DOC: resolve merge conflict

Author: aBiR1D

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.__dataframe__ SA01" \
-        -i "pandas.DataFrame.at_time PR01" \
-        -i "pandas.DataFrame.kurt RT03,SA01" \
-        -i "pandas.DataFrame.kurtosis RT03,SA01" \
         -i "pandas.DataFrame.max RT03" \
         -i "pandas.DataFrame.mean RT03,SA01" \
         -i "pandas.DataFrame.median RT03,SA01" \
@@ -92,23 +88,15 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Grouper PR02" \
         -i "pandas.Index.append PR07,RT03,SA01" \
         -i "pandas.Index.difference PR07,RT03,SA01" \
-        -i "pandas.Index.duplicated RT03" \
         -i "pandas.Index.get_indexer PR07,SA01" \
         -i "pandas.Index.get_indexer_for PR01,SA01" \
         -i "pandas.Index.get_indexer_non_unique PR07,SA01" \
         -i "pandas.Index.get_loc PR07,RT03,SA01" \
-        -i "pandas.Index.identical PR01,SA01" \
         -i "pandas.Index.join PR07,RT03,SA01" \
         -i "pandas.Index.names GL08" \
-        -i "pandas.Index.nunique RT03" \
         -i "pandas.Index.putmask PR01,RT03" \
         -i "pandas.Index.ravel PR01,RT03" \
-        -i "pandas.Index.slice_indexer PR07,RT03,SA01" \
         -i "pandas.Index.str PR01,SA01" \
-        -i "pandas.Index.symmetric_difference PR07,RT03,SA01" \
-        -i "pandas.Index.take PR01,PR07" \
-        -i "pandas.Index.union PR07,RT03,SA01" \
-        -i "pandas.Index.view GL08" \
         -i "pandas.Int16Dtype SA01" \
         -i "pandas.Int32Dtype SA01" \
         -i "pandas.Int64Dtype SA01" \
@@ -197,7 +185,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series SA01" \
         -i "pandas.Series.__iter__ RT03,SA01" \
         -i "pandas.Series.add PR07" \
-        -i "pandas.Series.at_time PR01" \
         -i "pandas.Series.backfill PR01,SA01" \
         -i "pandas.Series.case_when RT03" \
         -i "pandas.Series.cat PR07,SA01" \
@@ -257,7 +244,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.mode SA01" \
         -i "pandas.Series.mul PR07" \
         -i "pandas.Series.ne PR07,SA01" \
-        -i "pandas.Series.nunique RT03" \
         -i "pandas.Series.pad PR01,SA01" \
         -i "pandas.Series.plot PR02,SA01" \
         -i "pandas.Series.pop RT03,SA01" \

doc/source/whatsnew/v3.0.0.rst

@@ -39,6 +39,7 @@ Other enhancements
 - Users can globally disable any ``PerformanceWarning`` by setting the option ``mode.performance_warnings`` to ``False`` (:issue:`56920`)
 - :meth:`Styler.format_index_names` can now be used to format the index and column names (:issue:`48936` and :issue:`47489`)
 - :class:`.errors.DtypeWarning` improved to include column names when mixed data types are detected (:issue:`58174`)
+- :meth:`DataFrame.corrwith` now accepts ``min_periods`` as optional arguments, as in :meth:`DataFrame.corr` and :meth:`Series.corr` (:issue:`9490`)
 - :meth:`DataFrame.cummin`, :meth:`DataFrame.cummax`, :meth:`DataFrame.cumprod` and :meth:`DataFrame.cumsum` methods now have a ``numeric_only`` parameter (:issue:`53072`)
 - :meth:`DataFrame.fillna` and :meth:`Series.fillna` can now accept ``value=None``; for non-object dtype the corresponding NA value will be used (:issue:`57723`)
 - :meth:`Series.cummin` and :meth:`Series.cummax` now supports :class:`CategoricalDtype` (:issue:`52335`)
@@ -221,6 +222,7 @@ Removal of prior version deprecations/changes
 - :meth:`SeriesGroupBy.agg` no longer pins the name of the group to the input passed to the provided ``func`` (:issue:`51703`)
 - All arguments except ``name`` in :meth:`Index.rename` are now keyword only (:issue:`56493`)
 - All arguments except the first ``path``-like argument in IO writers are now keyword only (:issue:`54229`)
+- Changed behavior of :meth:`Series.__getitem__` and :meth:`Series.__setitem__` to always treat integer keys as labels, never as positional, consistent with :class:`DataFrame` behavior (:issue:`50617`)
 - Disallow allowing logical operations (``||``, ``&``, ``^``) between pandas objects and dtype-less sequences (e.g. ``list``, ``tuple``); wrap the objects in :class:`Series`, :class:`Index`, or ``np.array`` first instead (:issue:`52264`)
 - Disallow automatic casting to object in :class:`Series` logical operations (``&``, ``^``, ``||``) between series with mismatched indexes and dtypes other than ``object`` or ``bool`` (:issue:`52538`)
 - Disallow calling :meth:`Series.replace` or :meth:`DataFrame.replace` without a ``value`` and with non-dict-like ``to_replace`` (:issue:`33302`)
@@ -334,6 +336,7 @@ Performance improvements
 - Performance improvement in :meth:`Index.join` by propagating cached attributes in cases where the result matches one of the inputs (:issue:`57023`)
 - Performance improvement in :meth:`Index.take` when ``indices`` is a full range indexer from zero to length of index (:issue:`56806`)
 - Performance improvement in :meth:`Index.to_frame` returning a :class:`RangeIndex` columns of a :class:`Index` when possible. (:issue:`58018`)
+- Performance improvement in :meth:`MultiIndex._engine` to use smaller dtypes if possible (:issue:`58411`)
 - Performance improvement in :meth:`MultiIndex.equals` for equal length indexes (:issue:`56990`)
 - Performance improvement in :meth:`MultiIndex.memory_usage` to ignore the index engine when it isn't already cached. (:issue:`58385`)
 - Performance improvement in :meth:`RangeIndex.__getitem__` with a boolean mask or integers returning a :class:`RangeIndex` instead of a :class:`Index` when possible. (:issue:`57588`)
@@ -389,6 +392,7 @@ Numeric
 
