explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-10 00:02:19 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #561 from chssch/master

Browse Source 
Working version of rule matcher tutorial
This commit is contained in:
Matthew Honnibal 2016-10-23 02:52:20 +11:00 committed by GitHub
commit 30ebb84e73
1 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
website/docs/tutorials/rule-based-matcher.jade
View File

@ -9,6 +9,18 @@ p.u-text-large spaCy features a rule-matching engine that operates over tokens.
nlp = spacy.load('en', parser=False, entity=False) nlp = spacy.load('en', parser=False, entity=False)
def merge_phrases(matcher, doc, i, matches):
'''
Merge a phrase. We have to be careful here because we'll change the token indices.
To avoid problems, merge all the phrases once we're called on the last match.
'''
if i != len(matches)-1:
return None
# Get Span objects
spans = [(ent_id, label, doc[start : end]) for ent_id, label, start, end in matches]
for ent_id, label, span in spans:
span.merge(label=label, tag='NNP' if label else span.root.tag_)
matcher = Matcher(nlp.vocab) matcher = Matcher(nlp.vocab)
matcher.add_entity( matcher.add_entity(
@ -17,6 +29,7 @@ p.u-text-large spaCy features a rule-matching engine that operates over tokens.
acceptor=None, # Accept or modify the match acceptor=None, # Accept or modify the match
on_match=merge_phrases # Callback to act on the matches on_match=merge_phrases # Callback to act on the matches
) )
matcher.add_pattern( matcher.add_pattern(
"GoogleNow", # Entity ID -- Created if doesn't exist. "GoogleNow", # Entity ID -- Created if doesn't exist.
[ # The pattern is a list of *Token Specifiers*. [ # The pattern is a list of *Token Specifiers*.
@ -32,7 +45,7 @@ p.u-text-large spaCy features a rule-matching engine that operates over tokens.
doc = nlp(u"I prefer Siri to Google Now.") doc = nlp(u"I prefer Siri to Google Now.")
matches = matcher(doc) matches = matcher(doc)
for ent_id, label, start, end in matches: for ent_id, label, start, end in matches:
print(nlp.strings[ent_id], nlp.strings[label], doc[start : end].text) print(nlp.vocab.strings[ent_id], nlp.vocab.strings[label], doc[start : end].text)
entity = matcher.get_entity(ent_id) entity = matcher.get_entity(ent_id)
print(entity) print(entity)