Add files using upload-large-folder tool

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/_testing/__init__.py

@@ -0,0 +1,639 @@
+from __future__ import annotations
+
+from decimal import Decimal
+import operator
+import os
+from sys import byteorder
+from typing import (
+    TYPE_CHECKING,
+    Callable,
+    ContextManager,
+    cast,
+)
+import warnings
+
+import numpy as np
+
+from pandas._config.localization import (
+    can_set_locale,
+    get_locales,
+    set_locale,
+)
+
+from pandas.compat import pa_version_under10p1
+
+from pandas.core.dtypes.common import is_string_dtype
+
+import pandas as pd
+from pandas import (
+    ArrowDtype,
+    DataFrame,
+    Index,
+    MultiIndex,
+    RangeIndex,
+    Series,
+)
+from pandas._testing._io import (
+    round_trip_localpath,
+    round_trip_pathlib,
+    round_trip_pickle,
+    write_to_compressed,
+)
+from pandas._testing._warnings import (
+    assert_produces_warning,
+    maybe_produces_warning,
+)
+from pandas._testing.asserters import (
+    assert_almost_equal,
+    assert_attr_equal,
+    assert_categorical_equal,
+    assert_class_equal,
+    assert_contains_all,
+    assert_copy,
+    assert_datetime_array_equal,
+    assert_dict_equal,
+    assert_equal,
+    assert_extension_array_equal,
+    assert_frame_equal,
+    assert_index_equal,
+    assert_indexing_slices_equivalent,
+    assert_interval_array_equal,
+    assert_is_sorted,
+    assert_is_valid_plot_return_object,
+    assert_metadata_equivalent,
+    assert_numpy_array_equal,
+    assert_period_array_equal,
+    assert_series_equal,
+    assert_sp_array_equal,
+    assert_timedelta_array_equal,
+    raise_assert_detail,
+)
+from pandas._testing.compat import (
+    get_dtype,
+    get_obj,
+)
+from pandas._testing.contexts import (
+    assert_cow_warning,
+    decompress_file,
+    ensure_clean,
+    raises_chained_assignment_error,
+    set_timezone,
+    use_numexpr,
+    with_csv_dialect,
+)
+from pandas.core.arrays import (
+    BaseMaskedArray,
+    ExtensionArray,
+    NumpyExtensionArray,
+)
+from pandas.core.arrays._mixins import NDArrayBackedExtensionArray
+from pandas.core.construction import extract_array
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        Dtype,
+        NpDtype,
+    )
+
+    from pandas.core.arrays import ArrowExtensionArray
+
+UNSIGNED_INT_NUMPY_DTYPES: list[NpDtype] = ["uint8", "uint16", "uint32", "uint64"]
+UNSIGNED_INT_EA_DTYPES: list[Dtype] = ["UInt8", "UInt16", "UInt32", "UInt64"]
+SIGNED_INT_NUMPY_DTYPES: list[NpDtype] = [int, "int8", "int16", "int32", "int64"]
+SIGNED_INT_EA_DTYPES: list[Dtype] = ["Int8", "Int16", "Int32", "Int64"]
+ALL_INT_NUMPY_DTYPES = UNSIGNED_INT_NUMPY_DTYPES + SIGNED_INT_NUMPY_DTYPES
+ALL_INT_EA_DTYPES = UNSIGNED_INT_EA_DTYPES + SIGNED_INT_EA_DTYPES
+ALL_INT_DTYPES: list[Dtype] = [*ALL_INT_NUMPY_DTYPES, *ALL_INT_EA_DTYPES]
+
+FLOAT_NUMPY_DTYPES: list[NpDtype] = [float, "float32", "float64"]
+FLOAT_EA_DTYPES: list[Dtype] = ["Float32", "Float64"]
+ALL_FLOAT_DTYPES: list[Dtype] = [*FLOAT_NUMPY_DTYPES, *FLOAT_EA_DTYPES]
+
+COMPLEX_DTYPES: list[Dtype] = [complex, "complex64", "complex128"]
+STRING_DTYPES: list[Dtype] = [str, "str", "U"]
+COMPLEX_FLOAT_DTYPES: list[Dtype] = [*COMPLEX_DTYPES, *FLOAT_NUMPY_DTYPES]
+
+DATETIME64_DTYPES: list[Dtype] = ["datetime64[ns]", "M8[ns]"]
+TIMEDELTA64_DTYPES: list[Dtype] = ["timedelta64[ns]", "m8[ns]"]
+
+BOOL_DTYPES: list[Dtype] = [bool, "bool"]
+BYTES_DTYPES: list[Dtype] = [bytes, "bytes"]
+OBJECT_DTYPES: list[Dtype] = [object, "object"]
+
+ALL_REAL_NUMPY_DTYPES = FLOAT_NUMPY_DTYPES + ALL_INT_NUMPY_DTYPES
+ALL_REAL_EXTENSION_DTYPES = FLOAT_EA_DTYPES + ALL_INT_EA_DTYPES
+ALL_REAL_DTYPES: list[Dtype] = [*ALL_REAL_NUMPY_DTYPES, *ALL_REAL_EXTENSION_DTYPES]
+ALL_NUMERIC_DTYPES: list[Dtype] = [*ALL_REAL_DTYPES, *COMPLEX_DTYPES]
+
+ALL_NUMPY_DTYPES = (
+    ALL_REAL_NUMPY_DTYPES
+    + COMPLEX_DTYPES
+    + STRING_DTYPES
+    + DATETIME64_DTYPES
+    + TIMEDELTA64_DTYPES
+    + BOOL_DTYPES
+    + OBJECT_DTYPES
+    + BYTES_DTYPES
+)
+
+NARROW_NP_DTYPES = [
+    np.float16,
+    np.float32,
+    np.int8,
+    np.int16,
+    np.int32,
+    np.uint8,
+    np.uint16,
+    np.uint32,
+]
+
+PYTHON_DATA_TYPES = [
+    str,
+    int,
+    float,
+    complex,
+    list,
+    tuple,
+    range,
+    dict,
+    set,
+    frozenset,
+    bool,
+    bytes,
+    bytearray,
+    memoryview,
+]
+
+ENDIAN = {"little": "<", "big": ">"}[byteorder]
+
+NULL_OBJECTS = [None, np.nan, pd.NaT, float("nan"), pd.NA, Decimal("NaN")]
+NP_NAT_OBJECTS = [
+    cls("NaT", unit)
+    for cls in [np.datetime64, np.timedelta64]
+    for unit in [
+        "Y",
+        "M",
+        "W",
+        "D",
+        "h",
+        "m",
+        "s",
+        "ms",
+        "us",
+        "ns",
+        "ps",
+        "fs",
+        "as",
+    ]
+]
+
+if not pa_version_under10p1:
+    import pyarrow as pa
+
+    UNSIGNED_INT_PYARROW_DTYPES = [pa.uint8(), pa.uint16(), pa.uint32(), pa.uint64()]
+    SIGNED_INT_PYARROW_DTYPES = [pa.int8(), pa.int16(), pa.int32(), pa.int64()]
+    ALL_INT_PYARROW_DTYPES = UNSIGNED_INT_PYARROW_DTYPES + SIGNED_INT_PYARROW_DTYPES
+    ALL_INT_PYARROW_DTYPES_STR_REPR = [
+        str(ArrowDtype(typ)) for typ in ALL_INT_PYARROW_DTYPES
+    ]
+
+    # pa.float16 doesn't seem supported
+    # https://github.com/apache/arrow/blob/master/python/pyarrow/src/arrow/python/helpers.cc#L86
+    FLOAT_PYARROW_DTYPES = [pa.float32(), pa.float64()]
+    FLOAT_PYARROW_DTYPES_STR_REPR = [
+        str(ArrowDtype(typ)) for typ in FLOAT_PYARROW_DTYPES
+    ]
+    DECIMAL_PYARROW_DTYPES = [pa.decimal128(7, 3)]
+    STRING_PYARROW_DTYPES = [pa.string()]
+    BINARY_PYARROW_DTYPES = [pa.binary()]
+
+    TIME_PYARROW_DTYPES = [
+        pa.time32("s"),
+        pa.time32("ms"),
+        pa.time64("us"),
+        pa.time64("ns"),
+    ]
+    DATE_PYARROW_DTYPES = [pa.date32(), pa.date64()]
+    DATETIME_PYARROW_DTYPES = [
+        pa.timestamp(unit=unit, tz=tz)
+        for unit in ["s", "ms", "us", "ns"]
+        for tz in [None, "UTC", "US/Pacific", "US/Eastern"]
+    ]
+    TIMEDELTA_PYARROW_DTYPES = [pa.duration(unit) for unit in ["s", "ms", "us", "ns"]]
+
+    BOOL_PYARROW_DTYPES = [pa.bool_()]
+
+    # TODO: Add container like pyarrow types:
+    #  https://arrow.apache.org/docs/python/api/datatypes.html#factory-functions
+    ALL_PYARROW_DTYPES = (
+        ALL_INT_PYARROW_DTYPES
+        + FLOAT_PYARROW_DTYPES
+        + DECIMAL_PYARROW_DTYPES
+        + STRING_PYARROW_DTYPES
+        + BINARY_PYARROW_DTYPES
+        + TIME_PYARROW_DTYPES
+        + DATE_PYARROW_DTYPES
+        + DATETIME_PYARROW_DTYPES
+        + TIMEDELTA_PYARROW_DTYPES
+        + BOOL_PYARROW_DTYPES
+    )
+    ALL_REAL_PYARROW_DTYPES_STR_REPR = (
+        ALL_INT_PYARROW_DTYPES_STR_REPR + FLOAT_PYARROW_DTYPES_STR_REPR
+    )
+else:
+    FLOAT_PYARROW_DTYPES_STR_REPR = []
+    ALL_INT_PYARROW_DTYPES_STR_REPR = []
+    ALL_PYARROW_DTYPES = []
+    ALL_REAL_PYARROW_DTYPES_STR_REPR = []
+
+ALL_REAL_NULLABLE_DTYPES = (
+    FLOAT_NUMPY_DTYPES + ALL_REAL_EXTENSION_DTYPES + ALL_REAL_PYARROW_DTYPES_STR_REPR
+)
+
+arithmetic_dunder_methods = [
+    "__add__",
+    "__radd__",
+    "__sub__",
+    "__rsub__",
+    "__mul__",
+    "__rmul__",
+    "__floordiv__",
+    "__rfloordiv__",
+    "__truediv__",
+    "__rtruediv__",
+    "__pow__",
+    "__rpow__",
+    "__mod__",
+    "__rmod__",
+]
+
+comparison_dunder_methods = ["__eq__", "__ne__", "__le__", "__lt__", "__ge__", "__gt__"]
+
+
+# -----------------------------------------------------------------------------
+# Comparators
+
+
+def box_expected(expected, box_cls, transpose: bool = True):
+    """
+    Helper function to wrap the expected output of a test in a given box_class.
+
+    Parameters
+    ----------
+    expected : np.ndarray, Index, Series
+    box_cls : {Index, Series, DataFrame}
+
+    Returns
+    -------
+    subclass of box_cls
+    """
+    if box_cls is pd.array:
+        if isinstance(expected, RangeIndex):
+            # pd.array would return an IntegerArray
+            expected = NumpyExtensionArray(np.asarray(expected._values))
+        else:
+            expected = pd.array(expected, copy=False)
+    elif box_cls is Index:
+        with warnings.catch_warnings():
+            warnings.filterwarnings("ignore", "Dtype inference", category=FutureWarning)
+            expected = Index(expected)
+    elif box_cls is Series:
+        with warnings.catch_warnings():
+            warnings.filterwarnings("ignore", "Dtype inference", category=FutureWarning)
+            expected = Series(expected)
+    elif box_cls is DataFrame:
+        with warnings.catch_warnings():
+            warnings.filterwarnings("ignore", "Dtype inference", category=FutureWarning)
+            expected = Series(expected).to_frame()
+        if transpose:
+            # for vector operations, we need a DataFrame to be a single-row,
+            #  not a single-column, in order to operate against non-DataFrame
+            #  vectors of the same length. But convert to two rows to avoid
+            #  single-row special cases in datetime arithmetic
+            expected = expected.T
+            expected = pd.concat([expected] * 2, ignore_index=True)
+    elif box_cls is np.ndarray or box_cls is np.array:
+        expected = np.array(expected)
+    elif box_cls is to_array:
+        expected = to_array(expected)
+    else:
+        raise NotImplementedError(box_cls)
+    return expected
+
+
+def to_array(obj):
+    """
+    Similar to pd.array, but does not cast numpy dtypes to nullable dtypes.
+    """
+    # temporary implementation until we get pd.array in place
+    dtype = getattr(obj, "dtype", None)
+
+    if dtype is None:
+        return np.asarray(obj)
+
+    return extract_array(obj, extract_numpy=True)
+
+
+class SubclassedSeries(Series):
+    _metadata = ["testattr", "name"]
+
+    @property
+    def _constructor(self):
+        # For testing, those properties return a generic callable, and not
+        # the actual class. In this case that is equivalent, but it is to
+        # ensure we don't rely on the property returning a class
+        # See https://github.com/pandas-dev/pandas/pull/46018 and
+        # https://github.com/pandas-dev/pandas/issues/32638 and linked issues
+        return lambda *args, **kwargs: SubclassedSeries(*args, **kwargs)
+
+    @property
+    def _constructor_expanddim(self):
+        return lambda *args, **kwargs: SubclassedDataFrame(*args, **kwargs)
+
+
+class SubclassedDataFrame(DataFrame):
+    _metadata = ["testattr"]
+
+    @property
+    def _constructor(self):
+        return lambda *args, **kwargs: SubclassedDataFrame(*args, **kwargs)
+
+    @property
+    def _constructor_sliced(self):
+        return lambda *args, **kwargs: SubclassedSeries(*args, **kwargs)
+
+
+def convert_rows_list_to_csv_str(rows_list: list[str]) -> str:
+    """
+    Convert list of CSV rows to single CSV-formatted string for current OS.
+
+    This method is used for creating expected value of to_csv() method.
+
+    Parameters
+    ----------
+    rows_list : List[str]
+        Each element represents the row of csv.
+
+    Returns
+    -------
+    str
+        Expected output of to_csv() in current OS.
+    """
+    sep = os.linesep
+    return sep.join(rows_list) + sep
+
+
+def external_error_raised(expected_exception: type[Exception]) -> ContextManager:
+    """
+    Helper function to mark pytest.raises that have an external error message.
+
+    Parameters
+    ----------
+    expected_exception : Exception
+        Expected error to raise.
+
+    Returns
+    -------
+    Callable
+        Regular `pytest.raises` function with `match` equal to `None`.
+    """
+    import pytest
+
+    return pytest.raises(expected_exception, match=None)
+
+
+cython_table = pd.core.common._cython_table.items()
+
+
+def get_cython_table_params(ndframe, func_names_and_expected):
+    """
+    Combine frame, functions from com._cython_table
+    keys and expected result.
+
+    Parameters
+    ----------
+    ndframe : DataFrame or Series
+    func_names_and_expected : Sequence of two items
+        The first item is a name of a NDFrame method ('sum', 'prod') etc.
+        The second item is the expected return value.
+
+    Returns
+    -------
+    list
+        List of three items (DataFrame, function, expected result)
+    """
+    results = []
+    for func_name, expected in func_names_and_expected:
+        results.append((ndframe, func_name, expected))
+        results += [
+            (ndframe, func, expected)
+            for func, name in cython_table
+            if name == func_name
+        ]
+    return results
+
+
+def get_op_from_name(op_name: str) -> Callable:
+    """
+    The operator function for a given op name.
+
+    Parameters
+    ----------
+    op_name : str
+        The op name, in form of "add" or "__add__".
+
+    Returns
+    -------
+    function
+        A function performing the operation.
+    """
+    short_opname = op_name.strip("_")
+    try:
+        op = getattr(operator, short_opname)
+    except AttributeError:
+        # Assume it is the reverse operator
+        rop = getattr(operator, short_opname[1:])
+        op = lambda x, y: rop(y, x)
+
+    return op
+
+
+# -----------------------------------------------------------------------------
+# Indexing test helpers
+
+
+def getitem(x):
+    return x
+
+
+def setitem(x):
+    return x
+
+
+def loc(x):
+    return x.loc
+
+
+def iloc(x):
+    return x.iloc
+
+
+def at(x):
+    return x.at
+
+
+def iat(x):
+    return x.iat
+
+
+# -----------------------------------------------------------------------------
+
+_UNITS = ["s", "ms", "us", "ns"]
+
+
+def get_finest_unit(left: str, right: str):
+    """
+    Find the higher of two datetime64 units.
+    """
+    if _UNITS.index(left) >= _UNITS.index(right):
+        return left
+    return right
+
+
+def shares_memory(left, right) -> bool:
+    """
+    Pandas-compat for np.shares_memory.
+    """
+    if isinstance(left, np.ndarray) and isinstance(right, np.ndarray):
+        return np.shares_memory(left, right)
+    elif isinstance(left, np.ndarray):
+        # Call with reversed args to get to unpacking logic below.
+        return shares_memory(right, left)
+
+    if isinstance(left, RangeIndex):
+        return False
+    if isinstance(left, MultiIndex):
+        return shares_memory(left._codes, right)
+    if isinstance(left, (Index, Series)):
+        return shares_memory(left._values, right)
+
+    if isinstance(left, NDArrayBackedExtensionArray):
+        return shares_memory(left._ndarray, right)
+    if isinstance(left, pd.core.arrays.SparseArray):
+        return shares_memory(left.sp_values, right)
+    if isinstance(left, pd.core.arrays.IntervalArray):
+        return shares_memory(left._left, right) or shares_memory(left._right, right)
+
+    if (
+        isinstance(left, ExtensionArray)
+        and is_string_dtype(left.dtype)
+        and left.dtype.storage in ("pyarrow", "pyarrow_numpy")  # type: ignore[attr-defined]
+    ):
+        # https://github.com/pandas-dev/pandas/pull/43930#discussion_r736862669
+        left = cast("ArrowExtensionArray", left)
+        if (
+            isinstance(right, ExtensionArray)
+            and is_string_dtype(right.dtype)
+            and right.dtype.storage in ("pyarrow", "pyarrow_numpy")  # type: ignore[attr-defined]
+        ):
+            right = cast("ArrowExtensionArray", right)
+            left_pa_data = left._pa_array
+            right_pa_data = right._pa_array
+            left_buf1 = left_pa_data.chunk(0).buffers()[1]
+            right_buf1 = right_pa_data.chunk(0).buffers()[1]
+            return left_buf1 == right_buf1
+
+    if isinstance(left, BaseMaskedArray) and isinstance(right, BaseMaskedArray):
+        # By convention, we'll say these share memory if they share *either*
+        #  the _data or the _mask
+        return np.shares_memory(left._data, right._data) or np.shares_memory(
+            left._mask, right._mask
+        )
+
+    if isinstance(left, DataFrame) and len(left._mgr.arrays) == 1:
+        arr = left._mgr.arrays[0]
+        return shares_memory(arr, right)
+
+    raise NotImplementedError(type(left), type(right))
+
+
+__all__ = [
+    "ALL_INT_EA_DTYPES",
+    "ALL_INT_NUMPY_DTYPES",
+    "ALL_NUMPY_DTYPES",
+    "ALL_REAL_NUMPY_DTYPES",
+    "assert_almost_equal",
+    "assert_attr_equal",
+    "assert_categorical_equal",
+    "assert_class_equal",
+    "assert_contains_all",
+    "assert_copy",
+    "assert_datetime_array_equal",
+    "assert_dict_equal",
+    "assert_equal",
+    "assert_extension_array_equal",
+    "assert_frame_equal",
+    "assert_index_equal",
+    "assert_indexing_slices_equivalent",
+    "assert_interval_array_equal",
+    "assert_is_sorted",
+    "assert_is_valid_plot_return_object",
+    "assert_metadata_equivalent",
+    "assert_numpy_array_equal",
+    "assert_period_array_equal",
+    "assert_produces_warning",
+    "assert_series_equal",
+    "assert_sp_array_equal",
+    "assert_timedelta_array_equal",
+    "assert_cow_warning",
+    "at",
+    "BOOL_DTYPES",
+    "box_expected",
+    "BYTES_DTYPES",
+    "can_set_locale",
+    "COMPLEX_DTYPES",
+    "convert_rows_list_to_csv_str",
+    "DATETIME64_DTYPES",
+    "decompress_file",
+    "ENDIAN",
+    "ensure_clean",
+    "external_error_raised",
+    "FLOAT_EA_DTYPES",
+    "FLOAT_NUMPY_DTYPES",
+    "get_cython_table_params",
+    "get_dtype",
+    "getitem",
+    "get_locales",
+    "get_finest_unit",
+    "get_obj",
+    "get_op_from_name",
+    "iat",
+    "iloc",
+    "loc",
+    "maybe_produces_warning",
+    "NARROW_NP_DTYPES",
+    "NP_NAT_OBJECTS",
+    "NULL_OBJECTS",
+    "OBJECT_DTYPES",
+    "raise_assert_detail",
+    "raises_chained_assignment_error",
+    "round_trip_localpath",
+    "round_trip_pathlib",
+    "round_trip_pickle",
+    "setitem",
+    "set_locale",
+    "set_timezone",
+    "shares_memory",
+    "SIGNED_INT_EA_DTYPES",
+    "SIGNED_INT_NUMPY_DTYPES",
+    "STRING_DTYPES",
+    "SubclassedDataFrame",
+    "SubclassedSeries",
+    "TIMEDELTA64_DTYPES",
+    "to_array",
+    "UNSIGNED_INT_EA_DTYPES",
+    "UNSIGNED_INT_NUMPY_DTYPES",
+    "use_numexpr",
+    "with_csv_dialect",
+    "write_to_compressed",
+]

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/_testing/_hypothesis.py

@@ -0,0 +1,93 @@
+"""
+Hypothesis data generator helpers.
+"""
+from datetime import datetime
+
+from hypothesis import strategies as st
+from hypothesis.extra.dateutil import timezones as dateutil_timezones
+from hypothesis.extra.pytz import timezones as pytz_timezones
+
+from pandas.compat import is_platform_windows
+
+import pandas as pd
+
+from pandas.tseries.offsets import (
+    BMonthBegin,
+    BMonthEnd,
+    BQuarterBegin,
+    BQuarterEnd,
+    BYearBegin,
+    BYearEnd,
+    MonthBegin,
+    MonthEnd,
+    QuarterBegin,
+    QuarterEnd,
+    YearBegin,
+    YearEnd,
+)
+
+OPTIONAL_INTS = st.lists(st.one_of(st.integers(), st.none()), max_size=10, min_size=3)
+
+OPTIONAL_FLOATS = st.lists(st.one_of(st.floats(), st.none()), max_size=10, min_size=3)
+
+OPTIONAL_TEXT = st.lists(st.one_of(st.none(), st.text()), max_size=10, min_size=3)
+
+OPTIONAL_DICTS = st.lists(
+    st.one_of(st.none(), st.dictionaries(st.text(), st.integers())),
+    max_size=10,
+    min_size=3,
+)
+
+OPTIONAL_LISTS = st.lists(
+    st.one_of(st.none(), st.lists(st.text(), max_size=10, min_size=3)),
+    max_size=10,
+    min_size=3,
+)
+
+OPTIONAL_ONE_OF_ALL = st.one_of(
+    OPTIONAL_DICTS, OPTIONAL_FLOATS, OPTIONAL_INTS, OPTIONAL_LISTS, OPTIONAL_TEXT
+)
+
+if is_platform_windows():
+    DATETIME_NO_TZ = st.datetimes(min_value=datetime(1900, 1, 1))
+else:
+    DATETIME_NO_TZ = st.datetimes()
+
+DATETIME_JAN_1_1900_OPTIONAL_TZ = st.datetimes(
+    min_value=pd.Timestamp(
+        1900, 1, 1
+    ).to_pydatetime(),  # pyright: ignore[reportGeneralTypeIssues]
+    max_value=pd.Timestamp(
+        1900, 1, 1
+    ).to_pydatetime(),  # pyright: ignore[reportGeneralTypeIssues]
+    timezones=st.one_of(st.none(), dateutil_timezones(), pytz_timezones()),
+)
+
+DATETIME_IN_PD_TIMESTAMP_RANGE_NO_TZ = st.datetimes(
+    min_value=pd.Timestamp.min.to_pydatetime(warn=False),
+    max_value=pd.Timestamp.max.to_pydatetime(warn=False),
+)
+
+INT_NEG_999_TO_POS_999 = st.integers(-999, 999)
+
+# The strategy for each type is registered in conftest.py, as they don't carry
+# enough runtime information (e.g. type hints) to infer how to build them.
+YQM_OFFSET = st.one_of(
+    *map(
+        st.from_type,
+        [
+            MonthBegin,
+            MonthEnd,
+            BMonthBegin,
+            BMonthEnd,
+            QuarterBegin,
+            QuarterEnd,
+            BQuarterBegin,
+            BQuarterEnd,
+            YearBegin,
+            YearEnd,
+            BYearBegin,
+            BYearEnd,
+        ],
+    )
+)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/_testing/_io.py

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

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/_testing/_warnings.py

@@ -0,0 +1,232 @@
+from __future__ import annotations
+
+from contextlib import (
+    contextmanager,
+    nullcontext,
+)
+import inspect
+import re
+import sys
+from typing import (
+    TYPE_CHECKING,
+    Literal,
+    cast,
+)
+import warnings
+
+from pandas.compat import PY311
+
+if TYPE_CHECKING:
+    from collections.abc import (
+        Generator,
+        Sequence,
+    )
+
+
+@contextmanager
+def assert_produces_warning(
+    expected_warning: type[Warning] | bool | tuple[type[Warning], ...] | None = Warning,
+    filter_level: Literal[
+        "error", "ignore", "always", "default", "module", "once"
+    ] = "always",
+    check_stacklevel: bool = True,
+    raise_on_extra_warnings: bool = True,
+    match: str | None = None,
+) -> Generator[list[warnings.WarningMessage], None, None]:
+    """
+    Context manager for running code expected to either raise a specific warning,
+    multiple specific warnings, or not raise any warnings. Verifies that the code
+    raises the expected warning(s), and that it does not raise any other unexpected
+    warnings. It is basically a wrapper around ``warnings.catch_warnings``.
+
+    Parameters
+    ----------
+    expected_warning : {Warning, False, tuple[Warning, ...], None}, default Warning
+        The type of Exception raised. ``exception.Warning`` is the base
+        class for all warnings. To raise multiple types of exceptions,
+        pass them as a tuple. To check that no warning is returned,
+        specify ``False`` or ``None``.
+    filter_level : str or None, default "always"
+        Specifies whether warnings are ignored, displayed, or turned
+        into errors.
+        Valid values are:
+
+        * "error" - turns matching warnings into exceptions
+        * "ignore" - discard the warning
+        * "always" - always emit a warning
+        * "default" - print the warning the first time it is generated
+          from each location
+        * "module" - print the warning the first time it is generated
+          from each module
+        * "once" - print the warning the first time it is generated
+
+    check_stacklevel : bool, default True
+        If True, displays the line that called the function containing
+        the warning to show were the function is called. Otherwise, the
+        line that implements the function is displayed.
+    raise_on_extra_warnings : bool, default True
+        Whether extra warnings not of the type `expected_warning` should
+        cause the test to fail.
+    match : str, optional
+        Match warning message.
+
+    Examples
+    --------
+    >>> import warnings
+    >>> with assert_produces_warning():
+    ...     warnings.warn(UserWarning())
+    ...
+    >>> with assert_produces_warning(False):
+    ...     warnings.warn(RuntimeWarning())
+    ...
+    Traceback (most recent call last):
+        ...
+    AssertionError: Caused unexpected warning(s): ['RuntimeWarning'].
+    >>> with assert_produces_warning(UserWarning):
+    ...     warnings.warn(RuntimeWarning())
+    Traceback (most recent call last):
+        ...
+    AssertionError: Did not see expected warning of class 'UserWarning'.
+
+    ..warn:: This is *not* thread-safe.
+    """
+    __tracebackhide__ = True
+
+    with warnings.catch_warnings(record=True) as w:
+        warnings.simplefilter(filter_level)
+        try:
+            yield w
+        finally:
+            if expected_warning:
+                expected_warning = cast(type[Warning], expected_warning)
+                _assert_caught_expected_warning(
+                    caught_warnings=w,
+                    expected_warning=expected_warning,
+                    match=match,
+                    check_stacklevel=check_stacklevel,
+                )
+            if raise_on_extra_warnings:
+                _assert_caught_no_extra_warnings(
+                    caught_warnings=w,
+                    expected_warning=expected_warning,
+                )
+
+
+def maybe_produces_warning(warning: type[Warning], condition: bool, **kwargs):
+    """
+    Return a context manager that possibly checks a warning based on the condition
+    """
+    if condition:
+        return assert_produces_warning(warning, **kwargs)
+    else:
+        return nullcontext()
+
+
+def _assert_caught_expected_warning(
+    *,
+    caught_warnings: Sequence[warnings.WarningMessage],
+    expected_warning: type[Warning],
+    match: str | None,
+    check_stacklevel: bool,
+) -> None:
+    """Assert that there was the expected warning among the caught warnings."""
+    saw_warning = False
+    matched_message = False
+    unmatched_messages = []
+
+    for actual_warning in caught_warnings:
+        if issubclass(actual_warning.category, expected_warning):
+            saw_warning = True
+
+            if check_stacklevel:
+                _assert_raised_with_correct_stacklevel(actual_warning)
+
+            if match is not None:
+                if re.search(match, str(actual_warning.message)):
+                    matched_message = True
+                else:
+                    unmatched_messages.append(actual_warning.message)
+
+    if not saw_warning:
+        raise AssertionError(
+            f"Did not see expected warning of class "
+            f"{repr(expected_warning.__name__)}"
+        )
+
+    if match and not matched_message:
+        raise AssertionError(
+            f"Did not see warning {repr(expected_warning.__name__)} "
+            f"matching '{match}'. The emitted warning messages are "
+            f"{unmatched_messages}"
+        )
+
+
+def _assert_caught_no_extra_warnings(
+    *,
+    caught_warnings: Sequence[warnings.WarningMessage],
+    expected_warning: type[Warning] | bool | tuple[type[Warning], ...] | None,
+) -> None:
+    """Assert that no extra warnings apart from the expected ones are caught."""
+    extra_warnings = []
+
+    for actual_warning in caught_warnings:
+        if _is_unexpected_warning(actual_warning, expected_warning):
+            # GH#38630 pytest.filterwarnings does not suppress these.
+            if actual_warning.category == ResourceWarning:
+                # GH 44732: Don't make the CI flaky by filtering SSL-related
+                # ResourceWarning from dependencies
+                if "unclosed <ssl.SSLSocket" in str(actual_warning.message):
+                    continue
+                # GH 44844: Matplotlib leaves font files open during the entire process
+                # upon import. Don't make CI flaky if ResourceWarning raised
+                # due to these open files.
+                if any("matplotlib" in mod for mod in sys.modules):
+                    continue
+            if PY311 and actual_warning.category == EncodingWarning:
+                # EncodingWarnings are checked in the CI
+                # pyproject.toml errors on EncodingWarnings in pandas
+                # Ignore EncodingWarnings from other libraries
+                continue
+            extra_warnings.append(
+                (
+                    actual_warning.category.__name__,
+                    actual_warning.message,
+                    actual_warning.filename,
+                    actual_warning.lineno,
+                )
+            )
+
+    if extra_warnings:
+        raise AssertionError(f"Caused unexpected warning(s): {repr(extra_warnings)}")
+
+
+def _is_unexpected_warning(
+    actual_warning: warnings.WarningMessage,
+    expected_warning: type[Warning] | bool | tuple[type[Warning], ...] | None,
+) -> bool:
+    """Check if the actual warning issued is unexpected."""
+    if actual_warning and not expected_warning:
+        return True
+    expected_warning = cast(type[Warning], expected_warning)
+    return bool(not issubclass(actual_warning.category, expected_warning))
+
+
+def _assert_raised_with_correct_stacklevel(
+    actual_warning: warnings.WarningMessage,
+) -> None:
+    # https://stackoverflow.com/questions/17407119/python-inspect-stack-is-slow
+    frame = inspect.currentframe()
+    for _ in range(4):
+        frame = frame.f_back  # type: ignore[union-attr]
+    try:
+        caller_filename = inspect.getfile(frame)  # type: ignore[arg-type]
+    finally:
+        # See note in
+        # https://docs.python.org/3/library/inspect.html#inspect.Traceback
+        del frame
+    msg = (
+        "Warning not set with correct stacklevel. "
+        f"File where warning is raised: {actual_warning.filename} != "
+        f"{caller_filename}. Warning message: {actual_warning.message}"
+    )
+    assert actual_warning.filename == caller_filename, msg

