explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-13 10:46:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix get_matching_ents (#10451)

Browse Source 
* Fix get_matching_ents

Not sure what happened here - the code prior to this commit simply does
not work. It's already covered by entity linker tests, which were
succeeding in the NEL PR, but couldn't possibly succeed on master.

* Fix test

Test was indented inside another test and so doesn't seem to have been
running properly.
This commit is contained in:
Paul O'Leary McCann 2022-03-08 00:56:57 +09:00 committed by GitHub
parent 7ed7908716
commit 61ba5450ff
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 56 additions and 56 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/tests/pipeline/test_entity_linker.py
View File

@ -1009,7 +1009,7 @@ def test_legacy_architectures(name, config):
losses = {} losses = {}
nlp.update(train_examples, sgd=optimizer, losses=losses) nlp.update(train_examples, sgd=optimizer, losses=losses)
@pytest.mark.parametrize("patterns", [ @pytest.mark.parametrize("patterns", [
# perfect case # perfect case
[{"label": "CHARACTER", "pattern": "Kirby"}], [{"label": "CHARACTER", "pattern": "Kirby"}],
# typo for false negative # typo for false negative
@ -1017,8 +1017,8 @@ def test_legacy_architectures(name, config):
# random stuff for false positive # random stuff for false positive
[{"label": "IS", "pattern": "is"}, {"label": "COLOR", "pattern": "pink"}], [{"label": "IS", "pattern": "is"}, {"label": "COLOR", "pattern": "pink"}],
] ]
) )
def test_no_gold_ents(patterns): def test_no_gold_ents(patterns):
# test that annotating components work # test that annotating components work
TRAIN_DATA = [ TRAIN_DATA = [
( (

4
spacy/training/example.pyx
View File

@ -263,11 +263,11 @@ cdef class Example:
kept. Otherwise only the character indices need to match. kept. Otherwise only the character indices need to match.
""" """
gold = {} gold = {}
for ent in self.reference: for ent in self.reference.ents:
gold[(ent.start_char, ent.end_char)] = ent.label gold[(ent.start_char, ent.end_char)] = ent.label
keep = [] keep = []
for ent in self.predicted: for ent in self.predicted.ents:
key = (ent.start_char, ent.end_char) key = (ent.start_char, ent.end_char)
if key not in gold: if key not in gold:
continue continue