BUG GH23744 ufuncs on DataFrame keeps dtype sparseness

doc/source/whatsnew/v0.24.0.rst

@@ -1275,6 +1275,7 @@ Numeric
 - Bug in :meth:`Series.rpow` with object dtype ``NaN`` for ``1 ** NA`` instead of ``1`` (:issue:`22922`).
 - :meth:`Series.agg` can now handle numpy NaN-aware methods like :func:`numpy.nansum` (:issue:`19629`)
 - Bug in :meth:`Series.rank` and :meth:`DataFrame.rank` when ``pct=True`` and more than 2:sup:`24` rows are present resulted in percentages greater than 1.0 (:issue:`18271`)
+- Bug in :meth:`DataFrame.apply` where dtypes would lose sparseness (:issue:`23744`)
 
 Strings
 ^^^^^^^

pandas/core/apply.py

@@ -7,7 +7,7 @@
 from pandas.util._decorators import cache_readonly
 
 from pandas.core.dtypes.common import (
-    is_dict_like, is_extension_type, is_list_like, is_sequence)
+    is_dict_like, is_extension_type, is_list_like, is_sequence, is_sparse)
 from pandas.core.dtypes.generic import ABCSeries
 
 from pandas.io.formats.printing import pprint_thing
@@ -131,6 +131,17 @@ def get_result(self):
 
         # ufunc
         elif isinstance(self.f, np.ufunc):
+            for dtype in self.obj.dtypes:
+                # Column-by-column construction is slow, so only use
+                # when necessary (e.g. to preserve special dtypes)
+                if is_sparse(dtype):  # GH 23744
+                    result = self.obj._constructor(index=self.index,
+                                                   copy=False)
+                    with np.errstate(all='ignore'):
+                        for col in self.columns:
+                            result[col] = self.f(self.obj[col].values)
+                    return result
+
             with np.errstate(all='ignore'):
                 results = self.f(self.values)
             return self.obj._constructor(data=results, index=self.index,

pandas/tests/sparse/frame/test_apply.py

@@ -91,3 +91,14 @@ def test_applymap(frame):
     # just test that it works
     result = frame.applymap(lambda x: x * 2)
     assert isinstance(result, SparseDataFrame)
+
+
+def test_apply_keep_sparse_dtype():
+    # GH 23744
+    df = SparseDataFrame(np.array([[0, 1, 0], [0, 0, 0], [0, 0, 1]]),
+                         columns=['a', 'b', 'c'], default_fill_value=1)
+    df2 = DataFrame(df)
+
+    df = df.apply(np.exp)
+    df2 = df2.apply(np.exp)
+    tm.assert_frame_equal(df, df2)