Skip to content

Remove predicate pushdown from read_parquet #305

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

Merged
phofl merged 1 commit into from
Sep 21, 2023
Merged

Remove predicate pushdown from read_parquet #305

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
11 changes: 0 additions & 11 deletions dask_expr/io/parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,6 @@
And,
Blockwise,
Expr,
Filter,
Index,
Lengths,
Literal,
Expand Down Expand Up @@ -457,16 +456,6 @@ def _simplify_up(self, parent):
if isinstance(parent, Projection):
return super()._simplify_up(parent)

if isinstance(parent, Filter) and isinstance(
parent.predicate, (LE, GE, LT, GT, EQ, NE, And, Or)
):
# Predicate pushdown
filters = _DNF.extract_pq_filters(self, parent.predicate)
if filters:
kwargs = dict(zip(self._parameters, self.operands))
kwargs["filters"] = filters.combine(kwargs["filters"]).to_list_tuple()
return ReadParquet(**kwargs)

if isinstance(parent, Lengths):
_lengths = self._get_lengths()
if _lengths:
Expand Down
2 changes: 2 additions & 0 deletions dask_expr/io/tests/test_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,6 +85,7 @@ def test_io_fusion(tmpdir, fmt):
assert_eq(df2, df[["a", "b"]] + 1)


@pytest.mark.skip()
def test_predicate_pushdown(tmpdir):
original = lib.DataFrame(
{
Expand Down Expand Up @@ -112,6 +113,7 @@ def test_predicate_pushdown(tmpdir):
assert (y_result == 4).all()


@pytest.mark.skip()
def test_predicate_pushdown_compound(tmpdir):
pdf = lib.DataFrame(
{
Expand Down