 Conversion
 ^^^^^^^^^^
+- Bug in :meth:`DataFrame.astype` not casting ``values`` for Arrow-based dictionary dtype correctly (:issue:`58479`)
 - Bug in :meth:`DataFrame.update` bool dtype being converted to object (:issue:`55509`)
 - Bug in :meth:`Series.astype` might modify read-only array inplace when casting to a string dtype (:issue:`57212`)
 - Bug in :meth:`Series.reindex` not maintaining ``float32`` type when a ``reindex`` introduces a missing value (:issue:`45857`)
@@ -469,6 +473,7 @@ Styler
 Other
 ^^^^^
 - Bug in :class:`DataFrame` when passing a ``dict`` with a NA scalar and ``columns`` that would always return ``np.nan`` (:issue:`57205`)
+- Bug in :func:`eval` where the names of the :class:`Series` were not preserved when using ``engine="numexpr"``. (:issue:`10239`)
 - Bug in :func:`unique` on :class:`Index` not always returning :class:`Index` (:issue:`57043`)
 - Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which caused an exception when using NumPy attributes via ``@`` notation, e.g., ``df.eval("@np.floor(a)")``. (:issue:`58041`)
 - Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which did not allow to use ``tan`` function. (:issue:`55091`)
@@ -480,6 +485,7 @@ Other
 - Bug in :meth:`Series.rank` that doesn't preserve missing values for nullable integers when ``na_option='keep'``. (:issue:`56976`)
 - Bug in :meth:`Series.replace` and :meth:`DataFrame.replace` inconsistently replacing matching instances when ``regex=True`` and missing values are present. (:issue:`56599`)
 - Bug in Dataframe Interchange Protocol implementation was returning incorrect results for data buffers' associated dtype, for string and datetime columns (:issue:`54781`)
+- Bug in ``Series.list`` methods not preserving the original :class:`Index`. (:issue:`58425`)
 
 .. ***DO NOT USE THIS SECTION***
 

pandas/_libs/index.pyi

@@ -74,13 +74,13 @@ class MaskedBoolEngine(MaskedUInt8Engine): ...
 
 class BaseMultiIndexCodesEngine:
     levels: list[np.ndarray]
-    offsets: np.ndarray  # ndarray[uint64_t, ndim=1]
+    offsets: np.ndarray  # np.ndarray[..., ndim=1]
 
     def __init__(
         self,
         levels: list[Index],  # all entries hashable
         labels: list[np.ndarray],  # all entries integer-dtyped
-        offsets: np.ndarray,  # np.ndarray[np.uint64, ndim=1]
+        offsets: np.ndarray,  # np.ndarray[..., ndim=1]
     ) -> None: ...
     def get_indexer(self, target: npt.NDArray[np.object_]) -> npt.NDArray[np.intp]: ...
     def _extract_level_codes(self, target: MultiIndex) -> np.ndarray: ...

