Merge remote-tracking branch 'upstream/main' into cln/tests/plotting2

Author: mroeschke

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.3
+    rev: v0.4.7
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -40,7 +40,7 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.3.0
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown, cython, c]
@@ -92,7 +92,7 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v18.1.4
+    rev: v18.1.5
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

ci/code_checks.sh

@@ -470,24 +470,16 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.merge PR07" \
         -i "pandas.merge_asof PR07,RT03" \
         -i "pandas.merge_ordered PR07" \
-        -i "pandas.option_context SA01" \
         -i "pandas.period_range RT03,SA01" \
         -i "pandas.pivot PR07" \
         -i "pandas.pivot_table PR07" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
-        -i "pandas.plotting.autocorrelation_plot RT03,SA01" \
         -i "pandas.plotting.lag_plot RT03,SA01" \
-        -i "pandas.plotting.parallel_coordinates PR07,RT03,SA01" \
         -i "pandas.plotting.scatter_matrix PR07,SA01" \
-        -i "pandas.plotting.table PR07,RT03,SA01" \
         -i "pandas.qcut PR07,SA01" \
-        -i "pandas.read_orc SA01" \
         -i "pandas.read_spss SA01" \
-        -i "pandas.reset_option SA01" \
         -i "pandas.set_eng_float_format RT03,SA01" \
-        -i "pandas.show_versions SA01" \
         -i "pandas.testing.assert_extension_array_equal SA01" \
-        -i "pandas.testing.assert_series_equal PR07,SA01" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
         -i "pandas.tseries.offsets.BQuarterBegin PR02" \
         -i "pandas.tseries.offsets.BQuarterBegin.freqstr SA01" \
@@ -779,7 +771,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.YearEnd.nanos GL08" \
         -i "pandas.tseries.offsets.YearEnd.normalize GL08" \
         -i "pandas.tseries.offsets.YearEnd.rule_code GL08" \
-        -i "pandas.unique PR07" \
         -i "pandas.util.hash_pandas_object PR07,SA01" # There should be no backslash in the final line, please keep this comment in the last ignored function
 
     RET=$(($RET + $?)) ; echo $MSG "DONE"

doc/source/user_guide/missing_data.rst

@@ -337,10 +337,8 @@ When taking the product, NA values or empty data will be treated as 1.
    pd.Series([], dtype="float64").prod()
 
 Cumulative methods like :meth:`~DataFrame.cumsum` and :meth:`~DataFrame.cumprod`
-ignore NA values by default preserve them in the result. This behavior can be changed
-with ``skipna``
-
-* Cumulative methods like :meth:`~DataFrame.cumsum` and :meth:`~DataFrame.cumprod` ignore NA values by default, but preserve them in the resulting arrays. To override this behaviour and include NA values, use ``skipna=False``.
+ignore NA values by default, but preserve them in the resulting array. To override
+this behaviour and include NA values in the calculation, use ``skipna=False``.
 
 
 .. ipython:: python

doc/source/whatsnew/v3.0.0.rst

@@ -44,8 +44,8 @@ Other enhancements
 - :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`)
 - :meth:`Series.plot` now correctly handle the ``ylabel`` parameter for pie charts, allowing for explicit control over the y-axis label (:issue:`58239`)
+- Restore support for reading Stata 104-format and enable reading 103-format dta files (:issue:`58554`)
 - Support reading Stata 110-format (Stata 7) dta files (:issue:`47176`)
--
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_300.notable_bug_fixes:
@@ -311,6 +311,7 @@ Removal of prior version deprecations/changes
 - Removed the deprecated ``delim_whitespace`` keyword in :func:`read_csv` and :func:`read_table`, use ``sep=r"\s+"`` instead (:issue:`55569`)
 - Require :meth:`SparseDtype.fill_value` to be a valid value for the :meth:`SparseDtype.subtype` (:issue:`53043`)
 - Stopped automatically casting non-datetimelike values (mainly strings) in :meth:`Series.isin` and :meth:`Index.isin` with ``datetime64``, ``timedelta64``, and :class:`PeriodDtype` dtypes (:issue:`53111`)
+- Stopped performing dtype inference in :class:`Index`, :class:`Series` and :class:`DataFrame` constructors when given a pandas object (:class:`Series`, :class:`Index`, :class:`ExtensionArray`), call ``.infer_objects`` on the input to keep the current behavior (:issue:`56012`)
 - Stopped performing dtype inference when setting a :class:`Index` into a :class:`DataFrame` (:issue:`56102`)
 - Stopped performing dtype inference with in :meth:`Index.insert` with object-dtype index; this often affects the index/columns that result when setting new entries into an empty :class:`Series` or :class:`DataFrame` (:issue:`51363`)
 - Removed the "closed" and "unit" keywords in :meth:`TimedeltaIndex.__new__` (:issue:`52628`, :issue:`55499`)
@@ -536,7 +537,7 @@ Groupby/resample/rolling
 - Bug in :meth:`DataFrameGroupBy.apply` that was returning a completely empty DataFrame when all return values of ``func`` were ``None`` instead of returning an empty DataFrame with the original columns and dtypes. (:issue:`57775`)
 - Bug in :meth:`DataFrameGroupBy.apply` with ``as_index=False`` that was returning :class:`MultiIndex` instead of returning :class:`Index`. (:issue:`58291`)
 - Bug in :meth:`DataFrameGroupby.transform` and :meth:`SeriesGroupby.transform` with a reducer and ``observed=False`` that coerces dtype to float when there are unobserved categories. (:issue:`55326`)
-
+- Bug in :meth:`Rolling.apply` where the applied function could be called on fewer than ``min_period`` periods if ``method="table"``. (:issue:`58868`)
 