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/_testing/asserters.py

@@ -0,0 +1,1435 @@
+from __future__ import annotations
+
+import operator
+from typing import (
+    TYPE_CHECKING,
+    Literal,
+    NoReturn,
+    cast,
+)
+
+import numpy as np
+
+from pandas._libs import lib
+from pandas._libs.missing import is_matching_na
+from pandas._libs.sparse import SparseIndex
+import pandas._libs.testing as _testing
+from pandas._libs.tslibs.np_datetime import compare_mismatched_resolutions
+
+from pandas.core.dtypes.common import (
+    is_bool,
+    is_float_dtype,
+    is_integer_dtype,
+    is_number,
+    is_numeric_dtype,
+    needs_i8_conversion,
+)
+from pandas.core.dtypes.dtypes import (
+    CategoricalDtype,
+    DatetimeTZDtype,
+    ExtensionDtype,
+    NumpyEADtype,
+)
+from pandas.core.dtypes.missing import array_equivalent
+
+import pandas as pd
+from pandas import (
+    Categorical,
+    DataFrame,
+    DatetimeIndex,
+    Index,
+    IntervalDtype,
+    IntervalIndex,
+    MultiIndex,
+    PeriodIndex,
+    RangeIndex,
+    Series,
+    TimedeltaIndex,
+)
+from pandas.core.arrays import (
+    DatetimeArray,
+    ExtensionArray,
+    IntervalArray,
+    PeriodArray,
+    TimedeltaArray,
+)
+from pandas.core.arrays.datetimelike import DatetimeLikeArrayMixin
+from pandas.core.arrays.string_ import StringDtype
+from pandas.core.indexes.api import safe_sort_index
+
+from pandas.io.formats.printing import pprint_thing
+
+if TYPE_CHECKING:
+    from pandas._typing import DtypeObj
+
+
+def assert_almost_equal(
+    left,
+    right,
+    check_dtype: bool | Literal["equiv"] = "equiv",
+    rtol: float = 1.0e-5,
+    atol: float = 1.0e-8,
+    **kwargs,
+) -> None:
+    """
+    Check that the left and right objects are approximately equal.
+
+    By approximately equal, we refer to objects that are numbers or that
+    contain numbers which may be equivalent to specific levels of precision.
+
+    Parameters
+    ----------
+    left : object
+    right : object
+    check_dtype : bool or {'equiv'}, default 'equiv'
+        Check dtype if both a and b are the same type. If 'equiv' is passed in,
+        then `RangeIndex` and `Index` with int64 dtype are also considered
+        equivalent when doing type checking.
+    rtol : float, default 1e-5
+        Relative tolerance.
+    atol : float, default 1e-8
+        Absolute tolerance.
+    """
+    if isinstance(left, Index):
+        assert_index_equal(
+            left,
+            right,
+            check_exact=False,
+            exact=check_dtype,
+            rtol=rtol,
+            atol=atol,
+            **kwargs,
+        )
+
+    elif isinstance(left, Series):
+        assert_series_equal(
+            left,
+            right,
+            check_exact=False,
+            check_dtype=check_dtype,
+            rtol=rtol,
+            atol=atol,
+            **kwargs,
+        )
+
+    elif isinstance(left, DataFrame):
+        assert_frame_equal(
+            left,
+            right,
+            check_exact=False,
+            check_dtype=check_dtype,
+            rtol=rtol,
+            atol=atol,
+            **kwargs,
+        )
+
+    else:
+        # Other sequences.
+        if check_dtype:
+            if is_number(left) and is_number(right):
+                # Do not compare numeric classes, like np.float64 and float.
+                pass
+            elif is_bool(left) and is_bool(right):
+                # Do not compare bool classes, like np.bool_ and bool.
+                pass
+            else:
+                if isinstance(left, np.ndarray) or isinstance(right, np.ndarray):
+                    obj = "numpy array"
+                else:
+                    obj = "Input"
+                assert_class_equal(left, right, obj=obj)
+
+        # if we have "equiv", this becomes True
+        _testing.assert_almost_equal(
+            left, right, check_dtype=bool(check_dtype), rtol=rtol, atol=atol, **kwargs
+        )
+
+
+def _check_isinstance(left, right, cls) -> None:
+    """
+    Helper method for our assert_* methods that ensures that
+    the two objects being compared have the right type before
+    proceeding with the comparison.
+
+    Parameters
+    ----------
+    left : The first object being compared.
+    right : The second object being compared.
+    cls : The class type to check against.
+
+    Raises
+    ------
+    AssertionError : Either `left` or `right` is not an instance of `cls`.
+    """
+    cls_name = cls.__name__
+
+    if not isinstance(left, cls):
+        raise AssertionError(
+            f"{cls_name} Expected type {cls}, found {type(left)} instead"
+        )
+    if not isinstance(right, cls):
+        raise AssertionError(
+            f"{cls_name} Expected type {cls}, found {type(right)} instead"
+        )
+
+
+def assert_dict_equal(left, right, compare_keys: bool = True) -> None:
+    _check_isinstance(left, right, dict)
+    _testing.assert_dict_equal(left, right, compare_keys=compare_keys)
+
+
+def assert_index_equal(
+    left: Index,
+    right: Index,
+    exact: bool | str = "equiv",
+    check_names: bool = True,
+    check_exact: bool = True,
+    check_categorical: bool = True,
+    check_order: bool = True,
+    rtol: float = 1.0e-5,
+    atol: float = 1.0e-8,
+    obj: str = "Index",
+) -> None:
+    """
+    Check that left and right Index are equal.
+
+    Parameters
+    ----------
+    left : Index
+    right : Index
+    exact : bool or {'equiv'}, default 'equiv'
+        Whether to check the Index class, dtype and inferred_type
+        are identical. If 'equiv', then RangeIndex can be substituted for
+        Index with an int64 dtype as well.
+    check_names : bool, default True
+        Whether to check the names attribute.
+    check_exact : bool, default True
+        Whether to compare number exactly.
+    check_categorical : bool, default True
+        Whether to compare internal Categorical exactly.
+    check_order : bool, default True
+        Whether to compare the order of index entries as well as their values.
+        If True, both indexes must contain the same elements, in the same order.
+        If False, both indexes must contain the same elements, but in any order.
+    rtol : float, default 1e-5
+        Relative tolerance. Only used when check_exact is False.
+    atol : float, default 1e-8
+        Absolute tolerance. Only used when check_exact is False.
+    obj : str, default 'Index'
+        Specify object name being compared, internally used to show appropriate
+        assertion message.
+
+    Examples
+    --------
+    >>> from pandas import testing as tm
+    >>> a = pd.Index([1, 2, 3])
+    >>> b = pd.Index([1, 2, 3])
+    >>> tm.assert_index_equal(a, b)
+    """
+    __tracebackhide__ = True
+
+    def _check_types(left, right, obj: str = "Index") -> None:
+        if not exact:
+            return
+
+        assert_class_equal(left, right, exact=exact, obj=obj)
+        assert_attr_equal("inferred_type", left, right, obj=obj)
+
+        # Skip exact dtype checking when `check_categorical` is False
+        if isinstance(left.dtype, CategoricalDtype) and isinstance(
+            right.dtype, CategoricalDtype
+        ):
+            if check_categorical:
+                assert_attr_equal("dtype", left, right, obj=obj)
+                assert_index_equal(left.categories, right.categories, exact=exact)
+            return
+
+        assert_attr_equal("dtype", left, right, obj=obj)
+
+    # instance validation
+    _check_isinstance(left, right, Index)
+
+    # class / dtype comparison
+    _check_types(left, right, obj=obj)
+
+    # level comparison
+    if left.nlevels != right.nlevels:
+        msg1 = f"{obj} levels are different"
+        msg2 = f"{left.nlevels}, {left}"
+        msg3 = f"{right.nlevels}, {right}"
+        raise_assert_detail(obj, msg1, msg2, msg3)
+
+    # length comparison
+    if len(left) != len(right):
+        msg1 = f"{obj} length are different"
+        msg2 = f"{len(left)}, {left}"
+        msg3 = f"{len(right)}, {right}"
+        raise_assert_detail(obj, msg1, msg2, msg3)
+
+    # If order doesn't matter then sort the index entries
+    if not check_order:
+        left = safe_sort_index(left)
+        right = safe_sort_index(right)
+
+    # MultiIndex special comparison for little-friendly error messages
+    if isinstance(left, MultiIndex):
+        right = cast(MultiIndex, right)
+
+        for level in range(left.nlevels):
+            lobj = f"MultiIndex level [{level}]"
+            try:
+                # try comparison on levels/codes to avoid densifying MultiIndex
+                assert_index_equal(
+                    left.levels[level],
+                    right.levels[level],
+                    exact=exact,
+                    check_names=check_names,
+                    check_exact=check_exact,
+                    check_categorical=check_categorical,
+                    rtol=rtol,
+                    atol=atol,
+                    obj=lobj,
+                )
+                assert_numpy_array_equal(left.codes[level], right.codes[level])
+            except AssertionError:
+                llevel = left.get_level_values(level)
+                rlevel = right.get_level_values(level)
+
+                assert_index_equal(
+                    llevel,
+                    rlevel,
+                    exact=exact,
+                    check_names=check_names,
+                    check_exact=check_exact,
+                    check_categorical=check_categorical,
+                    rtol=rtol,
+                    atol=atol,
+                    obj=lobj,
+                )
+            # get_level_values may change dtype
+            _check_types(left.levels[level], right.levels[level], obj=obj)
+
+    # skip exact index checking when `check_categorical` is False
+    elif check_exact and check_categorical:
+        if not left.equals(right):
+            mismatch = left._values != right._values
+
+            if not isinstance(mismatch, np.ndarray):
+                mismatch = cast("ExtensionArray", mismatch).fillna(True)
+
+            diff = np.sum(mismatch.astype(int)) * 100.0 / len(left)
+            msg = f"{obj} values are different ({np.round(diff, 5)} %)"
+            raise_assert_detail(obj, msg, left, right)
+    else:
+        # if we have "equiv", this becomes True
+        exact_bool = bool(exact)
+        _testing.assert_almost_equal(
+            left.values,
+            right.values,
+            rtol=rtol,
+            atol=atol,
+            check_dtype=exact_bool,
+            obj=obj,
+            lobj=left,
+            robj=right,
+        )
+
+    # metadata comparison
+    if check_names:
+        assert_attr_equal("names", left, right, obj=obj)
+    if isinstance(left, PeriodIndex) or isinstance(right, PeriodIndex):
+        assert_attr_equal("dtype", left, right, obj=obj)
+    if isinstance(left, IntervalIndex) or isinstance(right, IntervalIndex):
+        assert_interval_array_equal(left._values, right._values)
+
+    if check_categorical:
+        if isinstance(left.dtype, CategoricalDtype) or isinstance(
+            right.dtype, CategoricalDtype
+        ):
+            assert_categorical_equal(left._values, right._values, obj=f"{obj} category")
+
+
+def assert_class_equal(
+    left, right, exact: bool | str = True, obj: str = "Input"
+) -> None:
+    """
+    Checks classes are equal.
+    """
+    __tracebackhide__ = True
+
+    def repr_class(x):
+        if isinstance(x, Index):
+            # return Index as it is to include values in the error message
+            return x
+
+        return type(x).__name__
+
+    def is_class_equiv(idx: Index) -> bool:
+        """Classes that are a RangeIndex (sub-)instance or exactly an `Index` .
+
+        This only checks class equivalence. There is a separate check that the
+        dtype is int64.
+        """
+        return type(idx) is Index or isinstance(idx, RangeIndex)
+
+    if type(left) == type(right):
+        return
+
+    if exact == "equiv":
+        if is_class_equiv(left) and is_class_equiv(right):
+            return
+
+    msg = f"{obj} classes are different"
+    raise_assert_detail(obj, msg, repr_class(left), repr_class(right))
+
+
+def assert_attr_equal(attr: str, left, right, obj: str = "Attributes") -> None:
+    """
+    Check attributes are equal. Both objects must have attribute.
+
+    Parameters
+    ----------
+    attr : str
+        Attribute name being compared.
+    left : object
+    right : object
+    obj : str, default 'Attributes'
+        Specify object name being compared, internally used to show appropriate
+        assertion message
+    """
+    __tracebackhide__ = True
+
+    left_attr = getattr(left, attr)
+    right_attr = getattr(right, attr)
+
+    if left_attr is right_attr or is_matching_na(left_attr, right_attr):
+        # e.g. both np.nan, both NaT, both pd.NA, ...
+        return None
+
+    try:
+        result = left_attr == right_attr
+    except TypeError:
+        # datetimetz on rhs may raise TypeError
+        result = False
+    if (left_attr is pd.NA) ^ (right_attr is pd.NA):
+        result = False
+    elif not isinstance(result, bool):
+        result = result.all()
+
+    if not result:
+        msg = f'Attribute "{attr}" are different'
+        raise_assert_detail(obj, msg, left_attr, right_attr)
+    return None
+
+
+def assert_is_valid_plot_return_object(objs) -> None:
+    from matplotlib.artist import Artist
+    from matplotlib.axes import Axes
+
+    if isinstance(objs, (Series, np.ndarray)):
+        if isinstance(objs, Series):
+            objs = objs._values
+        for el in objs.ravel():
+            msg = (
+                "one of 'objs' is not a matplotlib Axes instance, "
+                f"type encountered {repr(type(el).__name__)}"
+            )
+            assert isinstance(el, (Axes, dict)), msg
+    else:
+        msg = (
+            "objs is neither an ndarray of Artist instances nor a single "
+            "ArtistArtist instance, tuple, or dict, 'objs' is a "
+            f"{repr(type(objs).__name__)}"
+        )
+        assert isinstance(objs, (Artist, tuple, dict)), msg
+
+
+def assert_is_sorted(seq) -> None:
+    """Assert that the sequence is sorted."""
+    if isinstance(seq, (Index, Series)):
+        seq = seq.values
+    # sorting does not change precisions
+    if isinstance(seq, np.ndarray):
+        assert_numpy_array_equal(seq, np.sort(np.array(seq)))
+    else:
+        assert_extension_array_equal(seq, seq[seq.argsort()])
+
+
+def assert_categorical_equal(
+    left,
+    right,
+    check_dtype: bool = True,
+    check_category_order: bool = True,
+    obj: str = "Categorical",
+) -> None:
+    """
+    Test that Categoricals are equivalent.
+
+    Parameters
+    ----------
+    left : Categorical
+    right : Categorical
+    check_dtype : bool, default True
+        Check that integer dtype of the codes are the same.
+    check_category_order : bool, default True
+        Whether the order of the categories should be compared, which
+        implies identical integer codes.  If False, only the resulting
+        values are compared.  The ordered attribute is
+        checked regardless.
+    obj : str, default 'Categorical'
+        Specify object name being compared, internally used to show appropriate
+        assertion message.
+    """
+    _check_isinstance(left, right, Categorical)
+
+    exact: bool | str
+    if isinstance(left.categories, RangeIndex) or isinstance(
+        right.categories, RangeIndex
+    ):
+        exact = "equiv"
+    else:
+        # We still want to require exact matches for Index
+        exact = True
+
+    if check_category_order:
+        assert_index_equal(
+            left.categories, right.categories, obj=f"{obj}.categories", exact=exact
+        )
+        assert_numpy_array_equal(
+            left.codes, right.codes, check_dtype=check_dtype, obj=f"{obj}.codes"
+        )
+    else:
+        try:
+            lc = left.categories.sort_values()
+            rc = right.categories.sort_values()
+        except TypeError:
+            # e.g. '<' not supported between instances of 'int' and 'str'
+            lc, rc = left.categories, right.categories
+        assert_index_equal(lc, rc, obj=f"{obj}.categories", exact=exact)
+        assert_index_equal(
+            left.categories.take(left.codes),
+            right.categories.take(right.codes),
+            obj=f"{obj}.values",
+            exact=exact,
+        )
+
+    assert_attr_equal("ordered", left, right, obj=obj)
+
+
+def assert_interval_array_equal(
+    left, right, exact: bool | Literal["equiv"] = "equiv", obj: str = "IntervalArray"
+) -> None:
+    """
+    Test that two IntervalArrays are equivalent.
+
+    Parameters
+    ----------
+    left, right : IntervalArray
+        The IntervalArrays to compare.
+    exact : bool or {'equiv'}, default 'equiv'
+        Whether to check the Index class, dtype and inferred_type
+        are identical. If 'equiv', then RangeIndex can be substituted for
+        Index with an int64 dtype as well.
+    obj : str, default 'IntervalArray'
+        Specify object name being compared, internally used to show appropriate
+        assertion message
+    """
+    _check_isinstance(left, right, IntervalArray)
+
+    kwargs = {}
+    if left._left.dtype.kind in "mM":
+        # We have a DatetimeArray or TimedeltaArray
+        kwargs["check_freq"] = False
+
+    assert_equal(left._left, right._left, obj=f"{obj}.left", **kwargs)
+    assert_equal(left._right, right._right, obj=f"{obj}.left", **kwargs)
+
+    assert_attr_equal("closed", left, right, obj=obj)
+
+
+def assert_period_array_equal(left, right, obj: str = "PeriodArray") -> None:
+    _check_isinstance(left, right, PeriodArray)
+
+    assert_numpy_array_equal(left._ndarray, right._ndarray, obj=f"{obj}._ndarray")
+    assert_attr_equal("dtype", left, right, obj=obj)
+
+
+def assert_datetime_array_equal(
+    left, right, obj: str = "DatetimeArray", check_freq: bool = True
+) -> None:
+    __tracebackhide__ = True
+    _check_isinstance(left, right, DatetimeArray)
+
+    assert_numpy_array_equal(left._ndarray, right._ndarray, obj=f"{obj}._ndarray")
+    if check_freq:
+        assert_attr_equal("freq", left, right, obj=obj)
+    assert_attr_equal("tz", left, right, obj=obj)
+
+
+def assert_timedelta_array_equal(
+    left, right, obj: str = "TimedeltaArray", check_freq: bool = True
+) -> None:
+    __tracebackhide__ = True
+    _check_isinstance(left, right, TimedeltaArray)
+    assert_numpy_array_equal(left._ndarray, right._ndarray, obj=f"{obj}._ndarray")
+    if check_freq:
+        assert_attr_equal("freq", left, right, obj=obj)
+
+
+def raise_assert_detail(
+    obj, message, left, right, diff=None, first_diff=None, index_values=None
+) -> NoReturn:
+    __tracebackhide__ = True
+
+    msg = f"""{obj} are different
+
+{message}"""
+
+    if isinstance(index_values, Index):
+        index_values = np.asarray(index_values)
+
+    if isinstance(index_values, np.ndarray):
+        msg += f"\n[index]: {pprint_thing(index_values)}"
+
+    if isinstance(left, np.ndarray):
+        left = pprint_thing(left)
+    elif isinstance(left, (CategoricalDtype, NumpyEADtype, StringDtype)):
+        left = repr(left)
+
+    if isinstance(right, np.ndarray):
+        right = pprint_thing(right)
+    elif isinstance(right, (CategoricalDtype, NumpyEADtype, StringDtype)):
+        right = repr(right)
+
+    msg += f"""
+[left]:  {left}
+[right]: {right}"""
+
+    if diff is not None:
+        msg += f"\n[diff]: {diff}"
+
+    if first_diff is not None:
+        msg += f"\n{first_diff}"
+
+    raise AssertionError(msg)
+
+
+def assert_numpy_array_equal(
+    left,
+    right,
+    strict_nan: bool = False,
+    check_dtype: bool | Literal["equiv"] = True,
+    err_msg=None,
+    check_same=None,
+    obj: str = "numpy array",
+    index_values=None,
+) -> None:
+    """
+    Check that 'np.ndarray' is equivalent.
+
+    Parameters
+    ----------
+    left, right : numpy.ndarray or iterable
+        The two arrays to be compared.
+    strict_nan : bool, default False
+        If True, consider NaN and None to be different.
+    check_dtype : bool, default True
+        Check dtype if both a and b are np.ndarray.
+    err_msg : str, default None
+        If provided, used as assertion message.
+    check_same : None|'copy'|'same', default None
+        Ensure left and right refer/do not refer to the same memory area.
+    obj : str, default 'numpy array'
+        Specify object name being compared, internally used to show appropriate
+        assertion message.
+    index_values : Index | numpy.ndarray, default None
+        optional index (shared by both left and right), used in output.
+    """
+    __tracebackhide__ = True
+
+    # instance validation
+    # Show a detailed error message when classes are different
+    assert_class_equal(left, right, obj=obj)
+    # both classes must be an np.ndarray
+    _check_isinstance(left, right, np.ndarray)
+
+    def _get_base(obj):
+        return obj.base if getattr(obj, "base", None) is not None else obj
+
+    left_base = _get_base(left)
+    right_base = _get_base(right)
+
+    if check_same == "same":
+        if left_base is not right_base:
+            raise AssertionError(f"{repr(left_base)} is not {repr(right_base)}")
+    elif check_same == "copy":
+        if left_base is right_base:
+            raise AssertionError(f"{repr(left_base)} is {repr(right_base)}")
+
+    def _raise(left, right, err_msg) -> NoReturn:
+        if err_msg is None:
+            if left.shape != right.shape:
+                raise_assert_detail(
+                    obj, f"{obj} shapes are different", left.shape, right.shape
+                )
+
+            diff = 0
+            for left_arr, right_arr in zip(left, right):
+                # count up differences
+                if not array_equivalent(left_arr, right_arr, strict_nan=strict_nan):
+                    diff += 1
+
+            diff = diff * 100.0 / left.size
+            msg = f"{obj} values are different ({np.round(diff, 5)} %)"
+            raise_assert_detail(obj, msg, left, right, index_values=index_values)
+
+        raise AssertionError(err_msg)
+
+    # compare shape and values
+    if not array_equivalent(left, right, strict_nan=strict_nan):
+        _raise(left, right, err_msg)
+
+    if check_dtype:
+        if isinstance(left, np.ndarray) and isinstance(right, np.ndarray):
+            assert_attr_equal("dtype", left, right, obj=obj)
+
+
+def assert_extension_array_equal(
+    left,
+    right,
+    check_dtype: bool | Literal["equiv"] = True,
+    index_values=None,
+    check_exact: bool | lib.NoDefault = lib.no_default,
+    rtol: float | lib.NoDefault = lib.no_default,
+    atol: float | lib.NoDefault = lib.no_default,
+    obj: str = "ExtensionArray",
+) -> None:
+    """
+    Check that left and right ExtensionArrays are equal.
+
+    Parameters
+    ----------
+    left, right : ExtensionArray
+        The two arrays to compare.
+    check_dtype : bool, default True
+        Whether to check if the ExtensionArray dtypes are identical.
+    index_values : Index | numpy.ndarray, default None
+        Optional index (shared by both left and right), used in output.
+    check_exact : bool, default False
+        Whether to compare number exactly.
+
+        .. versionchanged:: 2.2.0
+
+            Defaults to True for integer dtypes if none of
+            ``check_exact``, ``rtol`` and ``atol`` are specified.
+    rtol : float, default 1e-5
+        Relative tolerance. Only used when check_exact is False.
+    atol : float, default 1e-8
+        Absolute tolerance. Only used when check_exact is False.
+    obj : str, default 'ExtensionArray'
+        Specify object name being compared, internally used to show appropriate
+        assertion message.
+
+        .. versionadded:: 2.0.0
+
+    Notes
+    -----
+    Missing values are checked separately from valid values.
+    A mask of missing values is computed for each and checked to match.
+    The remaining all-valid values are cast to object dtype and checked.
+
+    Examples
+    --------
+    >>> from pandas import testing as tm
+    >>> a = pd.Series([1, 2, 3, 4])
+    >>> b, c = a.array, a.array
+    >>> tm.assert_extension_array_equal(b, c)
+    """
+    if (
+        check_exact is lib.no_default
+        and rtol is lib.no_default
+        and atol is lib.no_default
+    ):
+        check_exact = (
+            is_numeric_dtype(left.dtype)
+            and not is_float_dtype(left.dtype)
+            or is_numeric_dtype(right.dtype)
+            and not is_float_dtype(right.dtype)
+        )
+    elif check_exact is lib.no_default:
+        check_exact = False
+
+    rtol = rtol if rtol is not lib.no_default else 1.0e-5
+    atol = atol if atol is not lib.no_default else 1.0e-8
+
+    assert isinstance(left, ExtensionArray), "left is not an ExtensionArray"
+    assert isinstance(right, ExtensionArray), "right is not an ExtensionArray"
+    if check_dtype:
+        assert_attr_equal("dtype", left, right, obj=f"Attributes of {obj}")
+
+    if (
+        isinstance(left, DatetimeLikeArrayMixin)
+        and isinstance(right, DatetimeLikeArrayMixin)
+        and type(right) == type(left)
+    ):
+        # GH 52449
+        if not check_dtype and left.dtype.kind in "mM":
+            if not isinstance(left.dtype, np.dtype):
+                l_unit = cast(DatetimeTZDtype, left.dtype).unit
+            else:
+                l_unit = np.datetime_data(left.dtype)[0]
+            if not isinstance(right.dtype, np.dtype):
+                r_unit = cast(DatetimeTZDtype, right.dtype).unit
+            else:
+                r_unit = np.datetime_data(right.dtype)[0]
+            if (
+                l_unit != r_unit
+                and compare_mismatched_resolutions(
+                    left._ndarray, right._ndarray, operator.eq
+                ).all()
+            ):
+                return
+        # Avoid slow object-dtype comparisons
+        # np.asarray for case where we have a np.MaskedArray
+        assert_numpy_array_equal(
+            np.asarray(left.asi8),
+            np.asarray(right.asi8),
+            index_values=index_values,
+            obj=obj,
+        )
+        return
+
+    left_na = np.asarray(left.isna())
+    right_na = np.asarray(right.isna())
+    assert_numpy_array_equal(
+        left_na, right_na, obj=f"{obj} NA mask", index_values=index_values
+    )
+
+    left_valid = left[~left_na].to_numpy(dtype=object)
+    right_valid = right[~right_na].to_numpy(dtype=object)
+    if check_exact:
+        assert_numpy_array_equal(
+            left_valid, right_valid, obj=obj, index_values=index_values
+        )
+    else:
+        _testing.assert_almost_equal(
+            left_valid,
+            right_valid,
+            check_dtype=bool(check_dtype),
+            rtol=rtol,
+            atol=atol,
+            obj=obj,
+            index_values=index_values,
+        )
+
+
+# This could be refactored to use the NDFrame.equals method
+def assert_series_equal(
+    left,
+    right,
+    check_dtype: bool | Literal["equiv"] = True,
+    check_index_type: bool | Literal["equiv"] = "equiv",
+    check_series_type: bool = True,
+    check_names: bool = True,
+    check_exact: bool | lib.NoDefault = lib.no_default,
+    check_datetimelike_compat: bool = False,
+    check_categorical: bool = True,
+    check_category_order: bool = True,
+    check_freq: bool = True,
+    check_flags: bool = True,
+    rtol: float | lib.NoDefault = lib.no_default,
+    atol: float | lib.NoDefault = lib.no_default,
+    obj: str = "Series",
+    *,
+    check_index: bool = True,
+    check_like: bool = False,
+) -> None:
+    """
+    Check that left and right Series are equal.
+
+    Parameters
+    ----------
+    left : Series
+    right : Series
+    check_dtype : bool, default True
+        Whether to check the Series dtype is identical.
+    check_index_type : bool or {'equiv'}, default 'equiv'
+        Whether to check the Index class, dtype and inferred_type
+        are identical.
+    check_series_type : bool, default True
+         Whether to check the Series class is identical.
+    check_names : bool, default True
+        Whether to check the Series and Index names attribute.
+    check_exact : bool, default False
+        Whether to compare number exactly.
+
+        .. versionchanged:: 2.2.0
+
+            Defaults to True for integer dtypes if none of
+            ``check_exact``, ``rtol`` and ``atol`` are specified.
+    check_datetimelike_compat : bool, default False
+        Compare datetime-like which is comparable ignoring dtype.
+    check_categorical : bool, default True
+        Whether to compare internal Categorical exactly.
+    check_category_order : bool, default True
+        Whether to compare category order of internal Categoricals.
+    check_freq : bool, default True
+        Whether to check the `freq` attribute on a DatetimeIndex or TimedeltaIndex.
+    check_flags : bool, default True
+        Whether to check the `flags` attribute.
+    rtol : float, default 1e-5
+        Relative tolerance. Only used when check_exact is False.
+    atol : float, default 1e-8
+        Absolute tolerance. Only used when check_exact is False.
+    obj : str, default 'Series'
+        Specify object name being compared, internally used to show appropriate
+        assertion message.
+    check_index : bool, default True
+        Whether to check index equivalence. If False, then compare only values.
+
+        .. versionadded:: 1.3.0
+    check_like : bool, default False
+        If True, ignore the order of the index. Must be False if check_index is False.
+        Note: same labels must be with the same data.
+
+        .. versionadded:: 1.5.0
+
+    Examples
+    --------
+    >>> from pandas import testing as tm
+    >>> a = pd.Series([1, 2, 3, 4])
+    >>> b = pd.Series([1, 2, 3, 4])
+    >>> tm.assert_series_equal(a, b)
+    """
+    __tracebackhide__ = True
+    check_exact_index = False if check_exact is lib.no_default else check_exact
+    if (
+        check_exact is lib.no_default
+        and rtol is lib.no_default
+        and atol is lib.no_default
+    ):
+        check_exact = (
+            is_numeric_dtype(left.dtype)
+            and not is_float_dtype(left.dtype)
+            or is_numeric_dtype(right.dtype)
+            and not is_float_dtype(right.dtype)
+        )
+    elif check_exact is lib.no_default:
+        check_exact = False
+
+    rtol = rtol if rtol is not lib.no_default else 1.0e-5
+    atol = atol if atol is not lib.no_default else 1.0e-8
+
+    if not check_index and check_like:
+        raise ValueError("check_like must be False if check_index is False")
+
+    # instance validation
+    _check_isinstance(left, right, Series)
+
+    if check_series_type:
+        assert_class_equal(left, right, obj=obj)
+
+    # length comparison
+    if len(left) != len(right):
+        msg1 = f"{len(left)}, {left.index}"
+        msg2 = f"{len(right)}, {right.index}"
+        raise_assert_detail(obj, "Series length are different", msg1, msg2)
+
+    if check_flags:
+        assert left.flags == right.flags, f"{repr(left.flags)} != {repr(right.flags)}"
+
+    if check_index:
+        # GH #38183
+        assert_index_equal(
+            left.index,
+            right.index,
+            exact=check_index_type,
+            check_names=check_names,
+            check_exact=check_exact_index,
+            check_categorical=check_categorical,
+            check_order=not check_like,
+            rtol=rtol,
+            atol=atol,
+            obj=f"{obj}.index",
+        )
+
+    if check_like:
+        left = left.reindex_like(right)
+
+    if check_freq and isinstance(left.index, (DatetimeIndex, TimedeltaIndex)):
+        lidx = left.index
+        ridx = right.index
+        assert lidx.freq == ridx.freq, (lidx.freq, ridx.freq)
+
+    if check_dtype:
+        # We want to skip exact dtype checking when `check_categorical`
+        # is False. We'll still raise if only one is a `Categorical`,
+        # regardless of `check_categorical`
+        if (
+            isinstance(left.dtype, CategoricalDtype)
+            and isinstance(right.dtype, CategoricalDtype)
+            and not check_categorical
+        ):
+            pass
+        else:
+            assert_attr_equal("dtype", left, right, obj=f"Attributes of {obj}")
+    if check_exact:
+        left_values = left._values
+        right_values = right._values
+        # Only check exact if dtype is numeric
+        if isinstance(left_values, ExtensionArray) and isinstance(
+            right_values, ExtensionArray
+        ):
+            assert_extension_array_equal(
+                left_values,
+                right_values,
+                check_dtype=check_dtype,
+                index_values=left.index,
+                obj=str(obj),
+            )
+        else:
+            # convert both to NumPy if not, check_dtype would raise earlier
+            lv, rv = left_values, right_values
+            if isinstance(left_values, ExtensionArray):
+                lv = left_values.to_numpy()
+            if isinstance(right_values, ExtensionArray):
+                rv = right_values.to_numpy()
+            assert_numpy_array_equal(
+                lv,
+                rv,
+                check_dtype=check_dtype,
+                obj=str(obj),
+                index_values=left.index,
+            )
+    elif check_datetimelike_compat and (
+        needs_i8_conversion(left.dtype) or needs_i8_conversion(right.dtype)
+    ):
+        # we want to check only if we have compat dtypes
+        # e.g. integer and M|m are NOT compat, but we can simply check
+        # the values in that case
+
+        # datetimelike may have different objects (e.g. datetime.datetime
+        # vs Timestamp) but will compare equal
+        if not Index(left._values).equals(Index(right._values)):
+            msg = (
+                f"[datetimelike_compat=True] {left._values} "
+                f"is not equal to {right._values}."
+            )
+            raise AssertionError(msg)
+    elif isinstance(left.dtype, IntervalDtype) and isinstance(
+        right.dtype, IntervalDtype
+    ):
+        assert_interval_array_equal(left.array, right.array)
+    elif isinstance(left.dtype, CategoricalDtype) or isinstance(
+        right.dtype, CategoricalDtype
+    ):
+        _testing.assert_almost_equal(
+            left._values,
+            right._values,
+            rtol=rtol,
+            atol=atol,
+            check_dtype=bool(check_dtype),
+            obj=str(obj),
+            index_values=left.index,
+        )
+    elif isinstance(left.dtype, ExtensionDtype) and isinstance(
+        right.dtype, ExtensionDtype
+    ):
+        assert_extension_array_equal(
+            left._values,
+            right._values,
+            rtol=rtol,
+            atol=atol,
+            check_dtype=check_dtype,
+            index_values=left.index,
+            obj=str(obj),
+        )
+    elif is_extension_array_dtype_and_needs_i8_conversion(
+        left.dtype, right.dtype
+    ) or is_extension_array_dtype_and_needs_i8_conversion(right.dtype, left.dtype):
+        assert_extension_array_equal(
+            left._values,
+            right._values,
+            check_dtype=check_dtype,
+            index_values=left.index,
+            obj=str(obj),
+        )
+    elif needs_i8_conversion(left.dtype) and needs_i8_conversion(right.dtype):
+        # DatetimeArray or TimedeltaArray
+        assert_extension_array_equal(
+            left._values,
+            right._values,
+            check_dtype=check_dtype,
+            index_values=left.index,
+            obj=str(obj),
+        )
+    else:
+        _testing.assert_almost_equal(
+            left._values,
+            right._values,
+            rtol=rtol,
+            atol=atol,
+            check_dtype=bool(check_dtype),
+            obj=str(obj),
+            index_values=left.index,
+        )
+
+    # metadata comparison
+    if check_names:
+        assert_attr_equal("name", left, right, obj=obj)
+
+    if check_categorical:
+        if isinstance(left.dtype, CategoricalDtype) or isinstance(
+            right.dtype, CategoricalDtype
+        ):
+            assert_categorical_equal(
+                left._values,
+                right._values,
+                obj=f"{obj} category",
+                check_category_order=check_category_order,
+            )
+
+
+# This could be refactored to use the NDFrame.equals method
+def assert_frame_equal(
+    left,
+    right,
+    check_dtype: bool | Literal["equiv"] = True,
+    check_index_type: bool | Literal["equiv"] = "equiv",
+    check_column_type: bool | Literal["equiv"] = "equiv",
+    check_frame_type: bool = True,
+    check_names: bool = True,
+    by_blocks: bool = False,
+    check_exact: bool | lib.NoDefault = lib.no_default,
+    check_datetimelike_compat: bool = False,
+    check_categorical: bool = True,
+    check_like: bool = False,
+    check_freq: bool = True,
+    check_flags: bool = True,
+    rtol: float | lib.NoDefault = lib.no_default,
+    atol: float | lib.NoDefault = lib.no_default,
+    obj: str = "DataFrame",
+) -> None:
+    """
+    Check that left and right DataFrame are equal.
+
+    This function is intended to compare two DataFrames and output any
+    differences. It is mostly intended for use in unit tests.
+    Additional parameters allow varying the strictness of the
+    equality checks performed.
+
+    Parameters
+    ----------
+    left : DataFrame
+        First DataFrame to compare.
+    right : DataFrame
+        Second DataFrame to compare.
+    check_dtype : bool, default True
+        Whether to check the DataFrame dtype is identical.
+    check_index_type : bool or {'equiv'}, default 'equiv'
+        Whether to check the Index class, dtype and inferred_type
+        are identical.
+    check_column_type : bool or {'equiv'}, default 'equiv'
+        Whether to check the columns class, dtype and inferred_type
+        are identical. Is passed as the ``exact`` argument of
+        :func:`assert_index_equal`.
+    check_frame_type : bool, default True
+        Whether to check the DataFrame class is identical.
+    check_names : bool, default True
+        Whether to check that the `names` attribute for both the `index`
+        and `column` attributes of the DataFrame is identical.
+    by_blocks : bool, default False
+        Specify how to compare internal data. If False, compare by columns.
+        If True, compare by blocks.
+    check_exact : bool, default False
+        Whether to compare number exactly.
+
+        .. versionchanged:: 2.2.0
+
+            Defaults to True for integer dtypes if none of
+            ``check_exact``, ``rtol`` and ``atol`` are specified.
+    check_datetimelike_compat : bool, default False
+        Compare datetime-like which is comparable ignoring dtype.
+    check_categorical : bool, default True
+        Whether to compare internal Categorical exactly.
+    check_like : bool, default False
+        If True, ignore the order of index & columns.
+        Note: index labels must match their respective rows
+        (same as in columns) - same labels must be with the same data.
+    check_freq : bool, default True
+        Whether to check the `freq` attribute on a DatetimeIndex or TimedeltaIndex.
+    check_flags : bool, default True
+        Whether to check the `flags` attribute.
+    rtol : float, default 1e-5
+        Relative tolerance. Only used when check_exact is False.
+    atol : float, default 1e-8
+        Absolute tolerance. Only used when check_exact is False.
+    obj : str, default 'DataFrame'
+        Specify object name being compared, internally used to show appropriate
+        assertion message.
+
+    See Also
+    --------
+    assert_series_equal : Equivalent method for asserting Series equality.
+    DataFrame.equals : Check DataFrame equality.
+
+    Examples
+    --------
+    This example shows comparing two DataFrames that are equal
+    but with columns of differing dtypes.
+
+    >>> from pandas.testing import assert_frame_equal
+    >>> df1 = pd.DataFrame({'a': [1, 2], 'b': [3, 4]})
+    >>> df2 = pd.DataFrame({'a': [1, 2], 'b': [3.0, 4.0]})
+
+    df1 equals itself.
+
+    >>> assert_frame_equal(df1, df1)
+
+    df1 differs from df2 as column 'b' is of a different type.
+
+    >>> assert_frame_equal(df1, df2)
+    Traceback (most recent call last):
+    ...
+    AssertionError: Attributes of DataFrame.iloc[:, 1] (column name="b") are different
+
+    Attribute "dtype" are different
+    [left]:  int64
+    [right]: float64
+
+    Ignore differing dtypes in columns with check_dtype.
+
+    >>> assert_frame_equal(df1, df2, check_dtype=False)
+    """
+    __tracebackhide__ = True
+    _rtol = rtol if rtol is not lib.no_default else 1.0e-5
+    _atol = atol if atol is not lib.no_default else 1.0e-8
+    _check_exact = check_exact if check_exact is not lib.no_default else False
+
+    # instance validation
+    _check_isinstance(left, right, DataFrame)
+
+    if check_frame_type:
+        assert isinstance(left, type(right))
+        # assert_class_equal(left, right, obj=obj)
+
+    # shape comparison
+    if left.shape != right.shape:
+        raise_assert_detail(
+            obj, f"{obj} shape mismatch", f"{repr(left.shape)}", f"{repr(right.shape)}"
+        )
+
+    if check_flags:
+        assert left.flags == right.flags, f"{repr(left.flags)} != {repr(right.flags)}"
+
+    # index comparison
+    assert_index_equal(
+        left.index,
+        right.index,
+        exact=check_index_type,
+        check_names=check_names,
+        check_exact=_check_exact,
+        check_categorical=check_categorical,
+        check_order=not check_like,
+        rtol=_rtol,
+        atol=_atol,
+        obj=f"{obj}.index",
+    )
+
+    # column comparison
+    assert_index_equal(
+        left.columns,
+        right.columns,
+        exact=check_column_type,
+        check_names=check_names,
+        check_exact=_check_exact,
+        check_categorical=check_categorical,
+        check_order=not check_like,
+        rtol=_rtol,
+        atol=_atol,
+        obj=f"{obj}.columns",
+    )
+
+    if check_like:
+        left = left.reindex_like(right)
+
+    # compare by blocks
+    if by_blocks:
+        rblocks = right._to_dict_of_blocks()
+        lblocks = left._to_dict_of_blocks()
+        for dtype in list(set(list(lblocks.keys()) + list(rblocks.keys()))):
+            assert dtype in lblocks
+            assert dtype in rblocks
+            assert_frame_equal(
+                lblocks[dtype], rblocks[dtype], check_dtype=check_dtype, obj=obj
+            )
+
+    # compare by columns
+    else:
+        for i, col in enumerate(left.columns):
+            # We have already checked that columns match, so we can do
+            #  fast location-based lookups
+            lcol = left._ixs(i, axis=1)
+            rcol = right._ixs(i, axis=1)
+
+            # GH #38183
+            # use check_index=False, because we do not want to run
+            # assert_index_equal for each column,
+            # as we already checked it for the whole dataframe before.
+            assert_series_equal(
+                lcol,
+                rcol,
+                check_dtype=check_dtype,
+                check_index_type=check_index_type,
+                check_exact=check_exact,
+                check_names=check_names,
+                check_datetimelike_compat=check_datetimelike_compat,
+                check_categorical=check_categorical,
+                check_freq=check_freq,
+                obj=f'{obj}.iloc[:, {i}] (column name="{col}")',
+                rtol=rtol,
+                atol=atol,
+                check_index=False,
+                check_flags=False,
+            )
+
+
+def assert_equal(left, right, **kwargs) -> None:
+    """
+    Wrapper for tm.assert_*_equal to dispatch to the appropriate test function.
+
+    Parameters
+    ----------
+    left, right : Index, Series, DataFrame, ExtensionArray, or np.ndarray
+        The two items to be compared.
+    **kwargs
+        All keyword arguments are passed through to the underlying assert method.
+    """
+    __tracebackhide__ = True
+
+    if isinstance(left, Index):
+        assert_index_equal(left, right, **kwargs)
+        if isinstance(left, (DatetimeIndex, TimedeltaIndex)):
+            assert left.freq == right.freq, (left.freq, right.freq)
+    elif isinstance(left, Series):
+        assert_series_equal(left, right, **kwargs)
+    elif isinstance(left, DataFrame):
+        assert_frame_equal(left, right, **kwargs)
+    elif isinstance(left, IntervalArray):
+        assert_interval_array_equal(left, right, **kwargs)
+    elif isinstance(left, PeriodArray):
+        assert_period_array_equal(left, right, **kwargs)
+    elif isinstance(left, DatetimeArray):
+        assert_datetime_array_equal(left, right, **kwargs)
+    elif isinstance(left, TimedeltaArray):
+        assert_timedelta_array_equal(left, right, **kwargs)
+    elif isinstance(left, ExtensionArray):
+        assert_extension_array_equal(left, right, **kwargs)
+    elif isinstance(left, np.ndarray):
+        assert_numpy_array_equal(left, right, **kwargs)
+    elif isinstance(left, str):
+        assert kwargs == {}
+        assert left == right
+    else:
+        assert kwargs == {}
+        assert_almost_equal(left, right)
+
+
+def assert_sp_array_equal(left, right) -> None:
+    """
+    Check that the left and right SparseArray are equal.
+
+    Parameters
+    ----------
+    left : SparseArray
+    right : SparseArray
+    """
+    _check_isinstance(left, right, pd.arrays.SparseArray)
+
+    assert_numpy_array_equal(left.sp_values, right.sp_values)
+
+    # SparseIndex comparison
+    assert isinstance(left.sp_index, SparseIndex)
+    assert isinstance(right.sp_index, SparseIndex)
+
+    left_index = left.sp_index
+    right_index = right.sp_index
+
+    if not left_index.equals(right_index):
+        raise_assert_detail(
+            "SparseArray.index", "index are not equal", left_index, right_index
+        )
+    else:
+        # Just ensure a
+        pass
+
+    assert_attr_equal("fill_value", left, right)
+    assert_attr_equal("dtype", left, right)
+    assert_numpy_array_equal(left.to_dense(), right.to_dense())
+
+
+def assert_contains_all(iterable, dic) -> None:
+    for k in iterable:
+        assert k in dic, f"Did not contain item: {repr(k)}"
+
+
+def assert_copy(iter1, iter2, **eql_kwargs) -> None:
+    """
+    iter1, iter2: iterables that produce elements
+    comparable with assert_almost_equal
+
+    Checks that the elements are equal, but not
+    the same object. (Does not check that items
+    in sequences are also not the same object)
+    """
+    for elem1, elem2 in zip(iter1, iter2):
+        assert_almost_equal(elem1, elem2, **eql_kwargs)
+        msg = (
+            f"Expected object {repr(type(elem1))} and object {repr(type(elem2))} to be "
+            "different objects, but they were the same object."
+        )
+        assert elem1 is not elem2, msg
+
+
+def is_extension_array_dtype_and_needs_i8_conversion(
+    left_dtype: DtypeObj, right_dtype: DtypeObj
+) -> bool:
+    """
+    Checks that we have the combination of an ExtensionArraydtype and
+    a dtype that should be converted to int64
+
+    Returns
+    -------
+    bool
+
+    Related to issue #37609
+    """
+    return isinstance(left_dtype, ExtensionDtype) and needs_i8_conversion(right_dtype)
+
+
+def assert_indexing_slices_equivalent(ser: Series, l_slc: slice, i_slc: slice) -> None:
+    """
+    Check that ser.iloc[i_slc] matches ser.loc[l_slc] and, if applicable,
+    ser[l_slc].
+    """
+    expected = ser.iloc[i_slc]
+
+    assert_series_equal(ser.loc[l_slc], expected)
+
+    if not is_integer_dtype(ser.index):
+        # For integer indices, .loc and plain getitem are position-based.
+        assert_series_equal(ser[l_slc], expected)
+
+
+def assert_metadata_equivalent(
+    left: DataFrame | Series, right: DataFrame | Series | None = None
+) -> None:
+    """
+    Check that ._metadata attributes are equivalent.
+    """
+    for attr in left._metadata:
+        val = getattr(left, attr, None)
+        if right is None:
+            assert val is None
+        else:
+            assert val == getattr(right, attr, None)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/_testing/compat.py

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

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/_testing/contexts.py

@@ -0,0 +1,257 @@
+from __future__ import annotations
+
+from contextlib import contextmanager
+import os
+from pathlib import Path
+import tempfile
+from typing import (
+    IO,
+    TYPE_CHECKING,
+    Any,
+)
+import uuid
+
+from pandas._config import using_copy_on_write
+
+from pandas.compat import PYPY
+from pandas.errors import ChainedAssignmentError
+
+from pandas import set_option
+
+from pandas.io.common import get_handle
+
+if TYPE_CHECKING:
+    from collections.abc import Generator
+
+    from pandas._typing import (
+        BaseBuffer,
+        CompressionOptions,
+        FilePath,
+    )
+
+
+@contextmanager
+def decompress_file(
+    path: FilePath | BaseBuffer, compression: CompressionOptions
+) -> Generator[IO[bytes], None, None]:
+    """
+    Open a compressed file and return a file object.
+
+    Parameters
+    ----------
+    path : str
+        The path where the file is read from.
+
+    compression : {'gzip', 'bz2', 'zip', 'xz', 'zstd', None}
+        Name of the decompression to use
+
+    Returns
+    -------
+    file object
+    """
+    with get_handle(path, "rb", compression=compression, is_text=False) as handle:
+        yield handle.handle
+
+
+@contextmanager
+def set_timezone(tz: str) -> Generator[None, None, None]:
+    """
+    Context manager for temporarily setting a timezone.
+
+    Parameters
+    ----------
+    tz : str
+        A string representing a valid timezone.
+
+    Examples
+    --------
+    >>> from datetime import datetime
+    >>> from dateutil.tz import tzlocal
+    >>> tzlocal().tzname(datetime(2021, 1, 1))  # doctest: +SKIP
+    'IST'
+
+    >>> with set_timezone('US/Eastern'):
+    ...     tzlocal().tzname(datetime(2021, 1, 1))
+    ...
+    'EST'
+    """
+    import time
+
+    def setTZ(tz) -> None:
+        if tz is None:
+            try:
+                del os.environ["TZ"]
+            except KeyError:
+                pass
+        else:
+            os.environ["TZ"] = tz
+            time.tzset()
+
+    orig_tz = os.environ.get("TZ")
+    setTZ(tz)
+    try:
+        yield
+    finally:
+        setTZ(orig_tz)
+
+
+@contextmanager
+def ensure_clean(
+    filename=None, return_filelike: bool = False, **kwargs: Any
+) -> Generator[Any, None, None]:
+    """
+    Gets a temporary path and agrees to remove on close.
+
+    This implementation does not use tempfile.mkstemp to avoid having a file handle.
+    If the code using the returned path wants to delete the file itself, windows
+    requires that no program has a file handle to it.
+
+    Parameters
+    ----------
+    filename : str (optional)
+        suffix of the created file.
+    return_filelike : bool (default False)
+        if True, returns a file-like which is *always* cleaned. Necessary for
+        savefig and other functions which want to append extensions.
+    **kwargs
+        Additional keywords are passed to open().
+
+    """
+    folder = Path(tempfile.gettempdir())
+
+    if filename is None:
+        filename = ""
+    filename = str(uuid.uuid4()) + filename
+    path = folder / filename
+
+    path.touch()
+
+    handle_or_str: str | IO = str(path)
+    encoding = kwargs.pop("encoding", None)
+    if return_filelike:
+        kwargs.setdefault("mode", "w+b")
+        if encoding is None and "b" not in kwargs["mode"]:
+            encoding = "utf-8"
+        handle_or_str = open(path, encoding=encoding, **kwargs)
+
+    try:
+        yield handle_or_str
+    finally:
+        if not isinstance(handle_or_str, str):
+            handle_or_str.close()
+        if path.is_file():
+            path.unlink()
+
+
+@contextmanager
+def with_csv_dialect(name: str, **kwargs) -> Generator[None, None, None]:
+    """
+    Context manager to temporarily register a CSV dialect for parsing CSV.
+
+    Parameters
+    ----------
+    name : str
+        The name of the dialect.
+    kwargs : mapping
+        The parameters for the dialect.
+
+    Raises
+    ------
+    ValueError : the name of the dialect conflicts with a builtin one.
+
+    See Also
+    --------
+    csv : Python's CSV library.
+    """
+    import csv
+
+    _BUILTIN_DIALECTS = {"excel", "excel-tab", "unix"}
+
+    if name in _BUILTIN_DIALECTS:
+        raise ValueError("Cannot override builtin dialect.")
+
+    csv.register_dialect(name, **kwargs)
+    try:
+        yield
+    finally:
+        csv.unregister_dialect(name)
+
+
+@contextmanager
+def use_numexpr(use, min_elements=None) -> Generator[None, None, None]:
+    from pandas.core.computation import expressions as expr
+
+    if min_elements is None:
+        min_elements = expr._MIN_ELEMENTS
+
+    olduse = expr.USE_NUMEXPR
+    oldmin = expr._MIN_ELEMENTS
+    set_option("compute.use_numexpr", use)
+    expr._MIN_ELEMENTS = min_elements
+    try:
+        yield
+    finally:
+        expr._MIN_ELEMENTS = oldmin
+        set_option("compute.use_numexpr", olduse)
+
+
+def raises_chained_assignment_error(warn=True, extra_warnings=(), extra_match=()):
+    from pandas._testing import assert_produces_warning
+
+    if not warn:
+        from contextlib import nullcontext
+
+        return nullcontext()
+
+    if PYPY and not extra_warnings:
+        from contextlib import nullcontext
+
+        return nullcontext()
+    elif PYPY and extra_warnings:
+        return assert_produces_warning(
+            extra_warnings,
+            match="|".join(extra_match),
+        )
+    else:
+        if using_copy_on_write():
+            warning = ChainedAssignmentError
+            match = (
+                "A value is trying to be set on a copy of a DataFrame or Series "
+                "through chained assignment"
+            )
+        else:
+            warning = FutureWarning  # type: ignore[assignment]
+            # TODO update match
+            match = "ChainedAssignmentError"
+        if extra_warnings:
+            warning = (warning, *extra_warnings)  # type: ignore[assignment]
+        return assert_produces_warning(
+            warning,
+            match="|".join((match, *extra_match)),
+        )
+
+
+def assert_cow_warning(warn=True, match=None, **kwargs):
+    """
+    Assert that a warning is raised in the CoW warning mode.
+
+    Parameters
+    ----------
+    warn : bool, default True
+        By default, check that a warning is raised. Can be turned off by passing False.
+    match : str
+        The warning message to match against, if different from the default.
+    kwargs
+        Passed through to assert_produces_warning
+    """
+    from pandas._testing import assert_produces_warning
+
+    if not warn:
+        from contextlib import nullcontext
+
+        return nullcontext()
+
+    if not match:
+        match = "Setting a value on a view"
+
+    return assert_produces_warning(FutureWarning, match=match, **kwargs)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/arrays/__init__.py

