Skip to content

PERF: Faster SparseArray.__getitem__ for boolean SparseArray mask (#23122) #44841

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

PERF: Faster SparseArray.__getitem__ for boolean SparseArray mask (#23122) #44841

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 11 additions & 6 deletions pandas/core/arrays/sparse/array.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,7 @@
)
from pandas.core.dtypes.common import (
is_array_like,
is_bool,
is_bool_dtype,
is_datetime64_any_dtype,
is_datetime64tz_dtype,
Expand Down Expand Up @@ -181,7 +182,6 @@ def _sparse_array_op(
ltype = SparseDtype(subtype, left.fill_value)
rtype = SparseDtype(subtype, right.fill_value)

# TODO(GH-23092): pass copy=False. Need to fix astype_nansafe
left = left.astype(ltype)
right = right.astype(rtype)
dtype = ltype.subtype
Expand Down Expand Up @@ -945,13 +945,18 @@ def __getitem__(
)

else:
# TODO: I think we can avoid densifying when masking a
# boolean SparseArray with another. Need to look at the
# key's fill_value for True / False, and then do an intersection
# on the indices of the sp_values.
if isinstance(key, SparseArray):
if is_bool_dtype(key):
key = key.to_dense()
if is_bool(key.fill_value):
msk = np.full(
shape=len(self),
fill_value=key.fill_value,
dtype=np.bool8,
)
msk[key.sp_index.indices] = not key.fill_value
return self.take(np.arange(len(self), dtype=np.int32)[msk])
else:
key = key.to_dense()
else:
key = np.asarray(key)

Expand Down
10 changes: 10 additions & 0 deletions pandas/tests/arrays/sparse/test_array.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -248,6 +248,16 @@ def test_scalar_with_index_infer_dtype(self, scalar, dtype):
assert arr.dtype == dtype
assert exp.dtype == dtype

# GH 23122
def test_get_item_bool_sparse_array(self):
spar_bool = SparseArray([False, True] * 5, dtype=np.bool8, fill_value=True)
exp = SparseArray([np.nan, 2, np.nan, 5, 6])
tm.assert_sp_array_equal(self.arr[spar_bool], exp)

spar_bool = SparseArray(~spar_bool.to_dense(), dtype=np.bool8, fill_value=False)
exp = SparseArray([np.nan, 1, 3, 4, np.nan])
tm.assert_sp_array_equal(self.arr[spar_bool], exp)

def test_get_item(self):

assert np.isnan(self.arr[1])
Expand Down