Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
nerval
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Named Entity Recognition
nerval
Commits
fa980bce
Commit
fa980bce
authored
1 year ago
by
Manon Blanco
Browse files
Options
Downloads
Patches
Plain Diff
Do not disable formatting
parent
525c1a9e
No related branches found
Branches containing commit
No related tags found
Tags containing commit
1 merge request
!37
Do not disable formatting
Pipeline
#150433
passed
1 year ago
Stage: test
Changes
2
Pipelines
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
tests/test_compute_matches.py
+194
-36
194 additions, 36 deletions
tests/test_compute_matches.py
tests/test_get_labels_aligned.py
+222
-40
222 additions, 40 deletions
tests/test_get_labels_aligned.py
with
416 additions
and
76 deletions
tests/test_compute_matches.py
+
194
−
36
View file @
fa980bce
...
...
@@ -5,85 +5,243 @@ from nerval import evaluate
THRESHOLD
=
0.30
# fmt: off
fake_tags_aligned_nested_perfect
=
[
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 1
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 2
"
I-PER
"
,
# Labels 3
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 4
"
I-PER
"
,
# Labels 5
"
I-PER
"
,
"
I-PER
"
,
# Labels 6
"
I-PER
"
,
# Labels 7
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 8
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 9
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 10
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 11
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 12
"
I-PER
"
,
# Labels 13
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 14
"
I-PER
"
,
# Labels 15
"
I-PER
"
,
"
I-PER
"
,
# Labels 16
"
I-PER
"
,
# Labels 17
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
# Labels 18
"
I-PER
"
,
# Labels 19
"
I-PER
"
,
"
I-PER
"
,
# Labels 20
"
I-PER
"
,
# Labels 21
"
I-PER
"
,
"
I-PER
"
,
# Labels 22
"
O
"
,
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
# Labels 23
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
# Labels 24
"
O
"
,
# Labels 25
"
O
"
,
]
fake_tags_aligned_nested_false
=
[
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 1
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 2
"
I-PER
"
,
# Labels 3
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 4
"
I-PER
"
,
# Labels 5
"
I-PER
"
,
"
I-PER
"
,
# Labels 6
"
I-PER
"
,
# Labels 7
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 8
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 9
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 10
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 11
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 12
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 13
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 14
"
I-PER
"
,
# Labels 15
"
I-PER
"
,
"
I-PER
"
,
# Labels 16
"
I-PER
"
,
# Labels 17
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 18
"
I-PER
"
,
# Labels 19
"
I-PER
"
,
"
I-PER
"
,
# Labels 20
"
I-PER
"
,
# Labels 21
"
I-PER
"
,
"
I-PER
"
,
# Labels 22
"
O
"
,
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
# Labels 23
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
# Labels 24
"
O
"
,
# Labels 25
"
O
"
,
]
fake_predict_tags_aligned
=
[
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 1
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 2
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 3
"
I-PER
"
,
"
I-PER
"
,
# Labels 4
"
I-PER
"
,
# Labels 5
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 6
"
O
"
,
# Labels 7
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 8
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
B-***
"
,
"
I-***
"
,
"
I-***
"
,
"
I-***
"
,
"
I-***
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 9
"
O
"
,
# Labels 10
"
O
"
,
"
O
"
,
# Labels 11
"
O
"
,
# Labels 12
"
B-***
"
,
"
I-***
"
,
"
I-***
"
,
"
I-***
"
,
"
I-***
"
,
# Labels 13
"
O
"
,
# Labels 14
"
O
"
,
"
O
"
,
# Labels 15
"
O
"
,
# Labels 16
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
# Labels 17
"
O
"
,
# Labels 18
"
O
"
,
"
O
"
,
]
# fmt: on
fake_annot_tags_aligned
=
[
"
B-PER
"
,
...
...
This diff is collapsed.
Click to expand it.
tests/test_get_labels_aligned.py
+
222
−
40
View file @
fa980bce
...
...
@@ -8,92 +8,274 @@ fake_predict_original = "G*rard de *N*erval bo*rn in Paris in 1833 *."
fake_annot_aligned
=
"
Gérard de -N-erval was bo-rn in Paris in 1808 -.
"
fake_predict_aligned
=
"
G*rard de *N*erval ----bo*rn in Paris in 1833 *.
"
# fmt: off
fake_annot_tags_original
=
[
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 1
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 2
"
I-PER
"
,
# Labels 3
"
I-PER
"
,
"
I-PER
"
,
# Labels 4
"
I-PER
"
,
# Labels 5
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 6
"
O
"
,
# Labels 7
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 8
"
O
"
,
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
# Labels 9
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
O
"
,
"
O
"
,
# Labels 10
"
O
"
,
# Labels 11
"
O
"
,
"
O
"
,
# Labels 12
"
O
"
,
# Labels 13
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
# Labels 14
"
O
"
,
# Labels 15
"
O
"
,
"
O
"
,
# Labels 16
"
O
"
,
# Labels 17
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
# Labels 18
"
O
"
,
# Labels 19
"
O
"
,
]
fake_predict_tags_original
=
[
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 1
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 2
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 3
"
I-PER
"
,
"
I-PER
"
,
# Labels 4
"
I-PER
"
,
# Labels 5
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 6
"
O
"
,
# Labels 7
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
***
"
,
"
***
"
,
"
***
"
,
"
***
"
,
"
***
"
,
# Labels 8
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 9
"
O
"
,
"
O
"
,
# Labels 10
"
O
"
,
# Labels 11
"
***
"
,
"
***
"
,
"
***
"
,
"
***
"
,
"
***
"
,
# Labels 12
"
O
"
,
# Labels 13
"
O
"
,
"
O
"
,
# Labels 14
"
O
"
,
# Labels 15
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
# Labels 16
"
O
"
,
# Labels 17
"
O
"
,
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
O
"
,
"
O
"
,
"
O
"
,
]
expected_annot_tags_aligned
=
[
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 1
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 2
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 3
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 4
"
I-PER
"
,
# Labels 5
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 6
"
O
"
,
# Labels 7
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 8
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 9
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
# Labels 10
"
O
"
,
# Labels 11
"
O
"
,
"
O
"
,
# Labels 12
"
O
"
,
# Labels 13
"
B-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
"
I-LOC
"
,
# Labels 14
"
O
"
,
# Labels 15
"
O
"
,
"
O
"
,
# Labels 16
"
O
"
,
# Labels 17
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
# Labels 18
"
O
"
,
# Labels 19
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
]
expected_predict_tags_aligned
=
[
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 1
"
B-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 2
"
I-PER
"
,
# Labels 3
"
I-PER
"
,
"
I-PER
"
,
# Labels 4
"
I-PER
"
,
# Labels 5
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
"
I-PER
"
,
# Labels 6
"
O
"
,
# Labels 7
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 8
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 9
"
O
"
,
# Labels 10
"
O
"
,
"
O
"
,
# Labels 11
"
O
"
,
# Labels 12
"
***
"
,
"
***
"
,
"
***
"
,
"
***
"
,
"
***
"
,
# Labels 13
"
O
"
,
# Labels 14
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 15
"
O
"
,
"
***
"
,
"
***
"
,
"
***
"
,
"
***
"
,
"
***
"
,
# Labels 16
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
# Labels 17
"
O
"
,
"
O
"
,
"
O
"
,
# Labels 18
"
O
"
,
"
B-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
I-DAT
"
,
"
O
"
,
"
O
"
,
"
O
"
,
]
# fmt: on
@pytest.mark.parametrize
(
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment