针对pulse-transit的工具

dist/client/pandas/core/arrays/sparse/__init__.py

@@ -0,0 +1,13 @@
+# flake8: noqa: F401
+
+from pandas.core.arrays.sparse.accessor import (
+    SparseAccessor,
+    SparseFrameAccessor,
+)
+from pandas.core.arrays.sparse.array import (
+    BlockIndex,
+    IntIndex,
+    SparseArray,
+    make_sparse_index,
+)
+from pandas.core.arrays.sparse.dtype import SparseDtype

dist/client/pandas/core/arrays/sparse/accessor.py

@@ -0,0 +1,386 @@
+"""Sparse accessor"""
+
+import numpy as np
+
+from pandas.compat._optional import import_optional_dependency
+
+from pandas.core.dtypes.cast import find_common_type
+
+from pandas.core.accessor import (
+    PandasDelegate,
+    delegate_names,
+)
+from pandas.core.arrays.sparse.array import SparseArray
+from pandas.core.arrays.sparse.dtype import SparseDtype
+
+
+class BaseAccessor:
+    _validation_msg = "Can only use the '.sparse' accessor with Sparse data."
+
+    def __init__(self, data=None):
+        self._parent = data
+        self._validate(data)
+
+    def _validate(self, data):
+        raise NotImplementedError
+
+
+@delegate_names(
+    SparseArray, ["npoints", "density", "fill_value", "sp_values"], typ="property"
+)
+class SparseAccessor(BaseAccessor, PandasDelegate):
+    """
+    Accessor for SparseSparse from other sparse matrix data types.
+    """
+
+    def _validate(self, data):
+        if not isinstance(data.dtype, SparseDtype):
+            raise AttributeError(self._validation_msg)
+
+    def _delegate_property_get(self, name, *args, **kwargs):
+        return getattr(self._parent.array, name)
+
+    def _delegate_method(self, name, *args, **kwargs):
+        if name == "from_coo":
+            return self.from_coo(*args, **kwargs)
+        elif name == "to_coo":
+            return self.to_coo(*args, **kwargs)
+        else:
+            raise ValueError
+
+    @classmethod
+    def from_coo(cls, A, dense_index=False):
+        """
+        Create a Series with sparse values from a scipy.sparse.coo_matrix.
+
+        Parameters
+        ----------
+        A : scipy.sparse.coo_matrix
+        dense_index : bool, default False
+            If False (default), the SparseSeries index consists of only the
+            coords of the non-null entries of the original coo_matrix.
+            If True, the SparseSeries index consists of the full sorted
+            (row, col) coordinates of the coo_matrix.
+
+        Returns
+        -------
+        s : Series
+            A Series with sparse values.
+
+        Examples
+        --------
+        >>> from scipy import sparse
+
+        >>> A = sparse.coo_matrix(
+        ...     ([3.0, 1.0, 2.0], ([1, 0, 0], [0, 2, 3])), shape=(3, 4)
+        ... )
+        >>> A
+        <3x4 sparse matrix of type '<class 'numpy.float64'>'
+        with 3 stored elements in COOrdinate format>
+
+        >>> A.todense()
+        matrix([[0., 0., 1., 2.],
+        [3., 0., 0., 0.],
+        [0., 0., 0., 0.]])
+
+        >>> ss = pd.Series.sparse.from_coo(A)
+        >>> ss
+        0  2    1.0
+           3    2.0
+        1  0    3.0
+        dtype: Sparse[float64, nan]
+        """
+        from pandas import Series
+        from pandas.core.arrays.sparse.scipy_sparse import coo_to_sparse_series
+
+        result = coo_to_sparse_series(A, dense_index=dense_index)
+        result = Series(result.array, index=result.index, copy=False)
+
+        return result
+
+    def to_coo(self, row_levels=(0,), column_levels=(1,), sort_labels=False):
+        """
+        Create a scipy.sparse.coo_matrix from a Series with MultiIndex.
+
+        Use row_levels and column_levels to determine the row and column
+        coordinates respectively. row_levels and column_levels are the names
+        (labels) or numbers of the levels. {row_levels, column_levels} must be
+        a partition of the MultiIndex level names (or numbers).
