Initial commit: Masina-Dock Vehicle Management System

AppDir/usr/lib/python3.12/site-packages/pandas/__init__.py

@@ -0,0 +1,353 @@
+from __future__ import annotations
+
+__docformat__ = "restructuredtext"
+
+# Let users know if they're missing any of our hard dependencies
+_hard_dependencies = ("numpy", "pytz", "dateutil")
+_missing_dependencies = []
+
+for _dependency in _hard_dependencies:
+    try:
+        __import__(_dependency)
+    except ImportError as _e:  # pragma: no cover
+        _missing_dependencies.append(f"{_dependency}: {_e}")
+
+if _missing_dependencies:  # pragma: no cover
+    raise ImportError(
+        "Unable to import required dependencies:\n" + "\n".join(_missing_dependencies)
+    )
+del _hard_dependencies, _dependency, _missing_dependencies
+
+try:
+    # numpy compat
+    from pandas.compat import (
+        is_numpy_dev as _is_numpy_dev,  # pyright: ignore[reportUnusedImport] # noqa: F401,E501
+    )
+except ImportError as _err:  # pragma: no cover
+    _module = _err.name
+    raise ImportError(
+        f"C extension: {_module} not built. If you want to import "
+        "pandas from the source directory, you may need to run "
+        "'python setup.py build_ext' to build the C extensions first."
+    ) from _err
+
+from pandas._config import (
+    get_option,
+    set_option,
+    reset_option,
+    describe_option,
+    option_context,
+    options,
+)
+
+# let init-time option registration happen
+import pandas.core.config_init  # pyright: ignore[reportUnusedImport] # noqa: F401
+
+from pandas.core.api import (
+    # dtype
+    ArrowDtype,
+    Int8Dtype,
+    Int16Dtype,
+    Int32Dtype,
+    Int64Dtype,
+    UInt8Dtype,
+    UInt16Dtype,
+    UInt32Dtype,
+    UInt64Dtype,
+    Float32Dtype,
+    Float64Dtype,
+    CategoricalDtype,
+    PeriodDtype,
+    IntervalDtype,
+    DatetimeTZDtype,
+    StringDtype,
+    BooleanDtype,
+    # missing
+    NA,
+    isna,
+    isnull,
+    notna,
+    notnull,
+    # indexes
+    Index,
+    CategoricalIndex,
+    RangeIndex,
+    MultiIndex,
+    IntervalIndex,
+    TimedeltaIndex,
+    DatetimeIndex,
+    PeriodIndex,
+    IndexSlice,
+    # tseries
+    NaT,
+    Period,
+    period_range,
+    Timedelta,
+    timedelta_range,
+    Timestamp,
+    date_range,
+    bdate_range,
+    Interval,
+    interval_range,
+    DateOffset,
+    # conversion
+    to_numeric,
+    to_datetime,
+    to_timedelta,
+    # misc
+    Flags,
+    Grouper,
+    factorize,
+    unique,
+    value_counts,
+    NamedAgg,
+    array,
+    Categorical,
+    set_eng_float_format,
+    Series,
+    DataFrame,
+)
+
+from pandas.core.dtypes.dtypes import SparseDtype
+
+from pandas.tseries.api import infer_freq
+from pandas.tseries import offsets
+
+from pandas.core.computation.api import eval
+
+from pandas.core.reshape.api import (
+    concat,
+    lreshape,
+    melt,
+    wide_to_long,
+    merge,
+    merge_asof,
+    merge_ordered,
+    crosstab,
+    pivot,
+    pivot_table,
+    get_dummies,
+    from_dummies,
+    cut,
+    qcut,
+)
+
+from pandas import api, arrays, errors, io, plotting, tseries
+from pandas import testing
+from pandas.util._print_versions import show_versions
+
+from pandas.io.api import (
+    # excel
+    ExcelFile,
+    ExcelWriter,
+    read_excel,
+    # parsers
+    read_csv,
+    read_fwf,
+    read_table,
+    # pickle
+    read_pickle,
+    to_pickle,
+    # pytables
+    HDFStore,
+    read_hdf,
+    # sql
+    read_sql,
+    read_sql_query,
+    read_sql_table,
+    # misc
+    read_clipboard,
+    read_parquet,
+    read_orc,
+    read_feather,
+    read_gbq,
+    read_html,
+    read_xml,
+    read_json,
+    read_stata,
+    read_sas,
+    read_spss,
+)
+
+from pandas.io.json._normalize import json_normalize
+
+from pandas.util._tester import test
+
+# use the closest tagged version if possible
+_built_with_meson = False
+try:
+    from pandas._version_meson import (  # pyright: ignore [reportMissingImports]
+        __version__,
+        __git_version__,
+    )
+
+    _built_with_meson = True
+except ImportError:
+    from pandas._version import get_versions
+
+    v = get_versions()
+    __version__ = v.get("closest-tag", v["version"])
+    __git_version__ = v.get("full-revisionid")
+    del get_versions, v
+
+
+# module level doc-string
+__doc__ = """
+pandas - a powerful data analysis and manipulation library for Python
+=====================================================================
+
+**pandas** is a Python package providing fast, flexible, and expressive data
+structures designed to make working with "relational" or "labeled" data both
+easy and intuitive. It aims to be the fundamental high-level building block for
+doing practical, **real world** data analysis in Python. Additionally, it has
+the broader goal of becoming **the most powerful and flexible open source data
+analysis / manipulation tool available in any language**. It is already well on
+its way toward this goal.
+
+Main Features
+-------------
+Here are just a few of the things that pandas does well:
+
+  - Easy handling of missing data in floating point as well as non-floating
+    point data.
+  - Size mutability: columns can be inserted and deleted from DataFrame and
+    higher dimensional objects
+  - Automatic and explicit data alignment: objects can be explicitly aligned
+    to a set of labels, or the user can simply ignore the labels and let
+    `Series`, `DataFrame`, etc. automatically align the data for you in
+    computations.
+  - Powerful, flexible group by functionality to perform split-apply-combine
+    operations on data sets, for both aggregating and transforming data.
+  - Make it easy to convert ragged, differently-indexed data in other Python
+    and NumPy data structures into DataFrame objects.
+  - Intelligent label-based slicing, fancy indexing, and subsetting of large
+    data sets.
+  - Intuitive merging and joining data sets.
+  - Flexible reshaping and pivoting of data sets.
+  - Hierarchical labeling of axes (possible to have multiple labels per tick).
+  - Robust IO tools for loading data from flat files (CSV and delimited),
+    Excel files, databases, and saving/loading data from the ultrafast HDF5
+    format.
+  - Time series-specific functionality: date range generation and frequency
+    conversion, moving window statistics, date shifting and lagging.
+"""
+
+# Use __all__ to let type checkers know what is part of the public API.
+# Pandas is not (yet) a py.typed library: the public API is determined
+# based on the documentation.
+__all__ = [
+    "ArrowDtype",
+    "BooleanDtype",
+    "Categorical",
+    "CategoricalDtype",
+    "CategoricalIndex",
+    "DataFrame",
+    "DateOffset",
+    "DatetimeIndex",
+    "DatetimeTZDtype",
+    "ExcelFile",
+    "ExcelWriter",
+    "Flags",
+    "Float32Dtype",
+    "Float64Dtype",
+    "Grouper",
+    "HDFStore",
+    "Index",
+    "IndexSlice",
+    "Int16Dtype",
+    "Int32Dtype",
+    "Int64Dtype",
+    "Int8Dtype",
+    "Interval",
+    "IntervalDtype",
+    "IntervalIndex",
+    "MultiIndex",
+    "NA",
+    "NaT",
+    "NamedAgg",
+    "Period",
+    "PeriodDtype",
+    "PeriodIndex",
+    "RangeIndex",
+    "Series",
+    "SparseDtype",
+    "StringDtype",
+    "Timedelta",
+    "TimedeltaIndex",
+    "Timestamp",
+    "UInt16Dtype",
+    "UInt32Dtype",
+    "UInt64Dtype",
+    "UInt8Dtype",
+    "api",
+    "array",
+    "arrays",
+    "bdate_range",
+    "concat",
+    "crosstab",
+    "cut",
+    "date_range",
+    "describe_option",
+    "errors",
+    "eval",
+    "factorize",
+    "get_dummies",
+    "from_dummies",
+    "get_option",
+    "infer_freq",
+    "interval_range",
+    "io",
+    "isna",
+    "isnull",
+    "json_normalize",
+    "lreshape",
+    "melt",
+    "merge",
+    "merge_asof",
+    "merge_ordered",
+    "notna",
+    "notnull",
+    "offsets",
+    "option_context",
+    "options",
+    "period_range",
+    "pivot",
+    "pivot_table",
+    "plotting",
+    "qcut",
+    "read_clipboard",
+    "read_csv",
+    "read_excel",
+    "read_feather",
+    "read_fwf",
+    "read_gbq",
+    "read_hdf",
+    "read_html",
+    "read_json",
+    "read_orc",
+    "read_parquet",
+    "read_pickle",
+    "read_sas",
+    "read_spss",
+    "read_sql",
+    "read_sql_query",
+    "read_sql_table",
+    "read_stata",
+    "read_table",
+    "read_xml",
+    "reset_option",
+    "set_eng_float_format",
+    "set_option",
+    "show_versions",
+    "test",
+    "testing",
+    "timedelta_range",
+    "to_datetime",
+    "to_numeric",
+    "to_pickle",
+    "to_timedelta",
+    "tseries",
+    "unique",
+    "value_counts",
+    "wide_to_long",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/_config/__init__.py

@@ -0,0 +1,45 @@
+"""
+pandas._config is considered explicitly upstream of everything else in pandas,
+should have no intra-pandas dependencies.
+
+importing `dates` and `display` ensures that keys needed by _libs
+are initialized.
+"""
+__all__ = [
+    "config",
+    "detect_console_encoding",
+    "get_option",
+    "set_option",
+    "reset_option",
+    "describe_option",
+    "option_context",
+    "options",
+    "using_copy_on_write",
+]
+from pandas._config import config
+from pandas._config import dates  # pyright: ignore[reportUnusedImport]  # noqa: F401
+from pandas._config.config import (
+    _global_config,
+    describe_option,
+    get_option,
+    option_context,
+    options,
+    reset_option,
+    set_option,
+)
+from pandas._config.display import detect_console_encoding
+
+
+def using_copy_on_write() -> bool:
+    _mode_options = _global_config["mode"]
+    return _mode_options["copy_on_write"] and _mode_options["data_manager"] == "block"
+
+
+def using_nullable_dtypes() -> bool:
+    _mode_options = _global_config["mode"]
+    return _mode_options["nullable_dtypes"]
+
+
+def using_pyarrow_string_dtype() -> bool:
+    _mode_options = _global_config["future"]
+    return _mode_options["infer_string"]

AppDir/usr/lib/python3.12/site-packages/pandas/_config/config.py

@@ -0,0 +1,946 @@
+"""
+The config module holds package-wide configurables and provides
+a uniform API for working with them.
+
+Overview
+========
+
+This module supports the following requirements:
+- options are referenced using keys in dot.notation, e.g. "x.y.option - z".
+- keys are case-insensitive.
+- functions should accept partial/regex keys, when unambiguous.
+- options can be registered by modules at import time.
+- options can be registered at init-time (via core.config_init)
+- options have a default value, and (optionally) a description and
+  validation function associated with them.
+- options can be deprecated, in which case referencing them
+  should produce a warning.
+- deprecated options can optionally be rerouted to a replacement
+  so that accessing a deprecated option reroutes to a differently
+  named option.
+- options can be reset to their default value.
+- all option can be reset to their default value at once.
+- all options in a certain sub - namespace can be reset at once.
+- the user can set / get / reset or ask for the description of an option.
+- a developer can register and mark an option as deprecated.
+- you can register a callback to be invoked when the option value
+  is set or reset. Changing the stored value is considered misuse, but
+  is not verboten.
+
+Implementation
+==============
+
+- Data is stored using nested dictionaries, and should be accessed
+  through the provided API.
+
+- "Registered options" and "Deprecated options" have metadata associated
+  with them, which are stored in auxiliary dictionaries keyed on the
+  fully-qualified key, e.g. "x.y.z.option".
+
+- the config_init module is imported by the package's __init__.py file.
+  placing any register_option() calls there will ensure those options
+  are available as soon as pandas is loaded. If you use register_option
+  in a module, it will only be available after that module is imported,
+  which you should be aware of.
+
+- `config_prefix` is a context_manager (for use with the `with` keyword)
+  which can save developers some typing, see the docstring.
+
+"""
+
+from __future__ import annotations
+
+from contextlib import (
+    ContextDecorator,
+    contextmanager,
+)
+import re
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Callable,
+    Generic,
+    NamedTuple,
+    cast,
+)
+import warnings
+
+from pandas._typing import (
+    F,
+    T,
+)
+from pandas.util._exceptions import find_stack_level
+
+if TYPE_CHECKING:
+    from collections.abc import (
+        Generator,
+        Iterable,
+    )
+
+
+class DeprecatedOption(NamedTuple):
+    key: str
+    msg: str | None
+    rkey: str | None
+    removal_ver: str | None
+
+
+class RegisteredOption(NamedTuple):
+    key: str
+    defval: object
+    doc: str
+    validator: Callable[[object], Any] | None
+    cb: Callable[[str], Any] | None
+
+
+# holds deprecated option metadata
+_deprecated_options: dict[str, DeprecatedOption] = {}
+
+# holds registered option metadata
+_registered_options: dict[str, RegisteredOption] = {}
+
+# holds the current values for registered options
+_global_config: dict[str, Any] = {}
+
+# keys which have a special meaning
+_reserved_keys: list[str] = ["all"]
+
+
+class OptionError(AttributeError, KeyError):
+    """
+    Exception raised for pandas.options.
+
+    Backwards compatible with KeyError checks.
+
+    Examples
+    --------
+    >>> pd.options.context
+    Traceback (most recent call last):
+    OptionError: No such option
+    """
+
+
+#
+# User API
+
+
+def _get_single_key(pat: str, silent: bool) -> str:
+    keys = _select_options(pat)
+    if len(keys) == 0:
+        if not silent:
+            _warn_if_deprecated(pat)
+        raise OptionError(f"No such keys(s): {repr(pat)}")
+    if len(keys) > 1:
+        raise OptionError("Pattern matched multiple keys")
+    key = keys[0]
+
+    if not silent:
+        _warn_if_deprecated(key)
+
+    key = _translate_key(key)
+
+    return key
+
+
+def _get_option(pat: str, silent: bool = False) -> Any:
+    key = _get_single_key(pat, silent)
+
+    # walk the nested dict
+    root, k = _get_root(key)
+    return root[k]
+
+
+def _set_option(*args, **kwargs) -> None:
+    # must at least 1 arg deal with constraints later
+    nargs = len(args)
+    if not nargs or nargs % 2 != 0:
+        raise ValueError("Must provide an even number of non-keyword arguments")
+
+    # default to false
+    silent = kwargs.pop("silent", False)
+
+    if kwargs:
+        kwarg = next(iter(kwargs.keys()))
+        raise TypeError(f'_set_option() got an unexpected keyword argument "{kwarg}"')
+
+    for k, v in zip(args[::2], args[1::2]):
+        key = _get_single_key(k, silent)
+
+        o = _get_registered_option(key)
+        if o and o.validator:
+            o.validator(v)
+
+        # walk the nested dict
+        root, k_root = _get_root(key)
+        root[k_root] = v
+
+        if o.cb:
+            if silent:
+                with warnings.catch_warnings(record=True):
+                    o.cb(key)
+            else:
+                o.cb(key)
+
+
+def _describe_option(pat: str = "", _print_desc: bool = True) -> str | None:
+    keys = _select_options(pat)
+    if len(keys) == 0:
+        raise OptionError("No such keys(s)")
+
+    s = "\n".join([_build_option_description(k) for k in keys])
+
+    if _print_desc:
+        print(s)
+        return None
+    return s
+
+
+def _reset_option(pat: str, silent: bool = False) -> None:
+    keys = _select_options(pat)
+
+    if len(keys) == 0:
+        raise OptionError("No such keys(s)")
+
+    if len(keys) > 1 and len(pat) < 4 and pat != "all":
+        raise ValueError(
+            "You must specify at least 4 characters when "
+            "resetting multiple keys, use the special keyword "
+            '"all" to reset all the options to their default value'
+        )
+
+    for k in keys:
+        _set_option(k, _registered_options[k].defval, silent=silent)
+
+
+def get_default_val(pat: str):
+    key = _get_single_key(pat, silent=True)
+    return _get_registered_option(key).defval
+
+
+class DictWrapper:
+    """provide attribute-style access to a nested dict"""
+
+    def __init__(self, d: dict[str, Any], prefix: str = "") -> None:
+        object.__setattr__(self, "d", d)
+        object.__setattr__(self, "prefix", prefix)
+
+    def __setattr__(self, key: str, val: Any) -> None:
+        prefix = object.__getattribute__(self, "prefix")
+        if prefix:
+            prefix += "."
+        prefix += key
+        # you can't set new keys
+        # can you can't overwrite subtrees
+        if key in self.d and not isinstance(self.d[key], dict):
+            _set_option(prefix, val)
+        else:
+            raise OptionError("You can only set the value of existing options")
+
+    def __getattr__(self, key: str):
+        prefix = object.__getattribute__(self, "prefix")
+        if prefix:
+            prefix += "."
+        prefix += key
+        try:
+            v = object.__getattribute__(self, "d")[key]
+        except KeyError as err:
+            raise OptionError("No such option") from err
+        if isinstance(v, dict):
+            return DictWrapper(v, prefix)
+        else:
+            return _get_option(prefix)
+
+    def __dir__(self) -> Iterable[str]:
+        return list(self.d.keys())
+
+
+# For user convenience,  we'd like to have the available options described
+# in the docstring. For dev convenience we'd like to generate the docstrings
+# dynamically instead of maintaining them by hand. To this, we use the
+# class below which wraps functions inside a callable, and converts
+# __doc__ into a property function. The doctsrings below are templates
+# using the py2.6+ advanced formatting syntax to plug in a concise list
+# of options, and option descriptions.
+
+
+class CallableDynamicDoc(Generic[T]):
+    def __init__(self, func: Callable[..., T], doc_tmpl: str) -> None:
+        self.__doc_tmpl__ = doc_tmpl
+        self.__func__ = func
+
+    def __call__(self, *args, **kwds) -> T:
+        return self.__func__(*args, **kwds)
+
+    # error: Signature of "__doc__" incompatible with supertype "object"
+    @property
+    def __doc__(self) -> str:  # type: ignore[override]
+        opts_desc = _describe_option("all", _print_desc=False)
+        opts_list = pp_options_list(list(_registered_options.keys()))
+        return self.__doc_tmpl__.format(opts_desc=opts_desc, opts_list=opts_list)
+
+
+_get_option_tmpl = """
+get_option(pat)
+
+Retrieves the value of the specified option.
+
+Available options:
+
+{opts_list}
+
+Parameters
+----------
+pat : str
+    Regexp which should match a single option.
+    Note: partial matches are supported for convenience, but unless you use the
+    full option name (e.g. x.y.z.option_name), your code may break in future
+    versions if new options with similar names are introduced.
+
+Returns
+-------
+result : the value of the option
+
+Raises
+------
+OptionError : if no such option exists
+
+Notes
+-----
+Please reference the :ref:`User Guide <options>` for more information.
+
+The available options with its descriptions:
+
+{opts_desc}
+
+Examples
+--------
+>>> pd.get_option('display.max_columns')  # doctest: +SKIP
+4
+"""
+
+_set_option_tmpl = """
+set_option(pat, value)
+
+Sets the value of the specified option.
+
+Available options:
+
+{opts_list}
+
+Parameters
+----------
+pat : str
+    Regexp which should match a single option.
+    Note: partial matches are supported for convenience, but unless you use the
+    full option name (e.g. x.y.z.option_name), your code may break in future
+    versions if new options with similar names are introduced.
+value : object
+    New value of option.
+
+Returns
+-------
+None
+
+Raises
+------
+OptionError if no such option exists
+
+Notes
+-----
+Please reference the :ref:`User Guide <options>` for more information.
+
+The available options with its descriptions:
+
+{opts_desc}
+
+Examples
+--------
+>>> pd.set_option('display.max_columns', 4)
+>>> df = pd.DataFrame([[1, 2, 3, 4, 5], [6, 7, 8, 9, 10]])
+>>> df
+   0  1  ...  3   4
+0  1  2  ...  4   5
+1  6  7  ...  9  10
+[2 rows x 5 columns]
+>>> pd.reset_option('display.max_columns')
+"""
+
+_describe_option_tmpl = """
+describe_option(pat, _print_desc=False)
+
+Prints the description for one or more registered options.
+
+Call with no arguments to get a listing for all registered options.
+
+Available options:
+
+{opts_list}
+
+Parameters
+----------
+pat : str
+    Regexp pattern. All matching keys will have their description displayed.
+_print_desc : bool, default True
+    If True (default) the description(s) will be printed to stdout.
+    Otherwise, the description(s) will be returned as a unicode string
+    (for testing).
+
+Returns
+-------
+None by default, the description(s) as a unicode string if _print_desc
+is False
+
+Notes
+-----
+Please reference the :ref:`User Guide <options>` for more information.
+
+The available options with its descriptions:
+
+{opts_desc}
+
+Examples
+--------
+>>> pd.describe_option('display.max_columns')  # doctest: +SKIP
+display.max_columns : int
+    If max_cols is exceeded, switch to truncate view...
+"""
+
+_reset_option_tmpl = """
+reset_option(pat)
+
+Reset one or more options to their default value.
+
+Pass "all" as argument to reset all options.
+
+Available options:
+
+{opts_list}
+
+Parameters
+----------
+pat : str/regex
+    If specified only options matching `prefix*` will be reset.
+    Note: partial matches are supported for convenience, but unless you
+    use the full option name (e.g. x.y.z.option_name), your code may break
+    in future versions if new options with similar names are introduced.
+
+Returns
+-------
+None
+
+Notes
+-----
+Please reference the :ref:`User Guide <options>` for more information.
+
+The available options with its descriptions:
+
+{opts_desc}
+
+Examples
+--------
+>>> pd.reset_option('display.max_columns')  # doctest: +SKIP
+"""
+
+# bind the functions with their docstrings into a Callable
+# and use that as the functions exposed in pd.api
+get_option = CallableDynamicDoc(_get_option, _get_option_tmpl)
+set_option = CallableDynamicDoc(_set_option, _set_option_tmpl)
+reset_option = CallableDynamicDoc(_reset_option, _reset_option_tmpl)
+describe_option = CallableDynamicDoc(_describe_option, _describe_option_tmpl)
+options = DictWrapper(_global_config)
+
+#
+# Functions for use by pandas developers, in addition to User - api
+
+
+class option_context(ContextDecorator):
+    """
+    Context manager to temporarily set options in the `with` statement context.
+
+    You need to invoke as ``option_context(pat, val, [(pat, val), ...])``.
+
+    Examples
+    --------
+    >>> from pandas import option_context
+    >>> with option_context('display.max_rows', 10, 'display.max_columns', 5):
+    ...     pass
+    """
+
+    def __init__(self, *args) -> None:
+        if len(args) % 2 != 0 or len(args) < 2:
+            raise ValueError(
+                "Need to invoke as option_context(pat, val, [(pat, val), ...])."
+            )
+
+        self.ops = list(zip(args[::2], args[1::2]))
+
+    def __enter__(self) -> None:
+        self.undo = [(pat, _get_option(pat)) for pat, val in self.ops]
+
+        for pat, val in self.ops:
+            _set_option(pat, val, silent=True)
+
+    def __exit__(self, *args) -> None:
+        if self.undo:
+            for pat, val in self.undo:
+                _set_option(pat, val, silent=True)
+
+
+def register_option(
+    key: str,
+    defval: object,
+    doc: str = "",
+    validator: Callable[[object], Any] | None = None,
+    cb: Callable[[str], Any] | None = None,
+) -> None:
+    """
+    Register an option in the package-wide pandas config object
+
+    Parameters
+    ----------
+    key : str
+        Fully-qualified key, e.g. "x.y.option - z".
+    defval : object
+        Default value of the option.
+    doc : str
+        Description of the option.
+    validator : Callable, optional
+        Function of a single argument, should raise `ValueError` if
+        called with a value which is not a legal value for the option.
+    cb
+        a function of a single argument "key", which is called
+        immediately after an option value is set/reset. key is
+        the full name of the option.
+
+    Raises
+    ------
+    ValueError if `validator` is specified and `defval` is not a valid value.
+
+    """
+    import keyword
+    import tokenize
+
+    key = key.lower()
+
+    if key in _registered_options:
+        raise OptionError(f"Option '{key}' has already been registered")
+    if key in _reserved_keys:
+        raise OptionError(f"Option '{key}' is a reserved key")
+
+    # the default value should be legal
+    if validator:
+        validator(defval)
+
+    # walk the nested dict, creating dicts as needed along the path
+    path = key.split(".")
+
+    for k in path:
+        if not re.match("^" + tokenize.Name + "$", k):
+            raise ValueError(f"{k} is not a valid identifier")
+        if keyword.iskeyword(k):
+            raise ValueError(f"{k} is a python keyword")
+
+    cursor = _global_config
+    msg = "Path prefix to option '{option}' is already an option"
+
+    for i, p in enumerate(path[:-1]):
+        if not isinstance(cursor, dict):
+            raise OptionError(msg.format(option=".".join(path[:i])))
+        if p not in cursor:
+            cursor[p] = {}
+        cursor = cursor[p]
+
+    if not isinstance(cursor, dict):
+        raise OptionError(msg.format(option=".".join(path[:-1])))
+
+    cursor[path[-1]] = defval  # initialize
+
+    # save the option metadata
+    _registered_options[key] = RegisteredOption(
+        key=key, defval=defval, doc=doc, validator=validator, cb=cb
+    )
+
+
+def deprecate_option(
+    key: str,
+    msg: str | None = None,
+    rkey: str | None = None,
+    removal_ver: str | None = None,
+) -> None:
+    """
+    Mark option `key` as deprecated, if code attempts to access this option,
+    a warning will be produced, using `msg` if given, or a default message
+    if not.
+    if `rkey` is given, any access to the key will be re-routed to `rkey`.
+
+    Neither the existence of `key` nor that if `rkey` is checked. If they
+    do not exist, any subsequence access will fail as usual, after the
+    deprecation warning is given.
+
+    Parameters
+    ----------
+    key : str
+        Name of the option to be deprecated.
+        must be a fully-qualified option name (e.g "x.y.z.rkey").
+    msg : str, optional
+        Warning message to output when the key is referenced.
+        if no message is given a default message will be emitted.
+    rkey : str, optional
+        Name of an option to reroute access to.
+        If specified, any referenced `key` will be
+        re-routed to `rkey` including set/get/reset.
+        rkey must be a fully-qualified option name (e.g "x.y.z.rkey").
+        used by the default message if no `msg` is specified.
+    removal_ver : str, optional
+        Specifies the version in which this option will
+        be removed. used by the default message if no `msg` is specified.
+
+    Raises
+    ------
+    OptionError
+        If the specified key has already been deprecated.
+    """
+    key = key.lower()
+
+    if key in _deprecated_options:
+        raise OptionError(f"Option '{key}' has already been defined as deprecated.")
+
+    _deprecated_options[key] = DeprecatedOption(key, msg, rkey, removal_ver)
+
+
+#
+# functions internal to the module
+
+
+def _select_options(pat: str) -> list[str]:
+    """
+    returns a list of keys matching `pat`
+
+    if pat=="all", returns all registered options
+    """
+    # short-circuit for exact key
+    if pat in _registered_options:
+        return [pat]
+
+    # else look through all of them
+    keys = sorted(_registered_options.keys())
+    if pat == "all":  # reserved key
+        return keys
+
+    return [k for k in keys if re.search(pat, k, re.I)]
+
+
+def _get_root(key: str) -> tuple[dict[str, Any], str]:
+    path = key.split(".")
+    cursor = _global_config
+    for p in path[:-1]:
+        cursor = cursor[p]
+    return cursor, path[-1]
+
+
+def _is_deprecated(key: str) -> bool:
+    """Returns True if the given option has been deprecated"""
+    key = key.lower()
+    return key in _deprecated_options
+
+
+def _get_deprecated_option(key: str):
+    """
+    Retrieves the metadata for a deprecated option, if `key` is deprecated.
+
+    Returns
+    -------
+    DeprecatedOption (namedtuple) if key is deprecated, None otherwise
+    """
+    try:
+        d = _deprecated_options[key]
+    except KeyError:
+        return None
+    else:
+        return d
+
+
+def _get_registered_option(key: str):
+    """
+    Retrieves the option metadata if `key` is a registered option.
+
+    Returns
+    -------
+    RegisteredOption (namedtuple) if key is deprecated, None otherwise
+    """
+    return _registered_options.get(key)
+
+
+def _translate_key(key: str) -> str:
+    """
+    if key id deprecated and a replacement key defined, will return the
+    replacement key, otherwise returns `key` as - is
+    """
+    d = _get_deprecated_option(key)
+    if d:
+        return d.rkey or key
+    else:
+        return key
+
+
+def _warn_if_deprecated(key: str) -> bool:
+    """
+    Checks if `key` is a deprecated option and if so, prints a warning.
+
+    Returns
+    -------
+    bool - True if `key` is deprecated, False otherwise.
+    """
+    d = _get_deprecated_option(key)
+    if d:
+        if d.msg:
+            warnings.warn(
+                d.msg,
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
+        else:
+            msg = f"'{key}' is deprecated"
+            if d.removal_ver:
+                msg += f" and will be removed in {d.removal_ver}"
+            if d.rkey:
+                msg += f", please use '{d.rkey}' instead."
+            else:
+                msg += ", please refrain from using it."
+
+            warnings.warn(msg, FutureWarning, stacklevel=find_stack_level())
+        return True
+    return False
+
+
+def _build_option_description(k: str) -> str:
+    """Builds a formatted description of a registered option and prints it"""
+    o = _get_registered_option(k)
+    d = _get_deprecated_option(k)
+
+    s = f"{k} "
+
+    if o.doc:
+        s += "\n".join(o.doc.strip().split("\n"))
+    else:
+        s += "No description available."
+
+    if o:
+        s += f"\n    [default: {o.defval}] [currently: {_get_option(k, True)}]"
+
+    if d:
+        rkey = d.rkey or ""
+        s += "\n    (Deprecated"
+        s += f", use `{rkey}` instead."
+        s += ")"
+
+    return s
+
+
+def pp_options_list(keys: Iterable[str], width: int = 80, _print: bool = False):
+    """Builds a concise listing of available options, grouped by prefix"""
+    from itertools import groupby
+    from textwrap import wrap
+
+    def pp(name: str, ks: Iterable[str]) -> list[str]:
+        pfx = "- " + name + ".[" if name else ""
+        ls = wrap(
+            ", ".join(ks),
+            width,
+            initial_indent=pfx,
+            subsequent_indent="  ",
+            break_long_words=False,
+        )
+        if ls and ls[-1] and name:
+            ls[-1] = ls[-1] + "]"
+        return ls
+
+    ls: list[str] = []
+    singles = [x for x in sorted(keys) if x.find(".") < 0]
+    if singles:
+        ls += pp("", singles)
+    keys = [x for x in keys if x.find(".") >= 0]
+
+    for k, g in groupby(sorted(keys), lambda x: x[: x.rfind(".")]):
+        ks = [x[len(k) + 1 :] for x in list(g)]
+        ls += pp(k, ks)
+    s = "\n".join(ls)
+    if _print:
+        print(s)
+    else:
+        return s
+
+
+#
+# helpers
+
+
+@contextmanager
+def config_prefix(prefix: str) -> Generator[None, None, None]:
+    """
+    contextmanager for multiple invocations of API with a common prefix
+
+    supported API functions: (register / get / set )__option
+
+    Warning: This is not thread - safe, and won't work properly if you import
+    the API functions into your module using the "from x import y" construct.
+
+    Example
+    -------
+    import pandas._config.config as cf
+    with cf.config_prefix("display.font"):
+        cf.register_option("color", "red")
+        cf.register_option("size", " 5 pt")
+        cf.set_option(size, " 6 pt")
+        cf.get_option(size)
+        ...
+
+        etc'
+
+    will register options "display.font.color", "display.font.size", set the
+    value of "display.font.size"... and so on.
+    """
+    # Note: reset_option relies on set_option, and on key directly
+    # it does not fit in to this monkey-patching scheme
+
+    global register_option, get_option, set_option
+
+    def wrap(func: F) -> F:
+        def inner(key: str, *args, **kwds):
+            pkey = f"{prefix}.{key}"
+            return func(pkey, *args, **kwds)
+
+        return cast(F, inner)
+
+    _register_option = register_option
+    _get_option = get_option
+    _set_option = set_option
+    set_option = wrap(set_option)
+    get_option = wrap(get_option)
+    register_option = wrap(register_option)
+    try:
+        yield
+    finally:
+        set_option = _set_option
+        get_option = _get_option
+        register_option = _register_option
+
+
+# These factories and methods are handy for use as the validator
+# arg in register_option
+
+
+def is_type_factory(_type: type[Any]) -> Callable[[Any], None]:
+    """
+
+    Parameters
+    ----------
+    `_type` - a type to be compared against (e.g. type(x) == `_type`)
+
+    Returns
+    -------
+    validator - a function of a single argument x , which raises
+                ValueError if type(x) is not equal to `_type`
+
+    """
+
+    def inner(x) -> None:
+        if type(x) != _type:
+            raise ValueError(f"Value must have type '{_type}'")
+
+    return inner
+
+
+def is_instance_factory(_type) -> Callable[[Any], None]:
+    """
+
+    Parameters
+    ----------
+    `_type` - the type to be checked against
+
+    Returns
+    -------
+    validator - a function of a single argument x , which raises
+                ValueError if x is not an instance of `_type`
+
+    """
+    if isinstance(_type, (tuple, list)):
+        _type = tuple(_type)
+        type_repr = "|".join(map(str, _type))
+    else:
+        type_repr = f"'{_type}'"
+
+    def inner(x) -> None:
+        if not isinstance(x, _type):
+            raise ValueError(f"Value must be an instance of {type_repr}")
+
+    return inner
+
+
+def is_one_of_factory(legal_values) -> Callable[[Any], None]:
+    callables = [c for c in legal_values if callable(c)]
+    legal_values = [c for c in legal_values if not callable(c)]
+
+    def inner(x) -> None:
+        if x not in legal_values:
+            if not any(c(x) for c in callables):
+                uvals = [str(lval) for lval in legal_values]
+                pp_values = "|".join(uvals)
+                msg = f"Value must be one of {pp_values}"
+                if len(callables):
+                    msg += " or a callable"
+                raise ValueError(msg)
+
+    return inner
+
+
+def is_nonnegative_int(value: object) -> None:
+    """
+    Verify that value is None or a positive int.
+
+    Parameters
+    ----------
+    value : None or int
+            The `value` to be checked.
+
+    Raises
+    ------
+    ValueError
+        When the value is not None or is a negative integer
+    """
+    if value is None:
+        return
+
+    elif isinstance(value, int):
+        if value >= 0:
+            return
+
+    msg = "Value must be a nonnegative integer or None"
+    raise ValueError(msg)
+
+
+# common type validators, for convenience
+# usage: register_option(... , validator = is_int)
+is_int = is_type_factory(int)
+is_bool = is_type_factory(bool)
+is_float = is_type_factory(float)
+is_str = is_type_factory(str)
+is_text = is_instance_factory((str, bytes))
+
+
+def is_callable(obj) -> bool:
+    """
+
+    Parameters
+    ----------
+    `obj` - the object to be checked
+
+    Returns
+    -------
+    validator - returns True if object is callable
+        raises ValueError otherwise.
+
+    """
+    if not callable(obj):
+        raise ValueError("Value must be a callable")
+    return True

AppDir/usr/lib/python3.12/site-packages/pandas/_config/dates.py

@@ -0,0 +1,25 @@
+"""
+config for datetime formatting
+"""
+from __future__ import annotations
+
+from pandas._config import config as cf
+
+pc_date_dayfirst_doc = """
+: boolean
+    When True, prints and parses dates with the day first, eg 20/01/2005
+"""
+
+pc_date_yearfirst_doc = """
+: boolean
+    When True, prints and parses dates with the year first, eg 2005/01/20
+"""
+
+with cf.config_prefix("display"):
+    # Needed upstream of `_libs` because these are used in tslibs.parsing
+    cf.register_option(
+        "date_dayfirst", False, pc_date_dayfirst_doc, validator=cf.is_bool
+    )
+    cf.register_option(
+        "date_yearfirst", False, pc_date_yearfirst_doc, validator=cf.is_bool
+    )

AppDir/usr/lib/python3.12/site-packages/pandas/_config/display.py

@@ -0,0 +1,62 @@
+"""
+Unopinionated display configuration.
+"""
+
+from __future__ import annotations
+
+import locale
+import sys
+
+from pandas._config import config as cf
+
+# -----------------------------------------------------------------------------
+# Global formatting options
+_initial_defencoding: str | None = None
+
+
+def detect_console_encoding() -> str:
+    """
+    Try to find the most capable encoding supported by the console.
+    slightly modified from the way IPython handles the same issue.
+    """
+    global _initial_defencoding
+
+    encoding = None
+    try:
+        encoding = sys.stdout.encoding or sys.stdin.encoding
+    except (AttributeError, OSError):
+        pass
+
+    # try again for something better
+    if not encoding or "ascii" in encoding.lower():
+        try:
+            encoding = locale.getpreferredencoding()
+        except locale.Error:
+            # can be raised by locale.setlocale(), which is
+            #  called by getpreferredencoding
+            #  (on some systems, see stdlib locale docs)
+            pass
+
+    # when all else fails. this will usually be "ascii"
+    if not encoding or "ascii" in encoding.lower():
+        encoding = sys.getdefaultencoding()
+
+    # GH#3360, save the reported defencoding at import time
+    # MPL backends may change it. Make available for debugging.
+    if not _initial_defencoding:
+        _initial_defencoding = sys.getdefaultencoding()
+
+    return encoding
+
+
+pc_encoding_doc = """
+: str/unicode
+    Defaults to the detected encoding of the console.
+    Specifies the encoding to be used for strings returned by to_string,
+    these are generally strings meant to be displayed on the console.
+"""
+
+with cf.config_prefix("display"):
+    cf.register_option(
+        "encoding", detect_console_encoding(), pc_encoding_doc, validator=cf.is_text
+    )

AppDir/usr/lib/python3.12/site-packages/pandas/_config/localization.py

@@ -0,0 +1,172 @@
+"""
+Helpers for configuring locale settings.
+
+Name `localization` is chosen to avoid overlap with builtin `locale` module.
+"""
+from __future__ import annotations
+
+from contextlib import contextmanager
+import locale
+import platform
+import re
+import subprocess
+from typing import TYPE_CHECKING
+
+from pandas._config.config import options
+
+if TYPE_CHECKING:
+    from collections.abc import Generator
+
+
+@contextmanager
+def set_locale(
+    new_locale: str | tuple[str, str], lc_var: int = locale.LC_ALL
+) -> Generator[str | tuple[str, str], None, None]:
+    """
+    Context manager for temporarily setting a locale.
+
+    Parameters
+    ----------
+    new_locale : str or tuple
+        A string of the form <language_country>.<encoding>. For example to set
+        the current locale to US English with a UTF8 encoding, you would pass
+        "en_US.UTF-8".
+    lc_var : int, default `locale.LC_ALL`
+        The category of the locale being set.
+
+    Notes
+    -----
+    This is useful when you want to run a particular block of code under a
+    particular locale, without globally setting the locale. This probably isn't
+    thread-safe.
+    """
+    # getlocale is not always compliant with setlocale, use setlocale. GH#46595
+    current_locale = locale.setlocale(lc_var)
+
+    try:
+        locale.setlocale(lc_var, new_locale)
+        normalized_code, normalized_encoding = locale.getlocale()
+        if normalized_code is not None and normalized_encoding is not None:
+            yield f"{normalized_code}.{normalized_encoding}"
+        else:
+            yield new_locale
+    finally:
+        locale.setlocale(lc_var, current_locale)
+
+
+def can_set_locale(lc: str, lc_var: int = locale.LC_ALL) -> bool:
+    """
+    Check to see if we can set a locale, and subsequently get the locale,
+    without raising an Exception.
+
+    Parameters
+    ----------
+    lc : str
+        The locale to attempt to set.
+    lc_var : int, default `locale.LC_ALL`
+        The category of the locale being set.
+
+    Returns
+    -------
+    bool
+        Whether the passed locale can be set
+    """
+    try:
+        with set_locale(lc, lc_var=lc_var):
+            pass
+    except (ValueError, locale.Error):
+        # horrible name for a Exception subclass
+        return False
+    else:
+        return True
+
+
+def _valid_locales(locales: list[str] | str, normalize: bool) -> list[str]:
+    """
+    Return a list of normalized locales that do not throw an ``Exception``
+    when set.
+
+    Parameters
+    ----------
+    locales : str
+        A string where each locale is separated by a newline.
+    normalize : bool
+        Whether to call ``locale.normalize`` on each locale.
+
+    Returns
+    -------
+    valid_locales : list
+        A list of valid locales.
+    """
+    return [
+        loc
+        for loc in (
+            locale.normalize(loc.strip()) if normalize else loc.strip()
+            for loc in locales
+        )
+        if can_set_locale(loc)
+    ]
+
+
+def get_locales(
+    prefix: str | None = None,
+    normalize: bool = True,
+) -> list[str]:
+    """
+    Get all the locales that are available on the system.
+
+    Parameters
+    ----------
+    prefix : str
+        If not ``None`` then return only those locales with the prefix
+        provided. For example to get all English language locales (those that
+        start with ``"en"``), pass ``prefix="en"``.
+    normalize : bool
+        Call ``locale.normalize`` on the resulting list of available locales.
+        If ``True``, only locales that can be set without throwing an
+        ``Exception`` are returned.
+
+    Returns
+    -------
+    locales : list of strings
+        A list of locale strings that can be set with ``locale.setlocale()``.
+        For example::
+
+            locale.setlocale(locale.LC_ALL, locale_string)
+
+    On error will return an empty list (no locale available, e.g. Windows)
+
+    """
+    if platform.system() in ("Linux", "Darwin"):
+        raw_locales = subprocess.check_output(["locale", "-a"])
+    else:
+        # Other platforms e.g. windows platforms don't define "locale -a"
+        #  Note: is_platform_windows causes circular import here
+        return []
+
+    try:
+        # raw_locales is "\n" separated list of locales
+        # it may contain non-decodable parts, so split
+        # extract what we can and then rejoin.
+        split_raw_locales = raw_locales.split(b"\n")
+        out_locales = []
+        for x in split_raw_locales:
+            try:
+                out_locales.append(str(x, encoding=options.display.encoding))
+            except UnicodeError:
+                # 'locale -a' is used to populated 'raw_locales' and on
+                # Redhat 7 Linux (and maybe others) prints locale names
+                # using windows-1252 encoding.  Bug only triggered by
+                # a few special characters and when there is an
+                # extensive list of installed locales.
+                out_locales.append(str(x, encoding="windows-1252"))
+
+    except TypeError:
+        pass
+
+    if prefix is None:
+        return _valid_locales(out_locales, normalize)
+
+    pattern = re.compile(f"{prefix}.*")
+    found = pattern.findall("\n".join(out_locales))
+    return _valid_locales(found, normalize)

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/__init__.py

@@ -0,0 +1,27 @@
+__all__ = [
+    "NaT",
+    "NaTType",
+    "OutOfBoundsDatetime",
+    "Period",
+    "Timedelta",
+    "Timestamp",
+    "iNaT",
+    "Interval",
+]
+
+
+# Below imports needs to happen first to ensure pandas top level
+# module gets monkeypatched with the pandas_datetime_CAPI
+# see pandas_datetime_exec in pd_datetime.c
+import pandas._libs.pandas_parser  # noqa: E501 # isort: skip # type: ignore[reportUnusedImport]
+import pandas._libs.pandas_datetime  # noqa: F401,E501 # isort: skip # type: ignore[reportUnusedImport]
+from pandas._libs.interval import Interval
+from pandas._libs.tslibs import (
+    NaT,
+    NaTType,
+    OutOfBoundsDatetime,
+    Period,
+    Timedelta,
+    Timestamp,
+    iNaT,
+)

