Merge branch 'main' into enh_numba_apply_support_kwargs

auderson · auderson · commit 33be300226f1 · 2024-10-30T09:24:46.000+08:00
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -2,9 +2,9 @@ minimum_pre_commit_version: 2.15.0
 exclude: ^LICENSES/|\.(html|csv|svg)$
 # reserve "manual" for relatively slow hooks which we still want to run in CI
 default_stages: [
-    commit,
-    merge-commit,
-    push,
+    pre-commit,
+    pre-merge-commit,
+    pre-push,
     prepare-commit-msg,
     commit-msg,
     post-checkout,
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -85,7 +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" \
@@ -97,7 +96,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.arrays.NumpyExtensionArray SA01" \
         -i "pandas.arrays.SparseArray PR07,SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.boxplot PR07,RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.groups SA01" \
@@ -106,7 +104,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.groups SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.indices SA01" \
@@ -115,7 +112,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
-        -i "pandas.core.resample.Resampler.__iter__ RT03,SA01" \
         -i "pandas.core.resample.Resampler.get_group RT03,SA01" \
         -i "pandas.core.resample.Resampler.groups SA01" \
         -i "pandas.core.resample.Resampler.indices SA01" \
@@ -126,11 +122,9 @@ 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" \
@@ -139,19 +133,15 @@ 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.PossiblePrecisionLoss 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" \
@@ -300,7 +290,6 @@ 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" \
diff --git a/doc/source/development/contributing_codebase.rst b/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.
 
diff --git a/pandas/_config/config.py b/pandas/_config/config.py
@@ -105,6 +105,10 @@ class OptionError(AttributeError, KeyError):
 
     Backwards compatible with KeyError checks.
 
+    See Also
+    --------
+    options : Access and modify global pandas settings.
+
     Examples
     --------
     >>> pd.options.context
diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx
@@ -1122,9 +1122,23 @@ def is_integer(obj: object) -> bool:
     """
     Return True if given object is integer.
 
+    This method checks whether the passed object is an integer type. It
+    returns `True` if the object is an integer, and `False` otherwise.
+
+    Parameters
+    ----------
+    obj : object
+        The object to check for integer type.
+
     Returns
     -------
     bool
+        `True` if the object is of integer type, otherwise `False`.
+
+    See Also
+    --------
+    api.types.is_float : Check if an object is of float type.
+    api.types.is_numeric_dtype : Check if an object is of numeric type.
 
     Examples
     --------
diff --git a/pandas/_libs/tslibs/offsets.pyx b/pandas/_libs/tslibs/offsets.pyx
@@ -3371,6 +3371,10 @@ cdef class SemiMonthBegin(SemiMonthOffset):
     """
     Two DateOffset's per month repeating on the first day of the month & day_of_month.
 
+    This offset moves dates to the first day of the month and an additional specified
+    day (typically the 15th by default), useful in scenarios where bi-monthly processing
+    occurs on set days.
+
     Attributes
     ----------
     n : int, default 1
@@ -3380,6 +3384,13 @@ cdef class SemiMonthBegin(SemiMonthOffset):
     day_of_month : int, {1, 3,...,27}, default 15
         A specific integer for the day of the month.
 
+    See Also
+    --------
+    tseries.offsets.SemiMonthEnd : Two DateOffset's per month repeating on the last day
+        of the month & day_of_month.
+    tseries.offsets.MonthEnd : Offset to the last calendar day of the month.
+    tseries.offsets.MonthBegin : Offset to the first calendar day of the month.
+
     Examples
     --------
     >>> ts = pd.Timestamp(2022, 1, 1)
diff --git a/pandas/_libs/tslibs/timedeltas.pyx b/pandas/_libs/tslibs/timedeltas.pyx
@@ -1864,10 +1864,12 @@ class Timedelta(_Timedelta):
 
     Parameters
     ----------
-    value : Timedelta, timedelta, np.timedelta64, str, or int
+    value : Timedelta, timedelta, np.timedelta64, str, int or float
         Input value.
     unit : str, default 'ns'
-        Denote the unit of the input, if input is an integer.
+        If input is an integer, denote the unit of the input.
+        If input is a float, denote the unit of the integer parts.
+        The decimal parts with resolution lower than 1 nanosecond are ignored.
 
