DOC: Enforce Numpy Docstring Validation for freqstr, nanos, and rule_code methods of pandas.tseries.offsets Week, WeekOfMonth, YearBegin, and YearEnd classes.

Author: Siniade

.devcontainer.json

@@ -8,7 +8,6 @@
 	// Use 'settings' to set *default* container specific settings.json values on container create.
 	// You can edit these settings after create using File > Preferences > Settings > Remote.
 	"settings": {
-		"terminal.integrated.shell.linux": "/bin/bash",
 		"python.pythonPath": "/usr/local/bin/python",
 		"python.formatting.provider": "black",
 		"python.linting.enabled": true,

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

@@ -14,3 +14,9 @@ runs:
         condarc-file: ci/.condarc
         cache-environment: true
         cache-downloads: true
+
+    - name: Uninstall pyarrow
+      if: ${{ env.REMOVE_PYARROW == '1' }}
+      run: |
+        micromamba remove -y pyarrow
+      shell: bash -el {0}

.github/workflows/unit-tests.yml

@@ -29,6 +29,7 @@ jobs:
         env_file: [actions-310.yaml, actions-311.yaml, actions-312.yaml]
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
+        pandas_future_infer_string: ["0"]
         include:
           - name: "Downstream Compat"
             env_file: actions-311-downstream_compat.yaml
@@ -58,6 +59,9 @@ jobs:
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "zh_CN"
           - name: "Future infer strings"
+            env_file: actions-312.yaml
+            pandas_future_infer_string: "1"
+          - name: "Future infer strings (without pyarrow)"
             env_file: actions-311.yaml
             pandas_future_infer_string: "1"
           - name: "Pypy"
@@ -85,9 +89,10 @@ jobs:
       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' }}
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_future_infer_string }}
       cancel-in-progress: true
 
     services:

.gitpod.yml

@@ -14,7 +14,7 @@ tasks:
       cp gitpod/settings.json .vscode/settings.json
       git fetch --tags
       python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true
-      pre-commit install
+      pre-commit install --install-hooks
     command: |
       python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true
       echo "✨ Pre-build complete! You can close this terminal ✨ "

Dockerfile

@@ -2,7 +2,7 @@ FROM python:3.10.8
 WORKDIR /home/pandas
 
 RUN apt-get update && apt-get -y upgrade
-RUN apt-get install -y build-essential
+RUN apt-get install -y build-essential bash-completion
 
 # hdf5 needed for pytables installation
 # libgles2-mesa needed for pytest-qt
@@ -12,4 +12,6 @@ RUN python -m pip install --upgrade pip
 COPY requirements-dev.txt /tmp
 RUN python -m pip install -r /tmp/requirements-dev.txt
 RUN git config --global --add safe.directory /home/pandas
+
+ENV SHELL "/bin/bash"
 CMD ["/bin/bash"]

ci/code_checks.sh

@@ -163,7 +163,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.str.center RT03,SA01" \
         -i "pandas.Series.str.decode PR07,RT03,SA01" \
         -i "pandas.Series.str.encode PR07,RT03,SA01" \
-        -i "pandas.Series.str.index RT03" \
         -i "pandas.Series.str.ljust RT03,SA01" \
         -i "pandas.Series.str.lower RT03" \
         -i "pandas.Series.str.lstrip RT03" \
@@ -172,7 +171,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.str.partition RT03" \
         -i "pandas.Series.str.repeat SA01" \
         -i "pandas.Series.str.replace SA01" \
-        -i "pandas.Series.str.rindex RT03" \
         -i "pandas.Series.str.rjust RT03,SA01" \
         -i "pandas.Series.str.rpartition RT03" \
         -i "pandas.Series.str.rstrip RT03" \