+
+        Parameters
+        ----------
+        row_levels : tuple/list
+        column_levels : tuple/list
+        sort_labels : bool, default False
+            Sort the row and column labels before forming the sparse matrix.
+            When `row_levels` and/or `column_levels` refer to a single level,
+            set to `True` for a faster execution.
+
+        Returns
+        -------
+        y : scipy.sparse.coo_matrix
+        rows : list (row labels)
+        columns : list (column labels)
+
+        Examples
+        --------
+        >>> s = pd.Series([3.0, np.nan, 1.0, 3.0, np.nan, np.nan])
+        >>> s.index = pd.MultiIndex.from_tuples(
+        ...     [
+        ...         (1, 2, "a", 0),
+        ...         (1, 2, "a", 1),
+        ...         (1, 1, "b", 0),
+        ...         (1, 1, "b", 1),
+        ...         (2, 1, "b", 0),
+        ...         (2, 1, "b", 1)
+        ...     ],
+        ...     names=["A", "B", "C", "D"],
+        ... )
+        >>> s
+        A  B  C  D
+        1  2  a  0    3.0
+                 1    NaN
+           1  b  0    1.0
+                 1    3.0
+        2  1  b  0    NaN
+                 1    NaN
+        dtype: float64
+
+        >>> ss = s.astype("Sparse")
+        >>> ss
+        A  B  C  D
+        1  2  a  0    3.0
+                 1    NaN
+           1  b  0    1.0
+                 1    3.0
+        2  1  b  0    NaN
+                 1    NaN
+        dtype: Sparse[float64, nan]
+
+        >>> A, rows, columns = ss.sparse.to_coo(
+        ...     row_levels=["A", "B"], column_levels=["C", "D"], sort_labels=True
+        ... )
+        >>> A
+        <3x4 sparse matrix of type '<class 'numpy.float64'>'
+        with 3 stored elements in COOrdinate format>
+        >>> A.todense()
+        matrix([[0., 0., 1., 3.],
+        [3., 0., 0., 0.],
+        [0., 0., 0., 0.]])
+
+        >>> rows
+        [(1, 1), (1, 2), (2, 1)]
+        >>> columns
+        [('a', 0), ('a', 1), ('b', 0), ('b', 1)]
+        """
+        from pandas.core.arrays.sparse.scipy_sparse import sparse_series_to_coo
+
+        A, rows, columns = sparse_series_to_coo(
+            self._parent, row_levels, column_levels, sort_labels=sort_labels
+        )
+        return A, rows, columns
+
+    def to_dense(self):
+        """
+        Convert a Series from sparse values to dense.
+
+        .. versionadded:: 0.25.0
+
+        Returns
+        -------
+        Series:
+            A Series with the same values, stored as a dense array.
+
+        Examples
+        --------
+        >>> series = pd.Series(pd.arrays.SparseArray([0, 1, 0]))
+        >>> series
+        0    0
+        1    1
+        2    0
+        dtype: Sparse[int64, 0]
+
+        >>> series.sparse.to_dense()
+        0    0
+        1    1
+        2    0
+        dtype: int64
+        """
+        from pandas import Series
+
+        return Series(
+            self._parent.array.to_dense(),
+            index=self._parent.index,
+            name=self._parent.name,
+        )
+
+
+class SparseFrameAccessor(BaseAccessor, PandasDelegate):
+    """
+    DataFrame accessor for sparse data.
+
+    .. versionadded:: 0.25.0
+    """
+
+    def _validate(self, data):
+        dtypes = data.dtypes
+        if not all(isinstance(t, SparseDtype) for t in dtypes):
+            raise AttributeError(self._validation_msg)
+
+    @classmethod
+    def from_spmatrix(cls, data, index=None, columns=None):
+        """
+        Create a new DataFrame from a scipy sparse matrix.
+
+        .. versionadded:: 0.25.0
+
+        Parameters
+        ----------
+        data : scipy.sparse.spmatrix
+            Must be convertible to csc format.
+        index, columns : Index, optional
+            Row and column labels to use for the resulting DataFrame.
+            Defaults to a RangeIndex.
+
+        Returns
+        -------
+        DataFrame
+            Each column of the DataFrame is stored as a
+            :class:`arrays.SparseArray`.