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/algos.pyi

@@ -0,0 +1,416 @@
+from typing import Any
+
+import numpy as np
+
+from pandas._typing import npt
+
+class Infinity:
+    def __eq__(self, other) -> bool: ...
+    def __ne__(self, other) -> bool: ...
+    def __lt__(self, other) -> bool: ...
+    def __le__(self, other) -> bool: ...
+    def __gt__(self, other) -> bool: ...
+    def __ge__(self, other) -> bool: ...
+
+class NegInfinity:
+    def __eq__(self, other) -> bool: ...
+    def __ne__(self, other) -> bool: ...
+    def __lt__(self, other) -> bool: ...
+    def __le__(self, other) -> bool: ...
+    def __gt__(self, other) -> bool: ...
+    def __ge__(self, other) -> bool: ...
+
+def unique_deltas(
+    arr: np.ndarray,  # const int64_t[:]
+) -> np.ndarray: ...  # np.ndarray[np.int64, ndim=1]
+def is_lexsorted(list_of_arrays: list[npt.NDArray[np.int64]]) -> bool: ...
+def groupsort_indexer(
+    index: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+) -> tuple[
+    np.ndarray,  # ndarray[int64_t, ndim=1]
+    np.ndarray,  # ndarray[int64_t, ndim=1]
+]: ...
+def kth_smallest(
+    arr: np.ndarray,  # numeric[:]
+    k: int,
+) -> Any: ...  # numeric
+
+# ----------------------------------------------------------------------
+# Pairwise correlation/covariance
+
+def nancorr(
+    mat: npt.NDArray[np.float64],  # const float64_t[:, :]
+    cov: bool = ...,
+    minp: int | None = ...,
+) -> npt.NDArray[np.float64]: ...  # ndarray[float64_t, ndim=2]
+def nancorr_spearman(
+    mat: npt.NDArray[np.float64],  # ndarray[float64_t, ndim=2]
+    minp: int = ...,
+) -> npt.NDArray[np.float64]: ...  # ndarray[float64_t, ndim=2]
+
+# ----------------------------------------------------------------------
+
+def validate_limit(nobs: int | None, limit=...) -> int: ...
+def get_fill_indexer(
+    mask: npt.NDArray[np.bool_],
+    limit: int | None = None,
+) -> npt.NDArray[np.intp]: ...
+def pad(
+    old: np.ndarray,  # ndarray[numeric_object_t]
+    new: np.ndarray,  # ndarray[numeric_object_t]
+    limit=...,
+) -> npt.NDArray[np.intp]: ...  # np.ndarray[np.intp, ndim=1]
+def pad_inplace(
+    values: np.ndarray,  # numeric_object_t[:]
+    mask: np.ndarray,  # uint8_t[:]
+    limit=...,
+) -> None: ...
+def pad_2d_inplace(
+    values: np.ndarray,  # numeric_object_t[:, :]
+    mask: np.ndarray,  # const uint8_t[:, :]
+    limit=...,
+) -> None: ...
+def backfill(
+    old: np.ndarray,  # ndarray[numeric_object_t]
+    new: np.ndarray,  # ndarray[numeric_object_t]
+    limit=...,
+) -> npt.NDArray[np.intp]: ...  # np.ndarray[np.intp, ndim=1]
+def backfill_inplace(
+    values: np.ndarray,  # numeric_object_t[:]
+    mask: np.ndarray,  # uint8_t[:]
+    limit=...,
+) -> None: ...
+def backfill_2d_inplace(
+    values: np.ndarray,  # numeric_object_t[:, :]
+    mask: np.ndarray,  # const uint8_t[:, :]
+    limit=...,
+) -> None: ...
+def is_monotonic(
+    arr: np.ndarray,  # ndarray[numeric_object_t, ndim=1]
+    timelike: bool,
+) -> tuple[bool, bool, bool]: ...
+
+# ----------------------------------------------------------------------
+# rank_1d, rank_2d
+# ----------------------------------------------------------------------
+
+def rank_1d(
+    values: np.ndarray,  # ndarray[numeric_object_t, ndim=1]
+    labels: np.ndarray | None = ...,  # const int64_t[:]=None
+    is_datetimelike: bool = ...,
+    ties_method=...,
+    ascending: bool = ...,
+    pct: bool = ...,
+    na_option=...,
+    mask: npt.NDArray[np.bool_] | None = ...,
+) -> np.ndarray: ...  # np.ndarray[float64_t, ndim=1]
+def rank_2d(
+    in_arr: np.ndarray,  # ndarray[numeric_object_t, ndim=2]
+    axis: int = ...,
+    is_datetimelike: bool = ...,
+    ties_method=...,
+    ascending: bool = ...,
+    na_option=...,
+    pct: bool = ...,
+) -> np.ndarray: ...  # np.ndarray[float64_t, ndim=1]
+def diff_2d(
+    arr: np.ndarray,  # ndarray[diff_t, ndim=2]
+    out: np.ndarray,  # ndarray[out_t, ndim=2]
+    periods: int,
+    axis: int,
+    datetimelike: bool = ...,
+) -> None: ...
+def ensure_platform_int(arr: object) -> npt.NDArray[np.intp]: ...
+def ensure_object(arr: object) -> npt.NDArray[np.object_]: ...
+def ensure_float64(arr: object) -> npt.NDArray[np.float64]: ...
+def ensure_int8(arr: object) -> npt.NDArray[np.int8]: ...
+def ensure_int16(arr: object) -> npt.NDArray[np.int16]: ...
+def ensure_int32(arr: object) -> npt.NDArray[np.int32]: ...
+def ensure_int64(arr: object) -> npt.NDArray[np.int64]: ...
+def ensure_uint64(arr: object) -> npt.NDArray[np.uint64]: ...
+def take_1d_int8_int8(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int8_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int8_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int8_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int16_int16(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int16_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int16_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int16_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int32_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int32_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int64_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_float32_float32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_float32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_float64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_object_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_bool_bool(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_bool_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int8_int8(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int8_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int8_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int8_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int16_int16(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int16_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int16_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int16_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int32_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int32_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int64_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_float32_float32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_float32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_float64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_object_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_bool_bool(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_bool_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int8_int8(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int8_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int8_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int8_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int16_int16(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int16_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int16_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int16_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int32_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int32_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int64_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_float32_float32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_float32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_float64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_object_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_bool_bool(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_bool_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_multi_int8_int8(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int8_int32(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int8_int64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int8_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int16_int16(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int16_int32(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int16_int64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int16_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int32_int32(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int32_int64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int32_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int64_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_float32_float32(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_float32_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_float64_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_object_object(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_bool_bool(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_bool_object(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int64_int64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/arrays.pyi

@@ -0,0 +1,40 @@
+from typing import Sequence
+
+import numpy as np
+
+from pandas._typing import (
+    AxisInt,
+    DtypeObj,
+    Self,
+    Shape,
+)
+
+class NDArrayBacked:
+    _dtype: DtypeObj
+    _ndarray: np.ndarray
+    def __init__(self, values: np.ndarray, dtype: DtypeObj) -> None: ...
+    @classmethod
+    def _simple_new(cls, values: np.ndarray, dtype: DtypeObj): ...
+    def _from_backing_data(self, values: np.ndarray): ...
+    def __setstate__(self, state): ...
+    def __len__(self) -> int: ...
+    @property
+    def shape(self) -> Shape: ...
+    @property
+    def ndim(self) -> int: ...
+    @property
+    def size(self) -> int: ...
+    @property
+    def nbytes(self) -> int: ...
+    def copy(self): ...
+    def delete(self, loc, axis=...): ...
+    def swapaxes(self, axis1, axis2): ...
+    def repeat(self, repeats: int | Sequence[int], axis: int | None = ...): ...
+    def reshape(self, *args, **kwargs): ...
+    def ravel(self, order=...): ...
+    @property
+    def T(self): ...
+    @classmethod
+    def _concat_same_type(
+        cls, to_concat: Sequence[Self], axis: AxisInt = ...
+    ) -> Self: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/byteswap.pyi

@@ -0,0 +1,5 @@
+def read_float_with_byteswap(data: bytes, offset: int, byteswap: bool) -> float: ...
+def read_double_with_byteswap(data: bytes, offset: int, byteswap: bool) -> float: ...
+def read_uint16_with_byteswap(data: bytes, offset: int, byteswap: bool) -> int: ...
+def read_uint32_with_byteswap(data: bytes, offset: int, byteswap: bool) -> int: ...
+def read_uint64_with_byteswap(data: bytes, offset: int, byteswap: bool) -> int: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/groupby.pyi

@@ -0,0 +1,203 @@
+from typing import Literal
+
+import numpy as np
+
+from pandas._typing import npt
+
+def group_median_float64(
+    out: np.ndarray,  # ndarray[float64_t, ndim=2]
+    counts: npt.NDArray[np.int64],
+    values: np.ndarray,  # ndarray[float64_t, ndim=2]
+    labels: npt.NDArray[np.int64],
+    min_count: int = ...,  # Py_ssize_t
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_cumprod(
+    out: np.ndarray,  # float64_t[:, ::1]
+    values: np.ndarray,  # const float64_t[:, :]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    skipna: bool = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_cumsum(
+    out: np.ndarray,  # int64float_t[:, ::1]
+    values: np.ndarray,  # ndarray[int64float_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    skipna: bool = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_shift_indexer(
+    out: np.ndarray,  # int64_t[::1]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    periods: int,
+) -> None: ...
+def group_fillna_indexer(
+    out: np.ndarray,  # ndarray[intp_t]
+    labels: np.ndarray,  # ndarray[int64_t]
+    sorted_labels: npt.NDArray[np.intp],
+    mask: npt.NDArray[np.uint8],
+    direction: Literal["ffill", "bfill"],
+    limit: int,  # int64_t
+    dropna: bool,
+) -> None: ...
+def group_any_all(
+    out: np.ndarray,  # uint8_t[::1]
+    values: np.ndarray,  # const uint8_t[::1]
+    labels: np.ndarray,  # const int64_t[:]
+    mask: np.ndarray,  # const uint8_t[::1]
+    val_test: Literal["any", "all"],
+    skipna: bool,
+    nullable: bool,
+) -> None: ...
+def group_sum(
+    out: np.ndarray,  # complexfloatingintuint_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[complexfloatingintuint_t, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    mask: np.ndarray | None,
+    result_mask: np.ndarray | None = ...,
+    min_count: int = ...,
+    is_datetimelike: bool = ...,
+) -> None: ...
+def group_prod(
+    out: np.ndarray,  # int64float_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[int64float_t, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    mask: np.ndarray | None,
+    result_mask: np.ndarray | None = ...,
+    min_count: int = ...,
+) -> None: ...
+def group_var(
+    out: np.ndarray,  # floating[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[floating, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    min_count: int = ...,  # Py_ssize_t
+    ddof: int = ...,  # int64_t
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    is_datetimelike: bool = ...,
+    name: str = ...,
+) -> None: ...
+def group_skew(
+    out: np.ndarray,  # float64_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[float64_T, ndim=2]
+    labels: np.ndarray,  # const intp_t[::1]
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    skipna: bool = ...,
+) -> None: ...
+def group_mean(
+    out: np.ndarray,  # floating[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[floating, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    min_count: int = ...,  # Py_ssize_t
+    is_datetimelike: bool = ...,  # bint
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_ohlc(
+    out: np.ndarray,  # floatingintuint_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[floatingintuint_t, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    min_count: int = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_quantile(
+    out: npt.NDArray[np.float64],
+    values: np.ndarray,  # ndarray[numeric, ndim=1]
+    labels: npt.NDArray[np.intp],
+    mask: npt.NDArray[np.uint8],
+    qs: npt.NDArray[np.float64],  # const
+    starts: npt.NDArray[np.int64],
+    ends: npt.NDArray[np.int64],
+    interpolation: Literal["linear", "lower", "higher", "nearest", "midpoint"],
+    result_mask: np.ndarray | None,
+    is_datetimelike: bool,
+) -> None: ...
+def group_last(
+    out: np.ndarray,  # rank_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[rank_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    mask: npt.NDArray[np.bool_] | None,
+    result_mask: npt.NDArray[np.bool_] | None = ...,
+    min_count: int = ...,  # Py_ssize_t
+    is_datetimelike: bool = ...,
+) -> None: ...
+def group_nth(
+    out: np.ndarray,  # rank_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[rank_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    mask: npt.NDArray[np.bool_] | None,
+    result_mask: npt.NDArray[np.bool_] | None = ...,
+    min_count: int = ...,  # int64_t
+    rank: int = ...,  # int64_t
+    is_datetimelike: bool = ...,
+) -> None: ...
+def group_rank(
+    out: np.ndarray,  # float64_t[:, ::1]
+    values: np.ndarray,  # ndarray[rank_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    ties_method: Literal["average", "min", "max", "first", "dense"] = ...,
+    ascending: bool = ...,
+    pct: bool = ...,
+    na_option: Literal["keep", "top", "bottom"] = ...,
+    mask: npt.NDArray[np.bool_] | None = ...,
+) -> None: ...
+def group_max(
+    out: np.ndarray,  # groupby_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[groupby_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    min_count: int = ...,
+    is_datetimelike: bool = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_min(
+    out: np.ndarray,  # groupby_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[groupby_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    min_count: int = ...,
+    is_datetimelike: bool = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_cummin(
+    out: np.ndarray,  # groupby_t[:, ::1]
+    values: np.ndarray,  # ndarray[groupby_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    skipna: bool = ...,
+) -> None: ...
+def group_cummax(
+    out: np.ndarray,  # groupby_t[:, ::1]
+    values: np.ndarray,  # ndarray[groupby_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    skipna: bool = ...,
+) -> None: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/hashing.pyi

@@ -0,0 +1,9 @@
+import numpy as np
+
+from pandas._typing import npt
+
+def hash_object_array(
+    arr: npt.NDArray[np.object_],
+    key: str,
+    encoding: str = ...,
+) -> npt.NDArray[np.uint64]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/hashtable.pyi

@@ -0,0 +1,251 @@
+from typing import (
+    Any,
+    Hashable,
+    Literal,
+)
+
+import numpy as np
+
+from pandas._typing import npt
+
+def unique_label_indices(
+    labels: np.ndarray,  # const int64_t[:]
+) -> np.ndarray: ...
+
+class Factorizer:
+    count: int
+    uniques: Any
+    def __init__(self, size_hint: int) -> None: ...
+    def get_count(self) -> int: ...
+    def factorize(
+        self,
+        values: np.ndarray,
+        sort: bool = ...,
+        na_sentinel=...,
+        na_value=...,
+        mask=...,
+    ) -> npt.NDArray[np.intp]: ...
+
+class ObjectFactorizer(Factorizer):
+    table: PyObjectHashTable
+    uniques: ObjectVector
+
+class Int64Factorizer(Factorizer):
+    table: Int64HashTable
+    uniques: Int64Vector
+
+class UInt64Factorizer(Factorizer):
+    table: UInt64HashTable
+    uniques: UInt64Vector
+
+class Int32Factorizer(Factorizer):
+    table: Int32HashTable
+    uniques: Int32Vector
+
+class UInt32Factorizer(Factorizer):
+    table: UInt32HashTable
+    uniques: UInt32Vector
+
+class Int16Factorizer(Factorizer):
+    table: Int16HashTable
+    uniques: Int16Vector
+
+class UInt16Factorizer(Factorizer):
+    table: UInt16HashTable
+    uniques: UInt16Vector
+
+class Int8Factorizer(Factorizer):
+    table: Int8HashTable
+    uniques: Int8Vector
+
+class UInt8Factorizer(Factorizer):
+    table: UInt8HashTable
+    uniques: UInt8Vector
+
+class Float64Factorizer(Factorizer):
+    table: Float64HashTable
+    uniques: Float64Vector
+
+class Float32Factorizer(Factorizer):
+    table: Float32HashTable
+    uniques: Float32Vector
+
+class Complex64Factorizer(Factorizer):
+    table: Complex64HashTable
+    uniques: Complex64Vector
+
+class Complex128Factorizer(Factorizer):
+    table: Complex128HashTable
+    uniques: Complex128Vector
+
+class Int64Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.int64]: ...
+
+class Int32Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.int32]: ...
+
+class Int16Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.int16]: ...
+
+class Int8Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.int8]: ...
+
+class UInt64Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.uint64]: ...
+
+class UInt32Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.uint32]: ...
+
+class UInt16Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.uint16]: ...
+
+class UInt8Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.uint8]: ...
+
+class Float64Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.float64]: ...
+
+class Float32Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.float32]: ...
+
+class Complex128Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.complex128]: ...
+
+class Complex64Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.complex64]: ...
+
+class StringVector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.object_]: ...
+
+class ObjectVector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.object_]: ...
+
+class HashTable:
+    # NB: The base HashTable class does _not_ actually have these methods;
+    #  we are putting them here for the sake of mypy to avoid
+    #  reproducing them in each subclass below.
+    def __init__(self, size_hint: int = ..., uses_mask: bool = ...) -> None: ...
+    def __len__(self) -> int: ...
+    def __contains__(self, key: Hashable) -> bool: ...
+    def sizeof(self, deep: bool = ...) -> int: ...
+    def get_state(self) -> dict[str, int]: ...
+    # TODO: `item` type is subclass-specific
+    def get_item(self, item): ...  # TODO: return type?
+    def set_item(self, item, val) -> None: ...
+    def get_na(self): ...  # TODO: return type?
+    def set_na(self, val) -> None: ...
+    def map_locations(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        mask: npt.NDArray[np.bool_] | None = ...,
+    ) -> None: ...
+    def lookup(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        mask: npt.NDArray[np.bool_] | None = ...,
+    ) -> npt.NDArray[np.intp]: ...
+    def get_labels(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        uniques,  # SubclassTypeVector
+        count_prior: int = ...,
+        na_sentinel: int = ...,
+        na_value: object = ...,
+        mask=...,
+    ) -> npt.NDArray[np.intp]: ...
+    def unique(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        return_inverse: bool = ...,
+    ) -> (
+        tuple[
+            np.ndarray,  # np.ndarray[subclass-specific]
+            npt.NDArray[np.intp],
+        ]
+        | np.ndarray
+    ): ...  # np.ndarray[subclass-specific]
+    def factorize(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        na_sentinel: int = ...,
+        na_value: object = ...,
+        mask=...,
+    ) -> tuple[np.ndarray, npt.NDArray[np.intp]]: ...  # np.ndarray[subclass-specific]
+
+class Complex128HashTable(HashTable): ...
+class Complex64HashTable(HashTable): ...
+class Float64HashTable(HashTable): ...
+class Float32HashTable(HashTable): ...
+
+class Int64HashTable(HashTable):
+    # Only Int64HashTable has get_labels_groupby, map_keys_to_values
+    def get_labels_groupby(
+        self,
+        values: npt.NDArray[np.int64],  # const int64_t[:]
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.int64]]: ...
+    def map_keys_to_values(
+        self,
+        keys: npt.NDArray[np.int64],
+        values: npt.NDArray[np.int64],  # const int64_t[:]
+    ) -> None: ...
+
+class Int32HashTable(HashTable): ...
+class Int16HashTable(HashTable): ...
+class Int8HashTable(HashTable): ...
+class UInt64HashTable(HashTable): ...
+class UInt32HashTable(HashTable): ...
+class UInt16HashTable(HashTable): ...
+class UInt8HashTable(HashTable): ...
+class StringHashTable(HashTable): ...
+class PyObjectHashTable(HashTable): ...
+class IntpHashTable(HashTable): ...
+
+def duplicated(
+    values: np.ndarray,
+    keep: Literal["last", "first", False] = ...,
+    mask: npt.NDArray[np.bool_] | None = ...,
+) -> npt.NDArray[np.bool_]: ...
+def mode(
+    values: np.ndarray, dropna: bool, mask: npt.NDArray[np.bool_] | None = ...
+) -> np.ndarray: ...
+def value_count(
+    values: np.ndarray,
+    dropna: bool,
+    mask: npt.NDArray[np.bool_] | None = ...,
+) -> tuple[np.ndarray, npt.NDArray[np.int64]]: ...  # np.ndarray[same-as-values]
+
+# arr and values should have same dtype
+def ismember(
+    arr: np.ndarray,
+    values: np.ndarray,
+) -> npt.NDArray[np.bool_]: ...
+def object_hash(obj) -> int: ...
+def objects_are_equal(a, b) -> bool: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/index.pyi

@@ -0,0 +1,107 @@
+import numpy as np
+
+from pandas._typing import npt
+
+from pandas import MultiIndex
+from pandas.core.arrays import ExtensionArray
+
+multiindex_nulls_shift: int
+
+class IndexEngine:
+    over_size_threshold: bool
+    def __init__(self, values: np.ndarray) -> None: ...
+    def __contains__(self, val: object) -> bool: ...
+
+    # -> int | slice | np.ndarray[bool]
+    def get_loc(self, val: object) -> int | slice | np.ndarray: ...
+    def sizeof(self, deep: bool = ...) -> int: ...
+    def __sizeof__(self) -> int: ...
+    @property
+    def is_unique(self) -> bool: ...
+    @property
+    def is_monotonic_increasing(self) -> bool: ...
+    @property
+    def is_monotonic_decreasing(self) -> bool: ...
+    @property
+    def is_mapping_populated(self) -> bool: ...
+    def clear_mapping(self): ...
+    def get_indexer(self, values: np.ndarray) -> npt.NDArray[np.intp]: ...
+    def get_indexer_non_unique(
+        self,
+        targets: np.ndarray,
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+
+class MaskedIndexEngine(IndexEngine):
+    def __init__(self, values: object) -> None: ...
+    def get_indexer_non_unique(
+        self, targets: object
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+
+class Float64Engine(IndexEngine): ...
+class Float32Engine(IndexEngine): ...
+class Complex128Engine(IndexEngine): ...
+class Complex64Engine(IndexEngine): ...
+class Int64Engine(IndexEngine): ...
+class Int32Engine(IndexEngine): ...
+class Int16Engine(IndexEngine): ...
+class Int8Engine(IndexEngine): ...
+class UInt64Engine(IndexEngine): ...
+class UInt32Engine(IndexEngine): ...
+class UInt16Engine(IndexEngine): ...
+class UInt8Engine(IndexEngine): ...
+class ObjectEngine(IndexEngine): ...
+class DatetimeEngine(Int64Engine): ...
+class TimedeltaEngine(DatetimeEngine): ...
+class PeriodEngine(Int64Engine): ...
+class BoolEngine(UInt8Engine): ...
+class MaskedFloat64Engine(MaskedIndexEngine): ...
+class MaskedFloat32Engine(MaskedIndexEngine): ...
+class MaskedComplex128Engine(MaskedIndexEngine): ...
+class MaskedComplex64Engine(MaskedIndexEngine): ...
+class MaskedInt64Engine(MaskedIndexEngine): ...
+class MaskedInt32Engine(MaskedIndexEngine): ...
+class MaskedInt16Engine(MaskedIndexEngine): ...
+class MaskedInt8Engine(MaskedIndexEngine): ...
+class MaskedUInt64Engine(MaskedIndexEngine): ...
+class MaskedUInt32Engine(MaskedIndexEngine): ...
+class MaskedUInt16Engine(MaskedIndexEngine): ...
+class MaskedUInt8Engine(MaskedIndexEngine): ...
+class MaskedBoolEngine(MaskedUInt8Engine): ...
+
+class BaseMultiIndexCodesEngine:
+    levels: list[np.ndarray]
+    offsets: np.ndarray  # ndarray[uint64_t, ndim=1]
+
+    def __init__(
+        self,
+        levels: list[np.ndarray],  # all entries hashable
+        labels: list[np.ndarray],  # all entries integer-dtyped
+        offsets: np.ndarray,  # np.ndarray[np.uint64, 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: ...
+    def get_indexer_with_fill(
+        self,
+        target: np.ndarray,  # np.ndarray[object] of tuples
+        values: np.ndarray,  # np.ndarray[object] of tuples
+        method: str,
+        limit: int | None,
+    ) -> npt.NDArray[np.intp]: ...
+
+class ExtensionEngine:
+    def __init__(self, values: ExtensionArray) -> None: ...
+    def __contains__(self, val: object) -> bool: ...
+    def get_loc(self, val: object) -> int | slice | np.ndarray: ...
+    def get_indexer(self, values: np.ndarray) -> npt.NDArray[np.intp]: ...
+    def get_indexer_non_unique(
+        self,
+        targets: np.ndarray,
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+    @property
+    def is_unique(self) -> bool: ...
+    @property
+    def is_monotonic_increasing(self) -> bool: ...
+    @property
+    def is_monotonic_decreasing(self) -> bool: ...
+    def sizeof(self, deep: bool = ...) -> int: ...
+    def clear_mapping(self): ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/indexing.pyi

@@ -0,0 +1,17 @@
+from typing import (
+    Generic,
+    TypeVar,
+)
+
+from pandas.core.indexing import IndexingMixin
+
+_IndexingMixinT = TypeVar("_IndexingMixinT", bound=IndexingMixin)
+
+class NDFrameIndexerBase(Generic[_IndexingMixinT]):
+    name: str
+    # in practice obj is either a DataFrame or a Series
+    obj: _IndexingMixinT
+
+    def __init__(self, name: str, obj: _IndexingMixinT) -> None: ...
+    @property
+    def ndim(self) -> int: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/internals.pyi

@@ -0,0 +1,106 @@
+from typing import (
+    Iterator,
+    Sequence,
+    final,
+    overload,
+)
+import weakref
+
+import numpy as np
+
+from pandas._typing import (
+    ArrayLike,
+    Self,
+    npt,
+)
+
+from pandas import Index
+from pandas.core.arrays._mixins import NDArrayBackedExtensionArray
+from pandas.core.internals.blocks import Block as B
+
+def slice_len(slc: slice, objlen: int = ...) -> int: ...
+def get_concat_blkno_indexers(
+    blknos_list: list[npt.NDArray[np.intp]],
+) -> list[tuple[npt.NDArray[np.intp], BlockPlacement]]: ...
+def get_blkno_indexers(
+    blknos: np.ndarray,  # int64_t[:]
+    group: bool = ...,
+) -> list[tuple[int, slice | np.ndarray]]: ...
+def get_blkno_placements(
+    blknos: np.ndarray,
+    group: bool = ...,
+) -> Iterator[tuple[int, BlockPlacement]]: ...
+def update_blklocs_and_blknos(
+    blklocs: npt.NDArray[np.intp],
+    blknos: npt.NDArray[np.intp],
+    loc: int,
+    nblocks: int,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+@final
+class BlockPlacement:
+    def __init__(self, val: int | slice | np.ndarray) -> None: ...
+    @property
+    def indexer(self) -> np.ndarray | slice: ...
+    @property
+    def as_array(self) -> np.ndarray: ...
+    @property
+    def as_slice(self) -> slice: ...
+    @property
+    def is_slice_like(self) -> bool: ...
+    @overload
+    def __getitem__(
+        self, loc: slice | Sequence[int] | npt.NDArray[np.intp]
+    ) -> BlockPlacement: ...
+    @overload
+    def __getitem__(self, loc: int) -> int: ...
+    def __iter__(self) -> Iterator[int]: ...
+    def __len__(self) -> int: ...
+    def delete(self, loc) -> BlockPlacement: ...
+    def add(self, other) -> BlockPlacement: ...
+    def append(self, others: list[BlockPlacement]) -> BlockPlacement: ...
+    def tile_for_unstack(self, factor: int) -> npt.NDArray[np.intp]: ...
+
+class SharedBlock:
+    _mgr_locs: BlockPlacement
+    ndim: int
+    values: ArrayLike
+    refs: BlockValuesRefs
+    def __init__(
+        self,
+        values: ArrayLike,
+        placement: BlockPlacement,
+        ndim: int,
+        refs: BlockValuesRefs | None = ...,
+    ) -> None: ...
+
+class NumpyBlock(SharedBlock):
+    values: np.ndarray
+    @final
+    def slice_block_rows(self, slicer: slice) -> Self: ...
+
+class NDArrayBackedBlock(SharedBlock):
+    values: NDArrayBackedExtensionArray
+    @final
+    def slice_block_rows(self, slicer: slice) -> Self: ...
+
+class Block(SharedBlock): ...
+
+class BlockManager:
+    blocks: tuple[B, ...]
+    axes: list[Index]
+    _known_consolidated: bool
+    _is_consolidated: bool
+    _blknos: np.ndarray
+    _blklocs: np.ndarray
+    def __init__(
+        self, blocks: tuple[B, ...], axes: list[Index], verify_integrity=...
+    ) -> None: ...
+    def get_slice(self, slobj: slice, axis: int = ...) -> Self: ...
+    def _rebuild_blknos_and_blklocs(self) -> None: ...
+
+class BlockValuesRefs:
+    referenced_blocks: list[weakref.ref]
+    def __init__(self, blk: SharedBlock | None = ...) -> None: ...
+    def add_reference(self, blk: SharedBlock) -> None: ...
+    def add_index_reference(self, index: Index) -> None: ...
+    def has_reference(self) -> bool: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/interval.pyi

@@ -0,0 +1,174 @@
+from typing import (
+    Any,
+    Generic,
+    TypeVar,
+    overload,
+)
+
+import numpy as np
+import numpy.typing as npt
+
+from pandas._typing import (
+    IntervalClosedType,
+    Timedelta,
+    Timestamp,
+)
+
+VALID_CLOSED: frozenset[str]
+
+_OrderableScalarT = TypeVar("_OrderableScalarT", int, float)
+_OrderableTimesT = TypeVar("_OrderableTimesT", Timestamp, Timedelta)
+_OrderableT = TypeVar("_OrderableT", int, float, Timestamp, Timedelta)
+
+class _LengthDescriptor:
+    @overload
+    def __get__(
+        self, instance: Interval[_OrderableScalarT], owner: Any
+    ) -> _OrderableScalarT: ...
+    @overload
+    def __get__(
+        self, instance: Interval[_OrderableTimesT], owner: Any
+    ) -> Timedelta: ...
+
+class _MidDescriptor:
+    @overload
+    def __get__(self, instance: Interval[_OrderableScalarT], owner: Any) -> float: ...
+    @overload
+    def __get__(
+        self, instance: Interval[_OrderableTimesT], owner: Any
+    ) -> _OrderableTimesT: ...
+
+class IntervalMixin:
+    @property
+    def closed_left(self) -> bool: ...
+    @property
+    def closed_right(self) -> bool: ...
+    @property
+    def open_left(self) -> bool: ...
+    @property
+    def open_right(self) -> bool: ...
+    @property
+    def is_empty(self) -> bool: ...
+    def _check_closed_matches(self, other: IntervalMixin, name: str = ...) -> None: ...
+
+class Interval(IntervalMixin, Generic[_OrderableT]):
+    @property
+    def left(self: Interval[_OrderableT]) -> _OrderableT: ...
+    @property
+    def right(self: Interval[_OrderableT]) -> _OrderableT: ...
+    @property
+    def closed(self) -> IntervalClosedType: ...
+    mid: _MidDescriptor
+    length: _LengthDescriptor
+    def __init__(
+        self,
+        left: _OrderableT,
+        right: _OrderableT,
+        closed: IntervalClosedType = ...,
+    ) -> None: ...
+    def __hash__(self) -> int: ...
+    @overload
+    def __contains__(
+        self: Interval[Timedelta], key: Timedelta | Interval[Timedelta]
+    ) -> bool: ...
+    @overload
+    def __contains__(
+        self: Interval[Timestamp], key: Timestamp | Interval[Timestamp]
+    ) -> bool: ...
+    @overload
+    def __contains__(
+        self: Interval[_OrderableScalarT],
+        key: _OrderableScalarT | Interval[_OrderableScalarT],
+    ) -> bool: ...
+    @overload
+    def __add__(
+        self: Interval[_OrderableTimesT], y: Timedelta
+    ) -> Interval[_OrderableTimesT]: ...
+    @overload
+    def __add__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __add__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __radd__(
+        self: Interval[_OrderableTimesT], y: Timedelta
+    ) -> Interval[_OrderableTimesT]: ...
+    @overload
+    def __radd__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __radd__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __sub__(
+        self: Interval[_OrderableTimesT], y: Timedelta
+    ) -> Interval[_OrderableTimesT]: ...
+    @overload
+    def __sub__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __sub__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __rsub__(
+        self: Interval[_OrderableTimesT], y: Timedelta
+    ) -> Interval[_OrderableTimesT]: ...
+    @overload
+    def __rsub__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __rsub__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __mul__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __mul__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __rmul__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __rmul__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __truediv__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __truediv__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __floordiv__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __floordiv__(self: Interval[float], y: float) -> Interval[float]: ...
+    def overlaps(self: Interval[_OrderableT], other: Interval[_OrderableT]) -> bool: ...
+
+def intervals_to_interval_bounds(
+    intervals: np.ndarray, validate_closed: bool = ...
+) -> tuple[np.ndarray, np.ndarray, IntervalClosedType]: ...
+
+class IntervalTree(IntervalMixin):
+    def __init__(
+        self,
+        left: np.ndarray,
+        right: np.ndarray,
+        closed: IntervalClosedType = ...,
+        leaf_size: int = ...,
+    ) -> None: ...
+    @property
+    def mid(self) -> np.ndarray: ...
+    @property
+    def length(self) -> np.ndarray: ...
+    def get_indexer(self, target) -> npt.NDArray[np.intp]: ...
+    def get_indexer_non_unique(
+        self, target
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+    _na_count: int
+    @property
+    def is_overlapping(self) -> bool: ...
+    @property
+    def is_monotonic_increasing(self) -> bool: ...
+    def clear_mapping(self) -> None: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/join.pyi

@@ -0,0 +1,78 @@
+import numpy as np
+
+from pandas._typing import npt
+
+def inner_join(
+    left: np.ndarray,  # const intp_t[:]
+    right: np.ndarray,  # const intp_t[:]
+    max_groups: int,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def left_outer_join(
+    left: np.ndarray,  # const intp_t[:]
+    right: np.ndarray,  # const intp_t[:]
+    max_groups: int,
+    sort: bool = ...,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def full_outer_join(
+    left: np.ndarray,  # const intp_t[:]
+    right: np.ndarray,  # const intp_t[:]
+    max_groups: int,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def ffill_indexer(
+    indexer: np.ndarray,  # const intp_t[:]
+) -> npt.NDArray[np.intp]: ...
+def left_join_indexer_unique(
+    left: np.ndarray,  # ndarray[join_t]
+    right: np.ndarray,  # ndarray[join_t]
+) -> npt.NDArray[np.intp]: ...
+def left_join_indexer(
+    left: np.ndarray,  # ndarray[join_t]
+    right: np.ndarray,  # ndarray[join_t]
+) -> tuple[
+    np.ndarray,  # np.ndarray[join_t]
+    npt.NDArray[np.intp],
+    npt.NDArray[np.intp],
+]: ...
+def inner_join_indexer(
+    left: np.ndarray,  # ndarray[join_t]
+    right: np.ndarray,  # ndarray[join_t]
+) -> tuple[
+    np.ndarray,  # np.ndarray[join_t]
+    npt.NDArray[np.intp],
+    npt.NDArray[np.intp],
+]: ...
+def outer_join_indexer(
+    left: np.ndarray,  # ndarray[join_t]
+    right: np.ndarray,  # ndarray[join_t]
+) -> tuple[
+    np.ndarray,  # np.ndarray[join_t]
+    npt.NDArray[np.intp],
+    npt.NDArray[np.intp],
+]: ...
+def asof_join_backward_on_X_by_Y(
+    left_values: np.ndarray,  # ndarray[numeric_t]
+    right_values: np.ndarray,  # ndarray[numeric_t]
+    left_by_values: np.ndarray,  # ndarray[by_t]
+    right_by_values: np.ndarray,  # ndarray[by_t]
+    allow_exact_matches: bool = ...,
+    tolerance: np.number | float | None = ...,
+    use_hashtable: bool = ...,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def asof_join_forward_on_X_by_Y(
+    left_values: np.ndarray,  # ndarray[numeric_t]
+    right_values: np.ndarray,  # ndarray[numeric_t]
+    left_by_values: np.ndarray,  # ndarray[by_t]
+    right_by_values: np.ndarray,  # ndarray[by_t]
+    allow_exact_matches: bool = ...,
+    tolerance: np.number | float | None = ...,
+    use_hashtable: bool = ...,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def asof_join_nearest_on_X_by_Y(
+    left_values: np.ndarray,  # ndarray[numeric_t]
+    right_values: np.ndarray,  # ndarray[numeric_t]
+    left_by_values: np.ndarray,  # ndarray[by_t]
+    right_by_values: np.ndarray,  # ndarray[by_t]
+    allow_exact_matches: bool = ...,
+    tolerance: np.number | float | None = ...,
+    use_hashtable: bool = ...,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/json.pyi

@@ -0,0 +1,23 @@
+from typing import (
+    Any,
+    Callable,
+)
+
+def ujson_dumps(
+    obj: Any,
+    ensure_ascii: bool = ...,
+    double_precision: int = ...,
+    indent: int = ...,
+    orient: str = ...,
+    date_unit: str = ...,
+    iso_dates: bool = ...,
+    default_handler: None
+    | Callable[[Any], str | float | bool | list | dict | None] = ...,
+) -> str: ...
+def ujson_loads(
+    s: str,
+    precise_float: bool = ...,
+    numpy: bool = ...,
+    dtype: None = ...,
+    labelled: bool = ...,
+) -> Any: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/lib.pyi

@@ -0,0 +1,207 @@
+# TODO(npdtypes): Many types specified here can be made more specific/accurate;
+#  the more specific versions are specified in comments
+from decimal import Decimal
+from typing import (
+    Any,
+    Callable,
+    Final,
+    Generator,
+    Hashable,
+    Literal,
+    TypeAlias,
+    overload,
+)
+
+import numpy as np
+
+from pandas._libs.interval import Interval
+from pandas._libs.tslibs import Period
+from pandas._typing import (
+    ArrayLike,
+    DtypeObj,
+    TypeGuard,
+    npt,
+)
+
+# placeholder until we can specify np.ndarray[object, ndim=2]
+ndarray_obj_2d = np.ndarray
+
+from enum import Enum
+
+class _NoDefault(Enum):
+    no_default = ...
+
+no_default: Final = _NoDefault.no_default
+NoDefault: TypeAlias = Literal[_NoDefault.no_default]
+
+i8max: int
+u8max: int
+
+def is_np_dtype(dtype: object, kinds: str | None = ...) -> TypeGuard[np.dtype]: ...
+def item_from_zerodim(val: object) -> object: ...
+def infer_dtype(value: object, skipna: bool = ...) -> str: ...
+def is_iterator(obj: object) -> bool: ...
+def is_scalar(val: object) -> bool: ...
+def is_list_like(obj: object, allow_sets: bool = ...) -> bool: ...
+def is_pyarrow_array(obj: object) -> bool: ...
+def is_period(val: object) -> TypeGuard[Period]: ...
+def is_interval(val: object) -> TypeGuard[Interval]: ...
+def is_decimal(val: object) -> TypeGuard[Decimal]: ...
+def is_complex(val: object) -> TypeGuard[complex]: ...
+def is_bool(val: object) -> TypeGuard[bool | np.bool_]: ...
+def is_integer(val: object) -> TypeGuard[int | np.integer]: ...
+def is_int_or_none(obj) -> bool: ...
+def is_float(val: object) -> TypeGuard[float]: ...
+def is_interval_array(values: np.ndarray) -> bool: ...
+def is_datetime64_array(values: np.ndarray) -> bool: ...
+def is_timedelta_or_timedelta64_array(values: np.ndarray) -> bool: ...
+def is_datetime_with_singletz_array(values: np.ndarray) -> bool: ...
+def is_time_array(values: np.ndarray, skipna: bool = ...): ...
+def is_date_array(values: np.ndarray, skipna: bool = ...): ...
+def is_datetime_array(values: np.ndarray, skipna: bool = ...): ...
+def is_string_array(values: np.ndarray, skipna: bool = ...): ...
+def is_float_array(values: np.ndarray, skipna: bool = ...): ...
+def is_integer_array(values: np.ndarray, skipna: bool = ...): ...
+def is_bool_array(values: np.ndarray, skipna: bool = ...): ...
+def fast_multiget(mapping: dict, keys: np.ndarray, default=...) -> np.ndarray: ...
+def fast_unique_multiple_list_gen(gen: Generator, sort: bool = ...) -> list: ...
+def fast_unique_multiple_list(lists: list, sort: bool | None = ...) -> list: ...
+def map_infer(
+    arr: np.ndarray,
+    f: Callable[[Any], Any],
+    convert: bool = ...,
+    ignore_na: bool = ...,
+) -> np.ndarray: ...
+@overload
+def maybe_convert_objects(
+    objects: npt.NDArray[np.object_],
+    *,
+    try_float: bool = ...,
+    safe: bool = ...,
+    convert_numeric: bool = ...,
+    convert_non_numeric: Literal[False] = ...,
+    convert_to_nullable_dtype: Literal[False] = ...,
+    dtype_if_all_nat: DtypeObj | None = ...,
+) -> npt.NDArray[np.object_ | np.number]: ...
+@overload
+def maybe_convert_objects(
+    objects: npt.NDArray[np.object_],
+    *,
+    try_float: bool = ...,
+    safe: bool = ...,
+    convert_numeric: bool = ...,
+    convert_non_numeric: bool = ...,
+    convert_to_nullable_dtype: Literal[True] = ...,
+    dtype_if_all_nat: DtypeObj | None = ...,
+) -> ArrayLike: ...
+@overload
+def maybe_convert_objects(
+    objects: npt.NDArray[np.object_],
+    *,
+    try_float: bool = ...,
+    safe: bool = ...,
+    convert_numeric: bool = ...,
+    convert_non_numeric: bool = ...,
+    convert_to_nullable_dtype: bool = ...,
+    dtype_if_all_nat: DtypeObj | None = ...,
+) -> ArrayLike: ...
+@overload
+def maybe_convert_numeric(
+    values: npt.NDArray[np.object_],
+    na_values: set,
+    convert_empty: bool = ...,
+    coerce_numeric: bool = ...,
+    convert_to_masked_nullable: Literal[False] = ...,
+) -> tuple[np.ndarray, None]: ...
+@overload
+def maybe_convert_numeric(
+    values: npt.NDArray[np.object_],
+    na_values: set,
+    convert_empty: bool = ...,
+    coerce_numeric: bool = ...,
+    *,
+    convert_to_masked_nullable: Literal[True],
+) -> tuple[np.ndarray, np.ndarray]: ...
+
+# TODO: restrict `arr`?
+def ensure_string_array(
+    arr,
+    na_value: object = ...,
+    convert_na_value: bool = ...,
+    copy: bool = ...,
+    skipna: bool = ...,
+) -> npt.NDArray[np.object_]: ...
+def convert_nans_to_NA(
+    arr: npt.NDArray[np.object_],
+) -> npt.NDArray[np.object_]: ...
+def fast_zip(ndarrays: list) -> npt.NDArray[np.object_]: ...
+
+# TODO: can we be more specific about rows?
+def to_object_array_tuples(rows: object) -> ndarray_obj_2d: ...
+def tuples_to_object_array(
+    tuples: npt.NDArray[np.object_],
+) -> ndarray_obj_2d: ...
+
+# TODO: can we be more specific about rows?
+def to_object_array(rows: object, min_width: int = ...) -> ndarray_obj_2d: ...
+def dicts_to_array(dicts: list, columns: list) -> ndarray_obj_2d: ...
+def maybe_booleans_to_slice(
+    mask: npt.NDArray[np.uint8],
+) -> slice | npt.NDArray[np.uint8]: ...
+def maybe_indices_to_slice(
+    indices: npt.NDArray[np.intp],
+    max_len: int,
+) -> slice | npt.NDArray[np.intp]: ...
+def is_all_arraylike(obj: list) -> bool: ...
+
+# -----------------------------------------------------------------
+# Functions which in reality take memoryviews
+
+def memory_usage_of_objects(arr: np.ndarray) -> int: ...  # object[:]  # np.int64
+def map_infer_mask(
+    arr: np.ndarray,
+    f: Callable[[Any], Any],
+    mask: np.ndarray,  # const uint8_t[:]
+    convert: bool = ...,
+    na_value: Any = ...,
+    dtype: np.dtype = ...,
+) -> np.ndarray: ...
+def indices_fast(
+    index: npt.NDArray[np.intp],
+    labels: np.ndarray,  # const int64_t[:]
+    keys: list,
+    sorted_labels: list[npt.NDArray[np.int64]],
+) -> dict[Hashable, npt.NDArray[np.intp]]: ...
+def generate_slices(
+    labels: np.ndarray, ngroups: int  # const intp_t[:]
+) -> tuple[npt.NDArray[np.int64], npt.NDArray[np.int64]]: ...
+def count_level_2d(
+    mask: np.ndarray,  # ndarray[uint8_t, ndim=2, cast=True],
+    labels: np.ndarray,  # const intp_t[:]
+    max_bin: int,
+) -> np.ndarray: ...  # np.ndarray[np.int64, ndim=2]
+def get_level_sorter(
+    label: np.ndarray,  # const int64_t[:]
+    starts: np.ndarray,  # const intp_t[:]
+) -> np.ndarray: ...  # np.ndarray[np.intp, ndim=1]
+def generate_bins_dt64(
+    values: npt.NDArray[np.int64],
+    binner: np.ndarray,  # const int64_t[:]
+    closed: object = ...,
+    hasnans: bool = ...,
+) -> np.ndarray: ...  # np.ndarray[np.int64, ndim=1]
+def array_equivalent_object(
+    left: npt.NDArray[np.object_],
+    right: npt.NDArray[np.object_],
+) -> bool: ...
+def has_infs(arr: np.ndarray) -> bool: ...  # const floating[:]
+def has_only_ints_or_nan(arr: np.ndarray) -> bool: ...  # const floating[:]
+def get_reverse_indexer(
+    indexer: np.ndarray,  # const intp_t[:]
+    length: int,
+) -> npt.NDArray[np.intp]: ...
+def is_bool_list(obj: list) -> bool: ...
+def dtypes_all_equal(types: list[DtypeObj]) -> bool: ...
+def is_range_indexer(
+    left: np.ndarray, n: int  # np.ndarray[np.int64, ndim=1]
+) -> bool: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/missing.pyi

@@ -0,0 +1,17 @@
+import numpy as np
+from numpy import typing as npt
+
+class NAType:
+    def __new__(cls, *args, **kwargs): ...
+
+NA: NAType
+
+def is_matching_na(
+    left: object, right: object, nan_matches_none: bool = ...
+) -> bool: ...
+def isposinf_scalar(val: object) -> bool: ...
+def isneginf_scalar(val: object) -> bool: ...
+def checknull(val: object, inf_as_na: bool = ...) -> bool: ...
+def isnaobj(arr: np.ndarray, inf_as_na: bool = ...) -> npt.NDArray[np.bool_]: ...
+def is_numeric_na(values: np.ndarray) -> npt.NDArray[np.bool_]: ...
+def is_float_nan(values: np.ndarray) -> npt.NDArray[np.bool_]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/ops.pyi

@@ -0,0 +1,51 @@
+from typing import (
+    Any,
+    Callable,
+    Iterable,
+    Literal,
+    TypeAlias,
+    overload,
+)
+
+import numpy as np
+
+from pandas._typing import npt
+
+_BinOp: TypeAlias = Callable[[Any, Any], Any]
+_BoolOp: TypeAlias = Callable[[Any, Any], bool]
+
+def scalar_compare(
+    values: np.ndarray,  # object[:]
+    val: object,
+    op: _BoolOp,  # {operator.eq, operator.ne, ...}
+) -> npt.NDArray[np.bool_]: ...
+def vec_compare(
+    left: npt.NDArray[np.object_],
+    right: npt.NDArray[np.object_],
+    op: _BoolOp,  # {operator.eq, operator.ne, ...}
+) -> npt.NDArray[np.bool_]: ...
+def scalar_binop(
+    values: np.ndarray,  # object[:]
+    val: object,
+    op: _BinOp,  # binary operator
+) -> np.ndarray: ...
+def vec_binop(
+    left: np.ndarray,  # object[:]
+    right: np.ndarray,  # object[:]
+    op: _BinOp,  # binary operator
+) -> np.ndarray: ...
+@overload
+def maybe_convert_bool(
+    arr: npt.NDArray[np.object_],
+    true_values: Iterable = ...,
+    false_values: Iterable = ...,
+    convert_to_masked_nullable: Literal[False] = ...,
+) -> tuple[np.ndarray, None]: ...
+@overload
+def maybe_convert_bool(
+    arr: npt.NDArray[np.object_],
+    true_values: Iterable = ...,
+    false_values: Iterable = ...,
+    *,
+    convert_to_masked_nullable: Literal[True],
+) -> tuple[np.ndarray, np.ndarray]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/ops_dispatch.pyi

