Merge remote-tracking branch 'upstream/main' into issue-60099

Author: ZKaoChi

doc/source/whatsnew/v2.3.0.rst

@@ -133,7 +133,7 @@ MultiIndex
 
 I/O
 ^^^
--
+- :meth:`DataFrame.to_excel` was storing decimals as strings instead of numbers (:issue:`49598`)
 -
 
 Period
@@ -173,7 +173,8 @@ Styler
 
 Other
 ^^^^^
--
+- Fixed usage of ``inspect`` when the optional dependencies ``pyarrow`` or ``jinja2``
+  are not installed (:issue:`60196`)
 -
 
 .. ---------------------------------------------------------------------------

doc/source/whatsnew/v3.0.0.rst

@@ -613,6 +613,7 @@ Categorical
 Datetimelike
 ^^^^^^^^^^^^
 - Bug in :attr:`is_year_start` where a DateTimeIndex constructed via a date_range with frequency 'MS' wouldn't have the correct year or quarter start attributes (:issue:`57377`)
+- Bug in :class:`DataFrame` raising ``ValueError`` when ``dtype`` is ``timedelta64`` and ``data`` is a list containing ``None`` (:issue:`60064`)
 - Bug in :class:`Timestamp` constructor failing to raise when ``tz=None`` is explicitly specified in conjunction with timezone-aware ``tzinfo`` or data (:issue:`48688`)
 - Bug in :func:`date_range` where the last valid timestamp would sometimes not be produced (:issue:`56134`)
 - Bug in :func:`date_range` where using a negative frequency value would not include all points between the start and end values (:issue:`56147`)
@@ -710,6 +711,7 @@ Period
 Plotting
 ^^^^^^^^
 - Bug in :meth:`.DataFrameGroupBy.boxplot` failed when there were multiple groupings (:issue:`14701`)
+- Bug in :meth:`DataFrame.plot.bar` with ``stacked=True`` where labels on stacked bars with zero-height segments were incorrectly positioned at the base instead of the label position of the previous segment (:issue:`59429`)
 - Bug in :meth:`DataFrame.plot.line` raising ``ValueError`` when set both color and a ``dict`` style (:issue:`59461`)
 - Bug in :meth:`DataFrame.plot` that causes a shift to the right when the frequency multiplier is greater than one. (:issue:`57587`)
 - Bug in :meth:`Series.plot` with ``kind="pie"`` with :class:`ArrowDtype` (:issue:`59192`)
@@ -771,7 +773,9 @@ Other
 - Bug in :meth:`DataFrame.apply` where passing ``engine="numba"`` ignored ``args`` passed to the applied function (:issue:`58712`)
 - 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`)
+- Bug in :meth:`DataFrame.query` where using duplicate column names led to a ``TypeError``. (:issue:`59950`)
 - Bug in :meth:`DataFrame.query` which raised an exception or produced incorrect results when expressions contained backtick-quoted column names containing the hash character ``#``, backticks, or characters that fall outside the ASCII range (U+0001..U+007F). (:issue:`59285`) (:issue:`49633`)
+- Bug in :meth:`DataFrame.shift` where passing a ``freq`` on a DataFrame with no columns did not shift the index correctly. (:issue:`60102`)
 - Bug in :meth:`DataFrame.sort_index` when passing ``axis="columns"`` and ``ignore_index=True`` and ``ascending=False`` not returning a :class:`RangeIndex` columns (:issue:`57293`)
 - Bug in :meth:`DataFrame.transform` that was returning the wrong order unless the index was monotonically increasing. (:issue:`57069`)
 - Bug in :meth:`DataFrame.where` where using a non-bool type array in the function would return a ``ValueError`` instead of a ``TypeError`` (:issue:`56330`)

pandas/_libs/tslibs/period.pyx

@@ -114,6 +114,7 @@ from pandas._libs.tslibs.offsets import (
     INVALID_FREQ_ERR_MSG,
     BDay,
 )
+from pandas.util._decorators import set_module
 
 cdef:
     enum:
@@ -2830,6 +2831,7 @@ cdef class _Period(PeriodMixin):
         return period_format(self.ordinal, base, fmt)
 
 
+@set_module("pandas")
 class Period(_Period):
     """
     Represents a period of time.

pandas/_libs/tslibs/timedeltas.pyx

@@ -1,6 +1,7 @@
 import collections
 import warnings
 
+from pandas.util._decorators import set_module
 from pandas.util._exceptions import find_stack_level
 
 cimport cython
@@ -1854,7 +1855,7 @@ cdef class _Timedelta(timedelta):
 
