Add files using upload-large-folder tool

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

@@ -0,0 +1,57 @@
+"""
+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",
+    "warn_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"] is True
+        and _mode_options["data_manager"] == "block"
+    )
+
+
+def warn_copy_on_write() -> bool:
+    _mode_options = _global_config["mode"]
+    return (
+        _mode_options["copy_on_write"] == "warn"
+        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"]

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

@@ -0,0 +1,948 @@
+"""
+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"""
+
+    d: dict[str, Any]
+
+    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) -> list[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

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
+    )

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
+    )

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)

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

@@ -0,0 +1,87 @@
+__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",
+    "guess_datetime_format",
+    "add_overflowsafe",
+    "get_supported_dtype",
+    "is_supported_dtype",
+]
+
+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,
+    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,
+    add_overflowsafe,
+    astype_overflowsafe,
+    get_supported_dtype,
+    is_supported_dtype,
+    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.parsing import guess_datetime_format
+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,
+)

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: ...

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 localize_pydatetime(dt: datetime, tz: tzinfo | None) -> datetime: ...
+def cast_from_unit_vectorized(
+    values: np.ndarray, unit: str, out_unit: str = ...
+) -> np.ndarray: ...

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

@@ -0,0 +1,83 @@
+from enum import Enum
+
+OFFSET_TO_PERIOD_FREQSTR: dict[str, str]
+
+def periods_per_day(reso: int = ...) -> int: ...
+def periods_per_second(reso: int) -> int: ...
+def abbrev_to_npy_unit(abbrev: str | None) -> int: ...
+def freq_to_period_freqstr(freq_n: int, freq_name: str) -> str: ...
+
+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

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]: ...

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

@@ -0,0 +1,141 @@
+from datetime import (
+    datetime,
+    timedelta,
+    tzinfo as _tzinfo,
+)
+import typing
+
+import numpy as np
+
+from pandas._libs.tslibs.period import Period
+from pandas._typing import Self
+
+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 __sub__(self, other: Self | timedelta | datetime) -> Self: ...
+    def __rsub__(self, other: Self | timedelta | datetime) -> Self: ...
+    def __add__(self, other: Self | timedelta | datetime) -> Self: ...
+    def __radd__(self, other: Self | timedelta | datetime) -> Self: ...
+    def __hash__(self) -> int: ...
+    def as_unit(self, unit: str, round_ok: bool = ...) -> NaTType: ...

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

@@ -0,0 +1,27 @@
+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(
+    values: 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_]: ...
+def add_overflowsafe(
+    left: npt.NDArray[np.int64],
+    right: npt.NDArray[np.int64],
+) -> npt.NDArray[np.int64]: ...
+def get_supported_dtype(dtype: np.dtype) -> np.dtype: ...
+def is_supported_dtype(dtype: np.dtype) -> bool: ...

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

@@ -0,0 +1,287 @@
+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
+    normalize: bool
+    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: np.ndarray) -> np.ndarray: ...
+    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, is_period: bool = ...) -> None: ...
+@overload
+def to_offset(freq: _BaseOffsetT, is_period: bool = ...) -> _BaseOffsetT: ...
+@overload
+def to_offset(freq: timedelta | str, is_period: bool = ...) -> 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 = ...,
+    reso: int = ...,
+) -> npt.NDArray[np.int64]: ...
+
+_offset_map: dict[str, BaseOffset]

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

@@ -0,0 +1,33 @@
+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 guess_datetime_format(
+    dt_str: str,
+    dayfirst: bool | None = ...,
+) -> str | None: ...
+def concat_date_cols(
+    date_cols: tuple,
+) -> npt.NDArray[np.object_]: ...
+def get_rule_month(source: str) -> str: ...

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: BaseOffset, 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: BaseOffset) -> Period: ...
+    @classmethod
+    def now(cls, freq: Frequency) -> Period: ...
+    def strftime(self, fmt: str | None) -> 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: ...