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

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/errors/__init__.py

@@ -0,0 +1,850 @@
+"""
+Expose public exceptions & warnings
+"""
+from __future__ import annotations
+
+import ctypes
+
+from pandas._config.config import OptionError
+
+from pandas._libs.tslibs import (
+    OutOfBoundsDatetime,
+    OutOfBoundsTimedelta,
+)
+
+from pandas.util.version import InvalidVersion
+
+
+class IntCastingNaNError(ValueError):
+    """
+    Exception raised when converting (``astype``) an array with NaN to an integer type.
+
+    Examples
+    --------
+    >>> pd.DataFrame(np.array([[1, np.nan], [2, 3]]), dtype="i8")
+    Traceback (most recent call last):
+    IntCastingNaNError: Cannot convert non-finite values (NA or inf) to integer
+    """
+
+
+class NullFrequencyError(ValueError):
+    """
+    Exception raised when a ``freq`` cannot be null.
+
+    Particularly ``DatetimeIndex.shift``, ``TimedeltaIndex.shift``,
+    ``PeriodIndex.shift``.
+
+    Examples
+    --------
+    >>> df = pd.DatetimeIndex(["2011-01-01 10:00", "2011-01-01"], freq=None)
+    >>> df.shift(2)
+    Traceback (most recent call last):
+    NullFrequencyError: Cannot shift with no freq
+    """
+
+
+class PerformanceWarning(Warning):
+    """
+    Warning raised when there is a possible performance impact.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({"jim": [0, 0, 1, 1],
+    ...                    "joe": ["x", "x", "z", "y"],
+    ...                    "jolie": [1, 2, 3, 4]})
+    >>> df = df.set_index(["jim", "joe"])
+    >>> df
+              jolie
+    jim  joe
+    0    x    1
+         x    2
+    1    z    3
+         y    4
+    >>> df.loc[(1, 'z')]  # doctest: +SKIP
+    # PerformanceWarning: indexing past lexsort depth may impact performance.
+    df.loc[(1, 'z')]
+              jolie
+    jim  joe
+    1    z        3
+    """
+
+
+class UnsupportedFunctionCall(ValueError):
+    """
+    Exception raised when attempting to call a unsupported numpy function.
+
+    For example, ``np.cumsum(groupby_object)``.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({"A": [0, 0, 1, 1],
+    ...                    "B": ["x", "x", "z", "y"],
+    ...                    "C": [1, 2, 3, 4]}
+    ...                   )
+    >>> np.cumsum(df.groupby(["A"]))
+    Traceback (most recent call last):
+    UnsupportedFunctionCall: numpy operations are not valid with groupby.
+    Use .groupby(...).cumsum() instead
+    """
+
+
+class UnsortedIndexError(KeyError):
+    """
+    Error raised when slicing a MultiIndex which has not been lexsorted.
+
+    Subclass of `KeyError`.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({"cat": [0, 0, 1, 1],
+    ...                    "color": ["white", "white", "brown", "black"],
+    ...                    "lives": [4, 4, 3, 7]},
+    ...                   )
+    >>> df = df.set_index(["cat", "color"])
+    >>> df
+                lives
+    cat  color
+    0    white    4
+         white    4
+    1    brown    3
+         black    7
+    >>> df.loc[(0, "black"):(1, "white")]
+    Traceback (most recent call last):
+    UnsortedIndexError: 'Key length (2) was greater
+    than MultiIndex lexsort depth (1)'
+    """
+
+
+class ParserError(ValueError):
+    """
+    Exception that is raised by an error encountered in parsing file contents.
+
+    This is a generic error raised for errors encountered when functions like
+    `read_csv` or `read_html` are parsing contents of a file.
+
+    See Also
+    --------
+    read_csv : Read CSV (comma-separated) file into a DataFrame.
+    read_html : Read HTML table into a DataFrame.
+
+    Examples
+    --------
+    >>> data = '''a,b,c
+    ... cat,foo,bar
+    ... dog,foo,"baz'''
+    >>> from io import StringIO
+    >>> pd.read_csv(StringIO(data), skipfooter=1, engine='python')
+    Traceback (most recent call last):
+    ParserError: ',' expected after '"'. Error could possibly be due
+    to parsing errors in the skipped footer rows
+    """
+
+
+class DtypeWarning(Warning):
+    """
+    Warning raised when reading different dtypes in a column from a file.
+
+    Raised for a dtype incompatibility. This can happen whenever `read_csv`
+    or `read_table` encounter non-uniform dtypes in a column(s) of a given
+    CSV file.
+
+    See Also
+    --------
+    read_csv : Read CSV (comma-separated) file into a DataFrame.
+    read_table : Read general delimited file into a DataFrame.
+
+    Notes
+    -----
+    This warning is issued when dealing with larger files because the dtype
+    checking happens per chunk read.
+
+    Despite the warning, the CSV file is read with mixed types in a single
+    column which will be an object type. See the examples below to better
+    understand this issue.
+
+    Examples
+    --------
+    This example creates and reads a large CSV file with a column that contains
+    `int` and `str`.
+
+    >>> df = pd.DataFrame({'a': (['1'] * 100000 + ['X'] * 100000 +
+    ...                          ['1'] * 100000),
+    ...                    'b': ['b'] * 300000})  # doctest: +SKIP
+    >>> df.to_csv('test.csv', index=False)  # doctest: +SKIP
+    >>> df2 = pd.read_csv('test.csv')  # doctest: +SKIP
+    ... # DtypeWarning: Columns (0) have mixed types
+
+    Important to notice that ``df2`` will contain both `str` and `int` for the
+    same input, '1'.
+
+    >>> df2.iloc[262140, 0]  # doctest: +SKIP
+    '1'
+    >>> type(df2.iloc[262140, 0])  # doctest: +SKIP
+    <class 'str'>
+    >>> df2.iloc[262150, 0]  # doctest: +SKIP
+    1
+    >>> type(df2.iloc[262150, 0])  # doctest: +SKIP
+    <class 'int'>
+
+    One way to solve this issue is using the `dtype` parameter in the
+    `read_csv` and `read_table` functions to explicit the conversion:
+
+    >>> df2 = pd.read_csv('test.csv', sep=',', dtype={'a': str})  # doctest: +SKIP
+
+    No warning was issued.
+    """
+
+
+class EmptyDataError(ValueError):
+    """
+    Exception raised in ``pd.read_csv`` when empty data or header is encountered.
+
+    Examples
+    --------
+    >>> from io import StringIO
+    >>> empty = StringIO()
+    >>> pd.read_csv(empty)
+    Traceback (most recent call last):
+    EmptyDataError: No columns to parse from file
+    """
+
+
+class ParserWarning(Warning):
+    """
+    Warning raised when reading a file that doesn't use the default 'c' parser.
+
+    Raised by `pd.read_csv` and `pd.read_table` when it is necessary to change
+    parsers, generally from the default 'c' parser to 'python'.
+
+    It happens due to a lack of support or functionality for parsing a
+    particular attribute of a CSV file with the requested engine.
+
+    Currently, 'c' unsupported options include the following parameters:
+
+    1. `sep` other than a single character (e.g. regex separators)
+    2. `skipfooter` higher than 0
+    3. `sep=None` with `delim_whitespace=False`
+
+    The warning can be avoided by adding `engine='python'` as a parameter in
+    `pd.read_csv` and `pd.read_table` methods.
+
+    See Also
+    --------
+    pd.read_csv : Read CSV (comma-separated) file into DataFrame.
+    pd.read_table : Read general delimited file into DataFrame.
+
+    Examples
+    --------
+    Using a `sep` in `pd.read_csv` other than a single character:
+
+    >>> import io
+    >>> csv = '''a;b;c
+    ...           1;1,8
+    ...           1;2,1'''
+    >>> df = pd.read_csv(io.StringIO(csv), sep='[;,]')  # doctest: +SKIP
+    ... # ParserWarning: Falling back to the 'python' engine...
+
+    Adding `engine='python'` to `pd.read_csv` removes the Warning:
+
+    >>> df = pd.read_csv(io.StringIO(csv), sep='[;,]', engine='python')
+    """
+
+
+class MergeError(ValueError):
+    """
+    Exception raised when merging data.
+
+    Subclass of ``ValueError``.
+
+    Examples
+    --------
+    >>> left = pd.DataFrame({"a": ["a", "b", "b", "d"],
+    ...                     "b": ["cat", "dog", "weasel", "horse"]},
+    ...                     index=range(4))
+    >>> right = pd.DataFrame({"a": ["a", "b", "c", "d"],
+    ...                      "c": ["meow", "bark", "chirp", "nay"]},
+    ...                      index=range(4)).set_index("a")
+    >>> left.join(right, on="a", validate="one_to_one",)
+    Traceback (most recent call last):
+    MergeError: Merge keys are not unique in left dataset; not a one-to-one merge
+    """
+
+
+class AbstractMethodError(NotImplementedError):
+    """
+    Raise this error instead of NotImplementedError for abstract methods.
+
+    Examples
+    --------
+    >>> class Foo:
+    ...     @classmethod
+    ...     def classmethod(cls):
+    ...         raise pd.errors.AbstractMethodError(cls, methodtype="classmethod")
+    ...     def method(self):
+    ...         raise pd.errors.AbstractMethodError(self)
+    >>> test = Foo.classmethod()
+    Traceback (most recent call last):
+    AbstractMethodError: This classmethod must be defined in the concrete class Foo
+
+    >>> test2 = Foo().method()
+    Traceback (most recent call last):
+    AbstractMethodError: This classmethod must be defined in the concrete class Foo
+    """
+
+    def __init__(self, class_instance, methodtype: str = "method") -> None:
+        types = {"method", "classmethod", "staticmethod", "property"}
+        if methodtype not in types:
+            raise ValueError(
+                f"methodtype must be one of {methodtype}, got {types} instead."
+            )
+        self.methodtype = methodtype
+        self.class_instance = class_instance
+
+    def __str__(self) -> str:
+        if self.methodtype == "classmethod":
+            name = self.class_instance.__name__
+        else:
+            name = type(self.class_instance).__name__
+        return f"This {self.methodtype} must be defined in the concrete class {name}"
+
+
+class NumbaUtilError(Exception):
+    """
+    Error raised for unsupported Numba engine routines.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({"key": ["a", "a", "b", "b"], "data": [1, 2, 3, 4]},
+    ...                   columns=["key", "data"])
+    >>> def incorrect_function(x):
+    ...     return sum(x) * 2.7
+    >>> df.groupby("key").agg(incorrect_function, engine="numba")
+    Traceback (most recent call last):
+    NumbaUtilError: The first 2 arguments to incorrect_function
+    must be ['values', 'index']
+    """
+
+
+class DuplicateLabelError(ValueError):
+    """
+    Error raised when an operation would introduce duplicate labels.
+
+    Examples
+    --------
+    >>> s = pd.Series([0, 1, 2], index=['a', 'b', 'c']).set_flags(
+    ...     allows_duplicate_labels=False
+    ... )
+    >>> s.reindex(['a', 'a', 'b'])
+    Traceback (most recent call last):
+       ...
+    DuplicateLabelError: Index has duplicates.
+          positions
+    label
+    a        [0, 1]
+    """
+
+
+class InvalidIndexError(Exception):
+    """
+    Exception raised when attempting to use an invalid index key.
+
+    Examples
+    --------
+    >>> idx = pd.MultiIndex.from_product([["x", "y"], [0, 1]])
+    >>> df = pd.DataFrame([[1, 1, 2, 2],
+    ...                   [3, 3, 4, 4]], columns=idx)
+    >>> df
+        x       y
+        0   1   0   1
+    0   1   1   2   2
+    1   3   3   4   4
+    >>> df[:, 0]
+    Traceback (most recent call last):
+    InvalidIndexError: (slice(None, None, None), 0)
+    """
+
+
+class DataError(Exception):
+    """
+    Exceptionn raised when performing an operation on non-numerical data.
+
+    For example, calling ``ohlc`` on a non-numerical column or a function
+    on a rolling window.
+
+    Examples
+    --------
+    >>> ser = pd.Series(['a', 'b', 'c'])
+    >>> ser.rolling(2).sum()
+    Traceback (most recent call last):
+    DataError: No numeric types to aggregate
+    """
+
+
+class SpecificationError(Exception):
+    """
+    Exception raised by ``agg`` when the functions are ill-specified.
+
+    The exception raised in two scenarios.
+
+    The first way is calling ``agg`` on a
+    Dataframe or Series using a nested renamer (dict-of-dict).
+
+    The second way is calling ``agg`` on a Dataframe with duplicated functions
+    names without assigning column name.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({'A': [1, 1, 1, 2, 2],
+    ...                    'B': range(5),
+    ...                    'C': range(5)})
+    >>> df.groupby('A').B.agg({'foo': 'count'}) # doctest: +SKIP
+    ... # SpecificationError: nested renamer is not supported
+
+    >>> df.groupby('A').agg({'B': {'foo': ['sum', 'max']}}) # doctest: +SKIP
+    ... # SpecificationError: nested renamer is not supported
+
+    >>> df.groupby('A').agg(['min', 'min']) # doctest: +SKIP
+    ... # SpecificationError: nested renamer is not supported
+    """
+
+
+class SettingWithCopyError(ValueError):
+    """
+    Exception raised when trying to set on a copied slice from a ``DataFrame``.
+
+    The ``mode.chained_assignment`` needs to be set to set to 'raise.' This can
+    happen unintentionally when chained indexing.
+
+    For more information on evaluation order,
+    see :ref:`the user guide<indexing.evaluation_order>`.
+
+    For more information on view vs. copy,
+    see :ref:`the user guide<indexing.view_versus_copy>`.
+
+    Examples
+    --------
+    >>> pd.options.mode.chained_assignment = 'raise'
+    >>> df = pd.DataFrame({'A': [1, 1, 1, 2, 2]}, columns=['A'])
+    >>> df.loc[0:3]['A'] = 'a' # doctest: +SKIP
+    ... # SettingWithCopyError: A value is trying to be set on a copy of a...
+    """
+
+
+class SettingWithCopyWarning(Warning):
+    """
+    Warning raised when trying to set on a copied slice from a ``DataFrame``.
+
+    The ``mode.chained_assignment`` needs to be set to set to 'warn.'
+    'Warn' is the default option. This can happen unintentionally when
+    chained indexing.
+
+    For more information on evaluation order,
+    see :ref:`the user guide<indexing.evaluation_order>`.
+
+    For more information on view vs. copy,
+    see :ref:`the user guide<indexing.view_versus_copy>`.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({'A': [1, 1, 1, 2, 2]}, columns=['A'])
+    >>> df.loc[0:3]['A'] = 'a' # doctest: +SKIP
+    ... # SettingWithCopyWarning: A value is trying to be set on a copy of a...
+    """
+
+
+class ChainedAssignmentError(Warning):
+    """
+    Warning raised when trying to set using chained assignment.
+
+    When the ``mode.copy_on_write`` option is enabled, chained assignment can
+    never work. In such a situation, we are always setting into a temporary
+    object that is the result of an indexing operation (getitem), which under
+    Copy-on-Write always behaves as a copy. Thus, assigning through a chain
+    can never update the original Series or DataFrame.
+
+    For more information on view vs. copy,
+    see :ref:`the user guide<indexing.view_versus_copy>`.
+
+    Examples
+    --------
+    >>> pd.options.mode.copy_on_write = True
+    >>> df = pd.DataFrame({'A': [1, 1, 1, 2, 2]}, columns=['A'])
+    >>> df["A"][0:3] = 10 # doctest: +SKIP
+    ... # ChainedAssignmentError: ...
+    >>> pd.options.mode.copy_on_write = False
+    """
+
+
+_chained_assignment_msg = (
+    "A value is trying to be set on a copy of a DataFrame or Series "
+    "through chained assignment.\n"
+    "When using the Copy-on-Write mode, such chained assignment never works "
+    "to update the original DataFrame or Series, because the intermediate "
+    "object on which we are setting values always behaves as a copy.\n\n"
+    "Try using '.loc[row_indexer, col_indexer] = value' instead, to perform "
+    "the assignment in a single step.\n\n"
+    "See the caveats in the documentation: "
+    "https://pandas.pydata.org/pandas-docs/stable/user_guide/"
+    "indexing.html#returning-a-view-versus-a-copy"
+)
+
+
+_chained_assignment_method_msg = (
+    "A value is trying to be set on a copy of a DataFrame or Series "
+    "through chained assignment using an inplace method.\n"
+    "When using the Copy-on-Write mode, such inplace method never works "
+    "to update the original DataFrame or Series, because the intermediate "
+    "object on which we are setting values always behaves as a copy.\n\n"
+    "For example, when doing 'df[col].method(value, inplace=True)', try "
+    "using 'df.method({col: value}, inplace=True)' instead, to perform "
+    "the operation inplace on the original object.\n\n"
+)
+
+
+_chained_assignment_warning_msg = (
+    "ChainedAssignmentError: behaviour will change in pandas 3.0!\n"
+    "You are setting values through chained assignment. Currently this works "
+    "in certain cases, but when using Copy-on-Write (which will become the "
+    "default behaviour in pandas 3.0) this will never work to update the "
+    "original DataFrame or Series, because the intermediate object on which "
+    "we are setting values will behave as a copy.\n"
+    "A typical example is when you are setting values in a column of a "
+    "DataFrame, like:\n\n"
+    'df["col"][row_indexer] = value\n\n'
+    'Use `df.loc[row_indexer, "col"] = values` instead, to perform the '
+    "assignment in a single step and ensure this keeps updating the original `df`.\n\n"
+    "See the caveats in the documentation: "
+    "https://pandas.pydata.org/pandas-docs/stable/user_guide/"
+    "indexing.html#returning-a-view-versus-a-copy\n"
+)
+
+
+_chained_assignment_warning_method_msg = (
+    "A value is trying to be set on a copy of a DataFrame or Series "
+    "through chained assignment using an inplace method.\n"
+    "The behavior will change in pandas 3.0. This inplace method will "
+    "never work because the intermediate object on which we are setting "
+    "values always behaves as a copy.\n\n"
+    "For example, when doing 'df[col].method(value, inplace=True)', try "
+    "using 'df.method({col: value}, inplace=True)' or "
+    "df[col] = df[col].method(value) instead, to perform "
+    "the operation inplace on the original object.\n\n"
+)
+
+
+def _check_cacher(obj):
+    # This is a mess, selection paths that return a view set the _cacher attribute
+    # on the Series; most of them also set _item_cache which adds 1 to our relevant
+    # reference count, but iloc does not, so we have to check if we are actually
+    # in the item cache
+    if hasattr(obj, "_cacher"):
+        parent = obj._cacher[1]()
+        # parent could be dead
+        if parent is None:
+            return False
+        if hasattr(parent, "_item_cache"):
+            if obj._cacher[0] in parent._item_cache:
+                # Check if we are actually the item from item_cache, iloc creates a
+                # new object
+                return obj is parent._item_cache[obj._cacher[0]]
+    return False
+
+
+class NumExprClobberingError(NameError):
+    """
+    Exception raised when trying to use a built-in numexpr name as a variable name.
+
+    ``eval`` or ``query`` will throw the error if the engine is set
+    to 'numexpr'. 'numexpr' is the default engine value for these methods if the
+    numexpr package is installed.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({'abs': [1, 1, 1]})
+    >>> df.query("abs > 2") # doctest: +SKIP
+    ... # NumExprClobberingError: Variables in expression "(abs) > (2)" overlap...
+    >>> sin, a = 1, 2
+    >>> pd.eval("sin + a", engine='numexpr') # doctest: +SKIP
+    ... # NumExprClobberingError: Variables in expression "(sin) + (a)" overlap...
+    """
+
+
+class UndefinedVariableError(NameError):
+    """
+    Exception raised by ``query`` or ``eval`` when using an undefined variable name.
+
+    It will also specify whether the undefined variable is local or not.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({'A': [1, 1, 1]})
+    >>> df.query("A > x") # doctest: +SKIP
+    ... # UndefinedVariableError: name 'x' is not defined
+    >>> df.query("A > @y") # doctest: +SKIP
+    ... # UndefinedVariableError: local variable 'y' is not defined
+    >>> pd.eval('x + 1') # doctest: +SKIP
+    ... # UndefinedVariableError: name 'x' is not defined
+    """
+
+    def __init__(self, name: str, is_local: bool | None = None) -> None:
+        base_msg = f"{repr(name)} is not defined"
+        if is_local:
+            msg = f"local variable {base_msg}"
+        else:
+            msg = f"name {base_msg}"
+        super().__init__(msg)
+
+
+class IndexingError(Exception):
+    """
+    Exception is raised when trying to index and there is a mismatch in dimensions.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({'A': [1, 1, 1]})
+    >>> df.loc[..., ..., 'A'] # doctest: +SKIP
+    ... # IndexingError: indexer may only contain one '...' entry
+    >>> df = pd.DataFrame({'A': [1, 1, 1]})
+    >>> df.loc[1, ..., ...] # doctest: +SKIP
+    ... # IndexingError: Too many indexers
+    >>> df[pd.Series([True], dtype=bool)] # doctest: +SKIP
+    ... # IndexingError: Unalignable boolean Series provided as indexer...
+    >>> s = pd.Series(range(2),
+    ...               index = pd.MultiIndex.from_product([["a", "b"], ["c"]]))
+    >>> s.loc["a", "c", "d"] # doctest: +SKIP
+    ... # IndexingError: Too many indexers
+    """
+
+
+class PyperclipException(RuntimeError):
+    """
+    Exception raised when clipboard functionality is unsupported.
+
+    Raised by ``to_clipboard()`` and ``read_clipboard()``.
+    """
+
+
+class PyperclipWindowsException(PyperclipException):
+    """
+    Exception raised when clipboard functionality is unsupported by Windows.
+
+    Access to the clipboard handle would be denied due to some other
+    window process is accessing it.
+    """
+
+    def __init__(self, message: str) -> None:
+        # attr only exists on Windows, so typing fails on other platforms
+        message += f" ({ctypes.WinError()})"  # type: ignore[attr-defined]
+        super().__init__(message)
+
+
+class CSSWarning(UserWarning):
+    """
+    Warning is raised when converting css styling fails.
+
+    This can be due to the styling not having an equivalent value or because the
+    styling isn't properly formatted.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({'A': [1, 1, 1]})
+    >>> df.style.applymap(
+    ...     lambda x: 'background-color: blueGreenRed;'
+    ... ).to_excel('styled.xlsx')  # doctest: +SKIP
+    CSSWarning: Unhandled color format: 'blueGreenRed'
+    >>> df.style.applymap(
+    ...     lambda x: 'border: 1px solid red red;'
+    ... ).to_excel('styled.xlsx')  # doctest: +SKIP
+    CSSWarning: Unhandled color format: 'blueGreenRed'
+    """
+
+
+class PossibleDataLossError(Exception):
+    """
+    Exception raised when trying to open a HDFStore file when already opened.
+
+    Examples
+    --------
+    >>> store = pd.HDFStore('my-store', 'a') # doctest: +SKIP
+    >>> store.open("w") # doctest: +SKIP
+    ... # PossibleDataLossError: Re-opening the file [my-store] with mode [a]...
+    """
+
+
+class ClosedFileError(Exception):
+    """
+    Exception is raised when trying to perform an operation on a closed HDFStore file.
+
+    Examples
+    --------
+    >>> store = pd.HDFStore('my-store', 'a') # doctest: +SKIP
+    >>> store.close() # doctest: +SKIP
+    >>> store.keys() # doctest: +SKIP
+    ... # ClosedFileError: my-store file is not open!
+    """
+
+
+class IncompatibilityWarning(Warning):
+    """
+    Warning raised when trying to use where criteria on an incompatible HDF5 file.
+    """
+
+
+class AttributeConflictWarning(Warning):
+    """
+    Warning raised when index attributes conflict when using HDFStore.
+
+    Occurs when attempting to append an index with a different
+    name than the existing index on an HDFStore or attempting to append an index with a
+    different frequency than the existing index on an HDFStore.
+
+    Examples
+    --------
+    >>> idx1 = pd.Index(['a', 'b'], name='name1')
+    >>> df1 = pd.DataFrame([[1, 2], [3, 4]], index=idx1)
+    >>> df1.to_hdf('file', 'data', 'w', append=True)  # doctest: +SKIP
+    >>> idx2 = pd.Index(['c', 'd'], name='name2')
+    >>> df2 = pd.DataFrame([[5, 6], [7, 8]], index=idx2)
+    >>> df2.to_hdf('file', 'data', 'a', append=True)  # doctest: +SKIP
+    AttributeConflictWarning: the [index_name] attribute of the existing index is
+    [name1] which conflicts with the new [name2]...
+    """
+
+
+class DatabaseError(OSError):
+    """
+    Error is raised when executing sql with bad syntax or sql that throws an error.
+
+    Examples
+    --------
+    >>> from sqlite3 import connect
+    >>> conn = connect(':memory:')
+    >>> pd.read_sql('select * test', conn) # doctest: +SKIP
+    ... # DatabaseError: Execution failed on sql 'test': near "test": syntax error
+    """
+
+
+class PossiblePrecisionLoss(Warning):
+    """
+    Warning raised by to_stata on a column with a value outside or equal to int64.
+
+    When the column value is outside or equal to the int64 value the column is
+    converted to a float64 dtype.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({"s": pd.Series([1, 2**53], dtype=np.int64)})
+    >>> df.to_stata('test') # doctest: +SKIP
+    ... # PossiblePrecisionLoss: Column converted from int64 to float64...
+    """
+
+
+class ValueLabelTypeMismatch(Warning):
+    """
+    Warning raised by to_stata on a category column that contains non-string values.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({"categories": pd.Series(["a", 2], dtype="category")})
+    >>> df.to_stata('test') # doctest: +SKIP
+    ... # ValueLabelTypeMismatch: Stata value labels (pandas categories) must be str...
+    """
+
+
+class InvalidColumnName(Warning):
+    """
+    Warning raised by to_stata the column contains a non-valid stata name.
+
+    Because the column name is an invalid Stata variable, the name needs to be
+    converted.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({"0categories": pd.Series([2, 2])})
+    >>> df.to_stata('test') # doctest: +SKIP
+    ... # InvalidColumnName: Not all pandas column names were valid Stata variable...
+    """
+
+
+class CategoricalConversionWarning(Warning):
+    """
+    Warning is raised when reading a partial labeled Stata file using a iterator.
+
+    Examples
+    --------
+    >>> from pandas.io.stata import StataReader
+    >>> with StataReader('dta_file', chunksize=2) as reader: # doctest: +SKIP
+    ...   for i, block in enumerate(reader):
+    ...      print(i, block)
+    ... # CategoricalConversionWarning: One or more series with value labels...
+    """
+
+
+class LossySetitemError(Exception):
+    """
+    Raised when trying to do a __setitem__ on an np.ndarray that is not lossless.
+
+    Notes
+    -----
+    This is an internal error.
+    """
+
+
+class NoBufferPresent(Exception):
+    """
+    Exception is raised in _get_data_buffer to signal that there is no requested buffer.
+    """
+
+
+class InvalidComparison(Exception):
+    """
+    Exception is raised by _validate_comparison_value to indicate an invalid comparison.
+
+    Notes
+    -----
+    This is an internal error.
+    """
+
+
+__all__ = [
+    "AbstractMethodError",
+    "AttributeConflictWarning",
+    "CategoricalConversionWarning",
+    "ClosedFileError",
+    "CSSWarning",
+    "DatabaseError",
+    "DataError",
+    "DtypeWarning",
+    "DuplicateLabelError",
+    "EmptyDataError",
+    "IncompatibilityWarning",
+    "IntCastingNaNError",
+    "InvalidColumnName",
+    "InvalidComparison",
+    "InvalidIndexError",
+    "InvalidVersion",
+    "IndexingError",
+    "LossySetitemError",
+    "MergeError",
+    "NoBufferPresent",
+    "NullFrequencyError",
+    "NumbaUtilError",
+    "NumExprClobberingError",
+    "OptionError",
+    "OutOfBoundsDatetime",
+    "OutOfBoundsTimedelta",
+    "ParserError",
+    "ParserWarning",
+    "PerformanceWarning",
+    "PossibleDataLossError",
+    "PossiblePrecisionLoss",
+    "PyperclipException",
+    "PyperclipWindowsException",
+    "SettingWithCopyError",
+    "SettingWithCopyWarning",
+    "SpecificationError",
+    "UndefinedVariableError",
+    "UnsortedIndexError",
+    "UnsupportedFunctionCall",
+    "ValueLabelTypeMismatch",
+]

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/io/feather_format.py

@@ -0,0 +1,143 @@
+""" feather-format compat """
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+
+from pandas._config import using_pyarrow_string_dtype
+
+from pandas._libs import lib
+from pandas.compat._optional import import_optional_dependency
+from pandas.util._decorators import doc
+from pandas.util._validators import check_dtype_backend
+
+import pandas as pd
+from pandas.core.api import DataFrame
+from pandas.core.shared_docs import _shared_docs
+
+from pandas.io._util import arrow_string_types_mapper
+from pandas.io.common import get_handle
+
+if TYPE_CHECKING:
+    from collections.abc import (
+        Hashable,
+        Sequence,
+    )
+
+    from pandas._typing import (
+        DtypeBackend,
+        FilePath,
+        ReadBuffer,
+        StorageOptions,
+        WriteBuffer,
+    )
+
+
+@doc(storage_options=_shared_docs["storage_options"])
+def to_feather(
+    df: DataFrame,
+    path: FilePath | WriteBuffer[bytes],
+    storage_options: StorageOptions | None = None,
+    **kwargs: Any,
+) -> None:
+    """
+    Write a DataFrame to the binary Feather format.
+
+    Parameters
+    ----------
+    df : DataFrame
+    path : str, path object, or file-like object
+    {storage_options}
+    **kwargs :
+        Additional keywords passed to `pyarrow.feather.write_feather`.
+
+    """
+    import_optional_dependency("pyarrow")
+    from pyarrow import feather
+
+    if not isinstance(df, DataFrame):
+        raise ValueError("feather only support IO with DataFrames")
+
+    with get_handle(
+        path, "wb", storage_options=storage_options, is_text=False
+    ) as handles:
+        feather.write_feather(df, handles.handle, **kwargs)
+
+
+@doc(storage_options=_shared_docs["storage_options"])
+def read_feather(
+    path: FilePath | ReadBuffer[bytes],
+    columns: Sequence[Hashable] | None = None,
+    use_threads: bool = True,
+    storage_options: StorageOptions | None = None,
+    dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
+) -> DataFrame:
+    """
+    Load a feather-format object from the file path.
+
+    Parameters
+    ----------
+    path : str, path object, or file-like object
+        String, path object (implementing ``os.PathLike[str]``), or file-like
+        object implementing a binary ``read()`` function. The string could be a URL.
+        Valid URL schemes include http, ftp, s3, and file. For file URLs, a host is
+        expected. A local file could be: ``file://localhost/path/to/table.feather``.
+    columns : sequence, default None
+        If not provided, all columns are read.
+    use_threads : bool, default True
+        Whether to parallelize reading using multiple threads.
+    {storage_options}
+
+    dtype_backend : {{'numpy_nullable', 'pyarrow'}}, default 'numpy_nullable'
+        Back-end data type applied to the resultant :class:`DataFrame`
+        (still experimental). Behaviour is as follows:
+
+        * ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame`
+          (default).
+        * ``"pyarrow"``: returns pyarrow-backed nullable :class:`ArrowDtype`
+          DataFrame.
+
+        .. versionadded:: 2.0
+
+    Returns
+    -------
+    type of object stored in file
+
+    Examples
+    --------
+    >>> df = pd.read_feather("path/to/file.feather")  # doctest: +SKIP
+    """
+    import_optional_dependency("pyarrow")
+    from pyarrow import feather
+
+    # import utils to register the pyarrow extension types
+    import pandas.core.arrays.arrow.extension_types  # pyright: ignore[reportUnusedImport] # noqa: F401
+
+    check_dtype_backend(dtype_backend)
+
+    with get_handle(
+        path, "rb", storage_options=storage_options, is_text=False
+    ) as handles:
+        if dtype_backend is lib.no_default and not using_pyarrow_string_dtype():
+            return feather.read_feather(
+                handles.handle, columns=columns, use_threads=bool(use_threads)
+            )
+
+        pa_table = feather.read_table(
+            handles.handle, columns=columns, use_threads=bool(use_threads)
+        )
+
+        if dtype_backend == "numpy_nullable":
+            from pandas.io._util import _arrow_dtype_mapping
+
+            return pa_table.to_pandas(types_mapper=_arrow_dtype_mapping().get)
+
+        elif dtype_backend == "pyarrow":
+            return pa_table.to_pandas(types_mapper=pd.ArrowDtype)
+
+        elif using_pyarrow_string_dtype():
+            return pa_table.to_pandas(types_mapper=arrow_string_types_mapper())
+        else:
+            raise NotImplementedError

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/io/gbq.py

@@ -0,0 +1,255 @@
+""" Google BigQuery support """
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+import warnings
+
+from pandas.compat._optional import import_optional_dependency
+from pandas.util._exceptions import find_stack_level
+
+if TYPE_CHECKING:
+    from google.auth.credentials import Credentials
+
+    from pandas import DataFrame
+
+
+def _try_import():
+    # since pandas is a dependency of pandas-gbq
+    # we need to import on first use
+    msg = (
+        "pandas-gbq is required to load data from Google BigQuery. "
+        "See the docs: https://pandas-gbq.readthedocs.io."
+    )
+    pandas_gbq = import_optional_dependency("pandas_gbq", extra=msg)
+    return pandas_gbq
+
+
+def read_gbq(
+    query: str,
+    project_id: str | None = None,
+    index_col: str | None = None,
+    col_order: list[str] | None = None,
+    reauth: bool = False,
+    auth_local_webserver: bool = True,
+    dialect: str | None = None,
+    location: str | None = None,
+    configuration: dict[str, Any] | None = None,
+    credentials: Credentials | None = None,
+    use_bqstorage_api: bool | None = None,
+    max_results: int | None = None,
+    progress_bar_type: str | None = None,
+) -> DataFrame:
+    """
+    Load data from Google BigQuery.
+
+    .. deprecated:: 2.2.0
+
+       Please use ``pandas_gbq.read_gbq`` instead.
+
+    This function requires the `pandas-gbq package
+    <https://pandas-gbq.readthedocs.io>`__.
+
+    See the `How to authenticate with Google BigQuery
+    <https://pandas-gbq.readthedocs.io/en/latest/howto/authentication.html>`__
+    guide for authentication instructions.
+
+    Parameters
+    ----------
+    query : str
+        SQL-Like Query to return data values.
+    project_id : str, optional
+        Google BigQuery Account project ID. Optional when available from
+        the environment.
+    index_col : str, optional
+        Name of result column to use for index in results DataFrame.
+    col_order : list(str), optional
+        List of BigQuery column names in the desired order for results
+        DataFrame.
+    reauth : bool, default False
+        Force Google BigQuery to re-authenticate the user. This is useful
+        if multiple accounts are used.
+    auth_local_webserver : bool, default True
+        Use the `local webserver flow`_ instead of the `console flow`_
+        when getting user credentials.
+
+        .. _local webserver flow:
+            https://google-auth-oauthlib.readthedocs.io/en/latest/reference/google_auth_oauthlib.flow.html#google_auth_oauthlib.flow.InstalledAppFlow.run_local_server
+        .. _console flow:
+            https://google-auth-oauthlib.readthedocs.io/en/latest/reference/google_auth_oauthlib.flow.html#google_auth_oauthlib.flow.InstalledAppFlow.run_console
+
+        *New in version 0.2.0 of pandas-gbq*.
+
+        .. versionchanged:: 1.5.0
+           Default value is changed to ``True``. Google has deprecated the
+           ``auth_local_webserver = False`` `"out of band" (copy-paste)
+           flow
+           <https://developers.googleblog.com/2022/02/making-oauth-flows-safer.html?m=1#disallowed-oob>`_.
+    dialect : str, default 'legacy'
+        Note: The default value is changing to 'standard' in a future version.
+
+        SQL syntax dialect to use. Value can be one of:
+
+        ``'legacy'``
+            Use BigQuery's legacy SQL dialect. For more information see
+            `BigQuery Legacy SQL Reference
+            <https://cloud.google.com/bigquery/docs/reference/legacy-sql>`__.
+        ``'standard'``
+            Use BigQuery's standard SQL, which is
+            compliant with the SQL 2011 standard. For more information
+            see `BigQuery Standard SQL Reference
+            <https://cloud.google.com/bigquery/docs/reference/standard-sql/>`__.
+    location : str, optional
+        Location where the query job should run. See the `BigQuery locations
+        documentation
+        <https://cloud.google.com/bigquery/docs/dataset-locations>`__ for a
+        list of available locations. The location must match that of any
+        datasets used in the query.
+
+        *New in version 0.5.0 of pandas-gbq*.
+    configuration : dict, optional
+        Query config parameters for job processing.
+        For example:
+
+            configuration = {'query': {'useQueryCache': False}}
+
+        For more information see `BigQuery REST API Reference
+        <https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs#configuration.query>`__.
+    credentials : google.auth.credentials.Credentials, optional
+        Credentials for accessing Google APIs. Use this parameter to override
+        default credentials, such as to use Compute Engine
+        :class:`google.auth.compute_engine.Credentials` or Service Account
+        :class:`google.oauth2.service_account.Credentials` directly.
+
+        *New in version 0.8.0 of pandas-gbq*.
+    use_bqstorage_api : bool, default False
+        Use the `BigQuery Storage API
+        <https://cloud.google.com/bigquery/docs/reference/storage/>`__ to
+        download query results quickly, but at an increased cost. To use this
+        API, first `enable it in the Cloud Console
+        <https://console.cloud.google.com/apis/library/bigquerystorage.googleapis.com>`__.
+        You must also have the `bigquery.readsessions.create
+        <https://cloud.google.com/bigquery/docs/access-control#roles>`__
+        permission on the project you are billing queries to.
+
+        This feature requires version 0.10.0 or later of the ``pandas-gbq``
+        package. It also requires the ``google-cloud-bigquery-storage`` and
+        ``fastavro`` packages.
+
+    max_results : int, optional
+        If set, limit the maximum number of rows to fetch from the query
+        results.
+
+    progress_bar_type : Optional, str
+        If set, use the `tqdm <https://tqdm.github.io/>`__ library to
+        display a progress bar while the data downloads. Install the
+        ``tqdm`` package to use this feature.
+
+        Possible values of ``progress_bar_type`` include:
+
+        ``None``
+            No progress bar.
+        ``'tqdm'``
+            Use the :func:`tqdm.tqdm` function to print a progress bar
+            to :data:`sys.stderr`.
+        ``'tqdm_notebook'``
+            Use the :func:`tqdm.tqdm_notebook` function to display a
+            progress bar as a Jupyter notebook widget.
+        ``'tqdm_gui'``
+            Use the :func:`tqdm.tqdm_gui` function to display a
+            progress bar as a graphical dialog box.
+
+    Returns
+    -------
+    df: DataFrame
+        DataFrame representing results of query.
+
+    See Also
+    --------
+    pandas_gbq.read_gbq : This function in the pandas-gbq library.
+    DataFrame.to_gbq : Write a DataFrame to Google BigQuery.
+
+    Examples
+    --------
+    Example taken from `Google BigQuery documentation
+    <https://cloud.google.com/bigquery/docs/pandas-gbq-migration>`_
+
+    >>> sql = "SELECT name FROM table_name WHERE state = 'TX' LIMIT 100;"
+    >>> df = pd.read_gbq(sql, dialect="standard")  # doctest: +SKIP
+    >>> project_id = "your-project-id"  # doctest: +SKIP
+    >>> df = pd.read_gbq(sql,
+    ...                  project_id=project_id,
+    ...                  dialect="standard"
+    ...                  )  # doctest: +SKIP
+    """
+    warnings.warn(
+        "read_gbq is deprecated and will be removed in a future version. "
+        "Please use pandas_gbq.read_gbq instead: "
+        "https://pandas-gbq.readthedocs.io/en/latest/api.html#pandas_gbq.read_gbq",
+        FutureWarning,
+        stacklevel=find_stack_level(),
+    )
+    pandas_gbq = _try_import()
+
+    kwargs: dict[str, str | bool | int | None] = {}
+
+    # START: new kwargs.  Don't populate unless explicitly set.
+    if use_bqstorage_api is not None:
+        kwargs["use_bqstorage_api"] = use_bqstorage_api
+    if max_results is not None:
+        kwargs["max_results"] = max_results
+
+    kwargs["progress_bar_type"] = progress_bar_type
+    # END: new kwargs
+
+    return pandas_gbq.read_gbq(
+        query,
+        project_id=project_id,
+        index_col=index_col,
+        col_order=col_order,
+        reauth=reauth,
+        auth_local_webserver=auth_local_webserver,
+        dialect=dialect,
+        location=location,
+        configuration=configuration,
+        credentials=credentials,
+        **kwargs,
+    )
+
+
+def to_gbq(
+    dataframe: DataFrame,
+    destination_table: str,
+    project_id: str | None = None,
+    chunksize: int | None = None,
+    reauth: bool = False,
+    if_exists: str = "fail",
+    auth_local_webserver: bool = True,
+    table_schema: list[dict[str, str]] | None = None,
+    location: str | None = None,
+    progress_bar: bool = True,
+    credentials: Credentials | None = None,
+) -> None:
+    warnings.warn(
+        "to_gbq is deprecated and will be removed in a future version. "
+        "Please use pandas_gbq.to_gbq instead: "
+        "https://pandas-gbq.readthedocs.io/en/latest/api.html#pandas_gbq.to_gbq",
+        FutureWarning,
+        stacklevel=find_stack_level(),
+    )
+    pandas_gbq = _try_import()
+    pandas_gbq.to_gbq(
+        dataframe,
+        destination_table,
+        project_id=project_id,
+        chunksize=chunksize,
+        reauth=reauth,
+        if_exists=if_exists,
+        auth_local_webserver=auth_local_webserver,
+        table_schema=table_schema,
+        location=location,
+        progress_bar=progress_bar,
+        credentials=credentials,
+    )

