Skip to content
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

[python-package] Add tests for passing Arrow arrays with empty chunks #6210

Merged
merged 6 commits into from
Dec 10, 2023
Merged

[python-package] Add tests for passing Arrow arrays with empty chunks #6210

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
48a48b4
[python-package] Add tests for passing Arrow arrays with empty chunks
borchero Nov 22, 2023
d813de4
isort
borchero Nov 22, 2023
597fa4e
Merge branch 'master' into empty-chunk-tests
jameslamb Dec 1, 2023
e6d97f6
Merge branch 'master' into empty-chunk-tests
jameslamb Dec 4, 2023
cb2f81e
Merge branch 'master' into empty-chunk-tests
jameslamb Dec 7, 2023
906bc78
Merge branch 'master' into empty-chunk-tests
jameslamb Dec 7, 2023
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
2 changes: 2 additions & 0 deletions include/LightGBM/arrow.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,6 +117,7 @@ class ArrowChunkedArray {
const struct ArrowSchema* schema) {
chunks_.reserve(n_chunks);
for (auto k = 0; k < n_chunks; ++k) {
if (chunks[k].length == 0) continue;
chunks_.push_back(&chunks[k]);
}
schema_ = schema;
Expand Down Expand Up @@ -220,6 +221,7 @@ class ArrowTable {
std::vector<const ArrowArray*> children_chunks;
children_chunks.reserve(n_chunks);
for (int64_t k = 0; k < n_chunks; ++k) {
if (chunks[k].length == 0) continue;
children_chunks.push_back(chunks[k].children[j]);
}
columns_.emplace_back(children_chunks, schema->children[j]);
Expand Down
38 changes: 25 additions & 13 deletions tests/python_package_test/test_arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,18 +30,19 @@
]


def generate_simple_arrow_table() -> pa.Table:
def generate_simple_arrow_table(empty_chunks: bool = False) -> pa.Table:
c: list[list[int]] = [[]] if empty_chunks else []
columns = [
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.uint8()),
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.int8()),
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.uint16()),
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.int16()),
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.uint32()),
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.int32()),
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.uint64()),
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.int64()),
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.float32()),
pa.chunked_array([[1, 2, 3, 4, 5]], type=pa.float64()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.uint8()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.int8()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.uint16()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.int16()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.uint32()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.int32()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.uint64()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.int64()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.float32()),
pa.chunked_array(c + [[1, 2, 3]] + c + [[4, 5]] + c, type=pa.float64()),
]
return pa.Table.from_arrays(columns, names=[f"col_{i}" for i in range(len(columns))])

Expand Down Expand Up @@ -104,6 +105,7 @@ def dummy_dataset_params() -> Dict[str, Any]:
("arrow_table_fn", "dataset_params"),
[ # Use lambda functions here to minimize memory consumption
(lambda: generate_simple_arrow_table(), dummy_dataset_params()),
(lambda: generate_simple_arrow_table(empty_chunks=True), dummy_dataset_params()),
(lambda: generate_dummy_arrow_table(), dummy_dataset_params()),
(lambda: generate_nullable_arrow_table(), dummy_dataset_params()),
(lambda: generate_random_arrow_table(3, 1000, 42), {}),
Expand Down Expand Up @@ -160,7 +162,12 @@ def test_dataset_construct_fields_fuzzy():

@pytest.mark.parametrize(
["array_type", "label_data"],
[(pa.array, [0, 1, 0, 0, 1]), (pa.chunked_array, [[0], [1, 0, 0, 1]])],
[
(pa.array, [0, 1, 0, 0, 1]),
(pa.chunked_array, [[0], [1, 0, 0, 1]]),
(pa.chunked_array, [[], [0], [1, 0, 0, 1]]),
(pa.chunked_array, [[0], [], [1, 0], [], [], [0, 1], []]),
],
)
@pytest.mark.parametrize("arrow_type", _INTEGER_TYPES + _FLOAT_TYPES)
def test_dataset_construct_labels(array_type, label_data, arrow_type):
Expand All @@ -187,7 +194,12 @@ def test_dataset_construct_weights_none():

@pytest.mark.parametrize(
["array_type", "weight_data"],
[(pa.array, [3, 0.7, 1.5, 0.5, 0.1]), (pa.chunked_array, [[3], [0.7, 1.5, 0.5, 0.1]])],
[
(pa.array, [3, 0.7, 1.5, 0.5, 0.1]),
(pa.chunked_array, [[3], [0.7, 1.5, 0.5, 0.1]]),
(pa.chunked_array, [[], [3], [0.7, 1.5, 0.5, 0.1]]),
(pa.chunked_array, [[3], [0.7], [], [], [1.5, 0.5, 0.1], []]),
],
)
@pytest.mark.parametrize("arrow_type", _FLOAT_TYPES)
def test_dataset_construct_weights(array_type, weight_data, arrow_type):
Expand Down