@@ -0,0 +1,5 @@
+import numpy as np
+
+def maybe_dispatch_ufunc_to_dunder_op(
+    self, ufunc: np.ufunc, method: str, *inputs, **kwargs
+): ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/parsers.pyi

@@ -0,0 +1,77 @@
+from typing import (
+    Hashable,
+    Literal,
+)
+
+import numpy as np
+
+from pandas._typing import (
+    ArrayLike,
+    Dtype,
+    npt,
+)
+
+STR_NA_VALUES: set[str]
+DEFAULT_BUFFER_HEURISTIC: int
+
+def sanitize_objects(
+    values: npt.NDArray[np.object_],
+    na_values: set,
+) -> int: ...
+
+class TextReader:
+    unnamed_cols: set[str]
+    table_width: int  # int64_t
+    leading_cols: int  # int64_t
+    header: list[list[int]]  # non-negative integers
+    def __init__(
+        self,
+        source,
+        delimiter: bytes | str = ...,  # single-character only
+        header=...,
+        header_start: int = ...,  # int64_t
+        header_end: int = ...,  # uint64_t
+        index_col=...,
+        names=...,
+        tokenize_chunksize: int = ...,  # int64_t
+        delim_whitespace: bool = ...,
+        converters=...,
+        skipinitialspace: bool = ...,
+        escapechar: bytes | str | None = ...,  # single-character only
+        doublequote: bool = ...,
+        quotechar: str | bytes | None = ...,  # at most 1 character
+        quoting: int = ...,
+        lineterminator: bytes | str | None = ...,  # at most 1 character
+        comment=...,
+        decimal: bytes | str = ...,  # single-character only
+        thousands: bytes | str | None = ...,  # single-character only
+        dtype: Dtype | dict[Hashable, Dtype] = ...,
+        usecols=...,
+        error_bad_lines: bool = ...,
+        warn_bad_lines: bool = ...,
+        na_filter: bool = ...,
+        na_values=...,
+        na_fvalues=...,
+        keep_default_na: bool = ...,
+        true_values=...,
+        false_values=...,
+        allow_leading_cols: bool = ...,
+        skiprows=...,
+        skipfooter: int = ...,  # int64_t
+        verbose: bool = ...,
+        float_precision: Literal["round_trip", "legacy", "high"] | None = ...,
+        skip_blank_lines: bool = ...,
+        encoding_errors: bytes | str = ...,
+    ) -> None: ...
+    def set_noconvert(self, i: int) -> None: ...
+    def remove_noconvert(self, i: int) -> None: ...
+    def close(self) -> None: ...
+    def read(self, rows: int | None = ...) -> dict[int, ArrayLike]: ...
+    def read_low_memory(self, rows: int | None) -> list[dict[int, ArrayLike]]: ...
+
+# _maybe_upcast, na_values are only exposed for testing
+na_values: dict
+
+def _maybe_upcast(
+    arr, use_dtype_backend: bool = ..., dtype_backend: str = ...
+) -> np.ndarray: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/properties.pyi

@@ -0,0 +1,27 @@
+from typing import (
+    Sequence,
+    overload,
+)
+
+from pandas._typing import (
+    AnyArrayLike,
+    DataFrame,
+    Index,
+    Series,
+)
+
+# note: this is a lie to make type checkers happy (they special
+# case property). cache_readonly uses attribute names similar to
+# property (fget) but it does not provide fset and fdel.
+cache_readonly = property
+
+class AxisProperty:
+    axis: int
+    def __init__(self, axis: int = ..., doc: str = ...) -> None: ...
+    @overload
+    def __get__(self, obj: DataFrame | Series, type) -> Index: ...
+    @overload
+    def __get__(self, obj: None, type) -> AxisProperty: ...
+    def __set__(
+        self, obj: DataFrame | Series, value: AnyArrayLike | Sequence
+    ) -> None: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/reshape.pyi

@@ -0,0 +1,16 @@
+import numpy as np
+
+from pandas._typing import npt
+
+def unstack(
+    values: np.ndarray,  # reshape_t[:, :]
+    mask: np.ndarray,  # const uint8_t[:]
+    stride: int,
+    length: int,
+    width: int,
+    new_values: np.ndarray,  # reshape_t[:, :]
+    new_mask: np.ndarray,  # uint8_t[:, :]
+) -> None: ...
+def explode(
+    values: npt.NDArray[np.object_],
+) -> tuple[npt.NDArray[np.object_], npt.NDArray[np.int64]]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/sas.pyi

@@ -0,0 +1,7 @@
+from pandas.io.sas.sas7bdat import SAS7BDATReader
+
+class Parser:
+    def __init__(self, parser: SAS7BDATReader) -> None: ...
+    def read(self, nrows: int) -> None: ...
+
+def get_subheader_index(signature: bytes) -> int: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/sparse.pyi

@@ -0,0 +1,47 @@
+from typing import Sequence
+
+import numpy as np
+
+from pandas._typing import (
+    Self,
+    npt,
+)
+
+class SparseIndex:
+    length: int
+    npoints: int
+    def __init__(self) -> None: ...
+    @property
+    def ngaps(self) -> int: ...
+    @property
+    def nbytes(self) -> int: ...
+    @property
+    def indices(self) -> npt.NDArray[np.int32]: ...
+    def equals(self, other) -> bool: ...
+    def lookup(self, index: int) -> np.int32: ...
+    def lookup_array(self, indexer: npt.NDArray[np.int32]) -> npt.NDArray[np.int32]: ...
+    def to_int_index(self) -> IntIndex: ...
+    def to_block_index(self) -> BlockIndex: ...
+    def intersect(self, y_: SparseIndex) -> Self: ...
+    def make_union(self, y_: SparseIndex) -> Self: ...
+
+class IntIndex(SparseIndex):
+    indices: npt.NDArray[np.int32]
+    def __init__(
+        self, length: int, indices: Sequence[int], check_integrity: bool = ...
+    ) -> None: ...
+
+class BlockIndex(SparseIndex):
+    nblocks: int
+    blocs: np.ndarray
+    blengths: np.ndarray
+    def __init__(
+        self, length: int, blocs: np.ndarray, blengths: np.ndarray
+    ) -> None: ...
+
+def make_mask_object_ndarray(
+    arr: npt.NDArray[np.object_], fill_value
+) -> npt.NDArray[np.bool_]: ...
+def get_blocks(
+    indices: npt.NDArray[np.int32],
+) -> tuple[npt.NDArray[np.int32], npt.NDArray[np.int32]]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/testing.pyi

@@ -0,0 +1,12 @@
+def assert_dict_equal(a, b, compare_keys: bool = ...): ...
+def assert_almost_equal(
+    a,
+    b,
+    rtol: float = ...,
+    atol: float = ...,
+    check_dtype: bool = ...,
+    obj=...,
+    lobj=...,
+    robj=...,
+    index_values=...,
+): ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslib.pyi

@@ -0,0 +1,32 @@
+from datetime import tzinfo
+
+import numpy as np
+
+from pandas._typing import npt
+
+def format_array_from_datetime(
+    values: npt.NDArray[np.int64],
+    tz: tzinfo | None = ...,
+    format: str | None = ...,
+    na_rep: str | float = ...,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.object_]: ...
+def array_with_unit_to_datetime(
+    values: npt.NDArray[np.object_],
+    unit: str,
+    errors: str = ...,
+) -> tuple[np.ndarray, tzinfo | None]: ...
+def first_non_null(values: np.ndarray) -> int: ...
+def array_to_datetime(
+    values: npt.NDArray[np.object_],
+    errors: str = ...,
+    dayfirst: bool = ...,
+    yearfirst: bool = ...,
+    utc: bool = ...,
+) -> tuple[np.ndarray, tzinfo | None]: ...
+
+# returned ndarray may be object dtype or datetime64[ns]
+
+def array_to_datetime_with_tz(
+    values: npt.NDArray[np.object_], tz: tzinfo
+) -> npt.NDArray[np.int64]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/__init__.py

@@ -0,0 +1,85 @@
+__all__ = [
+    "dtypes",
+    "localize_pydatetime",
+    "NaT",
+    "NaTType",
+    "iNaT",
+    "nat_strings",
+    "OutOfBoundsDatetime",
+    "OutOfBoundsTimedelta",
+    "IncompatibleFrequency",
+    "Period",
+    "Resolution",
+    "Timedelta",
+    "normalize_i8_timestamps",
+    "is_date_array_normalized",
+    "dt64arr_to_periodarr",
+    "delta_to_nanoseconds",
+    "ints_to_pydatetime",
+    "ints_to_pytimedelta",
+    "get_resolution",
+    "Timestamp",
+    "tz_convert_from_utc_single",
+    "tz_convert_from_utc",
+    "to_offset",
+    "Tick",
+    "BaseOffset",
+    "tz_compare",
+    "is_unitless",
+    "astype_overflowsafe",
+    "get_unit_from_dtype",
+    "periods_per_day",
+    "periods_per_second",
+    "is_supported_unit",
+    "npy_unit_to_abbrev",
+    "get_supported_reso",
+]
+
+from pandas._libs.tslibs import dtypes  # pylint: disable=import-self
+from pandas._libs.tslibs.conversion import localize_pydatetime
+from pandas._libs.tslibs.dtypes import (
+    Resolution,
+    get_supported_reso,
+    is_supported_unit,
+    npy_unit_to_abbrev,
+    periods_per_day,
+    periods_per_second,
+)
+from pandas._libs.tslibs.nattype import (
+    NaT,
+    NaTType,
+    iNaT,
+    nat_strings,
+)
+from pandas._libs.tslibs.np_datetime import (
+    OutOfBoundsDatetime,
+    OutOfBoundsTimedelta,
+    astype_overflowsafe,
+    is_unitless,
+    py_get_unit_from_dtype as get_unit_from_dtype,
+)
+from pandas._libs.tslibs.offsets import (
+    BaseOffset,
+    Tick,
+    to_offset,
+)
+from pandas._libs.tslibs.period import (
+    IncompatibleFrequency,
+    Period,
+)
+from pandas._libs.tslibs.timedeltas import (
+    Timedelta,
+    delta_to_nanoseconds,
+    ints_to_pytimedelta,
+)
+from pandas._libs.tslibs.timestamps import Timestamp
+from pandas._libs.tslibs.timezones import tz_compare
+from pandas._libs.tslibs.tzconversion import tz_convert_from_utc_single
+from pandas._libs.tslibs.vectorized import (
+    dt64arr_to_periodarr,
+    get_resolution,
+    ints_to_pydatetime,
+    is_date_array_normalized,
+    normalize_i8_timestamps,
+    tz_convert_from_utc,
+)

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/ccalendar.pyi

@@ -0,0 +1,12 @@
+DAYS: list[str]
+MONTH_ALIASES: dict[int, str]
+MONTH_NUMBERS: dict[str, int]
+MONTHS: list[str]
+int_to_weekday: dict[int, str]
+
+def get_firstbday(year: int, month: int) -> int: ...
+def get_lastbday(year: int, month: int) -> int: ...
+def get_day_of_year(year: int, month: int, day: int) -> int: ...
+def get_iso_calendar(year: int, month: int, day: int) -> tuple[int, int, int]: ...
+def get_week_of_year(year: int, month: int, day: int) -> int: ...
+def get_days_in_month(year: int, month: int) -> int: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/conversion.pyi

@@ -0,0 +1,14 @@
+from datetime import (
+    datetime,
+    tzinfo,
+)
+
+import numpy as np
+
+DT64NS_DTYPE: np.dtype
+TD64NS_DTYPE: np.dtype
+
+def precision_from_unit(
+    unit: str,
+) -> tuple[int, int]: ...  # (int64_t, _)
+def localize_pydatetime(dt: datetime, tz: tzinfo | None) -> datetime: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/dtypes.pyi

@@ -0,0 +1,88 @@
+from enum import Enum
+
+# These are not public API, but are exposed in the .pyi file because they
+#  are imported in tests.
+_attrname_to_abbrevs: dict[str, str]
+_period_code_map: dict[str, int]
+
+def periods_per_day(reso: int) -> int: ...
+def periods_per_second(reso: int) -> int: ...
+def is_supported_unit(reso: int) -> bool: ...
+def npy_unit_to_abbrev(reso: int) -> str: ...
+def get_supported_reso(reso: int) -> int: ...
+def abbrev_to_npy_unit(abbrev: str) -> int: ...
+
+class PeriodDtypeBase:
+    _dtype_code: int  # PeriodDtypeCode
+    _n: int
+
+    # actually __cinit__
+    def __new__(cls, code: int, n: int): ...
+    @property
+    def _freq_group_code(self) -> int: ...
+    @property
+    def _resolution_obj(self) -> Resolution: ...
+    def _get_to_timestamp_base(self) -> int: ...
+    @property
+    def _freqstr(self) -> str: ...
+    def __hash__(self) -> int: ...
+    def _is_tick_like(self) -> bool: ...
+    @property
+    def _creso(self) -> int: ...
+    @property
+    def _td64_unit(self) -> str: ...
+
+class FreqGroup(Enum):
+    FR_ANN: int
+    FR_QTR: int
+    FR_MTH: int
+    FR_WK: int
+    FR_BUS: int
+    FR_DAY: int
+    FR_HR: int
+    FR_MIN: int
+    FR_SEC: int
+    FR_MS: int
+    FR_US: int
+    FR_NS: int
+    FR_UND: int
+    @staticmethod
+    def from_period_dtype_code(code: int) -> FreqGroup: ...
+
+class Resolution(Enum):
+    RESO_NS: int
+    RESO_US: int
+    RESO_MS: int
+    RESO_SEC: int
+    RESO_MIN: int
+    RESO_HR: int
+    RESO_DAY: int
+    RESO_MTH: int
+    RESO_QTR: int
+    RESO_YR: int
+    def __lt__(self, other: Resolution) -> bool: ...
+    def __ge__(self, other: Resolution) -> bool: ...
+    @property
+    def attrname(self) -> str: ...
+    @classmethod
+    def from_attrname(cls, attrname: str) -> Resolution: ...
+    @classmethod
+    def get_reso_from_freqstr(cls, freq: str) -> Resolution: ...
+    @property
+    def attr_abbrev(self) -> str: ...
+
+class NpyDatetimeUnit(Enum):
+    NPY_FR_Y: int
+    NPY_FR_M: int
+    NPY_FR_W: int
+    NPY_FR_D: int
+    NPY_FR_h: int
+    NPY_FR_m: int
+    NPY_FR_s: int
+    NPY_FR_ms: int
+    NPY_FR_us: int
+    NPY_FR_ns: int
+    NPY_FR_ps: int
+    NPY_FR_fs: int
+    NPY_FR_as: int
+    NPY_FR_GENERIC: int

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/fields.pyi

@@ -0,0 +1,62 @@
+import numpy as np
+
+from pandas._typing import npt
+
+def build_field_sarray(
+    dtindex: npt.NDArray[np.int64],  # const int64_t[:]
+    reso: int,  # NPY_DATETIMEUNIT
+) -> np.ndarray: ...
+def month_position_check(fields, weekdays) -> str | None: ...
+def get_date_name_field(
+    dtindex: npt.NDArray[np.int64],  # const int64_t[:]
+    field: str,
+    locale: str | None = ...,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.object_]: ...
+def get_start_end_field(
+    dtindex: npt.NDArray[np.int64],
+    field: str,
+    freqstr: str | None = ...,
+    month_kw: int = ...,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.bool_]: ...
+def get_date_field(
+    dtindex: npt.NDArray[np.int64],  # const int64_t[:]
+    field: str,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.int32]: ...
+def get_timedelta_field(
+    tdindex: npt.NDArray[np.int64],  # const int64_t[:]
+    field: str,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.int32]: ...
+def get_timedelta_days(
+    tdindex: npt.NDArray[np.int64],  # const int64_t[:]
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.int64]: ...
+def isleapyear_arr(
+    years: np.ndarray,
+) -> npt.NDArray[np.bool_]: ...
+def build_isocalendar_sarray(
+    dtindex: npt.NDArray[np.int64],  # const int64_t[:]
+    reso: int,  # NPY_DATETIMEUNIT
+) -> np.ndarray: ...
+def _get_locale_names(name_type: str, locale: str | None = ...): ...
+
+class RoundTo:
+    @property
+    def MINUS_INFTY(self) -> int: ...
+    @property
+    def PLUS_INFTY(self) -> int: ...
+    @property
+    def NEAREST_HALF_EVEN(self) -> int: ...
+    @property
+    def NEAREST_HALF_PLUS_INFTY(self) -> int: ...
+    @property
+    def NEAREST_HALF_MINUS_INFTY(self) -> int: ...
+
+def round_nsint64(
+    values: npt.NDArray[np.int64],
+    mode: RoundTo,
+    nanos: int,
+) -> npt.NDArray[np.int64]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/nattype.pyi

@@ -0,0 +1,135 @@
+from datetime import (
+    datetime,
+    timedelta,
+    tzinfo as _tzinfo,
+)
+import typing
+
+import numpy as np
+
+from pandas._libs.tslibs.period import Period
+
+NaT: NaTType
+iNaT: int
+nat_strings: set[str]
+
+_NaTComparisonTypes: typing.TypeAlias = (
+    datetime | timedelta | Period | np.datetime64 | np.timedelta64
+)
+
+class _NatComparison:
+    def __call__(self, other: _NaTComparisonTypes) -> bool: ...
+
+class NaTType:
+    _value: np.int64
+    @property
+    def value(self) -> int: ...
+    @property
+    def asm8(self) -> np.datetime64: ...
+    def to_datetime64(self) -> np.datetime64: ...
+    def to_numpy(
+        self, dtype: np.dtype | str | None = ..., copy: bool = ...
+    ) -> np.datetime64 | np.timedelta64: ...
+    @property
+    def is_leap_year(self) -> bool: ...
+    @property
+    def is_month_start(self) -> bool: ...
+    @property
+    def is_quarter_start(self) -> bool: ...
+    @property
+    def is_year_start(self) -> bool: ...
+    @property
+    def is_month_end(self) -> bool: ...
+    @property
+    def is_quarter_end(self) -> bool: ...
+    @property
+    def is_year_end(self) -> bool: ...
+    @property
+    def day_of_year(self) -> float: ...
+    @property
+    def dayofyear(self) -> float: ...
+    @property
+    def days_in_month(self) -> float: ...
+    @property
+    def daysinmonth(self) -> float: ...
+    @property
+    def day_of_week(self) -> float: ...
+    @property
+    def dayofweek(self) -> float: ...
+    @property
+    def week(self) -> float: ...
+    @property
+    def weekofyear(self) -> float: ...
+    def day_name(self) -> float: ...
+    def month_name(self) -> float: ...
+    def weekday(self) -> float: ...
+    def isoweekday(self) -> float: ...
+    def total_seconds(self) -> float: ...
+    def today(self, *args, **kwargs) -> NaTType: ...
+    def now(self, *args, **kwargs) -> NaTType: ...
+    def to_pydatetime(self) -> NaTType: ...
+    def date(self) -> NaTType: ...
+    def round(self) -> NaTType: ...
+    def floor(self) -> NaTType: ...
+    def ceil(self) -> NaTType: ...
+    @property
+    def tzinfo(self) -> None: ...
+    @property
+    def tz(self) -> None: ...
+    def tz_convert(self, tz: _tzinfo | str | None) -> NaTType: ...
+    def tz_localize(
+        self,
+        tz: _tzinfo | str | None,
+        ambiguous: str = ...,
+        nonexistent: str = ...,
+    ) -> NaTType: ...
+    def replace(
+        self,
+        year: int | None = ...,
+        month: int | None = ...,
+        day: int | None = ...,
+        hour: int | None = ...,
+        minute: int | None = ...,
+        second: int | None = ...,
+        microsecond: int | None = ...,
+        nanosecond: int | None = ...,
+        tzinfo: _tzinfo | None = ...,
+        fold: int | None = ...,
+    ) -> NaTType: ...
+    @property
+    def year(self) -> float: ...
+    @property
+    def quarter(self) -> float: ...
+    @property
+    def month(self) -> float: ...
+    @property
+    def day(self) -> float: ...
+    @property
+    def hour(self) -> float: ...
+    @property
+    def minute(self) -> float: ...
+    @property
+    def second(self) -> float: ...
+    @property
+    def millisecond(self) -> float: ...
+    @property
+    def microsecond(self) -> float: ...
+    @property
+    def nanosecond(self) -> float: ...
+    # inject Timedelta properties
+    @property
+    def days(self) -> float: ...
+    @property
+    def microseconds(self) -> float: ...
+    @property
+    def nanoseconds(self) -> float: ...
+    # inject Period properties
+    @property
+    def qyear(self) -> float: ...
+    def __eq__(self, other: object) -> bool: ...
+    def __ne__(self, other: object) -> bool: ...
+    __lt__: _NatComparison
+    __le__: _NatComparison
+    __gt__: _NatComparison
+    __ge__: _NatComparison
+    def as_unit(self, unit: str, round_ok: bool = ...) -> NaTType: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/np_datetime.pyi

@@ -0,0 +1,21 @@
+import numpy as np
+
+from pandas._typing import npt
+
+class OutOfBoundsDatetime(ValueError): ...
+class OutOfBoundsTimedelta(ValueError): ...
+
+# only exposed for testing
+def py_get_unit_from_dtype(dtype: np.dtype): ...
+def py_td64_to_tdstruct(td64: int, unit: int) -> dict: ...
+def astype_overflowsafe(
+    arr: np.ndarray,
+    dtype: np.dtype,
+    copy: bool = ...,
+    round_ok: bool = ...,
+    is_coerce: bool = ...,
+) -> np.ndarray: ...
+def is_unitless(dtype: np.dtype) -> bool: ...
+def compare_mismatched_resolutions(
+    left: np.ndarray, right: np.ndarray, op
+) -> npt.NDArray[np.bool_]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/offsets.pyi

@@ -0,0 +1,283 @@
+from datetime import (
+    datetime,
+    time,
+    timedelta,
+)
+from typing import (
+    Any,
+    Collection,
+    Literal,
+    TypeVar,
+    overload,
+)
+
+import numpy as np
+
+from pandas._libs.tslibs.nattype import NaTType
+from pandas._typing import (
+    OffsetCalendar,
+    Self,
+    npt,
+)
+
+from .timedeltas import Timedelta
+
+_BaseOffsetT = TypeVar("_BaseOffsetT", bound=BaseOffset)
+_DatetimeT = TypeVar("_DatetimeT", bound=datetime)
+_TimedeltaT = TypeVar("_TimedeltaT", bound=timedelta)
+
+_relativedelta_kwds: set[str]
+prefix_mapping: dict[str, type]
+
+class ApplyTypeError(TypeError): ...
+
+class BaseOffset:
+    n: int
+    def __init__(self, n: int = ..., normalize: bool = ...) -> None: ...
+    def __eq__(self, other) -> bool: ...
+    def __ne__(self, other) -> bool: ...
+    def __hash__(self) -> int: ...
+    @property
+    def kwds(self) -> dict: ...
+    @property
+    def base(self) -> BaseOffset: ...
+    @overload
+    def __add__(self, other: npt.NDArray[np.object_]) -> npt.NDArray[np.object_]: ...
+    @overload
+    def __add__(self, other: BaseOffset) -> Self: ...
+    @overload
+    def __add__(self, other: _DatetimeT) -> _DatetimeT: ...
+    @overload
+    def __add__(self, other: _TimedeltaT) -> _TimedeltaT: ...
+    @overload
+    def __radd__(self, other: npt.NDArray[np.object_]) -> npt.NDArray[np.object_]: ...
+    @overload
+    def __radd__(self, other: BaseOffset) -> Self: ...
+    @overload
+    def __radd__(self, other: _DatetimeT) -> _DatetimeT: ...
+    @overload
+    def __radd__(self, other: _TimedeltaT) -> _TimedeltaT: ...
+    @overload
+    def __radd__(self, other: NaTType) -> NaTType: ...
+    def __sub__(self, other: BaseOffset) -> Self: ...
+    @overload
+    def __rsub__(self, other: npt.NDArray[np.object_]) -> npt.NDArray[np.object_]: ...
+    @overload
+    def __rsub__(self, other: BaseOffset): ...
+    @overload
+    def __rsub__(self, other: _DatetimeT) -> _DatetimeT: ...
+    @overload
+    def __rsub__(self, other: _TimedeltaT) -> _TimedeltaT: ...
+    @overload
+    def __mul__(self, other: np.ndarray) -> np.ndarray: ...
+    @overload
+    def __mul__(self, other: int): ...
+    @overload
+    def __rmul__(self, other: np.ndarray) -> np.ndarray: ...
+    @overload
+    def __rmul__(self, other: int) -> Self: ...
+    def __neg__(self) -> Self: ...
+    def copy(self) -> Self: ...
+    @property
+    def name(self) -> str: ...
+    @property
+    def rule_code(self) -> str: ...
+    @property
+    def freqstr(self) -> str: ...
+    def _apply(self, other): ...
+    def _apply_array(self, dtarr) -> None: ...
+    def rollback(self, dt: datetime) -> datetime: ...
+    def rollforward(self, dt: datetime) -> datetime: ...
+    def is_on_offset(self, dt: datetime) -> bool: ...
+    def __setstate__(self, state) -> None: ...
+    def __getstate__(self): ...
+    @property
+    def nanos(self) -> int: ...
+    def is_anchored(self) -> bool: ...
+
+def _get_offset(name: str) -> BaseOffset: ...
+
+class SingleConstructorOffset(BaseOffset):
+    @classmethod
+    def _from_name(cls, suffix: None = ...): ...
+    def __reduce__(self): ...
+
+@overload
+def to_offset(freq: None) -> None: ...
+@overload
+def to_offset(freq: _BaseOffsetT) -> _BaseOffsetT: ...
+@overload
+def to_offset(freq: timedelta | str) -> BaseOffset: ...
+
+class Tick(SingleConstructorOffset):
+    _creso: int
+    _prefix: str
+    def __init__(self, n: int = ..., normalize: bool = ...) -> None: ...
+    @property
+    def delta(self) -> Timedelta: ...
+    @property
+    def nanos(self) -> int: ...
+
+def delta_to_tick(delta: timedelta) -> Tick: ...
+
+class Day(Tick): ...
+class Hour(Tick): ...
+class Minute(Tick): ...
+class Second(Tick): ...
+class Milli(Tick): ...
+class Micro(Tick): ...
+class Nano(Tick): ...
+
+class RelativeDeltaOffset(BaseOffset):
+    def __init__(self, n: int = ..., normalize: bool = ..., **kwds: Any) -> None: ...
+
+class BusinessMixin(SingleConstructorOffset):
+    def __init__(
+        self, n: int = ..., normalize: bool = ..., offset: timedelta = ...
+    ) -> None: ...
+
+class BusinessDay(BusinessMixin): ...
+
+class BusinessHour(BusinessMixin):
+    def __init__(
+        self,
+        n: int = ...,
+        normalize: bool = ...,
+        start: str | time | Collection[str | time] = ...,
+        end: str | time | Collection[str | time] = ...,
+        offset: timedelta = ...,
+    ) -> None: ...
+
+class WeekOfMonthMixin(SingleConstructorOffset):
+    def __init__(
+        self, n: int = ..., normalize: bool = ..., weekday: int = ...
+    ) -> None: ...
+
+class YearOffset(SingleConstructorOffset):
+    def __init__(
+        self, n: int = ..., normalize: bool = ..., month: int | None = ...
+    ) -> None: ...
+
+class BYearEnd(YearOffset): ...
+class BYearBegin(YearOffset): ...
+class YearEnd(YearOffset): ...
+class YearBegin(YearOffset): ...
+
+class QuarterOffset(SingleConstructorOffset):
+    def __init__(
+        self, n: int = ..., normalize: bool = ..., startingMonth: int | None = ...
+    ) -> None: ...
+
+class BQuarterEnd(QuarterOffset): ...
+class BQuarterBegin(QuarterOffset): ...
+class QuarterEnd(QuarterOffset): ...
+class QuarterBegin(QuarterOffset): ...
+class MonthOffset(SingleConstructorOffset): ...
+class MonthEnd(MonthOffset): ...
+class MonthBegin(MonthOffset): ...
+class BusinessMonthEnd(MonthOffset): ...
+class BusinessMonthBegin(MonthOffset): ...
+
+class SemiMonthOffset(SingleConstructorOffset):
+    def __init__(
+        self, n: int = ..., normalize: bool = ..., day_of_month: int | None = ...
+    ) -> None: ...
+
+class SemiMonthEnd(SemiMonthOffset): ...
+class SemiMonthBegin(SemiMonthOffset): ...
+
+class Week(SingleConstructorOffset):
+    def __init__(
+        self, n: int = ..., normalize: bool = ..., weekday: int | None = ...
+    ) -> None: ...
+
+class WeekOfMonth(WeekOfMonthMixin):
+    def __init__(
+        self, n: int = ..., normalize: bool = ..., week: int = ..., weekday: int = ...
+    ) -> None: ...
+
+class LastWeekOfMonth(WeekOfMonthMixin): ...
+
+class FY5253Mixin(SingleConstructorOffset):
+    def __init__(
+        self,
+        n: int = ...,
+        normalize: bool = ...,
+        weekday: int = ...,
+        startingMonth: int = ...,
+        variation: Literal["nearest", "last"] = ...,
+    ) -> None: ...
+
+class FY5253(FY5253Mixin): ...
+
+class FY5253Quarter(FY5253Mixin):
+    def __init__(
+        self,
+        n: int = ...,
+        normalize: bool = ...,
+        weekday: int = ...,
+        startingMonth: int = ...,
+        qtr_with_extra_week: int = ...,
+        variation: Literal["nearest", "last"] = ...,
+    ) -> None: ...
+
+class Easter(SingleConstructorOffset): ...
+
+class _CustomBusinessMonth(BusinessMixin):
+    def __init__(
+        self,
+        n: int = ...,
+        normalize: bool = ...,
+        weekmask: str = ...,
+        holidays: list | None = ...,
+        calendar: OffsetCalendar | None = ...,
+        offset: timedelta = ...,
+    ) -> None: ...
+
+class CustomBusinessDay(BusinessDay):
+    def __init__(
+        self,
+        n: int = ...,
+        normalize: bool = ...,
+        weekmask: str = ...,
+        holidays: list | None = ...,
+        calendar: OffsetCalendar | None = ...,
+        offset: timedelta = ...,
+    ) -> None: ...
+
+class CustomBusinessHour(BusinessHour):
+    def __init__(
+        self,
+        n: int = ...,
+        normalize: bool = ...,
+        weekmask: str = ...,
+        holidays: list | None = ...,
+        calendar: OffsetCalendar | None = ...,
+        start: str | time | Collection[str | time] = ...,
+        end: str | time | Collection[str | time] = ...,
+        offset: timedelta = ...,
+    ) -> None: ...
+
+class CustomBusinessMonthEnd(_CustomBusinessMonth): ...
+class CustomBusinessMonthBegin(_CustomBusinessMonth): ...
+class OffsetMeta(type): ...
+class DateOffset(RelativeDeltaOffset, metaclass=OffsetMeta): ...
+
+BDay = BusinessDay
+BMonthEnd = BusinessMonthEnd
+BMonthBegin = BusinessMonthBegin
+CBMonthEnd = CustomBusinessMonthEnd
+CBMonthBegin = CustomBusinessMonthBegin
+CDay = CustomBusinessDay
+
+def roll_qtrday(
+    other: datetime, n: int, month: int, day_opt: str, modby: int
+) -> int: ...
+
+INVALID_FREQ_ERR_MSG: Literal["Invalid frequency: {0}"]
+
+def shift_months(
+    dtindex: npt.NDArray[np.int64], months: int, day_opt: str | None = ...
+) -> npt.NDArray[np.int64]: ...
+
+_offset_map: dict[str, BaseOffset]

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/parsing.pyi

@@ -0,0 +1,38 @@
+from datetime import datetime
+
+import numpy as np
+
+from pandas._typing import npt
+
+class DateParseError(ValueError): ...
+
+def py_parse_datetime_string(
+    date_string: str,
+    dayfirst: bool = ...,
+    yearfirst: bool = ...,
+) -> datetime: ...
+def parse_datetime_string_with_reso(
+    date_string: str,
+    freq: str | None = ...,
+    dayfirst: bool | None = ...,
+    yearfirst: bool | None = ...,
+) -> tuple[datetime, str]: ...
+def _does_string_look_like_datetime(py_string: str) -> bool: ...
+def quarter_to_myear(year: int, quarter: int, freq: str) -> tuple[int, int]: ...
+def try_parse_dates(
+    values: npt.NDArray[np.object_],  # object[:]
+    parser,
+) -> npt.NDArray[np.object_]: ...
+def try_parse_year_month_day(
+    years: npt.NDArray[np.object_],  # object[:]
+    months: npt.NDArray[np.object_],  # object[:]
+    days: npt.NDArray[np.object_],  # object[:]
+) -> npt.NDArray[np.object_]: ...
+def guess_datetime_format(
+    dt_str,
+    dayfirst: bool | None = ...,
+) -> str | None: ...
+def concat_date_cols(
+    date_cols: tuple,
+) -> npt.NDArray[np.object_]: ...
+def get_rule_month(source: str) -> str: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/period.pyi

@@ -0,0 +1,135 @@
+from datetime import timedelta
+from typing import Literal
+
+import numpy as np
+
+from pandas._libs.tslibs.dtypes import PeriodDtypeBase
+from pandas._libs.tslibs.nattype import NaTType
+from pandas._libs.tslibs.offsets import BaseOffset
+from pandas._libs.tslibs.timestamps import Timestamp
+from pandas._typing import (
+    Frequency,
+    npt,
+)
+
+INVALID_FREQ_ERR_MSG: str
+DIFFERENT_FREQ: str
+
+class IncompatibleFrequency(ValueError): ...
+
+def periodarr_to_dt64arr(
+    periodarr: npt.NDArray[np.int64],  # const int64_t[:]
+    freq: int,
+) -> npt.NDArray[np.int64]: ...
+def period_asfreq_arr(
+    arr: npt.NDArray[np.int64],
+    freq1: int,
+    freq2: int,
+    end: bool,
+) -> npt.NDArray[np.int64]: ...
+def get_period_field_arr(
+    field: str,
+    arr: npt.NDArray[np.int64],  # const int64_t[:]
+    freq: int,
+) -> npt.NDArray[np.int64]: ...
+def from_ordinals(
+    values: npt.NDArray[np.int64],  # const int64_t[:]
+    freq: timedelta | BaseOffset | str,
+) -> npt.NDArray[np.int64]: ...
+def extract_ordinals(
+    values: npt.NDArray[np.object_],
+    freq: Frequency | int,
+) -> npt.NDArray[np.int64]: ...
+def extract_freq(
+    values: npt.NDArray[np.object_],
+) -> BaseOffset: ...
+def period_array_strftime(
+    values: npt.NDArray[np.int64],
+    dtype_code: int,
+    na_rep,
+    date_format: str | None,
+) -> npt.NDArray[np.object_]: ...
+
+# exposed for tests
+def period_asfreq(ordinal: int, freq1: int, freq2: int, end: bool) -> int: ...
+def period_ordinal(
+    y: int, m: int, d: int, h: int, min: int, s: int, us: int, ps: int, freq: int
+) -> int: ...
+def freq_to_dtype_code(freq: BaseOffset) -> int: ...
+def validate_end_alias(how: str) -> Literal["E", "S"]: ...
+
+class PeriodMixin:
+    @property
+    def end_time(self) -> Timestamp: ...
+    @property
+    def start_time(self) -> Timestamp: ...
+    def _require_matching_freq(self, other, base: bool = ...) -> None: ...
+
+class Period(PeriodMixin):
+    ordinal: int  # int64_t
+    freq: BaseOffset
+    _dtype: PeriodDtypeBase
+
+    # error: "__new__" must return a class instance (got "Union[Period, NaTType]")
+    def __new__(  # type: ignore[misc]
+        cls,
+        value=...,
+        freq: int | str | BaseOffset | None = ...,
+        ordinal: int | None = ...,
+        year: int | None = ...,
+        month: int | None = ...,
+        quarter: int | None = ...,
+        day: int | None = ...,
+        hour: int | None = ...,
+        minute: int | None = ...,
+        second: int | None = ...,
+    ) -> Period | NaTType: ...
+    @classmethod
+    def _maybe_convert_freq(cls, freq) -> BaseOffset: ...
+    @classmethod
+    def _from_ordinal(cls, ordinal: int, freq) -> Period: ...
+    @classmethod
+    def now(cls, freq: BaseOffset = ...) -> Period: ...
+    def strftime(self, fmt: str) -> str: ...
+    def to_timestamp(
+        self,
+        freq: str | BaseOffset | None = ...,
+        how: str = ...,
+    ) -> Timestamp: ...
+    def asfreq(self, freq: str | BaseOffset, how: str = ...) -> Period: ...
+    @property
+    def freqstr(self) -> str: ...
+    @property
+    def is_leap_year(self) -> bool: ...
+    @property
+    def daysinmonth(self) -> int: ...
+    @property
+    def days_in_month(self) -> int: ...
+    @property
+    def qyear(self) -> int: ...
+    @property
+    def quarter(self) -> int: ...
+    @property
+    def day_of_year(self) -> int: ...
+    @property
+    def weekday(self) -> int: ...
+    @property
+    def day_of_week(self) -> int: ...
+    @property
+    def week(self) -> int: ...
+    @property
+    def weekofyear(self) -> int: ...
+    @property
+    def second(self) -> int: ...
+    @property
+    def minute(self) -> int: ...
+    @property
+    def hour(self) -> int: ...
+    @property
+    def day(self) -> int: ...
+    @property
+    def month(self) -> int: ...
+    @property
+    def year(self) -> int: ...
+    def __sub__(self, other) -> Period | BaseOffset: ...
+    def __add__(self, other) -> Period: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/strptime.pyi

@@ -0,0 +1,13 @@
+import numpy as np
+
+from pandas._typing import npt
+
+def array_strptime(
+    values: npt.NDArray[np.object_],
+    fmt: str | None,
+    exact: bool = ...,
+    errors: str = ...,
+    utc: bool = ...,
+) -> tuple[np.ndarray, np.ndarray]: ...
+
+# first ndarray is M8[ns], second is object ndarray of tzinfo | None

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/timedeltas.pyi

@@ -0,0 +1,169 @@
+from datetime import timedelta
+from typing import (
+    ClassVar,
+    Literal,
+    TypeAlias,
+    TypeVar,
+    overload,
+)
+
+import numpy as np
+
+from pandas._libs.tslibs import (
+    NaTType,
+    Tick,
+)
+from pandas._typing import (
+    Self,
+    npt,
+)
+
+# This should be kept consistent with the keys in the dict timedelta_abbrevs
+# in pandas/_libs/tslibs/timedeltas.pyx
+UnitChoices: TypeAlias = Literal[
+    "Y",
+    "y",
+    "M",
+    "W",
+    "w",
+    "D",
+    "d",
+    "days",
+    "day",
+    "hours",
+    "hour",
+    "hr",
+    "h",
+    "m",
+    "minute",
+    "min",
+    "minutes",
+    "T",
+    "t",
+    "s",
+    "seconds",
+    "sec",
+    "second",
+    "ms",
+    "milliseconds",
+    "millisecond",
+    "milli",
+    "millis",
+    "L",
+    "l",
+    "us",
+    "microseconds",
+    "microsecond",
+    "µs",
+    "micro",
+    "micros",
+    "u",
+    "ns",
+    "nanoseconds",
+    "nano",
+    "nanos",
+    "nanosecond",
+    "n",
+]
+_S = TypeVar("_S", bound=timedelta)
+
+def ints_to_pytimedelta(
+    arr: npt.NDArray[np.timedelta64],
+    box: bool = ...,
+) -> npt.NDArray[np.object_]: ...
+def array_to_timedelta64(
+    values: npt.NDArray[np.object_],
+    unit: str | None = ...,
+    errors: str = ...,
+) -> np.ndarray: ...  # np.ndarray[m8ns]
+def parse_timedelta_unit(unit: str | None) -> UnitChoices: ...
+def delta_to_nanoseconds(
+    delta: np.timedelta64 | timedelta | Tick,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+    round_ok: bool = ...,
+) -> int: ...
+def floordiv_object_array(
+    left: np.ndarray, right: npt.NDArray[np.object_]
+) -> np.ndarray: ...
+def truediv_object_array(
+    left: np.ndarray, right: npt.NDArray[np.object_]
+) -> np.ndarray: ...
+
+class Timedelta(timedelta):
+    _creso: int
+    min: ClassVar[Timedelta]
+    max: ClassVar[Timedelta]
+    resolution: ClassVar[Timedelta]
+    value: int  # np.int64
+    _value: int  # np.int64
+    # error: "__new__" must return a class instance (got "Union[Timestamp, NaTType]")
+    def __new__(  # type: ignore[misc]
+        cls: type[_S],
+        value=...,
+        unit: str | None = ...,
+        **kwargs: float | np.integer | np.floating,
+    ) -> _S | NaTType: ...
+    @classmethod
+    def _from_value_and_reso(cls, value: np.int64, reso: int) -> Timedelta: ...
+    @property
+    def days(self) -> int: ...
+    @property
+    def seconds(self) -> int: ...
+    @property
+    def microseconds(self) -> int: ...
+    def total_seconds(self) -> float: ...
+    def to_pytimedelta(self) -> timedelta: ...
+    def to_timedelta64(self) -> np.timedelta64: ...
+    @property
+    def asm8(self) -> np.timedelta64: ...
+    # TODO: round/floor/ceil could return NaT?
+    def round(self, freq: str) -> Self: ...
+    def floor(self, freq: str) -> Self: ...
+    def ceil(self, freq: str) -> Self: ...
+    @property
+    def resolution_string(self) -> str: ...
+    def __add__(self, other: timedelta) -> Timedelta: ...
+    def __radd__(self, other: timedelta) -> Timedelta: ...
+    def __sub__(self, other: timedelta) -> Timedelta: ...
+    def __rsub__(self, other: timedelta) -> Timedelta: ...
+    def __neg__(self) -> Timedelta: ...
+    def __pos__(self) -> Timedelta: ...
+    def __abs__(self) -> Timedelta: ...
+    def __mul__(self, other: float) -> Timedelta: ...
+    def __rmul__(self, other: float) -> Timedelta: ...
+    # error: Signature of "__floordiv__" incompatible with supertype "timedelta"
+    @overload  # type: ignore[override]
+    def __floordiv__(self, other: timedelta) -> int: ...
+    @overload
+    def __floordiv__(self, other: float) -> Timedelta: ...
+    @overload
+    def __floordiv__(
+        self, other: npt.NDArray[np.timedelta64]
+    ) -> npt.NDArray[np.intp]: ...
+    @overload
+    def __floordiv__(
+        self, other: npt.NDArray[np.number]
+    ) -> npt.NDArray[np.timedelta64] | Timedelta: ...
+    @overload
+    def __rfloordiv__(self, other: timedelta | str) -> int: ...
+    @overload
+    def __rfloordiv__(self, other: None | NaTType) -> NaTType: ...
+    @overload
+    def __rfloordiv__(self, other: np.ndarray) -> npt.NDArray[np.timedelta64]: ...
+    @overload
+    def __truediv__(self, other: timedelta) -> float: ...
+    @overload
+    def __truediv__(self, other: float) -> Timedelta: ...
+    def __mod__(self, other: timedelta) -> Timedelta: ...
+    def __divmod__(self, other: timedelta) -> tuple[int, Timedelta]: ...
+    def __le__(self, other: timedelta) -> bool: ...
+    def __lt__(self, other: timedelta) -> bool: ...
+    def __ge__(self, other: timedelta) -> bool: ...
+    def __gt__(self, other: timedelta) -> bool: ...
+    def __hash__(self) -> int: ...
+    def isoformat(self) -> str: ...
+    def to_numpy(self) -> np.timedelta64: ...
+    def view(self, dtype: npt.DTypeLike = ...) -> object: ...
+    @property
+    def unit(self) -> str: ...
+    def as_unit(self, unit: str, round_ok: bool = ...) -> Timedelta: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/timestamps.pyi