 # Python front end to C extension type _Timedelta
 # This serves as the box for timedelta64
-
+@set_module("pandas")
 class Timedelta(_Timedelta):
     """
     Represents a duration, the difference between two dates or times.
@@ -1916,7 +1917,7 @@ class Timedelta(_Timedelta):
     --------
     Here we initialize Timedelta object with both value and unit
 
-    >>> td = pd.Timedelta(1, "d")
+    >>> td = pd.Timedelta(1, "D")
     >>> td
     Timedelta('1 days 00:00:00')
 

pandas/_libs/tslibs/timestamps.pyx

@@ -50,6 +50,7 @@ import datetime as dt
 from pandas._libs.tslibs cimport ccalendar
 from pandas._libs.tslibs.base cimport ABCTimestamp
 
+from pandas.util._decorators import set_module
 from pandas.util._exceptions import find_stack_level
 
 from pandas._libs.tslibs.conversion cimport (
@@ -1648,7 +1649,7 @@ cdef class _Timestamp(ABCTimestamp):
 # Python front end to C extension type _Timestamp
 # This serves as the box for datetime64
 
-
+@set_module("pandas")
 class Timestamp(_Timestamp):
     """
     Pandas replacement for python datetime.datetime object.
@@ -2926,7 +2927,7 @@ timedelta}, default 'raise'
         --------
         >>> ts = pd.Timestamp(1584226800, unit='s', tz='Europe/Stockholm')
         >>> ts.tz
-        <DstTzInfo 'Europe/Stockholm' CET+1:00:00 STD>
+        zoneinfo.ZoneInfo(key='Europe/Stockholm')
         """
         return self.tzinfo
 

pandas/_testing/__init__.py

@@ -501,6 +501,8 @@ def shares_memory(left, right) -> bool:
     if isinstance(left, MultiIndex):
         return shares_memory(left._codes, right)
     if isinstance(left, (Index, Series)):
+        if isinstance(right, (Index, Series)):
+            return shares_memory(left._values, right._values)
         return shares_memory(left._values, right)
 
     if isinstance(left, NDArrayBackedExtensionArray):

pandas/conftest.py

@@ -600,7 +600,7 @@ def multiindex_year_month_day_dataframe_random_data():
     """
     tdf = DataFrame(
         np.random.default_rng(2).standard_normal((100, 4)),
-        columns=Index(list("ABCD"), dtype=object),
+        columns=Index(list("ABCD")),
         index=date_range("2000-01-01", periods=100, freq="B"),
     )
     ymd = tdf.groupby([lambda x: x.year, lambda x: x.month, lambda x: x.day]).sum()
@@ -787,7 +787,7 @@ def string_series() -> Series:
     """
     return Series(
         np.arange(30, dtype=np.float64) * 1.1,
-        index=Index([f"i_{i}" for i in range(30)], dtype=object),
+        index=Index([f"i_{i}" for i in range(30)]),
         name="series",
     )
 
@@ -798,7 +798,7 @@ def object_series() -> Series:
     Fixture for Series of dtype object with Index of unique strings
     """
     data = [f"foo_{i}" for i in range(30)]
-    index = Index([f"bar_{i}" for i in range(30)], dtype=object)
+    index = Index([f"bar_{i}" for i in range(30)])
     return Series(data, index=index, name="objects", dtype=object)
 
 
@@ -890,8 +890,8 @@ def int_frame() -> DataFrame:
     """
     return DataFrame(
         np.ones((30, 4), dtype=np.int64),
-        index=Index([f"foo_{i}" for i in range(30)], dtype=object),
-        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"foo_{i}" for i in range(30)]),
+        columns=Index(list("ABCD")),
     )
 
 

pandas/core/arrays/arrow/accessors.py

@@ -46,7 +46,7 @@ def _is_valid_pyarrow_dtype(self, pyarrow_dtype) -> bool:
 
     def _validate(self, data) -> None:
         dtype = data.dtype
-        if not isinstance(dtype, ArrowDtype):
+        if pa_version_under10p1 or not isinstance(dtype, ArrowDtype):
             # Raise AttributeError so that inspect can handle non-struct Series.
             raise AttributeError(self._validation_msg.format(dtype=dtype))
 

pandas/core/arrays/arrow/array.py

@@ -1145,7 +1145,7 @@ def fillna(
         try:
             fill_value = self._box_pa(value, pa_type=self._pa_array.type)
         except pa.ArrowTypeError as err:
-            msg = f"Invalid value '{value!s}' for dtype {self.dtype}"
+            msg = f"Invalid value '{value!s}' for dtype '{self.dtype}'"
             raise TypeError(msg) from err
 
         try:
@@ -2136,7 +2136,7 @@ def _maybe_convert_setitem_value(self, value):
         try:
             value = self._box_pa(value, self._pa_array.type)
         except pa.ArrowTypeError as err:
-            msg = f"Invalid value '{value!s}' for dtype {self.dtype}"
+            msg = f"Invalid value '{value!s}' for dtype '{self.dtype}'"
             raise TypeError(msg) from err
         return value
 

pandas/core/arrays/masked.py

@@ -286,7 +286,7 @@ def _validate_setitem_value(self, value):
 