 Reshaping
 ^^^^^^^^^

pandas/_config/config.py

@@ -323,6 +323,12 @@ def reset_option(pat: str) -> None:
     None
         No return value.
 
+    See Also
+    --------
+    get_option : Retrieve the value of the specified option.
+    set_option : Set the value of the specified option or options.
+    describe_option : Print the description for one or more registered options.
+
     Notes
     -----
     For all available options, please view the
@@ -414,6 +420,13 @@ def option_context(*args) -> Generator[None, None, None]:
     None
         No return value.
 
+    See Also
+    --------
+    get_option : Retrieve the value of the specified option.
+    set_option : Set the value of the specified option.
+    reset_option : Reset one or more options to their default value.
+    describe_option : Print the description for one or more registered options.
+
     Notes
     -----
     For all available options, please view the :ref:`User Guide <options.available>`

pandas/_testing/__init__.py

@@ -10,7 +10,6 @@
     ContextManager,
     cast,
 )
-import warnings
 
 import numpy as np
 
@@ -290,17 +289,11 @@ def box_expected(expected, box_cls, transpose: bool = True):
         else:
             expected = pd.array(expected, copy=False)
     elif box_cls is Index:
-        with warnings.catch_warnings():
-            warnings.filterwarnings("ignore", "Dtype inference", category=FutureWarning)
-            expected = Index(expected)
+        expected = Index(expected)
     elif box_cls is Series:
-        with warnings.catch_warnings():
-            warnings.filterwarnings("ignore", "Dtype inference", category=FutureWarning)
-            expected = Series(expected)
+        expected = Series(expected)
     elif box_cls is DataFrame:
-        with warnings.catch_warnings():
-            warnings.filterwarnings("ignore", "Dtype inference", category=FutureWarning)
-            expected = Series(expected).to_frame()
+        expected = Series(expected).to_frame()
         if transpose:
             # for vector operations, we need a DataFrame to be a single-row,
             #  not a single-column, in order to operate against non-DataFrame
@@ -538,8 +531,8 @@ def shares_memory(left, right) -> bool:
             left._mask, right._mask
         )
 
-    if isinstance(left, DataFrame) and len(left._mgr.arrays) == 1:
-        arr = left._mgr.arrays[0]
+    if isinstance(left, DataFrame) and len(left._mgr.blocks) == 1:
+        arr = left._mgr.blocks[0].values
         return shares_memory(arr, right)
 
     raise NotImplementedError(type(left), type(right))

pandas/_testing/asserters.py

@@ -857,7 +857,9 @@ def assert_series_equal(
     Parameters
     ----------
     left : Series
+        First Series to compare.
     right : Series
+        Second Series to compare.
     check_dtype : bool, default True
         Whether to check the Series dtype is identical.
     check_index_type : bool or {'equiv'}, default 'equiv'
@@ -908,6 +910,11 @@ def assert_series_equal(
 
         .. versionadded:: 1.5.0
 
+    See Also
+    --------
+    testing.assert_index_equal : Check that two Indexes are equal.
+    testing.assert_frame_equal : Check that two DataFrames are equal.
+
     Examples
     --------
     >>> from pandas import testing as tm

pandas/core/algorithms.py

@@ -319,6 +319,8 @@ def unique(values):
     Parameters
     ----------
     values : 1d array-like
+        The input array-like object containing values from which to extract
+        unique values.
 
