API: stop special-casing SparseArray._quantile (#49583)

* API: stop special-casing SparseArray._quantile

* GH ref

Author: jbrockmendel

doc/source/whatsnew/v2.0.0.rst

@@ -336,6 +336,7 @@ Other API changes
 - Passing ``dtype`` of "timedelta64[s]", "timedelta64[ms]", or "timedelta64[us]" to :class:`TimedeltaIndex`, :class:`Series`, or :class:`DataFrame` constructors will now retain that dtype instead of casting to "timedelta64[ns]"; passing a dtype with lower resolution for :class:`Series` or :class:`DataFrame` will be cast to the lowest supported resolution "timedelta64[s]" (:issue:`49014`)
 - Passing a ``np.datetime64`` object with non-nanosecond resolution to :class:`Timestamp` will retain the input resolution if it is "s", "ms", or "ns"; otherwise it will be cast to the closest supported resolution (:issue:`49008`)
 - The ``other`` argument in :meth:`DataFrame.mask` and :meth:`Series.mask` now defaults to ``no_default`` instead of ``np.nan`` consistent with :meth:`DataFrame.where` and :meth:`Series.where`. Entries will be filled with the corresponding NULL value (``np.nan`` for numpy dtypes, ``pd.NA`` for extension dtypes). (:issue:`49111`)
+- Changed behavior of :meth:`Series.quantile` and :meth:`DataFrame.quantile` with :class:`SparseDtype` to retain sparse dtype (:issue:`49583`)
 - When creating a :class:`Series` with a object-dtype :class:`Index` of datetime objects, pandas no longer silently converts the index to a :class:`DatetimeIndex` (:issue:`39307`, :issue:`23598`)
 - :meth:`Series.unique` with dtype "timedelta64[ns]" or "datetime64[ns]" now returns :class:`TimedeltaArray` or :class:`DatetimeArray` instead of ``numpy.ndarray`` (:issue:`49176`)
 - :func:`to_datetime` and :class:`DatetimeIndex` now allow sequences containing both ``datetime`` objects and numeric entries, matching :class:`Series` behavior (:issue:`49037`)

pandas/core/arrays/sparse/array.py

@@ -86,7 +86,6 @@
     ops,
 )
 import pandas.core.algorithms as algos
-from pandas.core.array_algos.quantile import quantile_with_mask
 from pandas.core.arraylike import OpsMixin
 from pandas.core.arrays import ExtensionArray
 from pandas.core.arrays.sparse.dtype import SparseDtype
@@ -909,29 +908,6 @@ def value_counts(self, dropna: bool = True) -> Series:
             index = keys
         return Series(counts, index=index)
 
-    def _quantile(self, qs: npt.NDArray[np.float64], interpolation: str):
-
-        if self._null_fill_value or self.sp_index.ngaps == 0:
-            # We can avoid densifying
-            npvalues = self.sp_values
-            mask = np.zeros(npvalues.shape, dtype=bool)
-        else:
-            npvalues = self.to_numpy()
-            mask = self.isna()
-
-        fill_value = na_value_for_dtype(npvalues.dtype, compat=False)
-        res_values = quantile_with_mask(
-            npvalues,
-            mask,
-            fill_value,
-            qs,
-            interpolation,
-        )
-
-        # Special case: the returned array isn't _really_ sparse, so we don't
-        #  wrap it in a SparseArray
-        return res_values
-
     # --------
     # Indexing
     # --------

pandas/tests/frame/methods/test_quantile.py

@@ -47,7 +47,7 @@ def test_quantile_sparse(self, df, expected):
         # GH#17198
         # GH#24600
         result = df.quantile()
-
+        expected = expected.astype("Sparse[float]")
         tm.assert_series_equal(result, expected)
 
     def test_quantile(

pandas/tests/series/methods/test_quantile.py

@@ -183,7 +183,7 @@ def test_quantile_nat(self):
     def test_quantile_sparse(self, values, dtype):
         ser = Series(values, dtype=dtype)
         result = ser.quantile([0.5])
-        expected = Series(np.asarray(ser)).quantile([0.5])
+        expected = Series(np.asarray(ser)).quantile([0.5]).astype("Sparse[float]")
         tm.assert_series_equal(result, expected)
 
     def test_quantile_empty(self):