@@ -0,0 +1,240 @@
+from datetime import (
+    date as _date,
+    datetime,
+    time as _time,
+    timedelta,
+    tzinfo as _tzinfo,
+)
+from time import struct_time
+from typing import (
+    ClassVar,
+    TypeVar,
+    overload,
+)
+
+import numpy as np
+
+from pandas._libs.tslibs import (
+    BaseOffset,
+    NaTType,
+    Period,
+    Tick,
+    Timedelta,
+)
+from pandas._typing import (
+    Self,
+    TimestampNonexistent,
+)
+
+_DatetimeT = TypeVar("_DatetimeT", bound=datetime)
+
+def integer_op_not_supported(obj: object) -> TypeError: ...
+
+class Timestamp(datetime):
+    _creso: int
+    min: ClassVar[Timestamp]
+    max: ClassVar[Timestamp]
+
+    resolution: ClassVar[Timedelta]
+    _value: int  # np.int64
+    # error: "__new__" must return a class instance (got "Union[Timestamp, NaTType]")
+    def __new__(  # type: ignore[misc]
+        cls: type[_DatetimeT],
+        ts_input: np.integer | float | str | _date | datetime | np.datetime64 = ...,
+        year: int | None = ...,
+        month: int | None = ...,
+        day: int | None = ...,
+        hour: int | None = ...,
+        minute: int | None = ...,
+        second: int | None = ...,
+        microsecond: int | None = ...,
+        tzinfo: _tzinfo | None = ...,
+        *,
+        nanosecond: int | None = ...,
+        tz: str | _tzinfo | None | int = ...,
+        unit: str | int | None = ...,
+        fold: int | None = ...,
+    ) -> _DatetimeT | NaTType: ...
+    @classmethod
+    def _from_value_and_reso(
+        cls, value: int, reso: int, tz: _tzinfo | None
+    ) -> Timestamp: ...
+    @property
+    def value(self) -> int: ...  # np.int64
+    @property
+    def year(self) -> int: ...
+    @property
+    def month(self) -> int: ...
+    @property
+    def day(self) -> int: ...
+    @property
+    def hour(self) -> int: ...
+    @property
+    def minute(self) -> int: ...
+    @property
+    def second(self) -> int: ...
+    @property
+    def microsecond(self) -> int: ...
+    @property
+    def nanosecond(self) -> int: ...
+    @property
+    def tzinfo(self) -> _tzinfo | None: ...
+    @property
+    def tz(self) -> _tzinfo | None: ...
+    @property
+    def fold(self) -> int: ...
+    @classmethod
+    def fromtimestamp(cls, ts: float, tz: _tzinfo | None = ...) -> Self: ...
+    @classmethod
+    def utcfromtimestamp(cls, ts: float) -> Self: ...
+    @classmethod
+    def today(cls, tz: _tzinfo | str | None = ...) -> Self: ...
+    @classmethod
+    def fromordinal(
+        cls,
+        ordinal: int,
+        tz: _tzinfo | str | None = ...,
+    ) -> Self: ...
+    @classmethod
+    def now(cls, tz: _tzinfo | str | None = ...) -> Self: ...
+    @classmethod
+    def utcnow(cls) -> Self: ...
+    # error: Signature of "combine" incompatible with supertype "datetime"
+    @classmethod
+    def combine(  # type: ignore[override]
+        cls, date: _date, time: _time
+    ) -> datetime: ...
+    @classmethod
+    def fromisoformat(cls, date_string: str) -> Self: ...
+    def strftime(self, format: str) -> str: ...
+    def __format__(self, fmt: str) -> str: ...
+    def toordinal(self) -> int: ...
+    def timetuple(self) -> struct_time: ...
+    def timestamp(self) -> float: ...
+    def utctimetuple(self) -> struct_time: ...
+    def date(self) -> _date: ...
+    def time(self) -> _time: ...
+    def timetz(self) -> _time: ...
+    # LSP violation: nanosecond is not present in datetime.datetime.replace
+    # and has positional args following it
+    def replace(  # type: ignore[override]
+        self,
+        year: int | None = ...,
+        month: int | None = ...,
+        day: int | None = ...,
+        hour: int | None = ...,
+        minute: int | None = ...,
+        second: int | None = ...,
+        microsecond: int | None = ...,
+        nanosecond: int | None = ...,
+        tzinfo: _tzinfo | type[object] | None = ...,
+        fold: int | None = ...,
+    ) -> Self: ...
+    # LSP violation: datetime.datetime.astimezone has a default value for tz
+    def astimezone(self, tz: _tzinfo | None) -> Self: ...  # type: ignore[override]
+    def ctime(self) -> str: ...
+    def isoformat(self, sep: str = ..., timespec: str = ...) -> str: ...
+    @classmethod
+    def strptime(
+        # Note: strptime is actually disabled and raises NotImplementedError
+        cls,
+        date_string: str,
+        format: str,
+    ) -> Self: ...
+    def utcoffset(self) -> timedelta | None: ...
+    def tzname(self) -> str | None: ...
+    def dst(self) -> timedelta | None: ...
+    def __le__(self, other: datetime) -> bool: ...  # type: ignore[override]
+    def __lt__(self, other: datetime) -> bool: ...  # type: ignore[override]
+    def __ge__(self, other: datetime) -> bool: ...  # type: ignore[override]
+    def __gt__(self, other: datetime) -> bool: ...  # type: ignore[override]
+    # error: Signature of "__add__" incompatible with supertype "date"/"datetime"
+    @overload  # type: ignore[override]
+    def __add__(self, other: np.ndarray) -> np.ndarray: ...
+    @overload
+    def __add__(self, other: timedelta | np.timedelta64 | Tick) -> Self: ...
+    def __radd__(self, other: timedelta) -> Self: ...
+    @overload  # type: ignore[override]
+    def __sub__(self, other: datetime) -> Timedelta: ...
+    @overload
+    def __sub__(self, other: timedelta | np.timedelta64 | Tick) -> Self: ...
+    def __hash__(self) -> int: ...
+    def weekday(self) -> int: ...
+    def isoweekday(self) -> int: ...
+    # Return type "Tuple[int, int, int]" of "isocalendar" incompatible with return
+    # type "_IsoCalendarDate" in supertype "date"
+    def isocalendar(self) -> tuple[int, int, int]: ...  # type: ignore[override]
+    @property
+    def is_leap_year(self) -> bool: ...
+    @property
+    def is_month_start(self) -> bool: ...
+    @property
+    def is_quarter_start(self) -> bool: ...
+    @property
+    def is_year_start(self) -> bool: ...
+    @property
+    def is_month_end(self) -> bool: ...
+    @property
+    def is_quarter_end(self) -> bool: ...
+    @property
+    def is_year_end(self) -> bool: ...
+    def to_pydatetime(self, warn: bool = ...) -> datetime: ...
+    def to_datetime64(self) -> np.datetime64: ...
+    def to_period(self, freq: BaseOffset | str = ...) -> Period: ...
+    def to_julian_date(self) -> np.float64: ...
+    @property
+    def asm8(self) -> np.datetime64: ...
+    def tz_convert(self, tz: _tzinfo | str | None) -> Self: ...
+    # TODO: could return NaT?
+    def tz_localize(
+        self,
+        tz: _tzinfo | str | None,
+        ambiguous: str = ...,
+        nonexistent: TimestampNonexistent = ...,
+    ) -> Self: ...
+    def normalize(self) -> Self: ...
+    # TODO: round/floor/ceil could return NaT?
+    def round(
+        self,
+        freq: str,
+        ambiguous: bool | str = ...,
+        nonexistent: TimestampNonexistent = ...,
+    ) -> Self: ...
+    def floor(
+        self,
+        freq: str,
+        ambiguous: bool | str = ...,
+        nonexistent: TimestampNonexistent = ...,
+    ) -> Self: ...
+    def ceil(
+        self,
+        freq: str,
+        ambiguous: bool | str = ...,
+        nonexistent: TimestampNonexistent = ...,
+    ) -> Self: ...
+    def day_name(self, locale: str | None = ...) -> str: ...
+    def month_name(self, locale: str | None = ...) -> str: ...
+    @property
+    def day_of_week(self) -> int: ...
+    @property
+    def dayofweek(self) -> int: ...
+    @property
+    def day_of_year(self) -> int: ...
+    @property
+    def dayofyear(self) -> int: ...
+    @property
+    def quarter(self) -> int: ...
+    @property
+    def week(self) -> int: ...
+    def to_numpy(
+        self, dtype: np.dtype | None = ..., copy: bool = ...
+    ) -> np.datetime64: ...
+    @property
+    def _date_repr(self) -> str: ...
+    @property
+    def days_in_month(self) -> int: ...
+    @property
+    def daysinmonth(self) -> int: ...
+    @property
+    def unit(self) -> str: ...
+    def as_unit(self, unit: str, round_ok: bool = ...) -> Timestamp: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/timezones.pyi

@@ -0,0 +1,21 @@
+from datetime import (
+    datetime,
+    tzinfo,
+)
+from typing import Callable
+
+import numpy as np
+
+# imported from dateutil.tz
+dateutil_gettz: Callable[[str], tzinfo]
+
+def tz_standardize(tz: tzinfo) -> tzinfo: ...
+def tz_compare(start: tzinfo | None, end: tzinfo | None) -> bool: ...
+def infer_tzinfo(
+    start: datetime | None,
+    end: datetime | None,
+) -> tzinfo | None: ...
+def maybe_get_tz(tz: str | int | np.int64 | tzinfo | None) -> tzinfo | None: ...
+def get_timezone(tz: tzinfo) -> tzinfo | str: ...
+def is_utc(tz: tzinfo | None) -> bool: ...
+def is_fixed_offset(tz: tzinfo) -> bool: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/tzconversion.pyi

@@ -0,0 +1,21 @@
+from datetime import (
+    timedelta,
+    tzinfo,
+)
+from typing import Iterable
+
+import numpy as np
+
+from pandas._typing import npt
+
+# tz_convert_from_utc_single exposed for testing
+def tz_convert_from_utc_single(
+    val: np.int64, tz: tzinfo, creso: int = ...
+) -> np.int64: ...
+def tz_localize_to_utc(
+    vals: npt.NDArray[np.int64],
+    tz: tzinfo | None,
+    ambiguous: str | bool | Iterable[bool] | None = ...,
+    nonexistent: str | timedelta | np.timedelta64 | None = ...,
+    creso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.int64]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/tslibs/vectorized.pyi

@@ -0,0 +1,43 @@
+"""
+For cython types that cannot be represented precisely, closest-available
+python equivalents are used, and the precise types kept as adjacent comments.
+"""
+from datetime import tzinfo
+
+import numpy as np
+
+from pandas._libs.tslibs.dtypes import Resolution
+from pandas._typing import npt
+
+def dt64arr_to_periodarr(
+    stamps: npt.NDArray[np.int64],
+    freq: int,
+    tz: tzinfo | None,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.int64]: ...
+def is_date_array_normalized(
+    stamps: npt.NDArray[np.int64],
+    tz: tzinfo | None,
+    reso: int,  # NPY_DATETIMEUNIT
+) -> bool: ...
+def normalize_i8_timestamps(
+    stamps: npt.NDArray[np.int64],
+    tz: tzinfo | None,
+    reso: int,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.int64]: ...
+def get_resolution(
+    stamps: npt.NDArray[np.int64],
+    tz: tzinfo | None = ...,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> Resolution: ...
+def ints_to_pydatetime(
+    arr: npt.NDArray[np.int64],
+    tz: tzinfo | None = ...,
+    box: str = ...,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.object_]: ...
+def tz_convert_from_utc(
+    stamps: npt.NDArray[np.int64],
+    tz: tzinfo | None,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.int64]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/window/aggregations.pyi

@@ -0,0 +1,127 @@
+from typing import (
+    Any,
+    Callable,
+    Literal,
+)
+
+import numpy as np
+
+from pandas._typing import (
+    WindowingRankType,
+    npt,
+)
+
+def roll_sum(
+    values: np.ndarray,  # const float64_t[:]
+    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_mean(
+    values: np.ndarray,  # const float64_t[:]
+    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_var(
+    values: np.ndarray,  # const float64_t[:]
+    start: np.ndarray,  # np.ndarray[np.int64]
+    end: np.ndarray,  # np.ndarray[np.int64]
+    minp: int,  # int64_t
+    ddof: int = ...,
+) -> np.ndarray: ...  # np.ndarray[float]
+def roll_skew(
+    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_kurt(
+    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_median_c(
+    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_max(
+    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_min(
+    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]
+    end: np.ndarray,  # np.ndarray[np.int64]
+    minp: int,  # int64_t
+    quantile: float,  # float64_t
+    interpolation: Literal["linear", "lower", "higher", "nearest", "midpoint"],
+) -> np.ndarray: ...  # np.ndarray[float]
+def roll_rank(
+    values: np.ndarray,
+    start: np.ndarray,
+    end: np.ndarray,
+    minp: int,
+    percentile: bool,
+    method: WindowingRankType,
+    ascending: bool,
+) -> np.ndarray: ...  # np.ndarray[float]
+def roll_apply(
+    obj: object,
+    start: np.ndarray,  # np.ndarray[np.int64]
+    end: np.ndarray,  # np.ndarray[np.int64]
+    minp: int,  # int64_t
+    function: Callable[..., Any],
+    raw: bool,
+    args: tuple[Any, ...],
+    kwargs: dict[str, Any],
+) -> npt.NDArray[np.float64]: ...
+def roll_weighted_sum(
+    values: np.ndarray,  # const float64_t[:]
+    weights: np.ndarray,  # const float64_t[:]
+    minp: int,
+) -> np.ndarray: ...  # np.ndarray[np.float64]
+def roll_weighted_mean(
+    values: np.ndarray,  # const float64_t[:]
+    weights: np.ndarray,  # const float64_t[:]
+    minp: int,
+) -> np.ndarray: ...  # np.ndarray[np.float64]
+def roll_weighted_var(
+    values: np.ndarray,  # const float64_t[:]
+    weights: np.ndarray,  # const float64_t[:]
+    minp: int,  # int64_t
+    ddof: int,  # unsigned int
+) -> np.ndarray: ...  # np.ndarray[np.float64]
+def ewm(
+    vals: np.ndarray,  # const float64_t[:]
+    start: np.ndarray,  # const int64_t[:]
+    end: np.ndarray,  # const int64_t[:]
+    minp: int,
+    com: float,  # float64_t
+    adjust: bool,
+    ignore_na: bool,
+    deltas: np.ndarray,  # const float64_t[:]
+    normalize: bool,
+) -> np.ndarray: ...  # np.ndarray[np.float64]
+def ewmcov(
+    input_x: np.ndarray,  # const float64_t[:]
+    start: np.ndarray,  # const int64_t[:]
+    end: np.ndarray,  # const int64_t[:]
+    minp: int,
+    input_y: np.ndarray,  # const float64_t[:]
+    com: float,  # float64_t
+    adjust: bool,
+    ignore_na: bool,
+    bias: bool,
+) -> np.ndarray: ...  # np.ndarray[np.float64]

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/window/indexers.pyi

@@ -0,0 +1,12 @@
+import numpy as np
+
+from pandas._typing import npt
+
+def calculate_variable_window_bounds(
+    num_values: int,  # int64_t
+    window_size: int,  # int64_t
+    min_periods,
+    center: bool,
+    closed: str | None,
+    index: np.ndarray,  # const int64_t[:]
+) -> tuple[npt.NDArray[np.int64], npt.NDArray[np.int64]]: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_libs/writers.pyi

@@ -0,0 +1,20 @@
+import numpy as np
+
+from pandas._typing import ArrayLike
+
+def write_csv_rows(
+    data: list[ArrayLike],
+    data_index: np.ndarray,
+    nlevels: int,
+    cols: np.ndarray,
+    writer: object,  # _csv.writer
+) -> None: ...
+def convert_json_to_lines(arr: str) -> str: ...
+def max_len_string_array(
+    arr: np.ndarray,  # pandas_string[:]
+) -> int: ...
+def word_len(val: object) -> int: ...
+def string_array_replace_from_nan_rep(
+    arr: np.ndarray,  # np.ndarray[object, ndim=1]
+    nan_rep: object,
+) -> None: ...

AppDir/usr/lib/python3.12/site-packages/pandas/_testing/_hypothesis.py

@@ -0,0 +1,89 @@
+"""
+Hypothesis data generator helpers.
+"""
+from datetime import datetime
+
+from hypothesis import strategies as st
+from hypothesis.extra.dateutil import timezones as dateutil_timezones
+from hypothesis.extra.pytz import timezones as pytz_timezones
+
+from pandas.compat import is_platform_windows
+
+import pandas as pd
+
+from pandas.tseries.offsets import (
+    BMonthBegin,
+    BMonthEnd,
+    BQuarterBegin,
+    BQuarterEnd,
+    BYearBegin,
+    BYearEnd,
+    MonthBegin,
+    MonthEnd,
+    QuarterBegin,
+    QuarterEnd,
+    YearBegin,
+    YearEnd,
+)
+
+OPTIONAL_INTS = st.lists(st.one_of(st.integers(), st.none()), max_size=10, min_size=3)
+
+OPTIONAL_FLOATS = st.lists(st.one_of(st.floats(), st.none()), max_size=10, min_size=3)
+
+OPTIONAL_TEXT = st.lists(st.one_of(st.none(), st.text()), max_size=10, min_size=3)
+
+OPTIONAL_DICTS = st.lists(
+    st.one_of(st.none(), st.dictionaries(st.text(), st.integers())),
+    max_size=10,
+    min_size=3,
+)
+
+OPTIONAL_LISTS = st.lists(
+    st.one_of(st.none(), st.lists(st.text(), max_size=10, min_size=3)),
+    max_size=10,
+    min_size=3,
+)
+
+OPTIONAL_ONE_OF_ALL = st.one_of(
+    OPTIONAL_DICTS, OPTIONAL_FLOATS, OPTIONAL_INTS, OPTIONAL_LISTS, OPTIONAL_TEXT
+)
+
+if is_platform_windows():
+    DATETIME_NO_TZ = st.datetimes(min_value=datetime(1900, 1, 1))
+else:
+    DATETIME_NO_TZ = st.datetimes()
+
+DATETIME_JAN_1_1900_OPTIONAL_TZ = st.datetimes(
+    min_value=pd.Timestamp(1900, 1, 1).to_pydatetime(),
+    max_value=pd.Timestamp(1900, 1, 1).to_pydatetime(),
+    timezones=st.one_of(st.none(), dateutil_timezones(), pytz_timezones()),
+)
+
+DATETIME_IN_PD_TIMESTAMP_RANGE_NO_TZ = st.datetimes(
+    min_value=pd.Timestamp.min.to_pydatetime(warn=False),
+    max_value=pd.Timestamp.max.to_pydatetime(warn=False),
+)
+
+INT_NEG_999_TO_POS_999 = st.integers(-999, 999)
+
+# The strategy for each type is registered in conftest.py, as they don't carry
+# enough runtime information (e.g. type hints) to infer how to build them.
+YQM_OFFSET = st.one_of(
+    *map(
+        st.from_type,
+        [
+            MonthBegin,
+            MonthEnd,
+            BMonthBegin,
+            BMonthEnd,
+            QuarterBegin,
+            QuarterEnd,
+            BQuarterBegin,
+            BQuarterEnd,
+            YearBegin,
+            YearEnd,
+            BYearBegin,
+            BYearEnd,
+        ],
+    )
+)

AppDir/usr/lib/python3.12/site-packages/pandas/_testing/_io.py

@@ -0,0 +1,170 @@
+from __future__ import annotations
+
+import gzip
+import io
+import pathlib
+import tarfile
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Callable,
+)
+import uuid
+import zipfile
+
+from pandas.compat import (
+    get_bz2_file,
+    get_lzma_file,
+)
+from pandas.compat._optional import import_optional_dependency
+
+import pandas as pd
+from pandas._testing.contexts import ensure_clean
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        FilePath,
+        ReadPickleBuffer,
+    )
+
+    from pandas import (
+        DataFrame,
+        Series,
+    )
+
+# ------------------------------------------------------------------
+# File-IO
+
+
+def round_trip_pickle(
+    obj: Any, path: FilePath | ReadPickleBuffer | None = None
+) -> DataFrame | Series:
+    """
+    Pickle an object and then read it again.
+
+    Parameters
+    ----------
+    obj : any object
+        The object to pickle and then re-read.
+    path : str, path object or file-like object, default None
+        The path where the pickled object is written and then read.
+
+    Returns
+    -------
+    pandas object
+        The original object that was pickled and then re-read.
+    """
+    _path = path
+    if _path is None:
+        _path = f"__{uuid.uuid4()}__.pickle"
+    with ensure_clean(_path) as temp_path:
+        pd.to_pickle(obj, temp_path)
+        return pd.read_pickle(temp_path)
+
+
+def round_trip_pathlib(writer, reader, path: str | None = None):
+    """
+    Write an object to file specified by a pathlib.Path and read it back
+
+    Parameters
+    ----------
+    writer : callable bound to pandas object
+        IO writing function (e.g. DataFrame.to_csv )
+    reader : callable
+        IO reading function (e.g. pd.read_csv )
+    path : str, default None
+        The path where the object is written and then read.
+
+    Returns
+    -------
+    pandas object
+        The original object that was serialized and then re-read.
+    """
+    Path = pathlib.Path
+    if path is None:
+        path = "___pathlib___"
+    with ensure_clean(path) as path:
+        writer(Path(path))  # type: ignore[arg-type]
+        obj = reader(Path(path))  # type: ignore[arg-type]
+    return obj
+
+
+def round_trip_localpath(writer, reader, path: str | None = None):
+    """
+    Write an object to file specified by a py.path LocalPath and read it back.
+
+    Parameters
+    ----------
+    writer : callable bound to pandas object
+        IO writing function (e.g. DataFrame.to_csv )
+    reader : callable
+        IO reading function (e.g. pd.read_csv )
+    path : str, default None
+        The path where the object is written and then read.
+
+    Returns
+    -------
+    pandas object
+        The original object that was serialized and then re-read.
+    """
+    import pytest
+
+    LocalPath = pytest.importorskip("py.path").local
+    if path is None:
+        path = "___localpath___"
+    with ensure_clean(path) as path:
+        writer(LocalPath(path))
+        obj = reader(LocalPath(path))
+    return obj
+
+
+def write_to_compressed(compression, path, data, dest: str = "test"):
+    """
+    Write data to a compressed file.
+
+    Parameters
+    ----------
+    compression : {'gzip', 'bz2', 'zip', 'xz', 'zstd'}
+        The compression type to use.
+    path : str
+        The file path to write the data.
+    data : str
+        The data to write.
+    dest : str, default "test"
+        The destination file (for ZIP only)
+
+    Raises
+    ------
+    ValueError : An invalid compression value was passed in.
+    """
+    args: tuple[Any, ...] = (data,)
+    mode = "wb"
+    method = "write"
+    compress_method: Callable
+
+    if compression == "zip":
+        compress_method = zipfile.ZipFile
+        mode = "w"
+        args = (dest, data)
+        method = "writestr"
+    elif compression == "tar":
+        compress_method = tarfile.TarFile
+        mode = "w"
+        file = tarfile.TarInfo(name=dest)
+        bytes = io.BytesIO(data)
+        file.size = len(data)
+        args = (file, bytes)
+        method = "addfile"
+    elif compression == "gzip":
+        compress_method = gzip.GzipFile
+    elif compression == "bz2":
+        compress_method = get_bz2_file()
+    elif compression == "zstd":
+        compress_method = import_optional_dependency("zstandard").open
+    elif compression == "xz":
+        compress_method = get_lzma_file()
+    else:
+        raise ValueError(f"Unrecognized compression type: {compression}")
+
+    with compress_method(path, mode=mode) as f:
+        getattr(f, method)(*args)

AppDir/usr/lib/python3.12/site-packages/pandas/_testing/_warnings.py

@@ -0,0 +1,227 @@
+from __future__ import annotations
+
+from contextlib import (
+    contextmanager,
+    nullcontext,
+)
+import re
+import sys
+from typing import (
+    TYPE_CHECKING,
+    Literal,
+    cast,
+)
+import warnings
+
+from pandas.compat import PY311
+
+if TYPE_CHECKING:
+    from collections.abc import (
+        Generator,
+        Sequence,
+    )
+
+
+@contextmanager
+def assert_produces_warning(
+    expected_warning: type[Warning] | bool | tuple[type[Warning], ...] | None = Warning,
+    filter_level: Literal[
+        "error", "ignore", "always", "default", "module", "once"
+    ] = "always",
+    check_stacklevel: bool = True,
+    raise_on_extra_warnings: bool = True,
+    match: str | None = None,
+) -> Generator[list[warnings.WarningMessage], None, None]:
+    """
+    Context manager for running code expected to either raise a specific warning,
+    multiple specific warnings, or not raise any warnings. Verifies that the code
+    raises the expected warning(s), and that it does not raise any other unexpected
+    warnings. It is basically a wrapper around ``warnings.catch_warnings``.
+
+    Parameters
+    ----------
+    expected_warning : {Warning, False, tuple[Warning, ...], None}, default Warning
+        The type of Exception raised. ``exception.Warning`` is the base
+        class for all warnings. To raise multiple types of exceptions,
+        pass them as a tuple. To check that no warning is returned,
+        specify ``False`` or ``None``.
+    filter_level : str or None, default "always"
+        Specifies whether warnings are ignored, displayed, or turned
+        into errors.
+        Valid values are:
+
+        * "error" - turns matching warnings into exceptions
+        * "ignore" - discard the warning
+        * "always" - always emit a warning
+        * "default" - print the warning the first time it is generated
+          from each location
+        * "module" - print the warning the first time it is generated
+          from each module
+        * "once" - print the warning the first time it is generated
+
+    check_stacklevel : bool, default True
+        If True, displays the line that called the function containing
+        the warning to show were the function is called. Otherwise, the
+        line that implements the function is displayed.
+    raise_on_extra_warnings : bool, default True
+        Whether extra warnings not of the type `expected_warning` should
+        cause the test to fail.
+    match : str, optional
+        Match warning message.
+
+    Examples
+    --------
+    >>> import warnings
+    >>> with assert_produces_warning():
+    ...     warnings.warn(UserWarning())
+    ...
+    >>> with assert_produces_warning(False):
+    ...     warnings.warn(RuntimeWarning())
+    ...
+    Traceback (most recent call last):
+        ...
+    AssertionError: Caused unexpected warning(s): ['RuntimeWarning'].
+    >>> with assert_produces_warning(UserWarning):
+    ...     warnings.warn(RuntimeWarning())
+    Traceback (most recent call last):
+        ...
+    AssertionError: Did not see expected warning of class 'UserWarning'.
+
+    ..warn:: This is *not* thread-safe.
+    """
+    __tracebackhide__ = True
+
+    with warnings.catch_warnings(record=True) as w:
+        warnings.simplefilter(filter_level)
+        try:
+            yield w
+        finally:
+            if expected_warning:
+                expected_warning = cast(type[Warning], expected_warning)
+                _assert_caught_expected_warning(
+                    caught_warnings=w,
+                    expected_warning=expected_warning,
+                    match=match,
+                    check_stacklevel=check_stacklevel,
+                )
+            if raise_on_extra_warnings:
+                _assert_caught_no_extra_warnings(
+                    caught_warnings=w,
+                    expected_warning=expected_warning,
+                )
+
+
+def maybe_produces_warning(warning: type[Warning], condition: bool, **kwargs):
+    """
+    Return a context manager that possibly checks a warning based on the condition
+    """
+    if condition:
+        return assert_produces_warning(warning, **kwargs)
+    else:
+        return nullcontext()
+
+
+def _assert_caught_expected_warning(
+    *,
+    caught_warnings: Sequence[warnings.WarningMessage],
+    expected_warning: type[Warning],
+    match: str | None,
+    check_stacklevel: bool,
+) -> None:
+    """Assert that there was the expected warning among the caught warnings."""
+    saw_warning = False
+    matched_message = False
+    unmatched_messages = []
+
+    for actual_warning in caught_warnings:
+        if issubclass(actual_warning.category, expected_warning):
+            saw_warning = True
+
+            if check_stacklevel:
+                _assert_raised_with_correct_stacklevel(actual_warning)
+
+            if match is not None:
+                if re.search(match, str(actual_warning.message)):
+                    matched_message = True
+                else:
+                    unmatched_messages.append(actual_warning.message)
+
+    if not saw_warning:
+        raise AssertionError(
+            f"Did not see expected warning of class "
+            f"{repr(expected_warning.__name__)}"
+        )
+
+    if match and not matched_message:
+        raise AssertionError(
+            f"Did not see warning {repr(expected_warning.__name__)} "
+            f"matching '{match}'. The emitted warning messages are "
+            f"{unmatched_messages}"
+        )
+
+
+def _assert_caught_no_extra_warnings(
+    *,
+    caught_warnings: Sequence[warnings.WarningMessage],
+    expected_warning: type[Warning] | bool | tuple[type[Warning], ...] | None,
+) -> None:
+    """Assert that no extra warnings apart from the expected ones are caught."""
+    extra_warnings = []
+
+    for actual_warning in caught_warnings:
+        if _is_unexpected_warning(actual_warning, expected_warning):
+            # GH#38630 pytest.filterwarnings does not suppress these.
+            if actual_warning.category == ResourceWarning:
+                # GH 44732: Don't make the CI flaky by filtering SSL-related
+                # ResourceWarning from dependencies
+                if "unclosed <ssl.SSLSocket" in str(actual_warning.message):
+                    continue
+                # GH 44844: Matplotlib leaves font files open during the entire process
+                # upon import. Don't make CI flaky if ResourceWarning raised
+                # due to these open files.
+                if any("matplotlib" in mod for mod in sys.modules):
+                    continue
+            if PY311 and actual_warning.category == EncodingWarning:
+                # EncodingWarnings are checked in the CI
+                # pyproject.toml errors on EncodingWarnings in pandas
+                # Ignore EncodingWarnings from other libraries
+                continue
+            extra_warnings.append(
+                (
+                    actual_warning.category.__name__,
+                    actual_warning.message,
+                    actual_warning.filename,
+                    actual_warning.lineno,
+                )
+            )
+
+    if extra_warnings:
+        raise AssertionError(f"Caused unexpected warning(s): {repr(extra_warnings)}")
+
+
+def _is_unexpected_warning(
+    actual_warning: warnings.WarningMessage,
+    expected_warning: type[Warning] | bool | tuple[type[Warning], ...] | None,
+) -> bool:
+    """Check if the actual warning issued is unexpected."""
+    if actual_warning and not expected_warning:
+        return True
+    expected_warning = cast(type[Warning], expected_warning)
+    return bool(not issubclass(actual_warning.category, expected_warning))
+
+
+def _assert_raised_with_correct_stacklevel(
+    actual_warning: warnings.WarningMessage,
+) -> None:
+    from inspect import (
+        getframeinfo,
+        stack,
+    )
+
+    caller = getframeinfo(stack()[4][0])
+    msg = (
+        "Warning not set with correct stacklevel. "
+        f"File where warning is raised: {actual_warning.filename} != "
+        f"{caller.filename}. Warning message: {actual_warning.message}"
+    )
+    assert actual_warning.filename == caller.filename, msg

AppDir/usr/lib/python3.12/site-packages/pandas/_testing/compat.py

@@ -0,0 +1,29 @@
+"""
+Helpers for sharing tests between DataFrame/Series
+"""
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from pandas import DataFrame
+
+if TYPE_CHECKING:
+    from pandas._typing import DtypeObj
+
+
+def get_dtype(obj) -> DtypeObj:
+    if isinstance(obj, DataFrame):
+        # Note: we are assuming only one column
+        return obj.dtypes.iat[0]
+    else:
+        return obj.dtype
+
+
+def get_obj(df: DataFrame, klass):
+    """
+    For sharing tests using frame_or_series, either return the DataFrame
+    unchanged or return it's first column as a Series.
+    """
+    if klass is DataFrame:
+        return df
+    return df._ixs(0, axis=1)

AppDir/usr/lib/python3.12/site-packages/pandas/_testing/contexts.py

@@ -0,0 +1,216 @@
+from __future__ import annotations
+
+from contextlib import contextmanager
+import os
+from pathlib import Path
+import tempfile
+from typing import (
+    IO,
+    TYPE_CHECKING,
+    Any,
+)
+import uuid
+
+from pandas.compat import PYPY
+from pandas.errors import ChainedAssignmentError
+
+from pandas import set_option
+
+from pandas.io.common import get_handle
+
+if TYPE_CHECKING:
+    from collections.abc import Generator
+
+    from pandas._typing import (
+        BaseBuffer,
+        CompressionOptions,
+        FilePath,
+    )
+
+
+@contextmanager
+def decompress_file(
+    path: FilePath | BaseBuffer, compression: CompressionOptions
+) -> Generator[IO[bytes], None, None]:
+    """
+    Open a compressed file and return a file object.
+
+    Parameters
+    ----------
+    path : str
+        The path where the file is read from.
+
+    compression : {'gzip', 'bz2', 'zip', 'xz', 'zstd', None}
+        Name of the decompression to use
+
+    Returns
+    -------
+    file object
+    """
+    with get_handle(path, "rb", compression=compression, is_text=False) as handle:
+        yield handle.handle
+
+
+@contextmanager
+def set_timezone(tz: str) -> Generator[None, None, None]:
+    """
+    Context manager for temporarily setting a timezone.
+
+    Parameters
+    ----------
+    tz : str
+        A string representing a valid timezone.
+
+    Examples
+    --------
+    >>> from datetime import datetime
+    >>> from dateutil.tz import tzlocal
+    >>> tzlocal().tzname(datetime(2021, 1, 1))  # doctest: +SKIP
+    'IST'
+
+    >>> with set_timezone('US/Eastern'):
+    ...     tzlocal().tzname(datetime(2021, 1, 1))
+    ...
+    'EST'
+    """
+    import time
+
+    def setTZ(tz) -> None:
+        if tz is None:
+            try:
+                del os.environ["TZ"]
+            except KeyError:
+                pass
+        else:
+            os.environ["TZ"] = tz
+            time.tzset()
+
+    orig_tz = os.environ.get("TZ")
+    setTZ(tz)
+    try:
+        yield
+    finally:
+        setTZ(orig_tz)
+
+
+@contextmanager
+def ensure_clean(
+    filename=None, return_filelike: bool = False, **kwargs: Any
+) -> Generator[Any, None, None]:
+    """
+    Gets a temporary path and agrees to remove on close.
+
+    This implementation does not use tempfile.mkstemp to avoid having a file handle.
+    If the code using the returned path wants to delete the file itself, windows
+    requires that no program has a file handle to it.
+
+    Parameters
+    ----------
+    filename : str (optional)
+        suffix of the created file.
+    return_filelike : bool (default False)
+        if True, returns a file-like which is *always* cleaned. Necessary for
+        savefig and other functions which want to append extensions.
+    **kwargs
+        Additional keywords are passed to open().
+
+    """
+    folder = Path(tempfile.gettempdir())
+
+    if filename is None:
+        filename = ""
+    filename = str(uuid.uuid4()) + filename
+    path = folder / filename
+
+    path.touch()
+
+    handle_or_str: str | IO = str(path)
+    encoding = kwargs.pop("encoding", None)
+    if return_filelike:
+        kwargs.setdefault("mode", "w+b")
+        if encoding is None and "b" not in kwargs["mode"]:
+            encoding = "utf-8"
+        handle_or_str = open(path, encoding=encoding, **kwargs)
+
+    try:
+        yield handle_or_str
+    finally:
+        if not isinstance(handle_or_str, str):
+            handle_or_str.close()
+        if path.is_file():
+            path.unlink()
+
+
+@contextmanager
+def with_csv_dialect(name: str, **kwargs) -> Generator[None, None, None]:
+    """
+    Context manager to temporarily register a CSV dialect for parsing CSV.
+
+    Parameters
+    ----------
+    name : str
+        The name of the dialect.
+    kwargs : mapping
+        The parameters for the dialect.
+
+    Raises
+    ------
+    ValueError : the name of the dialect conflicts with a builtin one.
+
+    See Also
+    --------
+    csv : Python's CSV library.
+    """
+    import csv
+
+    _BUILTIN_DIALECTS = {"excel", "excel-tab", "unix"}
+
+    if name in _BUILTIN_DIALECTS:
+        raise ValueError("Cannot override builtin dialect.")
+
+    csv.register_dialect(name, **kwargs)
+    try:
+        yield
+    finally:
+        csv.unregister_dialect(name)
+
+
+@contextmanager
+def use_numexpr(use, min_elements=None) -> Generator[None, None, None]:
+    from pandas.core.computation import expressions as expr
+
+    if min_elements is None:
+        min_elements = expr._MIN_ELEMENTS
+
+    olduse = expr.USE_NUMEXPR
+    oldmin = expr._MIN_ELEMENTS
+    set_option("compute.use_numexpr", use)
+    expr._MIN_ELEMENTS = min_elements
+    try:
+        yield
+    finally:
+        expr._MIN_ELEMENTS = oldmin
+        set_option("compute.use_numexpr", olduse)
+
+
+def raises_chained_assignment_error(extra_warnings=(), extra_match=()):
+    from pandas._testing import assert_produces_warning
+
+    if PYPY and not extra_warnings:
+        from contextlib import nullcontext
+
+        return nullcontext()
+    elif PYPY and extra_warnings:
+        return assert_produces_warning(
+            extra_warnings,
+            match="|".join(extra_match),
+        )
+    else:
+        match = (
+            "A value is trying to be set on a copy of a DataFrame or Series "
+            "through chained assignment"
+        )
+        return assert_produces_warning(
+            (ChainedAssignmentError, *extra_warnings),
+            match="|".join((match, *extra_match)),
+        )

AppDir/usr/lib/python3.12/site-packages/pandas/_typing.py

@@ -0,0 +1,476 @@
+from __future__ import annotations
+
+from collections.abc import (
+    Hashable,
+    Iterator,
+    Mapping,
+    Sequence,
+)
+from datetime import (
+    date,
+    datetime,
+    timedelta,
+    tzinfo,
+)
+from os import PathLike
+import sys
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Callable,
+    Literal,
+    Optional,
+    Protocol,
+    Type as type_t,
+    TypeVar,
+    Union,
+)
+
+import numpy as np
+
+# To prevent import cycles place any internal imports in the branch below
+# and use a string literal forward reference to it in subsequent types
+# https://mypy.readthedocs.io/en/latest/common_issues.html#import-cycles
+if TYPE_CHECKING:
+    import numpy.typing as npt
+
+    from pandas._libs import (
+        NaTType,
+        Period,
+        Timedelta,
+        Timestamp,
+    )
+    from pandas._libs.tslibs import BaseOffset
+
+    from pandas.core.dtypes.dtypes import ExtensionDtype
+
+    from pandas import Interval
+    from pandas.arrays import (
+        DatetimeArray,
+        TimedeltaArray,
+    )
+    from pandas.core.arrays.base import ExtensionArray
+    from pandas.core.frame import DataFrame
+    from pandas.core.generic import NDFrame
+    from pandas.core.groupby.generic import (
+        DataFrameGroupBy,
+        GroupBy,
+        SeriesGroupBy,
+    )
+    from pandas.core.indexes.base import Index
+    from pandas.core.internals import (
+        ArrayManager,
+        BlockManager,
+        SingleArrayManager,
+        SingleBlockManager,
+    )
+    from pandas.core.resample import Resampler
+    from pandas.core.series import Series
+    from pandas.core.window.rolling import BaseWindow
+
+    from pandas.io.formats.format import EngFormatter
+    from pandas.tseries.holiday import AbstractHolidayCalendar
+
+    ScalarLike_co = Union[
+        int,
+        float,
+        complex,
+        str,
+        bytes,
+        np.generic,
+    ]
+
+    # numpy compatible types
+    NumpyValueArrayLike = Union[ScalarLike_co, npt.ArrayLike]
+    # Name "npt._ArrayLikeInt_co" is not defined  [name-defined]
+    NumpySorter = Optional[npt._ArrayLikeInt_co]  # type: ignore[name-defined]
+
+    if sys.version_info >= (3, 10):
+        from typing import TypeGuard  # pyright: ignore[reportUnusedImport]
+    else:
+        from typing_extensions import TypeGuard  # pyright: ignore[reportUnusedImport]
+
+    if sys.version_info >= (3, 11):
+        from typing import Self  # pyright: ignore[reportUnusedImport]
+    else:
+        from typing_extensions import Self  # pyright: ignore[reportUnusedImport]
+else:
+    npt: Any = None
+    Self: Any = None
+    TypeGuard: Any = None
+
+HashableT = TypeVar("HashableT", bound=Hashable)
+
+# array-like
+
+ArrayLike = Union["ExtensionArray", np.ndarray]
+AnyArrayLike = Union[ArrayLike, "Index", "Series"]
+TimeArrayLike = Union["DatetimeArray", "TimedeltaArray"]
+
+# list-like
+
+# Cannot use `Sequence` because a string is a sequence, and we don't want to
+# accept that.  Could refine if https://github.com/python/typing/issues/256 is
+# resolved to differentiate between Sequence[str] and str
+ListLike = Union[AnyArrayLike, list, range]
+
+# scalars
+
+PythonScalar = Union[str, float, bool]
+DatetimeLikeScalar = Union["Period", "Timestamp", "Timedelta"]
+PandasScalar = Union["Period", "Timestamp", "Timedelta", "Interval"]
+Scalar = Union[PythonScalar, PandasScalar, np.datetime64, np.timedelta64, date]
+IntStrT = TypeVar("IntStrT", int, str)
+
+
+# timestamp and timedelta convertible types
+
+TimestampConvertibleTypes = Union[
+    "Timestamp", date, np.datetime64, np.int64, float, str
+]
+TimestampNonexistent = Union[
+    Literal["shift_forward", "shift_backward", "NaT", "raise"], timedelta
+]
+TimedeltaConvertibleTypes = Union[
+    "Timedelta", timedelta, np.timedelta64, np.int64, float, str
+]
+Timezone = Union[str, tzinfo]
+
+ToTimestampHow = Literal["s", "e", "start", "end"]
+
+# NDFrameT is stricter and ensures that the same subclass of NDFrame always is
+# used. E.g. `def func(a: NDFrameT) -> NDFrameT: ...` means that if a
+# Series is passed into a function, a Series is always returned and if a DataFrame is
+# passed in, a DataFrame is always returned.
+NDFrameT = TypeVar("NDFrameT", bound="NDFrame")
+
+NumpyIndexT = TypeVar("NumpyIndexT", np.ndarray, "Index")
+
+AxisInt = int
+Axis = Union[AxisInt, Literal["index", "columns", "rows"]]
+IndexLabel = Union[Hashable, Sequence[Hashable]]
+Level = Hashable
+Shape = tuple[int, ...]
+Suffixes = tuple[Optional[str], Optional[str]]
+Ordered = Optional[bool]
+JSONSerializable = Optional[Union[PythonScalar, list, dict]]
+Frequency = Union[str, "BaseOffset"]
+Axes = ListLike
+
+RandomState = Union[
+    int,
+    np.ndarray,
+    np.random.Generator,
+    np.random.BitGenerator,
+    np.random.RandomState,
+]
+
+# dtypes
+NpDtype = Union[str, np.dtype, type_t[Union[str, complex, bool, object]]]
+Dtype = Union["ExtensionDtype", NpDtype]
+AstypeArg = Union["ExtensionDtype", "npt.DTypeLike"]
+# DtypeArg specifies all allowable dtypes in a functions its dtype argument
+DtypeArg = Union[Dtype, dict[Hashable, Dtype]]
+DtypeObj = Union[np.dtype, "ExtensionDtype"]
+
+# converters
+ConvertersArg = dict[Hashable, Callable[[Dtype], Dtype]]
+
+# parse_dates
+ParseDatesArg = Union[
+    bool, list[Hashable], list[list[Hashable]], dict[Hashable, list[Hashable]]
+]
+
+# For functions like rename that convert one label to another
+Renamer = Union[Mapping[Any, Hashable], Callable[[Any], Hashable]]
+
+# to maintain type information across generic functions and parametrization
+T = TypeVar("T")
+
+# used in decorators to preserve the signature of the function it decorates
+# see https://mypy.readthedocs.io/en/stable/generics.html#declaring-decorators
+FuncType = Callable[..., Any]
+F = TypeVar("F", bound=FuncType)
+
+# types of vectorized key functions for DataFrame::sort_values and
+# DataFrame::sort_index, among others
+ValueKeyFunc = Optional[Callable[["Series"], Union["Series", AnyArrayLike]]]
+IndexKeyFunc = Optional[Callable[["Index"], Union["Index", AnyArrayLike]]]
+
+# types of `func` kwarg for DataFrame.aggregate and Series.aggregate
+AggFuncTypeBase = Union[Callable, str]
+AggFuncTypeDict = dict[Hashable, Union[AggFuncTypeBase, list[AggFuncTypeBase]]]
+AggFuncType = Union[
+    AggFuncTypeBase,
+    list[AggFuncTypeBase],
+    AggFuncTypeDict,
+]
+AggObjType = Union[
+    "Series",
+    "DataFrame",
+    "GroupBy",
+    "SeriesGroupBy",
+    "DataFrameGroupBy",
+    "BaseWindow",
+    "Resampler",
+]
+
+PythonFuncType = Callable[[Any], Any]
+
+# filenames and file-like-objects
+AnyStr_co = TypeVar("AnyStr_co", str, bytes, covariant=True)
+AnyStr_contra = TypeVar("AnyStr_contra", str, bytes, contravariant=True)
+
+
+class BaseBuffer(Protocol):
+    @property
+    def mode(self) -> str:
+        # for _get_filepath_or_buffer
+        ...
+
+    def seek(self, __offset: int, __whence: int = ...) -> int:
+        # with one argument: gzip.GzipFile, bz2.BZ2File
+        # with two arguments: zip.ZipFile, read_sas
+        ...
+
+    def seekable(self) -> bool:
+        # for bz2.BZ2File
+        ...
+
+    def tell(self) -> int:
+        # for zip.ZipFile, read_stata, to_stata
+        ...
+
+
+class ReadBuffer(BaseBuffer, Protocol[AnyStr_co]):
+    def read(self, __n: int = ...) -> AnyStr_co:
+        # for BytesIOWrapper, gzip.GzipFile, bz2.BZ2File
+        ...
+
+
+class WriteBuffer(BaseBuffer, Protocol[AnyStr_contra]):
+    def write(self, __b: AnyStr_contra) -> Any:
+        # for gzip.GzipFile, bz2.BZ2File
+        ...
+
+    def flush(self) -> Any:
+        # for gzip.GzipFile, bz2.BZ2File
+        ...
+
+
+class ReadPickleBuffer(ReadBuffer[bytes], Protocol):
+    def readline(self) -> bytes:
+        ...
+
+
+class WriteExcelBuffer(WriteBuffer[bytes], Protocol):
+    def truncate(self, size: int | None = ...) -> int:
+        ...
+
+
+class ReadCsvBuffer(ReadBuffer[AnyStr_co], Protocol):
+    def __iter__(self) -> Iterator[AnyStr_co]:
+        # for engine=python
+        ...
+
+    def fileno(self) -> int:
+        # for _MMapWrapper
+        ...
+
+    def readline(self) -> AnyStr_co:
+        # for engine=python
+        ...
+
+    @property
+    def closed(self) -> bool:
+        # for enine=pyarrow
+        ...
+
+
+FilePath = Union[str, "PathLike[str]"]
+
+# for arbitrary kwargs passed during reading/writing files
+StorageOptions = Optional[dict[str, Any]]
+
+
+# compression keywords and compression
+CompressionDict = dict[str, Any]
+CompressionOptions = Optional[
+    Union[Literal["infer", "gzip", "bz2", "zip", "xz", "zstd", "tar"], CompressionDict]
+]
+
+# types in DataFrameFormatter
+FormattersType = Union[
+    list[Callable], tuple[Callable, ...], Mapping[Union[str, int], Callable]
+]
+ColspaceType = Mapping[Hashable, Union[str, int]]
+FloatFormatType = Union[str, Callable, "EngFormatter"]
+ColspaceArgType = Union[
+    str, int, Sequence[Union[str, int]], Mapping[Hashable, Union[str, int]]
+]
+
+# Arguments for fillna()
+FillnaOptions = Literal["backfill", "bfill", "ffill", "pad"]
+InterpolateOptions = Literal[
+    "linear",
+    "time",
+    "index",
+    "values",
+    "nearest",
+    "zero",
+    "slinear",
+    "quadratic",
+    "cubic",
+    "barycentric",
+    "polynomial",
+    "krogh",
+    "piecewise_polynomial",
+    "spline",
+    "pchip",
+    "akima",
+    "cubicspline",
+    "from_derivatives",
+]
+
+# internals
+Manager = Union[
+    "ArrayManager", "SingleArrayManager", "BlockManager", "SingleBlockManager"
+]
+SingleManager = Union["SingleArrayManager", "SingleBlockManager"]
+Manager2D = Union["ArrayManager", "BlockManager"]
+
+# indexing
+# PositionalIndexer -> valid 1D positional indexer, e.g. can pass
+# to ndarray.__getitem__
+# ScalarIndexer is for a single value as the index
+# SequenceIndexer is for list like or slices (but not tuples)
+# PositionalIndexerTuple is extends the PositionalIndexer for 2D arrays
+# These are used in various __getitem__ overloads
+# TODO(typing#684): add Ellipsis, see
+# https://github.com/python/typing/issues/684#issuecomment-548203158
+# https://bugs.python.org/issue41810
+# Using List[int] here rather than Sequence[int] to disallow tuples.
+ScalarIndexer = Union[int, np.integer]
+SequenceIndexer = Union[slice, list[int], np.ndarray]
+PositionalIndexer = Union[ScalarIndexer, SequenceIndexer]
+PositionalIndexerTuple = tuple[PositionalIndexer, PositionalIndexer]
+PositionalIndexer2D = Union[PositionalIndexer, PositionalIndexerTuple]
+if TYPE_CHECKING:
+    TakeIndexer = Union[Sequence[int], Sequence[np.integer], npt.NDArray[np.integer]]
+else:
+    TakeIndexer = Any
+
+# Shared by functions such as drop and astype
+IgnoreRaise = Literal["ignore", "raise"]
+
+# Windowing rank methods
+WindowingRankType = Literal["average", "min", "max"]
+
+# read_csv engines
+CSVEngine = Literal["c", "python", "pyarrow", "python-fwf"]
+
+# read_json engines
+JSONEngine = Literal["ujson", "pyarrow"]
+
+# read_xml parsers
+XMLParsers = Literal["lxml", "etree"]
+
+# Interval closed type
+IntervalLeftRight = Literal["left", "right"]
+IntervalClosedType = Union[IntervalLeftRight, Literal["both", "neither"]]
+
+# datetime and NaTType
+DatetimeNaTType = Union[datetime, "NaTType"]
+DateTimeErrorChoices = Union[IgnoreRaise, Literal["coerce"]]
+
+# sort_index
+SortKind = Literal["quicksort", "mergesort", "heapsort", "stable"]
+NaPosition = Literal["first", "last"]
+
+# Arguments for nsmalles and n_largest
+NsmallestNlargestKeep = Literal["first", "last", "all"]
+
+# quantile interpolation
+QuantileInterpolation = Literal["linear", "lower", "higher", "midpoint", "nearest"]
+
+# plotting
+PlottingOrientation = Literal["horizontal", "vertical"]
+
+# dropna
+AnyAll = Literal["any", "all"]
+
+# merge
+MergeHow = Literal["left", "right", "inner", "outer", "cross"]
+MergeValidate = Literal[
+    "one_to_one",
+    "1:1",
+    "one_to_many",
+    "1:m",
+    "many_to_one",
+    "m:1",
+    "many_to_many",
+    "m:m",
+]
+
+# join
+JoinHow = Literal["left", "right", "inner", "outer"]
+JoinValidate = Literal[
+    "one_to_one",
+    "1:1",
+    "one_to_many",
+    "1:m",
+    "many_to_one",
+    "m:1",
+    "many_to_many",
+    "m:m",
+]
+
+# reindex
+ReindexMethod = Union[FillnaOptions, Literal["nearest"]]
+
+MatplotlibColor = Union[str, Sequence[float]]
+TimeGrouperOrigin = Union[
+    "Timestamp", Literal["epoch", "start", "start_day", "end", "end_day"]
+]
+TimeAmbiguous = Union[Literal["infer", "NaT", "raise"], "npt.NDArray[np.bool_]"]
+TimeNonexistent = Union[
+    Literal["shift_forward", "shift_backward", "NaT", "raise"], timedelta
+]
+DropKeep = Literal["first", "last", False]
+CorrelationMethod = Union[
+    Literal["pearson", "kendall", "spearman"], Callable[[np.ndarray, np.ndarray], float]
+]
+AlignJoin = Literal["outer", "inner", "left", "right"]
+DtypeBackend = Literal["pyarrow", "numpy_nullable"]
+
+TimeUnit = Literal["s", "ms", "us", "ns"]
+OpenFileErrors = Literal[
+    "strict",
+    "ignore",
+    "replace",
+    "surrogateescape",
+    "xmlcharrefreplace",
+    "backslashreplace",
+    "namereplace",
+]
+
+# update
+UpdateJoin = Literal["left"]
+
+# applymap
+NaAction = Literal["ignore"]
+
+# from_dict
+FromDictOrient = Literal["columns", "index", "tight"]
+
+# to_gbc
+ToGbqIfexist = Literal["fail", "replace", "append"]
+
+# to_stata
+ToStataByteorder = Literal[">", "<", "little", "big"]
+
+# ExcelWriter
+ExcelWriterIfSheetExists = Literal["error", "new", "replace", "overlay"]
+
+# Offsets
+OffsetCalendar = Union[np.busdaycalendar, "AbstractHolidayCalendar"]