+
+        Examples
+        --------
+        >>> import scipy.sparse
+        >>> mat = scipy.sparse.eye(3)
+        >>> pd.DataFrame.sparse.from_spmatrix(mat)
+             0    1    2
+        0  1.0  0.0  0.0
+        1  0.0  1.0  0.0
+        2  0.0  0.0  1.0
+        """
+        from pandas._libs.sparse import IntIndex
+
+        from pandas import DataFrame
+
+        data = data.tocsc()
+        index, columns = cls._prep_index(data, index, columns)
+        n_rows, n_columns = data.shape
+        # We need to make sure indices are sorted, as we create
+        # IntIndex with no input validation (i.e. check_integrity=False ).
+        # Indices may already be sorted in scipy in which case this adds
+        # a small overhead.
+        data.sort_indices()
+        indices = data.indices
+        indptr = data.indptr
+        array_data = data.data
+        dtype = SparseDtype(array_data.dtype, 0)
+        arrays = []
+        for i in range(n_columns):
+            sl = slice(indptr[i], indptr[i + 1])
+            idx = IntIndex(n_rows, indices[sl], check_integrity=False)
+            arr = SparseArray._simple_new(array_data[sl], idx, dtype)
+            arrays.append(arr)
+        return DataFrame._from_arrays(
+            arrays, columns=columns, index=index, verify_integrity=False
+        )
+
+    def to_dense(self):
+        """
+        Convert a DataFrame with sparse values to dense.
+
+        .. versionadded:: 0.25.0
+
+        Returns
+        -------
+        DataFrame
+            A DataFrame with the same values stored as dense arrays.
+
+        Examples
+        --------
+        >>> df = pd.DataFrame({"A": pd.arrays.SparseArray([0, 1, 0])})
+        >>> df.sparse.to_dense()
+           A
+        0  0
+        1  1
+        2  0
+        """
+        from pandas import DataFrame
+
+        data = {k: v.array.to_dense() for k, v in self._parent.items()}
+        return DataFrame(data, index=self._parent.index, columns=self._parent.columns)
+
+    def to_coo(self):
+        """
+        Return the contents of the frame as a sparse SciPy COO matrix.
+
+        .. versionadded:: 0.25.0
+
+        Returns
+        -------
+        coo_matrix : scipy.sparse.spmatrix
+            If the caller is heterogeneous and contains booleans or objects,
+            the result will be of dtype=object. See Notes.
+
+        Notes
+        -----
+        The dtype will be the lowest-common-denominator type (implicit
+        upcasting); that is to say if the dtypes (even of numeric types)
+        are mixed, the one that accommodates all will be chosen.
+
+        e.g. If the dtypes are float16 and float32, dtype will be upcast to
+        float32. By numpy.find_common_type convention, mixing int64 and
+        and uint64 will result in a float64 dtype.
+        """
+        import_optional_dependency("scipy")
+        from scipy.sparse import coo_matrix
+
+        dtype = find_common_type(self._parent.dtypes.to_list())
+        if isinstance(dtype, SparseDtype):
+            dtype = dtype.subtype
+
+        cols, rows, data = [], [], []
+        for col, (_, ser) in enumerate(self._parent.iteritems()):
+            sp_arr = ser.array
+            if sp_arr.fill_value != 0:
+                raise ValueError("fill value must be 0 when converting to COO matrix")
+
+            row = sp_arr.sp_index.indices
+            cols.append(np.repeat(col, len(row)))
+            rows.append(row)
+            data.append(sp_arr.sp_values.astype(dtype, copy=False))
+
+        cols = np.concatenate(cols)
+        rows = np.concatenate(rows)
+        data = np.concatenate(data)
+        return coo_matrix((data, (rows, cols)), shape=self._parent.shape)
+
+    @property
+    def density(self) -> float:
+        """
+        Ratio of non-sparse points to total (dense) data points.