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

@@ -0,0 +1,14 @@
+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 = ...,
+    creso: int = ...,  # NPY_DATETIMEUNIT
+) -> tuple[np.ndarray, np.ndarray]: ...
+
+# first ndarray is M8[ns], second is object ndarray of tzinfo | None

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

@@ -0,0 +1,174 @@
+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 (
+    Frequency,
+    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 get_unit_for_round(freq, creso: int) -> int: ...
+def disallow_ambiguous_unit(unit: str | None) -> None: ...
+def ints_to_pytimedelta(
+    m8values: 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: Frequency) -> Self: ...
+    def floor(self, freq: Frequency) -> Self: ...
+    def ceil(self, freq: Frequency) -> 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, dtype: npt.DTypeLike = ..., copy: bool = False
+    ) -> np.timedelta64: ...
+    def view(self, dtype: npt.DTypeLike) -> object: ...
+    @property
+    def unit(self) -> str: ...
+    def as_unit(self, unit: str, round_ok: bool = ...) -> Timedelta: ...

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

@@ -0,0 +1,241 @@
+from datetime import (
+    date as _date,
+    datetime,
+    time as _time,
+    timedelta,
+    tzinfo as _tzinfo,
+)
+from time import struct_time
+from typing import (
+    ClassVar,
+    Literal,
+    TypeAlias,
+    overload,
+)
+
+import numpy as np
+
+from pandas._libs.tslibs import (
+    BaseOffset,
+    NaTType,
+    Period,
+    Tick,
+    Timedelta,
+)
+from pandas._typing import (
+    Self,
+    TimestampNonexistent,
+)
+
+_TimeZones: TypeAlias = str | _tzinfo | None | int
+
+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[Self],
+        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: _TimeZones = ...,
+        unit: str | int | None = ...,
+        fold: int | None = ...,
+    ) -> Self | NaTType: ...
+    @classmethod
+    def _from_value_and_reso(
+        cls, value: int, reso: int, tz: _TimeZones
+    ) -> 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: _TimeZones = ...) -> Self: ...
+    @classmethod
+    def utcfromtimestamp(cls, ts: float) -> Self: ...
+    @classmethod
+    def today(cls, tz: _TimeZones = ...) -> Self: ...
+    @classmethod
+    def fromordinal(
+        cls,
+        ordinal: int,
+        tz: _TimeZones = ...,
+    ) -> Self: ...
+    @classmethod
+    def now(cls, tz: _TimeZones = ...) -> 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: _TimeZones) -> 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 | None = None) -> Period: ...
+    def to_julian_date(self) -> np.float64: ...
+    @property
+    def asm8(self) -> np.datetime64: ...
+    def tz_convert(self, tz: _TimeZones) -> Self: ...
+    # TODO: could return NaT?
+    def tz_localize(
+        self,
+        tz: _TimeZones,
+        ambiguous: bool | Literal["raise", "NaT"] = ...,
+        nonexistent: TimestampNonexistent = ...,
+    ) -> Self: ...
+    def normalize(self) -> Self: ...
+    # TODO: round/floor/ceil could return NaT?
+    def round(
+        self,
+        freq: str,
+        ambiguous: bool | Literal["raise", "NaT"] = ...,
+        nonexistent: TimestampNonexistent = ...,
+    ) -> Self: ...
+    def floor(
+        self,
+        freq: str,
+        ambiguous: bool | Literal["raise", "NaT"] = ...,
+        nonexistent: TimestampNonexistent = ...,
+    ) -> Self: ...
+    def ceil(
+        self,
+        freq: str,
+        ambiguous: bool | Literal["raise", "NaT"] = ...,
+        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: ...

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: ...

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(
+    utc_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]: ...

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(
+    stamps: 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]: ...

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 | None = None,  # const float64_t[:]
+    normalize: bool = True,
+) -> 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]

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]]: ...

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",
+]

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",
+]

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",
+]

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"]

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",
+]

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",
+]

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_under10p1,
+    pa_version_under11p0,
+    pa_version_under13p0,
+    pa_version_under14p0,
+    pa_version_under14p1,
+    pa_version_under16p0,
+    pa_version_under17p0,
+)
+
+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_under10p1",
+    "pa_version_under11p0",
+    "pa_version_under13p0",
+    "pa_version_under14p0",
+    "pa_version_under14p1",
+    "pa_version_under16p0",
+    "pa_version_under17p0",
+    "IS64",
+    "ISMUSL",
+    "PY310",
+    "PY311",
+    "PY312",
+    "PYPY",
+]