     Returns
     -------

pandas/core/construction.py

@@ -554,7 +554,7 @@ def sanitize_array(
         # Avoid ending up with a NumpyExtensionArray
         dtype = dtype.numpy_dtype
 
-    data_was_index = isinstance(data, ABCIndex)
+    infer_object = not isinstance(data, (ABCIndex, ABCSeries))
 
     # extract ndarray or ExtensionArray, ensure we have no NumpyExtensionArray
     data = extract_array(data, extract_numpy=True, extract_range=True)
@@ -607,7 +607,7 @@ def sanitize_array(
 
         if dtype is None:
             subarr = data
-            if data.dtype == object and not data_was_index:
+            if data.dtype == object and infer_object:
                 subarr = maybe_infer_to_datetimelike(data)
             elif data.dtype.kind == "U" and using_pyarrow_string_dtype():
                 from pandas.core.arrays.string_ import StringDtype

pandas/core/frame.py

@@ -728,10 +728,6 @@ def __init__(
                 NDFrame.__init__(self, data)
                 return
 
-        is_pandas_object = isinstance(data, (Series, Index, ExtensionArray))
-        data_dtype = getattr(data, "dtype", None)
-        original_dtype = dtype
-
         # GH47215
         if isinstance(index, set):
             raise ValueError("index cannot be a set")
@@ -896,18 +892,6 @@ def __init__(
 
         NDFrame.__init__(self, mgr)
 
-        if original_dtype is None and is_pandas_object and data_dtype == np.object_:
-            if self.dtypes.iloc[0] != data_dtype:
-                warnings.warn(
-                    "Dtype inference on a pandas object "
-                    "(Series, Index, ExtensionArray) is deprecated. The DataFrame "
-                    "constructor will keep the original dtype in the future. "
-                    "Call `infer_objects` on the result to get the old "
-                    "behavior.",
-                    FutureWarning,
-                    stacklevel=2,
-                )
-
     # ----------------------------------------------------------------------
 
     def __dataframe__(
@@ -1062,7 +1046,7 @@ def _is_homogeneous_type(self) -> bool:
         False
         """
         # The "<" part of "<=" here is for empty DataFrame cases
-        return len({arr.dtype for arr in self._mgr.arrays}) <= 1
+        return len({block.values.dtype for block in self._mgr.blocks}) <= 1
 
     @property
     def _can_fast_transpose(self) -> bool:
@@ -5742,7 +5726,6 @@ def shift(
         periods = cast(int, periods)
 
         ncols = len(self.columns)
-        arrays = self._mgr.arrays
         if axis == 1 and periods != 0 and ncols > 0 and freq is None:
             if fill_value is lib.no_default:
                 # We will infer fill_value to match the closest column
@@ -5768,12 +5751,12 @@ def shift(
 
                 result.columns = self.columns.copy()
                 return result
-            elif len(arrays) > 1 or (
+            elif len(self._mgr.blocks) > 1 or (
                 # If we only have one block and we know that we can't
                 #  keep the same dtype (i.e. the _can_hold_element check)
                 #  then we can go through the reindex_indexer path
                 #  (and avoid casting logic in the Block method).
-                not can_hold_element(arrays[0], fill_value)
+                not can_hold_element(self._mgr.blocks[0].values, fill_value)
             ):
                 # GH#35488 we need to watch out for multi-block cases
                 # We only get here with fill_value not-lib.no_default
@@ -11469,7 +11452,7 @@ def _get_data() -> DataFrame:
         if numeric_only:
             df = _get_data()
         if axis is None:
-            dtype = find_common_type([arr.dtype for arr in df._mgr.arrays])
+            dtype = find_common_type([block.values.dtype for block in df._mgr.blocks])
             if isinstance(dtype, ExtensionDtype):
                 df = df.astype(dtype)
                 arr = concat_compat(list(df._iter_column_arrays()))
@@ -11494,7 +11477,9 @@ def _get_data() -> DataFrame:
 
             # kurtosis excluded since groupby does not implement it
             if df.shape[1] and name != "kurt":
-                dtype = find_common_type([arr.dtype for arr in df._mgr.arrays])
+                dtype = find_common_type(
+                    [block.values.dtype for block in df._mgr.blocks]
+                )
                 if isinstance(dtype, ExtensionDtype):
                     # GH 54341: fastpath for EA-backed axis=1 reductions
                     # This flattens the frame into a single 1D array while keeping
@@ -11568,8 +11553,8 @@ def _reduce_axis1(self, name: str, func, skipna: bool) -> Series:
         else:
             raise NotImplementedError(name)
 