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/io/html.py

@@ -0,0 +1,1259 @@
+"""
+:mod:`pandas.io.html` is a module containing functionality for dealing with
+HTML IO.
+
+"""
+
+from __future__ import annotations
+
+from collections import abc
+import numbers
+import re
+from re import Pattern
+from typing import (
+    TYPE_CHECKING,
+    Literal,
+    cast,
+)
+import warnings
+
+from pandas._libs import lib
+from pandas.compat._optional import import_optional_dependency
+from pandas.errors import (
+    AbstractMethodError,
+    EmptyDataError,
+)
+from pandas.util._decorators import doc
+from pandas.util._exceptions import find_stack_level
+from pandas.util._validators import check_dtype_backend
+
+from pandas.core.dtypes.common import is_list_like
+
+from pandas import isna
+from pandas.core.indexes.base import Index
+from pandas.core.indexes.multi import MultiIndex
+from pandas.core.series import Series
+from pandas.core.shared_docs import _shared_docs
+
+from pandas.io.common import (
+    file_exists,
+    get_handle,
+    is_file_like,
+    is_fsspec_url,
+    is_url,
+    stringify_path,
+    validate_header_arg,
+)
+from pandas.io.formats.printing import pprint_thing
+from pandas.io.parsers import TextParser
+
+if TYPE_CHECKING:
+    from collections.abc import (
+        Iterable,
+        Sequence,
+    )
+
+    from pandas._typing import (
+        BaseBuffer,
+        DtypeBackend,
+        FilePath,
+        HTMLFlavors,
+        ReadBuffer,
+        StorageOptions,
+    )
+
+    from pandas import DataFrame
+
+#############
+# READ HTML #
+#############
+_RE_WHITESPACE = re.compile(r"[\r\n]+|\s{2,}")
+
+
+def _remove_whitespace(s: str, regex: Pattern = _RE_WHITESPACE) -> str:
+    """
+    Replace extra whitespace inside of a string with a single space.
+
+    Parameters
+    ----------
+    s : str or unicode
+        The string from which to remove extra whitespace.
+    regex : re.Pattern
+        The regular expression to use to remove extra whitespace.
+
+    Returns
+    -------
+    subd : str or unicode
+        `s` with all extra whitespace replaced with a single space.
+    """
+    return regex.sub(" ", s.strip())
+
+
+def _get_skiprows(skiprows: int | Sequence[int] | slice | None) -> int | Sequence[int]:
+    """
+    Get an iterator given an integer, slice or container.
+
+    Parameters
+    ----------
+    skiprows : int, slice, container
+        The iterator to use to skip rows; can also be a slice.
+
+    Raises
+    ------
+    TypeError
+        * If `skiprows` is not a slice, integer, or Container
+
+    Returns
+    -------
+    it : iterable
+        A proper iterator to use to skip rows of a DataFrame.
+    """
+    if isinstance(skiprows, slice):
+        start, step = skiprows.start or 0, skiprows.step or 1
+        return list(range(start, skiprows.stop, step))
+    elif isinstance(skiprows, numbers.Integral) or is_list_like(skiprows):
+        return cast("int | Sequence[int]", skiprows)
+    elif skiprows is None:
+        return 0
+    raise TypeError(f"{type(skiprows).__name__} is not a valid type for skipping rows")
+
+
+def _read(
+    obj: FilePath | BaseBuffer,
+    encoding: str | None,
+    storage_options: StorageOptions | None,
+) -> str | bytes:
+    """
+    Try to read from a url, file or string.
+
+    Parameters
+    ----------
+    obj : str, unicode, path object, or file-like object
+
+    Returns
+    -------
+    raw_text : str
+    """
+    text: str | bytes
+    if (
+        is_url(obj)
+        or hasattr(obj, "read")
+        or (isinstance(obj, str) and file_exists(obj))
+    ):
+        with get_handle(
+            obj, "r", encoding=encoding, storage_options=storage_options
+        ) as handles:
+            text = handles.handle.read()
+    elif isinstance(obj, (str, bytes)):
+        text = obj
+    else:
+        raise TypeError(f"Cannot read object of type '{type(obj).__name__}'")
+    return text
+
+
+class _HtmlFrameParser:
+    """
+    Base class for parsers that parse HTML into DataFrames.
+
+    Parameters
+    ----------
+    io : str or file-like
+        This can be either a string of raw HTML, a valid URL using the HTTP,
+        FTP, or FILE protocols or a file-like object.
+
+    match : str or regex
+        The text to match in the document.
+
+    attrs : dict
+        List of HTML <table> element attributes to match.
+
+    encoding : str
+        Encoding to be used by parser
+
+    displayed_only : bool
+        Whether or not items with "display:none" should be ignored
+
+    extract_links : {None, "all", "header", "body", "footer"}
+        Table elements in the specified section(s) with <a> tags will have their
+        href extracted.
+
+        .. versionadded:: 1.5.0
+
+    Attributes
+    ----------
+    io : str or file-like
+        raw HTML, URL, or file-like object
+
+    match : regex
+        The text to match in the raw HTML
+
+    attrs : dict-like
+        A dictionary of valid table attributes to use to search for table
+        elements.
+
+    encoding : str
+        Encoding to be used by parser
+
+    displayed_only : bool
+        Whether or not items with "display:none" should be ignored
+
+    extract_links : {None, "all", "header", "body", "footer"}
+        Table elements in the specified section(s) with <a> tags will have their
+        href extracted.
+
+        .. versionadded:: 1.5.0
+
+    Notes
+    -----
+    To subclass this class effectively you must override the following methods:
+        * :func:`_build_doc`
+        * :func:`_attr_getter`
+        * :func:`_href_getter`
+        * :func:`_text_getter`
+        * :func:`_parse_td`
+        * :func:`_parse_thead_tr`
+        * :func:`_parse_tbody_tr`
+        * :func:`_parse_tfoot_tr`
+        * :func:`_parse_tables`
+        * :func:`_equals_tag`
+    See each method's respective documentation for details on their
+    functionality.
+    """
+
+    def __init__(
+        self,
+        io: FilePath | ReadBuffer[str] | ReadBuffer[bytes],
+        match: str | Pattern,
+        attrs: dict[str, str] | None,
+        encoding: str,
+        displayed_only: bool,
+        extract_links: Literal[None, "header", "footer", "body", "all"],
+        storage_options: StorageOptions = None,
+    ) -> None:
+        self.io = io
+        self.match = match
+        self.attrs = attrs
+        self.encoding = encoding
+        self.displayed_only = displayed_only
+        self.extract_links = extract_links
+        self.storage_options = storage_options
+
+    def parse_tables(self):
+        """
+        Parse and return all tables from the DOM.
+
+        Returns
+        -------
+        list of parsed (header, body, footer) tuples from tables.
+        """
+        tables = self._parse_tables(self._build_doc(), self.match, self.attrs)
+        return (self._parse_thead_tbody_tfoot(table) for table in tables)
+
+    def _attr_getter(self, obj, attr):
+        """
+        Return the attribute value of an individual DOM node.
+
+        Parameters
+        ----------
+        obj : node-like
+            A DOM node.
+
+        attr : str or unicode
+            The attribute, such as "colspan"
+
+        Returns
+        -------
+        str or unicode
+            The attribute value.
+        """
+        # Both lxml and BeautifulSoup have the same implementation:
+        return obj.get(attr)
+
+    def _href_getter(self, obj) -> str | None:
+        """
+        Return a href if the DOM node contains a child <a> or None.
+
+        Parameters
+        ----------
+        obj : node-like
+            A DOM node.
+
+        Returns
+        -------
+        href : str or unicode
+            The href from the <a> child of the DOM node.
+        """
+        raise AbstractMethodError(self)
+
+    def _text_getter(self, obj):
+        """
+        Return the text of an individual DOM node.
+
+        Parameters
+        ----------
+        obj : node-like
+            A DOM node.
+
+        Returns
+        -------
+        text : str or unicode
+            The text from an individual DOM node.
+        """
+        raise AbstractMethodError(self)
+
+    def _parse_td(self, obj):
+        """
+        Return the td elements from a row element.
+
+        Parameters
+        ----------
+        obj : node-like
+            A DOM <tr> node.
+
+        Returns
+        -------
+        list of node-like
+            These are the elements of each row, i.e., the columns.
+        """
+        raise AbstractMethodError(self)
+
+    def _parse_thead_tr(self, table):
+        """
+        Return the list of thead row elements from the parsed table element.
+
+        Parameters
+        ----------
+        table : a table element that contains zero or more thead elements.
+
+        Returns
+        -------
+        list of node-like
+            These are the <tr> row elements of a table.
+        """
+        raise AbstractMethodError(self)
+
+    def _parse_tbody_tr(self, table):
+        """
+        Return the list of tbody row elements from the parsed table element.
+
+        HTML5 table bodies consist of either 0 or more <tbody> elements (which
+        only contain <tr> elements) or 0 or more <tr> elements. This method
+        checks for both structures.
+
+        Parameters
+        ----------
+        table : a table element that contains row elements.
+
+        Returns
+        -------
+        list of node-like
+            These are the <tr> row elements of a table.
+        """
+        raise AbstractMethodError(self)
+
+    def _parse_tfoot_tr(self, table):
+        """
+        Return the list of tfoot row elements from the parsed table element.
+
+        Parameters
+        ----------
+        table : a table element that contains row elements.
+
+        Returns
+        -------
+        list of node-like
+            These are the <tr> row elements of a table.
+        """
+        raise AbstractMethodError(self)
+
+    def _parse_tables(self, document, match, attrs):
+        """
+        Return all tables from the parsed DOM.
+
+        Parameters
+        ----------
+        document : the DOM from which to parse the table element.
+
+        match : str or regular expression
+            The text to search for in the DOM tree.
+
+        attrs : dict
+            A dictionary of table attributes that can be used to disambiguate
+            multiple tables on a page.
+
+        Raises
+        ------
+        ValueError : `match` does not match any text in the document.
+
+        Returns
+        -------
+        list of node-like
+            HTML <table> elements to be parsed into raw data.
+        """
+        raise AbstractMethodError(self)
+
+    def _equals_tag(self, obj, tag) -> bool:
+        """
+        Return whether an individual DOM node matches a tag
+
+        Parameters
+        ----------
+        obj : node-like
+            A DOM node.
+
+        tag : str
+            Tag name to be checked for equality.
+
+        Returns
+        -------
+        boolean
+            Whether `obj`'s tag name is `tag`
+        """
+        raise AbstractMethodError(self)
+
+    def _build_doc(self):
+        """
+        Return a tree-like object that can be used to iterate over the DOM.
+
+        Returns
+        -------
+        node-like
+            The DOM from which to parse the table element.
+        """
+        raise AbstractMethodError(self)
+
+    def _parse_thead_tbody_tfoot(self, table_html):
+        """
+        Given a table, return parsed header, body, and foot.
+
+        Parameters
+        ----------
+        table_html : node-like
+
+        Returns
+        -------
+        tuple of (header, body, footer), each a list of list-of-text rows.
+
+        Notes
+        -----
+        Header and body are lists-of-lists. Top level list is a list of
+        rows. Each row is a list of str text.
+
+        Logic: Use <thead>, <tbody>, <tfoot> elements to identify
+               header, body, and footer, otherwise:
+               - Put all rows into body
+               - Move rows from top of body to header only if
+                 all elements inside row are <th>
+               - Move rows from bottom of body to footer only if
+                 all elements inside row are <th>
+        """
+        header_rows = self._parse_thead_tr(table_html)
+        body_rows = self._parse_tbody_tr(table_html)
+        footer_rows = self._parse_tfoot_tr(table_html)
+
+        def row_is_all_th(row):
+            return all(self._equals_tag(t, "th") for t in self._parse_td(row))
+
+        if not header_rows:
+            # The table has no <thead>. Move the top all-<th> rows from
+            # body_rows to header_rows. (This is a common case because many
+            # tables in the wild have no <thead> or <tfoot>
+            while body_rows and row_is_all_th(body_rows[0]):
+                header_rows.append(body_rows.pop(0))
+
+        header = self._expand_colspan_rowspan(header_rows, section="header")
+        body = self._expand_colspan_rowspan(body_rows, section="body")
+        footer = self._expand_colspan_rowspan(footer_rows, section="footer")
+
+        return header, body, footer
+
+    def _expand_colspan_rowspan(
+        self, rows, section: Literal["header", "footer", "body"]
+    ):
+        """
+        Given a list of <tr>s, return a list of text rows.
+
+        Parameters
+        ----------
+        rows : list of node-like
+            List of <tr>s
+        section : the section that the rows belong to (header, body or footer).
+
+        Returns
+        -------
+        list of list
+            Each returned row is a list of str text, or tuple (text, link)
+            if extract_links is not None.
+
+        Notes
+        -----
+        Any cell with ``rowspan`` or ``colspan`` will have its contents copied
+        to subsequent cells.
+        """
+        all_texts = []  # list of rows, each a list of str
+        text: str | tuple
+        remainder: list[
+            tuple[int, str | tuple, int]
+        ] = []  # list of (index, text, nrows)
+
+        for tr in rows:
+            texts = []  # the output for this row
+            next_remainder = []
+
+            index = 0
+            tds = self._parse_td(tr)
+            for td in tds:
+                # Append texts from previous rows with rowspan>1 that come
+                # before this <td>
+                while remainder and remainder[0][0] <= index:
+                    prev_i, prev_text, prev_rowspan = remainder.pop(0)
+                    texts.append(prev_text)
+                    if prev_rowspan > 1:
+                        next_remainder.append((prev_i, prev_text, prev_rowspan - 1))
+                    index += 1
+
+                # Append the text from this <td>, colspan times
+                text = _remove_whitespace(self._text_getter(td))
+                if self.extract_links in ("all", section):
+                    href = self._href_getter(td)
+                    text = (text, href)
+                rowspan = int(self._attr_getter(td, "rowspan") or 1)
+                colspan = int(self._attr_getter(td, "colspan") or 1)
+
+                for _ in range(colspan):
+                    texts.append(text)
+                    if rowspan > 1:
+                        next_remainder.append((index, text, rowspan - 1))
+                    index += 1
+
+            # Append texts from previous rows at the final position
+            for prev_i, prev_text, prev_rowspan in remainder:
+                texts.append(prev_text)
+                if prev_rowspan > 1:
+                    next_remainder.append((prev_i, prev_text, prev_rowspan - 1))
+
+            all_texts.append(texts)
+            remainder = next_remainder
+
+        # Append rows that only appear because the previous row had non-1
+        # rowspan
+        while remainder:
+            next_remainder = []
+            texts = []
+            for prev_i, prev_text, prev_rowspan in remainder:
+                texts.append(prev_text)
+                if prev_rowspan > 1:
+                    next_remainder.append((prev_i, prev_text, prev_rowspan - 1))
+            all_texts.append(texts)
+            remainder = next_remainder
+
+        return all_texts
+
+    def _handle_hidden_tables(self, tbl_list, attr_name: str):
+        """
+        Return list of tables, potentially removing hidden elements
+
+        Parameters
+        ----------
+        tbl_list : list of node-like
+            Type of list elements will vary depending upon parser used
+        attr_name : str
+            Name of the accessor for retrieving HTML attributes
+
+        Returns
+        -------
+        list of node-like
+            Return type matches `tbl_list`
+        """
+        if not self.displayed_only:
+            return tbl_list
+
+        return [
+            x
+            for x in tbl_list
+            if "display:none"
+            not in getattr(x, attr_name).get("style", "").replace(" ", "")
+        ]
+
+
+class _BeautifulSoupHtml5LibFrameParser(_HtmlFrameParser):
+    """
+    HTML to DataFrame parser that uses BeautifulSoup under the hood.
+
+    See Also
+    --------
+    pandas.io.html._HtmlFrameParser
+    pandas.io.html._LxmlFrameParser
+
+    Notes
+    -----
+    Documentation strings for this class are in the base class
+    :class:`pandas.io.html._HtmlFrameParser`.
+    """
+
+    def _parse_tables(self, document, match, attrs):
+        element_name = "table"
+        tables = document.find_all(element_name, attrs=attrs)
+        if not tables:
+            raise ValueError("No tables found")
+
+        result = []
+        unique_tables = set()
+        tables = self._handle_hidden_tables(tables, "attrs")
+
+        for table in tables:
+            if self.displayed_only:
+                for elem in table.find_all("style"):
+                    elem.decompose()
+
+                for elem in table.find_all(style=re.compile(r"display:\s*none")):
+                    elem.decompose()
+
+            if table not in unique_tables and table.find(string=match) is not None:
+                result.append(table)
+            unique_tables.add(table)
+        if not result:
+            raise ValueError(f"No tables found matching pattern {repr(match.pattern)}")
+        return result
+
+    def _href_getter(self, obj) -> str | None:
+        a = obj.find("a", href=True)
+        return None if not a else a["href"]
+
+    def _text_getter(self, obj):
+        return obj.text
+
+    def _equals_tag(self, obj, tag) -> bool:
+        return obj.name == tag
+
+    def _parse_td(self, row):
+        return row.find_all(("td", "th"), recursive=False)
+
+    def _parse_thead_tr(self, table):
+        return table.select("thead tr")
+
+    def _parse_tbody_tr(self, table):
+        from_tbody = table.select("tbody tr")
+        from_root = table.find_all("tr", recursive=False)
+        # HTML spec: at most one of these lists has content
+        return from_tbody + from_root
+
+    def _parse_tfoot_tr(self, table):
+        return table.select("tfoot tr")
+
+    def _setup_build_doc(self):
+        raw_text = _read(self.io, self.encoding, self.storage_options)
+        if not raw_text:
+            raise ValueError(f"No text parsed from document: {self.io}")
+        return raw_text
+
+    def _build_doc(self):
+        from bs4 import BeautifulSoup
+
+        bdoc = self._setup_build_doc()
+        if isinstance(bdoc, bytes) and self.encoding is not None:
+            udoc = bdoc.decode(self.encoding)
+            from_encoding = None
+        else:
+            udoc = bdoc
+            from_encoding = self.encoding
+
+        soup = BeautifulSoup(udoc, features="html5lib", from_encoding=from_encoding)
+
+        for br in soup.find_all("br"):
+            br.replace_with("\n" + br.text)
+
+        return soup
+
+
+def _build_xpath_expr(attrs) -> str:
+    """
+    Build an xpath expression to simulate bs4's ability to pass in kwargs to
+    search for attributes when using the lxml parser.
+
+    Parameters
+    ----------
+    attrs : dict
+        A dict of HTML attributes. These are NOT checked for validity.
+
+    Returns
+    -------
+    expr : unicode
+        An XPath expression that checks for the given HTML attributes.
+    """
+    # give class attribute as class_ because class is a python keyword
+    if "class_" in attrs:
+        attrs["class"] = attrs.pop("class_")
+
+    s = " and ".join([f"@{k}={repr(v)}" for k, v in attrs.items()])
+    return f"[{s}]"
+
+
+_re_namespace = {"re": "http://exslt.org/regular-expressions"}
+
+
+class _LxmlFrameParser(_HtmlFrameParser):
+    """
+    HTML to DataFrame parser that uses lxml under the hood.
+
+    Warning
+    -------
+    This parser can only handle HTTP, FTP, and FILE urls.
+
+    See Also
+    --------
+    _HtmlFrameParser
+    _BeautifulSoupLxmlFrameParser
+
+    Notes
+    -----
+    Documentation strings for this class are in the base class
+    :class:`_HtmlFrameParser`.
+    """
+
+    def _href_getter(self, obj) -> str | None:
+        href = obj.xpath(".//a/@href")
+        return None if not href else href[0]
+
+    def _text_getter(self, obj):
+        return obj.text_content()
+
+    def _parse_td(self, row):
+        # Look for direct children only: the "row" element here may be a
+        # <thead> or <tfoot> (see _parse_thead_tr).
+        return row.xpath("./td|./th")
+
+    def _parse_tables(self, document, match, kwargs):
+        pattern = match.pattern
+
+        # 1. check all descendants for the given pattern and only search tables
+        # GH 49929
+        xpath_expr = f"//table[.//text()[re:test(., {repr(pattern)})]]"
+
+        # if any table attributes were given build an xpath expression to
+        # search for them
+        if kwargs:
+            xpath_expr += _build_xpath_expr(kwargs)
+
+        tables = document.xpath(xpath_expr, namespaces=_re_namespace)
+
+        tables = self._handle_hidden_tables(tables, "attrib")
+        if self.displayed_only:
+            for table in tables:
+                # lxml utilizes XPATH 1.0 which does not have regex
+                # support. As a result, we find all elements with a style
+                # attribute and iterate them to check for display:none
+                for elem in table.xpath(".//style"):
+                    elem.drop_tree()
+                for elem in table.xpath(".//*[@style]"):
+                    if "display:none" in elem.attrib.get("style", "").replace(" ", ""):
+                        elem.drop_tree()
+        if not tables:
+            raise ValueError(f"No tables found matching regex {repr(pattern)}")
+        return tables
+
+    def _equals_tag(self, obj, tag) -> bool:
+        return obj.tag == tag
+
+    def _build_doc(self):
+        """
+        Raises
+        ------
+        ValueError
+            * If a URL that lxml cannot parse is passed.
+
+        Exception
+            * Any other ``Exception`` thrown. For example, trying to parse a
+              URL that is syntactically correct on a machine with no internet
+              connection will fail.
+
+        See Also
+        --------
+        pandas.io.html._HtmlFrameParser._build_doc
+        """
+        from lxml.etree import XMLSyntaxError
+        from lxml.html import (
+            HTMLParser,
+            fromstring,
+            parse,
+        )
+
+        parser = HTMLParser(recover=True, encoding=self.encoding)
+
+        try:
+            if is_url(self.io):
+                with get_handle(
+                    self.io, "r", storage_options=self.storage_options
+                ) as f:
+                    r = parse(f.handle, parser=parser)
+            else:
+                # try to parse the input in the simplest way
+                r = parse(self.io, parser=parser)
+            try:
+                r = r.getroot()
+            except AttributeError:
+                pass
+        except (UnicodeDecodeError, OSError) as e:
+            # if the input is a blob of html goop
+            if not is_url(self.io):
+                r = fromstring(self.io, parser=parser)
+
+                try:
+                    r = r.getroot()
+                except AttributeError:
+                    pass
+            else:
+                raise e
+        else:
+            if not hasattr(r, "text_content"):
+                raise XMLSyntaxError("no text parsed from document", 0, 0, 0)
+
+        for br in r.xpath("*//br"):
+            br.tail = "\n" + (br.tail or "")
+
+        return r
+
+    def _parse_thead_tr(self, table):
+        rows = []
+
+        for thead in table.xpath(".//thead"):
+            rows.extend(thead.xpath("./tr"))
+
+            # HACK: lxml does not clean up the clearly-erroneous
+            # <thead><th>foo</th><th>bar</th></thead>. (Missing <tr>). Add
+            # the <thead> and _pretend_ it's a <tr>; _parse_td() will find its
+            # children as though it's a <tr>.
+            #
+            # Better solution would be to use html5lib.
+            elements_at_root = thead.xpath("./td|./th")
+            if elements_at_root:
+                rows.append(thead)
+
+        return rows
+
+    def _parse_tbody_tr(self, table):
+        from_tbody = table.xpath(".//tbody//tr")
+        from_root = table.xpath("./tr")
+        # HTML spec: at most one of these lists has content
+        return from_tbody + from_root
+
+    def _parse_tfoot_tr(self, table):
+        return table.xpath(".//tfoot//tr")
+
+
+def _expand_elements(body) -> None:
+    data = [len(elem) for elem in body]
+    lens = Series(data)
+    lens_max = lens.max()
+    not_max = lens[lens != lens_max]
+
+    empty = [""]
+    for ind, length in not_max.items():
+        body[ind] += empty * (lens_max - length)
+
+
+def _data_to_frame(**kwargs):
+    head, body, foot = kwargs.pop("data")
+    header = kwargs.pop("header")
+    kwargs["skiprows"] = _get_skiprows(kwargs["skiprows"])
+    if head:
+        body = head + body
+
+        # Infer header when there is a <thead> or top <th>-only rows
+        if header is None:
+            if len(head) == 1:
+                header = 0
+            else:
+                # ignore all-empty-text rows
+                header = [i for i, row in enumerate(head) if any(text for text in row)]
+
+    if foot:
+        body += foot
+
+    # fill out elements of body that are "ragged"
+    _expand_elements(body)
+    with TextParser(body, header=header, **kwargs) as tp:
+        return tp.read()
+
+
+_valid_parsers = {
+    "lxml": _LxmlFrameParser,
+    None: _LxmlFrameParser,
+    "html5lib": _BeautifulSoupHtml5LibFrameParser,
+    "bs4": _BeautifulSoupHtml5LibFrameParser,
+}
+
+
+def _parser_dispatch(flavor: HTMLFlavors | None) -> type[_HtmlFrameParser]:
+    """
+    Choose the parser based on the input flavor.
+
+    Parameters
+    ----------
+    flavor : {{"lxml", "html5lib", "bs4"}} or None
+        The type of parser to use. This must be a valid backend.
+
+    Returns
+    -------
+    cls : _HtmlFrameParser subclass
+        The parser class based on the requested input flavor.
+
+    Raises
+    ------
+    ValueError
+        * If `flavor` is not a valid backend.
+    ImportError
+        * If you do not have the requested `flavor`
+    """
+    valid_parsers = list(_valid_parsers.keys())
+    if flavor not in valid_parsers:
+        raise ValueError(
+            f"{repr(flavor)} is not a valid flavor, valid flavors are {valid_parsers}"
+        )
+
+    if flavor in ("bs4", "html5lib"):
+        import_optional_dependency("html5lib")
+        import_optional_dependency("bs4")
+    else:
+        import_optional_dependency("lxml.etree")
+    return _valid_parsers[flavor]
+
+
+def _print_as_set(s) -> str:
+    arg = ", ".join([pprint_thing(el) for el in s])
+    return f"{{{arg}}}"
+
+
+def _validate_flavor(flavor):
+    if flavor is None:
+        flavor = "lxml", "bs4"
+    elif isinstance(flavor, str):
+        flavor = (flavor,)
+    elif isinstance(flavor, abc.Iterable):
+        if not all(isinstance(flav, str) for flav in flavor):
+            raise TypeError(
+                f"Object of type {repr(type(flavor).__name__)} "
+                f"is not an iterable of strings"
+            )
+    else:
+        msg = repr(flavor) if isinstance(flavor, str) else str(flavor)
+        msg += " is not a valid flavor"
+        raise ValueError(msg)
+
+    flavor = tuple(flavor)
+    valid_flavors = set(_valid_parsers)
+    flavor_set = set(flavor)
+
+    if not flavor_set & valid_flavors:
+        raise ValueError(
+            f"{_print_as_set(flavor_set)} is not a valid set of flavors, valid "
+            f"flavors are {_print_as_set(valid_flavors)}"
+        )
+    return flavor
+
+
+def _parse(
+    flavor,
+    io,
+    match,
+    attrs,
+    encoding,
+    displayed_only,
+    extract_links,
+    storage_options,
+    **kwargs,
+):
+    flavor = _validate_flavor(flavor)
+    compiled_match = re.compile(match)  # you can pass a compiled regex here
+
+    retained = None
+    for flav in flavor:
+        parser = _parser_dispatch(flav)
+        p = parser(
+            io,
+            compiled_match,
+            attrs,
+            encoding,
+            displayed_only,
+            extract_links,
+            storage_options,
+        )
+
+        try:
+            tables = p.parse_tables()
+        except ValueError as caught:
+            # if `io` is an io-like object, check if it's seekable
+            # and try to rewind it before trying the next parser
+            if hasattr(io, "seekable") and io.seekable():
+                io.seek(0)
+            elif hasattr(io, "seekable") and not io.seekable():
+                # if we couldn't rewind it, let the user know
+                raise ValueError(
+                    f"The flavor {flav} failed to parse your input. "
+                    "Since you passed a non-rewindable file "
+                    "object, we can't rewind it to try "
+                    "another parser. Try read_html() with a different flavor."
+                ) from caught
+
+            retained = caught
+        else:
+            break
+    else:
+        assert retained is not None  # for mypy
+        raise retained
+
+    ret = []
+    for table in tables:
+        try:
+            df = _data_to_frame(data=table, **kwargs)
+            # Cast MultiIndex header to an Index of tuples when extracting header
+            # links and replace nan with None (therefore can't use mi.to_flat_index()).
+            # This maintains consistency of selection (e.g. df.columns.str[1])
+            if extract_links in ("all", "header") and isinstance(
+                df.columns, MultiIndex
+            ):
+                df.columns = Index(
+                    ((col[0], None if isna(col[1]) else col[1]) for col in df.columns),
+                    tupleize_cols=False,
+                )
+
+            ret.append(df)
+        except EmptyDataError:  # empty table
+            continue
+    return ret
+
+
+@doc(storage_options=_shared_docs["storage_options"])
+def read_html(
+    io: FilePath | ReadBuffer[str],
+    *,
+    match: str | Pattern = ".+",
+    flavor: HTMLFlavors | Sequence[HTMLFlavors] | None = None,
+    header: int | Sequence[int] | None = None,
+    index_col: int | Sequence[int] | None = None,
+    skiprows: int | Sequence[int] | slice | None = None,
+    attrs: dict[str, str] | None = None,
+    parse_dates: bool = False,
+    thousands: str | None = ",",
+    encoding: str | None = None,
+    decimal: str = ".",
+    converters: dict | None = None,
+    na_values: Iterable[object] | None = None,
+    keep_default_na: bool = True,
+    displayed_only: bool = True,
+    extract_links: Literal[None, "header", "footer", "body", "all"] = None,
+    dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
+    storage_options: StorageOptions = None,
+) -> list[DataFrame]:
+    r"""
+    Read HTML tables into a ``list`` of ``DataFrame`` objects.
+
+    Parameters
+    ----------
+    io : str, path object, or file-like object
+        String, path object (implementing ``os.PathLike[str]``), or file-like
+        object implementing a string ``read()`` function.
+        The string can represent a URL or the HTML itself. Note that
+        lxml only accepts the http, ftp and file url protocols. If you have a
+        URL that starts with ``'https'`` you might try removing the ``'s'``.
+
+        .. deprecated:: 2.1.0
+            Passing html literal strings is deprecated.
+            Wrap literal string/bytes input in ``io.StringIO``/``io.BytesIO`` instead.
+
+    match : str or compiled regular expression, optional
+        The set of tables containing text matching this regex or string will be
+        returned. Unless the HTML is extremely simple you will probably need to
+        pass a non-empty string here. Defaults to '.+' (match any non-empty
+        string). The default value will return all tables contained on a page.
+        This value is converted to a regular expression so that there is
+        consistent behavior between Beautiful Soup and lxml.
+
+    flavor : {{"lxml", "html5lib", "bs4"}} or list-like, optional
+        The parsing engine (or list of parsing engines) to use. 'bs4' and
+        'html5lib' are synonymous with each other, they are both there for
+        backwards compatibility. The default of ``None`` tries to use ``lxml``
+        to parse and if that fails it falls back on ``bs4`` + ``html5lib``.
+
+    header : int or list-like, optional
+        The row (or list of rows for a :class:`~pandas.MultiIndex`) to use to
+        make the columns headers.
+
+    index_col : int or list-like, optional
+        The column (or list of columns) to use to create the index.
+
+    skiprows : int, list-like or slice, optional
+        Number of rows to skip after parsing the column integer. 0-based. If a
+        sequence of integers or a slice is given, will skip the rows indexed by
+        that sequence.  Note that a single element sequence means 'skip the nth
+        row' whereas an integer means 'skip n rows'.
+
+    attrs : dict, optional
+        This is a dictionary of attributes that you can pass to use to identify
+        the table in the HTML. These are not checked for validity before being
+        passed to lxml or Beautiful Soup. However, these attributes must be
+        valid HTML table attributes to work correctly. For example, ::
+
+            attrs = {{'id': 'table'}}
+
+        is a valid attribute dictionary because the 'id' HTML tag attribute is
+        a valid HTML attribute for *any* HTML tag as per `this document
+        <https://html.spec.whatwg.org/multipage/dom.html#global-attributes>`__. ::
+
+            attrs = {{'asdf': 'table'}}
+
+        is *not* a valid attribute dictionary because 'asdf' is not a valid
+        HTML attribute even if it is a valid XML attribute.  Valid HTML 4.01
+        table attributes can be found `here
+        <http://www.w3.org/TR/REC-html40/struct/tables.html#h-11.2>`__. A
+        working draft of the HTML 5 spec can be found `here
+        <https://html.spec.whatwg.org/multipage/tables.html>`__. It contains the
+        latest information on table attributes for the modern web.
+
+    parse_dates : bool, optional
+        See :func:`~read_csv` for more details.
+
+    thousands : str, optional
+        Separator to use to parse thousands. Defaults to ``','``.
+
+    encoding : str, optional
+        The encoding used to decode the web page. Defaults to ``None``.``None``
+        preserves the previous encoding behavior, which depends on the
+        underlying parser library (e.g., the parser library will try to use
+        the encoding provided by the document).
+
+    decimal : str, default '.'
+        Character to recognize as decimal point (e.g. use ',' for European
+        data).
+
+    converters : dict, default None
+        Dict of functions for converting values in certain columns. Keys can
+        either be integers or column labels, values are functions that take one
+        input argument, the cell (not column) content, and return the
+        transformed content.
+
+    na_values : iterable, default None
+        Custom NA values.
+
+    keep_default_na : bool, default True
+        If na_values are specified and keep_default_na is False the default NaN
+        values are overridden, otherwise they're appended to.
+
+    displayed_only : bool, default True
+        Whether elements with "display: none" should be parsed.
+
+    extract_links : {{None, "all", "header", "body", "footer"}}
+        Table elements in the specified section(s) with <a> tags will have their
+        href extracted.
+
+        .. versionadded:: 1.5.0
+
+    dtype_backend : {{'numpy_nullable', 'pyarrow'}}, default 'numpy_nullable'
+        Back-end data type applied to the resultant :class:`DataFrame`
+        (still experimental). Behaviour is as follows:
+
+        * ``"numpy_nullable"``: returns nullable-dtype-backed :class:`DataFrame`
+          (default).
+        * ``"pyarrow"``: returns pyarrow-backed nullable :class:`ArrowDtype`
+          DataFrame.
+
+        .. versionadded:: 2.0
+
+    {storage_options}
+
+        .. versionadded:: 2.1.0
+
+    Returns
+    -------
+    dfs
+        A list of DataFrames.
+
+    See Also
+    --------
+    read_csv : Read a comma-separated values (csv) file into DataFrame.
+
+    Notes
+    -----
+    Before using this function you should read the :ref:`gotchas about the
+    HTML parsing libraries <io.html.gotchas>`.
+
+    Expect to do some cleanup after you call this function. For example, you
+    might need to manually assign column names if the column names are
+    converted to NaN when you pass the `header=0` argument. We try to assume as
+    little as possible about the structure of the table and push the
+    idiosyncrasies of the HTML contained in the table to the user.
+
+    This function searches for ``<table>`` elements and only for ``<tr>``
+    and ``<th>`` rows and ``<td>`` elements within each ``<tr>`` or ``<th>``
+    element in the table. ``<td>`` stands for "table data". This function
+    attempts to properly handle ``colspan`` and ``rowspan`` attributes.
+    If the function has a ``<thead>`` argument, it is used to construct
+    the header, otherwise the function attempts to find the header within
+    the body (by putting rows with only ``<th>`` elements into the header).
+
+    Similar to :func:`~read_csv` the `header` argument is applied
+    **after** `skiprows` is applied.
+
+    This function will *always* return a list of :class:`DataFrame` *or*
+    it will fail, e.g., it will *not* return an empty list.
+
+    Examples
+    --------
+    See the :ref:`read_html documentation in the IO section of the docs
+    <io.read_html>` for some examples of reading in HTML tables.
+    """
+    # Type check here. We don't want to parse only to fail because of an
+    # invalid value of an integer skiprows.
+    if isinstance(skiprows, numbers.Integral) and skiprows < 0:
+        raise ValueError(
+            "cannot skip rows starting from the end of the "
+            "data (you passed a negative value)"
+        )
+    if extract_links not in [None, "header", "footer", "body", "all"]:
+        raise ValueError(
+            "`extract_links` must be one of "
+            '{None, "header", "footer", "body", "all"}, got '
+            f'"{extract_links}"'
+        )
+
+    validate_header_arg(header)
+    check_dtype_backend(dtype_backend)
+
+    io = stringify_path(io)
+
+    if isinstance(io, str) and not any(
+        [
+            is_file_like(io),
+            file_exists(io),
+            is_url(io),
+            is_fsspec_url(io),
+        ]
+    ):
+        warnings.warn(
+            "Passing literal html to 'read_html' is deprecated and "
+            "will be removed in a future version. To read from a "
+            "literal string, wrap it in a 'StringIO' object.",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
+
+    return _parse(
+        flavor=flavor,
+        io=io,
+        match=match,
+        header=header,
+        index_col=index_col,
+        skiprows=skiprows,
+        parse_dates=parse_dates,
+        thousands=thousands,
+        attrs=attrs,
+        encoding=encoding,
+        decimal=decimal,
+        converters=converters,
+        na_values=na_values,
+        keep_default_na=keep_default_na,
+        displayed_only=displayed_only,
+        extract_links=extract_links,
+        dtype_backend=dtype_backend,
+        storage_options=storage_options,
+    )