         Possible values:
 
diff --git a/pandas/core/frame.py b/pandas/core/frame.py
@@ -10823,7 +10823,7 @@ def round(
         self, decimals: int | dict[IndexLabel, int] | Series = 0, *args, **kwargs
     ) -> DataFrame:
         """
-        Round a DataFrame to a variable number of decimal places.
+        Round numeric columns in a DataFrame to a variable number of decimal places.
 
         Parameters
         ----------
diff --git a/pandas/core/groupby/groupby.py b/pandas/core/groupby/groupby.py
@@ -768,10 +768,24 @@ def __iter__(self) -> Iterator[tuple[Hashable, NDFrameT]]:
         """
         Groupby iterator.
 
+        This method provides an iterator over the groups created by the ``resample``
+        or ``groupby`` operation on the object. The method yields tuples where
+        the first element is the label (group key) corresponding to each group or
+        resampled bin, and the second element is the subset of the data that falls
+        within that group or bin.
+
         Returns
         -------
-        Generator yielding sequence of (name, subsetted object)
-        for each group
+        Iterator
+            Generator yielding a sequence of (name, subsetted object)
+            for each group.
+
+        See Also
+        --------
+        Series.groupby : Group data by a specific key or column.
+        DataFrame.groupby : Group DataFrame using mapper or by columns.
+        DataFrame.resample : Resample a DataFrame.
+        Series.resample : Resample a Series.
 
         Examples
         --------
diff --git a/pandas/core/resample.py b/pandas/core/resample.py
@@ -1021,6 +1021,10 @@ def sum(
         """
         Compute sum of group values.
 
+        This method provides a simple way to compute the sum of values within each
+        resampled group, particularly useful for aggregating time-based data into
+        daily, monthly, or yearly sums.
+
         Parameters
         ----------
         numeric_only : bool, default False
@@ -1039,6 +1043,14 @@ def sum(
         Series or DataFrame
             Computed sum of values within each group.
 
+        See Also
+        --------
+        core.resample.Resampler.mean : Compute mean of groups, excluding missing values.
+        core.resample.Resampler.count : Compute count of group, excluding missing
+            values.
+        DataFrame.resample : Resample time-series data.
+        Series.sum : Return the sum of the values over the requested axis.
+
         Examples
         --------
         >>> ser = pd.Series(
diff --git a/pandas/core/strings/accessor.py b/pandas/core/strings/accessor.py
@@ -255,7 +255,9 @@ def _validate(data):
         inferred_dtype = lib.infer_dtype(values, skipna=True)
 
         if inferred_dtype not in allowed_types:
-            raise AttributeError("Can only use .str accessor with string values!")
+            raise AttributeError(
+                f"Can only use .str accessor with string values, not {inferred_dtype}"
+            )
         return inferred_dtype
 
     def __getitem__(self, key):
diff --git a/pandas/errors/__init__.py b/pandas/errors/__init__.py
@@ -76,6 +76,12 @@ class UnsupportedFunctionCall(ValueError):
 
     For example, ``np.cumsum(groupby_object)``.
 
+    See Also
+    --------
+    DataFrame.groupby : Group DataFrame using a mapper or by a Series of columns.
+    Series.groupby : Group Series using a mapper or by a Series of columns.
+    core.groupby.GroupBy.cumsum : Compute cumulative sum for each group.
+
     Examples
     --------
     >>> df = pd.DataFrame(
@@ -591,6 +597,14 @@ class CSSWarning(UserWarning):
     This can be due to the styling not having an equivalent value or because the
     styling isn't properly formatted.
 