doc/source/whatsnew/v3.0.0.rst

@@ -50,6 +50,8 @@ Other enhancements
 - :meth:`DataFrame.pivot_table` and :func:`pivot_table` now allow the passing of keyword arguments to ``aggfunc`` through ``**kwargs`` (:issue:`57884`)
 - :meth:`Series.cummin` and :meth:`Series.cummax` now supports :class:`CategoricalDtype` (:issue:`52335`)
 - :meth:`Series.plot` now correctly handle the ``ylabel`` parameter for pie charts, allowing for explicit control over the y-axis label (:issue:`58239`)
+- :meth:`pandas.concat` will raise a ``ValueError`` when ``ignore_index=True`` and ``keys`` is not ``None`` (:issue:`59274`)
+- Multiplying two :class:`DateOffset` objects will now raise a ``TypeError`` instead of a ``RecursionError`` (:issue:`59442`)
 - Restore support for reading Stata 104-format and enable reading 103-format dta files (:issue:`58554`)
 - Support reading Stata 102-format (Stata 1) dta files (:issue:`58978`)
 - Support reading Stata 110-format (Stata 7) dta files (:issue:`47176`)
@@ -617,6 +619,7 @@ Groupby/resample/rolling
 
 Reshaping
 ^^^^^^^^^
+- Bug in :func:`qcut` where values at the quantile boundaries could be incorrectly assigned (:issue:`59355`)
 - Bug in :meth:`DataFrame.join` inconsistently setting result index name (:issue:`55815`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when ``sort=False`` (:issue:`54987`, :issue:`55516`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when manipulating empty :class:`DataFrame` with an :class:`ExtentionDtype` (:issue:`59123`)

pandas/_libs/tslibs/offsets.pyx

@@ -491,6 +491,12 @@ cdef class BaseOffset:
         elif is_integer_object(other):
             return type(self)(n=other * self.n, normalize=self.normalize,
                               **self.kwds)
+        elif isinstance(other, BaseOffset):
+            # Otherwise raises RecurrsionError due to __rmul__
+            raise TypeError(
+                f"Cannot multiply {type(self).__name__} with "
+                f"{type(other).__name__}."
+            )
         return NotImplemented
 
     def __rmul__(self, other):
@@ -604,7 +610,7 @@ cdef class BaseOffset:
 
         >>> pd.offsets.Week(5).rule_code
         'W'
-        """
+        """ # noqa
         return self._prefix
 
     @cache_readonly
@@ -632,7 +638,7 @@ cdef class BaseOffset:
 
         >>> pd.offsets.Nano(-3).freqstr
         '-3ns'
-        """
+        """ # noqa
         try:
             code = self.rule_code
         except NotImplementedError:
@@ -797,25 +803,25 @@ cdef class BaseOffset:
     @property
     def nanos(self):
         """
-        Returns a ValueError becuase the frequency is non-fixed.
-        
+        Returns a ValueError because the frequency is non-fixed.
+
         Raises
         ------
         ValueError
             If the frequency is non-fixed.
 
         See Also
         --------
-        tseries.offsets.WeekOfMonth.nanos : Raises a ValueError becuase the frequency is non-fixed.
-        tseries.offsets.YearBegin.nanos : Raises a ValueError becuase the frequency is non-fixed.
+        tseries.offsets.WeekOfMonth.nanos : Raises a ValueError because the frequency is non-fixed.
+        tseries.offsets.YearBegin.nanos : Raises a ValueError because the frequency is non-fixed.
         tseries.offsets.Hour.nanos : Returns an integer of the total number of nanoseconds.
         tseries.offsets.Day.nanos : Returns an integer of the total number of nanoseconds.
 
         Examples
         --------
         >>> pd.offsets.Week(n=1).nanos
-        ValueError: <5 * Weeks: weekday=None> is a non-fixed frequency
-        """
+        ValueError: <Week: weekday=None> is a non-fixed frequency
+        """ # noqa
         raise ValueError(f"{self} is a non-fixed frequency")
 
     # ------------------------------------------------------------------
@@ -1029,14 +1035,14 @@ cdef class Tick(SingleConstructorOffset):
         --------
         tseries.offsets.Hour.nanos : Returns an integer of the total number of nanoseconds.
         tseries.offsets.Day.nanos : Returns an integer of the total number of nanoseconds.
-        tseries.offsets.WeekOfMonth.nanos : Raises a ValueError becuase the frequency is non-fixed.
-        tseries.offsets.YearBegin.nanos : Raises a ValueError becuase the frequency is non-fixed.
+        tseries.offsets.WeekOfMonth.nanos : Raises a ValueError because the frequency is non-fixed.
+        tseries.offsets.YearBegin.nanos : Raises a ValueError because the frequency is non-fixed.
 