pandas/_libs/index.pyx

@@ -9,7 +9,6 @@ from numpy cimport (
     intp_t,
     ndarray,
     uint8_t,
-    uint64_t,
 )
 
 cnp.import_array()
@@ -699,16 +698,15 @@ cdef class BaseMultiIndexCodesEngine:
     Keys are located by first locating each component against the respective
     level, then locating (the integer representation of) codes.
     """
-    def __init__(self, object levels, object labels,
-                 ndarray[uint64_t, ndim=1] offsets):
+    def __init__(self, object levels, object labels, ndarray offsets):
         """
         Parameters
         ----------
         levels : list-like of numpy arrays
             Levels of the MultiIndex.
         labels : list-like of numpy arrays of integer dtype
             Labels of the MultiIndex.
-        offsets : numpy array of uint64 dtype
+        offsets : numpy array of int dtype
             Pre-calculated offsets, one for each level of the index.
         """
         self.levels = levels
@@ -718,8 +716,9 @@ cdef class BaseMultiIndexCodesEngine:
         # with positive integers (-1 for NaN becomes 1). This enables us to
         # differentiate between values that are missing in other and matching
         # NaNs. We will set values that are not found to 0 later:
-        labels_arr = np.array(labels, dtype="int64").T + multiindex_nulls_shift
-        codes = labels_arr.astype("uint64", copy=False)
+        codes = np.array(labels).T
+        codes += multiindex_nulls_shift  # inplace sum optimisation
+
         self.level_has_nans = [-1 in lab for lab in labels]
 
         # Map each codes combination in the index to an integer unambiguously
@@ -731,8 +730,37 @@ cdef class BaseMultiIndexCodesEngine:
         # integers representing labels: we will use its get_loc and get_indexer
         self._base.__init__(self, lab_ints)
 
-    def _codes_to_ints(self, ndarray[uint64_t] codes) -> np.ndarray:
-        raise NotImplementedError("Implemented by subclass")  # pragma: no cover
+    def _codes_to_ints(self, ndarray codes) -> np.ndarray:
+        """
+        Transform combination(s) of uint in one uint or Python integer (each), in a
+        strictly monotonic way (i.e. respecting the lexicographic order of integer
+        combinations).
+
+        Parameters
+        ----------
+        codes : 1- or 2-dimensional array of dtype uint
+            Combinations of integers (one per row)
+
+        Returns
+        -------
+        scalar or 1-dimensional array, of dtype _codes_dtype
+            Integer(s) representing one combination (each).
+        """
+        # To avoid overflows, first make sure we are working with the right dtype:
+        codes = codes.astype(self._codes_dtype, copy=False)
+
+        # Shift the representation of each level by the pre-calculated number of bits:
+        codes <<= self.offsets  # inplace shift optimisation
+
+        # Now sum and OR are in fact interchangeable. This is a simple
+        # composition of the (disjunct) significant bits of each level (i.e.
+        # each column in "codes") in a single positive integer (per row):
+        if codes.ndim == 1:
+            # Single key
+            return np.bitwise_or.reduce(codes)
+
+        # Multiple keys
+        return np.bitwise_or.reduce(codes, axis=1)
 
     def _extract_level_codes(self, target) -> np.ndarray:
         """
@@ -757,7 +785,7 @@ cdef class BaseMultiIndexCodesEngine:
             codes[codes > 0] += 1
             if self.level_has_nans[i]:
                 codes[target.codes[i] == -1] += 1
-        return self._codes_to_ints(np.array(level_codes, dtype="uint64").T)
+        return self._codes_to_ints(np.array(level_codes, dtype=self._codes_dtype).T)
 
     def get_indexer(self, target: np.ndarray) -> np.ndarray:
         """
@@ -788,7 +816,7 @@ cdef class BaseMultiIndexCodesEngine:
             raise KeyError(key)
 
         # Transform indices into single integer:
-        lab_int = self._codes_to_ints(np.array(indices, dtype="uint64"))
+        lab_int = self._codes_to_ints(np.array(indices, dtype=self._codes_dtype))
 
         return self._base.get_loc(self, lab_int)
 

pandas/core/arrays/arrow/accessors.py

@@ -110,7 +110,9 @@ def len(self) -> Series:
         from pandas import Series
 
         value_lengths = pc.list_value_length(self._pa_array)
-        return Series(value_lengths, dtype=ArrowDtype(value_lengths.type))
+        return Series(
+            value_lengths, dtype=ArrowDtype(value_lengths.type), index=self._data.index
+        )
 
     def __getitem__(self, key: int | slice) -> Series:
         """
@@ -149,7 +151,9 @@ def __getitem__(self, key: int | slice) -> Series:
             # if key < 0:
             #     key = pc.add(key, pc.list_value_length(self._pa_array))
             element = pc.list_element(self._pa_array, key)
-            return Series(element, dtype=ArrowDtype(element.type))
+            return Series(
+                element, dtype=ArrowDtype(element.type), index=self._data.index
+            )
         elif isinstance(key, slice):
             if pa_version_under11p0:
                 raise NotImplementedError(
@@ -167,7 +171,7 @@ def __getitem__(self, key: int | slice) -> Series:
             if step is None:
                 step = 1
             sliced = pc.list_slice(self._pa_array, start, stop, step)
-            return Series(sliced, dtype=ArrowDtype(sliced.type))
+            return Series(sliced, dtype=ArrowDtype(sliced.type), index=self._data.index)
         else:
             raise ValueError(f"key must be an int or slice, got {type(key).__name__}")
 
