Remove SparseSeries and SparseDataFrame

doc/source/reference/frame.rst

@@ -361,10 +361,3 @@ Serialization / IO / conversion
    DataFrame.to_string
    DataFrame.to_clipboard
    DataFrame.style
-
-Sparse
-~~~~~~
-.. autosummary::
-   :toctree: api/
-
-   SparseDataFrame.to_coo

doc/source/reference/series.rst

@@ -581,13 +581,3 @@ Serialization / IO / conversion
    Series.to_string
    Series.to_clipboard
    Series.to_latex
-
-
-Sparse
-------
-
-.. autosummary::
-   :toctree: api/
-
-   SparseSeries.to_coo
-   SparseSeries.from_coo

doc/source/user_guide/sparse.rst

@@ -6,12 +6,6 @@
 Sparse data structures
 **********************
 
-.. note::
-
-   ``SparseSeries`` and ``SparseDataFrame`` have been deprecated. Their purpose
-   is served equally well by a :class:`Series` or :class:`DataFrame` with
-   sparse values. See :ref:`sparse.migration` for tips on migrating.
-
 Pandas provides data structures for efficiently storing sparse data.
 These are not necessarily sparse in the typical "mostly 0". Rather, you can view these
 objects as being "compressed" where any data matching a specific value (``NaN`` / missing value, though any value
@@ -168,6 +162,11 @@ the correct dense result.
 Migrating
 ---------
 
+.. note::
+
+   ``SparseSeries`` and ``SparseDataFrame`` were removed in pandas 1.0.0. This migration
+   guide is present to aid in migrating from previous versions.
+
 In older versions of pandas, the ``SparseSeries`` and ``SparseDataFrame`` classes (documented below)
 were the preferred way to work with sparse data. With the advent of extension arrays, these subclasses
 are no longer needed. Their purpose is better served by using a regular Series or DataFrame with
@@ -366,12 +365,3 @@ row and columns coordinates of the matrix. Note that this will consume a signifi
 
    ss_dense = pd.Series.sparse.from_coo(A, dense_index=True)
    ss_dense
-
-
-.. _sparse.subclasses:
-
-Sparse subclasses
------------------
-
-The :class:`SparseSeries` and :class:`SparseDataFrame` classes are deprecated. Visit their
-API pages for usage.

doc/source/whatsnew/v1.0.0.rst

@@ -78,6 +78,8 @@ Deprecations
 
 Removal of prior version deprecations/changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+- Removed ``SparseSeries`` and ``SparseDataFrame`` (:issue:``)
 - Removed the previously deprecated :meth:`Series.get_value`, :meth:`Series.set_value`, :meth:`DataFrame.get_value`, :meth:`DataFrame.set_value` (:issue:`17739`)
 - Changed the the default value of `inplace` in :meth:`DataFrame.set_index` and :meth:`Series.set_axis`. It now defaults to False (:issue:`27600`)
 - :meth:`pandas.Series.str.cat` now defaults to aligning ``others``, using ``join='left'`` (:issue:`27611`)

pandas/__init__.py

@@ -116,8 +116,6 @@
 
 from pandas.core.sparse.api import (
     SparseArray,
-    SparseDataFrame,
-    SparseSeries,
     SparseDtype,
 )
 

pandas/_typing.py

@@ -12,13 +12,10 @@
     from pandas.core.dtypes.dtypes import ExtensionDtype  # noqa: F401
     from pandas.core.indexes.base import Index  # noqa: F401
     from pandas.core.series import Series  # noqa: F401
-    from pandas.core.sparse.series import SparseSeries  # noqa: F401
     from pandas.core.generic import NDFrame  # noqa: F401
 
 
-AnyArrayLike = TypeVar(
-    "AnyArrayLike", "ExtensionArray", "Index", "Series", "SparseSeries", np.ndarray
-)
+AnyArrayLike = TypeVar("AnyArrayLike", "ExtensionArray", "Index", "Series", np.ndarray)
 ArrayLike = TypeVar("ArrayLike", "ExtensionArray", np.ndarray)
 DatetimeLikeScalar = TypeVar("DatetimeLikeScalar", "Period", "Timestamp", "Timedelta")
 Dtype = Union[str, np.dtype, "ExtensionDtype"]

pandas/core/arrays/sparse.py

@@ -43,7 +43,6 @@
     ABCIndexClass,
     ABCSeries,
     ABCSparseArray,
-    ABCSparseSeries,
 )
 from pandas.core.dtypes.missing import isna, na_value_for_dtype, notna
 
@@ -607,7 +606,7 @@ def __init__(
         if fill_value is None and isinstance(dtype, SparseDtype):
             fill_value = dtype.fill_value
 
-        if isinstance(data, (type(self), ABCSparseSeries)):
+        if isinstance(data, type(self)):
             # disable normal inference on dtype, sparse_index, & fill_value
             if sparse_index is None:
                 sparse_index = data.sp_index
@@ -1969,7 +1968,7 @@ def _delegate_method(self, name, *args, **kwargs):
     @classmethod
     def from_coo(cls, A, dense_index=False):
         """
-        Create a SparseSeries from a scipy.sparse.coo_matrix.
+        Create a Series with sparse values from a scipy.sparse.coo_matrix.
 
         Parameters
         ----------
@@ -1982,7 +1981,8 @@ def from_coo(cls, A, dense_index=False):
 
         Returns
         -------
-        s : SparseSeries
+        s : Series
+            A Series with sparse values.
 
         Examples
         --------
@@ -1996,7 +1996,7 @@ def from_coo(cls, A, dense_index=False):
         matrix([[ 0.,  0.,  1.,  2.],
                 [ 3.,  0.,  0.,  0.],
                 [ 0.,  0.,  0.,  0.]])
-        >>> ss = pd.SparseSeries.from_coo(A)
+        >>> ss = pd.Series.sparse.from_coo(A)
         >>> ss
         0  2    1
            3    2
@@ -2009,14 +2009,14 @@ def from_coo(cls, A, dense_index=False):
         from pandas.core.sparse.scipy_sparse import _coo_to_sparse_series
         from pandas import Series
 
-        result = _coo_to_sparse_series(A, dense_index=dense_index, sparse_series=False)
+        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 SparseSeries with MultiIndex.
+        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
@@ -2046,10 +2046,10 @@ def to_coo(self, row_levels=(0,), column_levels=(1,), sort_labels=False):
                                                 (2, 1, 'b', 0),
                                                 (2, 1, 'b', 1)],
                                                 names=['A', 'B', 'C', 'D'])
-        >>> ss = s.to_sparse()
-        >>> A, rows, columns = ss.to_coo(row_levels=['A', 'B'],
-                                         column_levels=['C', 'D'],
-                                         sort_labels=True)
+        >>> ss = s.astype("Sparse")
+        >>> 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>

pandas/core/dtypes/common.py

@@ -273,8 +273,6 @@ def is_sparse(arr):
 
     See Also
     --------
-    DataFrame.to_sparse : Convert DataFrame to a SparseDataFrame.
-    Series.to_sparse : Convert Series to SparseSeries.
     Series.to_dense : Return dense representation of a Series.
 
     Examples
@@ -283,7 +281,7 @@ def is_sparse(arr):
 
     >>> is_sparse(pd.SparseArray([0, 0, 1, 0]))
     True
-    >>> is_sparse(pd.SparseSeries([0, 0, 1, 0]))
+    >>> is_sparse(pd.Series(pd.SparseArray([0, 0, 1, 0])))
     True
 
     Returns `False` if the parameter is not sparse.
@@ -300,14 +298,6 @@ def is_sparse(arr):
     False
 
     Returns `False` if the parameter has more than one dimension.
-
-    >>> df = pd.SparseDataFrame([389., 24., 80.5, np.nan],
-                                columns=['max_speed'],
-                                index=['falcon', 'parrot', 'lion', 'monkey'])
-    >>> is_sparse(df)
-    False
-    >>> is_sparse(df.max_speed)
-    True
     """
     from pandas.core.arrays.sparse import SparseDtype
 
@@ -340,8 +330,6 @@ def is_scipy_sparse(arr):
     True
     >>> is_scipy_sparse(pd.SparseArray([1, 2, 3]))
     False
-    >>> is_scipy_sparse(pd.SparseSeries([1, 2, 3]))
-    False
     """
 
     global _is_scipy_sparse
@@ -1715,9 +1703,6 @@ def is_extension_type(arr):
     True
     >>> is_extension_type(pd.SparseArray([1, 2, 3]))
     True
-    >>> is_extension_type(pd.SparseSeries([1, 2, 3]))
-    True
-    >>>
     >>> from scipy.sparse import bsr_matrix
     >>> is_extension_type(bsr_matrix([1, 2, 3]))
     False

pandas/core/dtypes/generic.py

@@ -52,12 +52,7 @@ def _check(cls, inst):
 
 ABCSeries = create_pandas_abc_type("ABCSeries", "_typ", ("series",))
 ABCDataFrame = create_pandas_abc_type("ABCDataFrame", "_typ", ("dataframe",))
-ABCSparseDataFrame = create_pandas_abc_type(
-    "ABCSparseDataFrame", "_subtyp", ("sparse_frame",)
-)
-ABCSparseSeries = create_pandas_abc_type(
-    "ABCSparseSeries", "_subtyp", ("sparse_series", "sparse_time_series")
-)
+
 ABCSparseArray = create_pandas_abc_type(
     "ABCSparseArray", "_subtyp", ("sparse_array", "sparse_series")
 )

pandas/core/frame.py

@@ -1925,81 +1925,6 @@ def _from_arrays(cls, arrays, columns, index, dtype=None):
         mgr = arrays_to_mgr(arrays, columns, index, columns, dtype=dtype)
         return cls(mgr)
 