+        """
+        tmp = np.mean([column.array.density for _, column in self._parent.items()])
+        return tmp
+
+    @staticmethod
+    def _prep_index(data, index, columns):
+        from pandas.core.indexes.api import (
+            default_index,
+            ensure_index,
+        )
+
+        N, K = data.shape
+        if index is None:
+            index = default_index(N)
+        else:
+            index = ensure_index(index)
+        if columns is None:
+            columns = default_index(K)
+        else:
+            columns = ensure_index(columns)
+
+        if len(columns) != K:
+            raise ValueError(f"Column length mismatch: {len(columns)} vs. {K}")
+        if len(index) != N:
+            raise ValueError(f"Index length mismatch: {len(index)} vs. {N}")
+        return index, columns

dist/client/pandas/core/arrays/sparse/dtype.py

@@ -0,0 +1,414 @@
+"""Sparse Dtype"""
+from __future__ import annotations
+
+import re
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+import warnings
+
+import numpy as np
+
+from pandas._typing import (
+    Dtype,
+    DtypeObj,
+    type_t,
+)
+from pandas.errors import PerformanceWarning
+from pandas.util._exceptions import find_stack_level
+
+from pandas.core.dtypes.base import (
+    ExtensionDtype,
+    register_extension_dtype,
+)
+from pandas.core.dtypes.cast import astype_nansafe
+from pandas.core.dtypes.common import (
+    is_bool_dtype,
+    is_object_dtype,
+    is_scalar,
+    is_string_dtype,
+    pandas_dtype,
+)
+from pandas.core.dtypes.missing import (
+    isna,
+    na_value_for_dtype,
+)
+
+if TYPE_CHECKING:
+    from pandas.core.arrays.sparse.array import SparseArray
+
+
+@register_extension_dtype
+class SparseDtype(ExtensionDtype):
+    """
+    Dtype for data stored in :class:`SparseArray`.
+
+    This dtype implements the pandas ExtensionDtype interface.
+
+    Parameters
+    ----------
+    dtype : str, ExtensionDtype, numpy.dtype, type, default numpy.float64
+        The dtype of the underlying array storing the non-fill value values.
+    fill_value : scalar, optional
+        The scalar value not stored in the SparseArray. By default, this
+        depends on `dtype`.
+
+        =========== ==========
+        dtype       na_value
+        =========== ==========
+        float       ``np.nan``
+        int         ``0``
+        bool        ``False``
+        datetime64  ``pd.NaT``
+        timedelta64 ``pd.NaT``
+        =========== ==========
+
+        The default value may be overridden by specifying a `fill_value`.
+
+    Attributes
+    ----------
+    None
+
+    Methods
+    -------
+    None
+    """
+
+    # We include `_is_na_fill_value` in the metadata to avoid hash collisions
+    # between SparseDtype(float, 0.0) and SparseDtype(float, nan).
+    # Without is_na_fill_value in the comparison, those would be equal since
+    # hash(nan) is (sometimes?) 0.
+    _metadata = ("_dtype", "_fill_value", "_is_na_fill_value")
+
+    def __init__(self, dtype: Dtype = np.float64, fill_value: Any = None):
+
+        if isinstance(dtype, type(self)):
+            if fill_value is None:
+                fill_value = dtype.fill_value
+            dtype = dtype.subtype
+
+        dtype = pandas_dtype(dtype)
+        if is_string_dtype(dtype):
+            dtype = np.dtype("object")
+
+        if fill_value is None:
+            fill_value = na_value_for_dtype(dtype)
+
+        self._dtype = dtype
+        self._fill_value = fill_value
+        self._check_fill_value()
+
+    def __hash__(self):
+        # Python3 doesn't inherit __hash__ when a base class overrides
+        # __eq__, so we explicitly do it here.
+        return super().__hash__()
+
+    def __eq__(self, other: Any) -> bool:
+        # We have to override __eq__ to handle NA values in _metadata.
+        # The base class does simple == checks, which fail for NA.
+        if isinstance(other, str):
+            try:
+                other = self.construct_from_string(other)
+            except TypeError:
+                return False
+
+        if isinstance(other, type(self)):
+            subtype = self.subtype == other.subtype
+            if self._is_na_fill_value:
+                # this case is complicated by two things:
+                # SparseDtype(float, float(nan)) == SparseDtype(float, np.nan)
+                # SparseDtype(float, np.nan)     != SparseDtype(float, pd.NaT)
+                # i.e. we want to treat any floating-point NaN as equal, but
+                # not a floating-point NaN and a datetime NaT.