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/io/pickle.py

@@ -0,0 +1,210 @@
+""" pickle compat """
+from __future__ import annotations
+
+import pickle
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+import warnings
+
+from pandas.compat import pickle_compat as pc
+from pandas.util._decorators import doc
+
+from pandas.core.shared_docs import _shared_docs
+
+from pandas.io.common import get_handle
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        CompressionOptions,
+        FilePath,
+        ReadPickleBuffer,
+        StorageOptions,
+        WriteBuffer,
+    )
+
+    from pandas import (
+        DataFrame,
+        Series,
+    )
+
+
+@doc(
+    storage_options=_shared_docs["storage_options"],
+    compression_options=_shared_docs["compression_options"] % "filepath_or_buffer",
+)
+def to_pickle(
+    obj: Any,
+    filepath_or_buffer: FilePath | WriteBuffer[bytes],
+    compression: CompressionOptions = "infer",
+    protocol: int = pickle.HIGHEST_PROTOCOL,
+    storage_options: StorageOptions | None = None,
+) -> None:
+    """
+    Pickle (serialize) object to file.
+
+    Parameters
+    ----------
+    obj : any object
+        Any python object.
+    filepath_or_buffer : str, path object, or file-like object
+        String, path object (implementing ``os.PathLike[str]``), or file-like
+        object implementing a binary ``write()`` function.
+        Also accepts URL. URL has to be of S3 or GCS.
+    {compression_options}
+
+        .. versionchanged:: 1.4.0 Zstandard support.
+
+    protocol : int
+        Int which indicates which protocol should be used by the pickler,
+        default HIGHEST_PROTOCOL (see [1], paragraph 12.1.2). The possible
+        values for this parameter depend on the version of Python. For Python
+        2.x, possible values are 0, 1, 2. For Python>=3.0, 3 is a valid value.
+        For Python >= 3.4, 4 is a valid value. A negative value for the
+        protocol parameter is equivalent to setting its value to
+        HIGHEST_PROTOCOL.
+
+    {storage_options}
+
+        .. [1] https://docs.python.org/3/library/pickle.html
+
+    See Also
+    --------
+    read_pickle : Load pickled pandas object (or any object) from file.
+    DataFrame.to_hdf : Write DataFrame to an HDF5 file.
+    DataFrame.to_sql : Write DataFrame to a SQL database.
+    DataFrame.to_parquet : Write a DataFrame to the binary parquet format.
+
+    Examples
+    --------
+    >>> original_df = pd.DataFrame({{"foo": range(5), "bar": range(5, 10)}})  # doctest: +SKIP
+    >>> original_df  # doctest: +SKIP
+       foo  bar
+    0    0    5
+    1    1    6
+    2    2    7
+    3    3    8
+    4    4    9
+    >>> pd.to_pickle(original_df, "./dummy.pkl")  # doctest: +SKIP
+
+    >>> unpickled_df = pd.read_pickle("./dummy.pkl")  # doctest: +SKIP
+    >>> unpickled_df  # doctest: +SKIP
+       foo  bar
+    0    0    5
+    1    1    6
+    2    2    7
+    3    3    8
+    4    4    9
+    """  # noqa: E501
+    if protocol < 0:
+        protocol = pickle.HIGHEST_PROTOCOL
+
+    with get_handle(
+        filepath_or_buffer,
+        "wb",
+        compression=compression,
+        is_text=False,
+        storage_options=storage_options,
+    ) as handles:
+        # letting pickle write directly to the buffer is more memory-efficient
+        pickle.dump(obj, handles.handle, protocol=protocol)
+
+
+@doc(
+    storage_options=_shared_docs["storage_options"],
+    decompression_options=_shared_docs["decompression_options"] % "filepath_or_buffer",
+)
+def read_pickle(
+    filepath_or_buffer: FilePath | ReadPickleBuffer,
+    compression: CompressionOptions = "infer",
+    storage_options: StorageOptions | None = None,
+) -> DataFrame | Series:
+    """
+    Load pickled pandas object (or any object) from file.
+
+    .. warning::
+
+       Loading pickled data received from untrusted sources can be
+       unsafe. See `here <https://docs.python.org/3/library/pickle.html>`__.
+
+    Parameters
+    ----------
+    filepath_or_buffer : str, path object, or file-like object
+        String, path object (implementing ``os.PathLike[str]``), or file-like
+        object implementing a binary ``readlines()`` function.
+        Also accepts URL. URL is not limited to S3 and GCS.
+
+    {decompression_options}
+
+        .. versionchanged:: 1.4.0 Zstandard support.
+
+    {storage_options}
+
+    Returns
+    -------
+    same type as object stored in file
+
+    See Also
+    --------
+    DataFrame.to_pickle : Pickle (serialize) DataFrame object to file.
+    Series.to_pickle : Pickle (serialize) Series object to file.
+    read_hdf : Read HDF5 file into a DataFrame.
+    read_sql : Read SQL query or database table into a DataFrame.
+    read_parquet : Load a parquet object, returning a DataFrame.
+
+    Notes
+    -----
+    read_pickle is only guaranteed to be backwards compatible to pandas 0.20.3
+    provided the object was serialized with to_pickle.
+
+    Examples
+    --------
+    >>> original_df = pd.DataFrame(
+    ...     {{"foo": range(5), "bar": range(5, 10)}}
+    ...    )  # doctest: +SKIP
+    >>> original_df  # doctest: +SKIP
+       foo  bar
+    0    0    5
+    1    1    6
+    2    2    7
+    3    3    8
+    4    4    9
+    >>> pd.to_pickle(original_df, "./dummy.pkl")  # doctest: +SKIP
+
+    >>> unpickled_df = pd.read_pickle("./dummy.pkl")  # doctest: +SKIP
+    >>> unpickled_df  # doctest: +SKIP
+       foo  bar
+    0    0    5
+    1    1    6
+    2    2    7
+    3    3    8
+    4    4    9
+    """
+    excs_to_catch = (AttributeError, ImportError, ModuleNotFoundError, TypeError)
+    with get_handle(
+        filepath_or_buffer,
+        "rb",
+        compression=compression,
+        is_text=False,
+        storage_options=storage_options,
+    ) as handles:
+        # 1) try standard library Pickle
+        # 2) try pickle_compat (older pandas version) to handle subclass changes
+        # 3) try pickle_compat with latin-1 encoding upon a UnicodeDecodeError
+
+        try:
+            # TypeError for Cython complaints about object.__new__ vs Tick.__new__
+            try:
+                with warnings.catch_warnings(record=True):
+                    # We want to silence any warnings about, e.g. moved modules.
+                    warnings.simplefilter("ignore", Warning)
+                    return pickle.load(handles.handle)
+            except excs_to_catch:
+                # e.g.
+                #  "No module named 'pandas.core.sparse.series'"
+                #  "Can't get attribute '__nat_unpickle' on <module 'pandas._libs.tslib"
+                return pc.load(handles.handle, encoding=None)
+        except UnicodeDecodeError:
+            # e.g. can occur for files written in py27; see GH#28645 and GH#31988
+            return pc.load(handles.handle, encoding="latin-1")

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/arrays/masked_shared.py

@@ -0,0 +1,154 @@
+"""
+Tests shared by MaskedArray subclasses.
+"""
+import numpy as np
+import pytest
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.tests.extension.base import BaseOpsUtil
+
+
+class ComparisonOps(BaseOpsUtil):
+    def _compare_other(self, data, op, other):
+        # array
+        result = pd.Series(op(data, other))
+        expected = pd.Series(op(data._data, other), dtype="boolean")
+
+        # fill the nan locations
+        expected[data._mask] = pd.NA
+
+        tm.assert_series_equal(result, expected)
+
+        # series
+        ser = pd.Series(data)
+        result = op(ser, other)
+
+        # Set nullable dtype here to avoid upcasting when setting to pd.NA below
+        expected = op(pd.Series(data._data), other).astype("boolean")
+
+        # fill the nan locations
+        expected[data._mask] = pd.NA
+
+        tm.assert_series_equal(result, expected)
+
+    # subclass will override to parametrize 'other'
+    def test_scalar(self, other, comparison_op, dtype):
+        op = comparison_op
+        left = pd.array([1, 0, None], dtype=dtype)
+
+        result = op(left, other)
+
+        if other is pd.NA:
+            expected = pd.array([None, None, None], dtype="boolean")
+        else:
+            values = op(left._data, other)
+            expected = pd.arrays.BooleanArray(values, left._mask, copy=True)
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        result[0] = pd.NA
+        tm.assert_extension_array_equal(left, pd.array([1, 0, None], dtype=dtype))
+
+
+class NumericOps:
+    # Shared by IntegerArray and FloatingArray, not BooleanArray
+
+    def test_searchsorted_nan(self, dtype):
+        # The base class casts to object dtype, for which searchsorted returns
+        #  0 from the left and 10 from the right.
+        arr = pd.array(range(10), dtype=dtype)
+
+        assert arr.searchsorted(np.nan, side="left") == 10
+        assert arr.searchsorted(np.nan, side="right") == 10
+
+    def test_no_shared_mask(self, data):
+        result = data + 1
+        assert not tm.shares_memory(result, data)
+
+    def test_array(self, comparison_op, dtype):
+        op = comparison_op
+
+        left = pd.array([0, 1, 2, None, None, None], dtype=dtype)
+        right = pd.array([0, 1, None, 0, 1, None], dtype=dtype)
+
+        result = op(left, right)
+        values = op(left._data, right._data)
+        mask = left._mask | right._mask
+
+        expected = pd.arrays.BooleanArray(values, mask)
+        tm.assert_extension_array_equal(result, expected)
+
+        # ensure we haven't mutated anything inplace
+        result[0] = pd.NA
+        tm.assert_extension_array_equal(
+            left, pd.array([0, 1, 2, None, None, None], dtype=dtype)
+        )
+        tm.assert_extension_array_equal(
+            right, pd.array([0, 1, None, 0, 1, None], dtype=dtype)
+        )
+
+    def test_compare_with_booleanarray(self, comparison_op, dtype):
+        op = comparison_op
+
+        left = pd.array([True, False, None] * 3, dtype="boolean")
+        right = pd.array([0] * 3 + [1] * 3 + [None] * 3, dtype=dtype)
+        other = pd.array([False] * 3 + [True] * 3 + [None] * 3, dtype="boolean")
+
+        expected = op(left, other)
+        result = op(left, right)
+        tm.assert_extension_array_equal(result, expected)
+
+        # reversed op
+        expected = op(other, left)
+        result = op(right, left)
+        tm.assert_extension_array_equal(result, expected)
+
+    def test_compare_to_string(self, dtype):
+        # GH#28930
+        ser = pd.Series([1, None], dtype=dtype)
+        result = ser == "a"
+        expected = pd.Series([False, pd.NA], dtype="boolean")
+
+        tm.assert_series_equal(result, expected)
+
+    def test_ufunc_with_out(self, dtype):
+        arr = pd.array([1, 2, 3], dtype=dtype)
+        arr2 = pd.array([1, 2, pd.NA], dtype=dtype)
+
+        mask = arr == arr
+        mask2 = arr2 == arr2
+
+        result = np.zeros(3, dtype=bool)
+        result |= mask
+        # If MaskedArray.__array_ufunc__ handled "out" appropriately,
+        #  `result` should still be an ndarray.
+        assert isinstance(result, np.ndarray)
+        assert result.all()
+
+        # result |= mask worked because mask could be cast losslessly to
+        #  boolean ndarray. mask2 can't, so this raises
+        result = np.zeros(3, dtype=bool)
+        msg = "Specify an appropriate 'na_value' for this dtype"
+        with pytest.raises(ValueError, match=msg):
+            result |= mask2
+
+        # addition
+        res = np.add(arr, arr2)
+        expected = pd.array([2, 4, pd.NA], dtype=dtype)
+        tm.assert_extension_array_equal(res, expected)
+
+        # when passing out=arr, we will modify 'arr' inplace.
+        res = np.add(arr, arr2, out=arr)
+        assert res is arr
+        tm.assert_extension_array_equal(res, expected)
+        tm.assert_extension_array_equal(arr, expected)
+
+    def test_mul_td64_array(self, dtype):
+        # GH#45622
+        arr = pd.array([1, 2, pd.NA], dtype=dtype)
+        other = np.arange(3, dtype=np.int64).view("m8[ns]")
+
+        result = arr * other
+        expected = pd.array([pd.Timedelta(0), pd.Timedelta(2), pd.NaT])
+        tm.assert_extension_array_equal(result, expected)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/arrays/test_array.py

@@ -0,0 +1,478 @@
+import datetime
+import decimal
+import re
+
+import numpy as np
+import pytest
+import pytz
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.api.extensions import register_extension_dtype
+from pandas.arrays import (
+    BooleanArray,
+    DatetimeArray,
+    FloatingArray,
+    IntegerArray,
+    IntervalArray,
+    SparseArray,
+    TimedeltaArray,
+)
+from pandas.core.arrays import (
+    NumpyExtensionArray,
+    period_array,
+)
+from pandas.tests.extension.decimal import (
+    DecimalArray,
+    DecimalDtype,
+    to_decimal,
+)
+
+
+@pytest.mark.parametrize("dtype_unit", ["M8[h]", "M8[m]", "m8[h]", "M8[m]"])
+def test_dt64_array(dtype_unit):
+    # PR 53817
+    dtype_var = np.dtype(dtype_unit)
+    msg = (
+        r"datetime64 and timedelta64 dtype resolutions other than "
+        r"'s', 'ms', 'us', and 'ns' are deprecated. "
+        r"In future releases passing unsupported resolutions will "
+        r"raise an exception."
+    )
+    with tm.assert_produces_warning(FutureWarning, match=re.escape(msg)):
+        pd.array([], dtype=dtype_var)
+
+
+@pytest.mark.parametrize(
+    "data, dtype, expected",
+    [
+        # Basic NumPy defaults.
+        ([], None, FloatingArray._from_sequence([], dtype="Float64")),
+        ([1, 2], None, IntegerArray._from_sequence([1, 2], dtype="Int64")),
+        ([1, 2], object, NumpyExtensionArray(np.array([1, 2], dtype=object))),
+        (
+            [1, 2],
+            np.dtype("float32"),
+            NumpyExtensionArray(np.array([1.0, 2.0], dtype=np.dtype("float32"))),
+        ),
+        (
+            np.array([], dtype=object),
+            None,
+            NumpyExtensionArray(np.array([], dtype=object)),
+        ),
+        (
+            np.array([1, 2], dtype="int64"),
+            None,
+            IntegerArray._from_sequence([1, 2], dtype="Int64"),
+        ),
+        (
+            np.array([1.0, 2.0], dtype="float64"),
+            None,
+            FloatingArray._from_sequence([1.0, 2.0], dtype="Float64"),
+        ),
+        # String alias passes through to NumPy
+        ([1, 2], "float32", NumpyExtensionArray(np.array([1, 2], dtype="float32"))),
+        ([1, 2], "int64", NumpyExtensionArray(np.array([1, 2], dtype=np.int64))),
+        # GH#44715 FloatingArray does not support float16, so fall
+        #  back to NumpyExtensionArray
+        (
+            np.array([1, 2], dtype=np.float16),
+            None,
+            NumpyExtensionArray(np.array([1, 2], dtype=np.float16)),
+        ),
+        # idempotency with e.g. pd.array(pd.array([1, 2], dtype="int64"))
+        (
+            NumpyExtensionArray(np.array([1, 2], dtype=np.int32)),
+            None,
+            NumpyExtensionArray(np.array([1, 2], dtype=np.int32)),
+        ),
+        # Period alias
+        (
+            [pd.Period("2000", "D"), pd.Period("2001", "D")],
+            "Period[D]",
+            period_array(["2000", "2001"], freq="D"),
+        ),
+        # Period dtype
+        (
+            [pd.Period("2000", "D")],
+            pd.PeriodDtype("D"),
+            period_array(["2000"], freq="D"),
+        ),
+        # Datetime (naive)
+        (
+            [1, 2],
+            np.dtype("datetime64[ns]"),
+            DatetimeArray._from_sequence(
+                np.array([1, 2], dtype="M8[ns]"), dtype="M8[ns]"
+            ),
+        ),
+        (
+            [1, 2],
+            np.dtype("datetime64[s]"),
+            DatetimeArray._from_sequence(
+                np.array([1, 2], dtype="M8[s]"), dtype="M8[s]"
+            ),
+        ),
+        (
+            np.array([1, 2], dtype="datetime64[ns]"),
+            None,
+            DatetimeArray._from_sequence(
+                np.array([1, 2], dtype="M8[ns]"), dtype="M8[ns]"
+            ),
+        ),
+        (
+            pd.DatetimeIndex(["2000", "2001"]),
+            np.dtype("datetime64[ns]"),
+            DatetimeArray._from_sequence(["2000", "2001"], dtype="M8[ns]"),
+        ),
+        (
+            pd.DatetimeIndex(["2000", "2001"]),
+            None,
+            DatetimeArray._from_sequence(["2000", "2001"], dtype="M8[ns]"),
+        ),
+        (
+            ["2000", "2001"],
+            np.dtype("datetime64[ns]"),
+            DatetimeArray._from_sequence(["2000", "2001"], dtype="M8[ns]"),
+        ),
+        # Datetime (tz-aware)
+        (
+            ["2000", "2001"],
+            pd.DatetimeTZDtype(tz="CET"),
+            DatetimeArray._from_sequence(
+                ["2000", "2001"], dtype=pd.DatetimeTZDtype(tz="CET")
+            ),
+        ),
+        # Timedelta
+        (
+            ["1h", "2h"],
+            np.dtype("timedelta64[ns]"),
+            TimedeltaArray._from_sequence(["1h", "2h"], dtype="m8[ns]"),
+        ),
+        (
+            pd.TimedeltaIndex(["1h", "2h"]),
+            np.dtype("timedelta64[ns]"),
+            TimedeltaArray._from_sequence(["1h", "2h"], dtype="m8[ns]"),
+        ),
+        (
+            np.array([1, 2], dtype="m8[s]"),
+            np.dtype("timedelta64[s]"),
+            TimedeltaArray._from_sequence(
+                np.array([1, 2], dtype="m8[s]"), dtype="m8[s]"
+            ),
+        ),
+        (
+            pd.TimedeltaIndex(["1h", "2h"]),
+            None,
+            TimedeltaArray._from_sequence(["1h", "2h"], dtype="m8[ns]"),
+        ),
+        (
+            # preserve non-nano, i.e. don't cast to NumpyExtensionArray
+            TimedeltaArray._simple_new(
+                np.arange(5, dtype=np.int64).view("m8[s]"), dtype=np.dtype("m8[s]")
+            ),
+            None,
+            TimedeltaArray._simple_new(
+                np.arange(5, dtype=np.int64).view("m8[s]"), dtype=np.dtype("m8[s]")
+            ),
+        ),
+        (
+            # preserve non-nano, i.e. don't cast to NumpyExtensionArray
+            TimedeltaArray._simple_new(
+                np.arange(5, dtype=np.int64).view("m8[s]"), dtype=np.dtype("m8[s]")
+            ),
+            np.dtype("m8[s]"),
+            TimedeltaArray._simple_new(
+                np.arange(5, dtype=np.int64).view("m8[s]"), dtype=np.dtype("m8[s]")
+            ),
+        ),
+        # Category
+        (["a", "b"], "category", pd.Categorical(["a", "b"])),
+        (
+            ["a", "b"],
+            pd.CategoricalDtype(None, ordered=True),
+            pd.Categorical(["a", "b"], ordered=True),
+        ),
+        # Interval
+        (
+            [pd.Interval(1, 2), pd.Interval(3, 4)],
+            "interval",
+            IntervalArray.from_tuples([(1, 2), (3, 4)]),
+        ),
+        # Sparse
+        ([0, 1], "Sparse[int64]", SparseArray([0, 1], dtype="int64")),
+        # IntegerNA
+        ([1, None], "Int16", pd.array([1, None], dtype="Int16")),
+        (
+            pd.Series([1, 2]),
+            None,
+            NumpyExtensionArray(np.array([1, 2], dtype=np.int64)),
+        ),
+        # String
+        (
+            ["a", None],
+            "string",
+            pd.StringDtype()
+            .construct_array_type()
+            ._from_sequence(["a", None], dtype=pd.StringDtype()),
+        ),
+        (
+            ["a", None],
+            pd.StringDtype(),
+            pd.StringDtype()
+            .construct_array_type()
+            ._from_sequence(["a", None], dtype=pd.StringDtype()),
+        ),
+        # Boolean
+        (
+            [True, None],
+            "boolean",
+            BooleanArray._from_sequence([True, None], dtype="boolean"),
+        ),
+        (
+            [True, None],
+            pd.BooleanDtype(),
+            BooleanArray._from_sequence([True, None], dtype="boolean"),
+        ),
+        # Index
+        (pd.Index([1, 2]), None, NumpyExtensionArray(np.array([1, 2], dtype=np.int64))),
+        # Series[EA] returns the EA
+        (
+            pd.Series(pd.Categorical(["a", "b"], categories=["a", "b", "c"])),
+            None,
+            pd.Categorical(["a", "b"], categories=["a", "b", "c"]),
+        ),
+        # "3rd party" EAs work
+        ([decimal.Decimal(0), decimal.Decimal(1)], "decimal", to_decimal([0, 1])),
+        # pass an ExtensionArray, but a different dtype
+        (
+            period_array(["2000", "2001"], freq="D"),
+            "category",
+            pd.Categorical([pd.Period("2000", "D"), pd.Period("2001", "D")]),
+        ),
+    ],
+)
+def test_array(data, dtype, expected):
+    result = pd.array(data, dtype=dtype)
+    tm.assert_equal(result, expected)
+
+
+def test_array_copy():
+    a = np.array([1, 2])
+    # default is to copy
+    b = pd.array(a, dtype=a.dtype)
+    assert not tm.shares_memory(a, b)
+
+    # copy=True
+    b = pd.array(a, dtype=a.dtype, copy=True)
+    assert not tm.shares_memory(a, b)
+
+    # copy=False
+    b = pd.array(a, dtype=a.dtype, copy=False)
+    assert tm.shares_memory(a, b)
+
+
+cet = pytz.timezone("CET")
+
+
+@pytest.mark.parametrize(
+    "data, expected",
+    [
+        # period
+        (
+            [pd.Period("2000", "D"), pd.Period("2001", "D")],
+            period_array(["2000", "2001"], freq="D"),
+        ),
+        # interval
+        ([pd.Interval(0, 1), pd.Interval(1, 2)], IntervalArray.from_breaks([0, 1, 2])),
+        # datetime
+        (
+            [pd.Timestamp("2000"), pd.Timestamp("2001")],
+            DatetimeArray._from_sequence(["2000", "2001"], dtype="M8[ns]"),
+        ),
+        (
+            [datetime.datetime(2000, 1, 1), datetime.datetime(2001, 1, 1)],
+            DatetimeArray._from_sequence(["2000", "2001"], dtype="M8[ns]"),
+        ),
+        (
+            np.array([1, 2], dtype="M8[ns]"),
+            DatetimeArray._from_sequence(np.array([1, 2], dtype="M8[ns]")),
+        ),
+        (
+            np.array([1, 2], dtype="M8[us]"),
+            DatetimeArray._simple_new(
+                np.array([1, 2], dtype="M8[us]"), dtype=np.dtype("M8[us]")
+            ),
+        ),
+        # datetimetz
+        (
+            [pd.Timestamp("2000", tz="CET"), pd.Timestamp("2001", tz="CET")],
+            DatetimeArray._from_sequence(
+                ["2000", "2001"], dtype=pd.DatetimeTZDtype(tz="CET", unit="ns")
+            ),
+        ),
+        (
+            [
+                datetime.datetime(2000, 1, 1, tzinfo=cet),
+                datetime.datetime(2001, 1, 1, tzinfo=cet),
+            ],
+            DatetimeArray._from_sequence(
+                ["2000", "2001"], dtype=pd.DatetimeTZDtype(tz=cet, unit="ns")
+            ),
+        ),
+        # timedelta
+        (
+            [pd.Timedelta("1h"), pd.Timedelta("2h")],
+            TimedeltaArray._from_sequence(["1h", "2h"], dtype="m8[ns]"),
+        ),
+        (
+            np.array([1, 2], dtype="m8[ns]"),
+            TimedeltaArray._from_sequence(np.array([1, 2], dtype="m8[ns]")),
+        ),
+        (
+            np.array([1, 2], dtype="m8[us]"),
+            TimedeltaArray._from_sequence(np.array([1, 2], dtype="m8[us]")),
+        ),
+        # integer
+        ([1, 2], IntegerArray._from_sequence([1, 2], dtype="Int64")),
+        ([1, None], IntegerArray._from_sequence([1, None], dtype="Int64")),
+        ([1, pd.NA], IntegerArray._from_sequence([1, pd.NA], dtype="Int64")),
+        ([1, np.nan], IntegerArray._from_sequence([1, np.nan], dtype="Int64")),
+        # float
+        ([0.1, 0.2], FloatingArray._from_sequence([0.1, 0.2], dtype="Float64")),
+        ([0.1, None], FloatingArray._from_sequence([0.1, pd.NA], dtype="Float64")),
+        ([0.1, np.nan], FloatingArray._from_sequence([0.1, pd.NA], dtype="Float64")),
+        ([0.1, pd.NA], FloatingArray._from_sequence([0.1, pd.NA], dtype="Float64")),
+        # integer-like float
+        ([1.0, 2.0], FloatingArray._from_sequence([1.0, 2.0], dtype="Float64")),
+        ([1.0, None], FloatingArray._from_sequence([1.0, pd.NA], dtype="Float64")),
+        ([1.0, np.nan], FloatingArray._from_sequence([1.0, pd.NA], dtype="Float64")),
+        ([1.0, pd.NA], FloatingArray._from_sequence([1.0, pd.NA], dtype="Float64")),
+        # mixed-integer-float
+        ([1, 2.0], FloatingArray._from_sequence([1.0, 2.0], dtype="Float64")),
+        (
+            [1, np.nan, 2.0],
+            FloatingArray._from_sequence([1.0, None, 2.0], dtype="Float64"),
+        ),
+        # string
+        (
+            ["a", "b"],
+            pd.StringDtype()
+            .construct_array_type()
+            ._from_sequence(["a", "b"], dtype=pd.StringDtype()),
+        ),
+        (
+            ["a", None],
+            pd.StringDtype()
+            .construct_array_type()
+            ._from_sequence(["a", None], dtype=pd.StringDtype()),
+        ),
+        # Boolean
+        ([True, False], BooleanArray._from_sequence([True, False], dtype="boolean")),
+        ([True, None], BooleanArray._from_sequence([True, None], dtype="boolean")),
+    ],
+)
+def test_array_inference(data, expected):
+    result = pd.array(data)
+    tm.assert_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "data",
+    [
+        # mix of frequencies
+        [pd.Period("2000", "D"), pd.Period("2001", "Y")],
+        # mix of closed
+        [pd.Interval(0, 1, closed="left"), pd.Interval(1, 2, closed="right")],
+        # Mix of timezones
+        [pd.Timestamp("2000", tz="CET"), pd.Timestamp("2000", tz="UTC")],
+        # Mix of tz-aware and tz-naive
+        [pd.Timestamp("2000", tz="CET"), pd.Timestamp("2000")],
+        np.array([pd.Timestamp("2000"), pd.Timestamp("2000", tz="CET")]),
+    ],
+)
+def test_array_inference_fails(data):
+    result = pd.array(data)
+    expected = NumpyExtensionArray(np.array(data, dtype=object))
+    tm.assert_extension_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("data", [np.array(0)])
+def test_nd_raises(data):
+    with pytest.raises(ValueError, match="NumpyExtensionArray must be 1-dimensional"):
+        pd.array(data, dtype="int64")
+
+
+def test_scalar_raises():
+    with pytest.raises(ValueError, match="Cannot pass scalar '1'"):
+        pd.array(1)
+
+
+def test_dataframe_raises():
+    # GH#51167 don't accidentally cast to StringArray by doing inference on columns
+    df = pd.DataFrame([[1, 2], [3, 4]], columns=["A", "B"])
+    msg = "Cannot pass DataFrame to 'pandas.array'"
+    with pytest.raises(TypeError, match=msg):
+        pd.array(df)
+
+
+def test_bounds_check():
+    # GH21796
+    with pytest.raises(
+        TypeError, match=r"cannot safely cast non-equivalent int(32|64) to uint16"
+    ):
+        pd.array([-1, 2, 3], dtype="UInt16")
+
+
+# ---------------------------------------------------------------------------
+# A couple dummy classes to ensure that Series and Indexes are unboxed before
+# getting to the EA classes.
+
+
+@register_extension_dtype
+class DecimalDtype2(DecimalDtype):
+    name = "decimal2"
+
+    @classmethod
+    def construct_array_type(cls):
+        """
+        Return the array type associated with this dtype.
+
+        Returns
+        -------
+        type
+        """
+        return DecimalArray2
+
+
+class DecimalArray2(DecimalArray):
+    @classmethod
+    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
+        if isinstance(scalars, (pd.Series, pd.Index)):
+            raise TypeError("scalars should not be of type pd.Series or pd.Index")
+
+        return super()._from_sequence(scalars, dtype=dtype, copy=copy)
+
+
+def test_array_unboxes(index_or_series):
+    box = index_or_series
+
+    data = box([decimal.Decimal("1"), decimal.Decimal("2")])
+    dtype = DecimalDtype2()
+    # make sure it works
+    with pytest.raises(
+        TypeError, match="scalars should not be of type pd.Series or pd.Index"
+    ):
+        DecimalArray2._from_sequence(data, dtype=dtype)
+
+    result = pd.array(data, dtype="decimal2")
+    expected = DecimalArray2._from_sequence(data.values, dtype=dtype)
+    tm.assert_equal(result, expected)
+
+
+def test_array_to_numpy_na():
+    # GH#40638
+    arr = pd.array([pd.NA, 1], dtype="string[python]")
+    result = arr.to_numpy(na_value=True, dtype=bool)
+    expected = np.array([True, True])
+    tm.assert_numpy_array_equal(result, expected)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/arrays/test_datetimelike.py

