explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix evaluation of NER in scorer.py

Browse Source
This commit is contained in:
Matthew Honnibal 2015-05-27 03:18:16 +02:00
parent 6016ee83a6
commit 4c6058baa7
1 changed files with 18 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
spacy/scorer.py
View File

@ -1,5 +1,7 @@
from __future__ import division from __future__ import division
from spacy.munge.read_ner import tags_to_entities
class PRFScore(object): class PRFScore(object):
"""A precision / recall / F score""" """A precision / recall / F score"""
@ -56,25 +58,25 @@ class Scorer(object):
@property @property
def ents_p(self): def ents_p(self):
return self.ner.precision return self.ner.precision * 100
@property @property
def ents_r(self): def ents_r(self):
return self.ner.recall return self.ner.recall * 100
@property @property
def ents_f(self): def ents_f(self):
return self.ner.fscore return self.ner.fscore * 100
def score(self, tokens, gold, verbose=False): def score(self, tokens, gold, verbose=False):
assert len(tokens) == len(gold) assert len(tokens) == len(gold)
gold_deps = set() gold_deps = set()
gold_tags = set() gold_tags = set()
gold_tags = set() 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:
if dep.lower() not in ('p', 'punct'): if dep.lower() not in ('p', 'punct'):
gold_deps.add((id_, head, dep)) gold_deps.add((id_, head, dep.lower()))
gold_tags.add((id_, tag)) gold_tags.add((id_, tag))
cand_deps = set() cand_deps = set()
cand_tags = set() cand_tags = set()
@ -88,13 +90,22 @@ class Scorer(object):
self.unlabelled.fp += 1 self.unlabelled.fp += 1
self.labelled.fp += 1 self.labelled.fp += 1
else: else:
cand_deps.add((gold_i, gold_head, token.dep_)) cand_deps.add((gold_i, gold_head, token.dep_.lower()))
if gold_i is None: if gold_i is None:
self.tags.fp += 1 self.tags.fp += 1
else: else:
cand_tags.add((gold_i, token.tag_)) cand_tags.add((gold_i, token.tag_))
cand_ents = set()
for ent in tokens.ents:
first = gold.cand_to_gold[ent.start]
last = gold.cand_to_gold[ent.end-1]
if first is None or last is None:
self.ner.fp += 1
else:
cand_ents.add((ent.label_, first, last))
self.tags.score_set(cand_tags, cand_deps) self.ner.score_set(cand_ents, gold_ents)
self.tags.score_set(cand_tags, gold_tags)
self.labelled.score_set(cand_deps, gold_deps) self.labelled.score_set(cand_deps, gold_deps)
self.unlabelled.score_set( self.unlabelled.score_set(
set(item[:2] for item in cand_deps), set(item[:2] for item in cand_deps),