Merge branch 'main' into gha-arm64-ci

Author: lithomas1

ci/code_checks.sh

@@ -79,7 +79,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.min PR02" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
-        -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \

doc/source/reference/groupby.rst

@@ -104,6 +104,7 @@ Function application
    DataFrameGroupBy.shift
    DataFrameGroupBy.size
    DataFrameGroupBy.skew
+   DataFrameGroupBy.kurt
    DataFrameGroupBy.std
    DataFrameGroupBy.sum
    DataFrameGroupBy.var
@@ -159,6 +160,7 @@ Function application
    SeriesGroupBy.shift
    SeriesGroupBy.size
    SeriesGroupBy.skew
+   SeriesGroupBy.kurt
    SeriesGroupBy.std
    SeriesGroupBy.sum
    SeriesGroupBy.var

doc/source/reference/window.rst

@@ -30,6 +30,8 @@ Rolling window functions
    Rolling.std
    Rolling.min
    Rolling.max
+   Rolling.first
+   Rolling.last
    Rolling.corr
    Rolling.cov
    Rolling.skew
@@ -72,6 +74,8 @@ Expanding window functions
    Expanding.std
    Expanding.min
    Expanding.max
+   Expanding.first
+   Expanding.last
    Expanding.corr
    Expanding.cov
    Expanding.skew

doc/source/whatsnew/v2.3.0.rst

@@ -175,7 +175,6 @@ Other
 ^^^^^
 - Fixed usage of ``inspect`` when the optional dependencies ``pyarrow`` or ``jinja2``
   are not installed (:issue:`60196`)
--
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_230.contributors:

doc/source/whatsnew/v3.0.0.rst

@@ -57,6 +57,7 @@ Other enhancements
 - :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:`DataFrame.plot.scatter` argument ``c`` now accepts a column of strings, where rows with the same string are colored identically (:issue:`16827` and :issue:`16485`)
+- :class:`Rolling` and :class:`Expanding` now support aggregations ``first`` and ``last`` (:issue:`33155`)
 - :func:`read_parquet` accepts ``to_pandas_kwargs`` which are forwarded to :meth:`pyarrow.Table.to_pandas` which enables passing additional keywords to customize the conversion to pandas, such as ``maps_as_pydicts`` to read the Parquet map data type as python dictionaries (:issue:`56842`)
 - :meth:`.DataFrameGroupBy.transform`, :meth:`.SeriesGroupBy.transform`, :meth:`.DataFrameGroupBy.agg`, :meth:`.SeriesGroupBy.agg`, :meth:`.SeriesGroupBy.apply`, :meth:`.DataFrameGroupBy.apply` now support ``kurt`` (:issue:`40139`)
 - :meth:`DataFrameGroupBy.transform`, :meth:`SeriesGroupBy.transform`, :meth:`DataFrameGroupBy.agg`, :meth:`SeriesGroupBy.agg`, :meth:`RollingGroupby.apply`, :meth:`ExpandingGroupby.apply`, :meth:`Rolling.apply`, :meth:`Expanding.apply`, :meth:`DataFrame.apply` with ``engine="numba"`` now supports positional arguments passed as kwargs (:issue:`58995`)
@@ -811,6 +812,7 @@ Other
 - Bug in ``Series.list`` methods not preserving the original name. (:issue:`60522`)
 - Bug in printing a :class:`DataFrame` with a :class:`DataFrame` stored in :attr:`DataFrame.attrs` raised a ``ValueError`` (:issue:`60455`)
 - Bug in printing a :class:`Series` with a :class:`DataFrame` stored in :attr:`Series.attrs` raised a ``ValueError`` (:issue:`60568`)
+- Fixed regression in :meth:`DataFrame.from_records` not initializing subclasses properly (:issue:`57008`)
 
 .. ***DO NOT USE THIS SECTION***
 

pandas/_libs/window/aggregations.pyi

@@ -60,6 +60,18 @@ def roll_min(
     end: np.ndarray,  # np.ndarray[np.int64]
     minp: int,  # int64_t
 ) -> np.ndarray: ...  # np.ndarray[float]
+def roll_first(
+    values: np.ndarray,  # np.ndarray[np.float64]
+    start: np.ndarray,  # np.ndarray[np.int64]
+    end: np.ndarray,  # np.ndarray[np.int64]
+    minp: int,  # int64_t
+) -> np.ndarray: ...  # np.ndarray[float]
+def roll_last(
+    values: np.ndarray,  # np.ndarray[np.float64]
+    start: np.ndarray,  # np.ndarray[np.int64]
+    end: np.ndarray,  # np.ndarray[np.int64]
+    minp: int,  # int64_t
+) -> np.ndarray: ...  # np.ndarray[float]
 def roll_quantile(
     values: np.ndarray,  # const float64_t[:]
     start: np.ndarray,  # np.ndarray[np.int64]