@@ -0,0 +1,1344 @@
+from __future__ import annotations
+
+import re
+import warnings
+
+import numpy as np
+import pytest
+
+from pandas._libs import (
+    NaT,
+    OutOfBoundsDatetime,
+    Timestamp,
+)
+from pandas._libs.tslibs.dtypes import freq_to_period_freqstr
+from pandas.compat.numpy import np_version_gt2
+
+import pandas as pd
+from pandas import (
+    DatetimeIndex,
+    Period,
+    PeriodIndex,
+    TimedeltaIndex,
+)
+import pandas._testing as tm
+from pandas.core.arrays import (
+    DatetimeArray,
+    NumpyExtensionArray,
+    PeriodArray,
+    TimedeltaArray,
+)
+
+
+# TODO: more freq variants
+@pytest.fixture(params=["D", "B", "W", "ME", "QE", "YE"])
+def freqstr(request):
+    """Fixture returning parametrized frequency in string format."""
+    return request.param
+
+
+@pytest.fixture
+def period_index(freqstr):
+    """
+    A fixture to provide PeriodIndex objects with different frequencies.
+
+    Most PeriodArray behavior is already tested in PeriodIndex tests,
+    so here we just test that the PeriodArray behavior matches
+    the PeriodIndex behavior.
+    """
+    # TODO: non-monotone indexes; NaTs, different start dates
+    with warnings.catch_warnings():
+        # suppress deprecation of Period[B]
+        warnings.filterwarnings(
+            "ignore", message="Period with BDay freq", category=FutureWarning
+        )
+        freqstr = freq_to_period_freqstr(1, freqstr)
+        pi = pd.period_range(start=Timestamp("2000-01-01"), periods=100, freq=freqstr)
+    return pi
+
+
+@pytest.fixture
+def datetime_index(freqstr):
+    """
+    A fixture to provide DatetimeIndex objects with different frequencies.
+
+    Most DatetimeArray behavior is already tested in DatetimeIndex tests,
+    so here we just test that the DatetimeArray behavior matches
+    the DatetimeIndex behavior.
+    """
+    # TODO: non-monotone indexes; NaTs, different start dates, timezones
+    dti = pd.date_range(start=Timestamp("2000-01-01"), periods=100, freq=freqstr)
+    return dti
+
+
+@pytest.fixture
+def timedelta_index():
+    """
+    A fixture to provide TimedeltaIndex objects with different frequencies.
+     Most TimedeltaArray behavior is already tested in TimedeltaIndex tests,
+    so here we just test that the TimedeltaArray behavior matches
+    the TimedeltaIndex behavior.
+    """
+    # TODO: flesh this out
+    return TimedeltaIndex(["1 Day", "3 Hours", "NaT"])
+
+
+class SharedTests:
+    index_cls: type[DatetimeIndex | PeriodIndex | TimedeltaIndex]
+
+    @pytest.fixture
+    def arr1d(self):
+        """Fixture returning DatetimeArray with daily frequency."""
+        data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        if self.array_cls is PeriodArray:
+            arr = self.array_cls(data, freq="D")
+        else:
+            arr = self.index_cls(data, freq="D")._data
+        return arr
+
+    def test_compare_len1_raises(self, arr1d):
+        # make sure we raise when comparing with different lengths, specific
+        #  to the case where one has length-1, which numpy would broadcast
+        arr = arr1d
+        idx = self.index_cls(arr)
+
+        with pytest.raises(ValueError, match="Lengths must match"):
+            arr == arr[:1]
+
+        # test the index classes while we're at it, GH#23078
+        with pytest.raises(ValueError, match="Lengths must match"):
+            idx <= idx[[0]]
+
+    @pytest.mark.parametrize(
+        "result",
+        [
+            pd.date_range("2020", periods=3),
+            pd.date_range("2020", periods=3, tz="UTC"),
+            pd.timedelta_range("0 days", periods=3),
+            pd.period_range("2020Q1", periods=3, freq="Q"),
+        ],
+    )
+    def test_compare_with_Categorical(self, result):
+        expected = pd.Categorical(result)
+        assert all(result == expected)
+        assert not any(result != expected)
+
+    @pytest.mark.parametrize("reverse", [True, False])
+    @pytest.mark.parametrize("as_index", [True, False])
+    def test_compare_categorical_dtype(self, arr1d, as_index, reverse, ordered):
+        other = pd.Categorical(arr1d, ordered=ordered)
+        if as_index:
+            other = pd.CategoricalIndex(other)
+
+        left, right = arr1d, other
+        if reverse:
+            left, right = right, left
+
+        ones = np.ones(arr1d.shape, dtype=bool)
+        zeros = ~ones
+
+        result = left == right
+        tm.assert_numpy_array_equal(result, ones)
+
+        result = left != right
+        tm.assert_numpy_array_equal(result, zeros)
+
+        if not reverse and not as_index:
+            # Otherwise Categorical raises TypeError bc it is not ordered
+            # TODO: we should probably get the same behavior regardless?
+            result = left < right
+            tm.assert_numpy_array_equal(result, zeros)
+
+            result = left <= right
+            tm.assert_numpy_array_equal(result, ones)
+
+            result = left > right
+            tm.assert_numpy_array_equal(result, zeros)
+
+            result = left >= right
+            tm.assert_numpy_array_equal(result, ones)
+
+    def test_take(self):
+        data = np.arange(100, dtype="i8") * 24 * 3600 * 10**9
+        np.random.default_rng(2).shuffle(data)
+
+        if self.array_cls is PeriodArray:
+            arr = PeriodArray(data, dtype="period[D]")
+        else:
+            arr = self.index_cls(data)._data
+        idx = self.index_cls._simple_new(arr)
+
+        takers = [1, 4, 94]
+        result = arr.take(takers)
+        expected = idx.take(takers)
+
+        tm.assert_index_equal(self.index_cls(result), expected)
+
+        takers = np.array([1, 4, 94])
+        result = arr.take(takers)
+        expected = idx.take(takers)
+
+        tm.assert_index_equal(self.index_cls(result), expected)
+
+    @pytest.mark.parametrize("fill_value", [2, 2.0, Timestamp(2021, 1, 1, 12).time])
+    def test_take_fill_raises(self, fill_value, arr1d):
+        msg = f"value should be a '{arr1d._scalar_type.__name__}' or 'NaT'. Got"
+        with pytest.raises(TypeError, match=msg):
+            arr1d.take([0, 1], allow_fill=True, fill_value=fill_value)
+
+    def test_take_fill(self, arr1d):
+        arr = arr1d
+
+        result = arr.take([-1, 1], allow_fill=True, fill_value=None)
+        assert result[0] is NaT
+
+        result = arr.take([-1, 1], allow_fill=True, fill_value=np.nan)
+        assert result[0] is NaT
+
+        result = arr.take([-1, 1], allow_fill=True, fill_value=NaT)
+        assert result[0] is NaT
+
+    @pytest.mark.filterwarnings(
+        "ignore:Period with BDay freq is deprecated:FutureWarning"
+    )
+    def test_take_fill_str(self, arr1d):
+        # Cast str fill_value matching other fill_value-taking methods
+        result = arr1d.take([-1, 1], allow_fill=True, fill_value=str(arr1d[-1]))
+        expected = arr1d[[-1, 1]]
+        tm.assert_equal(result, expected)
+
+        msg = f"value should be a '{arr1d._scalar_type.__name__}' or 'NaT'. Got"
+        with pytest.raises(TypeError, match=msg):
+            arr1d.take([-1, 1], allow_fill=True, fill_value="foo")
+
+    def test_concat_same_type(self, arr1d):
+        arr = arr1d
+        idx = self.index_cls(arr)
+        idx = idx.insert(0, NaT)
+        arr = arr1d
+
+        result = arr._concat_same_type([arr[:-1], arr[1:], arr])
+        arr2 = arr.astype(object)
+        expected = self.index_cls(np.concatenate([arr2[:-1], arr2[1:], arr2]))
+
+        tm.assert_index_equal(self.index_cls(result), expected)
+
+    def test_unbox_scalar(self, arr1d):
+        result = arr1d._unbox_scalar(arr1d[0])
+        expected = arr1d._ndarray.dtype.type
+        assert isinstance(result, expected)
+
+        result = arr1d._unbox_scalar(NaT)
+        assert isinstance(result, expected)
+
+        msg = f"'value' should be a {self.scalar_type.__name__}."
+        with pytest.raises(ValueError, match=msg):
+            arr1d._unbox_scalar("foo")
+
+    def test_check_compatible_with(self, arr1d):
+        arr1d._check_compatible_with(arr1d[0])
+        arr1d._check_compatible_with(arr1d[:1])
+        arr1d._check_compatible_with(NaT)
+
+    def test_scalar_from_string(self, arr1d):
+        result = arr1d._scalar_from_string(str(arr1d[0]))
+        assert result == arr1d[0]
+
+    def test_reduce_invalid(self, arr1d):
+        msg = "does not support reduction 'not a method'"
+        with pytest.raises(TypeError, match=msg):
+            arr1d._reduce("not a method")
+
+    @pytest.mark.parametrize("method", ["pad", "backfill"])
+    def test_fillna_method_doesnt_change_orig(self, method):
+        data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        if self.array_cls is PeriodArray:
+            arr = self.array_cls(data, dtype="period[D]")
+        else:
+            arr = self.array_cls._from_sequence(data)
+        arr[4] = NaT
+
+        fill_value = arr[3] if method == "pad" else arr[5]
+
+        result = arr._pad_or_backfill(method=method)
+        assert result[4] == fill_value
+
+        # check that the original was not changed
+        assert arr[4] is NaT
+
+    def test_searchsorted(self):
+        data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        if self.array_cls is PeriodArray:
+            arr = self.array_cls(data, dtype="period[D]")
+        else:
+            arr = self.array_cls._from_sequence(data)
+
+        # scalar
+        result = arr.searchsorted(arr[1])
+        assert result == 1
+
+        result = arr.searchsorted(arr[2], side="right")
+        assert result == 3
+
+        # own-type
+        result = arr.searchsorted(arr[1:3])
+        expected = np.array([1, 2], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = arr.searchsorted(arr[1:3], side="right")
+        expected = np.array([2, 3], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # GH#29884 match numpy convention on whether NaT goes
+        #  at the end or the beginning
+        result = arr.searchsorted(NaT)
+        assert result == 10
+
+    @pytest.mark.parametrize("box", [None, "index", "series"])
+    def test_searchsorted_castable_strings(self, arr1d, box, string_storage):
+        arr = arr1d
+        if box is None:
+            pass
+        elif box == "index":
+            # Test the equivalent Index.searchsorted method while we're here
+            arr = self.index_cls(arr)
+        else:
+            # Test the equivalent Series.searchsorted method while we're here
+            arr = pd.Series(arr)
+
+        # scalar
+        result = arr.searchsorted(str(arr[1]))
+        assert result == 1
+
+        result = arr.searchsorted(str(arr[2]), side="right")
+        assert result == 3
+
+        result = arr.searchsorted([str(x) for x in arr[1:3]])
+        expected = np.array([1, 2], dtype=np.intp)
+        tm.assert_numpy_array_equal(result, expected)
+
+        with pytest.raises(
+            TypeError,
+            match=re.escape(
+                f"value should be a '{arr1d._scalar_type.__name__}', 'NaT', "
+                "or array of those. Got 'str' instead."
+            ),
+        ):
+            arr.searchsorted("foo")
+
+        with pd.option_context("string_storage", string_storage):
+            with pytest.raises(
+                TypeError,
+                match=re.escape(
+                    f"value should be a '{arr1d._scalar_type.__name__}', 'NaT', "
+                    "or array of those. Got string array instead."
+                ),
+            ):
+                arr.searchsorted([str(arr[1]), "baz"])
+
+    def test_getitem_near_implementation_bounds(self):
+        # We only check tz-naive for DTA bc the bounds are slightly different
+        #  for other tzs
+        i8vals = np.asarray([NaT._value + n for n in range(1, 5)], dtype="i8")
+        if self.array_cls is PeriodArray:
+            arr = self.array_cls(i8vals, dtype="period[ns]")
+        else:
+            arr = self.index_cls(i8vals, freq="ns")._data
+        arr[0]  # should not raise OutOfBoundsDatetime
+
+        index = pd.Index(arr)
+        index[0]  # should not raise OutOfBoundsDatetime
+
+        ser = pd.Series(arr)
+        ser[0]  # should not raise OutOfBoundsDatetime
+
+    def test_getitem_2d(self, arr1d):
+        # 2d slicing on a 1D array
+        expected = type(arr1d)._simple_new(
+            arr1d._ndarray[:, np.newaxis], dtype=arr1d.dtype
+        )
+        result = arr1d[:, np.newaxis]
+        tm.assert_equal(result, expected)
+
+        # Lookup on a 2D array
+        arr2d = expected
+        expected = type(arr2d)._simple_new(arr2d._ndarray[:3, 0], dtype=arr2d.dtype)
+        result = arr2d[:3, 0]
+        tm.assert_equal(result, expected)
+
+        # Scalar lookup
+        result = arr2d[-1, 0]
+        expected = arr1d[-1]
+        assert result == expected
+
+    def test_iter_2d(self, arr1d):
+        data2d = arr1d._ndarray[:3, np.newaxis]
+        arr2d = type(arr1d)._simple_new(data2d, dtype=arr1d.dtype)
+        result = list(arr2d)
+        assert len(result) == 3
+        for x in result:
+            assert isinstance(x, type(arr1d))
+            assert x.ndim == 1
+            assert x.dtype == arr1d.dtype
+
+    def test_repr_2d(self, arr1d):
+        data2d = arr1d._ndarray[:3, np.newaxis]
+        arr2d = type(arr1d)._simple_new(data2d, dtype=arr1d.dtype)
+
+        result = repr(arr2d)
+
+        if isinstance(arr2d, TimedeltaArray):
+            expected = (
+                f"<{type(arr2d).__name__}>\n"
+                "[\n"
+                f"['{arr1d[0]._repr_base()}'],\n"
+                f"['{arr1d[1]._repr_base()}'],\n"
+                f"['{arr1d[2]._repr_base()}']\n"
+                "]\n"
+                f"Shape: (3, 1), dtype: {arr1d.dtype}"
+            )
+        else:
+            expected = (
+                f"<{type(arr2d).__name__}>\n"
+                "[\n"
+                f"['{arr1d[0]}'],\n"
+                f"['{arr1d[1]}'],\n"
+                f"['{arr1d[2]}']\n"
+                "]\n"
+                f"Shape: (3, 1), dtype: {arr1d.dtype}"
+            )
+
+        assert result == expected
+
+    def test_setitem(self):
+        data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        if self.array_cls is PeriodArray:
+            arr = self.array_cls(data, dtype="period[D]")
+        else:
+            arr = self.index_cls(data, freq="D")._data
+
+        arr[0] = arr[1]
+        expected = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        expected[0] = expected[1]
+
+        tm.assert_numpy_array_equal(arr.asi8, expected)
+
+        arr[:2] = arr[-2:]
+        expected[:2] = expected[-2:]
+        tm.assert_numpy_array_equal(arr.asi8, expected)
+
+    @pytest.mark.parametrize(
+        "box",
+        [
+            pd.Index,
+            pd.Series,
+            np.array,
+            list,
+            NumpyExtensionArray,
+        ],
+    )
+    def test_setitem_object_dtype(self, box, arr1d):
+        expected = arr1d.copy()[::-1]
+        if expected.dtype.kind in ["m", "M"]:
+            expected = expected._with_freq(None)
+
+        vals = expected
+        if box is list:
+            vals = list(vals)
+        elif box is np.array:
+            # if we do np.array(x).astype(object) then dt64 and td64 cast to ints
+            vals = np.array(vals.astype(object))
+        elif box is NumpyExtensionArray:
+            vals = box(np.asarray(vals, dtype=object))
+        else:
+            vals = box(vals).astype(object)
+
+        arr1d[:] = vals
+
+        tm.assert_equal(arr1d, expected)
+
+    def test_setitem_strs(self, arr1d):
+        # Check that we parse strs in both scalar and listlike
+
+        # Setting list-like of strs
+        expected = arr1d.copy()
+        expected[[0, 1]] = arr1d[-2:]
+
+        result = arr1d.copy()
+        result[:2] = [str(x) for x in arr1d[-2:]]
+        tm.assert_equal(result, expected)
+
+        # Same thing but now for just a scalar str
+        expected = arr1d.copy()
+        expected[0] = arr1d[-1]
+
+        result = arr1d.copy()
+        result[0] = str(arr1d[-1])
+        tm.assert_equal(result, expected)
+
+    @pytest.mark.parametrize("as_index", [True, False])
+    def test_setitem_categorical(self, arr1d, as_index):
+        expected = arr1d.copy()[::-1]
+        if not isinstance(expected, PeriodArray):
+            expected = expected._with_freq(None)
+
+        cat = pd.Categorical(arr1d)
+        if as_index:
+            cat = pd.CategoricalIndex(cat)
+
+        arr1d[:] = cat[::-1]
+
+        tm.assert_equal(arr1d, expected)
+
+    def test_setitem_raises(self, arr1d):
+        arr = arr1d[:10]
+        val = arr[0]
+
+        with pytest.raises(IndexError, match="index 12 is out of bounds"):
+            arr[12] = val
+
+        with pytest.raises(TypeError, match="value should be a.* 'object'"):
+            arr[0] = object()
+
+        msg = "cannot set using a list-like indexer with a different length"
+        with pytest.raises(ValueError, match=msg):
+            # GH#36339
+            arr[[]] = [arr[1]]
+
+        msg = "cannot set using a slice indexer with a different length than"
+        with pytest.raises(ValueError, match=msg):
+            # GH#36339
+            arr[1:1] = arr[:3]
+
+    @pytest.mark.parametrize("box", [list, np.array, pd.Index, pd.Series])
+    def test_setitem_numeric_raises(self, arr1d, box):
+        # We dont case e.g. int64 to our own dtype for setitem
+
+        msg = (
+            f"value should be a '{arr1d._scalar_type.__name__}', "
+            "'NaT', or array of those. Got"
+        )
+        with pytest.raises(TypeError, match=msg):
+            arr1d[:2] = box([0, 1])
+
+        with pytest.raises(TypeError, match=msg):
+            arr1d[:2] = box([0.0, 1.0])
+
+    def test_inplace_arithmetic(self):
+        # GH#24115 check that iadd and isub are actually in-place
+        data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        if self.array_cls is PeriodArray:
+            arr = self.array_cls(data, dtype="period[D]")
+        else:
+            arr = self.index_cls(data, freq="D")._data
+
+        expected = arr + pd.Timedelta(days=1)
+        arr += pd.Timedelta(days=1)
+        tm.assert_equal(arr, expected)
+
+        expected = arr - pd.Timedelta(days=1)
+        arr -= pd.Timedelta(days=1)
+        tm.assert_equal(arr, expected)
+
+    def test_shift_fill_int_deprecated(self, arr1d):
+        # GH#31971, enforced in 2.0
+        with pytest.raises(TypeError, match="value should be a"):
+            arr1d.shift(1, fill_value=1)
+
+    def test_median(self, arr1d):
+        arr = arr1d
+        if len(arr) % 2 == 0:
+            # make it easier to define `expected`
+            arr = arr[:-1]
+
+        expected = arr[len(arr) // 2]
+
+        result = arr.median()
+        assert type(result) is type(expected)
+        assert result == expected
+
+        arr[len(arr) // 2] = NaT
+        if not isinstance(expected, Period):
+            expected = arr[len(arr) // 2 - 1 : len(arr) // 2 + 2].mean()
+
+        assert arr.median(skipna=False) is NaT
+
+        result = arr.median()
+        assert type(result) is type(expected)
+        assert result == expected
+
+        assert arr[:0].median() is NaT
+        assert arr[:0].median(skipna=False) is NaT
+
+        # 2d Case
+        arr2 = arr.reshape(-1, 1)
+
+        result = arr2.median(axis=None)
+        assert type(result) is type(expected)
+        assert result == expected
+
+        assert arr2.median(axis=None, skipna=False) is NaT
+
+        result = arr2.median(axis=0)
+        expected2 = type(arr)._from_sequence([expected], dtype=arr.dtype)
+        tm.assert_equal(result, expected2)
+
+        result = arr2.median(axis=0, skipna=False)
+        expected2 = type(arr)._from_sequence([NaT], dtype=arr.dtype)
+        tm.assert_equal(result, expected2)
+
+        result = arr2.median(axis=1)
+        tm.assert_equal(result, arr)
+
+        result = arr2.median(axis=1, skipna=False)
+        tm.assert_equal(result, arr)
+
+    def test_from_integer_array(self):
+        arr = np.array([1, 2, 3], dtype=np.int64)
+        data = pd.array(arr, dtype="Int64")
+        if self.array_cls is PeriodArray:
+            expected = self.array_cls(arr, dtype=self.example_dtype)
+            result = self.array_cls(data, dtype=self.example_dtype)
+        else:
+            expected = self.array_cls._from_sequence(arr, dtype=self.example_dtype)
+            result = self.array_cls._from_sequence(data, dtype=self.example_dtype)
+
+        tm.assert_extension_array_equal(result, expected)
+
+
+class TestDatetimeArray(SharedTests):
+    index_cls = DatetimeIndex
+    array_cls = DatetimeArray
+    scalar_type = Timestamp
+    example_dtype = "M8[ns]"
+
+    @pytest.fixture
+    def arr1d(self, tz_naive_fixture, freqstr):
+        """
+        Fixture returning DatetimeArray with parametrized frequency and
+        timezones
+        """
+        tz = tz_naive_fixture
+        dti = pd.date_range("2016-01-01 01:01:00", periods=5, freq=freqstr, tz=tz)
+        dta = dti._data
+        return dta
+
+    def test_round(self, arr1d):
+        # GH#24064
+        dti = self.index_cls(arr1d)
+
+        result = dti.round(freq="2min")
+        expected = dti - pd.Timedelta(minutes=1)
+        expected = expected._with_freq(None)
+        tm.assert_index_equal(result, expected)
+
+        dta = dti._data
+        result = dta.round(freq="2min")
+        expected = expected._data._with_freq(None)
+        tm.assert_datetime_array_equal(result, expected)
+
+    def test_array_interface(self, datetime_index):
+        arr = datetime_index._data
+        copy_false = None if np_version_gt2 else False
+
+        # default asarray gives the same underlying data (for tz naive)
+        result = np.asarray(arr)
+        expected = arr._ndarray
+        assert result is expected
+        tm.assert_numpy_array_equal(result, expected)
+        result = np.array(arr, copy=copy_false)
+        assert result is expected
+        tm.assert_numpy_array_equal(result, expected)
+
+        # specifying M8[ns] gives the same result as default
+        result = np.asarray(arr, dtype="datetime64[ns]")
+        expected = arr._ndarray
+        assert result is expected
+        tm.assert_numpy_array_equal(result, expected)
+        result = np.array(arr, dtype="datetime64[ns]", copy=copy_false)
+        assert result is expected
+        tm.assert_numpy_array_equal(result, expected)
+        result = np.array(arr, dtype="datetime64[ns]")
+        if not np_version_gt2:
+            # TODO: GH 57739
+            assert result is not expected
+        tm.assert_numpy_array_equal(result, expected)
+
+        # to object dtype
+        result = np.asarray(arr, dtype=object)
+        expected = np.array(list(arr), dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # to other dtype always copies
+        result = np.asarray(arr, dtype="int64")
+        assert result is not arr.asi8
+        assert not np.may_share_memory(arr, result)
+        expected = arr.asi8.copy()
+        tm.assert_numpy_array_equal(result, expected)
+
+        # other dtypes handled by numpy
+        for dtype in ["float64", str]:
+            result = np.asarray(arr, dtype=dtype)
+            expected = np.asarray(arr).astype(dtype)
+            tm.assert_numpy_array_equal(result, expected)
+
+    def test_array_object_dtype(self, arr1d):
+        # GH#23524
+        arr = arr1d
+        dti = self.index_cls(arr1d)
+
+        expected = np.array(list(dti))
+
+        result = np.array(arr, dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # also test the DatetimeIndex method while we're at it
+        result = np.array(dti, dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_array_tz(self, arr1d):
+        # GH#23524
+        arr = arr1d
+        dti = self.index_cls(arr1d)
+        copy_false = None if np_version_gt2 else False
+
+        expected = dti.asi8.view("M8[ns]")
+        result = np.array(arr, dtype="M8[ns]")
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = np.array(arr, dtype="datetime64[ns]")
+        tm.assert_numpy_array_equal(result, expected)
+
+        # check that we are not making copies when setting copy=copy_false
+        result = np.array(arr, dtype="M8[ns]", copy=copy_false)
+        assert result.base is expected.base
+        assert result.base is not None
+        result = np.array(arr, dtype="datetime64[ns]", copy=copy_false)
+        assert result.base is expected.base
+        assert result.base is not None
+
+    def test_array_i8_dtype(self, arr1d):
+        arr = arr1d
+        dti = self.index_cls(arr1d)
+        copy_false = None if np_version_gt2 else False
+
+        expected = dti.asi8
+        result = np.array(arr, dtype="i8")
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = np.array(arr, dtype=np.int64)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # check that we are still making copies when setting copy=copy_false
+        result = np.array(arr, dtype="i8", copy=copy_false)
+        assert result.base is not expected.base
+        assert result.base is None
+
+    def test_from_array_keeps_base(self):
+        # Ensure that DatetimeArray._ndarray.base isn't lost.
+        arr = np.array(["2000-01-01", "2000-01-02"], dtype="M8[ns]")
+        dta = DatetimeArray._from_sequence(arr)
+
+        assert dta._ndarray is arr
+        dta = DatetimeArray._from_sequence(arr[:0])
+        assert dta._ndarray.base is arr
+
+    def test_from_dti(self, arr1d):
+        arr = arr1d
+        dti = self.index_cls(arr1d)
+        assert list(dti) == list(arr)
+
+        # Check that Index.__new__ knows what to do with DatetimeArray
+        dti2 = pd.Index(arr)
+        assert isinstance(dti2, DatetimeIndex)
+        assert list(dti2) == list(arr)
+
+    def test_astype_object(self, arr1d):
+        arr = arr1d
+        dti = self.index_cls(arr1d)
+
+        asobj = arr.astype("O")
+        assert isinstance(asobj, np.ndarray)
+        assert asobj.dtype == "O"
+        assert list(asobj) == list(dti)
+
+    @pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning")
+    def test_to_period(self, datetime_index, freqstr):
+        dti = datetime_index
+        arr = dti._data
+
+        freqstr = freq_to_period_freqstr(1, freqstr)
+        expected = dti.to_period(freq=freqstr)
+        result = arr.to_period(freq=freqstr)
+        assert isinstance(result, PeriodArray)
+
+        tm.assert_equal(result, expected._data)
+
+    def test_to_period_2d(self, arr1d):
+        arr2d = arr1d.reshape(1, -1)
+
+        warn = None if arr1d.tz is None else UserWarning
+        with tm.assert_produces_warning(warn):
+            result = arr2d.to_period("D")
+            expected = arr1d.to_period("D").reshape(1, -1)
+        tm.assert_period_array_equal(result, expected)
+
+    @pytest.mark.parametrize("propname", DatetimeArray._bool_ops)
+    def test_bool_properties(self, arr1d, propname):
+        # in this case _bool_ops is just `is_leap_year`
+        dti = self.index_cls(arr1d)
+        arr = arr1d
+        assert dti.freq == arr.freq
+
+        result = getattr(arr, propname)
+        expected = np.array(getattr(dti, propname), dtype=result.dtype)
+
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("propname", DatetimeArray._field_ops)
+    def test_int_properties(self, arr1d, propname):
+        dti = self.index_cls(arr1d)
+        arr = arr1d
+
+        result = getattr(arr, propname)
+        expected = np.array(getattr(dti, propname), dtype=result.dtype)
+
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_take_fill_valid(self, arr1d, fixed_now_ts):
+        arr = arr1d
+        dti = self.index_cls(arr1d)
+
+        now = fixed_now_ts.tz_localize(dti.tz)
+        result = arr.take([-1, 1], allow_fill=True, fill_value=now)
+        assert result[0] == now
+
+        msg = f"value should be a '{arr1d._scalar_type.__name__}' or 'NaT'. Got"
+        with pytest.raises(TypeError, match=msg):
+            # fill_value Timedelta invalid
+            arr.take([-1, 1], allow_fill=True, fill_value=now - now)
+
+        with pytest.raises(TypeError, match=msg):
+            # fill_value Period invalid
+            arr.take([-1, 1], allow_fill=True, fill_value=Period("2014Q1"))
+
+        tz = None if dti.tz is not None else "US/Eastern"
+        now = fixed_now_ts.tz_localize(tz)
+        msg = "Cannot compare tz-naive and tz-aware datetime-like objects"
+        with pytest.raises(TypeError, match=msg):
+            # Timestamp with mismatched tz-awareness
+            arr.take([-1, 1], allow_fill=True, fill_value=now)
+
+        value = NaT._value
+        msg = f"value should be a '{arr1d._scalar_type.__name__}' or 'NaT'. Got"
+        with pytest.raises(TypeError, match=msg):
+            # require NaT, not iNaT, as it could be confused with an integer
+            arr.take([-1, 1], allow_fill=True, fill_value=value)
+
+        value = np.timedelta64("NaT", "ns")
+        with pytest.raises(TypeError, match=msg):
+            # require appropriate-dtype if we have a NA value
+            arr.take([-1, 1], allow_fill=True, fill_value=value)
+
+        if arr.tz is not None:
+            # GH#37356
+            # Assuming here that arr1d fixture does not include Australia/Melbourne
+            value = fixed_now_ts.tz_localize("Australia/Melbourne")
+            result = arr.take([-1, 1], allow_fill=True, fill_value=value)
+
+            expected = arr.take(
+                [-1, 1],
+                allow_fill=True,
+                fill_value=value.tz_convert(arr.dtype.tz),
+            )
+            tm.assert_equal(result, expected)
+
+    def test_concat_same_type_invalid(self, arr1d):
+        # different timezones
+        arr = arr1d
+
+        if arr.tz is None:
+            other = arr.tz_localize("UTC")
+        else:
+            other = arr.tz_localize(None)
+
+        with pytest.raises(ValueError, match="to_concat must have the same"):
+            arr._concat_same_type([arr, other])
+
+    def test_concat_same_type_different_freq(self, unit):
+        # we *can* concatenate DTI with different freqs.
+        a = pd.date_range("2000", periods=2, freq="D", tz="US/Central", unit=unit)._data
+        b = pd.date_range("2000", periods=2, freq="h", tz="US/Central", unit=unit)._data
+        result = DatetimeArray._concat_same_type([a, b])
+        expected = (
+            pd.to_datetime(
+                [
+                    "2000-01-01 00:00:00",
+                    "2000-01-02 00:00:00",
+                    "2000-01-01 00:00:00",
+                    "2000-01-01 01:00:00",
+                ]
+            )
+            .tz_localize("US/Central")
+            .as_unit(unit)
+            ._data
+        )
+
+        tm.assert_datetime_array_equal(result, expected)
+
+    def test_strftime(self, arr1d):
+        arr = arr1d
+
+        result = arr.strftime("%Y %b")
+        expected = np.array([ts.strftime("%Y %b") for ts in arr], dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_strftime_nat(self):
+        # GH 29578
+        arr = DatetimeIndex(["2019-01-01", NaT])._data
+
+        result = arr.strftime("%Y-%m-%d")
+        expected = np.array(["2019-01-01", np.nan], dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+
+class TestTimedeltaArray(SharedTests):
+    index_cls = TimedeltaIndex
+    array_cls = TimedeltaArray
+    scalar_type = pd.Timedelta
+    example_dtype = "m8[ns]"
+
+    def test_from_tdi(self):
+        tdi = TimedeltaIndex(["1 Day", "3 Hours"])
+        arr = tdi._data
+        assert list(arr) == list(tdi)
+
+        # Check that Index.__new__ knows what to do with TimedeltaArray
+        tdi2 = pd.Index(arr)
+        assert isinstance(tdi2, TimedeltaIndex)
+        assert list(tdi2) == list(arr)
+
+    def test_astype_object(self):
+        tdi = TimedeltaIndex(["1 Day", "3 Hours"])
+        arr = tdi._data
+        asobj = arr.astype("O")
+        assert isinstance(asobj, np.ndarray)
+        assert asobj.dtype == "O"
+        assert list(asobj) == list(tdi)
+
+    def test_to_pytimedelta(self, timedelta_index):
+        tdi = timedelta_index
+        arr = tdi._data
+
+        expected = tdi.to_pytimedelta()
+        result = arr.to_pytimedelta()
+
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_total_seconds(self, timedelta_index):
+        tdi = timedelta_index
+        arr = tdi._data
+
+        expected = tdi.total_seconds()
+        result = arr.total_seconds()
+
+        tm.assert_numpy_array_equal(result, expected.values)
+
+    @pytest.mark.parametrize("propname", TimedeltaArray._field_ops)
+    def test_int_properties(self, timedelta_index, propname):
+        tdi = timedelta_index
+        arr = tdi._data
+
+        result = getattr(arr, propname)
+        expected = np.array(getattr(tdi, propname), dtype=result.dtype)
+
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_array_interface(self, timedelta_index):
+        arr = timedelta_index._data
+        copy_false = None if np_version_gt2 else False
+
+        # default asarray gives the same underlying data
+        result = np.asarray(arr)
+        expected = arr._ndarray
+        assert result is expected
+        tm.assert_numpy_array_equal(result, expected)
+        result = np.array(arr, copy=copy_false)
+        assert result is expected
+        tm.assert_numpy_array_equal(result, expected)
+
+        # specifying m8[ns] gives the same result as default
+        result = np.asarray(arr, dtype="timedelta64[ns]")
+        expected = arr._ndarray
+        assert result is expected
+        tm.assert_numpy_array_equal(result, expected)
+        result = np.array(arr, dtype="timedelta64[ns]", copy=copy_false)
+        assert result is expected
+        tm.assert_numpy_array_equal(result, expected)
+        result = np.array(arr, dtype="timedelta64[ns]")
+        if not np_version_gt2:
+            # TODO: GH 57739
+            assert result is not expected
+        tm.assert_numpy_array_equal(result, expected)
+
+        # to object dtype
+        result = np.asarray(arr, dtype=object)
+        expected = np.array(list(arr), dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # to other dtype always copies
+        result = np.asarray(arr, dtype="int64")
+        assert result is not arr.asi8
+        assert not np.may_share_memory(arr, result)
+        expected = arr.asi8.copy()
+        tm.assert_numpy_array_equal(result, expected)
+
+        # other dtypes handled by numpy
+        for dtype in ["float64", str]:
+            result = np.asarray(arr, dtype=dtype)
+            expected = np.asarray(arr).astype(dtype)
+            tm.assert_numpy_array_equal(result, expected)
+
+    def test_take_fill_valid(self, timedelta_index, fixed_now_ts):
+        tdi = timedelta_index
+        arr = tdi._data
+
+        td1 = pd.Timedelta(days=1)
+        result = arr.take([-1, 1], allow_fill=True, fill_value=td1)
+        assert result[0] == td1
+
+        value = fixed_now_ts
+        msg = f"value should be a '{arr._scalar_type.__name__}' or 'NaT'. Got"
+        with pytest.raises(TypeError, match=msg):
+            # fill_value Timestamp invalid
+            arr.take([0, 1], allow_fill=True, fill_value=value)
+
+        value = fixed_now_ts.to_period("D")
+        with pytest.raises(TypeError, match=msg):
+            # fill_value Period invalid
+            arr.take([0, 1], allow_fill=True, fill_value=value)
+
+        value = np.datetime64("NaT", "ns")
+        with pytest.raises(TypeError, match=msg):
+            # require appropriate-dtype if we have a NA value
+            arr.take([-1, 1], allow_fill=True, fill_value=value)
+
+
+@pytest.mark.filterwarnings(r"ignore:Period with BDay freq is deprecated:FutureWarning")
+@pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning")
+class TestPeriodArray(SharedTests):
+    index_cls = PeriodIndex
+    array_cls = PeriodArray
+    scalar_type = Period
+    example_dtype = PeriodIndex([], freq="W").dtype
+
+    @pytest.fixture
+    def arr1d(self, period_index):
+        """
+        Fixture returning DatetimeArray from parametrized PeriodIndex objects
+        """
+        return period_index._data
+
+    def test_from_pi(self, arr1d):
+        pi = self.index_cls(arr1d)
+        arr = arr1d
+        assert list(arr) == list(pi)
+
+        # Check that Index.__new__ knows what to do with PeriodArray
+        pi2 = pd.Index(arr)
+        assert isinstance(pi2, PeriodIndex)
+        assert list(pi2) == list(arr)
+
+    def test_astype_object(self, arr1d):
+        pi = self.index_cls(arr1d)
+        arr = arr1d
+        asobj = arr.astype("O")
+        assert isinstance(asobj, np.ndarray)
+        assert asobj.dtype == "O"
+        assert list(asobj) == list(pi)
+
+    def test_take_fill_valid(self, arr1d):
+        arr = arr1d
+
+        value = NaT._value
+        msg = f"value should be a '{arr1d._scalar_type.__name__}' or 'NaT'. Got"
+        with pytest.raises(TypeError, match=msg):
+            # require NaT, not iNaT, as it could be confused with an integer
+            arr.take([-1, 1], allow_fill=True, fill_value=value)
+
+        value = np.timedelta64("NaT", "ns")
+        with pytest.raises(TypeError, match=msg):
+            # require appropriate-dtype if we have a NA value
+            arr.take([-1, 1], allow_fill=True, fill_value=value)
+
+    @pytest.mark.parametrize("how", ["S", "E"])
+    def test_to_timestamp(self, how, arr1d):
+        pi = self.index_cls(arr1d)
+        arr = arr1d
+
+        expected = DatetimeIndex(pi.to_timestamp(how=how))._data
+        result = arr.to_timestamp(how=how)
+        assert isinstance(result, DatetimeArray)
+
+        tm.assert_equal(result, expected)
+
+    def test_to_timestamp_roundtrip_bday(self):
+        # Case where infer_freq inside would choose "D" instead of "B"
+        dta = pd.date_range("2021-10-18", periods=3, freq="B")._data
+        parr = dta.to_period()
+        result = parr.to_timestamp()
+        assert result.freq == "B"
+        tm.assert_extension_array_equal(result, dta)
+
+        dta2 = dta[::2]
+        parr2 = dta2.to_period()
+        result2 = parr2.to_timestamp()
+        assert result2.freq == "2B"
+        tm.assert_extension_array_equal(result2, dta2)
+
+        parr3 = dta.to_period("2B")
+        result3 = parr3.to_timestamp()
+        assert result3.freq == "B"
+        tm.assert_extension_array_equal(result3, dta)
+
+    def test_to_timestamp_out_of_bounds(self):
+        # GH#19643 previously overflowed silently
+        pi = pd.period_range("1500", freq="Y", periods=3)
+        msg = "Out of bounds nanosecond timestamp: 1500-01-01 00:00:00"
+        with pytest.raises(OutOfBoundsDatetime, match=msg):
+            pi.to_timestamp()
+
+        with pytest.raises(OutOfBoundsDatetime, match=msg):
+            pi._data.to_timestamp()
+
+    @pytest.mark.parametrize("propname", PeriodArray._bool_ops)
+    def test_bool_properties(self, arr1d, propname):
+        # in this case _bool_ops is just `is_leap_year`
+        pi = self.index_cls(arr1d)
+        arr = arr1d
+
+        result = getattr(arr, propname)
+        expected = np.array(getattr(pi, propname))
+
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("propname", PeriodArray._field_ops)
+    def test_int_properties(self, arr1d, propname):
+        pi = self.index_cls(arr1d)
+        arr = arr1d
+
+        result = getattr(arr, propname)
+        expected = np.array(getattr(pi, propname))
+
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_array_interface(self, arr1d):
+        arr = arr1d
+
+        # default asarray gives objects
+        result = np.asarray(arr)
+        expected = np.array(list(arr), dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+        # to object dtype (same as default)
+        result = np.asarray(arr, dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = np.asarray(arr, dtype="int64")
+        tm.assert_numpy_array_equal(result, arr.asi8)
+
+        # to other dtypes
+        msg = r"float\(\) argument must be a string or a( real)? number, not 'Period'"
+        with pytest.raises(TypeError, match=msg):
+            np.asarray(arr, dtype="float64")
+
+        result = np.asarray(arr, dtype="S20")
+        expected = np.asarray(arr).astype("S20")
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_strftime(self, arr1d):
+        arr = arr1d
+
+        result = arr.strftime("%Y")
+        expected = np.array([per.strftime("%Y") for per in arr], dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_strftime_nat(self):
+        # GH 29578
+        arr = PeriodArray(PeriodIndex(["2019-01-01", NaT], dtype="period[D]"))
+
+        result = arr.strftime("%Y-%m-%d")
+        expected = np.array(["2019-01-01", np.nan], dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "arr,casting_nats",
+    [
+        (
+            TimedeltaIndex(["1 Day", "3 Hours", "NaT"])._data,
+            (NaT, np.timedelta64("NaT", "ns")),
+        ),
+        (
+            pd.date_range("2000-01-01", periods=3, freq="D")._data,
+            (NaT, np.datetime64("NaT", "ns")),
+        ),
+        (pd.period_range("2000-01-01", periods=3, freq="D")._data, (NaT,)),
+    ],
+    ids=lambda x: type(x).__name__,
+)
+def test_casting_nat_setitem_array(arr, casting_nats):
+    expected = type(arr)._from_sequence([NaT, arr[1], arr[2]], dtype=arr.dtype)
+
+    for nat in casting_nats:
+        arr = arr.copy()
+        arr[0] = nat
+        tm.assert_equal(arr, expected)
+
+
+@pytest.mark.parametrize(
+    "arr,non_casting_nats",
+    [
+        (
+            TimedeltaIndex(["1 Day", "3 Hours", "NaT"])._data,
+            (np.datetime64("NaT", "ns"), NaT._value),
+        ),
+        (
+            pd.date_range("2000-01-01", periods=3, freq="D")._data,
+            (np.timedelta64("NaT", "ns"), NaT._value),
+        ),
+        (
+            pd.period_range("2000-01-01", periods=3, freq="D")._data,
+            (np.datetime64("NaT", "ns"), np.timedelta64("NaT", "ns"), NaT._value),
+        ),
+    ],
+    ids=lambda x: type(x).__name__,
+)
+def test_invalid_nat_setitem_array(arr, non_casting_nats):
+    msg = (
+        "value should be a '(Timestamp|Timedelta|Period)', 'NaT', or array of those. "
+        "Got '(timedelta64|datetime64|int)' instead."
+    )
+
+    for nat in non_casting_nats:
+        with pytest.raises(TypeError, match=msg):
+            arr[0] = nat
+
+
+@pytest.mark.parametrize(
+    "arr",
+    [
+        pd.date_range("2000", periods=4).array,
+        pd.timedelta_range("2000", periods=4).array,
+    ],
+)
+def test_to_numpy_extra(arr):
+    arr[0] = NaT
+    original = arr.copy()
+
+    result = arr.to_numpy()
+    assert np.isnan(result[0])
+
+    result = arr.to_numpy(dtype="int64")
+    assert result[0] == -9223372036854775808
+
+    result = arr.to_numpy(dtype="int64", na_value=0)
+    assert result[0] == 0
+
+    result = arr.to_numpy(na_value=arr[1].to_numpy())
+    assert result[0] == result[1]
+
+    result = arr.to_numpy(na_value=arr[1].to_numpy(copy=False))
+    assert result[0] == result[1]
+
+    tm.assert_equal(arr, original)
+
+
+@pytest.mark.parametrize("as_index", [True, False])
+@pytest.mark.parametrize(
+    "values",
+    [
+        pd.to_datetime(["2020-01-01", "2020-02-01"]),
+        pd.to_timedelta([1, 2], unit="D"),
+        PeriodIndex(["2020-01-01", "2020-02-01"], freq="D"),
+    ],
+)
+@pytest.mark.parametrize(
+    "klass",
+    [
+        list,
+        np.array,
+        pd.array,
+        pd.Series,
+        pd.Index,
+        pd.Categorical,
+        pd.CategoricalIndex,
+    ],
+)
+def test_searchsorted_datetimelike_with_listlike(values, klass, as_index):
+    # https://github.com/pandas-dev/pandas/issues/32762
+    if not as_index:
+        values = values._data
+
+    result = values.searchsorted(klass(values))
+    expected = np.array([0, 1], dtype=result.dtype)
+
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "values",
+    [
+        pd.to_datetime(["2020-01-01", "2020-02-01"]),
+        pd.to_timedelta([1, 2], unit="D"),
+        PeriodIndex(["2020-01-01", "2020-02-01"], freq="D"),
+    ],
+)
+@pytest.mark.parametrize(
+    "arg", [[1, 2], ["a", "b"], [Timestamp("2020-01-01", tz="Europe/London")] * 2]
+)
+def test_searchsorted_datetimelike_with_listlike_invalid_dtype(values, arg):
+    # https://github.com/pandas-dev/pandas/issues/32762
+    msg = "[Unexpected type|Cannot compare]"
+    with pytest.raises(TypeError, match=msg):
+        values.searchsorted(arg)
+
+
+@pytest.mark.parametrize("klass", [list, tuple, np.array, pd.Series])
+def test_period_index_construction_from_strings(klass):
+    # https://github.com/pandas-dev/pandas/issues/26109
+    strings = ["2020Q1", "2020Q2"] * 2
+    data = klass(strings)
+    result = PeriodIndex(data, freq="Q")
+    expected = PeriodIndex([Period(s) for s in strings])
+    tm.assert_index_equal(result, expected)
+
+
+@pytest.mark.parametrize("dtype", ["M8[ns]", "m8[ns]"])
+def test_from_pandas_array(dtype):
+    # GH#24615
+    data = np.array([1, 2, 3], dtype=dtype)
+    arr = NumpyExtensionArray(data)
+
+    cls = {"M8[ns]": DatetimeArray, "m8[ns]": TimedeltaArray}[dtype]
+
+    depr_msg = f"{cls.__name__}.__init__ is deprecated"
+    with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+        result = cls(arr)
+        expected = cls(data)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = cls._from_sequence(arr, dtype=dtype)
+    expected = cls._from_sequence(data, dtype=dtype)
+    tm.assert_extension_array_equal(result, expected)
+
+    func = {"M8[ns]": pd.to_datetime, "m8[ns]": pd.to_timedelta}[dtype]
+    result = func(arr).array
+    expected = func(data).array
+    tm.assert_equal(result, expected)
+
+    # Let's check the Indexes while we're here
+    idx_cls = {"M8[ns]": DatetimeIndex, "m8[ns]": TimedeltaIndex}[dtype]
+    result = idx_cls(arr)
+    expected = idx_cls(data)
+    tm.assert_index_equal(result, expected)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/arrays/test_datetimes.py

