explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-25 19:33:42 +03:00
Code Issues Packages Projects Releases Wiki Activity

Allow setting ents in get_doc

Browse Source
This commit is contained in:
Ines Montani 2017-01-12 12:25:10 +01:00
parent c5914c6fe5
commit c2406e92bc
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/tests/util.py
View File

@ -5,7 +5,7 @@ from ..tokens import Doc
from ..attrs import ORTH, POS, HEAD, DEP from ..attrs import ORTH, POS, HEAD, DEP
def get_doc(vocab, words=[], pos=None, heads=None, deps=None, tags=None): def get_doc(vocab, words=[], pos=None, heads=None, deps=None, tags=None, ents=None):
"""Create Doc object from given vocab, words and annotations.""" """Create Doc object from given vocab, words and annotations."""
pos = pos or [''] * len(words) pos = pos or [''] * len(words)
heads = heads or [0] * len(words) heads = heads or [0] * len(words)
@ -18,6 +18,8 @@ def get_doc(vocab, words=[], pos=None, heads=None, deps=None, tags=None):
attrs[i, 1] = head attrs[i, 1] = head
attrs[i, 2] = doc.vocab.strings[dep] attrs[i, 2] = doc.vocab.strings[dep]
doc.from_array([POS, HEAD, DEP], attrs) doc.from_array([POS, HEAD, DEP], attrs)
if ents:
doc.ents = [(ent_id, doc.vocab.strings[label], start, end) for ent_id, label, start, end in ents]
if tags: if tags:
for token in doc: for token in doc:
token.tag_ = tags[token.i] token.tag_ = tags[token.i]