-    def to_sparse(self, fill_value=None, kind="block"):
-        """
-        Convert to SparseDataFrame.
-
-        .. deprecated:: 0.25.0
-
-        Implement the sparse version of the DataFrame meaning that any data
-        matching a specific value it's omitted in the representation.
-        The sparse DataFrame allows for a more efficient storage.
-
-        Parameters
-        ----------
-        fill_value : float, default None
-            The specific value that should be omitted in the representation.
-        kind : {'block', 'integer'}, default 'block'
-            The kind of the SparseIndex tracking where data is not equal to
-            the fill value:
-
-            - 'block' tracks only the locations and sizes of blocks of data.
-            - 'integer' keeps an array with all the locations of the data.
-
-            In most cases 'block' is recommended, since it's more memory
-            efficient.
-
-        Returns
-        -------
-        SparseDataFrame
-            The sparse representation of the DataFrame.
-
-        See Also
-        --------
-        DataFrame.to_dense :
-            Converts the DataFrame back to the its dense form.
-
-        Examples
-        --------
-        >>> df = pd.DataFrame([(np.nan, np.nan),
-        ...                    (1., np.nan),
-        ...                    (np.nan, 1.)])
-        >>> df
-             0    1
-        0  NaN  NaN
-        1  1.0  NaN
-        2  NaN  1.0
-        >>> type(df)
-        <class 'pandas.core.frame.DataFrame'>
-
-        >>> sdf = df.to_sparse()  # doctest: +SKIP
-        >>> sdf  # doctest: +SKIP
-             0    1
-        0  NaN  NaN
-        1  1.0  NaN
-        2  NaN  1.0
-        >>> type(sdf)  # doctest: +SKIP
-        <class 'pandas.core.sparse.frame.SparseDataFrame'>
-        """
-        warnings.warn(
-            "DataFrame.to_sparse is deprecated and will be removed "
-            "in a future version",
-            FutureWarning,
-            stacklevel=2,
-        )
-
-        from pandas.core.sparse.api import SparseDataFrame
-
-        with warnings.catch_warnings():
-            warnings.filterwarnings("ignore", message="SparseDataFrame")
-            return SparseDataFrame(
-                self._series,
-                index=self.index,
-                columns=self.columns,
-                default_kind=kind,
-                default_fill_value=fill_value,
-            )
-
     @deprecate_kwarg(old_arg_name="encoding", new_arg_name=None)
     def to_stata(
         self,
@@ -7192,7 +7117,6 @@ def join(self, other, on=None, how="left", lsuffix="", rsuffix="", sort=False):
         4  K4  A4  NaN
         5  K5  A5  NaN
         """
-        # For SparseDataFrame's benefit
         return self._join_compat(
             other, on=on, how=how, lsuffix=lsuffix, rsuffix=rsuffix, sort=sort
         )

pandas/core/generic.py

@@ -5575,9 +5575,6 @@ def get_ftype_counts(self):
 
         .. deprecated:: 0.23.0
 
-        This is useful for SparseDataFrame or for DataFrames containing
-        sparse arrays.
-
         Returns
         -------
         dtype : Series
@@ -5672,7 +5669,6 @@ def ftypes(self):
         See Also
         --------
         DataFrame.dtypes: Series with just dtype information.
-        SparseDataFrame : Container for sparse tabular data.
 
         Notes
         -----
@@ -5688,13 +5684,6 @@ def ftypes(self):
         2    float64:dense
         3    float64:dense
         dtype: object
-
-        >>> pd.SparseDataFrame(arr).ftypes  # doctest: +SKIP
-        0    float64:sparse
-        1    float64:sparse
-        2    float64:sparse
-        3    float64:sparse
-        dtype: object
         """
         warnings.warn(
             "DataFrame.ftypes is deprecated and will "

pandas/core/groupby/generic.py

@@ -58,7 +58,6 @@
 import pandas.core.indexes.base as ibase
 from pandas.core.internals import BlockManager, make_block
 from pandas.core.series import Series
-from pandas.core.sparse.frame import SparseDataFrame
 
 from pandas.plotting import boxplot_frame_groupby
 
@@ -258,12 +257,6 @@ def aggregate(self, func, *args, **kwargs):
                         result.columns.levels[0], name=self._selected_obj.columns.name
                     )
 
-                    if isinstance(self.obj, SparseDataFrame):
-                        # Backwards compat for groupby.agg() with sparse
-                        # values. concat no longer converts DataFrame[Sparse]
-                        # to SparseDataFrame, so we do it here.
-                        result = SparseDataFrame(result._data)
-
         if not self.as_index:
             self._insert_inaxis_grouper_inplace(result)
             result.index = np.arange(len(result))

pandas/core/ops/__init__.py

@@ -32,7 +32,6 @@
     ABCExtensionArray,
     ABCIndexClass,
     ABCSeries,
-    ABCSparseSeries,
     ABCTimedeltaArray,
     ABCTimedeltaIndex,
 )
@@ -1151,8 +1150,6 @@ def wrapper(self, other):
         if isinstance(other, ABCDataFrame):
             return NotImplemented
         elif isinstance(other, ABCSeries):
-            if not isinstance(other, ABCSparseSeries):
-                other = other.to_sparse(fill_value=self.fill_value)
             return _sparse_series_op(self, other, op, op_name)
         elif is_scalar(other):
             with np.errstate(all="ignore"):