         Examples
         --------
         >>> pd.offsets.Hour(5).nanos
         18000000000000
-        """
+        """ # noqa
         return self.n * self._nanos_inc
 
     def is_on_offset(self, dt: datetime) -> bool:
@@ -2480,7 +2486,7 @@ cdef class WeekOfMonthMixin(SingleConstructorOffset):
 
         >>> pd.offsets.WeekOfMonth(n=1, week=0, weekday=0).rule_code
         'WOM-1MON'
-        """
+        """ # noqa
         weekday = int_to_weekday.get(self.weekday, "")
         if self.week == -1:
             # LastWeekOfMonth
@@ -2542,7 +2548,7 @@ cdef class YearOffset(SingleConstructorOffset):
 
         >>> pd.tseries.offsets.YearEnd(n=1, month=6).rule_code
         'YE-JUN'
-        """
+        """ # noqa
         month = MONTH_ALIASES[self.month]
         return f"{self._prefix}-{month}"
 
@@ -3544,7 +3550,7 @@ cdef class Week(SingleConstructorOffset):
 
         >>> pd.offsets.Week(5).rule_code
         'W'
-        """
+        """ # noqa
         suffix = ""
         if self.weekday is not None:
             weekday = int_to_weekday[self.weekday]

pandas/core/array_algos/quantile.py

@@ -94,9 +94,9 @@ def quantile_with_mask(
         flat = np.array([fill_value] * len(qs))
         result = np.repeat(flat, len(values)).reshape(len(values), len(qs))
     else:
-        result = _nanpercentile(
+        result = _nanquantile(
             values,
-            qs * 100.0,
+            qs,
             na_value=fill_value,
             mask=mask,
             interpolation=interpolation,
@@ -108,15 +108,15 @@ def quantile_with_mask(
     return result
 
 
-def _nanpercentile_1d(
+def _nanquantile_1d(
     values: np.ndarray,
     mask: npt.NDArray[np.bool_],
     qs: npt.NDArray[np.float64],
     na_value: Scalar,
     interpolation: str,
 ) -> Scalar | np.ndarray:
     """
-    Wrapper for np.percentile that skips missing values, specialized to
+    Wrapper for np.quantile that skips missing values, specialized to
     1-dimensional case.
 
     Parameters
@@ -142,7 +142,7 @@ def _nanpercentile_1d(
         # equiv: 'np.array([na_value] * len(qs))' but much faster
         return np.full(len(qs), na_value)
 
-    return np.percentile(
+    return np.quantile(
         values,
         qs,
         # error: No overload variant of "percentile" matches argument
@@ -152,7 +152,7 @@ def _nanpercentile_1d(
     )
 
 
-def _nanpercentile(
+def _nanquantile(
     values: np.ndarray,
     qs: npt.NDArray[np.float64],
     *,
@@ -161,7 +161,7 @@ def _nanpercentile(
     interpolation: str,
 ):
     """
-    Wrapper for np.percentile that skips missing values.
+    Wrapper for np.quantile that skips missing values.
 
     Parameters
     ----------
@@ -180,7 +180,7 @@ def _nanpercentile(
 
     if values.dtype.kind in "mM":
         # need to cast to integer to avoid rounding errors in numpy
-        result = _nanpercentile(
+        result = _nanquantile(
             values.view("i8"),
             qs=qs,
             na_value=na_value.view("i8"),
@@ -196,7 +196,7 @@ def _nanpercentile(
         # Caller is responsible for ensuring mask shape match
         assert mask.shape == values.shape
         result = [
-            _nanpercentile_1d(val, m, qs, na_value, interpolation=interpolation)
+            _nanquantile_1d(val, m, qs, na_value, interpolation=interpolation)
             for (val, m) in zip(list(values), list(mask))
         ]
         if values.dtype.kind == "f":
@@ -215,7 +215,7 @@ def _nanpercentile(
                 result = result.astype(values.dtype, copy=False)
         return result
     else:
-        return np.percentile(
+        return np.quantile(
             values,
             qs,
             axis=1,