" \
-        -i "pandas.Period.now SA01" \
         -i "pandas.Period.ordinal GL08" \
         -i "pandas.Period.strftime PR01,SA01" \
         -i "pandas.Period.to_timestamp SA01" \
@@ -167,7 +162,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.product RT03" \
         -i "pandas.Series.reorder_levels RT03,SA01" \
         -i "pandas.Series.sem PR01,RT03,SA01" \
-        -i "pandas.Series.skew RT03,SA01" \
+        -i "pandas.Series.skew SA01" \
         -i "pandas.Series.sparse PR01,SA01" \
         -i "pandas.Series.sparse.density SA01" \
         -i "pandas.Series.sparse.fill_value SA01" \

doc/source/getting_started/intro_tutorials/04_plotting.rst

@@ -32,8 +32,10 @@ How do I create plots in pandas?
     air_quality.head()
 
 .. note::
-    The usage of the ``index_col`` and ``parse_dates`` parameters of the ``read_csv`` function to define the first (0th) column as
-    index of the resulting ``DataFrame`` and convert the dates in the column to :class:`Timestamp` objects, respectively.
+    The ``index_col=0`` and ``parse_dates=True`` parameters passed to the ``read_csv`` function define
+    the first (0th) column as index of the resulting ``DataFrame`` and convert the dates in the column
+    to :class:`Timestamp`  objects, respectively.
+
 
 .. raw:: html
 

doc/source/getting_started/overview.rst

@@ -6,11 +6,11 @@
 Package overview
 ****************
 
-pandas is a `Python <https://www.python.org>`__ package providing fast,
+pandas is a `Python <https://www.python.org>`__ package that provides fast,
 flexible, and expressive data structures designed to make working with
 "relational" or "labeled" data both easy and intuitive. It aims to be the
-fundamental high-level building block for doing practical, **real-world** data
-analysis in Python. Additionally, it has the broader goal of becoming **the
+fundamental high-level building block for Python's practical, **real-world** data
+analysis. Additionally, it seeks to become **the
 most powerful and flexible open source data analysis/manipulation tool
 available in any language**. It is already well on its way toward this goal.
 

doc/source/user_guide/categorical.rst

@@ -793,7 +793,7 @@ Assigning a ``Categorical`` to parts of a column of other types will use the val
     :okwarning:
 
     df = pd.DataFrame({"a": [1, 1, 1, 1, 1], "b": ["a", "a", "a", "a", "a"]})
-    df.loc[1:2, "a"] = pd.Categorical(["b", "b"], categories=["a", "b"])
+    df.loc[1:2, "a"] = pd.Categorical([2, 2], categories=[2, 3])
     df.loc[2:3, "b"] = pd.Categorical(["b", "b"], categories=["a", "b"])
     df
     df.dtypes

doc/source/user_guide/io.rst

@@ -2161,7 +2161,7 @@ a JSON string with two fields, ``schema`` and ``data``.
        {
            "A": [1, 2, 3],
            "B": ["a", "b", "c"],
-           "C": pd.date_range("2016-01-01", freq="d", periods=3),
+           "C": pd.date_range("2016-01-01", freq="D", periods=3),
        },
        index=pd.Index(range(3), name="idx"),
    )
@@ -2270,7 +2270,7 @@ round-trippable manner.
        {
            "foo": [1, 2, 3, 4],
            "bar": ["a", "b", "c", "d"],
-           "baz": pd.date_range("2018-01-01", freq="d", periods=4),
+           "baz": pd.date_range("2018-01-01", freq="D", periods=4),
            "qux": pd.Categorical(["a", "b", "c", "c"]),
        },
        index=pd.Index(range(4), name="idx"),

doc/source/whatsnew/v0.18.0.rst

@@ -322,15 +322,28 @@ Tz-aware are rounded, floored and ceiled in local times
 
 Timedeltas
 
-.. ipython:: python
+.. code-block:: ipython
+
+   In [37]: t = pd.timedelta_range('1 days 2 hr 13 min 45 us', periods=3, freq='d')
 
-   t = pd.timedelta_range('1 days 2 hr 13 min 45 us', periods=3, freq='d')
-   t
-   t.round('10min')
+   In [38]: t
+   Out[38]:
+   TimedeltaIndex(['1 days 02:13:00.000045', '2 days 02:13:00.000045',
+                   '3 days 02:13:00.000045'],
+                  dtype='timedelta64[ns]', freq='D')
+
+   In [39]: t.round('10min')
+   Out[39]:
+   TimedeltaIndex(['1 days 02:10:00', '2 days 02:10:00',
+                   '3 days 02:10:00'],
+                  dtype='timedelta64[ns]', freq=None)
 
    # Timedelta scalar
-   t[0]
-   t[0].round('2h')
+   In [40]: t[0]
+   Out[40]: Timedelta('1 days 02:13:00.000045')
+
+   In [41]: t[0].round('2h')
+   Out[41]: Timedelta('1 days 02:00:00')
 
 
 In addition, ``.round()``, ``.floor()`` and ``.ceil()`` will be available through the ``.dt`` accessor of ``Series``.

doc/source/whatsnew/v0.20.0.rst

@@ -308,15 +308,26 @@ The new orient ``'table'`` for :meth:`DataFrame.to_json`
 will generate a `Table Schema`_ compatible string representation of
 the data.
 
-.. ipython:: python
+.. code-block:: ipython
 
-   df = pd.DataFrame(
-       {'A': [1, 2, 3],
-        'B': ['a', 'b', 'c'],
-        'C': pd.date_range('2016-01-01', freq='d', periods=3)},
-       index=pd.Index(range(3), name='idx'))
-   df
-   df.to_json(orient='table')
+   In [38]: df = pd.DataFrame(
+      ....: {'A': [1, 2, 3],
+      ....:  'B': ['a', 'b', 'c'],
+      ....:  'C': pd.date_range('2016-01-01', freq='d', periods=3)},
+      ....: index=pd.Index(range(3), name='idx'))
+   In [39]: df
+   Out[39]:
+        A  B          C
+   idx
+   0    1  a 2016-01-01
+   1    2  b 2016-01-02
+   2    3  c 2016-01-03
+
+   [3 rows x 3 columns]
+
+   In [40]: df.to_json(orient='table')
+   Out[40]:
+   '{"schema":{"fields":[{"name":"idx","type":"integer"},{"name":"A","type":"integer"},{"name":"B","type":"string"},{"name":"C","type":"datetime"}],"primaryKey":["idx"],"pandas_version":"1.4.0"},"data":[{"idx":0,"A":1,"B":"a","C":"2016-01-01T00:00:00.000"},{"idx":1,"A":2,"B":"b","C":"2016-01-02T00:00:00.000"},{"idx":2,"A":3,"B":"c","C":"2016-01-03T00:00:00.000"}]}'
 
 
 See :ref:`IO: Table Schema for more information <io.table_schema>`.