+                fill_value = (
+                    other._is_na_fill_value
+                    and isinstance(self.fill_value, type(other.fill_value))
+                    or isinstance(other.fill_value, type(self.fill_value))
+                )
+            else:
+                fill_value = self.fill_value == other.fill_value
+
+            return subtype and fill_value
+        return False
+
+    @property
+    def fill_value(self):
+        """
+        The fill value of the array.
+
+        Converting the SparseArray to a dense ndarray will fill the
+        array with this value.
+
+        .. warning::
+
+           It's possible to end up with a SparseArray that has ``fill_value``
+           values in ``sp_values``. This can occur, for example, when setting
+           ``SparseArray.fill_value`` directly.
+        """
+        return self._fill_value
+
+    def _check_fill_value(self):
+        if not is_scalar(self._fill_value):
+            raise ValueError(
+                f"fill_value must be a scalar. Got {self._fill_value} instead"
+            )
+        # TODO: Right now we can use Sparse boolean array
+        #       with any fill_value. Here was an attempt
+        #       to allow only 3 value: True, False or nan
+        #       but plenty test has failed.
+        # see pull 44955
+        # if self._is_boolean and not (
+        #    is_bool(self._fill_value) or isna(self._fill_value)
+        # ):
+        #    raise ValueError(
+        #        "fill_value must be True, False or nan "
+        #        f"for boolean type. Got {self._fill_value} instead"
+        #    )
+
+    @property
+    def _is_na_fill_value(self) -> bool:
+        return isna(self.fill_value)
+
+    @property
+    def _is_numeric(self) -> bool:
+        return not is_object_dtype(self.subtype)
+
+    @property
+    def _is_boolean(self) -> bool:
+        return is_bool_dtype(self.subtype)
+
+    @property
+    def kind(self):
+        """
+        The sparse kind. Either 'integer', or 'block'.
+        """
+        return self.subtype.kind
+
+    @property
+    def type(self):
+        return self.subtype.type
+
+    @property
+    def subtype(self):
+        return self._dtype
+
+    @property
+    def name(self):
+        return f"Sparse[{self.subtype.name}, {repr(self.fill_value)}]"
+
+    def __repr__(self) -> str:
+        return self.name
+
+    @classmethod
+    def construct_array_type(cls) -> type_t[SparseArray]:
+        """
+        Return the array type associated with this dtype.
+
+        Returns
+        -------
+        type
+        """
+        from pandas.core.arrays.sparse.array import SparseArray
+
+        return SparseArray
+
+    @classmethod
+    def construct_from_string(cls, string: str) -> SparseDtype:
+        """
+        Construct a SparseDtype from a string form.
+
+        Parameters
+        ----------
+        string : str
+            Can take the following forms.
+
+            string           dtype
+            ================ ============================
+            'int'            SparseDtype[np.int64, 0]
+            'Sparse'         SparseDtype[np.float64, nan]
+            'Sparse[int]'    SparseDtype[np.int64, 0]
+            'Sparse[int, 0]' SparseDtype[np.int64, 0]
+            ================ ============================
+
+            It is not possible to specify non-default fill values
+            with a string. An argument like ``'Sparse[int, 1]'``
+            will raise a ``TypeError`` because the default fill value
+            for integers is 0.
+
+        Returns
+        -------
+        SparseDtype
+        """
+        if not isinstance(string, str):
+            raise TypeError(
+                f"'construct_from_string' expects a string, got {type(string)}"
+            )
+        msg = f"Cannot construct a 'SparseDtype' from '{string}'"
+        if string.startswith("Sparse"):
+            try:
+                sub_type, has_fill_value = cls._parse_subtype(string)
+            except ValueError as err:
+                raise TypeError(msg) from err
+            else:
+                result = SparseDtype(sub_type)
+                msg = (
+                    f"Cannot construct a 'SparseDtype' from '{string}'.\n\nIt "
+                    "looks like the fill_value in the string is not "
+                    "the default for the dtype. Non-default fill_values "
+                    "are not supported. Use the 'SparseDtype()' "
+                    "constructor instead."