-        for arr in self._mgr.arrays:
-            middle = func(arr, axis=0, skipna=skipna)
+        for blocks in self._mgr.blocks:
+            middle = func(blocks.values, axis=0, skipna=skipna)
             result = ufunc(result, middle)
 
         res_ser = self._constructor_sliced(result, index=self.index, copy=False)

pandas/core/generic.py

@@ -6373,7 +6373,7 @@ def astype(
             # TODO(EA2D): special case not needed with 2D EAs
             dtype = pandas_dtype(dtype)
             if isinstance(dtype, ExtensionDtype) and all(
-                arr.dtype == dtype for arr in self._mgr.arrays
+                block.values.dtype == dtype for block in self._mgr.blocks
             ):
                 return self.copy(deep=False)
             # GH 18099/22869: columnwise conversion to extension dtype
@@ -11148,9 +11148,9 @@ def _logical_func(
         if (
             self.ndim > 1
             and axis == 1
-            and len(self._mgr.arrays) > 1
+            and len(self._mgr.blocks) > 1
             # TODO(EA2D): special-case not needed
-            and all(x.ndim == 2 for x in self._mgr.arrays)
+            and all(block.values.ndim == 2 for block in self._mgr.blocks)
             and not kwargs
         ):
             # Fastpath avoiding potentially expensive transpose

pandas/core/indexes/base.py

@@ -490,8 +490,6 @@ def __new__(
         if not copy and isinstance(data, (ABCSeries, Index)):
             refs = data._references
 
-        is_pandas_object = isinstance(data, (ABCSeries, Index, ExtensionArray))
-
         # range
         if isinstance(data, (range, RangeIndex)):
             result = RangeIndex(start=data, copy=copy, name=name)
@@ -508,7 +506,7 @@ def __new__(
         elif is_ea_or_datetimelike_dtype(data_dtype):
             pass
 
-        elif isinstance(data, (np.ndarray, Index, ABCSeries)):
+        elif isinstance(data, (np.ndarray, ABCMultiIndex)):
             if isinstance(data, ABCMultiIndex):
                 data = data._values
 
@@ -518,7 +516,9 @@ def __new__(
                 # they are actually ints, e.g. '0' and 0.0
                 # should not be coerced
                 data = com.asarray_tuplesafe(data, dtype=_dtype_obj)
-
+        elif isinstance(data, (ABCSeries, Index)):
+            # GH 56244: Avoid potential inference on object types
+            pass
         elif is_scalar(data):
             raise cls._raise_scalar_data_error(data)
         elif hasattr(data, "__array__"):
@@ -571,19 +571,7 @@ def __new__(
         klass = cls._dtype_to_subclass(arr.dtype)
 
         arr = klass._ensure_array(arr, arr.dtype, copy=False)
-        result = klass._simple_new(arr, name, refs=refs)
-        if dtype is None and is_pandas_object and data_dtype == np.object_:
-            if result.dtype != data_dtype:
-                warnings.warn(
-                    "Dtype inference on a pandas object "
-                    "(Series, Index, ExtensionArray) is deprecated. The Index "
-                    "constructor will keep the original dtype in the future. "
-                    "Call `infer_objects` on the result to get the old "
-                    "behavior.",
-                    FutureWarning,
-                    stacklevel=2,
-                )
-        return result  # type: ignore[return-value]
+        return klass._simple_new(arr, name, refs=refs)
 
     @classmethod
     def _ensure_array(cls, data, dtype, copy: bool):

pandas/core/indexing.py

@@ -1804,10 +1804,10 @@ def _setitem_with_indexer(self, indexer, value, name: str = "iloc") -> None:
 
         # if there is only one block/type, still have to take split path
         # unless the block is one-dimensional or it can hold the value
-        if not take_split_path and len(self.obj._mgr.arrays) and self.ndim > 1:
+        if not take_split_path and len(self.obj._mgr.blocks) and self.ndim > 1:
             # in case of dict, keys are indices
             val = list(value.values()) if isinstance(value, dict) else value
-            arr = self.obj._mgr.arrays[0]
+            arr = self.obj._mgr.blocks[0].values
             take_split_path = not can_hold_element(
                 arr, extract_array(val, extract_numpy=True)
             )