pandas/_libs/window/aggregations.pyx

@@ -1133,6 +1133,89 @@ cdef _roll_min_max(ndarray[float64_t] values,
 
     return output
 
+# ----------------------------------------------------------------------
+# Rolling first, last
+
+
+def roll_first(const float64_t[:] values, ndarray[int64_t] start,
+               ndarray[int64_t] end, int64_t minp) -> np.ndarray:
+    return _roll_first_last(values, start, end, minp, is_first=1)
+
+
+def roll_last(const float64_t[:] values, ndarray[int64_t] start,
+              ndarray[int64_t] end, int64_t minp) -> np.ndarray:
+    return _roll_first_last(values, start, end, minp, is_first=0)
+
+
+cdef _roll_first_last(const float64_t[:] values, ndarray[int64_t] start,
+                      ndarray[int64_t] end, int64_t minp, bint is_first):
+    cdef:
+        Py_ssize_t i, j, fl_idx
+        bint is_monotonic_increasing_bounds
+        int64_t nobs = 0, N = len(start), s, e
+        float64_t val, res
+        ndarray[float64_t] output
+
+    is_monotonic_increasing_bounds = is_monotonic_increasing_start_end_bounds(
+        start, end
+    )
+
+    output = np.empty(N, dtype=np.float64)
+
+    if (end - start).max() == 0:
+        output[:] = NaN
+        return output
+
+    with nogil:
+        for i in range(0, N):
+            s = start[i]
+            e = end[i]
+
+            if i == 0 or not is_monotonic_increasing_bounds or s >= end[i - 1]:
+                fl_idx = -1
+                nobs = 0
+                for j in range(s, e):
+                    val = values[j]
+                    if val == val:
+                        if not is_first or fl_idx < s:
+                            fl_idx = j
+                        nobs += 1
+            else:
+                # handle deletes
+                for j in range(start[i - 1], s):
+                    val = values[j]
+                    if val == val:
+                        nobs -= 1
+
+                # update fl_idx if out of range, if first
+                if is_first and fl_idx < s:
+                    fl_idx = -1
+                    for j in range(s, end[i - 1]):
+                        val = values[j]
+                        if val == val:
+                            fl_idx = j
+                            break
+
+                # handle adds
+                for j in range(end[i - 1], e):
+                    val = values[j]
+                    if val == val:
+                        if not is_first or fl_idx < s:
+                            fl_idx = j
+                        nobs += 1
+
+            if nobs >= minp and fl_idx >= s:
+                res = values[fl_idx]
+            else:
+                res = NaN
+
+            output[i] = res
+
+            if not is_monotonic_increasing_bounds:
+                nobs = 0
+
+    return output
+
 
 cdef enum InterpolationType:
     LINEAR,

pandas/core/arrays/arrow/array.py

@@ -258,6 +258,7 @@ class ArrowExtensionArray(
     Parameters
     ----------
     values : pyarrow.Array or pyarrow.ChunkedArray
+        The input data to initialize the ArrowExtensionArray.
 
     Attributes
     ----------
@@ -271,6 +272,12 @@ class ArrowExtensionArray(
     -------
     ArrowExtensionArray
 
+    See Also
+    --------
+    array : Create a Pandas array with a specified dtype.
+    DataFrame.to_feather : Write a DataFrame to the binary Feather format.
+    read_feather : Load a feather-format object from the file path.
+
     Notes
     -----
     Most methods are implemented using `pyarrow compute functions. <https://arrow.apache.org/docs/python/api/compute.html>`__

pandas/core/frame.py

@@ -2317,7 +2317,10 @@ def maybe_reorder(
             columns = columns.drop(exclude)
 
         mgr = arrays_to_mgr(arrays, columns, result_index)
-        return cls._from_mgr(mgr, axes=mgr.axes)
+        df = DataFrame._from_mgr(mgr, axes=mgr.axes)
+        if cls is not DataFrame:
+            return cls(df, copy=False)
+        return df
 
     def to_records(
         self, index: bool = True, column_dtypes=None, index_dtypes=None

pandas/core/window/expanding.py

@@ -723,6 +723,78 @@ def skew(self, numeric_only: bool = False):
     def kurt(self, numeric_only: bool = False):
         return super().kurt(numeric_only=numeric_only)
 
+    @doc(
+        template_header,
+        create_section_header("Parameters"),
+        kwargs_numeric_only,
+        create_section_header("Returns"),
+        template_returns,
+        create_section_header("See Also"),
+        dedent(
+            """
+        GroupBy.first : Similar method for GroupBy objects.
+        Expanding.last : Method to get the last element in each window.\n
+        """
+        ).replace("\n", "", 1),
+        create_section_header("Examples"),
+        dedent(
+            """
+        The example below will show an expanding calculation with a window size of
+        three.
+
+        >>> s = pd.Series(range(5))
+        >>> s.expanding(3).first()
+        0         NaN
+        1         NaN
+        2         0.0
+        3         0.0
+        4         0.0
+        dtype: float64
+        """
+        ).replace("\n", "", 1),
+        window_method="expanding",
+        aggregation_description="First (left-most) element of the window",
+        agg_method="first",
+    )
+    def first(self, numeric_only: bool = False):
+        return super().first(numeric_only=numeric_only)
+
+    @doc(
+        template_header,
+        create_section_header("Parameters"),
+        kwargs_numeric_only,
+        create_section_header("Returns"),
+        template_returns,
+        create_section_header("See Also"),
+        dedent(
+            """
+        GroupBy.last : Similar method for GroupBy objects.
+        Expanding.first : Method to get the first element in each window.\n
+        """
+        ).replace("\n", "", 1),
+        create_section_header("Examples"),
+        dedent(
+            """
+        The example below will show an expanding calculation with a window size of
+        three.
+
+        >>> s = pd.Series(range(5))
+        >>> s.expanding(3).last()
+        0         NaN
+        1         NaN
+        2         2.0
+        3         3.0
+        4         4.0
+        dtype: float64
+        """
+        ).replace("\n", "", 1),
+        window_method="expanding",
+        aggregation_description="Last (right-most) element of the window",
+        agg_method="last",
+    )
+    def last(self, numeric_only: bool = False):
+        return super().last(numeric_only=numeric_only)
+
     @doc(
         template_header,
         create_section_header("Parameters"),