+                )
+                if has_fill_value and str(result) != string:
+                    raise TypeError(msg)
+                return result
+        else:
+            raise TypeError(msg)
+
+    @staticmethod
+    def _parse_subtype(dtype: str) -> tuple[str, bool]:
+        """
+        Parse a string to get the subtype
+
+        Parameters
+        ----------
+        dtype : str
+            A string like
+
+            * Sparse[subtype]
+            * Sparse[subtype, fill_value]
+
+        Returns
+        -------
+        subtype : str
+
+        Raises
+        ------
+        ValueError
+            When the subtype cannot be extracted.
+        """
+        xpr = re.compile(r"Sparse\[(?P<subtype>[^,]*)(, )?(?P<fill_value>.*?)?\]$")
+        m = xpr.match(dtype)
+        has_fill_value = False
+        if m:
+            subtype = m.groupdict()["subtype"]
+            has_fill_value = bool(m.groupdict()["fill_value"])
+        elif dtype == "Sparse":
+            subtype = "float64"
+        else:
+            raise ValueError(f"Cannot parse {dtype}")
+        return subtype, has_fill_value
+
+    @classmethod
+    def is_dtype(cls, dtype: object) -> bool:
+        dtype = getattr(dtype, "dtype", dtype)
+        if isinstance(dtype, str) and dtype.startswith("Sparse"):
+            sub_type, _ = cls._parse_subtype(dtype)
+            dtype = np.dtype(sub_type)
+        elif isinstance(dtype, cls):
+            return True
+        return isinstance(dtype, np.dtype) or dtype == "Sparse"
+
+    def update_dtype(self, dtype) -> SparseDtype:
+        """
+        Convert the SparseDtype to a new dtype.
+
+        This takes care of converting the ``fill_value``.
+
+        Parameters
+        ----------
+        dtype : Union[str, numpy.dtype, SparseDtype]
+            The new dtype to use.
+
+            * For a SparseDtype, it is simply returned
+            * For a NumPy dtype (or str), the current fill value
+              is converted to the new dtype, and a SparseDtype
+              with `dtype` and the new fill value is returned.
+
+        Returns
+        -------
+        SparseDtype
+            A new SparseDtype with the correct `dtype` and fill value
+            for that `dtype`.
+
+        Raises
+        ------
+        ValueError
+            When the current fill value cannot be converted to the
+            new `dtype` (e.g. trying to convert ``np.nan`` to an
+            integer dtype).
+
+
+        Examples
+        --------
+        >>> SparseDtype(int, 0).update_dtype(float)
+        Sparse[float64, 0.0]
+
+        >>> SparseDtype(int, 1).update_dtype(SparseDtype(float, np.nan))
+        Sparse[float64, nan]
+        """
+        cls = type(self)
+        dtype = pandas_dtype(dtype)
+
+        if not isinstance(dtype, cls):
+            if not isinstance(dtype, np.dtype):
+                raise TypeError("sparse arrays of extension dtypes not supported")
+
+            fill_value = astype_nansafe(np.array(self.fill_value), dtype).item()
+            dtype = cls(dtype, fill_value=fill_value)
+
+        return dtype
+
+    @property
+    def _subtype_with_str(self):
+        """
+        Whether the SparseDtype's subtype should be considered ``str``.
+
+        Typically, pandas will store string data in an object-dtype array.
+        When converting values to a dtype, e.g. in ``.astype``, we need to
+        be more specific, we need the actual underlying type.
+
+        Returns
+        -------
+        >>> SparseDtype(int, 1)._subtype_with_str
+        dtype('int64')
+
+        >>> SparseDtype(object, 1)._subtype_with_str
+        dtype('O')
+
+        >>> dtype = SparseDtype(str, '')
+        >>> dtype.subtype
+        dtype('O')
+
+        >>> dtype._subtype_with_str
+        <class 'str'>
+        """
+        if isinstance(self.fill_value, str):
+            return type(self.fill_value)
+        return self.subtype
+
+    def _get_common_dtype(self, dtypes: list[DtypeObj]) -> DtypeObj | None:
+        # TODO for now only handle SparseDtypes and numpy dtypes => extend
+        # with other compatible extension dtypes
+        if any(
+            isinstance(x, ExtensionDtype) and not isinstance(x, SparseDtype)
+            for x in dtypes
+        ):
+            return None
+
+        fill_values = [x.fill_value for x in dtypes if isinstance(x, SparseDtype)]
+        fill_value = fill_values[0]
+
+        # np.nan isn't a singleton, so we may end up with multiple
+        # NaNs here, so we ignore the all NA case too.