@@ -0,0 +1,840 @@
+"""
+Tests for DatetimeArray
+"""
+from __future__ import annotations
+
+from datetime import timedelta
+import operator
+
+try:
+    from zoneinfo import ZoneInfo
+except ImportError:
+    # Cannot assign to a type
+    ZoneInfo = None  # type: ignore[misc, assignment]
+
+import numpy as np
+import pytest
+
+from pandas._libs.tslibs import tz_compare
+
+from pandas.core.dtypes.dtypes import DatetimeTZDtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import (
+    DatetimeArray,
+    TimedeltaArray,
+)
+
+
+class TestNonNano:
+    @pytest.fixture(params=["s", "ms", "us"])
+    def unit(self, request):
+        """Fixture returning parametrized time units"""
+        return request.param
+
+    @pytest.fixture
+    def dtype(self, unit, tz_naive_fixture):
+        tz = tz_naive_fixture
+        if tz is None:
+            return np.dtype(f"datetime64[{unit}]")
+        else:
+            return DatetimeTZDtype(unit=unit, tz=tz)
+
+    @pytest.fixture
+    def dta_dti(self, unit, dtype):
+        tz = getattr(dtype, "tz", None)
+
+        dti = pd.date_range("2016-01-01", periods=55, freq="D", tz=tz)
+        if tz is None:
+            arr = np.asarray(dti).astype(f"M8[{unit}]")
+        else:
+            arr = np.asarray(dti.tz_convert("UTC").tz_localize(None)).astype(
+                f"M8[{unit}]"
+            )
+
+        dta = DatetimeArray._simple_new(arr, dtype=dtype)
+        return dta, dti
+
+    @pytest.fixture
+    def dta(self, dta_dti):
+        dta, dti = dta_dti
+        return dta
+
+    def test_non_nano(self, unit, dtype):
+        arr = np.arange(5, dtype=np.int64).view(f"M8[{unit}]")
+        dta = DatetimeArray._simple_new(arr, dtype=dtype)
+
+        assert dta.dtype == dtype
+        assert dta[0].unit == unit
+        assert tz_compare(dta.tz, dta[0].tz)
+        assert (dta[0] == dta[:1]).all()
+
+    @pytest.mark.parametrize(
+        "field", DatetimeArray._field_ops + DatetimeArray._bool_ops
+    )
+    def test_fields(self, unit, field, dtype, dta_dti):
+        dta, dti = dta_dti
+
+        assert (dti == dta).all()
+
+        res = getattr(dta, field)
+        expected = getattr(dti._data, field)
+        tm.assert_numpy_array_equal(res, expected)
+
+    def test_normalize(self, unit):
+        dti = pd.date_range("2016-01-01 06:00:00", periods=55, freq="D")
+        arr = np.asarray(dti).astype(f"M8[{unit}]")
+
+        dta = DatetimeArray._simple_new(arr, dtype=arr.dtype)
+
+        assert not dta.is_normalized
+
+        # TODO: simplify once we can just .astype to other unit
+        exp = np.asarray(dti.normalize()).astype(f"M8[{unit}]")
+        expected = DatetimeArray._simple_new(exp, dtype=exp.dtype)
+
+        res = dta.normalize()
+        tm.assert_extension_array_equal(res, expected)
+
+    def test_simple_new_requires_match(self, unit):
+        arr = np.arange(5, dtype=np.int64).view(f"M8[{unit}]")
+        dtype = DatetimeTZDtype(unit, "UTC")
+
+        dta = DatetimeArray._simple_new(arr, dtype=dtype)
+        assert dta.dtype == dtype
+
+        wrong = DatetimeTZDtype("ns", "UTC")
+        with pytest.raises(AssertionError, match=""):
+            DatetimeArray._simple_new(arr, dtype=wrong)
+
+    def test_std_non_nano(self, unit):
+        dti = pd.date_range("2016-01-01", periods=55, freq="D")
+        arr = np.asarray(dti).astype(f"M8[{unit}]")
+
+        dta = DatetimeArray._simple_new(arr, dtype=arr.dtype)
+
+        # we should match the nano-reso std, but floored to our reso.
+        res = dta.std()
+        assert res._creso == dta._creso
+        assert res == dti.std().floor(unit)
+
+    @pytest.mark.filterwarnings("ignore:Converting to PeriodArray.*:UserWarning")
+    def test_to_period(self, dta_dti):
+        dta, dti = dta_dti
+        result = dta.to_period("D")
+        expected = dti._data.to_period("D")
+
+        tm.assert_extension_array_equal(result, expected)
+
+    def test_iter(self, dta):
+        res = next(iter(dta))
+        expected = dta[0]
+
+        assert type(res) is pd.Timestamp
+        assert res._value == expected._value
+        assert res._creso == expected._creso
+        assert res == expected
+
+    def test_astype_object(self, dta):
+        result = dta.astype(object)
+        assert all(x._creso == dta._creso for x in result)
+        assert all(x == y for x, y in zip(result, dta))
+
+    def test_to_pydatetime(self, dta_dti):
+        dta, dti = dta_dti
+
+        result = dta.to_pydatetime()
+        expected = dti.to_pydatetime()
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("meth", ["time", "timetz", "date"])
+    def test_time_date(self, dta_dti, meth):
+        dta, dti = dta_dti
+
+        result = getattr(dta, meth)
+        expected = getattr(dti, meth)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_format_native_types(self, unit, dtype, dta_dti):
+        # In this case we should get the same formatted values with our nano
+        #  version dti._data as we do with the non-nano dta
+        dta, dti = dta_dti
+
+        res = dta._format_native_types()
+        exp = dti._data._format_native_types()
+        tm.assert_numpy_array_equal(res, exp)
+
+    def test_repr(self, dta_dti, unit):
+        dta, dti = dta_dti
+
+        assert repr(dta) == repr(dti._data).replace("[ns", f"[{unit}")
+
+    # TODO: tests with td64
+    def test_compare_mismatched_resolutions(self, comparison_op):
+        # comparison that numpy gets wrong bc of silent overflows
+        op = comparison_op
+
+        iinfo = np.iinfo(np.int64)
+        vals = np.array([iinfo.min, iinfo.min + 1, iinfo.max], dtype=np.int64)
+
+        # Construct so that arr2[1] < arr[1] < arr[2] < arr2[2]
+        arr = np.array(vals).view("M8[ns]")
+        arr2 = arr.view("M8[s]")
+
+        left = DatetimeArray._simple_new(arr, dtype=arr.dtype)
+        right = DatetimeArray._simple_new(arr2, dtype=arr2.dtype)
+
+        if comparison_op is operator.eq:
+            expected = np.array([False, False, False])
+        elif comparison_op is operator.ne:
+            expected = np.array([True, True, True])
+        elif comparison_op in [operator.lt, operator.le]:
+            expected = np.array([False, False, True])
+        else:
+            expected = np.array([False, True, False])
+
+        result = op(left, right)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = op(left[1], right)
+        tm.assert_numpy_array_equal(result, expected)
+
+        if op not in [operator.eq, operator.ne]:
+            # check that numpy still gets this wrong; if it is fixed we may be
+            #  able to remove compare_mismatched_resolutions
+            np_res = op(left._ndarray, right._ndarray)
+            tm.assert_numpy_array_equal(np_res[1:], ~expected[1:])
+
+    def test_add_mismatched_reso_doesnt_downcast(self):
+        # https://github.com/pandas-dev/pandas/pull/48748#issuecomment-1260181008
+        td = pd.Timedelta(microseconds=1)
+        dti = pd.date_range("2016-01-01", periods=3) - td
+        dta = dti._data.as_unit("us")
+
+        res = dta + td.as_unit("us")
+        # even though the result is an even number of days
+        #  (so we _could_ downcast to unit="s"), we do not.
+        assert res.unit == "us"
+
+    @pytest.mark.parametrize(
+        "scalar",
+        [
+            timedelta(hours=2),
+            pd.Timedelta(hours=2),
+            np.timedelta64(2, "h"),
+            np.timedelta64(2 * 3600 * 1000, "ms"),
+            pd.offsets.Minute(120),
+            pd.offsets.Hour(2),
+        ],
+    )
+    def test_add_timedeltalike_scalar_mismatched_reso(self, dta_dti, scalar):
+        dta, dti = dta_dti
+
+        td = pd.Timedelta(scalar)
+        exp_unit = tm.get_finest_unit(dta.unit, td.unit)
+
+        expected = (dti + td)._data.as_unit(exp_unit)
+        result = dta + scalar
+        tm.assert_extension_array_equal(result, expected)
+
+        result = scalar + dta
+        tm.assert_extension_array_equal(result, expected)
+
+        expected = (dti - td)._data.as_unit(exp_unit)
+        result = dta - scalar
+        tm.assert_extension_array_equal(result, expected)
+
+    def test_sub_datetimelike_scalar_mismatch(self):
+        dti = pd.date_range("2016-01-01", periods=3)
+        dta = dti._data.as_unit("us")
+
+        ts = dta[0].as_unit("s")
+
+        result = dta - ts
+        expected = (dti - dti[0])._data.as_unit("us")
+        assert result.dtype == "m8[us]"
+        tm.assert_extension_array_equal(result, expected)
+
+    def test_sub_datetime64_reso_mismatch(self):
+        dti = pd.date_range("2016-01-01", periods=3)
+        left = dti._data.as_unit("s")
+        right = left.as_unit("ms")
+
+        result = left - right
+        exp_values = np.array([0, 0, 0], dtype="m8[ms]")
+        expected = TimedeltaArray._simple_new(
+            exp_values,
+            dtype=exp_values.dtype,
+        )
+        tm.assert_extension_array_equal(result, expected)
+        result2 = right - left
+        tm.assert_extension_array_equal(result2, expected)
+
+
+class TestDatetimeArrayComparisons:
+    # TODO: merge this into tests/arithmetic/test_datetime64 once it is
+    #  sufficiently robust
+
+    def test_cmp_dt64_arraylike_tznaive(self, comparison_op):
+        # arbitrary tz-naive DatetimeIndex
+        op = comparison_op
+
+        dti = pd.date_range("2016-01-1", freq="MS", periods=9, tz=None)
+        arr = dti._data
+        assert arr.freq == dti.freq
+        assert arr.tz == dti.tz
+
+        right = dti
+
+        expected = np.ones(len(arr), dtype=bool)
+        if comparison_op.__name__ in ["ne", "gt", "lt"]:
+            # for these the comparisons should be all-False
+            expected = ~expected
+
+        result = op(arr, arr)
+        tm.assert_numpy_array_equal(result, expected)
+        for other in [
+            right,
+            np.array(right),
+            list(right),
+            tuple(right),
+            right.astype(object),
+        ]:
+            result = op(arr, other)
+            tm.assert_numpy_array_equal(result, expected)
+
+            result = op(other, arr)
+            tm.assert_numpy_array_equal(result, expected)
+
+
+class TestDatetimeArray:
+    def test_astype_ns_to_ms_near_bounds(self):
+        # GH#55979
+        ts = pd.Timestamp("1677-09-21 00:12:43.145225")
+        target = ts.as_unit("ms")
+
+        dta = DatetimeArray._from_sequence([ts], dtype="M8[ns]")
+        assert (dta.view("i8") == ts.as_unit("ns").value).all()
+
+        result = dta.astype("M8[ms]")
+        assert result[0] == target
+
+        expected = DatetimeArray._from_sequence([ts], dtype="M8[ms]")
+        assert (expected.view("i8") == target._value).all()
+
+        tm.assert_datetime_array_equal(result, expected)
+
+    def test_astype_non_nano_tznaive(self):
+        dti = pd.date_range("2016-01-01", periods=3)
+
+        res = dti.astype("M8[s]")
+        assert res.dtype == "M8[s]"
+
+        dta = dti._data
+        res = dta.astype("M8[s]")
+        assert res.dtype == "M8[s]"
+        assert isinstance(res, pd.core.arrays.DatetimeArray)  # used to be ndarray
+
+    def test_astype_non_nano_tzaware(self):
+        dti = pd.date_range("2016-01-01", periods=3, tz="UTC")
+
+        res = dti.astype("M8[s, US/Pacific]")
+        assert res.dtype == "M8[s, US/Pacific]"
+
+        dta = dti._data
+        res = dta.astype("M8[s, US/Pacific]")
+        assert res.dtype == "M8[s, US/Pacific]"
+
+        # from non-nano to non-nano, preserving reso
+        res2 = res.astype("M8[s, UTC]")
+        assert res2.dtype == "M8[s, UTC]"
+        assert not tm.shares_memory(res2, res)
+
+        res3 = res.astype("M8[s, UTC]", copy=False)
+        assert res2.dtype == "M8[s, UTC]"
+        assert tm.shares_memory(res3, res)
+
+    def test_astype_to_same(self):
+        arr = DatetimeArray._from_sequence(
+            ["2000"], dtype=DatetimeTZDtype(tz="US/Central")
+        )
+        result = arr.astype(DatetimeTZDtype(tz="US/Central"), copy=False)
+        assert result is arr
+
+    @pytest.mark.parametrize("dtype", ["datetime64[ns]", "datetime64[ns, UTC]"])
+    @pytest.mark.parametrize(
+        "other", ["datetime64[ns]", "datetime64[ns, UTC]", "datetime64[ns, CET]"]
+    )
+    def test_astype_copies(self, dtype, other):
+        # https://github.com/pandas-dev/pandas/pull/32490
+        ser = pd.Series([1, 2], dtype=dtype)
+        orig = ser.copy()
+
+        err = False
+        if (dtype == "datetime64[ns]") ^ (other == "datetime64[ns]"):
+            # deprecated in favor of tz_localize
+            err = True
+
+        if err:
+            if dtype == "datetime64[ns]":
+                msg = "Use obj.tz_localize instead or series.dt.tz_localize instead"
+            else:
+                msg = "from timezone-aware dtype to timezone-naive dtype"
+            with pytest.raises(TypeError, match=msg):
+                ser.astype(other)
+        else:
+            t = ser.astype(other)
+            t[:] = pd.NaT
+            tm.assert_series_equal(ser, orig)
+
+    @pytest.mark.parametrize("dtype", [int, np.int32, np.int64, "uint32", "uint64"])
+    def test_astype_int(self, dtype):
+        arr = DatetimeArray._from_sequence(
+            [pd.Timestamp("2000"), pd.Timestamp("2001")], dtype="M8[ns]"
+        )
+
+        if np.dtype(dtype) != np.int64:
+            with pytest.raises(TypeError, match=r"Do obj.astype\('int64'\)"):
+                arr.astype(dtype)
+            return
+
+        result = arr.astype(dtype)
+        expected = arr._ndarray.view("i8")
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_astype_to_sparse_dt64(self):
+        # GH#50082
+        dti = pd.date_range("2016-01-01", periods=4)
+        dta = dti._data
+        result = dta.astype("Sparse[datetime64[ns]]")
+
+        assert result.dtype == "Sparse[datetime64[ns]]"
+        assert (result == dta).all()
+
+    def test_tz_setter_raises(self):
+        arr = DatetimeArray._from_sequence(
+            ["2000"], dtype=DatetimeTZDtype(tz="US/Central")
+        )
+        with pytest.raises(AttributeError, match="tz_localize"):
+            arr.tz = "UTC"
+
+    def test_setitem_str_impute_tz(self, tz_naive_fixture):
+        # Like for getitem, if we are passed a naive-like string, we impute
+        #  our own timezone.
+        tz = tz_naive_fixture
+
+        data = np.array([1, 2, 3], dtype="M8[ns]")
+        dtype = data.dtype if tz is None else DatetimeTZDtype(tz=tz)
+        arr = DatetimeArray._from_sequence(data, dtype=dtype)
+        expected = arr.copy()
+
+        ts = pd.Timestamp("2020-09-08 16:50").tz_localize(tz)
+        setter = str(ts.tz_localize(None))
+
+        # Setting a scalar tznaive string
+        expected[0] = ts
+        arr[0] = setter
+        tm.assert_equal(arr, expected)
+
+        # Setting a listlike of tznaive strings
+        expected[1] = ts
+        arr[:2] = [setter, setter]
+        tm.assert_equal(arr, expected)
+
+    def test_setitem_different_tz_raises(self):
+        # pre-2.0 we required exact tz match, in 2.0 we require only
+        #  tzawareness-match
+        data = np.array([1, 2, 3], dtype="M8[ns]")
+        arr = DatetimeArray._from_sequence(
+            data, copy=False, dtype=DatetimeTZDtype(tz="US/Central")
+        )
+        with pytest.raises(TypeError, match="Cannot compare tz-naive and tz-aware"):
+            arr[0] = pd.Timestamp("2000")
+
+        ts = pd.Timestamp("2000", tz="US/Eastern")
+        arr[0] = ts
+        assert arr[0] == ts.tz_convert("US/Central")
+
+    def test_setitem_clears_freq(self):
+        a = pd.date_range("2000", periods=2, freq="D", tz="US/Central")._data
+        a[0] = pd.Timestamp("2000", tz="US/Central")
+        assert a.freq is None
+
+    @pytest.mark.parametrize(
+        "obj",
+        [
+            pd.Timestamp("2021-01-01"),
+            pd.Timestamp("2021-01-01").to_datetime64(),
+            pd.Timestamp("2021-01-01").to_pydatetime(),
+        ],
+    )
+    def test_setitem_objects(self, obj):
+        # make sure we accept datetime64 and datetime in addition to Timestamp
+        dti = pd.date_range("2000", periods=2, freq="D")
+        arr = dti._data
+
+        arr[0] = obj
+        assert arr[0] == obj
+
+    def test_repeat_preserves_tz(self):
+        dti = pd.date_range("2000", periods=2, freq="D", tz="US/Central")
+        arr = dti._data
+
+        repeated = arr.repeat([1, 1])
+
+        # preserves tz and values, but not freq
+        expected = DatetimeArray._from_sequence(arr.asi8, dtype=arr.dtype)
+        tm.assert_equal(repeated, expected)
+
+    def test_value_counts_preserves_tz(self):
+        dti = pd.date_range("2000", periods=2, freq="D", tz="US/Central")
+        arr = dti._data.repeat([4, 3])
+
+        result = arr.value_counts()
+
+        # Note: not tm.assert_index_equal, since `freq`s do not match
+        assert result.index.equals(dti)
+
+        arr[-2] = pd.NaT
+        result = arr.value_counts(dropna=False)
+        expected = pd.Series([4, 2, 1], index=[dti[0], dti[1], pd.NaT], name="count")
+        tm.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize("method", ["pad", "backfill"])
+    def test_fillna_preserves_tz(self, method):
+        dti = pd.date_range("2000-01-01", periods=5, freq="D", tz="US/Central")
+        arr = DatetimeArray._from_sequence(dti, copy=True)
+        arr[2] = pd.NaT
+
+        fill_val = dti[1] if method == "pad" else dti[3]
+        expected = DatetimeArray._from_sequence(
+            [dti[0], dti[1], fill_val, dti[3], dti[4]],
+            dtype=DatetimeTZDtype(tz="US/Central"),
+        )
+
+        result = arr._pad_or_backfill(method=method)
+        tm.assert_extension_array_equal(result, expected)
+
+        # assert that arr and dti were not modified in-place
+        assert arr[2] is pd.NaT
+        assert dti[2] == pd.Timestamp("2000-01-03", tz="US/Central")
+
+    def test_fillna_2d(self):
+        dti = pd.date_range("2016-01-01", periods=6, tz="US/Pacific")
+        dta = dti._data.reshape(3, 2).copy()
+        dta[0, 1] = pd.NaT
+        dta[1, 0] = pd.NaT
+
+        res1 = dta._pad_or_backfill(method="pad")
+        expected1 = dta.copy()
+        expected1[1, 0] = dta[0, 0]
+        tm.assert_extension_array_equal(res1, expected1)
+
+        res2 = dta._pad_or_backfill(method="backfill")
+        expected2 = dta.copy()
+        expected2 = dta.copy()
+        expected2[1, 0] = dta[2, 0]
+        expected2[0, 1] = dta[1, 1]
+        tm.assert_extension_array_equal(res2, expected2)
+
+        # with different ordering for underlying ndarray; behavior should
+        #  be unchanged
+        dta2 = dta._from_backing_data(dta._ndarray.copy(order="F"))
+        assert dta2._ndarray.flags["F_CONTIGUOUS"]
+        assert not dta2._ndarray.flags["C_CONTIGUOUS"]
+        tm.assert_extension_array_equal(dta, dta2)
+
+        res3 = dta2._pad_or_backfill(method="pad")
+        tm.assert_extension_array_equal(res3, expected1)
+
+        res4 = dta2._pad_or_backfill(method="backfill")
+        tm.assert_extension_array_equal(res4, expected2)
+
+        # test the DataFrame method while we're here
+        df = pd.DataFrame(dta)
+        res = df.ffill()
+        expected = pd.DataFrame(expected1)
+        tm.assert_frame_equal(res, expected)
+
+        res = df.bfill()
+        expected = pd.DataFrame(expected2)
+        tm.assert_frame_equal(res, expected)
+
+    def test_array_interface_tz(self):
+        tz = "US/Central"
+        data = pd.date_range("2017", periods=2, tz=tz)._data
+        result = np.asarray(data)
+
+        expected = np.array(
+            [
+                pd.Timestamp("2017-01-01T00:00:00", tz=tz),
+                pd.Timestamp("2017-01-02T00:00:00", tz=tz),
+            ],
+            dtype=object,
+        )
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = np.asarray(data, dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = np.asarray(data, dtype="M8[ns]")
+
+        expected = np.array(
+            ["2017-01-01T06:00:00", "2017-01-02T06:00:00"], dtype="M8[ns]"
+        )
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_array_interface(self):
+        data = pd.date_range("2017", periods=2)._data
+        expected = np.array(
+            ["2017-01-01T00:00:00", "2017-01-02T00:00:00"], dtype="datetime64[ns]"
+        )
+
+        result = np.asarray(data)
+        tm.assert_numpy_array_equal(result, expected)
+
+        result = np.asarray(data, dtype=object)
+        expected = np.array(
+            [pd.Timestamp("2017-01-01T00:00:00"), pd.Timestamp("2017-01-02T00:00:00")],
+            dtype=object,
+        )
+        tm.assert_numpy_array_equal(result, expected)
+
+    @pytest.mark.parametrize("index", [True, False])
+    def test_searchsorted_different_tz(self, index):
+        data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        arr = pd.DatetimeIndex(data, freq="D")._data.tz_localize("Asia/Tokyo")
+        if index:
+            arr = pd.Index(arr)
+
+        expected = arr.searchsorted(arr[2])
+        result = arr.searchsorted(arr[2].tz_convert("UTC"))
+        assert result == expected
+
+        expected = arr.searchsorted(arr[2:6])
+        result = arr.searchsorted(arr[2:6].tz_convert("UTC"))
+        tm.assert_equal(result, expected)
+
+    @pytest.mark.parametrize("index", [True, False])
+    def test_searchsorted_tzawareness_compat(self, index):
+        data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        arr = pd.DatetimeIndex(data, freq="D")._data
+        if index:
+            arr = pd.Index(arr)
+
+        mismatch = arr.tz_localize("Asia/Tokyo")
+
+        msg = "Cannot compare tz-naive and tz-aware datetime-like objects"
+        with pytest.raises(TypeError, match=msg):
+            arr.searchsorted(mismatch[0])
+        with pytest.raises(TypeError, match=msg):
+            arr.searchsorted(mismatch)
+
+        with pytest.raises(TypeError, match=msg):
+            mismatch.searchsorted(arr[0])
+        with pytest.raises(TypeError, match=msg):
+            mismatch.searchsorted(arr)
+
+    @pytest.mark.parametrize(
+        "other",
+        [
+            1,
+            np.int64(1),
+            1.0,
+            np.timedelta64("NaT"),
+            pd.Timedelta(days=2),
+            "invalid",
+            np.arange(10, dtype="i8") * 24 * 3600 * 10**9,
+            np.arange(10).view("timedelta64[ns]") * 24 * 3600 * 10**9,
+            pd.Timestamp("2021-01-01").to_period("D"),
+        ],
+    )
+    @pytest.mark.parametrize("index", [True, False])
+    def test_searchsorted_invalid_types(self, other, index):
+        data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        arr = pd.DatetimeIndex(data, freq="D")._data
+        if index:
+            arr = pd.Index(arr)
+
+        msg = "|".join(
+            [
+                "searchsorted requires compatible dtype or scalar",
+                "value should be a 'Timestamp', 'NaT', or array of those. Got",
+            ]
+        )
+        with pytest.raises(TypeError, match=msg):
+            arr.searchsorted(other)
+
+    def test_shift_fill_value(self):
+        dti = pd.date_range("2016-01-01", periods=3)
+
+        dta = dti._data
+        expected = DatetimeArray._from_sequence(np.roll(dta._ndarray, 1))
+
+        fv = dta[-1]
+        for fill_value in [fv, fv.to_pydatetime(), fv.to_datetime64()]:
+            result = dta.shift(1, fill_value=fill_value)
+            tm.assert_datetime_array_equal(result, expected)
+
+        dta = dta.tz_localize("UTC")
+        expected = expected.tz_localize("UTC")
+        fv = dta[-1]
+        for fill_value in [fv, fv.to_pydatetime()]:
+            result = dta.shift(1, fill_value=fill_value)
+            tm.assert_datetime_array_equal(result, expected)
+
+    def test_shift_value_tzawareness_mismatch(self):
+        dti = pd.date_range("2016-01-01", periods=3)
+
+        dta = dti._data
+
+        fv = dta[-1].tz_localize("UTC")
+        for invalid in [fv, fv.to_pydatetime()]:
+            with pytest.raises(TypeError, match="Cannot compare"):
+                dta.shift(1, fill_value=invalid)
+
+        dta = dta.tz_localize("UTC")
+        fv = dta[-1].tz_localize(None)
+        for invalid in [fv, fv.to_pydatetime(), fv.to_datetime64()]:
+            with pytest.raises(TypeError, match="Cannot compare"):
+                dta.shift(1, fill_value=invalid)
+
+    def test_shift_requires_tzmatch(self):
+        # pre-2.0 we required exact tz match, in 2.0 we require just
+        #  matching tzawareness
+        dti = pd.date_range("2016-01-01", periods=3, tz="UTC")
+        dta = dti._data
+
+        fill_value = pd.Timestamp("2020-10-18 18:44", tz="US/Pacific")
+
+        result = dta.shift(1, fill_value=fill_value)
+        expected = dta.shift(1, fill_value=fill_value.tz_convert("UTC"))
+        tm.assert_equal(result, expected)
+
+    def test_tz_localize_t2d(self):
+        dti = pd.date_range("1994-05-12", periods=12, tz="US/Pacific")
+        dta = dti._data.reshape(3, 4)
+        result = dta.tz_localize(None)
+
+        expected = dta.ravel().tz_localize(None).reshape(dta.shape)
+        tm.assert_datetime_array_equal(result, expected)
+
+        roundtrip = expected.tz_localize("US/Pacific")
+        tm.assert_datetime_array_equal(roundtrip, dta)
+
+    easts = ["US/Eastern", "dateutil/US/Eastern"]
+    if ZoneInfo is not None:
+        try:
+            tz = ZoneInfo("US/Eastern")
+        except KeyError:
+            # no tzdata
+            pass
+        else:
+            # Argument 1 to "append" of "list" has incompatible type "ZoneInfo";
+            # expected "str"
+            easts.append(tz)  # type: ignore[arg-type]
+
+    @pytest.mark.parametrize("tz", easts)
+    def test_iter_zoneinfo_fold(self, tz):
+        # GH#49684
+        utc_vals = np.array(
+            [1320552000, 1320555600, 1320559200, 1320562800], dtype=np.int64
+        )
+        utc_vals *= 1_000_000_000
+
+        dta = DatetimeArray._from_sequence(utc_vals).tz_localize("UTC").tz_convert(tz)
+
+        left = dta[2]
+        right = list(dta)[2]
+        assert str(left) == str(right)
+        # previously there was a bug where with non-pytz right would be
+        #  Timestamp('2011-11-06 01:00:00-0400', tz='US/Eastern')
+        # while left would be
+        #  Timestamp('2011-11-06 01:00:00-0500', tz='US/Eastern')
+        # The .value's would match (so they would compare as equal),
+        #  but the folds would not
+        assert left.utcoffset() == right.utcoffset()
+
+        # The same bug in ints_to_pydatetime affected .astype, so we test
+        #  that here.
+        right2 = dta.astype(object)[2]
+        assert str(left) == str(right2)
+        assert left.utcoffset() == right2.utcoffset()
+
+    @pytest.mark.parametrize(
+        "freq, freq_depr",
+        [
+            ("2ME", "2M"),
+            ("2SME", "2SM"),
+            ("2SME", "2sm"),
+            ("2QE", "2Q"),
+            ("2QE-SEP", "2Q-SEP"),
+            ("1YE", "1Y"),
+            ("2YE-MAR", "2Y-MAR"),
+            ("1YE", "1A"),
+            ("2YE-MAR", "2A-MAR"),
+            ("2ME", "2m"),
+            ("2QE-SEP", "2q-sep"),
+            ("2YE-MAR", "2a-mar"),
+            ("2YE", "2y"),
+        ],
+    )
+    def test_date_range_frequency_M_Q_Y_A_deprecated(self, freq, freq_depr):
+        # GH#9586, GH#54275
+        depr_msg = f"'{freq_depr[1:]}' is deprecated and will be removed "
+        f"in a future version, please use '{freq[1:]}' instead."
+
+        expected = pd.date_range("1/1/2000", periods=4, freq=freq)
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            result = pd.date_range("1/1/2000", periods=4, freq=freq_depr)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize("freq_depr", ["2H", "2CBH", "2MIN", "2S", "2mS", "2Us"])
+    def test_date_range_uppercase_frequency_deprecated(self, freq_depr):
+        # GH#9586, GH#54939
+        depr_msg = f"'{freq_depr[1:]}' is deprecated and will be removed in a "
+        f"future version. Please use '{freq_depr.lower()[1:]}' instead."
+
+        expected = pd.date_range("1/1/2000", periods=4, freq=freq_depr.lower())
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            result = pd.date_range("1/1/2000", periods=4, freq=freq_depr)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize(
+        "freq_depr",
+        [
+            "2ye-mar",
+            "2ys",
+            "2qe",
+            "2qs-feb",
+            "2bqs",
+            "2sms",
+            "2bms",
+            "2cbme",
+            "2me",
+            "2w",
+        ],
+    )
+    def test_date_range_lowercase_frequency_deprecated(self, freq_depr):
+        # GH#9586, GH#54939
+        depr_msg = f"'{freq_depr[1:]}' is deprecated and will be removed in a "
+        f"future version, please use '{freq_depr.upper()[1:]}' instead."
+
+        expected = pd.date_range("1/1/2000", periods=4, freq=freq_depr.upper())
+        with tm.assert_produces_warning(FutureWarning, match=depr_msg):
+            result = pd.date_range("1/1/2000", periods=4, freq=freq_depr)
+        tm.assert_index_equal(result, expected)
+
+
+def test_factorize_sort_without_freq():
+    dta = DatetimeArray._from_sequence([0, 2, 1], dtype="M8[ns]")
+
+    msg = r"call pd.factorize\(obj, sort=True\) instead"
+    with pytest.raises(NotImplementedError, match=msg):
+        dta.factorize(sort=True)
+
+    # Do TimedeltaArray while we're here
+    tda = dta - dta[0]
+    with pytest.raises(NotImplementedError, match=msg):
+        tda.factorize(sort=True)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/arrays/test_ndarray_backed.py

@@ -0,0 +1,75 @@
+"""
+Tests for subclasses of NDArrayBackedExtensionArray
+"""
+import numpy as np
+
+from pandas import (
+    CategoricalIndex,
+    date_range,
+)
+from pandas.core.arrays import (
+    Categorical,
+    DatetimeArray,
+    NumpyExtensionArray,
+    TimedeltaArray,
+)
+
+
+class TestEmpty:
+    def test_empty_categorical(self):
+        ci = CategoricalIndex(["a", "b", "c"], ordered=True)
+        dtype = ci.dtype
+
+        # case with int8 codes
+        shape = (4,)
+        result = Categorical._empty(shape, dtype=dtype)
+        assert isinstance(result, Categorical)
+        assert result.shape == shape
+        assert result._ndarray.dtype == np.int8
+
+        # case where repr would segfault if we didn't override base implementation
+        result = Categorical._empty((4096,), dtype=dtype)
+        assert isinstance(result, Categorical)
+        assert result.shape == (4096,)
+        assert result._ndarray.dtype == np.int8
+        repr(result)
+
+        # case with int16 codes
+        ci = CategoricalIndex(list(range(512)) * 4, ordered=False)
+        dtype = ci.dtype
+        result = Categorical._empty(shape, dtype=dtype)
+        assert isinstance(result, Categorical)
+        assert result.shape == shape
+        assert result._ndarray.dtype == np.int16
+
+    def test_empty_dt64tz(self):
+        dti = date_range("2016-01-01", periods=2, tz="Asia/Tokyo")
+        dtype = dti.dtype
+
+        shape = (0,)
+        result = DatetimeArray._empty(shape, dtype=dtype)
+        assert result.dtype == dtype
+        assert isinstance(result, DatetimeArray)
+        assert result.shape == shape
+
+    def test_empty_dt64(self):
+        shape = (3, 9)
+        result = DatetimeArray._empty(shape, dtype="datetime64[ns]")
+        assert isinstance(result, DatetimeArray)
+        assert result.shape == shape
+
+    def test_empty_td64(self):
+        shape = (3, 9)
+        result = TimedeltaArray._empty(shape, dtype="m8[ns]")
+        assert isinstance(result, TimedeltaArray)
+        assert result.shape == shape
+
+    def test_empty_pandas_array(self):
+        arr = NumpyExtensionArray(np.array([1, 2]))
+        dtype = arr.dtype
+
+        shape = (3, 9)
+        result = NumpyExtensionArray._empty(shape, dtype=dtype)
+        assert isinstance(result, NumpyExtensionArray)
+        assert result.dtype == dtype
+        assert result.shape == shape

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/arrays/test_period.py

@@ -0,0 +1,184 @@
+import numpy as np
+import pytest
+
+from pandas._libs.tslibs import iNaT
+from pandas._libs.tslibs.period import IncompatibleFrequency
+
+from pandas.core.dtypes.base import _registry as registry
+from pandas.core.dtypes.dtypes import PeriodDtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.core.arrays import PeriodArray
+
+# ----------------------------------------------------------------------------
+# Dtype
+
+
+def test_registered():
+    assert PeriodDtype in registry.dtypes
+    result = registry.find("Period[D]")
+    expected = PeriodDtype("D")
+    assert result == expected
+
+
+# ----------------------------------------------------------------------------
+# period_array
+
+
+def test_asi8():
+    result = PeriodArray._from_sequence(["2000", "2001", None], dtype="period[D]").asi8
+    expected = np.array([10957, 11323, iNaT])
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_take_raises():
+    arr = PeriodArray._from_sequence(["2000", "2001"], dtype="period[D]")
+    with pytest.raises(IncompatibleFrequency, match="freq"):
+        arr.take([0, -1], allow_fill=True, fill_value=pd.Period("2000", freq="W"))
+
+    msg = "value should be a 'Period' or 'NaT'. Got 'str' instead"
+    with pytest.raises(TypeError, match=msg):
+        arr.take([0, -1], allow_fill=True, fill_value="foo")
+
+
+def test_fillna_raises():
+    arr = PeriodArray._from_sequence(["2000", "2001", "2002"], dtype="period[D]")
+    with pytest.raises(ValueError, match="Length"):
+        arr.fillna(arr[:2])
+
+
+def test_fillna_copies():
+    arr = PeriodArray._from_sequence(["2000", "2001", "2002"], dtype="period[D]")
+    result = arr.fillna(pd.Period("2000", "D"))
+    assert result is not arr
+
+
+# ----------------------------------------------------------------------------
+# setitem
+
+
+@pytest.mark.parametrize(
+    "key, value, expected",
+    [
+        ([0], pd.Period("2000", "D"), [10957, 1, 2]),
+        ([0], None, [iNaT, 1, 2]),
+        ([0], np.nan, [iNaT, 1, 2]),
+        ([0, 1, 2], pd.Period("2000", "D"), [10957] * 3),
+        (
+            [0, 1, 2],
+            [pd.Period("2000", "D"), pd.Period("2001", "D"), pd.Period("2002", "D")],
+            [10957, 11323, 11688],
+        ),
+    ],
+)
+def test_setitem(key, value, expected):
+    arr = PeriodArray(np.arange(3), dtype="period[D]")
+    expected = PeriodArray(expected, dtype="period[D]")
+    arr[key] = value
+    tm.assert_period_array_equal(arr, expected)
+
+
+def test_setitem_raises_incompatible_freq():
+    arr = PeriodArray(np.arange(3), dtype="period[D]")
+    with pytest.raises(IncompatibleFrequency, match="freq"):
+        arr[0] = pd.Period("2000", freq="Y")
+
+    other = PeriodArray._from_sequence(["2000", "2001"], dtype="period[Y]")
+    with pytest.raises(IncompatibleFrequency, match="freq"):
+        arr[[0, 1]] = other
+
+
+def test_setitem_raises_length():
+    arr = PeriodArray(np.arange(3), dtype="period[D]")
+    with pytest.raises(ValueError, match="length"):
+        arr[[0, 1]] = [pd.Period("2000", freq="D")]
+
+
+def test_setitem_raises_type():
+    arr = PeriodArray(np.arange(3), dtype="period[D]")
+    with pytest.raises(TypeError, match="int"):
+        arr[0] = 1
+
+
+# ----------------------------------------------------------------------------
+# Ops
+
+
+def test_sub_period():
+    arr = PeriodArray._from_sequence(["2000", "2001"], dtype="period[D]")
+    other = pd.Period("2000", freq="M")
+    with pytest.raises(IncompatibleFrequency, match="freq"):
+        arr - other
+
+
+def test_sub_period_overflow():
+    # GH#47538
+    dti = pd.date_range("1677-09-22", periods=2, freq="D")
+    pi = dti.to_period("ns")
+
+    per = pd.Period._from_ordinal(10**14, pi.freq)
+
+    with pytest.raises(OverflowError, match="Overflow in int64 addition"):
+        pi - per
+
+    with pytest.raises(OverflowError, match="Overflow in int64 addition"):
+        per - pi
+
+
+# ----------------------------------------------------------------------------
+# Methods
+
+
+@pytest.mark.parametrize(
+    "other",
+    [
+        pd.Period("2000", freq="h"),
+        PeriodArray._from_sequence(["2000", "2001", "2000"], dtype="period[h]"),
+    ],
+)
+def test_where_different_freq_raises(other):
+    # GH#45768 The PeriodArray method raises, the Series method coerces
+    ser = pd.Series(
+        PeriodArray._from_sequence(["2000", "2001", "2002"], dtype="period[D]")
+    )
+    cond = np.array([True, False, True])
+
+    with pytest.raises(IncompatibleFrequency, match="freq"):
+        ser.array._where(cond, other)
+
+    res = ser.where(cond, other)
+    expected = ser.astype(object).where(cond, other)
+    tm.assert_series_equal(res, expected)
+
+
+# ----------------------------------------------------------------------------
+# Printing
+
+
+def test_repr_small():
+    arr = PeriodArray._from_sequence(["2000", "2001"], dtype="period[D]")
+    result = str(arr)
+    expected = (
+        "<PeriodArray>\n['2000-01-01', '2001-01-01']\nLength: 2, dtype: period[D]"
+    )
+    assert result == expected
+
+
+def test_repr_large():
+    arr = PeriodArray._from_sequence(["2000", "2001"] * 500, dtype="period[D]")
+    result = str(arr)
+    expected = (
+        "<PeriodArray>\n"
+        "['2000-01-01', '2001-01-01', '2000-01-01', '2001-01-01', "
+        "'2000-01-01',\n"
+        " '2001-01-01', '2000-01-01', '2001-01-01', '2000-01-01', "
+        "'2001-01-01',\n"
+        " ...\n"
+        " '2000-01-01', '2001-01-01', '2000-01-01', '2001-01-01', "
+        "'2000-01-01',\n"
+        " '2001-01-01', '2000-01-01', '2001-01-01', '2000-01-01', "
+        "'2001-01-01']\n"
+        "Length: 1000, dtype: period[D]"
+    )
+    assert result == expected

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/arrays/test_timedeltas.py

@@ -0,0 +1,313 @@
+from datetime import timedelta
+
+import numpy as np
+import pytest
+
+import pandas as pd
+from pandas import Timedelta
+import pandas._testing as tm
+from pandas.core.arrays import (
+    DatetimeArray,
+    TimedeltaArray,
+)
+
+
+class TestNonNano:
+    @pytest.fixture(params=["s", "ms", "us"])
+    def unit(self, request):
+        return request.param
+
+    @pytest.fixture
+    def tda(self, unit):
+        arr = np.arange(5, dtype=np.int64).view(f"m8[{unit}]")
+        return TimedeltaArray._simple_new(arr, dtype=arr.dtype)
+
+    def test_non_nano(self, unit):
+        arr = np.arange(5, dtype=np.int64).view(f"m8[{unit}]")
+        tda = TimedeltaArray._simple_new(arr, dtype=arr.dtype)
+
+        assert tda.dtype == arr.dtype
+        assert tda[0].unit == unit
+
+    def test_as_unit_raises(self, tda):
+        # GH#50616
+        with pytest.raises(ValueError, match="Supported units"):
+            tda.as_unit("D")
+
+        tdi = pd.Index(tda)
+        with pytest.raises(ValueError, match="Supported units"):
+            tdi.as_unit("D")
+
+    @pytest.mark.parametrize("field", TimedeltaArray._field_ops)
+    def test_fields(self, tda, field):
+        as_nano = tda._ndarray.astype("m8[ns]")
+        tda_nano = TimedeltaArray._simple_new(as_nano, dtype=as_nano.dtype)
+
+        result = getattr(tda, field)
+        expected = getattr(tda_nano, field)
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_to_pytimedelta(self, tda):
+        as_nano = tda._ndarray.astype("m8[ns]")
+        tda_nano = TimedeltaArray._simple_new(as_nano, dtype=as_nano.dtype)
+
+        result = tda.to_pytimedelta()
+        expected = tda_nano.to_pytimedelta()
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_total_seconds(self, unit, tda):
+        as_nano = tda._ndarray.astype("m8[ns]")
+        tda_nano = TimedeltaArray._simple_new(as_nano, dtype=as_nano.dtype)
+
+        result = tda.total_seconds()
+        expected = tda_nano.total_seconds()
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_timedelta_array_total_seconds(self):
+        # GH34290
+        expected = Timedelta("2 min").total_seconds()
+
+        result = pd.array([Timedelta("2 min")]).total_seconds()[0]
+        assert result == expected
+
+    def test_total_seconds_nanoseconds(self):
+        # issue #48521
+        start_time = pd.Series(["2145-11-02 06:00:00"]).astype("datetime64[ns]")
+        end_time = pd.Series(["2145-11-02 07:06:00"]).astype("datetime64[ns]")
+        expected = (end_time - start_time).values / np.timedelta64(1, "s")
+        result = (end_time - start_time).dt.total_seconds().values
+        assert result == expected
+
+    @pytest.mark.parametrize(
+        "nat", [np.datetime64("NaT", "ns"), np.datetime64("NaT", "us")]
+    )
+    def test_add_nat_datetimelike_scalar(self, nat, tda):
+        result = tda + nat
+        assert isinstance(result, DatetimeArray)
+        assert result._creso == tda._creso
+        assert result.isna().all()
+
+        result = nat + tda
+        assert isinstance(result, DatetimeArray)
+        assert result._creso == tda._creso
+        assert result.isna().all()
+
+    def test_add_pdnat(self, tda):
+        result = tda + pd.NaT
+        assert isinstance(result, TimedeltaArray)
+        assert result._creso == tda._creso
+        assert result.isna().all()
+
+        result = pd.NaT + tda
+        assert isinstance(result, TimedeltaArray)
+        assert result._creso == tda._creso
+        assert result.isna().all()
+
+    # TODO: 2022-07-11 this is the only test that gets to DTA.tz_convert
+    #  or tz_localize with non-nano; implement tests specific to that.
+    def test_add_datetimelike_scalar(self, tda, tz_naive_fixture):
+        ts = pd.Timestamp("2016-01-01", tz=tz_naive_fixture).as_unit("ns")
+
+        expected = tda.as_unit("ns") + ts
+        res = tda + ts
+        tm.assert_extension_array_equal(res, expected)
+        res = ts + tda
+        tm.assert_extension_array_equal(res, expected)
+
+        ts += Timedelta(1)  # case where we can't cast losslessly
+
+        exp_values = tda._ndarray + ts.asm8
+        expected = (
+            DatetimeArray._simple_new(exp_values, dtype=exp_values.dtype)
+            .tz_localize("UTC")
+            .tz_convert(ts.tz)
+        )
+
+        result = tda + ts
+        tm.assert_extension_array_equal(result, expected)
+
+        result = ts + tda
+        tm.assert_extension_array_equal(result, expected)
+
+    def test_mul_scalar(self, tda):
+        other = 2
+        result = tda * other
+        expected = TimedeltaArray._simple_new(tda._ndarray * other, dtype=tda.dtype)
+        tm.assert_extension_array_equal(result, expected)
+        assert result._creso == tda._creso
+
+    def test_mul_listlike(self, tda):
+        other = np.arange(len(tda))
+        result = tda * other
+        expected = TimedeltaArray._simple_new(tda._ndarray * other, dtype=tda.dtype)
+        tm.assert_extension_array_equal(result, expected)
+        assert result._creso == tda._creso
+
+    def test_mul_listlike_object(self, tda):
+        other = np.arange(len(tda))
+        result = tda * other.astype(object)
+        expected = TimedeltaArray._simple_new(tda._ndarray * other, dtype=tda.dtype)
+        tm.assert_extension_array_equal(result, expected)
+        assert result._creso == tda._creso
+
+    def test_div_numeric_scalar(self, tda):
+        other = 2
+        result = tda / other
+        expected = TimedeltaArray._simple_new(tda._ndarray / other, dtype=tda.dtype)
+        tm.assert_extension_array_equal(result, expected)
+        assert result._creso == tda._creso
+
+    def test_div_td_scalar(self, tda):
+        other = timedelta(seconds=1)
+        result = tda / other
+        expected = tda._ndarray / np.timedelta64(1, "s")
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_div_numeric_array(self, tda):
+        other = np.arange(len(tda))
+        result = tda / other
+        expected = TimedeltaArray._simple_new(tda._ndarray / other, dtype=tda.dtype)
+        tm.assert_extension_array_equal(result, expected)
+        assert result._creso == tda._creso
+
+    def test_div_td_array(self, tda):
+        other = tda._ndarray + tda._ndarray[-1]
+        result = tda / other
+        expected = tda._ndarray / other
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_add_timedeltaarraylike(self, tda):
+        tda_nano = tda.astype("m8[ns]")
+
+        expected = tda_nano * 2
+        res = tda_nano + tda
+        tm.assert_extension_array_equal(res, expected)
+        res = tda + tda_nano
+        tm.assert_extension_array_equal(res, expected)
+
+        expected = tda_nano * 0
+        res = tda - tda_nano
+        tm.assert_extension_array_equal(res, expected)
+
+        res = tda_nano - tda
+        tm.assert_extension_array_equal(res, expected)
+
+
+class TestTimedeltaArray:
+    @pytest.mark.parametrize("dtype", [int, np.int32, np.int64, "uint32", "uint64"])
+    def test_astype_int(self, dtype):
+        arr = TimedeltaArray._from_sequence(
+            [Timedelta("1h"), Timedelta("2h")], dtype="m8[ns]"
+        )
+
+        if np.dtype(dtype) != np.int64:
+            with pytest.raises(TypeError, match=r"Do obj.astype\('int64'\)"):
+                arr.astype(dtype)
+            return
+
+        result = arr.astype(dtype)
+        expected = arr._ndarray.view("i8")
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_setitem_clears_freq(self):
+        a = pd.timedelta_range("1h", periods=2, freq="h")._data
+        a[0] = Timedelta("1h")
+        assert a.freq is None
+
+    @pytest.mark.parametrize(
+        "obj",
+        [
+            Timedelta(seconds=1),
+            Timedelta(seconds=1).to_timedelta64(),
+            Timedelta(seconds=1).to_pytimedelta(),
+        ],
+    )
+    def test_setitem_objects(self, obj):
+        # make sure we accept timedelta64 and timedelta in addition to Timedelta
+        tdi = pd.timedelta_range("2 Days", periods=4, freq="h")
+        arr = tdi._data
+
+        arr[0] = obj
+        assert arr[0] == Timedelta(seconds=1)
+
+    @pytest.mark.parametrize(
+        "other",
+        [
+            1,
+            np.int64(1),
+            1.0,
+            np.datetime64("NaT"),
+            pd.Timestamp("2021-01-01"),
+            "invalid",
+            np.arange(10, dtype="i8") * 24 * 3600 * 10**9,
+            (np.arange(10) * 24 * 3600 * 10**9).view("datetime64[ns]"),
+            pd.Timestamp("2021-01-01").to_period("D"),
+        ],
+    )
+    @pytest.mark.parametrize("index", [True, False])
+    def test_searchsorted_invalid_types(self, other, index):
+        data = np.arange(10, dtype="i8") * 24 * 3600 * 10**9
+        arr = pd.TimedeltaIndex(data, freq="D")._data
+        if index:
+            arr = pd.Index(arr)
+
+        msg = "|".join(
+            [
+                "searchsorted requires compatible dtype or scalar",
+                "value should be a 'Timedelta', 'NaT', or array of those. Got",
+            ]
+        )
+        with pytest.raises(TypeError, match=msg):
+            arr.searchsorted(other)
+
+
+class TestUnaryOps:
+    def test_abs(self):
+        vals = np.array([-3600 * 10**9, "NaT", 7200 * 10**9], dtype="m8[ns]")
+        arr = TimedeltaArray._from_sequence(vals)
+
+        evals = np.array([3600 * 10**9, "NaT", 7200 * 10**9], dtype="m8[ns]")
+        expected = TimedeltaArray._from_sequence(evals)
+
+        result = abs(arr)
+        tm.assert_timedelta_array_equal(result, expected)
+
+        result2 = np.abs(arr)
+        tm.assert_timedelta_array_equal(result2, expected)
+
+    def test_pos(self):
+        vals = np.array([-3600 * 10**9, "NaT", 7200 * 10**9], dtype="m8[ns]")
+        arr = TimedeltaArray._from_sequence(vals)
+
+        result = +arr
+        tm.assert_timedelta_array_equal(result, arr)
+        assert not tm.shares_memory(result, arr)
+
+        result2 = np.positive(arr)
+        tm.assert_timedelta_array_equal(result2, arr)
+        assert not tm.shares_memory(result2, arr)
+
+    def test_neg(self):
+        vals = np.array([-3600 * 10**9, "NaT", 7200 * 10**9], dtype="m8[ns]")
+        arr = TimedeltaArray._from_sequence(vals)
+
+        evals = np.array([3600 * 10**9, "NaT", -7200 * 10**9], dtype="m8[ns]")
+        expected = TimedeltaArray._from_sequence(evals)
+
+        result = -arr
+        tm.assert_timedelta_array_equal(result, expected)
+
+        result2 = np.negative(arr)
+        tm.assert_timedelta_array_equal(result2, expected)
+
+    def test_neg_freq(self):
+        tdi = pd.timedelta_range("2 Days", periods=4, freq="h")
+        arr = tdi._data
+
+        expected = -tdi._data
+
+        result = -arr
+        tm.assert_timedelta_array_equal(result, expected)
+
+        result2 = np.negative(arr)
+        tm.assert_timedelta_array_equal(result2, expected)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/base/common.py