AppDir/usr/lib/python3.12/site-packages/pandas/_version.py

@@ -0,0 +1,692 @@
+# This file helps to compute a version number in source trees obtained from
+# git-archive tarball (such as those provided by githubs download-from-tag
+# feature). Distribution tarballs (built by setup.py sdist) and build
+# directories (produced by setup.py build) will contain a much shorter file
+# that just contains the computed version number.
+
+# This file is released into the public domain.
+# Generated by versioneer-0.28
+# https://github.com/python-versioneer/python-versioneer
+
+"""Git implementation of _version.py."""
+
+import errno
+import functools
+import os
+import re
+import subprocess
+import sys
+from typing import Callable
+
+
+def get_keywords():
+    """Get the keywords needed to look up the version information."""
+    # these strings will be replaced by git during git-archive.
+    # setup.py/versioneer.py will grep for the variable names, so they must
+    # each be defined on a line of their own. _version.py will just call
+    # get_keywords().
+    git_refnames = "$Format:%d$"
+    git_full = "$Format:%H$"
+    git_date = "$Format:%ci$"
+    keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
+    return keywords
+
+
+class VersioneerConfig:
+    """Container for Versioneer configuration parameters."""
+
+
+def get_config():
+    """Create, populate and return the VersioneerConfig() object."""
+    # these strings are filled in when 'setup.py versioneer' creates
+    # _version.py
+    cfg = VersioneerConfig()
+    cfg.VCS = "git"
+    cfg.style = "pep440"
+    cfg.tag_prefix = "v"
+    cfg.parentdir_prefix = "pandas-"
+    cfg.versionfile_source = "pandas/_version.py"
+    cfg.verbose = False
+    return cfg
+
+
+class NotThisMethod(Exception):
+    """Exception raised if a method is not valid for the current scenario."""
+
+
+LONG_VERSION_PY: dict[str, str] = {}
+HANDLERS: dict[str, dict[str, Callable]] = {}
+
+
+def register_vcs_handler(vcs, method):  # decorator
+    """Create decorator to mark a method as the handler of a VCS."""
+
+    def decorate(f):
+        """Store f in HANDLERS[vcs][method]."""
+        if vcs not in HANDLERS:
+            HANDLERS[vcs] = {}
+        HANDLERS[vcs][method] = f
+        return f
+
+    return decorate
+
+
+def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False, env=None):
+    """Call the given command(s)."""
+    assert isinstance(commands, list)
+    process = None
+
+    popen_kwargs = {}
+    if sys.platform == "win32":
+        # This hides the console window if pythonw.exe is used
+        startupinfo = subprocess.STARTUPINFO()
+        startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
+        popen_kwargs["startupinfo"] = startupinfo
+
+    for command in commands:
+        dispcmd = str([command] + args)
+        try:
+            # remember shell=False, so use git.cmd on windows, not just git
+            process = subprocess.Popen(
+                [command] + args,
+                cwd=cwd,
+                env=env,
+                stdout=subprocess.PIPE,
+                stderr=(subprocess.PIPE if hide_stderr else None),
+                **popen_kwargs,
+            )
+            break
+        except OSError:
+            e = sys.exc_info()[1]
+            if e.errno == errno.ENOENT:
+                continue
+            if verbose:
+                print(f"unable to run {dispcmd}")
+                print(e)
+            return None, None
+    else:
+        if verbose:
+            print(f"unable to find command, tried {commands}")
+        return None, None
+    stdout = process.communicate()[0].strip().decode()
+    if process.returncode != 0:
+        if verbose:
+            print(f"unable to run {dispcmd} (error)")
+            print(f"stdout was {stdout}")
+        return None, process.returncode
+    return stdout, process.returncode
+
+
+def versions_from_parentdir(parentdir_prefix, root, verbose):
+    """Try to determine the version from the parent directory name.
+
+    Source tarballs conventionally unpack into a directory that includes both
+    the project name and a version string. We will also support searching up
+    two directory levels for an appropriately named parent directory
+    """
+    rootdirs = []
+
+    for _ in range(3):
+        dirname = os.path.basename(root)
+        if dirname.startswith(parentdir_prefix):
+            return {
+                "version": dirname[len(parentdir_prefix) :],
+                "full-revisionid": None,
+                "dirty": False,
+                "error": None,
+                "date": None,
+            }
+        rootdirs.append(root)
+        root = os.path.dirname(root)  # up a level
+
+    if verbose:
+        print(
+            f"Tried directories {str(rootdirs)} \
+            but none started with prefix {parentdir_prefix}"
+        )
+    raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
+
+
+@register_vcs_handler("git", "get_keywords")
+def git_get_keywords(versionfile_abs):
+    """Extract version information from the given file."""
+    # the code embedded in _version.py can just fetch the value of these
+    # keywords. When used from setup.py, we don't want to import _version.py,
+    # so we do it with a regexp instead. This function is not used from
+    # _version.py.
+    keywords = {}
+    try:
+        with open(versionfile_abs, encoding="utf-8") as fobj:
+            for line in fobj:
+                if line.strip().startswith("git_refnames ="):
+                    mo = re.search(r'=\s*"(.*)"', line)
+                    if mo:
+                        keywords["refnames"] = mo.group(1)
+                if line.strip().startswith("git_full ="):
+                    mo = re.search(r'=\s*"(.*)"', line)
+                    if mo:
+                        keywords["full"] = mo.group(1)
+                if line.strip().startswith("git_date ="):
+                    mo = re.search(r'=\s*"(.*)"', line)
+                    if mo:
+                        keywords["date"] = mo.group(1)
+    except OSError:
+        pass
+    return keywords
+
+
+@register_vcs_handler("git", "keywords")
+def git_versions_from_keywords(keywords, tag_prefix, verbose):
+    """Get version information from git keywords."""
+    if "refnames" not in keywords:
+        raise NotThisMethod("Short version file found")
+    date = keywords.get("date")
+    if date is not None:
+        # Use only the last line.  Previous lines may contain GPG signature
+        # information.
+        date = date.splitlines()[-1]
+
+        # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant
+        # datestamp. However we prefer "%ci" (which expands to an "ISO-8601
+        # -like" string, which we must then edit to make compliant), because
+        # it's been around since git-1.5.3, and it's too difficult to
+        # discover which version we're using, or to work around using an
+        # older one.
+        date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
+    refnames = keywords["refnames"].strip()
+    if refnames.startswith("$Format"):
+        if verbose:
+            print("keywords are unexpanded, not using")
+        raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
+    refs = {r.strip() for r in refnames.strip("()").split(",")}
+    # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
+    # just "foo-1.0". If we see a "tag: " prefix, prefer those.
+    TAG = "tag: "
+    tags = {r[len(TAG) :] for r in refs if r.startswith(TAG)}
+    if not tags:
+        # Either we're using git < 1.8.3, or there really are no tags. We use
+        # a heuristic: assume all version tags have a digit. The old git %d
+        # expansion behaves like git log --decorate=short and strips out the
+        # refs/heads/ and refs/tags/ prefixes that would let us distinguish
+        # between branches and tags. By ignoring refnames without digits, we
+        # filter out many common branch names like "release" and
+        # "stabilization", as well as "HEAD" and "master".
+        tags = {r for r in refs if re.search(r"\d", r)}
+        if verbose:
+            print(f"discarding '{','.join(refs - tags)}', no digits")
+    if verbose:
+        print(f"likely tags: {','.join(sorted(tags))}")
+    for ref in sorted(tags):
+        # sorting will prefer e.g. "2.0" over "2.0rc1"
+        if ref.startswith(tag_prefix):
+            r = ref[len(tag_prefix) :]
+            # Filter out refs that exactly match prefix or that don't start
+            # with a number once the prefix is stripped (mostly a concern
+            # when prefix is '')
+            if not re.match(r"\d", r):
+                continue
+            if verbose:
+                print(f"picking {r}")
+            return {
+                "version": r,
+                "full-revisionid": keywords["full"].strip(),
+                "dirty": False,
+                "error": None,
+                "date": date,
+            }
+    # no suitable tags, so version is "0+unknown", but full hex is still there
+    if verbose:
+        print("no suitable tags, using unknown + full revision id")
+    return {
+        "version": "0+unknown",
+        "full-revisionid": keywords["full"].strip(),
+        "dirty": False,
+        "error": "no suitable tags",
+        "date": None,
+    }
+
+
+@register_vcs_handler("git", "pieces_from_vcs")
+def git_pieces_from_vcs(tag_prefix, root, verbose, runner=run_command):
+    """Get version from 'git describe' in the root of the source tree.
+
+    This only gets called if the git-archive 'subst' keywords were *not*
+    expanded, and _version.py hasn't already been rewritten with a short
+    version string, meaning we're inside a checked out source tree.
+    """
+    GITS = ["git"]
+    if sys.platform == "win32":
+        GITS = ["git.cmd", "git.exe"]
+
+    # GIT_DIR can interfere with correct operation of Versioneer.
+    # It may be intended to be passed to the Versioneer-versioned project,
+    # but that should not change where we get our version from.
+    env = os.environ.copy()
+    env.pop("GIT_DIR", None)
+    runner = functools.partial(runner, env=env)
+
+    _, rc = runner(GITS, ["rev-parse", "--git-dir"], cwd=root, hide_stderr=not verbose)
+    if rc != 0:
+        if verbose:
+            print(f"Directory {root} not under git control")
+        raise NotThisMethod("'git rev-parse --git-dir' returned error")
+
+    # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
+    # if there isn't one, this yields HEX[-dirty] (no NUM)
+    describe_out, rc = runner(
+        GITS,
+        [
+            "describe",
+            "--tags",
+            "--dirty",
+            "--always",
+            "--long",
+            "--match",
+            f"{tag_prefix}[[:digit:]]*",
+        ],
+        cwd=root,
+    )
+    # --long was added in git-1.5.5
+    if describe_out is None:
+        raise NotThisMethod("'git describe' failed")
+    describe_out = describe_out.strip()
+    full_out, rc = runner(GITS, ["rev-parse", "HEAD"], cwd=root)
+    if full_out is None:
+        raise NotThisMethod("'git rev-parse' failed")
+    full_out = full_out.strip()
+
+    pieces = {}
+    pieces["long"] = full_out
+    pieces["short"] = full_out[:7]  # maybe improved later
+    pieces["error"] = None
+
+    branch_name, rc = runner(GITS, ["rev-parse", "--abbrev-ref", "HEAD"], cwd=root)
+    # --abbrev-ref was added in git-1.6.3
+    if rc != 0 or branch_name is None:
+        raise NotThisMethod("'git rev-parse --abbrev-ref' returned error")
+    branch_name = branch_name.strip()
+
+    if branch_name == "HEAD":
+        # If we aren't exactly on a branch, pick a branch which represents
+        # the current commit. If all else fails, we are on a branchless
+        # commit.
+        branches, rc = runner(GITS, ["branch", "--contains"], cwd=root)
+        # --contains was added in git-1.5.4
+        if rc != 0 or branches is None:
+            raise NotThisMethod("'git branch --contains' returned error")
+        branches = branches.split("\n")
+
+        # Remove the first line if we're running detached
+        if "(" in branches[0]:
+            branches.pop(0)
+
+        # Strip off the leading "* " from the list of branches.
+        branches = [branch[2:] for branch in branches]
+        if "master" in branches:
+            branch_name = "master"
+        elif not branches:
+            branch_name = None
+        else:
+            # Pick the first branch that is returned. Good or bad.
+            branch_name = branches[0]
+
+    pieces["branch"] = branch_name
+
+    # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty]
+    # TAG might have hyphens.
+    git_describe = describe_out
+
+    # look for -dirty suffix
+    dirty = git_describe.endswith("-dirty")
+    pieces["dirty"] = dirty
+    if dirty:
+        git_describe = git_describe[: git_describe.rindex("-dirty")]
+
+    # now we have TAG-NUM-gHEX or HEX
+
+    if "-" in git_describe:
+        # TAG-NUM-gHEX
+        mo = re.search(r"^(.+)-(\d+)-g([0-9a-f]+)$", git_describe)
+        if not mo:
+            # unparsable. Maybe git-describe is misbehaving?
+            pieces["error"] = f"unable to parse git-describe output: '{describe_out}'"
+            return pieces
+
+        # tag
+        full_tag = mo.group(1)
+        if not full_tag.startswith(tag_prefix):
+            if verbose:
+                fmt = "tag '%s' doesn't start with prefix '%s'"
+                print(fmt % (full_tag, tag_prefix))
+            pieces[
+                "error"
+            ] = f"tag '{full_tag}' doesn't start with prefix '{tag_prefix}'"
+            return pieces
+        pieces["closest-tag"] = full_tag[len(tag_prefix) :]
+
+        # distance: number of commits since tag
+        pieces["distance"] = int(mo.group(2))
+
+        # commit: short hex revision ID
+        pieces["short"] = mo.group(3)
+
+    else:
+        # HEX: no tags
+        pieces["closest-tag"] = None
+        out, rc = runner(GITS, ["rev-list", "HEAD", "--left-right"], cwd=root)
+        pieces["distance"] = len(out.split())  # total number of commits
+
+    # commit date: see ISO-8601 comment in git_versions_from_keywords()
+    date = runner(GITS, ["show", "-s", "--format=%ci", "HEAD"], cwd=root)[0].strip()
+    # Use only the last line.  Previous lines may contain GPG signature
+    # information.
+    date = date.splitlines()[-1]
+    pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
+
+    return pieces
+
+
+def plus_or_dot(pieces):
+    """Return a + if we don't already have one, else return a ."""
+    if "+" in pieces.get("closest-tag", ""):
+        return "."
+    return "+"
+
+
+def render_pep440(pieces):
+    """Build up version string, with post-release "local version identifier".
+
+    Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you
+    get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty
+
+    Exceptions:
+    1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += plus_or_dot(pieces)
+            rendered += f"{pieces['distance']}.g{pieces['short']}"
+            if pieces["dirty"]:
+                rendered += ".dirty"
+    else:
+        # exception #1
+        rendered = f"0+untagged.{pieces['distance']}.g{pieces['short']}"
+        if pieces["dirty"]:
+            rendered += ".dirty"
+    return rendered
+
+
+def render_pep440_branch(pieces):
+    """TAG[[.dev0]+DISTANCE.gHEX[.dirty]] .
+
+    The ".dev0" means not master branch. Note that .dev0 sorts backwards
+    (a feature branch will appear "older" than the master branch).
+
+    Exceptions:
+    1: no tags. 0[.dev0]+untagged.DISTANCE.gHEX[.dirty]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            if pieces["branch"] != "master":
+                rendered += ".dev0"
+            rendered += plus_or_dot(pieces)
+            rendered += f"{pieces['distance']}.g{pieces['short']}"
+            if pieces["dirty"]:
+                rendered += ".dirty"
+    else:
+        # exception #1
+        rendered = "0"
+        if pieces["branch"] != "master":
+            rendered += ".dev0"
+        rendered += f"+untagged.{pieces['distance']}.g{pieces['short']}"
+        if pieces["dirty"]:
+            rendered += ".dirty"
+    return rendered
+
+
+def pep440_split_post(ver):
+    """Split pep440 version string at the post-release segment.
+
+    Returns the release segments before the post-release and the
+    post-release version number (or -1 if no post-release segment is present).
+    """
+    vc = str.split(ver, ".post")
+    return vc[0], int(vc[1] or 0) if len(vc) == 2 else None
+
+
+def render_pep440_pre(pieces):
+    """TAG[.postN.devDISTANCE] -- No -dirty.
+
+    Exceptions:
+    1: no tags. 0.post0.devDISTANCE
+    """
+    if pieces["closest-tag"]:
+        if pieces["distance"]:
+            # update the post release segment
+            tag_version, post_version = pep440_split_post(pieces["closest-tag"])
+            rendered = tag_version
+            if post_version is not None:
+                rendered += f".post{post_version + 1}.dev{pieces['distance']}"
+            else:
+                rendered += f".post0.dev{pieces['distance']}"
+        else:
+            # no commits, use the tag as the version
+            rendered = pieces["closest-tag"]
+    else:
+        # exception #1
+        rendered = f"0.post0.dev{pieces['distance']}"
+    return rendered
+
+
+def render_pep440_post(pieces):
+    """TAG[.postDISTANCE[.dev0]+gHEX] .
+
+    The ".dev0" means dirty. Note that .dev0 sorts backwards
+    (a dirty tree will appear "older" than the corresponding clean one),
+    but you shouldn't be releasing software with -dirty anyways.
+
+    Exceptions:
+    1: no tags. 0.postDISTANCE[.dev0]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += f".post{pieces['distance']}"
+            if pieces["dirty"]:
+                rendered += ".dev0"
+            rendered += plus_or_dot(pieces)
+            rendered += f"g{pieces['short']}"
+    else:
+        # exception #1
+        rendered = f"0.post{pieces['distance']}"
+        if pieces["dirty"]:
+            rendered += ".dev0"
+        rendered += f"+g{pieces['short']}"
+    return rendered
+
+
+def render_pep440_post_branch(pieces):
+    """TAG[.postDISTANCE[.dev0]+gHEX[.dirty]] .
+
+    The ".dev0" means not master branch.
+
+    Exceptions:
+    1: no tags. 0.postDISTANCE[.dev0]+gHEX[.dirty]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += f".post{pieces['distance']}"
+            if pieces["branch"] != "master":
+                rendered += ".dev0"
+            rendered += plus_or_dot(pieces)
+            rendered += f"g{pieces['short']}"
+            if pieces["dirty"]:
+                rendered += ".dirty"
+    else:
+        # exception #1
+        rendered = f"0.post{pieces['distance']}"
+        if pieces["branch"] != "master":
+            rendered += ".dev0"
+        rendered += f"+g{pieces['short']}"
+        if pieces["dirty"]:
+            rendered += ".dirty"
+    return rendered
+
+
+def render_pep440_old(pieces):
+    """TAG[.postDISTANCE[.dev0]] .
+
+    The ".dev0" means dirty.
+
+    Exceptions:
+    1: no tags. 0.postDISTANCE[.dev0]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += f"0.post{pieces['distance']}"
+            if pieces["dirty"]:
+                rendered += ".dev0"
+    else:
+        # exception #1
+        rendered = f"0.post{pieces['distance']}"
+        if pieces["dirty"]:
+            rendered += ".dev0"
+    return rendered
+
+
+def render_git_describe(pieces):
+    """TAG[-DISTANCE-gHEX][-dirty].
+
+    Like 'git describe --tags --dirty --always'.
+
+    Exceptions:
+    1: no tags. HEX[-dirty]  (note: no 'g' prefix)
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"]:
+            rendered += f"-{pieces['distance']}-g{pieces['short']}"
+    else:
+        # exception #1
+        rendered = pieces["short"]
+    if pieces["dirty"]:
+        rendered += "-dirty"
+    return rendered
+
+
+def render_git_describe_long(pieces):
+    """TAG-DISTANCE-gHEX[-dirty].
+
+    Like 'git describe --tags --dirty --always -long'.
+    The distance/hash is unconditional.
+
+    Exceptions:
+    1: no tags. HEX[-dirty]  (note: no 'g' prefix)
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        rendered += f"-{pieces['distance']}-g{pieces['short']}"
+    else:
+        # exception #1
+        rendered = pieces["short"]
+    if pieces["dirty"]:
+        rendered += "-dirty"
+    return rendered
+
+
+def render(pieces, style):
+    """Render the given version pieces into the requested style."""
+    if pieces["error"]:
+        return {
+            "version": "unknown",
+            "full-revisionid": pieces.get("long"),
+            "dirty": None,
+            "error": pieces["error"],
+            "date": None,
+        }
+
+    if not style or style == "default":
+        style = "pep440"  # the default
+
+    if style == "pep440":
+        rendered = render_pep440(pieces)
+    elif style == "pep440-branch":
+        rendered = render_pep440_branch(pieces)
+    elif style == "pep440-pre":
+        rendered = render_pep440_pre(pieces)
+    elif style == "pep440-post":
+        rendered = render_pep440_post(pieces)
+    elif style == "pep440-post-branch":
+        rendered = render_pep440_post_branch(pieces)
+    elif style == "pep440-old":
+        rendered = render_pep440_old(pieces)
+    elif style == "git-describe":
+        rendered = render_git_describe(pieces)
+    elif style == "git-describe-long":
+        rendered = render_git_describe_long(pieces)
+    else:
+        raise ValueError(f"unknown style '{style}'")
+
+    return {
+        "version": rendered,
+        "full-revisionid": pieces["long"],
+        "dirty": pieces["dirty"],
+        "error": None,
+        "date": pieces.get("date"),
+    }
+
+
+def get_versions():
+    """Get version information or return default if unable to do so."""
+    # I am in _version.py, which lives at ROOT/VERSIONFILE_SOURCE. If we have
+    # __file__, we can work backwards from there to the root. Some
+    # py2exe/bbfreeze/non-CPython implementations don't do __file__, in which
+    # case we can only use expanded keywords.
+
+    cfg = get_config()
+    verbose = cfg.verbose
+
+    try:
+        return git_versions_from_keywords(get_keywords(), cfg.tag_prefix, verbose)
+    except NotThisMethod:
+        pass
+
+    try:
+        root = os.path.realpath(__file__)
+        # versionfile_source is the relative path from the top of the source
+        # tree (where the .git directory might live) to this file. Invert
+        # this to find the root from __file__.
+        for _ in cfg.versionfile_source.split("/"):
+            root = os.path.dirname(root)
+    except NameError:
+        return {
+            "version": "0+unknown",
+            "full-revisionid": None,
+            "dirty": None,
+            "error": "unable to find root of source tree",
+            "date": None,
+        }
+
+    try:
+        pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
+        return render(pieces, cfg.style)
+    except NotThisMethod:
+        pass
+
+    try:
+        if cfg.parentdir_prefix:
+            return versions_from_parentdir(cfg.parentdir_prefix, root, verbose)
+    except NotThisMethod:
+        pass
+
+    return {
+        "version": "0+unknown",
+        "full-revisionid": None,
+        "dirty": None,
+        "error": "unable to compute version",
+        "date": None,
+    }

AppDir/usr/lib/python3.12/site-packages/pandas/_version_meson.py

@@ -0,0 +1,2 @@
+__version__="2.1.4"
+__git_version__="a671b5a8bf5dd13fb19f0e88edc679bc9e15c673"

AppDir/usr/lib/python3.12/site-packages/pandas/api/__init__.py

@@ -0,0 +1,16 @@
+""" public toolkit API """
+from pandas.api import (
+    extensions,
+    indexers,
+    interchange,
+    types,
+    typing,
+)
+
+__all__ = [
+    "interchange",
+    "extensions",
+    "indexers",
+    "types",
+    "typing",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/api/extensions/__init__.py

@@ -0,0 +1,33 @@
+"""
+Public API for extending pandas objects.
+"""
+
+from pandas._libs.lib import no_default
+
+from pandas.core.dtypes.base import (
+    ExtensionDtype,
+    register_extension_dtype,
+)
+
+from pandas.core.accessor import (
+    register_dataframe_accessor,
+    register_index_accessor,
+    register_series_accessor,
+)
+from pandas.core.algorithms import take
+from pandas.core.arrays import (
+    ExtensionArray,
+    ExtensionScalarOpsMixin,
+)
+
+__all__ = [
+    "no_default",
+    "ExtensionDtype",
+    "register_extension_dtype",
+    "register_dataframe_accessor",
+    "register_index_accessor",
+    "register_series_accessor",
+    "take",
+    "ExtensionArray",
+    "ExtensionScalarOpsMixin",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/api/indexers/__init__.py

@@ -0,0 +1,17 @@
+"""
+Public API for Rolling Window Indexers.
+"""
+
+from pandas.core.indexers import check_array_indexer
+from pandas.core.indexers.objects import (
+    BaseIndexer,
+    FixedForwardWindowIndexer,
+    VariableOffsetWindowIndexer,
+)
+
+__all__ = [
+    "check_array_indexer",
+    "BaseIndexer",
+    "FixedForwardWindowIndexer",
+    "VariableOffsetWindowIndexer",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/api/interchange/__init__.py

@@ -0,0 +1,8 @@
+"""
+Public API for DataFrame interchange protocol.
+"""
+
+from pandas.core.interchange.dataframe_protocol import DataFrame
+from pandas.core.interchange.from_dataframe import from_dataframe
+
+__all__ = ["from_dataframe", "DataFrame"]

AppDir/usr/lib/python3.12/site-packages/pandas/api/types/__init__.py

@@ -0,0 +1,23 @@
+"""
+Public toolkit API.
+"""
+
+from pandas._libs.lib import infer_dtype
+
+from pandas.core.dtypes.api import *  # noqa: F403
+from pandas.core.dtypes.concat import union_categoricals
+from pandas.core.dtypes.dtypes import (
+    CategoricalDtype,
+    DatetimeTZDtype,
+    IntervalDtype,
+    PeriodDtype,
+)
+
+__all__ = [
+    "infer_dtype",
+    "union_categoricals",
+    "CategoricalDtype",
+    "DatetimeTZDtype",
+    "IntervalDtype",
+    "PeriodDtype",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/api/typing/__init__.py

@@ -0,0 +1,55 @@
+"""
+Public API classes that store intermediate results useful for type-hinting.
+"""
+
+from pandas._libs import NaTType
+from pandas._libs.missing import NAType
+
+from pandas.core.groupby import (
+    DataFrameGroupBy,
+    SeriesGroupBy,
+)
+from pandas.core.resample import (
+    DatetimeIndexResamplerGroupby,
+    PeriodIndexResamplerGroupby,
+    Resampler,
+    TimedeltaIndexResamplerGroupby,
+    TimeGrouper,
+)
+from pandas.core.window import (
+    Expanding,
+    ExpandingGroupby,
+    ExponentialMovingWindow,
+    ExponentialMovingWindowGroupby,
+    Rolling,
+    RollingGroupby,
+    Window,
+)
+
+# TODO: Can't import Styler without importing jinja2
+# from pandas.io.formats.style import Styler
+from pandas.io.json._json import JsonReader
+from pandas.io.stata import StataReader
+
+__all__ = [
+    "DataFrameGroupBy",
+    "DatetimeIndexResamplerGroupby",
+    "Expanding",
+    "ExpandingGroupby",
+    "ExponentialMovingWindow",
+    "ExponentialMovingWindowGroupby",
+    "JsonReader",
+    "NaTType",
+    "NAType",
+    "PeriodIndexResamplerGroupby",
+    "Resampler",
+    "Rolling",
+    "RollingGroupby",
+    "SeriesGroupBy",
+    "StataReader",
+    # See TODO above
+    # "Styler",
+    "TimedeltaIndexResamplerGroupby",
+    "TimeGrouper",
+    "Window",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/arrays/__init__.py

@@ -0,0 +1,53 @@
+"""
+All of pandas' ExtensionArrays.
+
+See :ref:`extending.extension-types` for more.
+"""
+from pandas.core.arrays import (
+    ArrowExtensionArray,
+    ArrowStringArray,
+    BooleanArray,
+    Categorical,
+    DatetimeArray,
+    FloatingArray,
+    IntegerArray,
+    IntervalArray,
+    NumpyExtensionArray,
+    PeriodArray,
+    SparseArray,
+    StringArray,
+    TimedeltaArray,
+)
+
+__all__ = [
+    "ArrowExtensionArray",
+    "ArrowStringArray",
+    "BooleanArray",
+    "Categorical",
+    "DatetimeArray",
+    "FloatingArray",
+    "IntegerArray",
+    "IntervalArray",
+    "NumpyExtensionArray",
+    "PeriodArray",
+    "SparseArray",
+    "StringArray",
+    "TimedeltaArray",
+]
+
+
+def __getattr__(name: str):
+    if name == "PandasArray":
+        # GH#53694
+        import warnings
+
+        from pandas.util._exceptions import find_stack_level
+
+        warnings.warn(
+            "PandasArray has been renamed NumpyExtensionArray. Use that "
+            "instead. This alias will be removed in a future version.",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
+        return NumpyExtensionArray
+    raise AttributeError(f"module 'pandas.arrays' has no attribute '{name}'")

AppDir/usr/lib/python3.12/site-packages/pandas/compat/__init__.py

@@ -0,0 +1,199 @@
+"""
+compat
+======
+
+Cross-compatible functions for different versions of Python.
+
+Other items:
+* platform checker
+"""
+from __future__ import annotations
+
+import os
+import platform
+import sys
+from typing import TYPE_CHECKING
+
+from pandas.compat._constants import (
+    IS64,
+    ISMUSL,
+    PY310,
+    PY311,
+    PY312,
+    PYPY,
+)
+import pandas.compat.compressors
+from pandas.compat.numpy import is_numpy_dev
+from pandas.compat.pyarrow import (
+    pa_version_under7p0,
+    pa_version_under8p0,
+    pa_version_under9p0,
+    pa_version_under11p0,
+    pa_version_under13p0,
+    pa_version_under14p0,
+    pa_version_under14p1,
+)
+
+if TYPE_CHECKING:
+    from pandas._typing import F
+
+
+def set_function_name(f: F, name: str, cls: type) -> F:
+    """
+    Bind the name/qualname attributes of the function.
+    """
+    f.__name__ = name
+    f.__qualname__ = f"{cls.__name__}.{name}"
+    f.__module__ = cls.__module__
+    return f
+
+
+def is_platform_little_endian() -> bool:
+    """
+    Checking if the running platform is little endian.
+
+    Returns
+    -------
+    bool
+        True if the running platform is little endian.
+    """
+    return sys.byteorder == "little"
+
+
+def is_platform_windows() -> bool:
+    """
+    Checking if the running platform is windows.
+
+    Returns
+    -------
+    bool
+        True if the running platform is windows.
+    """
+    return sys.platform in ["win32", "cygwin"]
+
+
+def is_platform_linux() -> bool:
+    """
+    Checking if the running platform is linux.
+
+    Returns
+    -------
+    bool
+        True if the running platform is linux.
+    """
+    return sys.platform == "linux"
+
+
+def is_platform_mac() -> bool:
+    """
+    Checking if the running platform is mac.
+
+    Returns
+    -------
+    bool
+        True if the running platform is mac.
+    """
+    return sys.platform == "darwin"
+
+
+def is_platform_arm() -> bool:
+    """
+    Checking if the running platform use ARM architecture.
+
+    Returns
+    -------
+    bool
+        True if the running platform uses ARM architecture.
+    """
+    return platform.machine() in ("arm64", "aarch64") or platform.machine().startswith(
+        "armv"
+    )
+
+
+def is_platform_power() -> bool:
+    """
+    Checking if the running platform use Power architecture.
+
+    Returns
+    -------
+    bool
+        True if the running platform uses ARM architecture.
+    """
+    return platform.machine() in ("ppc64", "ppc64le")
+
+
+def is_ci_environment() -> bool:
+    """
+    Checking if running in a continuous integration environment by checking
+    the PANDAS_CI environment variable.
+
+    Returns
+    -------
+    bool
+        True if the running in a continuous integration environment.
+    """
+    return os.environ.get("PANDAS_CI", "0") == "1"
+
+
+def get_lzma_file() -> type[pandas.compat.compressors.LZMAFile]:
+    """
+    Importing the `LZMAFile` class from the `lzma` module.
+
+    Returns
+    -------
+    class
+        The `LZMAFile` class from the `lzma` module.
+
+    Raises
+    ------
+    RuntimeError
+        If the `lzma` module was not imported correctly, or didn't exist.
+    """
+    if not pandas.compat.compressors.has_lzma:
+        raise RuntimeError(
+            "lzma module not available. "
+            "A Python re-install with the proper dependencies, "
+            "might be required to solve this issue."
+        )
+    return pandas.compat.compressors.LZMAFile
+
+
+def get_bz2_file() -> type[pandas.compat.compressors.BZ2File]:
+    """
+    Importing the `BZ2File` class from the `bz2` module.
+
+    Returns
+    -------
+    class
+        The `BZ2File` class from the `bz2` module.
+
+    Raises
+    ------
+    RuntimeError
+        If the `bz2` module was not imported correctly, or didn't exist.
+    """
+    if not pandas.compat.compressors.has_bz2:
+        raise RuntimeError(
+            "bz2 module not available. "
+            "A Python re-install with the proper dependencies, "
+            "might be required to solve this issue."
+        )
+    return pandas.compat.compressors.BZ2File
+
+
+__all__ = [
+    "is_numpy_dev",
+    "pa_version_under7p0",
+    "pa_version_under8p0",
+    "pa_version_under9p0",
+    "pa_version_under11p0",
+    "pa_version_under13p0",
+    "pa_version_under14p0",
+    "pa_version_under14p1",
+    "IS64",
+    "ISMUSL",
+    "PY310",
+    "PY311",
+    "PY312",
+    "PYPY",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/compat/_constants.py

@@ -0,0 +1,30 @@
+"""
+_constants
+======
+
+Constants relevant for the Python implementation.
+"""
+
+from __future__ import annotations
+
+import platform
+import sys
+import sysconfig
+
+IS64 = sys.maxsize > 2**32
+
+PY310 = sys.version_info >= (3, 10)
+PY311 = sys.version_info >= (3, 11)
+PY312 = sys.version_info >= (3, 12)
+PYPY = platform.python_implementation() == "PyPy"
+ISMUSL = "musl" in (sysconfig.get_config_var("HOST_GNU_TYPE") or "")
+REF_COUNT = 2 if PY311 else 3
+
+__all__ = [
+    "IS64",
+    "ISMUSL",
+    "PY310",
+    "PY311",
+    "PY312",
+    "PYPY",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/compat/_optional.py

@@ -0,0 +1,163 @@
+from __future__ import annotations
+
+import importlib
+import sys
+from typing import TYPE_CHECKING
+import warnings
+
+from pandas.util._exceptions import find_stack_level
+
+from pandas.util.version import Version
+
+if TYPE_CHECKING:
+    import types
+
+# Update install.rst & setup.cfg when updating versions!
+
+VERSIONS = {
+    "bs4": "4.11.1",
+    "blosc": "1.21.0",
+    "bottleneck": "1.3.4",
+    "dataframe-api-compat": "0.1.7",
+    "fastparquet": "0.8.1",
+    "fsspec": "2022.05.0",
+    "html5lib": "1.1",
+    "hypothesis": "6.46.1",
+    "gcsfs": "2022.05.0",
+    "jinja2": "3.1.2",
+    "lxml.etree": "4.8.0",
+    "matplotlib": "3.6.1",
+    "numba": "0.55.2",
+    "numexpr": "2.8.0",
+    "odfpy": "1.4.1",
+    "openpyxl": "3.0.10",
+    "pandas_gbq": "0.17.5",
+    "psycopg2": "2.9.3",  # (dt dec pq3 ext lo64)
+    "pymysql": "1.0.2",
+    "pyarrow": "7.0.0",
+    "pyreadstat": "1.1.5",
+    "pytest": "7.3.2",
+    "pyxlsb": "1.0.9",
+    "s3fs": "2022.05.0",
+    "scipy": "1.8.1",
+    "sqlalchemy": "1.4.36",
+    "tables": "3.7.0",
+    "tabulate": "0.8.10",
+    "xarray": "2022.03.0",
+    "xlrd": "2.0.1",
+    "xlsxwriter": "3.0.3",
+    "zstandard": "0.17.0",
+    "tzdata": "2022.1",
+    "qtpy": "2.2.0",
+    "pyqt5": "5.15.6",
+}
+
+# A mapping from import name to package name (on PyPI) for packages where
+# these two names are different.
+
+INSTALL_MAPPING = {
+    "bs4": "beautifulsoup4",
+    "bottleneck": "Bottleneck",
+    "jinja2": "Jinja2",
+    "lxml.etree": "lxml",
+    "odf": "odfpy",
+    "pandas_gbq": "pandas-gbq",
+    "sqlalchemy": "SQLAlchemy",
+    "tables": "pytables",
+}
+
+
+def get_version(module: types.ModuleType) -> str:
+    version = getattr(module, "__version__", None)
+
+    if version is None:
+        raise ImportError(f"Can't determine version for {module.__name__}")
+    if module.__name__ == "psycopg2":
+        # psycopg2 appends " (dt dec pq3 ext lo64)" to it's version
+        version = version.split()[0]
+    return version
+
+
+def import_optional_dependency(
+    name: str,
+    extra: str = "",
+    errors: str = "raise",
+    min_version: str | None = None,
+):
+    """
+    Import an optional dependency.
+
+    By default, if a dependency is missing an ImportError with a nice
+    message will be raised. If a dependency is present, but too old,
+    we raise.
+
+    Parameters
+    ----------
+    name : str
+        The module name.
+    extra : str
+        Additional text to include in the ImportError message.
+    errors : str {'raise', 'warn', 'ignore'}
+        What to do when a dependency is not found or its version is too old.
+
+        * raise : Raise an ImportError
+        * warn : Only applicable when a module's version is to old.
+          Warns that the version is too old and returns None
+        * ignore: If the module is not installed, return None, otherwise,
+          return the module, even if the version is too old.
+          It's expected that users validate the version locally when
+          using ``errors="ignore"`` (see. ``io/html.py``)
+    min_version : str, default None
+        Specify a minimum version that is different from the global pandas
+        minimum version required.
+    Returns
+    -------
+    maybe_module : Optional[ModuleType]
+        The imported module, when found and the version is correct.
+        None is returned when the package is not found and `errors`
+        is False, or when the package's version is too old and `errors`
+        is ``'warn'``.
+    """
+
+    assert errors in {"warn", "raise", "ignore"}
+
+    package_name = INSTALL_MAPPING.get(name)
+    install_name = package_name if package_name is not None else name
+
+    msg = (
+        f"Missing optional dependency '{install_name}'. {extra} "
+        f"Use pip or conda to install {install_name}."
+    )
+    try:
+        module = importlib.import_module(name)
+    except ImportError:
+        if errors == "raise":
+            raise ImportError(msg)
+        return None
+
+    # Handle submodules: if we have submodule, grab parent module from sys.modules
+    parent = name.split(".")[0]
+    if parent != name:
+        install_name = parent
+        module_to_get = sys.modules[install_name]
+    else:
+        module_to_get = module
+    minimum_version = min_version if min_version is not None else VERSIONS.get(parent)
+    if minimum_version:
+        version = get_version(module_to_get)
+        if version and Version(version) < Version(minimum_version):
+            msg = (
+                f"Pandas requires version '{minimum_version}' or newer of '{parent}' "
+                f"(version '{version}' currently installed)."
+            )
+            if errors == "warn":
+                warnings.warn(
+                    msg,
+                    UserWarning,
+                    stacklevel=find_stack_level(),
+                )
+                return None
+            elif errors == "raise":
+                raise ImportError(msg)
+
+    return module

AppDir/usr/lib/python3.12/site-packages/pandas/compat/compressors.py

@@ -0,0 +1,77 @@
+"""
+Patched ``BZ2File`` and ``LZMAFile`` to handle pickle protocol 5.
+"""
+
+from __future__ import annotations
+
+from pickle import PickleBuffer
+
+from pandas.compat._constants import PY310
+
+try:
+    import bz2
+
+    has_bz2 = True
+except ImportError:
+    has_bz2 = False
+
+try:
+    import lzma
+
+    has_lzma = True
+except ImportError:
+    has_lzma = False
+
+
+def flatten_buffer(
+    b: bytes | bytearray | memoryview | PickleBuffer,
+) -> bytes | bytearray | memoryview:
+    """
+    Return some 1-D `uint8` typed buffer.
+
+    Coerces anything that does not match that description to one that does
+    without copying if possible (otherwise will copy).
+    """
+
+    if isinstance(b, (bytes, bytearray)):
+        return b
+
+    if not isinstance(b, PickleBuffer):
+        b = PickleBuffer(b)
+
+    try:
+        # coerce to 1-D `uint8` C-contiguous `memoryview` zero-copy
+        return b.raw()
+    except BufferError:
+        # perform in-memory copy if buffer is not contiguous
+        return memoryview(b).tobytes("A")
+
+
+if has_bz2:
+
+    class BZ2File(bz2.BZ2File):
+        if not PY310:
+
+            def write(self, b) -> int:
+                # Workaround issue where `bz2.BZ2File` expects `len`
+                # to return the number of bytes in `b` by converting
+                # `b` into something that meets that constraint with
+                # minimal copying.
+                #
+                # Note: This is fixed in Python 3.10.
+                return super().write(flatten_buffer(b))
+
+
+if has_lzma:
+
+    class LZMAFile(lzma.LZMAFile):
+        if not PY310:
+
+            def write(self, b) -> int:
+                # Workaround issue where `lzma.LZMAFile` expects `len`
+                # to return the number of bytes in `b` by converting
+                # `b` into something that meets that constraint with
+                # minimal copying.
+                #
+                # Note: This is fixed in Python 3.10.
+                return super().write(flatten_buffer(b))

