Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* Fix POS tag evaluation in scorer.py: do evaluate punctuation tags

This commit is contained in:
Matthew Honnibal 2015-05-30 18:24:32 +02:00
parent 9e39a206da
commit c4f0914b4e
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/scorer.py
View File

@ -75,14 +75,18 @@ class Scorer(object):
gold_tags = set() gold_tags = set()
gold_ents = set(tags_to_entities([annot[-1] for annot in gold.orig_annot])) gold_ents = set(tags_to_entities([annot[-1] for annot in gold.orig_annot]))
for id_, word, tag, head, dep, ner in gold.orig_annot: for id_, word, tag, head, dep, ner in gold.orig_annot:
gold_tags.add((id_, tag))
if dep.lower() not in ('p', 'punct'): if dep.lower() not in ('p', 'punct'):
gold_deps.add((id_, head, dep.lower())) gold_deps.add((id_, head, dep.lower()))
gold_tags.add((id_, tag))
cand_deps = set() cand_deps = set()
cand_tags = set() cand_tags = set()
for token in tokens: for token in tokens:
gold_i = gold.cand_to_gold[token.i]
if gold_i is None:
self.tags.fp += 1
else:
cand_tags.add((gold_i, token.tag_))
if token.dep_ not in ('p', 'punct') and token.orth_.strip(): if token.dep_ not in ('p', 'punct') and token.orth_.strip():
gold_i = gold.cand_to_gold[token.i]
gold_head = gold.cand_to_gold[token.head.i] gold_head = gold.cand_to_gold[token.head.i]
# None is indistinct, so we can't just add it to the set # None is indistinct, so we can't just add it to the set
# Multiple (None, None) deps are possible # Multiple (None, None) deps are possible
@ -91,10 +95,6 @@ class Scorer(object):
self.labelled.fp += 1 self.labelled.fp += 1
else: else:
cand_deps.add((gold_i, gold_head, token.dep_.lower())) cand_deps.add((gold_i, gold_head, token.dep_.lower()))
if gold_i is None:
self.tags.fp += 1
else:
cand_tags.add((gold_i, token.tag_))
if '-' not in [token[-1] for token in gold.orig_annot]: if '-' not in [token[-1] for token in gold.orig_annot]:
cand_ents = set() cand_ents = set()
for ent in tokens.ents: for ent in tokens.ents: