BUG: Summing a sparse boolean series raises TypeError

doc/source/whatsnew/v1.1.0.rst

@@ -852,7 +852,7 @@ Sparse
 ^^^^^^
 - Creating a :class:`SparseArray` from timezone-aware dtype will issue a warning before dropping timezone information, instead of doing so silently (:issue:`32501`)
 - Bug in :meth:`arrays.SparseArray.from_spmatrix` wrongly read scipy sparse matrix (:issue:`31991`)
--
+- Bug in :meth:`Series.sum` with ``SparseArray`` raises ``TypeError`` (:issue:`25777`)
 
 ExtensionArray
 ^^^^^^^^^^^^^^

pandas/core/arrays/sparse/array.py

@@ -1220,7 +1220,7 @@ def any(self, axis=0, *args, **kwargs):
 
  return values.any().item()
 
- def sum(self, axis=0, *args, **kwargs):
+ def sum(self, axis=0, min_count=0, *args, **kwargs):
  """
  Sum of non-NA/null values
 
@@ -1230,11 +1230,17 @@ def sum(self, axis=0, *args, **kwargs):
  """
  nv.validate_sum(args, kwargs)
  valid_vals = self._valid_sp_values
+ count = len(valid_vals)
  sp_sum = valid_vals.sum()
  if self._null_fill_value:
+ if count < min_count:
+ return na_value_for_dtype(self.dtype.subtype, compat=False)
  return sp_sum
  else:
  nsparse = self.sp_index.ngaps
+ count += nsparse
+ if count < min_count:
+ return na_value_for_dtype(self.dtype.subtype, compat=False)
  return sp_sum + self.fill_value * nsparse
 
  def cumsum(self, axis=0, *args, **kwargs):

pandas/core/dtypes/missing.py

@@ -520,7 +520,9 @@ def na_value_for_dtype(dtype, compat: bool = True):
  return 0
  return np.nan
  elif is_bool_dtype(dtype):
- return False
+ if compat:
+ return False
+ return np.nan
  return np.nan
 
 

pandas/tests/arrays/sparse/test_array.py

@@ -983,6 +983,25 @@ def test_sum(self):
  out = SparseArray(data, fill_value=np.nan).sum()
  assert out == 40.0
 
+ @pytest.mark.parametrize(
+ "arr",
+ [
+ np.array([0, 1, np.nan, 1]),
+ np.array([0, 1, 1]),
+ np.array([True, True, False]),
+ ],
+ )
+ @pytest.mark.parametrize("fill_value", [0, 1, np.nan, True, False])
+ @pytest.mark.parametrize("min_count, expected", [(3, 2), (4, np.nan)])
+ def test_sum_min_count(self, arr, fill_value, min_count, expected):
+ # https://github.com/pandas-dev/pandas/issues/25777
+ sparray = SparseArray(arr, fill_value=fill_value)
+ result = sparray.sum(min_count=min_count)
+ if np.isnan(expected):
+ assert np.isnan(result)
+ else:
+ assert result == expected
+
  def test_numpy_sum(self):
  data = np.arange(10).astype(float)
  out = np.sum(SparseArray(data))