Skip to content

Fix TokenOverlap crash when references list is empty #1973

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
romainsc wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix TokenOverlap crash when references list is empty #1973

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
2 changes: 2 additions & 0 deletions src/unitxt/metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4408,6 +4408,8 @@ def compute(
self._compute_single_ref(str(reference), str(prediction))
for reference in references
]
if not results:
return {"precision": 0, "recall": 0, "f1": 0}
return {
measure: max(r[i] for r in results)
for i, measure in enumerate(["precision", "recall", "f1"])
Expand Down
11 changes: 11 additions & 0 deletions tests/library/test_metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1190,6 +1190,17 @@ def test_token_overlap(self):
for target, value in global_targets.items():
self.assertAlmostEqual(value, outputs[0]["score"]["global"][target])

def test_token_overlap_empty_references(self):
metric = TokenOverlap()
predictions = ["hello there"]
references = [[]]
outputs = apply_metric(
metric=metric, predictions=predictions, references=references
)
global_targets = {"f1": 0, "precision": 0, "recall": 0}
for target, value in global_targets.items():
self.assertAlmostEqual(value, outputs[0]["score"]["global"][target])

def test_roc_auc(self):
metric = RocAuc()
predictions = [0.2, 0.8, 1.0]
Expand Down