         # Note: without the "str" here, the f-string rendering raises in
         #  py38 builds.
-        raise TypeError(f"Invalid value '{value!s}' for dtype {self.dtype}")
+        raise TypeError(f"Invalid value '{value!s}' for dtype '{self.dtype}'")
 
     def __setitem__(self, key, value) -> None:
         key = check_array_indexer(self, key)

pandas/core/arrays/string_.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from functools import partial
 import operator
 from typing import (
     TYPE_CHECKING,
@@ -64,6 +65,8 @@
 from pandas.core.indexers import check_array_indexer
 from pandas.core.missing import isna
 
+from pandas.io.formats import printing
+
 if TYPE_CHECKING:
     import pyarrow
 
@@ -391,6 +394,14 @@ def _from_scalars(cls, scalars, dtype: DtypeObj) -> Self:
             raise ValueError
         return cls._from_sequence(scalars, dtype=dtype)
 
+    def _formatter(self, boxed: bool = False):
+        formatter = partial(
+            printing.pprint_thing,
+            escape_chars=("\t", "\r", "\n"),
+            quote_strings=not boxed,
+        )
+        return formatter
+
     def _str_map(
         self,
         f,
@@ -641,7 +652,8 @@ def _validate_scalar(self, value):
             return self.dtype.na_value
         elif not isinstance(value, str):
             raise TypeError(
-                f"Cannot set non-string value '{value}' into a string array."
+                f"Invalid value '{value}' for dtype '{self.dtype}'. Value should be a "
+                f"string or missing value, got '{type(value).__name__}' instead."
             )
         return value
 
@@ -732,7 +744,9 @@ def __setitem__(self, key, value) -> None:
                 value = self.dtype.na_value
             elif not isinstance(value, str):
                 raise TypeError(
-                    f"Cannot set non-string value '{value}' into a StringArray."
+                    f"Invalid value '{value}' for dtype '{self.dtype}'. Value should "
+                    f"be a string or missing value, got '{type(value).__name__}' "
+                    "instead."
                 )
         else:
             if not is_array_like(value):
@@ -742,7 +756,10 @@ def __setitem__(self, key, value) -> None:
                 # compatible, compatibility with arrow backed strings
                 value = np.asarray(value)
             if len(value) and not lib.is_string_array(value, skipna=True):
-                raise TypeError("Must provide strings.")
+                raise TypeError(
+                    "Invalid value for dtype 'str'. Value should be a "
+                    "string or missing value (or array of those)."
+                )
 
             mask = isna(value)
             if mask.any():
@@ -757,6 +774,12 @@ def _putmask(self, mask: npt.NDArray[np.bool_], value) -> None:
         # base class implementation that uses __setitem__
         ExtensionArray._putmask(self, mask, value)
 
+    def _where(self, mask: npt.NDArray[np.bool_], value) -> Self:
+        # the super() method NDArrayBackedExtensionArray._where uses
+        # np.putmask which doesn't properly handle None/pd.NA, so using the
+        # base class implementation that uses __setitem__
+        return ExtensionArray._where(self, mask, value)
+
     def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:
         if isinstance(values, BaseStringArray) or (
             isinstance(values, ExtensionArray) and is_string_dtype(values.dtype)

pandas/core/arrays/string_arrow.py

@@ -17,6 +17,7 @@
 from pandas.compat import (
     pa_version_under10p1,
     pa_version_under13p0,
+    pa_version_under16p0,
 )
 from pandas.util._exceptions import find_stack_level
 
@@ -71,6 +72,10 @@ def _chk_pyarrow_available() -> None:
         raise ImportError(msg)
 
