explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-14 18:40:33 +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

3
spacy/scorer.py
View File

@ -371,11 +371,12 @@ class Scorer(object):
self.ner_per_ents[ent_label] = PRFScore() self.ner_per_ents[ent_label] = PRFScore()
# Find all candidate labels, for all and per type # Find all candidate labels, for all and per type
gold_ents = set() gold_ents = set()
cand_ents = set()
if gold_doc.is_nered:
for ent in gold_doc.ents: for ent in gold_doc.ents:
gold_ent = (ent.label_, ent.start, ent.end - 1) gold_ent = (ent.label_, ent.start, ent.end - 1)
gold_ents.add(gold_ent) gold_ents.add(gold_ent)
gold_per_ents[ent.label_].add((ent.label_, ent.start, ent.end - 1)) 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} cand_per_ents = {ent_label: set() for ent_label in ent_labels}
for ent in doc.ents: for ent in doc.ents:
first = align.cand_to_gold[ent.start] first = align.cand_to_gold[ent.start]