+    See Also
+    --------
+    DataFrame.style : Returns a Styler object for applying CSS-like styles.
+    io.formats.style.Styler : Helps style a DataFrame or Series according to the
+        data with HTML and CSS.
+    io.formats.style.Styler.to_excel : Export styled DataFrame to Excel.
+    io.formats.style.Styler.to_html : Export styled DataFrame to HTML.
+
     Examples
     --------
     >>> df = pd.DataFrame({"A": [1, 1, 1]})
@@ -691,6 +705,10 @@ class PossiblePrecisionLoss(Warning):
     When the column value is outside or equal to the int64 value the column is
     converted to a float64 dtype.
 
+    See Also
+    --------
+    DataFrame.to_stata : Export DataFrame object to Stata dta format.
+
     Examples
     --------
     >>> df = pd.DataFrame({"s": pd.Series([1, 2**53], dtype=np.int64)})
diff --git a/pandas/io/json/_normalize.py b/pandas/io/json/_normalize.py
@@ -279,6 +279,10 @@ def json_normalize(
     """
     Normalize semi-structured JSON data into a flat table.
 
+    This method is designed to transform semi-structured JSON data, such as nested
+    dictionaries or lists, into a flat table. This is particularly useful when
+    handling JSON-like data structures that contain deeply nested fields.
+
     Parameters
     ----------
     data : dict, list of dicts, or Series of dicts
@@ -310,8 +314,13 @@ def json_normalize(
 
     Returns
     -------
-    frame : DataFrame
-    Normalize semi-structured JSON data into a flat table.
+    DataFrame
+        The normalized data, represented as a pandas DataFrame.
+
+    See Also
+    --------
+    DataFrame : Two-dimensional, size-mutable, potentially heterogeneous tabular data.
+    Series : One-dimensional ndarray with axis labels (including time series).
 
     Examples
     --------
diff --git a/pandas/tests/series/accessors/test_str_accessor.py b/pandas/tests/series/accessors/test_str_accessor.py
@@ -15,7 +15,8 @@ def test_str_attribute(self):
 
         # str accessor only valid with string values
         ser = Series(range(5))
-        with pytest.raises(AttributeError, match="only use .str accessor"):
+        msg = "Can only use .str accessor with string values, not integer"
+        with pytest.raises(AttributeError, match=msg):
             ser.str.repeat(2)
 
     def test_str_accessor_updates_on_inplace(self):
diff --git a/pyproject.toml b/pyproject.toml
@@ -2,8 +2,8 @@
 # Minimum requirements for the build system to execute.
 # See https://github.com/scipy/scipy/pull/12940 for the AIX issue.
 requires = [
-    "meson-python==0.13.1",
-    "meson==1.2.1",
+    "meson-python>=0.13.1",
+    "meson>=1.2.1,<2",
     "wheel",
     "Cython~=3.0.5",  # Note: sync with setup.py, environment.yml and asv.conf.json
     # Force numpy higher than 2.0rc1, so that built wheels are compatible
diff --git a/web/pandas/community/ecosystem.md b/web/pandas/community/ecosystem.md
@@ -239,6 +239,17 @@ Console](https://docs.spyder-ide.org/current/panes/ipythonconsole.html), and Spy
 render Numpydoc documentation on pandas objects in rich text with Sphinx
 both automatically and on-demand.
 
+### [marimo](https://marimo.io)
+
+marimo is a reactive notebook for Python and SQL that enhances productivity when working with dataframes. It provides several features to make data manipulation and visualization more interactive and fun:
+
+1. Rich, interactive displays: marimo can display pandas dataframes in interactive tables or charts with filtering and sorting capabilities.
+2. Data selection: Users can select data in tables or pandas-backed plots, and the selections are automatically sent to Python as pandas dataframes.
+3. No-code transformations: Users can interactively transform pandas dataframes using a GUI, without writing code. The generated code can be copied and pasted into the notebook.
+4. Custom filters: marimo allows the creation of pandas-backed filters using UI elements like sliders and dropdowns.
+5. Dataset explorer: marimo automatically discovers and displays all dataframes in the notebook, allowing users to explore and visualize data interactively.
+6. SQL integration: marimo allows users to write SQL queries against any pandas dataframes existing in memory.
+
 ## API
 
 ### [pandas-datareader](https://github.com/pydata/pandas-datareader)