 
+def _is_string_view(typ):
+    return not pa_version_under16p0 and pa.types.is_string_view(typ)
+
+
 # TODO: Inherit directly from BaseStringArrayMethods. Currently we inherit from
 # ObjectStringArrayMixin because we want to have the object-dtype based methods as
 # fallback for the ones that pyarrow doesn't yet support
@@ -128,11 +133,13 @@ def __init__(self, values) -> None:
         _chk_pyarrow_available()
         if isinstance(values, (pa.Array, pa.ChunkedArray)) and (
             pa.types.is_string(values.type)
+            or _is_string_view(values.type)
             or (
                 pa.types.is_dictionary(values.type)
                 and (
                     pa.types.is_string(values.type.value_type)
                     or pa.types.is_large_string(values.type.value_type)
+                    or _is_string_view(values.type.value_type)
                 )
             )
         ):
@@ -216,7 +223,10 @@ def insert(self, loc: int, item) -> ArrowStringArray:
         if self.dtype.na_value is np.nan and item is np.nan:
             item = libmissing.NA
         if not isinstance(item, str) and item is not libmissing.NA:
-            raise TypeError("Scalar must be NA or str")
+            raise TypeError(
+                f"Invalid value '{item}' for dtype 'str'. Value should be a "
+                f"string or missing value, got '{type(item).__name__}' instead."
+            )
         return super().insert(loc, item)
 
     def _convert_bool_result(self, values, na=lib.no_default, method_name=None):
@@ -248,13 +258,19 @@ def _maybe_convert_setitem_value(self, value):
             if isna(value):
                 value = None
             elif not isinstance(value, str):
-                raise TypeError("Scalar must be NA or str")
+                raise TypeError(
+                    f"Invalid value '{value}' for dtype 'str'. Value should be a "
+                    f"string or missing value, got '{type(value).__name__}' instead."
+                )
         else:
             value = np.array(value, dtype=object, copy=True)
             value[isna(value)] = None
             for v in value:
                 if not (v is None or isinstance(v, str)):
-                    raise TypeError("Must provide strings")
+                    raise TypeError(
+                        "Invalid value for dtype 'str'. Value should be a "
+                        "string or missing value (or array of those)."
+                    )
         return super()._maybe_convert_setitem_value(value)
 
     def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:

pandas/core/base.py

@@ -361,8 +361,11 @@ def __len__(self) -> int:
         # We need this defined here for mypy
         raise AbstractMethodError(self)
 
+    # Temporarily avoid using `-> Literal[1]:` because of an IPython (jedi) bug
+    # https://github.com/ipython/ipython/issues/14412
+    # https://github.com/davidhalter/jedi/issues/1990
     @property
-    def ndim(self) -> Literal[1]:
+    def ndim(self) -> int:
         """
         Number of dimensions of the underlying data, by definition 1.
 

pandas/core/config_init.py

@@ -100,7 +100,10 @@ def use_numba_cb(key: str) -> None:
 : int
     If max_rows is exceeded, switch to truncate view. Depending on
     `large_repr`, objects are either centrally truncated or printed as
-    a summary view. 'None' value means unlimited.
+    a summary view.
+
+    'None' value means unlimited. Beware that printing a large number of rows
+    could cause your rendering environment (the browser, etc.) to crash.
 
     In case python/IPython is running in a terminal and `large_repr`
     equals 'truncate' this can be set to 0 and pandas will auto-detect
@@ -121,7 +124,11 @@ def use_numba_cb(key: str) -> None:
 : int
     If max_cols is exceeded, switch to truncate view. Depending on
     `large_repr`, objects are either centrally truncated or printed as
-    a summary view. 'None' value means unlimited.
+    a summary view.
+
+    'None' value means unlimited. Beware that printing a large number of
+    columns could cause your rendering environment (the browser, etc.) to
+    crash.
 
     In case python/IPython is running in a terminal and `large_repr`
     equals 'truncate' this can be set to 0 or None and pandas will auto-detect

pandas/core/construction.py

@@ -807,6 +807,12 @@ def _try_cast(
         )
 
     elif dtype.kind in "mM":
+        if is_ndarray:
+            arr = cast(np.ndarray, arr)
+            if arr.ndim == 2 and arr.shape[1] == 1:
+                # GH#60081: DataFrame Constructor converts 1D data to array of
+                # shape (N, 1), but maybe_cast_to_datetime assumes 1D input
+                return maybe_cast_to_datetime(arr[:, 0], dtype).reshape(arr.shape)
         return maybe_cast_to_datetime(arr, dtype)
 
     # GH#15832: Check if we are requesting a numeric dtype and

pandas/core/dtypes/cast.py

@@ -1205,7 +1205,7 @@ def maybe_infer_to_datetimelike(
 
 def maybe_cast_to_datetime(
     value: np.ndarray | list, dtype: np.dtype
-) -> ExtensionArray | np.ndarray:
+) -> DatetimeArray | TimedeltaArray | np.ndarray:
     """
     try to cast the array/value to a datetimelike dtype, converting float
     nan to iNaT