@@ -195,15 +199,17 @@ def flatten(self) -> Series:
         ... )
         >>> s.list.flatten()
         0    1
-        1    2
-        2    3
-        3    3
+        0    2
+        0    3
+        1    3
         dtype: int64[pyarrow]
         """
         from pandas import Series
 
-        flattened = pc.list_flatten(self._pa_array)
-        return Series(flattened, dtype=ArrowDtype(flattened.type))
+        counts = pa.compute.list_value_length(self._pa_array)
+        flattened = pa.compute.list_flatten(self._pa_array)
+        index = self._data.index.repeat(counts.fill_null(pa.scalar(0, counts.type)))
+        return Series(flattened, dtype=ArrowDtype(flattened.type), index=index)
 
 
 class StructAccessor(ArrowAccessor):

pandas/core/arrays/arrow/array.py

@@ -525,6 +525,8 @@ def _box_pa_array(
         if pa_type is not None and pa_array.type != pa_type:
             if pa.types.is_dictionary(pa_type):
                 pa_array = pa_array.dictionary_encode()
+                if pa_array.type != pa_type:
+                    pa_array = pa_array.cast(pa_type)
             else:
                 try:
                     pa_array = pa_array.cast(pa_type)

pandas/core/base.py

@@ -1062,6 +1062,7 @@ def nunique(self, dropna: bool = True) -> int:
         Returns
         -------
         int
+            A integer indicating the number of unique elements in the object.
 
         See Also
         --------

pandas/core/computation/align.py

@@ -160,19 +160,24 @@ def align_terms(terms):
         # can't iterate so it must just be a constant or single variable
         if isinstance(terms.value, (ABCSeries, ABCDataFrame)):
             typ = type(terms.value)
-            return typ, _zip_axes_from_type(typ, terms.value.axes)
-        return np.result_type(terms.type), None
+            name = terms.value.name if isinstance(terms.value, ABCSeries) else None
+            return typ, _zip_axes_from_type(typ, terms.value.axes), name
+        return np.result_type(terms.type), None, None
 
     # if all resolved variables are numeric scalars
     if all(term.is_scalar for term in terms):
-        return result_type_many(*(term.value for term in terms)).type, None
+        return result_type_many(*(term.value for term in terms)).type, None, None
+
+    # if all input series have a common name, propagate it to the returned series
+    names = {term.value.name for term in terms if isinstance(term.value, ABCSeries)}
+    name = names.pop() if len(names) == 1 else None
 
     # perform the main alignment
     typ, axes = _align_core(terms)
-    return typ, axes
+    return typ, axes, name
 
 
-def reconstruct_object(typ, obj, axes, dtype):
+def reconstruct_object(typ, obj, axes, dtype, name):
     """
     Reconstruct an object given its type, raw value, and possibly empty
     (None) axes.
@@ -200,7 +205,9 @@ def reconstruct_object(typ, obj, axes, dtype):
     res_t = np.result_type(obj.dtype, dtype)
 
     if not isinstance(typ, partial) and issubclass(typ, PandasObject):
-        return typ(obj, dtype=res_t, **axes)
+        if name is None:
+            return typ(obj, dtype=res_t, **axes)
+        return typ(obj, dtype=res_t, name=name, **axes)
 
     # special case for pathological things like ~True/~False
     if hasattr(res_t, "type") and typ == np.bool_ and res_t != np.bool_:

pandas/core/computation/engines.py

@@ -54,6 +54,7 @@ def __init__(self, expr) -> None:
         self.expr = expr
         self.aligned_axes = None
         self.result_type = None
+        self.result_name = None
 
     def convert(self) -> str:
         """
@@ -76,12 +77,18 @@ def evaluate(self) -> object:
             The result of the passed expression.
         """
         if not self._is_aligned:
-            self.result_type, self.aligned_axes = align_terms(self.expr.terms)
+            self.result_type, self.aligned_axes, self.result_name = align_terms(
+                self.expr.terms
+            )
 
         # make sure no names in resolvers and locals/globals clash
         res = self._evaluate()
         return reconstruct_object(
-            self.result_type, res, self.aligned_axes, self.expr.terms.return_type
+            self.result_type,
+            res,
+            self.aligned_axes,
+            self.expr.terms.return_type,
+            self.result_name,
         )
 
     @property