AppDir/usr/lib/python3.12/site-packages/pandas/compat/numpy/__init__.py

@@ -0,0 +1,52 @@
+""" support numpy compatibility across versions """
+import warnings
+
+import numpy as np
+
+from pandas.util.version import Version
+
+# numpy versioning
+_np_version = np.__version__
+_nlv = Version(_np_version)
+np_version_gte1p24 = _nlv >= Version("1.24")
+np_version_gte1p24p3 = _nlv >= Version("1.24.3")
+np_version_gte1p25 = _nlv >= Version("1.25")
+np_version_gt2 = _nlv >= Version("2.0.0.dev0")
+is_numpy_dev = _nlv.dev is not None
+_min_numpy_ver = "1.22.4"
+
+
+if _nlv < Version(_min_numpy_ver):
+    raise ImportError(
+        f"this version of pandas is incompatible with numpy < {_min_numpy_ver}\n"
+        f"your numpy version is {_np_version}.\n"
+        f"Please upgrade numpy to >= {_min_numpy_ver} to use this pandas version"
+    )
+
+
+np_long: type
+np_ulong: type
+
+if np_version_gt2:
+    try:
+        with warnings.catch_warnings():
+            warnings.filterwarnings(
+                "ignore",
+                r".*In the future `np\.long` will be defined as.*",
+                FutureWarning,
+            )
+            np_long = np.long  # type: ignore[attr-defined]
+            np_ulong = np.ulong  # type: ignore[attr-defined]
+    except AttributeError:
+        np_long = np.int_
+        np_ulong = np.uint
+else:
+    np_long = np.int_
+    np_ulong = np.uint
+
+
+__all__ = [
+    "np",
+    "_np_version",
+    "is_numpy_dev",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/compat/numpy/function.py

@@ -0,0 +1,416 @@
+"""
+For compatibility with numpy libraries, pandas functions or methods have to
+accept '*args' and '**kwargs' parameters to accommodate numpy arguments that
+are not actually used or respected in the pandas implementation.
+
+To ensure that users do not abuse these parameters, validation is performed in
+'validators.py' to make sure that any extra parameters passed correspond ONLY
+to those in the numpy signature. Part of that validation includes whether or
+not the user attempted to pass in non-default values for these extraneous
+parameters. As we want to discourage users from relying on these parameters
+when calling the pandas implementation, we want them only to pass in the
+default values for these parameters.
+
+This module provides a set of commonly used default arguments for functions and
+methods that are spread throughout the codebase. This module will make it
+easier to adjust to future upstream changes in the analogous numpy signatures.
+"""
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    TypeVar,
+    cast,
+    overload,
+)
+
+import numpy as np
+from numpy import ndarray
+
+from pandas._libs.lib import (
+    is_bool,
+    is_integer,
+)
+from pandas.errors import UnsupportedFunctionCall
+from pandas.util._validators import (
+    validate_args,
+    validate_args_and_kwargs,
+    validate_kwargs,
+)
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        Axis,
+        AxisInt,
+    )
+
+    AxisNoneT = TypeVar("AxisNoneT", Axis, None)
+
+
+class CompatValidator:
+    def __init__(
+        self,
+        defaults,
+        fname=None,
+        method: str | None = None,
+        max_fname_arg_count=None,
+    ) -> None:
+        self.fname = fname
+        self.method = method
+        self.defaults = defaults
+        self.max_fname_arg_count = max_fname_arg_count
+
+    def __call__(
+        self,
+        args,
+        kwargs,
+        fname=None,
+        max_fname_arg_count=None,
+        method: str | None = None,
+    ) -> None:
+        if not args and not kwargs:
+            return None
+
+        fname = self.fname if fname is None else fname
+        max_fname_arg_count = (
+            self.max_fname_arg_count
+            if max_fname_arg_count is None
+            else max_fname_arg_count
+        )
+        method = self.method if method is None else method
+
+        if method == "args":
+            validate_args(fname, args, max_fname_arg_count, self.defaults)
+        elif method == "kwargs":
+            validate_kwargs(fname, kwargs, self.defaults)
+        elif method == "both":
+            validate_args_and_kwargs(
+                fname, args, kwargs, max_fname_arg_count, self.defaults
+            )
+        else:
+            raise ValueError(f"invalid validation method '{method}'")
+
+
+ARGMINMAX_DEFAULTS = {"out": None}
+validate_argmin = CompatValidator(
+    ARGMINMAX_DEFAULTS, fname="argmin", method="both", max_fname_arg_count=1
+)
+validate_argmax = CompatValidator(
+    ARGMINMAX_DEFAULTS, fname="argmax", method="both", max_fname_arg_count=1
+)
+
+
+def process_skipna(skipna: bool | ndarray | None, args) -> tuple[bool, Any]:
+    if isinstance(skipna, ndarray) or skipna is None:
+        args = (skipna,) + args
+        skipna = True
+
+    return skipna, args
+
+
+def validate_argmin_with_skipna(skipna: bool | ndarray | None, args, kwargs) -> bool:
+    """
+    If 'Series.argmin' is called via the 'numpy' library, the third parameter
+    in its signature is 'out', which takes either an ndarray or 'None', so
+    check if the 'skipna' parameter is either an instance of ndarray or is
+    None, since 'skipna' itself should be a boolean
+    """
+    skipna, args = process_skipna(skipna, args)
+    validate_argmin(args, kwargs)
+    return skipna
+
+
+def validate_argmax_with_skipna(skipna: bool | ndarray | None, args, kwargs) -> bool:
+    """
+    If 'Series.argmax' is called via the 'numpy' library, the third parameter
+    in its signature is 'out', which takes either an ndarray or 'None', so
+    check if the 'skipna' parameter is either an instance of ndarray or is
+    None, since 'skipna' itself should be a boolean
+    """
+    skipna, args = process_skipna(skipna, args)
+    validate_argmax(args, kwargs)
+    return skipna
+
+
+ARGSORT_DEFAULTS: dict[str, int | str | None] = {}
+ARGSORT_DEFAULTS["axis"] = -1
+ARGSORT_DEFAULTS["kind"] = "quicksort"
+ARGSORT_DEFAULTS["order"] = None
+ARGSORT_DEFAULTS["kind"] = None
+
+
+validate_argsort = CompatValidator(
+    ARGSORT_DEFAULTS, fname="argsort", max_fname_arg_count=0, method="both"
+)
+
+# two different signatures of argsort, this second validation for when the
+# `kind` param is supported
+ARGSORT_DEFAULTS_KIND: dict[str, int | None] = {}
+ARGSORT_DEFAULTS_KIND["axis"] = -1
+ARGSORT_DEFAULTS_KIND["order"] = None
+validate_argsort_kind = CompatValidator(
+    ARGSORT_DEFAULTS_KIND, fname="argsort", max_fname_arg_count=0, method="both"
+)
+
+
+def validate_argsort_with_ascending(ascending: bool | int | None, args, kwargs) -> bool:
+    """
+    If 'Categorical.argsort' is called via the 'numpy' library, the first
+    parameter in its signature is 'axis', which takes either an integer or
+    'None', so check if the 'ascending' parameter has either integer type or is
+    None, since 'ascending' itself should be a boolean
+    """
+    if is_integer(ascending) or ascending is None:
+        args = (ascending,) + args
+        ascending = True
+
+    validate_argsort_kind(args, kwargs, max_fname_arg_count=3)
+    ascending = cast(bool, ascending)
+    return ascending
+
+
+CLIP_DEFAULTS: dict[str, Any] = {"out": None}
+validate_clip = CompatValidator(
+    CLIP_DEFAULTS, fname="clip", method="both", max_fname_arg_count=3
+)
+
+
+@overload
+def validate_clip_with_axis(axis: ndarray, args, kwargs) -> None:
+    ...
+
+
+@overload
+def validate_clip_with_axis(axis: AxisNoneT, args, kwargs) -> AxisNoneT:
+    ...
+
+
+def validate_clip_with_axis(
+    axis: ndarray | AxisNoneT, args, kwargs
+) -> AxisNoneT | None:
+    """
+    If 'NDFrame.clip' is called via the numpy library, the third parameter in
+    its signature is 'out', which can takes an ndarray, so check if the 'axis'
+    parameter is an instance of ndarray, since 'axis' itself should either be
+    an integer or None
+    """
+    if isinstance(axis, ndarray):
+        args = (axis,) + args
+        # error: Incompatible types in assignment (expression has type "None",
+        # variable has type "Union[ndarray[Any, Any], str, int]")
+        axis = None  # type: ignore[assignment]
+
+    validate_clip(args, kwargs)
+    # error: Incompatible return value type (got "Union[ndarray[Any, Any],
+    # str, int]", expected "Union[str, int, None]")
+    return axis  # type: ignore[return-value]
+
+
+CUM_FUNC_DEFAULTS: dict[str, Any] = {}
+CUM_FUNC_DEFAULTS["dtype"] = None
+CUM_FUNC_DEFAULTS["out"] = None
+validate_cum_func = CompatValidator(
+    CUM_FUNC_DEFAULTS, method="both", max_fname_arg_count=1
+)
+validate_cumsum = CompatValidator(
+    CUM_FUNC_DEFAULTS, fname="cumsum", method="both", max_fname_arg_count=1
+)
+
+
+def validate_cum_func_with_skipna(skipna: bool, args, kwargs, name) -> bool:
+    """
+    If this function is called via the 'numpy' library, the third parameter in
+    its signature is 'dtype', which takes either a 'numpy' dtype or 'None', so
+    check if the 'skipna' parameter is a boolean or not
+    """
+    if not is_bool(skipna):
+        args = (skipna,) + args
+        skipna = True
+    elif isinstance(skipna, np.bool_):
+        skipna = bool(skipna)
+
+    validate_cum_func(args, kwargs, fname=name)
+    return skipna
+
+
+ALLANY_DEFAULTS: dict[str, bool | None] = {}
+ALLANY_DEFAULTS["dtype"] = None
+ALLANY_DEFAULTS["out"] = None
+ALLANY_DEFAULTS["keepdims"] = False
+ALLANY_DEFAULTS["axis"] = None
+validate_all = CompatValidator(
+    ALLANY_DEFAULTS, fname="all", method="both", max_fname_arg_count=1
+)
+validate_any = CompatValidator(
+    ALLANY_DEFAULTS, fname="any", method="both", max_fname_arg_count=1
+)
+
+LOGICAL_FUNC_DEFAULTS = {"out": None, "keepdims": False}
+validate_logical_func = CompatValidator(LOGICAL_FUNC_DEFAULTS, method="kwargs")
+
+MINMAX_DEFAULTS = {"axis": None, "dtype": None, "out": None, "keepdims": False}
+validate_min = CompatValidator(
+    MINMAX_DEFAULTS, fname="min", method="both", max_fname_arg_count=1
+)
+validate_max = CompatValidator(
+    MINMAX_DEFAULTS, fname="max", method="both", max_fname_arg_count=1
+)
+
+RESHAPE_DEFAULTS: dict[str, str] = {"order": "C"}
+validate_reshape = CompatValidator(
+    RESHAPE_DEFAULTS, fname="reshape", method="both", max_fname_arg_count=1
+)
+
+REPEAT_DEFAULTS: dict[str, Any] = {"axis": None}
+validate_repeat = CompatValidator(
+    REPEAT_DEFAULTS, fname="repeat", method="both", max_fname_arg_count=1
+)
+
+ROUND_DEFAULTS: dict[str, Any] = {"out": None}
+validate_round = CompatValidator(
+    ROUND_DEFAULTS, fname="round", method="both", max_fname_arg_count=1
+)
+
+SORT_DEFAULTS: dict[str, int | str | None] = {}
+SORT_DEFAULTS["axis"] = -1
+SORT_DEFAULTS["kind"] = "quicksort"
+SORT_DEFAULTS["order"] = None
+validate_sort = CompatValidator(SORT_DEFAULTS, fname="sort", method="kwargs")
+
+STAT_FUNC_DEFAULTS: dict[str, Any | None] = {}
+STAT_FUNC_DEFAULTS["dtype"] = None
+STAT_FUNC_DEFAULTS["out"] = None
+
+SUM_DEFAULTS = STAT_FUNC_DEFAULTS.copy()
+SUM_DEFAULTS["axis"] = None
+SUM_DEFAULTS["keepdims"] = False
+SUM_DEFAULTS["initial"] = None
+
+PROD_DEFAULTS = SUM_DEFAULTS.copy()
+
+MEAN_DEFAULTS = SUM_DEFAULTS.copy()
+
+MEDIAN_DEFAULTS = STAT_FUNC_DEFAULTS.copy()
+MEDIAN_DEFAULTS["overwrite_input"] = False
+MEDIAN_DEFAULTS["keepdims"] = False
+
+STAT_FUNC_DEFAULTS["keepdims"] = False
+
+validate_stat_func = CompatValidator(STAT_FUNC_DEFAULTS, method="kwargs")
+validate_sum = CompatValidator(
+    SUM_DEFAULTS, fname="sum", method="both", max_fname_arg_count=1
+)
+validate_prod = CompatValidator(
+    PROD_DEFAULTS, fname="prod", method="both", max_fname_arg_count=1
+)
+validate_mean = CompatValidator(
+    MEAN_DEFAULTS, fname="mean", method="both", max_fname_arg_count=1
+)
+validate_median = CompatValidator(
+    MEDIAN_DEFAULTS, fname="median", method="both", max_fname_arg_count=1
+)
+
+STAT_DDOF_FUNC_DEFAULTS: dict[str, bool | None] = {}
+STAT_DDOF_FUNC_DEFAULTS["dtype"] = None
+STAT_DDOF_FUNC_DEFAULTS["out"] = None
+STAT_DDOF_FUNC_DEFAULTS["keepdims"] = False
+validate_stat_ddof_func = CompatValidator(STAT_DDOF_FUNC_DEFAULTS, method="kwargs")
+
+TAKE_DEFAULTS: dict[str, str | None] = {}
+TAKE_DEFAULTS["out"] = None
+TAKE_DEFAULTS["mode"] = "raise"
+validate_take = CompatValidator(TAKE_DEFAULTS, fname="take", method="kwargs")
+
+
+def validate_take_with_convert(convert: ndarray | bool | None, args, kwargs) -> bool:
+    """
+    If this function is called via the 'numpy' library, the third parameter in
+    its signature is 'axis', which takes either an ndarray or 'None', so check
+    if the 'convert' parameter is either an instance of ndarray or is None
+    """
+    if isinstance(convert, ndarray) or convert is None:
+        args = (convert,) + args
+        convert = True
+
+    validate_take(args, kwargs, max_fname_arg_count=3, method="both")
+    return convert
+
+
+TRANSPOSE_DEFAULTS = {"axes": None}
+validate_transpose = CompatValidator(
+    TRANSPOSE_DEFAULTS, fname="transpose", method="both", max_fname_arg_count=0
+)
+
+
+def validate_groupby_func(name: str, args, kwargs, allowed=None) -> None:
+    """
+    'args' and 'kwargs' should be empty, except for allowed kwargs because all
+    of their necessary parameters are explicitly listed in the function
+    signature
+    """
+    if allowed is None:
+        allowed = []
+
+    kwargs = set(kwargs) - set(allowed)
+
+    if len(args) + len(kwargs) > 0:
+        raise UnsupportedFunctionCall(
+            "numpy operations are not valid with groupby. "
+            f"Use .groupby(...).{name}() instead"
+        )
+
+
+RESAMPLER_NUMPY_OPS = ("min", "max", "sum", "prod", "mean", "std", "var")
+
+
+def validate_resampler_func(method: str, args, kwargs) -> None:
+    """
+    'args' and 'kwargs' should be empty because all of their necessary
+    parameters are explicitly listed in the function signature
+    """
+    if len(args) + len(kwargs) > 0:
+        if method in RESAMPLER_NUMPY_OPS:
+            raise UnsupportedFunctionCall(
+                "numpy operations are not valid with resample. "
+                f"Use .resample(...).{method}() instead"
+            )
+        raise TypeError("too many arguments passed in")
+
+
+def validate_minmax_axis(axis: AxisInt | None, ndim: int = 1) -> None:
+    """
+    Ensure that the axis argument passed to min, max, argmin, or argmax is zero
+    or None, as otherwise it will be incorrectly ignored.
+
+    Parameters
+    ----------
+    axis : int or None
+    ndim : int, default 1
+
+    Raises
+    ------
+    ValueError
+    """
+    if axis is None:
+        return
+    if axis >= ndim or (axis < 0 and ndim + axis < 0):
+        raise ValueError(f"`axis` must be fewer than the number of dimensions ({ndim})")
+
+
+_validation_funcs = {
+    "median": validate_median,
+    "mean": validate_mean,
+    "min": validate_min,
+    "max": validate_max,
+    "sum": validate_sum,
+    "prod": validate_prod,
+}
+
+
+def validate_func(fname, args, kwargs) -> None:
+    if fname not in _validation_funcs:
+        return validate_stat_func(args, kwargs, fname=fname)
+
+    validation_func = _validation_funcs[fname]
+    return validation_func(args, kwargs)

AppDir/usr/lib/python3.12/site-packages/pandas/compat/pickle_compat.py

@@ -0,0 +1,262 @@
+"""
+Support pre-0.12 series pickle compatibility.
+"""
+from __future__ import annotations
+
+import contextlib
+import copy
+import io
+import pickle as pkl
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+from pandas._libs.arrays import NDArrayBacked
+from pandas._libs.tslibs import BaseOffset
+
+from pandas import Index
+from pandas.core.arrays import (
+    DatetimeArray,
+    PeriodArray,
+    TimedeltaArray,
+)
+from pandas.core.internals import BlockManager
+
+if TYPE_CHECKING:
+    from collections.abc import Generator
+
+
+def load_reduce(self):
+    stack = self.stack
+    args = stack.pop()
+    func = stack[-1]
+
+    try:
+        stack[-1] = func(*args)
+        return
+    except TypeError as err:
+        # If we have a deprecated function,
+        # try to replace and try again.
+
+        msg = "_reconstruct: First argument must be a sub-type of ndarray"
+
+        if msg in str(err):
+            try:
+                cls = args[0]
+                stack[-1] = object.__new__(cls)
+                return
+            except TypeError:
+                pass
+        elif args and isinstance(args[0], type) and issubclass(args[0], BaseOffset):
+            # TypeError: object.__new__(Day) is not safe, use Day.__new__()
+            cls = args[0]
+            stack[-1] = cls.__new__(*args)
+            return
+        elif args and issubclass(args[0], PeriodArray):
+            cls = args[0]
+            stack[-1] = NDArrayBacked.__new__(*args)
+            return
+
+        raise
+
+
+# If classes are moved, provide compat here.
+_class_locations_map = {
+    ("pandas.core.sparse.array", "SparseArray"): ("pandas.core.arrays", "SparseArray"),
+    # 15477
+    ("pandas.core.base", "FrozenNDArray"): ("numpy", "ndarray"),
+    # Re-routing unpickle block logic to go through _unpickle_block instead
+    # for pandas <= 1.3.5
+    ("pandas.core.internals.blocks", "new_block"): (
+        "pandas._libs.internals",
+        "_unpickle_block",
+    ),
+    ("pandas.core.indexes.frozen", "FrozenNDArray"): ("numpy", "ndarray"),
+    ("pandas.core.base", "FrozenList"): ("pandas.core.indexes.frozen", "FrozenList"),
+    # 10890
+    ("pandas.core.series", "TimeSeries"): ("pandas.core.series", "Series"),
+    ("pandas.sparse.series", "SparseTimeSeries"): (
+        "pandas.core.sparse.series",
+        "SparseSeries",
+    ),
+    # 12588, extensions moving
+    ("pandas._sparse", "BlockIndex"): ("pandas._libs.sparse", "BlockIndex"),
+    ("pandas.tslib", "Timestamp"): ("pandas._libs.tslib", "Timestamp"),
+    # 18543 moving period
+    ("pandas._period", "Period"): ("pandas._libs.tslibs.period", "Period"),
+    ("pandas._libs.period", "Period"): ("pandas._libs.tslibs.period", "Period"),
+    # 18014 moved __nat_unpickle from _libs.tslib-->_libs.tslibs.nattype
+    ("pandas.tslib", "__nat_unpickle"): (
+        "pandas._libs.tslibs.nattype",
+        "__nat_unpickle",
+    ),
+    ("pandas._libs.tslib", "__nat_unpickle"): (
+        "pandas._libs.tslibs.nattype",
+        "__nat_unpickle",
+    ),
+    # 15998 top-level dirs moving
+    ("pandas.sparse.array", "SparseArray"): (
+        "pandas.core.arrays.sparse",
+        "SparseArray",
+    ),
+    ("pandas.indexes.base", "_new_Index"): ("pandas.core.indexes.base", "_new_Index"),
+    ("pandas.indexes.base", "Index"): ("pandas.core.indexes.base", "Index"),
+    ("pandas.indexes.numeric", "Int64Index"): (
+        "pandas.core.indexes.base",
+        "Index",  # updated in 50775
+    ),
+    ("pandas.indexes.range", "RangeIndex"): ("pandas.core.indexes.range", "RangeIndex"),
+    ("pandas.indexes.multi", "MultiIndex"): ("pandas.core.indexes.multi", "MultiIndex"),
+    ("pandas.tseries.index", "_new_DatetimeIndex"): (
+        "pandas.core.indexes.datetimes",
+        "_new_DatetimeIndex",
+    ),
+    ("pandas.tseries.index", "DatetimeIndex"): (
+        "pandas.core.indexes.datetimes",
+        "DatetimeIndex",
+    ),
+    ("pandas.tseries.period", "PeriodIndex"): (
+        "pandas.core.indexes.period",
+        "PeriodIndex",
+    ),
+    # 19269, arrays moving
+    ("pandas.core.categorical", "Categorical"): ("pandas.core.arrays", "Categorical"),
+    # 19939, add timedeltaindex, float64index compat from 15998 move
+    ("pandas.tseries.tdi", "TimedeltaIndex"): (
+        "pandas.core.indexes.timedeltas",
+        "TimedeltaIndex",
+    ),
+    ("pandas.indexes.numeric", "Float64Index"): (
+        "pandas.core.indexes.base",
+        "Index",  # updated in 50775
+    ),
+    # 50775, remove Int64Index, UInt64Index & Float64Index from codabase
+    ("pandas.core.indexes.numeric", "Int64Index"): (
+        "pandas.core.indexes.base",
+        "Index",
+    ),
+    ("pandas.core.indexes.numeric", "UInt64Index"): (
+        "pandas.core.indexes.base",
+        "Index",
+    ),
+    ("pandas.core.indexes.numeric", "Float64Index"): (
+        "pandas.core.indexes.base",
+        "Index",
+    ),
+    ("pandas.core.arrays.sparse.dtype", "SparseDtype"): (
+        "pandas.core.dtypes.dtypes",
+        "SparseDtype",
+    ),
+}
+
+
+# our Unpickler sub-class to override methods and some dispatcher
+# functions for compat and uses a non-public class of the pickle module.
+
+
+class Unpickler(pkl._Unpickler):
+    def find_class(self, module, name):
+        # override superclass
+        key = (module, name)
+        module, name = _class_locations_map.get(key, key)
+        return super().find_class(module, name)
+
+
+Unpickler.dispatch = copy.copy(Unpickler.dispatch)
+Unpickler.dispatch[pkl.REDUCE[0]] = load_reduce
+
+
+def load_newobj(self) -> None:
+    args = self.stack.pop()
+    cls = self.stack[-1]
+
+    # compat
+    if issubclass(cls, Index):
+        obj = object.__new__(cls)
+    elif issubclass(cls, DatetimeArray) and not args:
+        arr = np.array([], dtype="M8[ns]")
+        obj = cls.__new__(cls, arr, arr.dtype)
+    elif issubclass(cls, TimedeltaArray) and not args:
+        arr = np.array([], dtype="m8[ns]")
+        obj = cls.__new__(cls, arr, arr.dtype)
+    elif cls is BlockManager and not args:
+        obj = cls.__new__(cls, (), [], False)
+    else:
+        obj = cls.__new__(cls, *args)
+
+    self.stack[-1] = obj
+
+
+Unpickler.dispatch[pkl.NEWOBJ[0]] = load_newobj
+
+
+def load_newobj_ex(self) -> None:
+    kwargs = self.stack.pop()
+    args = self.stack.pop()
+    cls = self.stack.pop()
+
+    # compat
+    if issubclass(cls, Index):
+        obj = object.__new__(cls)
+    else:
+        obj = cls.__new__(cls, *args, **kwargs)
+    self.append(obj)
+
+
+try:
+    Unpickler.dispatch[pkl.NEWOBJ_EX[0]] = load_newobj_ex
+except (AttributeError, KeyError):
+    pass
+
+
+def load(fh, encoding: str | None = None, is_verbose: bool = False):
+    """
+    Load a pickle, with a provided encoding,
+
+    Parameters
+    ----------
+    fh : a filelike object
+    encoding : an optional encoding
+    is_verbose : show exception output
+    """
+    try:
+        fh.seek(0)
+        if encoding is not None:
+            up = Unpickler(fh, encoding=encoding)
+        else:
+            up = Unpickler(fh)
+        # "Unpickler" has no attribute "is_verbose"  [attr-defined]
+        up.is_verbose = is_verbose  # type: ignore[attr-defined]
+
+        return up.load()
+    except (ValueError, TypeError):
+        raise
+
+
+def loads(
+    bytes_object: bytes,
+    *,
+    fix_imports: bool = True,
+    encoding: str = "ASCII",
+    errors: str = "strict",
+):
+    """
+    Analogous to pickle._loads.
+    """
+    fd = io.BytesIO(bytes_object)
+    return Unpickler(
+        fd, fix_imports=fix_imports, encoding=encoding, errors=errors
+    ).load()
+
+
+@contextlib.contextmanager
+def patch_pickle() -> Generator[None, None, None]:
+    """
+    Temporarily patch pickle to use our unpickler.
+    """
+    orig_loads = pkl.loads
+    try:
+        setattr(pkl, "loads", loads)
+        yield
+    finally:
+        setattr(pkl, "loads", orig_loads)

AppDir/usr/lib/python3.12/site-packages/pandas/compat/pyarrow.py

@@ -0,0 +1,31 @@
+""" support pyarrow compatibility across versions """
+
+from __future__ import annotations
+
+from pandas.util.version import Version
+
+try:
+    import pyarrow as pa
+
+    _palv = Version(Version(pa.__version__).base_version)
+    pa_version_under7p0 = _palv < Version("7.0.0")
+    pa_version_under8p0 = _palv < Version("8.0.0")
+    pa_version_under9p0 = _palv < Version("9.0.0")
+    pa_version_under10p0 = _palv < Version("10.0.0")
+    pa_version_under11p0 = _palv < Version("11.0.0")
+    pa_version_under12p0 = _palv < Version("12.0.0")
+    pa_version_under13p0 = _palv < Version("13.0.0")
+    pa_version_under14p0 = _palv < Version("14.0.0")
+    pa_version_under14p1 = _palv < Version("14.0.1")
+    pa_version_under15p0 = _palv < Version("15.0.0")
+except ImportError:
+    pa_version_under7p0 = True
+    pa_version_under8p0 = True
+    pa_version_under9p0 = True
+    pa_version_under10p0 = True
+    pa_version_under11p0 = True
+    pa_version_under12p0 = True
+    pa_version_under13p0 = True
+    pa_version_under14p0 = True
+    pa_version_under14p1 = True
+    pa_version_under15p0 = True

AppDir/usr/lib/python3.12/site-packages/pandas/core/_numba/executor.py

@@ -0,0 +1,200 @@
+from __future__ import annotations
+
+import functools
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Callable,
+)
+
+if TYPE_CHECKING:
+    from pandas._typing import Scalar
+
+import numpy as np
+
+from pandas.compat._optional import import_optional_dependency
+
+
+@functools.cache
+def make_looper(func, result_dtype, is_grouped_kernel, nopython, nogil, parallel):
+    if TYPE_CHECKING:
+        import numba
+    else:
+        numba = import_optional_dependency("numba")
+
+    if is_grouped_kernel:
+
+        @numba.jit(nopython=nopython, nogil=nogil, parallel=parallel)
+        def column_looper(
+            values: np.ndarray,
+            labels: np.ndarray,
+            ngroups: int,
+            min_periods: int,
+            *args,
+        ):
+            result = np.empty((values.shape[0], ngroups), dtype=result_dtype)
+            na_positions = {}
+            for i in numba.prange(values.shape[0]):
+                output, na_pos = func(
+                    values[i], result_dtype, labels, ngroups, min_periods, *args
+                )
+                result[i] = output
+                if len(na_pos) > 0:
+                    na_positions[i] = np.array(na_pos)
+            return result, na_positions
+
+    else:
+
+        @numba.jit(nopython=nopython, nogil=nogil, parallel=parallel)
+        def column_looper(
+            values: np.ndarray,
+            start: np.ndarray,
+            end: np.ndarray,
+            min_periods: int,
+            *args,
+        ):
+            result = np.empty((values.shape[0], len(start)), dtype=result_dtype)
+            na_positions = {}
+            for i in numba.prange(values.shape[0]):
+                output, na_pos = func(
+                    values[i], result_dtype, start, end, min_periods, *args
+                )
+                result[i] = output
+                if len(na_pos) > 0:
+                    na_positions[i] = np.array(na_pos)
+            return result, na_positions
+
+    return column_looper
+
+
+default_dtype_mapping: dict[np.dtype, Any] = {
+    np.dtype("int8"): np.int64,
+    np.dtype("int16"): np.int64,
+    np.dtype("int32"): np.int64,
+    np.dtype("int64"): np.int64,
+    np.dtype("uint8"): np.uint64,
+    np.dtype("uint16"): np.uint64,
+    np.dtype("uint32"): np.uint64,
+    np.dtype("uint64"): np.uint64,
+    np.dtype("float32"): np.float64,
+    np.dtype("float64"): np.float64,
+    np.dtype("complex64"): np.complex128,
+    np.dtype("complex128"): np.complex128,
+}
+
+
+# TODO: Preserve complex dtypes
+
+float_dtype_mapping: dict[np.dtype, Any] = {
+    np.dtype("int8"): np.float64,
+    np.dtype("int16"): np.float64,
+    np.dtype("int32"): np.float64,
+    np.dtype("int64"): np.float64,
+    np.dtype("uint8"): np.float64,
+    np.dtype("uint16"): np.float64,
+    np.dtype("uint32"): np.float64,
+    np.dtype("uint64"): np.float64,
+    np.dtype("float32"): np.float64,
+    np.dtype("float64"): np.float64,
+    np.dtype("complex64"): np.float64,
+    np.dtype("complex128"): np.float64,
+}
+
+identity_dtype_mapping: dict[np.dtype, Any] = {
+    np.dtype("int8"): np.int8,
+    np.dtype("int16"): np.int16,
+    np.dtype("int32"): np.int32,
+    np.dtype("int64"): np.int64,
+    np.dtype("uint8"): np.uint8,
+    np.dtype("uint16"): np.uint16,
+    np.dtype("uint32"): np.uint32,
+    np.dtype("uint64"): np.uint64,
+    np.dtype("float32"): np.float32,
+    np.dtype("float64"): np.float64,
+    np.dtype("complex64"): np.complex64,
+    np.dtype("complex128"): np.complex128,
+}
+
+
+def generate_shared_aggregator(
+    func: Callable[..., Scalar],
+    dtype_mapping: dict[np.dtype, np.dtype],
+    is_grouped_kernel: bool,
+    nopython: bool,
+    nogil: bool,
+    parallel: bool,
+):
+    """
+    Generate a Numba function that loops over the columns 2D object and applies
+    a 1D numba kernel over each column.
+
+    Parameters
+    ----------
+    func : function
+        aggregation function to be applied to each column
+    dtype_mapping: dict or None
+        If not None, maps a dtype to a result dtype.
+        Otherwise, will fall back to default mapping.
+    is_grouped_kernel: bool, default False
+        Whether func operates using the group labels (True)
+        or using starts/ends arrays
+
+        If true, you also need to pass the number of groups to this function
+    nopython : bool
+        nopython to be passed into numba.jit
+    nogil : bool
+        nogil to be passed into numba.jit
+    parallel : bool
+        parallel to be passed into numba.jit
+
+    Returns
+    -------
+    Numba function
+    """
+
+    # A wrapper around the looper function,
+    # to dispatch based on dtype since numba is unable to do that in nopython mode
+
+    # It also post-processes the values by inserting nans where number of observations
+    # is less than min_periods
+    # Cannot do this in numba nopython mode
+    # (you'll run into type-unification error when you cast int -> float)
+    def looper_wrapper(
+        values,
+        start=None,
+        end=None,
+        labels=None,
+        ngroups=None,
+        min_periods: int = 0,
+        **kwargs,
+    ):
+        result_dtype = dtype_mapping[values.dtype]
+        column_looper = make_looper(
+            func, result_dtype, is_grouped_kernel, nopython, nogil, parallel
+        )
+        # Need to unpack kwargs since numba only supports *args
+        if is_grouped_kernel:
+            result, na_positions = column_looper(
+                values, labels, ngroups, min_periods, *kwargs.values()
+            )
+        else:
+            result, na_positions = column_looper(
+                values, start, end, min_periods, *kwargs.values()
+            )
+        if result.dtype.kind == "i":
+            # Look if na_positions is not empty
+            # If so, convert the whole block
+            # This is OK since int dtype cannot hold nan,
+            # so if min_periods not satisfied for 1 col, it is not satisfied for
+            # all columns at that index
+            for na_pos in na_positions.values():
+                if len(na_pos) > 0:
+                    result = result.astype("float64")
+                    break
+        # TODO: Optimize this
+        for i, na_pos in na_positions.items():
+            if len(na_pos) > 0:
+                result[i, na_pos] = np.nan
+        return result
+
+    return looper_wrapper

AppDir/usr/lib/python3.12/site-packages/pandas/core/_numba/kernels/__init__.py

@@ -0,0 +1,27 @@
+from pandas.core._numba.kernels.mean_ import (
+    grouped_mean,
+    sliding_mean,
+)
+from pandas.core._numba.kernels.min_max_ import (
+    grouped_min_max,
+    sliding_min_max,
+)
+from pandas.core._numba.kernels.sum_ import (
+    grouped_sum,
+    sliding_sum,
+)
+from pandas.core._numba.kernels.var_ import (
+    grouped_var,
+    sliding_var,
+)
+
+__all__ = [
+    "sliding_mean",
+    "grouped_mean",
+    "sliding_sum",
+    "grouped_sum",
+    "sliding_var",
+    "grouped_var",
+    "sliding_min_max",
+    "grouped_min_max",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/core/_numba/kernels/mean_.py

@@ -0,0 +1,196 @@
+"""
+Numba 1D mean kernels that can be shared by
+* Dataframe / Series
+* groupby
+* rolling / expanding
+
+Mirrors pandas/_libs/window/aggregation.pyx
+"""
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numba
+import numpy as np
+
+from pandas.core._numba.kernels.shared import is_monotonic_increasing
+from pandas.core._numba.kernels.sum_ import grouped_kahan_sum
+
+if TYPE_CHECKING:
+    from pandas._typing import npt
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def add_mean(
+    val: float,
+    nobs: int,
+    sum_x: float,
+    neg_ct: int,
+    compensation: float,
+    num_consecutive_same_value: int,
+    prev_value: float,
+) -> tuple[int, float, int, float, int, float]:
+    if not np.isnan(val):
+        nobs += 1
+        y = val - compensation
+        t = sum_x + y
+        compensation = t - sum_x - y
+        sum_x = t
+        if val < 0:
+            neg_ct += 1
+
+        if val == prev_value:
+            num_consecutive_same_value += 1
+        else:
+            num_consecutive_same_value = 1
+        prev_value = val
+
+    return nobs, sum_x, neg_ct, compensation, num_consecutive_same_value, prev_value
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def remove_mean(
+    val: float, nobs: int, sum_x: float, neg_ct: int, compensation: float
+) -> tuple[int, float, int, float]:
+    if not np.isnan(val):
+        nobs -= 1
+        y = -val - compensation
+        t = sum_x + y
+        compensation = t - sum_x - y
+        sum_x = t
+        if val < 0:
+            neg_ct -= 1
+    return nobs, sum_x, neg_ct, compensation
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def sliding_mean(
+    values: np.ndarray,
+    result_dtype: np.dtype,
+    start: np.ndarray,
+    end: np.ndarray,
+    min_periods: int,
+) -> tuple[np.ndarray, list[int]]:
+    N = len(start)
+    nobs = 0
+    sum_x = 0.0
+    neg_ct = 0
+    compensation_add = 0.0
+    compensation_remove = 0.0
+
+    is_monotonic_increasing_bounds = is_monotonic_increasing(
+        start
+    ) and is_monotonic_increasing(end)
+
+    output = np.empty(N, dtype=result_dtype)
+
+    for i in range(N):
+        s = start[i]
+        e = end[i]
+        if i == 0 or not is_monotonic_increasing_bounds:
+            prev_value = values[s]
+            num_consecutive_same_value = 0
+
+            for j in range(s, e):
+                val = values[j]
+                (
+                    nobs,
+                    sum_x,
+                    neg_ct,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,
+                ) = add_mean(
+                    val,
+                    nobs,
+                    sum_x,
+                    neg_ct,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,  # pyright: ignore[reportGeneralTypeIssues]
+                )
+        else:
+            for j in range(start[i - 1], s):
+                val = values[j]
+                nobs, sum_x, neg_ct, compensation_remove = remove_mean(
+                    val, nobs, sum_x, neg_ct, compensation_remove
+                )
+
+            for j in range(end[i - 1], e):
+                val = values[j]
+                (
+                    nobs,
+                    sum_x,
+                    neg_ct,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,
+                ) = add_mean(
+                    val,
+                    nobs,
+                    sum_x,
+                    neg_ct,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,  # pyright: ignore[reportGeneralTypeIssues]
+                )
+
+        if nobs >= min_periods and nobs > 0:
+            result = sum_x / nobs
+            if num_consecutive_same_value >= nobs:
+                result = prev_value
+            elif neg_ct == 0 and result < 0:
+                result = 0
+            elif neg_ct == nobs and result > 0:
+                result = 0
+        else:
+            result = np.nan
+
+        output[i] = result
+
+        if not is_monotonic_increasing_bounds:
+            nobs = 0
+            sum_x = 0.0
+            neg_ct = 0
+            compensation_remove = 0.0
+
+    # na_position is empty list since float64 can already hold nans
+    # Do list comprehension, since numba cannot figure out that na_pos is
+    # empty list of ints on its own
+    na_pos = [0 for i in range(0)]
+    return output, na_pos
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def grouped_mean(
+    values: np.ndarray,
+    result_dtype: np.dtype,
+    labels: npt.NDArray[np.intp],
+    ngroups: int,
+    min_periods: int,
+) -> tuple[np.ndarray, list[int]]:
+    output, nobs_arr, comp_arr, consecutive_counts, prev_vals = grouped_kahan_sum(
+        values, result_dtype, labels, ngroups
+    )
+
+    # Post-processing, replace sums that don't satisfy min_periods
+    for lab in range(ngroups):
+        nobs = nobs_arr[lab]
+        num_consecutive_same_value = consecutive_counts[lab]
+        prev_value = prev_vals[lab]
+        sum_x = output[lab]
+        if nobs >= min_periods:
+            if num_consecutive_same_value >= nobs:
+                result = prev_value * nobs
+            else:
+                result = sum_x
+        else:
+            result = np.nan
+        result /= nobs
+        output[lab] = result
+
+    # na_position is empty list since float64 can already hold nans
+    # Do list comprehension, since numba cannot figure out that na_pos is
+    # empty list of ints on its own
+    na_pos = [0 for i in range(0)]
+    return output, na_pos

AppDir/usr/lib/python3.12/site-packages/pandas/core/_numba/kernels/min_max_.py

@@ -0,0 +1,125 @@
+"""
+Numba 1D min/max kernels that can be shared by
+* Dataframe / Series
+* groupby
+* rolling / expanding
+
+Mirrors pandas/_libs/window/aggregation.pyx
+"""
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numba
+import numpy as np
+
+if TYPE_CHECKING:
+    from pandas._typing import npt
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def sliding_min_max(
+    values: np.ndarray,
+    result_dtype: np.dtype,
+    start: np.ndarray,
+    end: np.ndarray,
+    min_periods: int,
+    is_max: bool,
+) -> tuple[np.ndarray, list[int]]:
+    N = len(start)
+    nobs = 0
+    output = np.empty(N, dtype=result_dtype)
+    na_pos = []
+    # Use deque once numba supports it
+    # https://github.com/numba/numba/issues/7417
+    Q: list = []
+    W: list = []
+    for i in range(N):
+        curr_win_size = end[i] - start[i]
+        if i == 0:
+            st = start[i]
+        else:
+            st = end[i - 1]
+
+        for k in range(st, end[i]):
+            ai = values[k]
+            if not np.isnan(ai):
+                nobs += 1
+            elif is_max:
+                ai = -np.inf
+            else:
+                ai = np.inf
+            # Discard previous entries if we find new min or max
+            if is_max:
+                while Q and ((ai >= values[Q[-1]]) or values[Q[-1]] != values[Q[-1]]):
+                    Q.pop()
+            else:
+                while Q and ((ai <= values[Q[-1]]) or values[Q[-1]] != values[Q[-1]]):
+                    Q.pop()
+            Q.append(k)
+            W.append(k)
+
+        # Discard entries outside and left of current window
+        while Q and Q[0] <= start[i] - 1:
+            Q.pop(0)
+        while W and W[0] <= start[i] - 1:
+            if not np.isnan(values[W[0]]):
+                nobs -= 1
+            W.pop(0)
+
+        # Save output based on index in input value array
+        if Q and curr_win_size > 0 and nobs >= min_periods:
+            output[i] = values[Q[0]]
+        else:
+            if values.dtype.kind != "i":
+                output[i] = np.nan
+            else:
+                na_pos.append(i)
+
+    return output, na_pos
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def grouped_min_max(
+    values: np.ndarray,
+    result_dtype: np.dtype,
+    labels: npt.NDArray[np.intp],
+    ngroups: int,
+    min_periods: int,
+    is_max: bool,
+) -> tuple[np.ndarray, list[int]]:
+    N = len(labels)
+    nobs = np.zeros(ngroups, dtype=np.int64)
+    na_pos = []
+    output = np.empty(ngroups, dtype=result_dtype)
+
+    for i in range(N):
+        lab = labels[i]
+        val = values[i]
+        if lab < 0:
+            continue
+
+        if values.dtype.kind == "i" or not np.isnan(val):
+            nobs[lab] += 1
+        else:
+            # NaN value cannot be a min/max value
+            continue
+
+        if nobs[lab] == 1:
+            # First element in group, set output equal to this
+            output[lab] = val
+            continue
+
+        if is_max:
+            if val > output[lab]:
+                output[lab] = val
+        else:
+            if val < output[lab]:
+                output[lab] = val
+
+    # Set labels that don't satisfy min_periods as np.nan
+    for lab, count in enumerate(nobs):
+        if count < min_periods:
+            na_pos.append(lab)
+
+    return output, na_pos

AppDir/usr/lib/python3.12/site-packages/pandas/core/_numba/kernels/shared.py

@@ -0,0 +1,29 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numba
+
+if TYPE_CHECKING:
+    import numpy as np
+
+
+@numba.jit(
+    # error: Any? not callable
+    numba.boolean(numba.int64[:]),  # type: ignore[misc]
+    nopython=True,
+    nogil=True,
+    parallel=False,
+)
+def is_monotonic_increasing(bounds: np.ndarray) -> bool:
+    """Check if int64 values are monotonically increasing."""
+    n = len(bounds)
+    if n < 2:
+        return True
+    prev = bounds[0]
+    for i in range(1, n):
+        cur = bounds[i]
+        if cur < prev:
+            return False
+        prev = cur
+    return True