+        if not (len(set(fill_values)) == 1 or isna(fill_values).all()):
+            warnings.warn(
+                "Concatenating sparse arrays with multiple fill "
+                f"values: '{fill_values}'. Picking the first and "
+                "converting the rest.",
+                PerformanceWarning,
+                stacklevel=find_stack_level(),
+            )
+
+        np_dtypes = [x.subtype if isinstance(x, SparseDtype) else x for x in dtypes]
+        return SparseDtype(np.find_common_type(np_dtypes, []), fill_value=fill_value)

dist/client/pandas/core/arrays/sparse/scipy_sparse.py

@@ -0,0 +1,211 @@
+"""
+Interaction with scipy.sparse matrices.
+
+Currently only includes to_coo helpers.
+"""
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Iterable,
+)
+
+import numpy as np
+
+from pandas._libs import lib
+from pandas._typing import (
+    IndexLabel,
+    npt,
+)
+
+from pandas.core.dtypes.missing import notna
+
+from pandas.core.algorithms import factorize
+from pandas.core.indexes.api import MultiIndex
+from pandas.core.series import Series
+
+if TYPE_CHECKING:
+    import scipy.sparse
+
+
+def _check_is_partition(parts: Iterable, whole: Iterable):
+    whole = set(whole)
+    parts = [set(x) for x in parts]
+    if set.intersection(*parts) != set():
+        raise ValueError("Is not a partition because intersection is not null.")
+    if set.union(*parts) != whole:
+        raise ValueError("Is not a partition because union is not the whole.")
+
+
+def _levels_to_axis(
+    ss,
+    levels: tuple[int] | list[int],
+    valid_ilocs: npt.NDArray[np.intp],
+    sort_labels: bool = False,
+) -> tuple[npt.NDArray[np.intp], list[IndexLabel]]:
+    """
+    For a MultiIndexed sparse Series `ss`, return `ax_coords` and `ax_labels`,
+    where `ax_coords` are the coordinates along one of the two axes of the
+    destination sparse matrix, and `ax_labels` are the labels from `ss`' Index
+    which correspond to these coordinates.
+
+    Parameters
+    ----------
+    ss : Series
+    levels : tuple/list
+    valid_ilocs : numpy.ndarray
+        Array of integer positions of valid values for the sparse matrix in ss.
+    sort_labels : bool, default False
+        Sort the axis labels before forming the sparse matrix. When `levels`
+        refers to a single level, set to True for a faster execution.
+
+    Returns
+    -------
+    ax_coords : numpy.ndarray (axis coordinates)
+    ax_labels : list (axis labels)
+    """
+    # Since the labels are sorted in `Index.levels`, when we wish to sort and
+    # there is only one level of the MultiIndex for this axis, the desired
+    # output can be obtained in the following simpler, more efficient way.
+    if sort_labels and len(levels) == 1:
+        ax_coords = ss.index.codes[levels[0]][valid_ilocs]
+        ax_labels = ss.index.levels[levels[0]]
+
+    else:
+        levels_values = lib.fast_zip(
+            [ss.index.get_level_values(lvl).values for lvl in levels]
+        )
+        codes, ax_labels = factorize(levels_values, sort=sort_labels)
+        ax_coords = codes[valid_ilocs]
+
+    ax_labels = ax_labels.tolist()
+    return ax_coords, ax_labels
+
+
+def _to_ijv(
+    ss,
+    row_levels: tuple[int] | list[int] = (0,),
+    column_levels: tuple[int] | list[int] = (1,),
+    sort_labels: bool = False,
+) -> tuple[
+    np.ndarray,
+    npt.NDArray[np.intp],
+    npt.NDArray[np.intp],
+    list[IndexLabel],
+    list[IndexLabel],
+]:
+    """
+    For an arbitrary MultiIndexed sparse Series return (v, i, j, ilabels,
+    jlabels) where (v, (i, j)) is suitable for passing to scipy.sparse.coo
+    constructor, and ilabels and jlabels are the row and column labels
+    respectively.
