Skip to content

streaming aggregation and progress bar for _run_task_get_arffcontent #1720

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

Open
yashikavishwakarma wants to merge 2 commits into
base: main
Choose a base branch
from
Open

streaming aggregation and progress bar for _run_task_get_arffcontent #1720

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0685e0e
Reduce memory usage in _run_task_get_arffcontent by streaming fold re…
yashikavishwakarma Mar 18, 2026
dcb59d3
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Mar 18, 2026
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
Prev Previous commit
[pre-commit.ci] auto fixes from pre-commit.com hooks 
for more information, see https://pre-commit.ci
  • Loading branch information
@pre-commit-ci
pre-commit-ci[bot] committed Mar 18, 2026
commit dcb59d3ba68b0e1fbf1beead1735ac1b7b2f0510
28 changes: 16 additions & 12 deletions openml/runs/functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -463,7 +463,7 @@ def run_exists(task_id: int, setup_id: int) -> set[int]:
return set()


def _run_task_get_arffcontent( # noqa: PLR0913
def _run_task_get_arffcontent(
*,
model: Any,
task: OpenMLTask,
Expand Down Expand Up @@ -505,6 +505,7 @@ def _run_task_get_arffcontent( # noqa: PLR0913
"""
try:
from tqdm import tqdm

has_tqdm = True
except ImportError:
has_tqdm = False
Expand All @@ -523,11 +524,13 @@ def _run_task_get_arffcontent( # noqa: PLR0913
num_reps, num_folds, num_samples = task.get_split_dimensions()

# Build jobs list
jobs = list(itertools.product(
range(num_reps),
range(num_folds),
range(num_samples),
))
jobs = list(
itertools.product(
range(num_reps),
range(num_folds),
range(num_samples),
)
)
total_jobs = len(jobs)

_config = openml.config.get_config_as_dict()
Expand Down Expand Up @@ -556,7 +559,7 @@ def _run_task_get_arffcontent( # noqa: PLR0913
)

# Aggregate results as each fold completes (streaming)
for (rep_no, fold_no, sample_no), result in zip(jobs, job_generator):
for (rep_no, fold_no, sample_no), result in zip(jobs, job_generator, strict=False):
pred_y, proba_y, test_indices, test_y, inner_trace, user_defined_measures_fold = result

if inner_trace is not None:
Expand All @@ -576,8 +579,8 @@ def _run_task_get_arffcontent( # noqa: PLR0913
)
)
if add_local_measures:
user_defined_measures_fold["predictive_accuracy"] = (
sklearn.metrics.accuracy_score(test_y, pred_y)
user_defined_measures_fold["predictive_accuracy"] = sklearn.metrics.accuracy_score(
test_y, pred_y
)

elif isinstance(task, OpenMLRegressionTask):
Expand Down Expand Up @@ -792,13 +795,14 @@ def _update_evaluation_measures(
if fold_no not in user_defined_measures_per_sample[measure][rep_no]:
user_defined_measures_per_sample[measure][rep_no][fold_no] = OrderedDict()

user_defined_measures_per_fold[measure][rep_no][fold_no] = (
user_defined_measures_fold[measure]
)
user_defined_measures_per_fold[measure][rep_no][fold_no] = user_defined_measures_fold[
measure
]
user_defined_measures_per_sample[measure][rep_no][fold_no][sample_no] = (
user_defined_measures_fold[measure]
)


def _run_task_get_arffcontent_parallel_helper( # noqa: PLR0913
extension: Extension,
fold_no: int,
Expand Down