AppDir/usr/lib/python3.12/site-packages/pandas/core/_numba/kernels/sum_.py

@@ -0,0 +1,244 @@
+"""
+Numba 1D sum kernels that can be shared by
+* Dataframe / Series
+* groupby
+* rolling / expanding
+
+Mirrors pandas/_libs/window/aggregation.pyx
+"""
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+
+import numba
+from numba.extending import register_jitable
+import numpy as np
+
+if TYPE_CHECKING:
+    from pandas._typing import npt
+
+from pandas.core._numba.kernels.shared import is_monotonic_increasing
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def add_sum(
+    val: Any,
+    nobs: int,
+    sum_x: Any,
+    compensation: Any,
+    num_consecutive_same_value: int,
+    prev_value: Any,
+) -> tuple[int, Any, Any, int, Any]:
+    if not np.isnan(val):
+        nobs += 1
+        y = val - compensation
+        t = sum_x + y
+        compensation = t - sum_x - y
+        sum_x = t
+
+        if val == prev_value:
+            num_consecutive_same_value += 1
+        else:
+            num_consecutive_same_value = 1
+        prev_value = val
+
+    return nobs, sum_x, compensation, num_consecutive_same_value, prev_value
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def remove_sum(
+    val: Any, nobs: int, sum_x: Any, compensation: Any
+) -> tuple[int, Any, Any]:
+    if not np.isnan(val):
+        nobs -= 1
+        y = -val - compensation
+        t = sum_x + y
+        compensation = t - sum_x - y
+        sum_x = t
+    return nobs, sum_x, compensation
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def sliding_sum(
+    values: np.ndarray,
+    result_dtype: np.dtype,
+    start: np.ndarray,
+    end: np.ndarray,
+    min_periods: int,
+) -> tuple[np.ndarray, list[int]]:
+    dtype = values.dtype
+
+    na_val: object = np.nan
+    if dtype.kind == "i":
+        na_val = 0
+
+    N = len(start)
+    nobs = 0
+    sum_x = 0
+    compensation_add = 0
+    compensation_remove = 0
+    na_pos = []
+
+    is_monotonic_increasing_bounds = is_monotonic_increasing(
+        start
+    ) and is_monotonic_increasing(end)
+
+    output = np.empty(N, dtype=result_dtype)
+
+    for i in range(N):
+        s = start[i]
+        e = end[i]
+        if i == 0 or not is_monotonic_increasing_bounds:
+            prev_value = values[s]
+            num_consecutive_same_value = 0
+
+            for j in range(s, e):
+                val = values[j]
+                (
+                    nobs,
+                    sum_x,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,
+                ) = add_sum(
+                    val,
+                    nobs,
+                    sum_x,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,
+                )
+        else:
+            for j in range(start[i - 1], s):
+                val = values[j]
+                nobs, sum_x, compensation_remove = remove_sum(
+                    val, nobs, sum_x, compensation_remove
+                )
+
+            for j in range(end[i - 1], e):
+                val = values[j]
+                (
+                    nobs,
+                    sum_x,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,
+                ) = add_sum(
+                    val,
+                    nobs,
+                    sum_x,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,
+                )
+
+        if nobs == 0 == min_periods:
+            result: object = 0
+        elif nobs >= min_periods:
+            if num_consecutive_same_value >= nobs:
+                result = prev_value * nobs
+            else:
+                result = sum_x
+        else:
+            result = na_val
+            if dtype.kind == "i":
+                na_pos.append(i)
+
+        output[i] = result
+
+        if not is_monotonic_increasing_bounds:
+            nobs = 0
+            sum_x = 0
+            compensation_remove = 0
+
+    return output, na_pos
+
+
+# Mypy/pyright don't like the fact that the decorator is untyped
+@register_jitable  # type: ignore[misc]
+def grouped_kahan_sum(
+    values: np.ndarray,
+    result_dtype: np.dtype,
+    labels: npt.NDArray[np.intp],
+    ngroups: int,
+) -> tuple[
+    np.ndarray, npt.NDArray[np.int64], np.ndarray, npt.NDArray[np.int64], np.ndarray
+]:
+    N = len(labels)
+
+    nobs_arr = np.zeros(ngroups, dtype=np.int64)
+    comp_arr = np.zeros(ngroups, dtype=values.dtype)
+    consecutive_counts = np.zeros(ngroups, dtype=np.int64)
+    prev_vals = np.zeros(ngroups, dtype=values.dtype)
+    output = np.zeros(ngroups, dtype=result_dtype)
+
+    for i in range(N):
+        lab = labels[i]
+        val = values[i]
+
+        if lab < 0:
+            continue
+
+        sum_x = output[lab]
+        nobs = nobs_arr[lab]
+        compensation_add = comp_arr[lab]
+        num_consecutive_same_value = consecutive_counts[lab]
+        prev_value = prev_vals[lab]
+
+        (
+            nobs,
+            sum_x,
+            compensation_add,
+            num_consecutive_same_value,
+            prev_value,
+        ) = add_sum(
+            val,
+            nobs,
+            sum_x,
+            compensation_add,
+            num_consecutive_same_value,
+            prev_value,
+        )
+
+        output[lab] = sum_x
+        consecutive_counts[lab] = num_consecutive_same_value
+        prev_vals[lab] = prev_value
+        comp_arr[lab] = compensation_add
+        nobs_arr[lab] = nobs
+    return output, nobs_arr, comp_arr, consecutive_counts, prev_vals
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def grouped_sum(
+    values: np.ndarray,
+    result_dtype: np.dtype,
+    labels: npt.NDArray[np.intp],
+    ngroups: int,
+    min_periods: int,
+) -> tuple[np.ndarray, list[int]]:
+    na_pos = []
+
+    output, nobs_arr, comp_arr, consecutive_counts, prev_vals = grouped_kahan_sum(
+        values, result_dtype, labels, ngroups
+    )
+
+    # Post-processing, replace sums that don't satisfy min_periods
+    for lab in range(ngroups):
+        nobs = nobs_arr[lab]
+        num_consecutive_same_value = consecutive_counts[lab]
+        prev_value = prev_vals[lab]
+        sum_x = output[lab]
+        if nobs >= min_periods:
+            if num_consecutive_same_value >= nobs:
+                result = prev_value * nobs
+            else:
+                result = sum_x
+        else:
+            result = sum_x  # Don't change val, will be replaced by nan later
+            na_pos.append(lab)
+        output[lab] = result
+
+    return output, na_pos

AppDir/usr/lib/python3.12/site-packages/pandas/core/_numba/kernels/var_.py

@@ -0,0 +1,245 @@
+"""
+Numba 1D var kernels that can be shared by
+* Dataframe / Series
+* groupby
+* rolling / expanding
+
+Mirrors pandas/_libs/window/aggregation.pyx
+"""
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numba
+import numpy as np
+
+if TYPE_CHECKING:
+    from pandas._typing import npt
+
+from pandas.core._numba.kernels.shared import is_monotonic_increasing
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def add_var(
+    val: float,
+    nobs: int,
+    mean_x: float,
+    ssqdm_x: float,
+    compensation: float,
+    num_consecutive_same_value: int,
+    prev_value: float,
+) -> tuple[int, float, float, float, int, float]:
+    if not np.isnan(val):
+        if val == prev_value:
+            num_consecutive_same_value += 1
+        else:
+            num_consecutive_same_value = 1
+        prev_value = val
+
+        nobs += 1
+        prev_mean = mean_x - compensation
+        y = val - compensation
+        t = y - mean_x
+        compensation = t + mean_x - y
+        delta = t
+        if nobs:
+            mean_x += delta / nobs
+        else:
+            mean_x = 0
+        ssqdm_x += (val - prev_mean) * (val - mean_x)
+    return nobs, mean_x, ssqdm_x, compensation, num_consecutive_same_value, prev_value
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def remove_var(
+    val: float, nobs: int, mean_x: float, ssqdm_x: float, compensation: float
+) -> tuple[int, float, float, float]:
+    if not np.isnan(val):
+        nobs -= 1
+        if nobs:
+            prev_mean = mean_x - compensation
+            y = val - compensation
+            t = y - mean_x
+            compensation = t + mean_x - y
+            delta = t
+            mean_x -= delta / nobs
+            ssqdm_x -= (val - prev_mean) * (val - mean_x)
+        else:
+            mean_x = 0
+            ssqdm_x = 0
+    return nobs, mean_x, ssqdm_x, compensation
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def sliding_var(
+    values: np.ndarray,
+    result_dtype: np.dtype,
+    start: np.ndarray,
+    end: np.ndarray,
+    min_periods: int,
+    ddof: int = 1,
+) -> tuple[np.ndarray, list[int]]:
+    N = len(start)
+    nobs = 0
+    mean_x = 0.0
+    ssqdm_x = 0.0
+    compensation_add = 0.0
+    compensation_remove = 0.0
+
+    min_periods = max(min_periods, 1)
+    is_monotonic_increasing_bounds = is_monotonic_increasing(
+        start
+    ) and is_monotonic_increasing(end)
+
+    output = np.empty(N, dtype=result_dtype)
+
+    for i in range(N):
+        s = start[i]
+        e = end[i]
+        if i == 0 or not is_monotonic_increasing_bounds:
+            prev_value = values[s]
+            num_consecutive_same_value = 0
+
+            for j in range(s, e):
+                val = values[j]
+                (
+                    nobs,
+                    mean_x,
+                    ssqdm_x,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,
+                ) = add_var(
+                    val,
+                    nobs,
+                    mean_x,
+                    ssqdm_x,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,  # pyright: ignore[reportGeneralTypeIssues]
+                )
+        else:
+            for j in range(start[i - 1], s):
+                val = values[j]
+                nobs, mean_x, ssqdm_x, compensation_remove = remove_var(
+                    val, nobs, mean_x, ssqdm_x, compensation_remove
+                )
+
+            for j in range(end[i - 1], e):
+                val = values[j]
+                (
+                    nobs,
+                    mean_x,
+                    ssqdm_x,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,
+                ) = add_var(
+                    val,
+                    nobs,
+                    mean_x,
+                    ssqdm_x,
+                    compensation_add,
+                    num_consecutive_same_value,
+                    prev_value,  # pyright: ignore[reportGeneralTypeIssues]
+                )
+
+        if nobs >= min_periods and nobs > ddof:
+            if nobs == 1 or num_consecutive_same_value >= nobs:
+                result = 0.0
+            else:
+                result = ssqdm_x / (nobs - ddof)
+        else:
+            result = np.nan
+
+        output[i] = result
+
+        if not is_monotonic_increasing_bounds:
+            nobs = 0
+            mean_x = 0.0
+            ssqdm_x = 0.0
+            compensation_remove = 0.0
+
+    # na_position is empty list since float64 can already hold nans
+    # Do list comprehension, since numba cannot figure out that na_pos is
+    # empty list of ints on its own
+    na_pos = [0 for i in range(0)]
+    return output, na_pos
+
+
+@numba.jit(nopython=True, nogil=True, parallel=False)
+def grouped_var(
+    values: np.ndarray,
+    result_dtype: np.dtype,
+    labels: npt.NDArray[np.intp],
+    ngroups: int,
+    min_periods: int,
+    ddof: int = 1,
+) -> tuple[np.ndarray, list[int]]:
+    N = len(labels)
+
+    nobs_arr = np.zeros(ngroups, dtype=np.int64)
+    comp_arr = np.zeros(ngroups, dtype=values.dtype)
+    consecutive_counts = np.zeros(ngroups, dtype=np.int64)
+    prev_vals = np.zeros(ngroups, dtype=values.dtype)
+    output = np.zeros(ngroups, dtype=result_dtype)
+    means = np.zeros(ngroups, dtype=result_dtype)
+
+    for i in range(N):
+        lab = labels[i]
+        val = values[i]
+
+        if lab < 0:
+            continue
+
+        mean_x = means[lab]
+        ssqdm_x = output[lab]
+        nobs = nobs_arr[lab]
+        compensation_add = comp_arr[lab]
+        num_consecutive_same_value = consecutive_counts[lab]
+        prev_value = prev_vals[lab]
+
+        (
+            nobs,
+            mean_x,
+            ssqdm_x,
+            compensation_add,
+            num_consecutive_same_value,
+            prev_value,
+        ) = add_var(
+            val,
+            nobs,
+            mean_x,
+            ssqdm_x,
+            compensation_add,
+            num_consecutive_same_value,
+            prev_value,
+        )
+
+        output[lab] = ssqdm_x
+        means[lab] = mean_x
+        consecutive_counts[lab] = num_consecutive_same_value
+        prev_vals[lab] = prev_value
+        comp_arr[lab] = compensation_add
+        nobs_arr[lab] = nobs
+
+    # Post-processing, replace vars that don't satisfy min_periods
+    for lab in range(ngroups):
+        nobs = nobs_arr[lab]
+        num_consecutive_same_value = consecutive_counts[lab]
+        ssqdm_x = output[lab]
+        if nobs >= min_periods and nobs > ddof:
+            if nobs == 1 or num_consecutive_same_value >= nobs:
+                result = 0.0
+            else:
+                result = ssqdm_x / (nobs - ddof)
+        else:
+            result = np.nan
+        output[lab] = result
+
+    # Second pass to get the std.dev
+    # na_position is empty list since float64 can already hold nans
+    # Do list comprehension, since numba cannot figure out that na_pos is
+    # empty list of ints on its own
+    na_pos = [0 for i in range(0)]
+    return output, na_pos

AppDir/usr/lib/python3.12/site-packages/pandas/core/accessor.py

@@ -0,0 +1,340 @@
+"""
+
+accessor.py contains base classes for implementing accessor properties
+that can be mixed into or pinned onto other pandas classes.
+
+"""
+from __future__ import annotations
+
+from typing import (
+    Callable,
+    final,
+)
+import warnings
+
+from pandas.util._decorators import doc
+from pandas.util._exceptions import find_stack_level
+
+
+class DirNamesMixin:
+    _accessors: set[str] = set()
+    _hidden_attrs: frozenset[str] = frozenset()
+
+    @final
+    def _dir_deletions(self) -> set[str]:
+        """
+        Delete unwanted __dir__ for this object.
+        """
+        return self._accessors | self._hidden_attrs
+
+    def _dir_additions(self) -> set[str]:
+        """
+        Add additional __dir__ for this object.
+        """
+        return {accessor for accessor in self._accessors if hasattr(self, accessor)}
+
+    def __dir__(self) -> list[str]:
+        """
+        Provide method name lookup and completion.
+
+        Notes
+        -----
+        Only provide 'public' methods.
+        """
+        rv = set(super().__dir__())
+        rv = (rv - self._dir_deletions()) | self._dir_additions()
+        return sorted(rv)
+
+
+class PandasDelegate:
+    """
+    Abstract base class for delegating methods/properties.
+    """
+
+    def _delegate_property_get(self, name: str, *args, **kwargs):
+        raise TypeError(f"You cannot access the property {name}")
+
+    def _delegate_property_set(self, name: str, value, *args, **kwargs):
+        raise TypeError(f"The property {name} cannot be set")
+
+    def _delegate_method(self, name: str, *args, **kwargs):
+        raise TypeError(f"You cannot call method {name}")
+
+    @classmethod
+    def _add_delegate_accessors(
+        cls,
+        delegate,
+        accessors: list[str],
+        typ: str,
+        overwrite: bool = False,
+        accessor_mapping: Callable[[str], str] = lambda x: x,
+        raise_on_missing: bool = True,
+    ) -> None:
+        """
+        Add accessors to cls from the delegate class.
+
+        Parameters
+        ----------
+        cls
+            Class to add the methods/properties to.
+        delegate
+            Class to get methods/properties and doc-strings.
+        accessors : list of str
+            List of accessors to add.
+        typ : {'property', 'method'}
+        overwrite : bool, default False
+            Overwrite the method/property in the target class if it exists.
+        accessor_mapping: Callable, default lambda x: x
+            Callable to map the delegate's function to the cls' function.
+        raise_on_missing: bool, default True
+            Raise if an accessor does not exist on delegate.
+            False skips the missing accessor.
+        """
+
+        def _create_delegator_property(name: str):
+            def _getter(self):
+                return self._delegate_property_get(name)
+
+            def _setter(self, new_values):
+                return self._delegate_property_set(name, new_values)
+
+            _getter.__name__ = name
+            _setter.__name__ = name
+
+            return property(
+                fget=_getter,
+                fset=_setter,
+                doc=getattr(delegate, accessor_mapping(name)).__doc__,
+            )
+
+        def _create_delegator_method(name: str):
+            def f(self, *args, **kwargs):
+                return self._delegate_method(name, *args, **kwargs)
+
+            f.__name__ = name
+            f.__doc__ = getattr(delegate, accessor_mapping(name)).__doc__
+
+            return f
+
+        for name in accessors:
+            if (
+                not raise_on_missing
+                and getattr(delegate, accessor_mapping(name), None) is None
+            ):
+                continue
+
+            if typ == "property":
+                f = _create_delegator_property(name)
+            else:
+                f = _create_delegator_method(name)
+
+            # don't overwrite existing methods/properties
+            if overwrite or not hasattr(cls, name):
+                setattr(cls, name, f)
+
+
+def delegate_names(
+    delegate,
+    accessors: list[str],
+    typ: str,
+    overwrite: bool = False,
+    accessor_mapping: Callable[[str], str] = lambda x: x,
+    raise_on_missing: bool = True,
+):
+    """
+    Add delegated names to a class using a class decorator.  This provides
+    an alternative usage to directly calling `_add_delegate_accessors`
+    below a class definition.
+
+    Parameters
+    ----------
+    delegate : object
+        The class to get methods/properties & doc-strings.
+    accessors : Sequence[str]
+        List of accessor to add.
+    typ : {'property', 'method'}
+    overwrite : bool, default False
+       Overwrite the method/property in the target class if it exists.
+    accessor_mapping: Callable, default lambda x: x
+        Callable to map the delegate's function to the cls' function.
+    raise_on_missing: bool, default True
+        Raise if an accessor does not exist on delegate.
+        False skips the missing accessor.
+
+    Returns
+    -------
+    callable
+        A class decorator.
+
+    Examples
+    --------
+    @delegate_names(Categorical, ["categories", "ordered"], "property")
+    class CategoricalAccessor(PandasDelegate):
+        [...]
+    """
+
+    def add_delegate_accessors(cls):
+        cls._add_delegate_accessors(
+            delegate,
+            accessors,
+            typ,
+            overwrite=overwrite,
+            accessor_mapping=accessor_mapping,
+            raise_on_missing=raise_on_missing,
+        )
+        return cls
+
+    return add_delegate_accessors
+
+
+# Ported with modifications from xarray
+# https://github.com/pydata/xarray/blob/master/xarray/core/extensions.py
+# 1. We don't need to catch and re-raise AttributeErrors as RuntimeErrors
+# 2. We use a UserWarning instead of a custom Warning
+
+
+class CachedAccessor:
+    """
+    Custom property-like object.
+
+    A descriptor for caching accessors.
+
+    Parameters
+    ----------
+    name : str
+        Namespace that will be accessed under, e.g. ``df.foo``.
+    accessor : cls
+        Class with the extension methods.
+
+    Notes
+    -----
+    For accessor, The class's __init__ method assumes that one of
+    ``Series``, ``DataFrame`` or ``Index`` as the
+    single argument ``data``.
+    """
+
+    def __init__(self, name: str, accessor) -> None:
+        self._name = name
+        self._accessor = accessor
+
+    def __get__(self, obj, cls):
+        if obj is None:
+            # we're accessing the attribute of the class, i.e., Dataset.geo
+            return self._accessor
+        accessor_obj = self._accessor(obj)
+        # Replace the property with the accessor object. Inspired by:
+        # https://www.pydanny.com/cached-property.html
+        # We need to use object.__setattr__ because we overwrite __setattr__ on
+        # NDFrame
+        object.__setattr__(obj, self._name, accessor_obj)
+        return accessor_obj
+
+
+@doc(klass="", others="")
+def _register_accessor(name: str, cls):
+    """
+    Register a custom accessor on {klass} objects.
+
+    Parameters
+    ----------
+    name : str
+        Name under which the accessor should be registered. A warning is issued
+        if this name conflicts with a preexisting attribute.
+
+    Returns
+    -------
+    callable
+        A class decorator.
+
+    See Also
+    --------
+    register_dataframe_accessor : Register a custom accessor on DataFrame objects.
+    register_series_accessor : Register a custom accessor on Series objects.
+    register_index_accessor : Register a custom accessor on Index objects.
+
+    Notes
+    -----
+    When accessed, your accessor will be initialized with the pandas object
+    the user is interacting with. So the signature must be
+
+    .. code-block:: python
+
+        def __init__(self, pandas_object):  # noqa: E999
+            ...
+
+    For consistency with pandas methods, you should raise an ``AttributeError``
+    if the data passed to your accessor has an incorrect dtype.
+
+    >>> pd.Series(['a', 'b']).dt
+    Traceback (most recent call last):
+    ...
+    AttributeError: Can only use .dt accessor with datetimelike values
+
+    Examples
+    --------
+    In your library code::
+
+        import pandas as pd
+
+        @pd.api.extensions.register_dataframe_accessor("geo")
+        class GeoAccessor:
+            def __init__(self, pandas_obj):
+                self._obj = pandas_obj
+
+            @property
+            def center(self):
+                # return the geographic center point of this DataFrame
+                lat = self._obj.latitude
+                lon = self._obj.longitude
+                return (float(lon.mean()), float(lat.mean()))
+
+            def plot(self):
+                # plot this array's data on a map, e.g., using Cartopy
+                pass
+
+    Back in an interactive IPython session:
+
+        .. code-block:: ipython
+
+            In [1]: ds = pd.DataFrame({{"longitude": np.linspace(0, 10),
+               ...:                    "latitude": np.linspace(0, 20)}})
+            In [2]: ds.geo.center
+            Out[2]: (5.0, 10.0)
+            In [3]: ds.geo.plot()  # plots data on a map
+    """
+
+    def decorator(accessor):
+        if hasattr(cls, name):
+            warnings.warn(
+                f"registration of accessor {repr(accessor)} under name "
+                f"{repr(name)} for type {repr(cls)} is overriding a preexisting "
+                f"attribute with the same name.",
+                UserWarning,
+                stacklevel=find_stack_level(),
+            )
+        setattr(cls, name, CachedAccessor(name, accessor))
+        cls._accessors.add(name)
+        return accessor
+
+    return decorator
+
+
+@doc(_register_accessor, klass="DataFrame")
+def register_dataframe_accessor(name: str):
+    from pandas import DataFrame
+
+    return _register_accessor(name, DataFrame)
+
+
+@doc(_register_accessor, klass="Series")
+def register_series_accessor(name: str):
+    from pandas import Series
+
+    return _register_accessor(name, Series)
+
+
+@doc(_register_accessor, klass="Index")
+def register_index_accessor(name: str):
+    from pandas import Index
+
+    return _register_accessor(name, Index)

AppDir/usr/lib/python3.12/site-packages/pandas/core/api.py

@@ -0,0 +1,140 @@
+from pandas._libs import (
+    NaT,
+    Period,
+    Timedelta,
+    Timestamp,
+)
+from pandas._libs.missing import NA
+
+from pandas.core.dtypes.dtypes import (
+    ArrowDtype,
+    CategoricalDtype,
+    DatetimeTZDtype,
+    IntervalDtype,
+    PeriodDtype,
+)
+from pandas.core.dtypes.missing import (
+    isna,
+    isnull,
+    notna,
+    notnull,
+)
+
+from pandas.core.algorithms import (
+    factorize,
+    unique,
+    value_counts,
+)
+from pandas.core.arrays import Categorical
+from pandas.core.arrays.boolean import BooleanDtype
+from pandas.core.arrays.floating import (
+    Float32Dtype,
+    Float64Dtype,
+)
+from pandas.core.arrays.integer import (
+    Int8Dtype,
+    Int16Dtype,
+    Int32Dtype,
+    Int64Dtype,
+    UInt8Dtype,
+    UInt16Dtype,
+    UInt32Dtype,
+    UInt64Dtype,
+)
+from pandas.core.arrays.string_ import StringDtype
+from pandas.core.construction import array
+from pandas.core.flags import Flags
+from pandas.core.groupby import (
+    Grouper,
+    NamedAgg,
+)
+from pandas.core.indexes.api import (
+    CategoricalIndex,
+    DatetimeIndex,
+    Index,
+    IntervalIndex,
+    MultiIndex,
+    PeriodIndex,
+    RangeIndex,
+    TimedeltaIndex,
+)
+from pandas.core.indexes.datetimes import (
+    bdate_range,
+    date_range,
+)
+from pandas.core.indexes.interval import (
+    Interval,
+    interval_range,
+)
+from pandas.core.indexes.period import period_range
+from pandas.core.indexes.timedeltas import timedelta_range
+from pandas.core.indexing import IndexSlice
+from pandas.core.series import Series
+from pandas.core.tools.datetimes import to_datetime
+from pandas.core.tools.numeric import to_numeric
+from pandas.core.tools.timedeltas import to_timedelta
+
+from pandas.io.formats.format import set_eng_float_format
+from pandas.tseries.offsets import DateOffset
+
+# DataFrame needs to be imported after NamedAgg to avoid a circular import
+from pandas.core.frame import DataFrame  # isort:skip
+
+__all__ = [
+    "array",
+    "ArrowDtype",
+    "bdate_range",
+    "BooleanDtype",
+    "Categorical",
+    "CategoricalDtype",
+    "CategoricalIndex",
+    "DataFrame",
+    "DateOffset",
+    "date_range",
+    "DatetimeIndex",
+    "DatetimeTZDtype",
+    "factorize",
+    "Flags",
+    "Float32Dtype",
+    "Float64Dtype",
+    "Grouper",
+    "Index",
+    "IndexSlice",
+    "Int16Dtype",
+    "Int32Dtype",
+    "Int64Dtype",
+    "Int8Dtype",
+    "Interval",
+    "IntervalDtype",
+    "IntervalIndex",
+    "interval_range",
+    "isna",
+    "isnull",
+    "MultiIndex",
+    "NA",
+    "NamedAgg",
+    "NaT",
+    "notna",
+    "notnull",
+    "Period",
+    "PeriodDtype",
+    "PeriodIndex",
+    "period_range",
+    "RangeIndex",
+    "Series",
+    "set_eng_float_format",
+    "StringDtype",
+    "Timedelta",
+    "TimedeltaIndex",
+    "timedelta_range",
+    "Timestamp",
+    "to_datetime",
+    "to_numeric",
+    "to_timedelta",
+    "UInt16Dtype",
+    "UInt32Dtype",
+    "UInt64Dtype",
+    "UInt8Dtype",
+    "unique",
+    "value_counts",
+]

AppDir/usr/lib/python3.12/site-packages/pandas/core/array_algos/__init__.py

@@ -0,0 +1,9 @@
+"""
+core.array_algos is for algorithms that operate on ndarray and ExtensionArray.
+These should:
+
+- Assume that any Index, Series, or DataFrame objects have already been unwrapped.
+- Assume that any list arguments have already been cast to ndarray/EA.
+- Not depend on Index, Series, or DataFrame, nor import any of these.
+- May dispatch to ExtensionArray methods, but should not import from core.arrays.
+"""

AppDir/usr/lib/python3.12/site-packages/pandas/core/array_algos/datetimelike_accumulations.py

@@ -0,0 +1,67 @@
+"""
+datetimelke_accumulations.py is for accumulations of datetimelike extension arrays
+"""
+
+from __future__ import annotations
+
+from typing import Callable
+
+import numpy as np
+
+from pandas._libs import iNaT
+
+from pandas.core.dtypes.missing import isna
+
+
+def _cum_func(
+    func: Callable,
+    values: np.ndarray,
+    *,
+    skipna: bool = True,
+):
+    """
+    Accumulations for 1D datetimelike arrays.
+
+    Parameters
+    ----------
+    func : np.cumsum, np.maximum.accumulate, np.minimum.accumulate
+    values : np.ndarray
+        Numpy array with the values (can be of any dtype that support the
+        operation). Values is changed is modified inplace.
+    skipna : bool, default True
+        Whether to skip NA.
+    """
+    try:
+        fill_value = {
+            np.maximum.accumulate: np.iinfo(np.int64).min,
+            np.cumsum: 0,
+            np.minimum.accumulate: np.iinfo(np.int64).max,
+        }[func]
+    except KeyError:
+        raise ValueError(f"No accumulation for {func} implemented on BaseMaskedArray")
+
+    mask = isna(values)
+    y = values.view("i8")
+    y[mask] = fill_value
+
+    if not skipna:
+        mask = np.maximum.accumulate(mask)
+
+    result = func(y)
+    result[mask] = iNaT
+
+    if values.dtype.kind in "mM":
+        return result.view(values.dtype.base)
+    return result
+
+
+def cumsum(values: np.ndarray, *, skipna: bool = True) -> np.ndarray:
+    return _cum_func(np.cumsum, values, skipna=skipna)
+
+
+def cummin(values: np.ndarray, *, skipna: bool = True):
+    return _cum_func(np.minimum.accumulate, values, skipna=skipna)
+
+
+def cummax(values: np.ndarray, *, skipna: bool = True):
+    return _cum_func(np.maximum.accumulate, values, skipna=skipna)

AppDir/usr/lib/python3.12/site-packages/pandas/core/array_algos/masked_accumulations.py

@@ -0,0 +1,90 @@
+"""
+masked_accumulations.py is for accumulation algorithms using a mask-based approach
+for missing values.
+"""
+
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Callable,
+)
+
+import numpy as np
+
+if TYPE_CHECKING:
+    from pandas._typing import npt
+
+
+def _cum_func(
+    func: Callable,
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+):
+    """
+    Accumulations for 1D masked array.
+
+    We will modify values in place to replace NAs with the appropriate fill value.
+
+    Parameters
+    ----------
+    func : np.cumsum, np.cumprod, np.maximum.accumulate, np.minimum.accumulate
+    values : np.ndarray
+        Numpy array with the values (can be of any dtype that support the
+        operation).
+    mask : np.ndarray
+        Boolean numpy array (True values indicate missing values).
+    skipna : bool, default True
+        Whether to skip NA.
+    """
+    dtype_info: np.iinfo | np.finfo
+    if values.dtype.kind == "f":
+        dtype_info = np.finfo(values.dtype.type)
+    elif values.dtype.kind in "iu":
+        dtype_info = np.iinfo(values.dtype.type)
+    elif values.dtype.kind == "b":
+        # Max value of bool is 1, but since we are setting into a boolean
+        # array, 255 is fine as well. Min value has to be 0 when setting
+        # into the boolean array.
+        dtype_info = np.iinfo(np.uint8)
+    else:
+        raise NotImplementedError(
+            f"No masked accumulation defined for dtype {values.dtype.type}"
+        )
+    try:
+        fill_value = {
+            np.cumprod: 1,
+            np.maximum.accumulate: dtype_info.min,
+            np.cumsum: 0,
+            np.minimum.accumulate: dtype_info.max,
+        }[func]
+    except KeyError:
+        raise NotImplementedError(
+            f"No accumulation for {func} implemented on BaseMaskedArray"
+        )
+
+    values[mask] = fill_value
+
+    if not skipna:
+        mask = np.maximum.accumulate(mask)
+
+    values = func(values)
+    return values, mask
+
+
+def cumsum(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+    return _cum_func(np.cumsum, values, mask, skipna=skipna)
+
+
+def cumprod(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+    return _cum_func(np.cumprod, values, mask, skipna=skipna)
+
+
+def cummin(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+    return _cum_func(np.minimum.accumulate, values, mask, skipna=skipna)
+
+
+def cummax(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+    return _cum_func(np.maximum.accumulate, values, mask, skipna=skipna)

AppDir/usr/lib/python3.12/site-packages/pandas/core/array_algos/masked_reductions.py

@@ -0,0 +1,197 @@
+"""
+masked_reductions.py is for reduction algorithms using a mask-based approach
+for missing values.
+"""
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Callable,
+)
+import warnings
+
+import numpy as np
+
+from pandas._libs import missing as libmissing
+
+from pandas.core.nanops import check_below_min_count
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        AxisInt,
+        npt,
+    )
+
+
+def _reductions(
+    func: Callable,
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    min_count: int = 0,
+    axis: AxisInt | None = None,
+    **kwargs,
+):
+    """
+    Sum, mean or product for 1D masked array.
+
+    Parameters
+    ----------
+    func : np.sum or np.prod
+    values : np.ndarray
+        Numpy array with the values (can be of any dtype that support the
+        operation).
+    mask : np.ndarray[bool]
+        Boolean numpy array (True values indicate missing values).
+    skipna : bool, default True
+        Whether to skip NA.
+    min_count : int, default 0
+        The required number of valid values to perform the operation. If fewer than
+        ``min_count`` non-NA values are present the result will be NA.
+    axis : int, optional, default None
+    """
+    if not skipna:
+        if mask.any() or check_below_min_count(values.shape, None, min_count):
+            return libmissing.NA
+        else:
+            return func(values, axis=axis, **kwargs)
+    else:
+        if check_below_min_count(values.shape, mask, min_count) and (
+            axis is None or values.ndim == 1
+        ):
+            return libmissing.NA
+
+        return func(values, where=~mask, axis=axis, **kwargs)
+
+
+def sum(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    min_count: int = 0,
+    axis: AxisInt | None = None,
+):
+    return _reductions(
+        np.sum, values=values, mask=mask, skipna=skipna, min_count=min_count, axis=axis
+    )
+
+
+def prod(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    min_count: int = 0,
+    axis: AxisInt | None = None,
+):
+    return _reductions(
+        np.prod, values=values, mask=mask, skipna=skipna, min_count=min_count, axis=axis
+    )
+
+
+def _minmax(
+    func: Callable,
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+):
+    """
+    Reduction for 1D masked array.
+
+    Parameters
+    ----------
+    func : np.min or np.max
+    values : np.ndarray
+        Numpy array with the values (can be of any dtype that support the
+        operation).
+    mask : np.ndarray[bool]
+        Boolean numpy array (True values indicate missing values).
+    skipna : bool, default True
+        Whether to skip NA.
+    axis : int, optional, default None
+    """
+    if not skipna:
+        if mask.any() or not values.size:
+            # min/max with empty array raise in numpy, pandas returns NA
+            return libmissing.NA
+        else:
+            return func(values, axis=axis)
+    else:
+        subset = values[~mask]
+        if subset.size:
+            return func(subset, axis=axis)
+        else:
+            # min/max with empty array raise in numpy, pandas returns NA
+            return libmissing.NA
+
+
+def min(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+):
+    return _minmax(np.min, values=values, mask=mask, skipna=skipna, axis=axis)
+
+
+def max(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+):
+    return _minmax(np.max, values=values, mask=mask, skipna=skipna, axis=axis)
+
+
+def mean(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+):
+    if not values.size or mask.all():
+        return libmissing.NA
+    return _reductions(np.mean, values=values, mask=mask, skipna=skipna, axis=axis)
+
+
+def var(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+    ddof: int = 1,
+):
+    if not values.size or mask.all():
+        return libmissing.NA
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", RuntimeWarning)
+        return _reductions(
+            np.var, values=values, mask=mask, skipna=skipna, axis=axis, ddof=ddof
+        )
+
+
+def std(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+    ddof: int = 1,
+):
+    if not values.size or mask.all():
+        return libmissing.NA
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", RuntimeWarning)
+        return _reductions(
+            np.std, values=values, mask=mask, skipna=skipna, axis=axis, ddof=ddof
+        )

AppDir/usr/lib/python3.12/site-packages/pandas/core/array_algos/putmask.py

@@ -0,0 +1,149 @@
+"""
+EA-compatible analogue to np.putmask
+"""
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+
+import numpy as np
+
+from pandas._libs import lib
+
+from pandas.core.dtypes.cast import infer_dtype_from
+from pandas.core.dtypes.common import is_list_like
+
+from pandas.core.arrays import ExtensionArray
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        ArrayLike,
+        npt,
+    )
+
+    from pandas import MultiIndex
+
+
+def putmask_inplace(values: ArrayLike, mask: npt.NDArray[np.bool_], value: Any) -> None:
+    """
+    ExtensionArray-compatible implementation of np.putmask.  The main
+    difference is we do not handle repeating or truncating like numpy.
+
+    Parameters
+    ----------
+    values: np.ndarray or ExtensionArray
+    mask : np.ndarray[bool]
+        We assume extract_bool_array has already been called.
+    value : Any
+    """
+
+    if (
+        not isinstance(values, np.ndarray)
+        or (values.dtype == object and not lib.is_scalar(value))
+        # GH#43424: np.putmask raises TypeError if we cannot cast between types with
+        # rule = "safe", a stricter guarantee we may not have here
+        or (
+            isinstance(value, np.ndarray) and not np.can_cast(value.dtype, values.dtype)
+        )
+    ):
+        # GH#19266 using np.putmask gives unexpected results with listlike value
+        #  along with object dtype
+        if is_list_like(value) and len(value) == len(values):
+            values[mask] = value[mask]
+        else:
+            values[mask] = value
+    else:
+        # GH#37833 np.putmask is more performant than __setitem__
+        np.putmask(values, mask, value)
+
+
+def putmask_without_repeat(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], new: Any
+) -> None:
+    """
+    np.putmask will truncate or repeat if `new` is a listlike with
+    len(new) != len(values).  We require an exact match.
+
+    Parameters
+    ----------
+    values : np.ndarray
+    mask : np.ndarray[bool]
+    new : Any
+    """
+    if getattr(new, "ndim", 0) >= 1:
+        new = new.astype(values.dtype, copy=False)
+
+    # TODO: this prob needs some better checking for 2D cases
+    nlocs = mask.sum()
+    if nlocs > 0 and is_list_like(new) and getattr(new, "ndim", 1) == 1:
+        shape = np.shape(new)
+        # np.shape compat for if setitem_datetimelike_compat
+        #  changed arraylike to list e.g. test_where_dt64_2d
+        if nlocs == shape[-1]:
+            # GH#30567
+            # If length of ``new`` is less than the length of ``values``,
+            # `np.putmask` would first repeat the ``new`` array and then
+            # assign the masked values hence produces incorrect result.
+            # `np.place` on the other hand uses the ``new`` values at it is
+            # to place in the masked locations of ``values``
+            np.place(values, mask, new)
+            # i.e. values[mask] = new
+        elif mask.shape[-1] == shape[-1] or shape[-1] == 1:
+            np.putmask(values, mask, new)
+        else:
+            raise ValueError("cannot assign mismatch length to masked array")
+    else:
+        np.putmask(values, mask, new)
+
+
+def validate_putmask(
+    values: ArrayLike | MultiIndex, mask: np.ndarray
+) -> tuple[npt.NDArray[np.bool_], bool]:
+    """
+    Validate mask and check if this putmask operation is a no-op.
+    """
+    mask = extract_bool_array(mask)
+    if mask.shape != values.shape:
+        raise ValueError("putmask: mask and data must be the same size")
+
+    noop = not mask.any()
+    return mask, noop
+
+
+def extract_bool_array(mask: ArrayLike) -> npt.NDArray[np.bool_]:
+    """
+    If we have a SparseArray or BooleanArray, convert it to ndarray[bool].
+    """
+    if isinstance(mask, ExtensionArray):
+        # We could have BooleanArray, Sparse[bool], ...
+        #  Except for BooleanArray, this is equivalent to just
+        #  np.asarray(mask, dtype=bool)
+        mask = mask.to_numpy(dtype=bool, na_value=False)
+
+    mask = np.asarray(mask, dtype=bool)
+    return mask
+
+
+def setitem_datetimelike_compat(values: np.ndarray, num_set: int, other):
+    """
+    Parameters
+    ----------
+    values : np.ndarray
+    num_set : int
+        For putmask, this is mask.sum()
+    other : Any
+    """
+    if values.dtype == object:
+        dtype, _ = infer_dtype_from(other)
+
+        if lib.is_np_dtype(dtype, "mM"):
+            # https://github.com/numpy/numpy/issues/12550
+            #  timedelta64 will incorrectly cast to int
+            if not is_list_like(other):
+                other = [other] * num_set
+            else:
+                other = list(other)
+
+    return other

AppDir/usr/lib/python3.12/site-packages/pandas/core/array_algos/quantile.py

@@ -0,0 +1,226 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+from pandas.core.dtypes.missing import (
+    isna,
+    na_value_for_dtype,
+)
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        ArrayLike,
+        Scalar,
+        npt,
+    )
+
+
+def quantile_compat(
+    values: ArrayLike, qs: npt.NDArray[np.float64], interpolation: str
+) -> ArrayLike:
+    """
+    Compute the quantiles of the given values for each quantile in `qs`.
+
+    Parameters
+    ----------
+    values : np.ndarray or ExtensionArray
+    qs : np.ndarray[float64]
+    interpolation : str
+
+    Returns
+    -------
+    np.ndarray or ExtensionArray
+    """
+    if isinstance(values, np.ndarray):
+        fill_value = na_value_for_dtype(values.dtype, compat=False)
+        mask = isna(values)
+        return quantile_with_mask(values, mask, fill_value, qs, interpolation)
+    else:
+        return values._quantile(qs, interpolation)
+
+
+def quantile_with_mask(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    fill_value,
+    qs: npt.NDArray[np.float64],
+    interpolation: str,
+) -> np.ndarray:
+    """
+    Compute the quantiles of the given values for each quantile in `qs`.
+
+    Parameters
+    ----------
+    values : np.ndarray
+        For ExtensionArray, this is _values_for_factorize()[0]
+    mask : np.ndarray[bool]
+        mask = isna(values)
+        For ExtensionArray, this is computed before calling _value_for_factorize
+    fill_value : Scalar
+        The value to interpret fill NA entries with
+        For ExtensionArray, this is _values_for_factorize()[1]
+    qs : np.ndarray[float64]
+    interpolation : str
+        Type of interpolation
+
+    Returns
+    -------
+    np.ndarray
+
+    Notes
+    -----
+    Assumes values is already 2D.  For ExtensionArray this means np.atleast_2d
+    has been called on _values_for_factorize()[0]
+
+    Quantile is computed along axis=1.
+    """
+    assert values.shape == mask.shape
+    if values.ndim == 1:
+        # unsqueeze, operate, re-squeeze
+        values = np.atleast_2d(values)
+        mask = np.atleast_2d(mask)
+        res_values = quantile_with_mask(values, mask, fill_value, qs, interpolation)
+        return res_values[0]
+
+    assert values.ndim == 2
+
+    is_empty = values.shape[1] == 0
+
+    if is_empty:
+        # create the array of na_values
+        # 2d len(values) * len(qs)
+        flat = np.array([fill_value] * len(qs))
+        result = np.repeat(flat, len(values)).reshape(len(values), len(qs))
+    else:
+        result = _nanpercentile(
+            values,
+            qs * 100.0,
+            na_value=fill_value,
+            mask=mask,
+            interpolation=interpolation,
+        )
+
+        result = np.array(result, copy=False)
+        result = result.T
+
+    return result
+
+
+def _nanpercentile_1d(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    qs: npt.NDArray[np.float64],
+    na_value: Scalar,
+    interpolation: str,
+) -> Scalar | np.ndarray:
+    """
+    Wrapper for np.percentile that skips missing values, specialized to
+    1-dimensional case.
+
+    Parameters
+    ----------
+    values : array over which to find quantiles
+    mask : ndarray[bool]
+        locations in values that should be considered missing
+    qs : np.ndarray[float64] of quantile indices to find
+    na_value : scalar
+        value to return for empty or all-null values
+    interpolation : str
+
+    Returns
+    -------
+    quantiles : scalar or array
+    """
+    # mask is Union[ExtensionArray, ndarray]
+    values = values[~mask]
+
+    if len(values) == 0:
+        # Can't pass dtype=values.dtype here bc we might have na_value=np.nan
+        #  with values.dtype=int64 see test_quantile_empty
+        # equiv: 'np.array([na_value] * len(qs))' but much faster
+        return np.full(len(qs), na_value)
+
+    return np.percentile(
+        values,
+        qs,
+        # error: No overload variant of "percentile" matches argument
+        # types "ndarray[Any, Any]", "ndarray[Any, dtype[floating[_64Bit]]]"
+        # , "Dict[str, str]"  [call-overload]
+        method=interpolation,  # type: ignore[call-overload]
+    )
+
+
+def _nanpercentile(
+    values: np.ndarray,
+    qs: npt.NDArray[np.float64],
+    *,
+    na_value,
+    mask: npt.NDArray[np.bool_],
+    interpolation: str,
+):
+    """
+    Wrapper for np.percentile that skips missing values.
+
+    Parameters
+    ----------
+    values : np.ndarray[ndim=2]  over which to find quantiles
+    qs : np.ndarray[float64] of quantile indices to find
+    na_value : scalar
+        value to return for empty or all-null values
+    mask : np.ndarray[bool]
+        locations in values that should be considered missing
+    interpolation : str
+
+    Returns
+    -------
+    quantiles : scalar or array
+    """
+
+    if values.dtype.kind in "mM":
+        # need to cast to integer to avoid rounding errors in numpy
+        result = _nanpercentile(
+            values.view("i8"),
+            qs=qs,
+            na_value=na_value.view("i8"),
+            mask=mask,
+            interpolation=interpolation,
+        )
+
+        # Note: we have to do `astype` and not view because in general we
+        #  have float result at this point, not i8
+        return result.astype(values.dtype)
+
+    if mask.any():
+        # Caller is responsible for ensuring mask shape match
+        assert mask.shape == values.shape
+        result = [
+            _nanpercentile_1d(val, m, qs, na_value, interpolation=interpolation)
+            for (val, m) in zip(list(values), list(mask))
+        ]
+        if values.dtype.kind == "f":
+            # preserve itemsize
+            result = np.array(result, dtype=values.dtype, copy=False).T
+        else:
+            result = np.array(result, copy=False).T
+            if (
+                result.dtype != values.dtype
+                and not mask.all()
+                and (result == result.astype(values.dtype, copy=False)).all()
+            ):
+                # mask.all() will never get cast back to int
+                # e.g. values id integer dtype and result is floating dtype,
+                #  only cast back to integer dtype if result values are all-integer.
+                result = result.astype(values.dtype, copy=False)
+        return result
+    else:
+        return np.percentile(
+            values,
+            qs,
+            axis=1,
+            # error: No overload variant of "percentile" matches argument types
+            # "ndarray[Any, Any]", "ndarray[Any, dtype[floating[_64Bit]]]",
+            # "int", "Dict[str, str]"  [call-overload]
+            method=interpolation,  # type: ignore[call-overload]
+        )

AppDir/usr/lib/python3.12/site-packages/pandas/core/array_algos/replace.py

@@ -0,0 +1,152 @@
+"""
+Methods used by Block.replace and related methods.
+"""
+from __future__ import annotations
+
+import operator
+import re
+from re import Pattern
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+
+import numpy as np
+
+from pandas.core.dtypes.common import (
+    is_bool,
+    is_re,
+    is_re_compilable,
+)
+from pandas.core.dtypes.missing import isna
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        ArrayLike,
+        Scalar,
+        npt,
+    )
+
+
+def should_use_regex(regex: bool, to_replace: Any) -> bool:
+    """
+    Decide whether to treat `to_replace` as a regular expression.
+    """
+    if is_re(to_replace):
+        regex = True
+
+    regex = regex and is_re_compilable(to_replace)
+
+    # Don't use regex if the pattern is empty.
+    regex = regex and re.compile(to_replace).pattern != ""
+    return regex
+
+
+def compare_or_regex_search(
+    a: ArrayLike, b: Scalar | Pattern, regex: bool, mask: npt.NDArray[np.bool_]
+) -> ArrayLike:
+    """
+    Compare two array-like inputs of the same shape or two scalar values
+
+    Calls operator.eq or re.search, depending on regex argument. If regex is
+    True, perform an element-wise regex matching.
+
+    Parameters
+    ----------
+    a : array-like
+    b : scalar or regex pattern
+    regex : bool
+    mask : np.ndarray[bool]
+
+    Returns
+    -------
+    mask : array-like of bool
+    """
+    if isna(b):
+        return ~mask
+
+    def _check_comparison_types(
+        result: ArrayLike | bool, a: ArrayLike, b: Scalar | Pattern
+    ):
+        """
+        Raises an error if the two arrays (a,b) cannot be compared.
+        Otherwise, returns the comparison result as expected.
+        """
+        if is_bool(result) and isinstance(a, np.ndarray):
+            type_names = [type(a).__name__, type(b).__name__]
+
+            type_names[0] = f"ndarray(dtype={a.dtype})"
+
+            raise TypeError(
+                f"Cannot compare types {repr(type_names[0])} and {repr(type_names[1])}"
+            )
+
+    if not regex or not should_use_regex(regex, b):
+        # TODO: should use missing.mask_missing?
+        op = lambda x: operator.eq(x, b)
+    else:
+        op = np.vectorize(
+            lambda x: bool(re.search(b, x))
+            if isinstance(x, str) and isinstance(b, (str, Pattern))
+            else False
+        )
+
+    # GH#32621 use mask to avoid comparing to NAs
+    if isinstance(a, np.ndarray):
+        a = a[mask]
+
+    result = op(a)
+
+    if isinstance(result, np.ndarray) and mask is not None:
+        # The shape of the mask can differ to that of the result
+        # since we may compare only a subset of a's or b's elements
+        tmp = np.zeros(mask.shape, dtype=np.bool_)
+        np.place(tmp, mask, result)
+        result = tmp
+
+    _check_comparison_types(result, a, b)
+    return result
+
+
+def replace_regex(
+    values: ArrayLike, rx: re.Pattern, value, mask: npt.NDArray[np.bool_] | None
+) -> None:
+    """
+    Parameters
+    ----------
+    values : ArrayLike
+        Object dtype.
+    rx : re.Pattern
+    value : Any
+    mask : np.ndarray[bool], optional
+
+    Notes
+    -----
+    Alters values in-place.
+    """
+
+    # deal with replacing values with objects (strings) that match but
+    # whose replacement is not a string (numeric, nan, object)
+    if isna(value) or not isinstance(value, str):
+
+        def re_replacer(s):
+            if is_re(rx) and isinstance(s, str):
+                return value if rx.search(s) is not None else s
+            else:
+                return s
+
+    else:
+        # value is guaranteed to be a string here, s can be either a string
+        # or null if it's null it gets returned
+        def re_replacer(s):
+            if is_re(rx) and isinstance(s, str):
+                return rx.sub(value, s)
+            else:
+                return s
+
+    f = np.vectorize(re_replacer, otypes=[np.object_])
+
+    if mask is None:
+        values[:] = f(values)
+    else:
+        values[mask] = f(values[mask])

