Merge remote-tracking branch 'upstream/main' into array-copy-false-extra-test

Author: jorisvandenbossche

doc/source/whatsnew/v2.3.0.rst

@@ -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

@@ -771,7 +771,9 @@ 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/_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/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,
@@ -757,6 +768,12 @@ 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)
                 )
             )
         ):

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/frame.py

@@ -1397,6 +1397,11 @@ def style(self) -> Styler:
         Please see
         `Table Visualization <../../user_guide/style.ipynb>`_ for more examples.
         """
+        # Raise AttributeError so that inspect works even if jinja2 is not installed.
+        has_jinja2 = import_optional_dependency("jinja2", errors="ignore")
+        if not has_jinja2:
+            raise AttributeError("The '.style' accessor requires jinja2")
+
         from pandas.io.formats.style import Styler
 
         return Styler(self)
@@ -5705,7 +5710,7 @@ def shift(
                 "Passing a 'freq' together with a 'fill_value' is not allowed."
             )
 
-        if self.empty:
+        if self.empty and freq is None:
             return self.copy()
 
         axis = self._get_axis_number(axis)