explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-10 16:40:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Hack scorer to avoid evaluating non-nered data

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-24 18:02:59 +02:00
parent 70bd7fb611
commit 359e874766
1 changed files with 21 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
spacy/scorer.py
View File

@ -371,27 +371,28 @@ class Scorer(object):
self.ner_per_ents[ent_label] = PRFScore()
# Find all candidate labels, for all and per type
gold_ents = set()
for ent in gold_doc.ents:
gold_ent = (ent.label_, ent.start, ent.end - 1)
gold_ents.add(gold_ent)
gold_per_ents[ent.label_].add((ent.label_, ent.start, ent.end - 1))
cand_ents = set()
cand_per_ents = {ent_label: set() for ent_label in ent_labels}
for ent in doc.ents:
first = align.cand_to_gold[ent.start]
last = align.cand_to_gold[ent.end - 1]
if first is None or last is None:
self.ner.fp += 1
self.ner_per_ents[ent.label_].fp += 1
else:
cand_ents.add((ent.label_, first, last))
cand_per_ents[ent.label_].add((ent.label_, first, last))
# Scores per ent
for k, v in self.ner_per_ents.items():
if k in cand_per_ents:
v.score_set(cand_per_ents[k], gold_per_ents[k])
# Score for all ents
self.ner.score_set(cand_ents, gold_ents)
if gold_doc.is_nered:
for ent in gold_doc.ents:
gold_ent = (ent.label_, ent.start, ent.end - 1)
gold_ents.add(gold_ent)
gold_per_ents[ent.label_].add((ent.label_, ent.start, ent.end - 1))
cand_per_ents = {ent_label: set() for ent_label in ent_labels}
for ent in doc.ents:
first = align.cand_to_gold[ent.start]
last = align.cand_to_gold[ent.end - 1]
if first is None or last is None:
self.ner.fp += 1
self.ner_per_ents[ent.label_].fp += 1
else:
cand_ents.add((ent.label_, first, last))
cand_per_ents[ent.label_].add((ent.label_, first, last))
# Scores per ent
for k, v in self.ner_per_ents.items():
if k in cand_per_ents:
v.score_set(cand_per_ents[k], gold_per_ents[k])
# Score for all ents
self.ner.score_set(cand_ents, gold_ents)
self.tags.score_set(cand_tags, gold_tags)
self.pos.score_set(cand_pos, gold_pos)
self.morphs.score_set(cand_morphs, gold_morphs)