AppDir/usr/lib/python3.12/site-packages/pandas/core/array_algos/take.py

@@ -0,0 +1,595 @@
+from __future__ import annotations
+
+import functools
+from typing import (
+    TYPE_CHECKING,
+    cast,
+    overload,
+)
+
+import numpy as np
+
+from pandas._libs import (
+    algos as libalgos,
+    lib,
+)
+
+from pandas.core.dtypes.cast import maybe_promote
+from pandas.core.dtypes.common import (
+    ensure_platform_int,
+    is_1d_only_ea_dtype,
+)
+from pandas.core.dtypes.missing import na_value_for_dtype
+
+from pandas.core.construction import ensure_wrapped_if_datetimelike
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        ArrayLike,
+        AxisInt,
+        npt,
+    )
+
+    from pandas.core.arrays._mixins import NDArrayBackedExtensionArray
+    from pandas.core.arrays.base import ExtensionArray
+
+
+@overload
+def take_nd(
+    arr: np.ndarray,
+    indexer,
+    axis: AxisInt = ...,
+    fill_value=...,
+    allow_fill: bool = ...,
+) -> np.ndarray:
+    ...
+
+
+@overload
+def take_nd(
+    arr: ExtensionArray,
+    indexer,
+    axis: AxisInt = ...,
+    fill_value=...,
+    allow_fill: bool = ...,
+) -> ArrayLike:
+    ...
+
+
+def take_nd(
+    arr: ArrayLike,
+    indexer,
+    axis: AxisInt = 0,
+    fill_value=lib.no_default,
+    allow_fill: bool = True,
+) -> ArrayLike:
+    """
+    Specialized Cython take which sets NaN values in one pass
+
+    This dispatches to ``take`` defined on ExtensionArrays. It does not
+    currently dispatch to ``SparseArray.take`` for sparse ``arr``.
+
+    Note: this function assumes that the indexer is a valid(ated) indexer with
+    no out of bound indices.
+
+    Parameters
+    ----------
+    arr : np.ndarray or ExtensionArray
+        Input array.
+    indexer : ndarray
+        1-D array of indices to take, subarrays corresponding to -1 value
+        indices are filed with fill_value
+    axis : int, default 0
+        Axis to take from
+    fill_value : any, default np.nan
+        Fill value to replace -1 values with
+    allow_fill : bool, default True
+        If False, indexer is assumed to contain no -1 values so no filling
+        will be done.  This short-circuits computation of a mask.  Result is
+        undefined if allow_fill == False and -1 is present in indexer.
+
+    Returns
+    -------
+    subarray : np.ndarray or ExtensionArray
+        May be the same type as the input, or cast to an ndarray.
+    """
+    if fill_value is lib.no_default:
+        fill_value = na_value_for_dtype(arr.dtype, compat=False)
+    elif lib.is_np_dtype(arr.dtype, "mM"):
+        dtype, fill_value = maybe_promote(arr.dtype, fill_value)
+        if arr.dtype != dtype:
+            # EA.take is strict about returning a new object of the same type
+            # so for that case cast upfront
+            arr = arr.astype(dtype)
+
+    if not isinstance(arr, np.ndarray):
+        # i.e. ExtensionArray,
+        # includes for EA to catch DatetimeArray, TimedeltaArray
+        if not is_1d_only_ea_dtype(arr.dtype):
+            # i.e. DatetimeArray, TimedeltaArray
+            arr = cast("NDArrayBackedExtensionArray", arr)
+            return arr.take(
+                indexer, fill_value=fill_value, allow_fill=allow_fill, axis=axis
+            )
+
+        return arr.take(indexer, fill_value=fill_value, allow_fill=allow_fill)
+
+    arr = np.asarray(arr)
+    return _take_nd_ndarray(arr, indexer, axis, fill_value, allow_fill)
+
+
+def _take_nd_ndarray(
+    arr: np.ndarray,
+    indexer: npt.NDArray[np.intp] | None,
+    axis: AxisInt,
+    fill_value,
+    allow_fill: bool,
+) -> np.ndarray:
+    if indexer is None:
+        indexer = np.arange(arr.shape[axis], dtype=np.intp)
+        dtype, fill_value = arr.dtype, arr.dtype.type()
+    else:
+        indexer = ensure_platform_int(indexer)
+
+    dtype, fill_value, mask_info = _take_preprocess_indexer_and_fill_value(
+        arr, indexer, fill_value, allow_fill
+    )
+
+    flip_order = False
+    if arr.ndim == 2 and arr.flags.f_contiguous:
+        flip_order = True
+
+    if flip_order:
+        arr = arr.T
+        axis = arr.ndim - axis - 1
+
+    # at this point, it's guaranteed that dtype can hold both the arr values
+    # and the fill_value
+    out_shape_ = list(arr.shape)
+    out_shape_[axis] = len(indexer)
+    out_shape = tuple(out_shape_)
+    if arr.flags.f_contiguous and axis == arr.ndim - 1:
+        # minor tweak that can make an order-of-magnitude difference
+        # for dataframes initialized directly from 2-d ndarrays
+        # (s.t. df.values is c-contiguous and df._mgr.blocks[0] is its
+        # f-contiguous transpose)
+        out = np.empty(out_shape, dtype=dtype, order="F")
+    else:
+        out = np.empty(out_shape, dtype=dtype)
+
+    func = _get_take_nd_function(
+        arr.ndim, arr.dtype, out.dtype, axis=axis, mask_info=mask_info
+    )
+    func(arr, indexer, out, fill_value)
+
+    if flip_order:
+        out = out.T
+    return out
+
+
+def take_1d(
+    arr: ArrayLike,
+    indexer: npt.NDArray[np.intp],
+    fill_value=None,
+    allow_fill: bool = True,
+    mask: npt.NDArray[np.bool_] | None = None,
+) -> ArrayLike:
+    """
+    Specialized version for 1D arrays. Differences compared to `take_nd`:
+
+    - Assumes input array has already been converted to numpy array / EA
+    - Assumes indexer is already guaranteed to be intp dtype ndarray
+    - Only works for 1D arrays
+
+    To ensure the lowest possible overhead.
+
+    Note: similarly to `take_nd`, this function assumes that the indexer is
+    a valid(ated) indexer with no out of bound indices.
+
+    Parameters
+    ----------
+    arr : np.ndarray or ExtensionArray
+        Input array.
+    indexer : ndarray
+        1-D array of indices to take (validated indices, intp dtype).
+    fill_value : any, default np.nan
+        Fill value to replace -1 values with
+    allow_fill : bool, default True
+        If False, indexer is assumed to contain no -1 values so no filling
+        will be done.  This short-circuits computation of a mask. Result is
+        undefined if allow_fill == False and -1 is present in indexer.
+    mask : np.ndarray, optional, default None
+        If `allow_fill` is True, and the mask (where indexer == -1) is already
+        known, it can be passed to avoid recomputation.
+    """
+    if not isinstance(arr, np.ndarray):
+        # ExtensionArray -> dispatch to their method
+        return arr.take(indexer, fill_value=fill_value, allow_fill=allow_fill)
+
+    if not allow_fill:
+        return arr.take(indexer)
+
+    dtype, fill_value, mask_info = _take_preprocess_indexer_and_fill_value(
+        arr, indexer, fill_value, True, mask
+    )
+
+    # at this point, it's guaranteed that dtype can hold both the arr values
+    # and the fill_value
+    out = np.empty(indexer.shape, dtype=dtype)
+
+    func = _get_take_nd_function(
+        arr.ndim, arr.dtype, out.dtype, axis=0, mask_info=mask_info
+    )
+    func(arr, indexer, out, fill_value)
+
+    return out
+
+
+def take_2d_multi(
+    arr: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    fill_value=np.nan,
+) -> np.ndarray:
+    """
+    Specialized Cython take which sets NaN values in one pass.
+    """
+    # This is only called from one place in DataFrame._reindex_multi,
+    #  so we know indexer is well-behaved.
+    assert indexer is not None
+    assert indexer[0] is not None
+    assert indexer[1] is not None
+
+    row_idx, col_idx = indexer
+
+    row_idx = ensure_platform_int(row_idx)
+    col_idx = ensure_platform_int(col_idx)
+    indexer = row_idx, col_idx
+    mask_info = None
+
+    # check for promotion based on types only (do this first because
+    # it's faster than computing a mask)
+    dtype, fill_value = maybe_promote(arr.dtype, fill_value)
+    if dtype != arr.dtype:
+        # check if promotion is actually required based on indexer
+        row_mask = row_idx == -1
+        col_mask = col_idx == -1
+        row_needs = row_mask.any()
+        col_needs = col_mask.any()
+        mask_info = (row_mask, col_mask), (row_needs, col_needs)
+
+        if not (row_needs or col_needs):
+            # if not, then depromote, set fill_value to dummy
+            # (it won't be used but we don't want the cython code
+            # to crash when trying to cast it to dtype)
+            dtype, fill_value = arr.dtype, arr.dtype.type()
+
+    # at this point, it's guaranteed that dtype can hold both the arr values
+    # and the fill_value
+    out_shape = len(row_idx), len(col_idx)
+    out = np.empty(out_shape, dtype=dtype)
+
+    func = _take_2d_multi_dict.get((arr.dtype.name, out.dtype.name), None)
+    if func is None and arr.dtype != out.dtype:
+        func = _take_2d_multi_dict.get((out.dtype.name, out.dtype.name), None)
+        if func is not None:
+            func = _convert_wrapper(func, out.dtype)
+
+    if func is not None:
+        func(arr, indexer, out=out, fill_value=fill_value)
+    else:
+        # test_reindex_multi
+        _take_2d_multi_object(
+            arr, indexer, out, fill_value=fill_value, mask_info=mask_info
+        )
+
+    return out
+
+
+@functools.lru_cache
+def _get_take_nd_function_cached(
+    ndim: int, arr_dtype: np.dtype, out_dtype: np.dtype, axis: AxisInt
+):
+    """
+    Part of _get_take_nd_function below that doesn't need `mask_info` and thus
+    can be cached (mask_info potentially contains a numpy ndarray which is not
+    hashable and thus cannot be used as argument for cached function).
+    """
+    tup = (arr_dtype.name, out_dtype.name)
+    if ndim == 1:
+        func = _take_1d_dict.get(tup, None)
+    elif ndim == 2:
+        if axis == 0:
+            func = _take_2d_axis0_dict.get(tup, None)
+        else:
+            func = _take_2d_axis1_dict.get(tup, None)
+    if func is not None:
+        return func
+
+    # We get here with string, uint, float16, and complex dtypes that could
+    #  potentially be handled in algos_take_helper.
+    #  Also a couple with (M8[ns], object) and (m8[ns], object)
+    tup = (out_dtype.name, out_dtype.name)
+    if ndim == 1:
+        func = _take_1d_dict.get(tup, None)
+    elif ndim == 2:
+        if axis == 0:
+            func = _take_2d_axis0_dict.get(tup, None)
+        else:
+            func = _take_2d_axis1_dict.get(tup, None)
+    if func is not None:
+        func = _convert_wrapper(func, out_dtype)
+        return func
+
+    return None
+
+
+def _get_take_nd_function(
+    ndim: int,
+    arr_dtype: np.dtype,
+    out_dtype: np.dtype,
+    axis: AxisInt = 0,
+    mask_info=None,
+):
+    """
+    Get the appropriate "take" implementation for the given dimension, axis
+    and dtypes.
+    """
+    func = None
+    if ndim <= 2:
+        # for this part we don't need `mask_info` -> use the cached algo lookup
+        func = _get_take_nd_function_cached(ndim, arr_dtype, out_dtype, axis)
+
+    if func is None:
+
+        def func(arr, indexer, out, fill_value=np.nan) -> None:
+            indexer = ensure_platform_int(indexer)
+            _take_nd_object(
+                arr, indexer, out, axis=axis, fill_value=fill_value, mask_info=mask_info
+            )
+
+    return func
+
+
+def _view_wrapper(f, arr_dtype=None, out_dtype=None, fill_wrap=None):
+    def wrapper(
+        arr: np.ndarray, indexer: np.ndarray, out: np.ndarray, fill_value=np.nan
+    ) -> None:
+        if arr_dtype is not None:
+            arr = arr.view(arr_dtype)
+        if out_dtype is not None:
+            out = out.view(out_dtype)
+        if fill_wrap is not None:
+            # FIXME: if we get here with dt64/td64 we need to be sure we have
+            #  matching resos
+            if fill_value.dtype.kind == "m":
+                fill_value = fill_value.astype("m8[ns]")
+            else:
+                fill_value = fill_value.astype("M8[ns]")
+            fill_value = fill_wrap(fill_value)
+
+        f(arr, indexer, out, fill_value=fill_value)
+
+    return wrapper
+
+
+def _convert_wrapper(f, conv_dtype):
+    def wrapper(
+        arr: np.ndarray, indexer: np.ndarray, out: np.ndarray, fill_value=np.nan
+    ) -> None:
+        if conv_dtype == object:
+            # GH#39755 avoid casting dt64/td64 to integers
+            arr = ensure_wrapped_if_datetimelike(arr)
+        arr = arr.astype(conv_dtype)
+        f(arr, indexer, out, fill_value=fill_value)
+
+    return wrapper
+
+
+_take_1d_dict = {
+    ("int8", "int8"): libalgos.take_1d_int8_int8,
+    ("int8", "int32"): libalgos.take_1d_int8_int32,
+    ("int8", "int64"): libalgos.take_1d_int8_int64,
+    ("int8", "float64"): libalgos.take_1d_int8_float64,
+    ("int16", "int16"): libalgos.take_1d_int16_int16,
+    ("int16", "int32"): libalgos.take_1d_int16_int32,
+    ("int16", "int64"): libalgos.take_1d_int16_int64,
+    ("int16", "float64"): libalgos.take_1d_int16_float64,
+    ("int32", "int32"): libalgos.take_1d_int32_int32,
+    ("int32", "int64"): libalgos.take_1d_int32_int64,
+    ("int32", "float64"): libalgos.take_1d_int32_float64,
+    ("int64", "int64"): libalgos.take_1d_int64_int64,
+    ("int64", "float64"): libalgos.take_1d_int64_float64,
+    ("float32", "float32"): libalgos.take_1d_float32_float32,
+    ("float32", "float64"): libalgos.take_1d_float32_float64,
+    ("float64", "float64"): libalgos.take_1d_float64_float64,
+    ("object", "object"): libalgos.take_1d_object_object,
+    ("bool", "bool"): _view_wrapper(libalgos.take_1d_bool_bool, np.uint8, np.uint8),
+    ("bool", "object"): _view_wrapper(libalgos.take_1d_bool_object, np.uint8, None),
+    ("datetime64[ns]", "datetime64[ns]"): _view_wrapper(
+        libalgos.take_1d_int64_int64, np.int64, np.int64, np.int64
+    ),
+    ("timedelta64[ns]", "timedelta64[ns]"): _view_wrapper(
+        libalgos.take_1d_int64_int64, np.int64, np.int64, np.int64
+    ),
+}
+
+_take_2d_axis0_dict = {
+    ("int8", "int8"): libalgos.take_2d_axis0_int8_int8,
+    ("int8", "int32"): libalgos.take_2d_axis0_int8_int32,
+    ("int8", "int64"): libalgos.take_2d_axis0_int8_int64,
+    ("int8", "float64"): libalgos.take_2d_axis0_int8_float64,
+    ("int16", "int16"): libalgos.take_2d_axis0_int16_int16,
+    ("int16", "int32"): libalgos.take_2d_axis0_int16_int32,
+    ("int16", "int64"): libalgos.take_2d_axis0_int16_int64,
+    ("int16", "float64"): libalgos.take_2d_axis0_int16_float64,
+    ("int32", "int32"): libalgos.take_2d_axis0_int32_int32,
+    ("int32", "int64"): libalgos.take_2d_axis0_int32_int64,
+    ("int32", "float64"): libalgos.take_2d_axis0_int32_float64,
+    ("int64", "int64"): libalgos.take_2d_axis0_int64_int64,
+    ("int64", "float64"): libalgos.take_2d_axis0_int64_float64,
+    ("float32", "float32"): libalgos.take_2d_axis0_float32_float32,
+    ("float32", "float64"): libalgos.take_2d_axis0_float32_float64,
+    ("float64", "float64"): libalgos.take_2d_axis0_float64_float64,
+    ("object", "object"): libalgos.take_2d_axis0_object_object,
+    ("bool", "bool"): _view_wrapper(
+        libalgos.take_2d_axis0_bool_bool, np.uint8, np.uint8
+    ),
+    ("bool", "object"): _view_wrapper(
+        libalgos.take_2d_axis0_bool_object, np.uint8, None
+    ),
+    ("datetime64[ns]", "datetime64[ns]"): _view_wrapper(
+        libalgos.take_2d_axis0_int64_int64, np.int64, np.int64, fill_wrap=np.int64
+    ),
+    ("timedelta64[ns]", "timedelta64[ns]"): _view_wrapper(
+        libalgos.take_2d_axis0_int64_int64, np.int64, np.int64, fill_wrap=np.int64
+    ),
+}
+
+_take_2d_axis1_dict = {
+    ("int8", "int8"): libalgos.take_2d_axis1_int8_int8,
+    ("int8", "int32"): libalgos.take_2d_axis1_int8_int32,
+    ("int8", "int64"): libalgos.take_2d_axis1_int8_int64,
+    ("int8", "float64"): libalgos.take_2d_axis1_int8_float64,
+    ("int16", "int16"): libalgos.take_2d_axis1_int16_int16,
+    ("int16", "int32"): libalgos.take_2d_axis1_int16_int32,
+    ("int16", "int64"): libalgos.take_2d_axis1_int16_int64,
+    ("int16", "float64"): libalgos.take_2d_axis1_int16_float64,
+    ("int32", "int32"): libalgos.take_2d_axis1_int32_int32,
+    ("int32", "int64"): libalgos.take_2d_axis1_int32_int64,
+    ("int32", "float64"): libalgos.take_2d_axis1_int32_float64,
+    ("int64", "int64"): libalgos.take_2d_axis1_int64_int64,
+    ("int64", "float64"): libalgos.take_2d_axis1_int64_float64,
+    ("float32", "float32"): libalgos.take_2d_axis1_float32_float32,
+    ("float32", "float64"): libalgos.take_2d_axis1_float32_float64,
+    ("float64", "float64"): libalgos.take_2d_axis1_float64_float64,
+    ("object", "object"): libalgos.take_2d_axis1_object_object,
+    ("bool", "bool"): _view_wrapper(
+        libalgos.take_2d_axis1_bool_bool, np.uint8, np.uint8
+    ),
+    ("bool", "object"): _view_wrapper(
+        libalgos.take_2d_axis1_bool_object, np.uint8, None
+    ),
+    ("datetime64[ns]", "datetime64[ns]"): _view_wrapper(
+        libalgos.take_2d_axis1_int64_int64, np.int64, np.int64, fill_wrap=np.int64
+    ),
+    ("timedelta64[ns]", "timedelta64[ns]"): _view_wrapper(
+        libalgos.take_2d_axis1_int64_int64, np.int64, np.int64, fill_wrap=np.int64
+    ),
+}
+
+_take_2d_multi_dict = {
+    ("int8", "int8"): libalgos.take_2d_multi_int8_int8,
+    ("int8", "int32"): libalgos.take_2d_multi_int8_int32,
+    ("int8", "int64"): libalgos.take_2d_multi_int8_int64,
+    ("int8", "float64"): libalgos.take_2d_multi_int8_float64,
+    ("int16", "int16"): libalgos.take_2d_multi_int16_int16,
+    ("int16", "int32"): libalgos.take_2d_multi_int16_int32,
+    ("int16", "int64"): libalgos.take_2d_multi_int16_int64,
+    ("int16", "float64"): libalgos.take_2d_multi_int16_float64,
+    ("int32", "int32"): libalgos.take_2d_multi_int32_int32,
+    ("int32", "int64"): libalgos.take_2d_multi_int32_int64,
+    ("int32", "float64"): libalgos.take_2d_multi_int32_float64,
+    ("int64", "int64"): libalgos.take_2d_multi_int64_int64,
+    ("int64", "float64"): libalgos.take_2d_multi_int64_float64,
+    ("float32", "float32"): libalgos.take_2d_multi_float32_float32,
+    ("float32", "float64"): libalgos.take_2d_multi_float32_float64,
+    ("float64", "float64"): libalgos.take_2d_multi_float64_float64,
+    ("object", "object"): libalgos.take_2d_multi_object_object,
+    ("bool", "bool"): _view_wrapper(
+        libalgos.take_2d_multi_bool_bool, np.uint8, np.uint8
+    ),
+    ("bool", "object"): _view_wrapper(
+        libalgos.take_2d_multi_bool_object, np.uint8, None
+    ),
+    ("datetime64[ns]", "datetime64[ns]"): _view_wrapper(
+        libalgos.take_2d_multi_int64_int64, np.int64, np.int64, fill_wrap=np.int64
+    ),
+    ("timedelta64[ns]", "timedelta64[ns]"): _view_wrapper(
+        libalgos.take_2d_multi_int64_int64, np.int64, np.int64, fill_wrap=np.int64
+    ),
+}
+
+
+def _take_nd_object(
+    arr: np.ndarray,
+    indexer: npt.NDArray[np.intp],
+    out: np.ndarray,
+    axis: AxisInt,
+    fill_value,
+    mask_info,
+) -> None:
+    if mask_info is not None:
+        mask, needs_masking = mask_info
+    else:
+        mask = indexer == -1
+        needs_masking = mask.any()
+    if arr.dtype != out.dtype:
+        arr = arr.astype(out.dtype)
+    if arr.shape[axis] > 0:
+        arr.take(indexer, axis=axis, out=out)
+    if needs_masking:
+        outindexer = [slice(None)] * arr.ndim
+        outindexer[axis] = mask
+        out[tuple(outindexer)] = fill_value
+
+
+def _take_2d_multi_object(
+    arr: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value,
+    mask_info,
+) -> None:
+    # this is not ideal, performance-wise, but it's better than raising
+    # an exception (best to optimize in Cython to avoid getting here)
+    row_idx, col_idx = indexer  # both np.intp
+    if mask_info is not None:
+        (row_mask, col_mask), (row_needs, col_needs) = mask_info
+    else:
+        row_mask = row_idx == -1
+        col_mask = col_idx == -1
+        row_needs = row_mask.any()
+        col_needs = col_mask.any()
+    if fill_value is not None:
+        if row_needs:
+            out[row_mask, :] = fill_value
+        if col_needs:
+            out[:, col_mask] = fill_value
+    for i, u_ in enumerate(row_idx):
+        if u_ != -1:
+            for j, v in enumerate(col_idx):
+                if v != -1:
+                    out[i, j] = arr[u_, v]
+
+
+def _take_preprocess_indexer_and_fill_value(
+    arr: np.ndarray,
+    indexer: npt.NDArray[np.intp],
+    fill_value,
+    allow_fill: bool,
+    mask: npt.NDArray[np.bool_] | None = None,
+):
+    mask_info: tuple[np.ndarray | None, bool] | None = None
+
+    if not allow_fill:
+        dtype, fill_value = arr.dtype, arr.dtype.type()
+        mask_info = None, False
+    else:
+        # check for promotion based on types only (do this first because
+        # it's faster than computing a mask)
+        dtype, fill_value = maybe_promote(arr.dtype, fill_value)
+        if dtype != arr.dtype:
+            # check if promotion is actually required based on indexer
+            if mask is not None:
+                needs_masking = True
+            else:
+                mask = indexer == -1
+                needs_masking = bool(mask.any())
+            mask_info = mask, needs_masking
+            if not needs_masking:
+                # if not, then depromote, set fill_value to dummy
+                # (it won't be used but we don't want the cython code
+                # to crash when trying to cast it to dtype)
+                dtype, fill_value = arr.dtype, arr.dtype.type()
+
+    return dtype, fill_value, mask_info

AppDir/usr/lib/python3.12/site-packages/pandas/core/array_algos/transforms.py

@@ -0,0 +1,50 @@
+"""
+transforms.py is for shape-preserving functions.
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        AxisInt,
+        Scalar,
+    )
+
+
+def shift(
+    values: np.ndarray, periods: int, axis: AxisInt, fill_value: Scalar
+) -> np.ndarray:
+    new_values = values
+
+    if periods == 0 or values.size == 0:
+        return new_values.copy()
+
+    # make sure array sent to np.roll is c_contiguous
+    f_ordered = values.flags.f_contiguous
+    if f_ordered:
+        new_values = new_values.T
+        axis = new_values.ndim - axis - 1
+
+    if new_values.size:
+        new_values = np.roll(
+            new_values,
+            np.intp(periods),
+            axis=axis,
+        )
+
+    axis_indexer = [slice(None)] * values.ndim
+    if periods > 0:
+        axis_indexer[axis] = slice(None, periods)
+    else:
+        axis_indexer[axis] = slice(periods, None)
+    new_values[tuple(axis_indexer)] = fill_value
+
+    # restore original order
+    if f_ordered:
+        new_values = new_values.T
+
+    return new_values

AppDir/usr/lib/python3.12/site-packages/pandas/core/arraylike.py

@@ -0,0 +1,527 @@
+"""
+Methods that can be shared by many array-like classes or subclasses:
+    Series
+    Index
+    ExtensionArray
+"""
+from __future__ import annotations
+
+import operator
+from typing import Any
+
+import numpy as np
+
+from pandas._libs import lib
+from pandas._libs.ops_dispatch import maybe_dispatch_ufunc_to_dunder_op
+
+from pandas.core.dtypes.generic import ABCNDFrame
+
+from pandas.core import roperator
+from pandas.core.construction import extract_array
+from pandas.core.ops.common import unpack_zerodim_and_defer
+
+REDUCTION_ALIASES = {
+    "maximum": "max",
+    "minimum": "min",
+    "add": "sum",
+    "multiply": "prod",
+}
+
+
+class OpsMixin:
+    # -------------------------------------------------------------
+    # Comparisons
+
+    def _cmp_method(self, other, op):
+        return NotImplemented
+
+    @unpack_zerodim_and_defer("__eq__")
+    def __eq__(self, other):
+        return self._cmp_method(other, operator.eq)
+
+    @unpack_zerodim_and_defer("__ne__")
+    def __ne__(self, other):
+        return self._cmp_method(other, operator.ne)
+
+    @unpack_zerodim_and_defer("__lt__")
+    def __lt__(self, other):
+        return self._cmp_method(other, operator.lt)
+
+    @unpack_zerodim_and_defer("__le__")
+    def __le__(self, other):
+        return self._cmp_method(other, operator.le)
+
+    @unpack_zerodim_and_defer("__gt__")
+    def __gt__(self, other):
+        return self._cmp_method(other, operator.gt)
+
+    @unpack_zerodim_and_defer("__ge__")
+    def __ge__(self, other):
+        return self._cmp_method(other, operator.ge)
+
+    # -------------------------------------------------------------
+    # Logical Methods
+
+    def _logical_method(self, other, op):
+        return NotImplemented
+
+    @unpack_zerodim_and_defer("__and__")
+    def __and__(self, other):
+        return self._logical_method(other, operator.and_)
+
+    @unpack_zerodim_and_defer("__rand__")
+    def __rand__(self, other):
+        return self._logical_method(other, roperator.rand_)
+
+    @unpack_zerodim_and_defer("__or__")
+    def __or__(self, other):
+        return self._logical_method(other, operator.or_)
+
+    @unpack_zerodim_and_defer("__ror__")
+    def __ror__(self, other):
+        return self._logical_method(other, roperator.ror_)
+
+    @unpack_zerodim_and_defer("__xor__")
+    def __xor__(self, other):
+        return self._logical_method(other, operator.xor)
+
+    @unpack_zerodim_and_defer("__rxor__")
+    def __rxor__(self, other):
+        return self._logical_method(other, roperator.rxor)
+
+    # -------------------------------------------------------------
+    # Arithmetic Methods
+
+    def _arith_method(self, other, op):
+        return NotImplemented
+
+    @unpack_zerodim_and_defer("__add__")
+    def __add__(self, other):
+        """
+        Get Addition of DataFrame and other, column-wise.
+
+        Equivalent to ``DataFrame.add(other)``.
+
+        Parameters
+        ----------
+        other : scalar, sequence, Series, dict or DataFrame
+            Object to be added to the DataFrame.
+
+        Returns
+        -------
+        DataFrame
+            The result of adding ``other`` to DataFrame.
+
+        See Also
+        --------
+        DataFrame.add : Add a DataFrame and another object, with option for index-
+            or column-oriented addition.
+
+        Examples
+        --------
+        >>> df = pd.DataFrame({'height': [1.5, 2.6], 'weight': [500, 800]},
+        ...                   index=['elk', 'moose'])
+        >>> df
+               height  weight
+        elk       1.5     500
+        moose     2.6     800
+
+        Adding a scalar affects all rows and columns.
+
+        >>> df[['height', 'weight']] + 1.5
+               height  weight
+        elk       3.0   501.5
+        moose     4.1   801.5
+
+        Each element of a list is added to a column of the DataFrame, in order.
+
+        >>> df[['height', 'weight']] + [0.5, 1.5]
+               height  weight
+        elk       2.0   501.5
+        moose     3.1   801.5
+
+        Keys of a dictionary are aligned to the DataFrame, based on column names;
+        each value in the dictionary is added to the corresponding column.
+
+        >>> df[['height', 'weight']] + {'height': 0.5, 'weight': 1.5}
+               height  weight
+        elk       2.0   501.5
+        moose     3.1   801.5
+
+        When `other` is a :class:`Series`, the index of `other` is aligned with the
+        columns of the DataFrame.
+
+        >>> s1 = pd.Series([0.5, 1.5], index=['weight', 'height'])
+        >>> df[['height', 'weight']] + s1
+               height  weight
+        elk       3.0   500.5
+        moose     4.1   800.5
+
+        Even when the index of `other` is the same as the index of the DataFrame,
+        the :class:`Series` will not be reoriented. If index-wise alignment is desired,
+        :meth:`DataFrame.add` should be used with `axis='index'`.
+
+        >>> s2 = pd.Series([0.5, 1.5], index=['elk', 'moose'])
+        >>> df[['height', 'weight']] + s2
+               elk  height  moose  weight
+        elk    NaN     NaN    NaN     NaN
+        moose  NaN     NaN    NaN     NaN
+
+        >>> df[['height', 'weight']].add(s2, axis='index')
+               height  weight
+        elk       2.0   500.5
+        moose     4.1   801.5
+
+        When `other` is a :class:`DataFrame`, both columns names and the
+        index are aligned.
+
+        >>> other = pd.DataFrame({'height': [0.2, 0.4, 0.6]},
+        ...                      index=['elk', 'moose', 'deer'])
+        >>> df[['height', 'weight']] + other
+               height  weight
+        deer      NaN     NaN
+        elk       1.7     NaN
+        moose     3.0     NaN
+        """
+        return self._arith_method(other, operator.add)
+
+    @unpack_zerodim_and_defer("__radd__")
+    def __radd__(self, other):
+        return self._arith_method(other, roperator.radd)
+
+    @unpack_zerodim_and_defer("__sub__")
+    def __sub__(self, other):
+        return self._arith_method(other, operator.sub)
+
+    @unpack_zerodim_and_defer("__rsub__")
+    def __rsub__(self, other):
+        return self._arith_method(other, roperator.rsub)
+
+    @unpack_zerodim_and_defer("__mul__")
+    def __mul__(self, other):
+        return self._arith_method(other, operator.mul)
+
+    @unpack_zerodim_and_defer("__rmul__")
+    def __rmul__(self, other):
+        return self._arith_method(other, roperator.rmul)
+
+    @unpack_zerodim_and_defer("__truediv__")
+    def __truediv__(self, other):
+        return self._arith_method(other, operator.truediv)
+
+    @unpack_zerodim_and_defer("__rtruediv__")
+    def __rtruediv__(self, other):
+        return self._arith_method(other, roperator.rtruediv)
+
+    @unpack_zerodim_and_defer("__floordiv__")
+    def __floordiv__(self, other):
+        return self._arith_method(other, operator.floordiv)
+
+    @unpack_zerodim_and_defer("__rfloordiv")
+    def __rfloordiv__(self, other):
+        return self._arith_method(other, roperator.rfloordiv)
+
+    @unpack_zerodim_and_defer("__mod__")
+    def __mod__(self, other):
+        return self._arith_method(other, operator.mod)
+
+    @unpack_zerodim_and_defer("__rmod__")
+    def __rmod__(self, other):
+        return self._arith_method(other, roperator.rmod)
+
+    @unpack_zerodim_and_defer("__divmod__")
+    def __divmod__(self, other):
+        return self._arith_method(other, divmod)
+
+    @unpack_zerodim_and_defer("__rdivmod__")
+    def __rdivmod__(self, other):
+        return self._arith_method(other, roperator.rdivmod)
+
+    @unpack_zerodim_and_defer("__pow__")
+    def __pow__(self, other):
+        return self._arith_method(other, operator.pow)
+
+    @unpack_zerodim_and_defer("__rpow__")
+    def __rpow__(self, other):
+        return self._arith_method(other, roperator.rpow)
+
+
+# -----------------------------------------------------------------------------
+# Helpers to implement __array_ufunc__
+
+
+def array_ufunc(self, ufunc: np.ufunc, method: str, *inputs: Any, **kwargs: Any):
+    """
+    Compatibility with numpy ufuncs.
+
+    See also
+    --------
+    numpy.org/doc/stable/reference/arrays.classes.html#numpy.class.__array_ufunc__
+    """
+    from pandas.core.frame import (
+        DataFrame,
+        Series,
+    )
+    from pandas.core.generic import NDFrame
+    from pandas.core.internals import BlockManager
+
+    cls = type(self)
+
+    kwargs = _standardize_out_kwarg(**kwargs)
+
+    # for binary ops, use our custom dunder methods
+    result = maybe_dispatch_ufunc_to_dunder_op(self, ufunc, method, *inputs, **kwargs)
+    if result is not NotImplemented:
+        return result
+
+    # Determine if we should defer.
+    no_defer = (
+        np.ndarray.__array_ufunc__,
+        cls.__array_ufunc__,
+    )
+
+    for item in inputs:
+        higher_priority = (
+            hasattr(item, "__array_priority__")
+            and item.__array_priority__ > self.__array_priority__
+        )
+        has_array_ufunc = (
+            hasattr(item, "__array_ufunc__")
+            and type(item).__array_ufunc__ not in no_defer
+            and not isinstance(item, self._HANDLED_TYPES)
+        )
+        if higher_priority or has_array_ufunc:
+            return NotImplemented
+
+    # align all the inputs.
+    types = tuple(type(x) for x in inputs)
+    alignable = [x for x, t in zip(inputs, types) if issubclass(t, NDFrame)]
+
+    if len(alignable) > 1:
+        # This triggers alignment.
+        # At the moment, there aren't any ufuncs with more than two inputs
+        # so this ends up just being x1.index | x2.index, but we write
+        # it to handle *args.
+        set_types = set(types)
+        if len(set_types) > 1 and {DataFrame, Series}.issubset(set_types):
+            # We currently don't handle ufunc(DataFrame, Series)
+            # well. Previously this raised an internal ValueError. We might
+            # support it someday, so raise a NotImplementedError.
+            raise NotImplementedError(
+                f"Cannot apply ufunc {ufunc} to mixed DataFrame and Series inputs."
+            )
+        axes = self.axes
+        for obj in alignable[1:]:
+            # this relies on the fact that we aren't handling mixed
+            # series / frame ufuncs.
+            for i, (ax1, ax2) in enumerate(zip(axes, obj.axes)):
+                axes[i] = ax1.union(ax2)
+
+        reconstruct_axes = dict(zip(self._AXIS_ORDERS, axes))
+        inputs = tuple(
+            x.reindex(**reconstruct_axes) if issubclass(t, NDFrame) else x
+            for x, t in zip(inputs, types)
+        )
+    else:
+        reconstruct_axes = dict(zip(self._AXIS_ORDERS, self.axes))
+
+    if self.ndim == 1:
+        names = [getattr(x, "name") for x in inputs if hasattr(x, "name")]
+        name = names[0] if len(set(names)) == 1 else None
+        reconstruct_kwargs = {"name": name}
+    else:
+        reconstruct_kwargs = {}
+
+    def reconstruct(result):
+        if ufunc.nout > 1:
+            # np.modf, np.frexp, np.divmod
+            return tuple(_reconstruct(x) for x in result)
+
+        return _reconstruct(result)
+
+    def _reconstruct(result):
+        if lib.is_scalar(result):
+            return result
+
+        if result.ndim != self.ndim:
+            if method == "outer":
+                raise NotImplementedError
+            return result
+        if isinstance(result, BlockManager):
+            # we went through BlockManager.apply e.g. np.sqrt
+            result = self._constructor_from_mgr(result, axes=result.axes)
+        else:
+            # we converted an array, lost our axes
+            result = self._constructor(
+                result, **reconstruct_axes, **reconstruct_kwargs, copy=False
+            )
+        # TODO: When we support multiple values in __finalize__, this
+        # should pass alignable to `__finalize__` instead of self.
+        # Then `np.add(a, b)` would consider attrs from both a and b
+        # when a and b are NDFrames.
+        if len(alignable) == 1:
+            result = result.__finalize__(self)
+        return result
+
+    if "out" in kwargs:
+        # e.g. test_multiindex_get_loc
+        result = dispatch_ufunc_with_out(self, ufunc, method, *inputs, **kwargs)
+        return reconstruct(result)
+
+    if method == "reduce":
+        # e.g. test.series.test_ufunc.test_reduce
+        result = dispatch_reduction_ufunc(self, ufunc, method, *inputs, **kwargs)
+        if result is not NotImplemented:
+            return result
+
+    # We still get here with kwargs `axis` for e.g. np.maximum.accumulate
+    #  and `dtype` and `keepdims` for np.ptp
+
+    if self.ndim > 1 and (len(inputs) > 1 or ufunc.nout > 1):
+        # Just give up on preserving types in the complex case.
+        # In theory we could preserve them for them.
+        # * nout>1 is doable if BlockManager.apply took nout and
+        #   returned a Tuple[BlockManager].
+        # * len(inputs) > 1 is doable when we know that we have
+        #   aligned blocks / dtypes.
+
+        # e.g. my_ufunc, modf, logaddexp, heaviside, subtract, add
+        inputs = tuple(np.asarray(x) for x in inputs)
+        # Note: we can't use default_array_ufunc here bc reindexing means
+        #  that `self` may not be among `inputs`
+        result = getattr(ufunc, method)(*inputs, **kwargs)
+    elif self.ndim == 1:
+        # ufunc(series, ...)
+        inputs = tuple(extract_array(x, extract_numpy=True) for x in inputs)
+        result = getattr(ufunc, method)(*inputs, **kwargs)
+    else:
+        # ufunc(dataframe)
+        if method == "__call__" and not kwargs:
+            # for np.<ufunc>(..) calls
+            # kwargs cannot necessarily be handled block-by-block, so only
+            # take this path if there are no kwargs
+            mgr = inputs[0]._mgr
+            result = mgr.apply(getattr(ufunc, method))
+        else:
+            # otherwise specific ufunc methods (eg np.<ufunc>.accumulate(..))
+            # Those can have an axis keyword and thus can't be called block-by-block
+            result = default_array_ufunc(inputs[0], ufunc, method, *inputs, **kwargs)
+            # e.g. np.negative (only one reached), with "where" and "out" in kwargs
+
+    result = reconstruct(result)
+    return result
+
+
+def _standardize_out_kwarg(**kwargs) -> dict:
+    """
+    If kwargs contain "out1" and "out2", replace that with a tuple "out"
+
+    np.divmod, np.modf, np.frexp can have either `out=(out1, out2)` or
+    `out1=out1, out2=out2)`
+    """
+    if "out" not in kwargs and "out1" in kwargs and "out2" in kwargs:
+        out1 = kwargs.pop("out1")
+        out2 = kwargs.pop("out2")
+        out = (out1, out2)
+        kwargs["out"] = out
+    return kwargs
+
+
+def dispatch_ufunc_with_out(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
+    """
+    If we have an `out` keyword, then call the ufunc without `out` and then
+    set the result into the given `out`.
+    """
+
+    # Note: we assume _standardize_out_kwarg has already been called.
+    out = kwargs.pop("out")
+    where = kwargs.pop("where", None)
+
+    result = getattr(ufunc, method)(*inputs, **kwargs)
+
+    if result is NotImplemented:
+        return NotImplemented
+
+    if isinstance(result, tuple):
+        # i.e. np.divmod, np.modf, np.frexp
+        if not isinstance(out, tuple) or len(out) != len(result):
+            raise NotImplementedError
+
+        for arr, res in zip(out, result):
+            _assign_where(arr, res, where)
+
+        return out
+
+    if isinstance(out, tuple):
+        if len(out) == 1:
+            out = out[0]
+        else:
+            raise NotImplementedError
+
+    _assign_where(out, result, where)
+    return out
+
+
+def _assign_where(out, result, where) -> None:
+    """
+    Set a ufunc result into 'out', masking with a 'where' argument if necessary.
+    """
+    if where is None:
+        # no 'where' arg passed to ufunc
+        out[:] = result
+    else:
+        np.putmask(out, where, result)
+
+
+def default_array_ufunc(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
+    """
+    Fallback to the behavior we would get if we did not define __array_ufunc__.
+
+    Notes
+    -----
+    We are assuming that `self` is among `inputs`.
+    """
+    if not any(x is self for x in inputs):
+        raise NotImplementedError
+
+    new_inputs = [x if x is not self else np.asarray(x) for x in inputs]
+
+    return getattr(ufunc, method)(*new_inputs, **kwargs)
+
+
+def dispatch_reduction_ufunc(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
+    """
+    Dispatch ufunc reductions to self's reduction methods.
+    """
+    assert method == "reduce"
+
+    if len(inputs) != 1 or inputs[0] is not self:
+        return NotImplemented
+
+    if ufunc.__name__ not in REDUCTION_ALIASES:
+        return NotImplemented
+
+    method_name = REDUCTION_ALIASES[ufunc.__name__]
+
+    # NB: we are assuming that min/max represent minimum/maximum methods,
+    #  which would not be accurate for e.g. Timestamp.min
+    if not hasattr(self, method_name):
+        return NotImplemented
+
+    if self.ndim > 1:
+        if isinstance(self, ABCNDFrame):
+            # TODO: test cases where this doesn't hold, i.e. 2D DTA/TDA
+            kwargs["numeric_only"] = False
+
+        if "axis" not in kwargs:
+            # For DataFrame reductions we don't want the default axis=0
+            # Note: np.min is not a ufunc, but uses array_function_dispatch,
+            #  so calls DataFrame.min (without ever getting here) with the np.min
+            #  default of axis=None, which DataFrame.min catches and changes to axis=0.
+            # np.minimum.reduce(df) gets here bc axis is not in kwargs,
+            #  so we set axis=0 to match the behaviorof np.minimum.reduce(df.values)
+            kwargs["axis"] = 0
+
+    # By default, numpy's reductions do not skip NaNs, so we have to
+    #  pass skipna=False
+    return getattr(self, method_name)(skipna=False, **kwargs)

AppDir/usr/lib/python3.12/site-packages/pandas/core/arrays/__init__.py

@@ -0,0 +1,43 @@
+from pandas.core.arrays.arrow import ArrowExtensionArray
+from pandas.core.arrays.base import (
+    ExtensionArray,
+    ExtensionOpsMixin,
+    ExtensionScalarOpsMixin,
+)
+from pandas.core.arrays.boolean import BooleanArray
+from pandas.core.arrays.categorical import Categorical
+from pandas.core.arrays.datetimes import DatetimeArray
+from pandas.core.arrays.floating import FloatingArray
+from pandas.core.arrays.integer import IntegerArray
+from pandas.core.arrays.interval import IntervalArray
+from pandas.core.arrays.masked import BaseMaskedArray
+from pandas.core.arrays.numpy_ import NumpyExtensionArray
+from pandas.core.arrays.period import (
+    PeriodArray,
+    period_array,
+)
+from pandas.core.arrays.sparse import SparseArray
+from pandas.core.arrays.string_ import StringArray
+from pandas.core.arrays.string_arrow import ArrowStringArray
+from pandas.core.arrays.timedeltas import TimedeltaArray
+
+__all__ = [
+    "ArrowExtensionArray",
+    "ExtensionArray",
+    "ExtensionOpsMixin",
+    "ExtensionScalarOpsMixin",
+    "ArrowStringArray",
+    "BaseMaskedArray",
+    "BooleanArray",
+    "Categorical",
+    "DatetimeArray",
+    "FloatingArray",
+    "IntegerArray",
+    "IntervalArray",
+    "NumpyExtensionArray",
+    "PeriodArray",
+    "period_array",
+    "SparseArray",
+    "StringArray",
+    "TimedeltaArray",
+]