@@ -0,0 +1,9 @@
+from typing import Any
+
+from pandas import Index
+
+
+def allow_na_ops(obj: Any) -> bool:
+    """Whether to skip test cases including NaN"""
+    is_bool_index = isinstance(obj, Index) and obj.inferred_type == "boolean"
+    return not is_bool_index and obj._can_hold_na

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/base/test_constructors.py

@@ -0,0 +1,179 @@
+from datetime import datetime
+import sys
+
+import numpy as np
+import pytest
+
+from pandas.compat import PYPY
+
+import pandas as pd
+from pandas import (
+    DataFrame,
+    Index,
+    Series,
+)
+import pandas._testing as tm
+from pandas.core.accessor import PandasDelegate
+from pandas.core.base import (
+    NoNewAttributesMixin,
+    PandasObject,
+)
+
+
+def series_via_frame_from_dict(x, **kwargs):
+    return DataFrame({"a": x}, **kwargs)["a"]
+
+
+def series_via_frame_from_scalar(x, **kwargs):
+    return DataFrame(x, **kwargs)[0]
+
+
+@pytest.fixture(
+    params=[
+        Series,
+        series_via_frame_from_dict,
+        series_via_frame_from_scalar,
+        Index,
+    ],
+    ids=["Series", "DataFrame-dict", "DataFrame-array", "Index"],
+)
+def constructor(request):
+    return request.param
+
+
+class TestPandasDelegate:
+    class Delegator:
+        _properties = ["prop"]
+        _methods = ["test_method"]
+
+        def _set_prop(self, value):
+            self.prop = value
+
+        def _get_prop(self):
+            return self.prop
+
+        prop = property(_get_prop, _set_prop, doc="foo property")
+
+        def test_method(self, *args, **kwargs):
+            """a test method"""
+
+    class Delegate(PandasDelegate, PandasObject):
+        def __init__(self, obj) -> None:
+            self.obj = obj
+
+    def test_invalid_delegation(self):
+        # these show that in order for the delegation to work
+        # the _delegate_* methods need to be overridden to not raise
+        # a TypeError
+
+        self.Delegate._add_delegate_accessors(
+            delegate=self.Delegator,
+            accessors=self.Delegator._properties,
+            typ="property",
+        )
+        self.Delegate._add_delegate_accessors(
+            delegate=self.Delegator, accessors=self.Delegator._methods, typ="method"
+        )
+
+        delegate = self.Delegate(self.Delegator())
+
+        msg = "You cannot access the property prop"
+        with pytest.raises(TypeError, match=msg):
+            delegate.prop
+
+        msg = "The property prop cannot be set"
+        with pytest.raises(TypeError, match=msg):
+            delegate.prop = 5
+
+        msg = "You cannot access the property prop"
+        with pytest.raises(TypeError, match=msg):
+            delegate.prop
+
+    @pytest.mark.skipif(PYPY, reason="not relevant for PyPy")
+    def test_memory_usage(self):
+        # Delegate does not implement memory_usage.
+        # Check that we fall back to in-built `__sizeof__`
+        # GH 12924
+        delegate = self.Delegate(self.Delegator())
+        sys.getsizeof(delegate)
+
+
+class TestNoNewAttributesMixin:
+    def test_mixin(self):
+        class T(NoNewAttributesMixin):
+            pass
+
+        t = T()
+        assert not hasattr(t, "__frozen")
+
+        t.a = "test"
+        assert t.a == "test"
+
+        t._freeze()
+        assert "__frozen" in dir(t)
+        assert getattr(t, "__frozen")
+        msg = "You cannot add any new attribute"
+        with pytest.raises(AttributeError, match=msg):
+            t.b = "test"
+
+        assert not hasattr(t, "b")
+
+
+class TestConstruction:
+    # test certain constructor behaviours on dtype inference across Series,
+    # Index and DataFrame
+
+    @pytest.mark.parametrize(
+        "a",
+        [
+            np.array(["2263-01-01"], dtype="datetime64[D]"),
+            np.array([datetime(2263, 1, 1)], dtype=object),
+            np.array([np.datetime64("2263-01-01", "D")], dtype=object),
+            np.array(["2263-01-01"], dtype=object),
+        ],
+        ids=[
+            "datetime64[D]",
+            "object-datetime.datetime",
+            "object-numpy-scalar",
+            "object-string",
+        ],
+    )
+    def test_constructor_datetime_outofbound(
+        self, a, constructor, request, using_infer_string
+    ):
+        # GH-26853 (+ bug GH-26206 out of bound non-ns unit)
+
+        # No dtype specified (dtype inference)
+        # datetime64[non-ns] raise error, other cases result in object dtype
+        # and preserve original data
+        if a.dtype.kind == "M":
+            # Can't fit in nanosecond bounds -> get the nearest supported unit
+            result = constructor(a)
+            assert result.dtype == "M8[s]"
+        else:
+            result = constructor(a)
+            if using_infer_string and "object-string" in request.node.callspec.id:
+                assert result.dtype == "string"
+            else:
+                assert result.dtype == "object"
+            tm.assert_numpy_array_equal(result.to_numpy(), a)
+
+        # Explicit dtype specified
+        # Forced conversion fails for all -> all cases raise error
+        msg = "Out of bounds|Out of bounds .* present at position 0"
+        with pytest.raises(pd.errors.OutOfBoundsDatetime, match=msg):
+            constructor(a, dtype="datetime64[ns]")
+
+    def test_constructor_datetime_nonns(self, constructor):
+        arr = np.array(["2020-01-01T00:00:00.000000"], dtype="datetime64[us]")
+        dta = pd.core.arrays.DatetimeArray._simple_new(arr, dtype=arr.dtype)
+        expected = constructor(dta)
+        assert expected.dtype == arr.dtype
+
+        result = constructor(arr)
+        tm.assert_equal(result, expected)
+
+        # https://github.com/pandas-dev/pandas/issues/34843
+        arr.flags.writeable = False
+        result = constructor(arr)
+        tm.assert_equal(result, expected)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/base/test_conversion.py

@@ -0,0 +1,562 @@
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.dtypes import DatetimeTZDtype
+
+import pandas as pd
+from pandas import (
+    CategoricalIndex,
+    Series,
+    Timedelta,
+    Timestamp,
+    date_range,
+)
+import pandas._testing as tm
+from pandas.core.arrays import (
+    DatetimeArray,
+    IntervalArray,
+    NumpyExtensionArray,
+    PeriodArray,
+    SparseArray,
+    TimedeltaArray,
+)
+from pandas.core.arrays.string_arrow import ArrowStringArrayNumpySemantics
+
+
+class TestToIterable:
+    # test that we convert an iterable to python types
+
+    dtypes = [
+        ("int8", int),
+        ("int16", int),
+        ("int32", int),
+        ("int64", int),
+        ("uint8", int),
+        ("uint16", int),
+        ("uint32", int),
+        ("uint64", int),
+        ("float16", float),
+        ("float32", float),
+        ("float64", float),
+        ("datetime64[ns]", Timestamp),
+        ("datetime64[ns, US/Eastern]", Timestamp),
+        ("timedelta64[ns]", Timedelta),
+    ]
+
+    @pytest.mark.parametrize("dtype, rdtype", dtypes)
+    @pytest.mark.parametrize(
+        "method",
+        [
+            lambda x: x.tolist(),
+            lambda x: x.to_list(),
+            lambda x: list(x),
+            lambda x: list(x.__iter__()),
+        ],
+        ids=["tolist", "to_list", "list", "iter"],
+    )
+    def test_iterable(self, index_or_series, method, dtype, rdtype):
+        # gh-10904
+        # gh-13258
+        # coerce iteration to underlying python / pandas types
+        typ = index_or_series
+        if dtype == "float16" and issubclass(typ, pd.Index):
+            with pytest.raises(NotImplementedError, match="float16 indexes are not "):
+                typ([1], dtype=dtype)
+            return
+        s = typ([1], dtype=dtype)
+        result = method(s)[0]
+        assert isinstance(result, rdtype)
+
+    @pytest.mark.parametrize(
+        "dtype, rdtype, obj",
+        [
+            ("object", object, "a"),
+            ("object", int, 1),
+            ("category", object, "a"),
+            ("category", int, 1),
+        ],
+    )
+    @pytest.mark.parametrize(
+        "method",
+        [
+            lambda x: x.tolist(),
+            lambda x: x.to_list(),
+            lambda x: list(x),
+            lambda x: list(x.__iter__()),
+        ],
+        ids=["tolist", "to_list", "list", "iter"],
+    )
+    def test_iterable_object_and_category(
+        self, index_or_series, method, dtype, rdtype, obj
+    ):
+        # gh-10904
+        # gh-13258
+        # coerce iteration to underlying python / pandas types
+        typ = index_or_series
+        s = typ([obj], dtype=dtype)
+        result = method(s)[0]
+        assert isinstance(result, rdtype)
+
+    @pytest.mark.parametrize("dtype, rdtype", dtypes)
+    def test_iterable_items(self, dtype, rdtype):
+        # gh-13258
+        # test if items yields the correct boxed scalars
+        # this only applies to series
+        s = Series([1], dtype=dtype)
+        _, result = next(iter(s.items()))
+        assert isinstance(result, rdtype)
+
+        _, result = next(iter(s.items()))
+        assert isinstance(result, rdtype)
+
+    @pytest.mark.parametrize(
+        "dtype, rdtype", dtypes + [("object", int), ("category", int)]
+    )
+    def test_iterable_map(self, index_or_series, dtype, rdtype):
+        # gh-13236
+        # coerce iteration to underlying python / pandas types
+        typ = index_or_series
+        if dtype == "float16" and issubclass(typ, pd.Index):
+            with pytest.raises(NotImplementedError, match="float16 indexes are not "):
+                typ([1], dtype=dtype)
+            return
+        s = typ([1], dtype=dtype)
+        result = s.map(type)[0]
+        if not isinstance(rdtype, tuple):
+            rdtype = (rdtype,)
+        assert result in rdtype
+
+    @pytest.mark.parametrize(
+        "method",
+        [
+            lambda x: x.tolist(),
+            lambda x: x.to_list(),
+            lambda x: list(x),
+            lambda x: list(x.__iter__()),
+        ],
+        ids=["tolist", "to_list", "list", "iter"],
+    )
+    def test_categorial_datetimelike(self, method):
+        i = CategoricalIndex([Timestamp("1999-12-31"), Timestamp("2000-12-31")])
+
+        result = method(i)[0]
+        assert isinstance(result, Timestamp)
+
+    def test_iter_box_dt64(self, unit):
+        vals = [Timestamp("2011-01-01"), Timestamp("2011-01-02")]
+        ser = Series(vals).dt.as_unit(unit)
+        assert ser.dtype == f"datetime64[{unit}]"
+        for res, exp in zip(ser, vals):
+            assert isinstance(res, Timestamp)
+            assert res.tz is None
+            assert res == exp
+            assert res.unit == unit
+
+    def test_iter_box_dt64tz(self, unit):
+        vals = [
+            Timestamp("2011-01-01", tz="US/Eastern"),
+            Timestamp("2011-01-02", tz="US/Eastern"),
+        ]
+        ser = Series(vals).dt.as_unit(unit)
+
+        assert ser.dtype == f"datetime64[{unit}, US/Eastern]"
+        for res, exp in zip(ser, vals):
+            assert isinstance(res, Timestamp)
+            assert res.tz == exp.tz
+            assert res == exp
+            assert res.unit == unit
+
+    def test_iter_box_timedelta64(self, unit):
+        # timedelta
+        vals = [Timedelta("1 days"), Timedelta("2 days")]
+        ser = Series(vals).dt.as_unit(unit)
+        assert ser.dtype == f"timedelta64[{unit}]"
+        for res, exp in zip(ser, vals):
+            assert isinstance(res, Timedelta)
+            assert res == exp
+            assert res.unit == unit
+
+    def test_iter_box_period(self):
+        # period
+        vals = [pd.Period("2011-01-01", freq="M"), pd.Period("2011-01-02", freq="M")]
+        s = Series(vals)
+        assert s.dtype == "Period[M]"
+        for res, exp in zip(s, vals):
+            assert isinstance(res, pd.Period)
+            assert res.freq == "ME"
+            assert res == exp
+
+
+@pytest.mark.parametrize(
+    "arr, expected_type, dtype",
+    [
+        (np.array([0, 1], dtype=np.int64), np.ndarray, "int64"),
+        (np.array(["a", "b"]), np.ndarray, "object"),
+        (pd.Categorical(["a", "b"]), pd.Categorical, "category"),
+        (
+            pd.DatetimeIndex(["2017", "2018"], tz="US/Central"),
+            DatetimeArray,
+            "datetime64[ns, US/Central]",
+        ),
+        (
+            pd.PeriodIndex([2018, 2019], freq="Y"),
+            PeriodArray,
+            pd.core.dtypes.dtypes.PeriodDtype("Y-DEC"),
+        ),
+        (pd.IntervalIndex.from_breaks([0, 1, 2]), IntervalArray, "interval"),
+        (
+            pd.DatetimeIndex(["2017", "2018"]),
+            DatetimeArray,
+            "datetime64[ns]",
+        ),
+        (
+            pd.TimedeltaIndex([10**10]),
+            TimedeltaArray,
+            "m8[ns]",
+        ),
+    ],
+)
+def test_values_consistent(arr, expected_type, dtype, using_infer_string):
+    if using_infer_string and dtype == "object":
+        expected_type = ArrowStringArrayNumpySemantics
+    l_values = Series(arr)._values
+    r_values = pd.Index(arr)._values
+    assert type(l_values) is expected_type
+    assert type(l_values) is type(r_values)
+
+    tm.assert_equal(l_values, r_values)
+
+
+@pytest.mark.parametrize("arr", [np.array([1, 2, 3])])
+def test_numpy_array(arr):
+    ser = Series(arr)
+    result = ser.array
+    expected = NumpyExtensionArray(arr)
+    tm.assert_extension_array_equal(result, expected)
+
+
+def test_numpy_array_all_dtypes(any_numpy_dtype):
+    ser = Series(dtype=any_numpy_dtype)
+    result = ser.array
+    if np.dtype(any_numpy_dtype).kind == "M":
+        assert isinstance(result, DatetimeArray)
+    elif np.dtype(any_numpy_dtype).kind == "m":
+        assert isinstance(result, TimedeltaArray)
+    else:
+        assert isinstance(result, NumpyExtensionArray)
+
+
+@pytest.mark.parametrize(
+    "arr, attr",
+    [
+        (pd.Categorical(["a", "b"]), "_codes"),
+        (PeriodArray._from_sequence(["2000", "2001"], dtype="period[D]"), "_ndarray"),
+        (pd.array([0, np.nan], dtype="Int64"), "_data"),
+        (IntervalArray.from_breaks([0, 1]), "_left"),
+        (SparseArray([0, 1]), "_sparse_values"),
+        (
+            DatetimeArray._from_sequence(np.array([1, 2], dtype="datetime64[ns]")),
+            "_ndarray",
+        ),
+        # tz-aware Datetime
+        (
+            DatetimeArray._from_sequence(
+                np.array(
+                    ["2000-01-01T12:00:00", "2000-01-02T12:00:00"], dtype="M8[ns]"
+                ),
+                dtype=DatetimeTZDtype(tz="US/Central"),
+            ),
+            "_ndarray",
+        ),
+    ],
+)
+def test_array(arr, attr, index_or_series, request):
+    box = index_or_series
+
+    result = box(arr, copy=False).array
+
+    if attr:
+        arr = getattr(arr, attr)
+        result = getattr(result, attr)
+
+    assert result is arr
+
+
+def test_array_multiindex_raises():
+    idx = pd.MultiIndex.from_product([["A"], ["a", "b"]])
+    msg = "MultiIndex has no single backing array"
+    with pytest.raises(ValueError, match=msg):
+        idx.array
+
+
+@pytest.mark.parametrize(
+    "arr, expected",
+    [
+        (np.array([1, 2], dtype=np.int64), np.array([1, 2], dtype=np.int64)),
+        (pd.Categorical(["a", "b"]), np.array(["a", "b"], dtype=object)),
+        (
+            pd.core.arrays.period_array(["2000", "2001"], freq="D"),
+            np.array([pd.Period("2000", freq="D"), pd.Period("2001", freq="D")]),
+        ),
+        (pd.array([0, np.nan], dtype="Int64"), np.array([0, np.nan])),
+        (
+            IntervalArray.from_breaks([0, 1, 2]),
+            np.array([pd.Interval(0, 1), pd.Interval(1, 2)], dtype=object),
+        ),
+        (SparseArray([0, 1]), np.array([0, 1], dtype=np.int64)),
+        # tz-naive datetime
+        (
+            DatetimeArray._from_sequence(np.array(["2000", "2001"], dtype="M8[ns]")),
+            np.array(["2000", "2001"], dtype="M8[ns]"),
+        ),
+        # tz-aware stays tz`-aware
+        (
+            DatetimeArray._from_sequence(
+                np.array(["2000-01-01T06:00:00", "2000-01-02T06:00:00"], dtype="M8[ns]")
+            )
+            .tz_localize("UTC")
+            .tz_convert("US/Central"),
+            np.array(
+                [
+                    Timestamp("2000-01-01", tz="US/Central"),
+                    Timestamp("2000-01-02", tz="US/Central"),
+                ]
+            ),
+        ),
+        # Timedelta
+        (
+            TimedeltaArray._from_sequence(
+                np.array([0, 3600000000000], dtype="i8").view("m8[ns]")
+            ),
+            np.array([0, 3600000000000], dtype="m8[ns]"),
+        ),
+        # GH#26406 tz is preserved in Categorical[dt64tz]
+        (
+            pd.Categorical(date_range("2016-01-01", periods=2, tz="US/Pacific")),
+            np.array(
+                [
+                    Timestamp("2016-01-01", tz="US/Pacific"),
+                    Timestamp("2016-01-02", tz="US/Pacific"),
+                ]
+            ),
+        ),
+    ],
+)
+def test_to_numpy(arr, expected, index_or_series_or_array, request):
+    box = index_or_series_or_array
+
+    with tm.assert_produces_warning(None):
+        thing = box(arr)
+
+    result = thing.to_numpy()
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = np.asarray(thing)
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("as_series", [True, False])
+@pytest.mark.parametrize(
+    "arr", [np.array([1, 2, 3], dtype="int64"), np.array(["a", "b", "c"], dtype=object)]
+)
+def test_to_numpy_copy(arr, as_series, using_infer_string):
+    obj = pd.Index(arr, copy=False)
+    if as_series:
+        obj = Series(obj.values, copy=False)
+
+    # no copy by default
+    result = obj.to_numpy()
+    if using_infer_string and arr.dtype == object:
+        assert np.shares_memory(arr, result) is False
+    else:
+        assert np.shares_memory(arr, result) is True
+
+    result = obj.to_numpy(copy=False)
+    if using_infer_string and arr.dtype == object:
+        assert np.shares_memory(arr, result) is False
+    else:
+        assert np.shares_memory(arr, result) is True
+
+    # copy=True
+    result = obj.to_numpy(copy=True)
+    assert np.shares_memory(arr, result) is False
+
+
+@pytest.mark.parametrize("as_series", [True, False])
+def test_to_numpy_dtype(as_series, unit):
+    tz = "US/Eastern"
+    obj = pd.DatetimeIndex(["2000", "2001"], tz=tz)
+    if as_series:
+        obj = Series(obj)
+
+    # preserve tz by default
+    result = obj.to_numpy()
+    expected = np.array(
+        [Timestamp("2000", tz=tz), Timestamp("2001", tz=tz)], dtype=object
+    )
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = obj.to_numpy(dtype="object")
+    tm.assert_numpy_array_equal(result, expected)
+
+    result = obj.to_numpy(dtype="M8[ns]")
+    expected = np.array(["2000-01-01T05", "2001-01-01T05"], dtype="M8[ns]")
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "values, dtype, na_value, expected",
+    [
+        ([1, 2, None], "float64", 0, [1.0, 2.0, 0.0]),
+        (
+            [Timestamp("2000"), Timestamp("2000"), pd.NaT],
+            None,
+            Timestamp("2000"),
+            [np.datetime64("2000-01-01T00:00:00.000000000")] * 3,
+        ),
+    ],
+)
+def test_to_numpy_na_value_numpy_dtype(
+    index_or_series, values, dtype, na_value, expected
+):
+    obj = index_or_series(values)
+    result = obj.to_numpy(dtype=dtype, na_value=na_value)
+    expected = np.array(expected)
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "data, multiindex, dtype, na_value, expected",
+    [
+        (
+            [1, 2, None, 4],
+            [(0, "a"), (0, "b"), (1, "b"), (1, "c")],
+            float,
+            None,
+            [1.0, 2.0, np.nan, 4.0],
+        ),
+        (
+            [1, 2, None, 4],
+            [(0, "a"), (0, "b"), (1, "b"), (1, "c")],
+            float,
+            np.nan,
+            [1.0, 2.0, np.nan, 4.0],
+        ),
+        (
+            [1.0, 2.0, np.nan, 4.0],
+            [("a", 0), ("a", 1), ("a", 2), ("b", 0)],
+            int,
+            0,
+            [1, 2, 0, 4],
+        ),
+        (
+            [Timestamp("2000"), Timestamp("2000"), pd.NaT],
+            [(0, Timestamp("2021")), (0, Timestamp("2022")), (1, Timestamp("2000"))],
+            None,
+            Timestamp("2000"),
+            [np.datetime64("2000-01-01T00:00:00.000000000")] * 3,
+        ),
+    ],
+)
+def test_to_numpy_multiindex_series_na_value(
+    data, multiindex, dtype, na_value, expected
+):
+    index = pd.MultiIndex.from_tuples(multiindex)
+    series = Series(data, index=index)
+    result = series.to_numpy(dtype=dtype, na_value=na_value)
+    expected = np.array(expected)
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_to_numpy_kwargs_raises():
+    # numpy
+    s = Series([1, 2, 3])
+    msg = r"to_numpy\(\) got an unexpected keyword argument 'foo'"
+    with pytest.raises(TypeError, match=msg):
+        s.to_numpy(foo=True)
+
+    # extension
+    s = Series([1, 2, 3], dtype="Int64")
+    with pytest.raises(TypeError, match=msg):
+        s.to_numpy(foo=True)
+
+
+@pytest.mark.parametrize(
+    "data",
+    [
+        {"a": [1, 2, 3], "b": [1, 2, None]},
+        {"a": np.array([1, 2, 3]), "b": np.array([1, 2, np.nan])},
+        {"a": pd.array([1, 2, 3]), "b": pd.array([1, 2, None])},
+    ],
+)
+@pytest.mark.parametrize("dtype, na_value", [(float, np.nan), (object, None)])
+def test_to_numpy_dataframe_na_value(data, dtype, na_value):
+    # https://github.com/pandas-dev/pandas/issues/33820
+    df = pd.DataFrame(data)
+    result = df.to_numpy(dtype=dtype, na_value=na_value)
+    expected = np.array([[1, 1], [2, 2], [3, na_value]], dtype=dtype)
+    tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "data, expected",
+    [
+        (
+            {"a": pd.array([1, 2, None])},
+            np.array([[1.0], [2.0], [np.nan]], dtype=float),
+        ),
+        (
+            {"a": [1, 2, 3], "b": [1, 2, 3]},
+            np.array([[1, 1], [2, 2], [3, 3]], dtype=float),
+        ),
+    ],
+)
+def test_to_numpy_dataframe_single_block(data, expected):
+    # https://github.com/pandas-dev/pandas/issues/33820
+    df = pd.DataFrame(data)
+    result = df.to_numpy(dtype=float, na_value=np.nan)
+    tm.assert_numpy_array_equal(result, expected)
+
+
+def test_to_numpy_dataframe_single_block_no_mutate():
+    # https://github.com/pandas-dev/pandas/issues/33820
+    result = pd.DataFrame(np.array([1.0, 2.0, np.nan]))
+    expected = pd.DataFrame(np.array([1.0, 2.0, np.nan]))
+    result.to_numpy(na_value=0.0)
+    tm.assert_frame_equal(result, expected)
+
+
+class TestAsArray:
+    @pytest.mark.parametrize("tz", [None, "US/Central"])
+    def test_asarray_object_dt64(self, tz):
+        ser = Series(date_range("2000", periods=2, tz=tz))
+
+        with tm.assert_produces_warning(None):
+            # Future behavior (for tzaware case) with no warning
+            result = np.asarray(ser, dtype=object)
+
+        expected = np.array(
+            [Timestamp("2000-01-01", tz=tz), Timestamp("2000-01-02", tz=tz)]
+        )
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_asarray_tz_naive(self):
+        # This shouldn't produce a warning.
+        ser = Series(date_range("2000", periods=2))
+        expected = np.array(["2000-01-01", "2000-01-02"], dtype="M8[ns]")
+        result = np.asarray(ser)
+
+        tm.assert_numpy_array_equal(result, expected)
+
+    def test_asarray_tz_aware(self):
+        tz = "US/Central"
+        ser = Series(date_range("2000", periods=2, tz=tz))
+        expected = np.array(["2000-01-01T06", "2000-01-02T06"], dtype="M8[ns]")
+        result = np.asarray(ser, dtype="datetime64[ns]")
+
+        tm.assert_numpy_array_equal(result, expected)
+
+        # Old behavior with no warning
+        result = np.asarray(ser, dtype="M8[ns]")
+
+        tm.assert_numpy_array_equal(result, expected)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/base/test_fillna.py

@@ -0,0 +1,60 @@
+"""
+Though Index.fillna and Series.fillna has separate impl,
+test here to confirm these works as the same
+"""
+
+import numpy as np
+import pytest
+
+from pandas import MultiIndex
+import pandas._testing as tm
+from pandas.tests.base.common import allow_na_ops
+
+
+def test_fillna(index_or_series_obj):
+    # GH 11343
+    obj = index_or_series_obj
+
+    if isinstance(obj, MultiIndex):
+        msg = "isna is not defined for MultiIndex"
+        with pytest.raises(NotImplementedError, match=msg):
+            obj.fillna(0)
+        return
+
+    # values will not be changed
+    fill_value = obj.values[0] if len(obj) > 0 else 0
+    result = obj.fillna(fill_value)
+
+    tm.assert_equal(obj, result)
+
+    # check shallow_copied
+    assert obj is not result
+
+
+@pytest.mark.parametrize("null_obj", [np.nan, None])
+def test_fillna_null(null_obj, index_or_series_obj):
+    # GH 11343
+    obj = index_or_series_obj
+    klass = type(obj)
+
+    if not allow_na_ops(obj):
+        pytest.skip(f"{klass} doesn't allow for NA operations")
+    elif len(obj) < 1:
+        pytest.skip("Test doesn't make sense on empty data")
+    elif isinstance(obj, MultiIndex):
+        pytest.skip(f"MultiIndex can't hold '{null_obj}'")
+
+    values = obj._values
+    fill_value = values[0]
+    expected = values.copy()
+    values[0:2] = null_obj
+    expected[0:2] = fill_value
+
+    expected = klass(expected)
+    obj = klass(values)
+
+    result = obj.fillna(fill_value)
+    tm.assert_equal(result, expected)
+
+    # check shallow_copied
+    assert obj is not result

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/base/test_misc.py

@@ -0,0 +1,191 @@
+import sys
+
+import numpy as np
+import pytest
+
+from pandas._config import using_pyarrow_string_dtype
+
+from pandas.compat import PYPY
+
+from pandas.core.dtypes.common import (
+    is_dtype_equal,
+    is_object_dtype,
+)
+
+import pandas as pd
+from pandas import (
+    Index,
+    Series,
+)
+import pandas._testing as tm
+
+
+def test_isnull_notnull_docstrings():
+    # GH#41855 make sure its clear these are aliases
+    doc = pd.DataFrame.notnull.__doc__
+    assert doc.startswith("\nDataFrame.notnull is an alias for DataFrame.notna.\n")
+    doc = pd.DataFrame.isnull.__doc__
+    assert doc.startswith("\nDataFrame.isnull is an alias for DataFrame.isna.\n")
+
+    doc = Series.notnull.__doc__
+    assert doc.startswith("\nSeries.notnull is an alias for Series.notna.\n")
+    doc = Series.isnull.__doc__
+    assert doc.startswith("\nSeries.isnull is an alias for Series.isna.\n")
+
+
+@pytest.mark.parametrize(
+    "op_name, op",
+    [
+        ("add", "+"),
+        ("sub", "-"),
+        ("mul", "*"),
+        ("mod", "%"),
+        ("pow", "**"),
+        ("truediv", "/"),
+        ("floordiv", "//"),
+    ],
+)
+def test_binary_ops_docstring(frame_or_series, op_name, op):
+    # not using the all_arithmetic_functions fixture with _get_opstr
+    # as _get_opstr is used internally in the dynamic implementation of the docstring
+    klass = frame_or_series
+
+    operand1 = klass.__name__.lower()
+    operand2 = "other"
+    expected_str = " ".join([operand1, op, operand2])
+    assert expected_str in getattr(klass, op_name).__doc__
+
+    # reverse version of the binary ops
+    expected_str = " ".join([operand2, op, operand1])
+    assert expected_str in getattr(klass, "r" + op_name).__doc__
+
+
+def test_ndarray_compat_properties(index_or_series_obj):
+    obj = index_or_series_obj
+
+    # Check that we work.
+    for p in ["shape", "dtype", "T", "nbytes"]:
+        assert getattr(obj, p, None) is not None
+
+    # deprecated properties
+    for p in ["strides", "itemsize", "base", "data"]:
+        assert not hasattr(obj, p)
+
+    msg = "can only convert an array of size 1 to a Python scalar"
+    with pytest.raises(ValueError, match=msg):
+        obj.item()  # len > 1
+
+    assert obj.ndim == 1
+    assert obj.size == len(obj)
+
+    assert Index([1]).item() == 1
+    assert Series([1]).item() == 1
+
+
+@pytest.mark.skipif(
+    PYPY or using_pyarrow_string_dtype(),
+    reason="not relevant for PyPy doesn't work properly for arrow strings",
+)
+def test_memory_usage(index_or_series_memory_obj):
+    obj = index_or_series_memory_obj
+    # Clear index caches so that len(obj) == 0 report 0 memory usage
+    if isinstance(obj, Series):
+        is_ser = True
+        obj.index._engine.clear_mapping()
+    else:
+        is_ser = False
+        obj._engine.clear_mapping()
+
+    res = obj.memory_usage()
+    res_deep = obj.memory_usage(deep=True)
+
+    is_object = is_object_dtype(obj) or (is_ser and is_object_dtype(obj.index))
+    is_categorical = isinstance(obj.dtype, pd.CategoricalDtype) or (
+        is_ser and isinstance(obj.index.dtype, pd.CategoricalDtype)
+    )
+    is_object_string = is_dtype_equal(obj, "string[python]") or (
+        is_ser and is_dtype_equal(obj.index.dtype, "string[python]")
+    )
+
+    if len(obj) == 0:
+        expected = 0
+        assert res_deep == res == expected
+    elif is_object or is_categorical or is_object_string:
+        # only deep will pick them up
+        assert res_deep > res
+    else:
+        assert res == res_deep
+
+    # sys.getsizeof will call the .memory_usage with
+    # deep=True, and add on some GC overhead
+    diff = res_deep - sys.getsizeof(obj)
+    assert abs(diff) < 100
+
+
+def test_memory_usage_components_series(series_with_simple_index):
+    series = series_with_simple_index
+    total_usage = series.memory_usage(index=True)
+    non_index_usage = series.memory_usage(index=False)
+    index_usage = series.index.memory_usage()
+    assert total_usage == non_index_usage + index_usage
+
+
+@pytest.mark.parametrize("dtype", tm.NARROW_NP_DTYPES)
+def test_memory_usage_components_narrow_series(dtype):
+    series = Series(range(5), dtype=dtype, index=[f"i-{i}" for i in range(5)], name="a")
+    total_usage = series.memory_usage(index=True)
+    non_index_usage = series.memory_usage(index=False)
+    index_usage = series.index.memory_usage()
+    assert total_usage == non_index_usage + index_usage
+
+
+def test_searchsorted(request, index_or_series_obj):
+    # numpy.searchsorted calls obj.searchsorted under the hood.
+    # See gh-12238
+    obj = index_or_series_obj
+
+    if isinstance(obj, pd.MultiIndex):
+        # See gh-14833
+        request.applymarker(
+            pytest.mark.xfail(
+                reason="np.searchsorted doesn't work on pd.MultiIndex: GH 14833"
+            )
+        )
+    elif obj.dtype.kind == "c" and isinstance(obj, Index):
+        # TODO: Should Series cases also raise? Looks like they use numpy
+        #  comparison semantics https://github.com/numpy/numpy/issues/15981
+        mark = pytest.mark.xfail(reason="complex objects are not comparable")
+        request.applymarker(mark)
+
+    max_obj = max(obj, default=0)
+    index = np.searchsorted(obj, max_obj)
+    assert 0 <= index <= len(obj)
+
+    index = np.searchsorted(obj, max_obj, sorter=range(len(obj)))
+    assert 0 <= index <= len(obj)
+
+
+def test_access_by_position(index_flat):
+    index = index_flat
+
+    if len(index) == 0:
+        pytest.skip("Test doesn't make sense on empty data")
+
+    series = Series(index)
+    assert index[0] == series.iloc[0]
+    assert index[5] == series.iloc[5]
+    assert index[-1] == series.iloc[-1]
+
+    size = len(index)
+    assert index[-1] == index[size - 1]
+
+    msg = f"index {size} is out of bounds for axis 0 with size {size}"
+    if is_dtype_equal(index.dtype, "string[pyarrow]") or is_dtype_equal(
+        index.dtype, "string[pyarrow_numpy]"
+    ):
+        msg = "index out of bounds"
+    with pytest.raises(IndexError, match=msg):
+        index[size]
+    msg = "single positional indexer is out-of-bounds"
+    with pytest.raises(IndexError, match=msg):
+        series.iloc[size]

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/base/test_transpose.py

@@ -0,0 +1,56 @@
+import numpy as np
+import pytest
+
+from pandas import (
+    CategoricalDtype,
+    DataFrame,
+)
+import pandas._testing as tm
+
+
+def test_transpose(index_or_series_obj):
+    obj = index_or_series_obj
+    tm.assert_equal(obj.transpose(), obj)
+
+
+def test_transpose_non_default_axes(index_or_series_obj):
+    msg = "the 'axes' parameter is not supported"
+    obj = index_or_series_obj
+    with pytest.raises(ValueError, match=msg):
+        obj.transpose(1)
+    with pytest.raises(ValueError, match=msg):
+        obj.transpose(axes=1)
+
+
+def test_numpy_transpose(index_or_series_obj):
+    msg = "the 'axes' parameter is not supported"
+    obj = index_or_series_obj
+    tm.assert_equal(np.transpose(obj), obj)
+
+    with pytest.raises(ValueError, match=msg):
+        np.transpose(obj, axes=1)
+
+
+@pytest.mark.parametrize(
+    "data, transposed_data, index, columns, dtype",
+    [
+        ([[1], [2]], [[1, 2]], ["a", "a"], ["b"], int),
+        ([[1], [2]], [[1, 2]], ["a", "a"], ["b"], CategoricalDtype([1, 2])),
+        ([[1, 2]], [[1], [2]], ["b"], ["a", "a"], int),
+        ([[1, 2]], [[1], [2]], ["b"], ["a", "a"], CategoricalDtype([1, 2])),
+        ([[1, 2], [3, 4]], [[1, 3], [2, 4]], ["a", "a"], ["b", "b"], int),
+        (
+            [[1, 2], [3, 4]],
+            [[1, 3], [2, 4]],
+            ["a", "a"],
+            ["b", "b"],
+            CategoricalDtype([1, 2, 3, 4]),
+        ),
+    ],
+)
+def test_duplicate_labels(data, transposed_data, index, columns, dtype):
+    # GH 42380
+    df = DataFrame(data, index=index, columns=columns, dtype=dtype)
+    result = df.T
+    expected = DataFrame(transposed_data, index=columns, columns=index, dtype=dtype)
+    tm.assert_frame_equal(result, expected)

Prism/LLaDA/LLaDA_Prism/.venv/lib/python3.12/site-packages/pandas/tests/base/test_unique.py

@@ -0,0 +1,124 @@
+import numpy as np
+import pytest
+
+from pandas._config import using_pyarrow_string_dtype
+
+import pandas as pd
+import pandas._testing as tm
+from pandas.tests.base.common import allow_na_ops
+
+
+@pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning")
+def test_unique(index_or_series_obj):
+    obj = index_or_series_obj
+    obj = np.repeat(obj, range(1, len(obj) + 1))
+    result = obj.unique()
+
+    # dict.fromkeys preserves the order
+    unique_values = list(dict.fromkeys(obj.values))
+    if isinstance(obj, pd.MultiIndex):
+        expected = pd.MultiIndex.from_tuples(unique_values)
+        expected.names = obj.names
+        tm.assert_index_equal(result, expected, exact=True)
+    elif isinstance(obj, pd.Index):
+        expected = pd.Index(unique_values, dtype=obj.dtype)
+        if isinstance(obj.dtype, pd.DatetimeTZDtype):
+            expected = expected.normalize()
+        tm.assert_index_equal(result, expected, exact=True)
+    else:
+        expected = np.array(unique_values)
+        tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.filterwarnings(r"ignore:PeriodDtype\[B\] is deprecated:FutureWarning")
+@pytest.mark.parametrize("null_obj", [np.nan, None])
+def test_unique_null(null_obj, index_or_series_obj):
+    obj = index_or_series_obj
+
+    if not allow_na_ops(obj):
+        pytest.skip("type doesn't allow for NA operations")
+    elif len(obj) < 1:
+        pytest.skip("Test doesn't make sense on empty data")
+    elif isinstance(obj, pd.MultiIndex):
+        pytest.skip(f"MultiIndex can't hold '{null_obj}'")
+
+    values = obj._values
+    values[0:2] = null_obj
+
+    klass = type(obj)
+    repeated_values = np.repeat(values, range(1, len(values) + 1))
+    obj = klass(repeated_values, dtype=obj.dtype)
+    result = obj.unique()
+
+    unique_values_raw = dict.fromkeys(obj.values)
+    # because np.nan == np.nan is False, but None == None is True
+    # np.nan would be duplicated, whereas None wouldn't
+    unique_values_not_null = [val for val in unique_values_raw if not pd.isnull(val)]
+    unique_values = [null_obj] + unique_values_not_null
+
+    if isinstance(obj, pd.Index):
+        expected = pd.Index(unique_values, dtype=obj.dtype)
+        if isinstance(obj.dtype, pd.DatetimeTZDtype):
+            result = result.normalize()
+            expected = expected.normalize()
+        tm.assert_index_equal(result, expected, exact=True)
+    else:
+        expected = np.array(unique_values, dtype=obj.dtype)
+        tm.assert_numpy_array_equal(result, expected)
+
+
+def test_nunique(index_or_series_obj):
+    obj = index_or_series_obj
+    obj = np.repeat(obj, range(1, len(obj) + 1))
+    expected = len(obj.unique())
+    assert obj.nunique(dropna=False) == expected
+
+
+@pytest.mark.parametrize("null_obj", [np.nan, None])
+def test_nunique_null(null_obj, index_or_series_obj):
+    obj = index_or_series_obj
+
+    if not allow_na_ops(obj):
+        pytest.skip("type doesn't allow for NA operations")
+    elif isinstance(obj, pd.MultiIndex):
+        pytest.skip(f"MultiIndex can't hold '{null_obj}'")
+
+    values = obj._values
+    values[0:2] = null_obj
+
+    klass = type(obj)
+    repeated_values = np.repeat(values, range(1, len(values) + 1))
+    obj = klass(repeated_values, dtype=obj.dtype)
+
+    if isinstance(obj, pd.CategoricalIndex):
+        assert obj.nunique() == len(obj.categories)
+        assert obj.nunique(dropna=False) == len(obj.categories) + 1
+    else:
+        num_unique_values = len(obj.unique())
+        assert obj.nunique() == max(0, num_unique_values - 1)
+        assert obj.nunique(dropna=False) == max(0, num_unique_values)
+
+
+@pytest.mark.single_cpu
+@pytest.mark.xfail(using_pyarrow_string_dtype(), reason="decoding fails")
+def test_unique_bad_unicode(index_or_series):
+    # regression test for #34550
+    uval = "\ud83d"  # smiley emoji
+
+    obj = index_or_series([uval] * 2)
+    result = obj.unique()
+
+    if isinstance(obj, pd.Index):
+        expected = pd.Index(["\ud83d"], dtype=object)
+        tm.assert_index_equal(result, expected, exact=True)
+    else:
+        expected = np.array(["\ud83d"], dtype=object)
+        tm.assert_numpy_array_equal(result, expected)
+
+
+@pytest.mark.parametrize("dropna", [True, False])
+def test_nunique_dropna(dropna):
+    # GH37566
+    ser = pd.Series(["yes", "yes", pd.NA, np.nan, None, pd.NaT])
+    res = ser.nunique(dropna)
+    assert res == 1 if dropna else 5