+
+    Parameters
+    ----------
+    ss : Series
+    row_levels : tuple/list
+    column_levels : tuple/list
+    sort_labels : bool, default False
+        Sort the row and column labels before forming the sparse matrix.
+        When `row_levels` and/or `column_levels` refer to a single level,
+        set to `True` for a faster execution.
+
+    Returns
+    -------
+    values : numpy.ndarray
+        Valid values to populate a sparse matrix, extracted from
+        ss.
+    i_coords : numpy.ndarray (row coordinates of the values)
+    j_coords : numpy.ndarray (column coordinates of the values)
+    i_labels : list (row labels)
+    j_labels : list (column labels)
+    """
+    # index and column levels must be a partition of the index
+    _check_is_partition([row_levels, column_levels], range(ss.index.nlevels))
+    # From the sparse Series, get the integer indices and data for valid sparse
+    # entries.
+    sp_vals = ss.array.sp_values
+    na_mask = notna(sp_vals)
+    values = sp_vals[na_mask]
+    valid_ilocs = ss.array.sp_index.indices[na_mask]
+
+    i_coords, i_labels = _levels_to_axis(
+        ss, row_levels, valid_ilocs, sort_labels=sort_labels
+    )
+
+    j_coords, j_labels = _levels_to_axis(
+        ss, column_levels, valid_ilocs, sort_labels=sort_labels
+    )
+
+    return values, i_coords, j_coords, i_labels, j_labels
+
+
+def sparse_series_to_coo(
+    ss: Series,
+    row_levels: Iterable[int] = (0,),
+    column_levels: Iterable[int] = (1,),
+    sort_labels: bool = False,
+) -> tuple[scipy.sparse.coo_matrix, list[IndexLabel], list[IndexLabel]]:
+    """
+    Convert a sparse Series to a scipy.sparse.coo_matrix using index
+    levels row_levels, column_levels as the row and column
+    labels respectively. Returns the sparse_matrix, row and column labels.
+    """
+    import scipy.sparse
+
+    if ss.index.nlevels < 2:
+        raise ValueError("to_coo requires MultiIndex with nlevels >= 2.")
+    if not ss.index.is_unique:
+        raise ValueError(
+            "Duplicate index entries are not allowed in to_coo transformation."
+        )
+
+    # to keep things simple, only rely on integer indexing (not labels)
+    row_levels = [ss.index._get_level_number(x) for x in row_levels]
+    column_levels = [ss.index._get_level_number(x) for x in column_levels]
+
+    v, i, j, rows, columns = _to_ijv(
+        ss, row_levels=row_levels, column_levels=column_levels, sort_labels=sort_labels
+    )
+    sparse_matrix = scipy.sparse.coo_matrix(
+        (v, (i, j)), shape=(len(rows), len(columns))
+    )
+    return sparse_matrix, rows, columns
+
+
+def coo_to_sparse_series(
+    A: scipy.sparse.coo_matrix, dense_index: bool = False
+) -> Series:
+    """
+    Convert a scipy.sparse.coo_matrix to a SparseSeries.
+
+    Parameters
+    ----------
+    A : scipy.sparse.coo_matrix
+    dense_index : bool, default False
+
+    Returns
+    -------
+    Series
+
+    Raises
+    ------
+    TypeError if A is not a coo_matrix
+    """
+    from pandas import SparseDtype
+
+    try:
+        ser = Series(A.data, MultiIndex.from_arrays((A.row, A.col)))
+    except AttributeError as err:
+        raise TypeError(
+            f"Expected coo_matrix. Got {type(A).__name__} instead."
+        ) from err
+    ser = ser.sort_index()
+    ser = ser.astype(SparseDtype(ser.dtype))
+    if dense_index:
+        # is there a better constructor method to use here?
+        i = range(A.shape[0])
+        j = range(A.shape[1])
+        ind = MultiIndex.from_product([i, j])
+        ser = ser.reindex(ind)
+    return ser