explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-06 14:40:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix NewExample class

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-09 15:43:19 +02:00
parent f1189dc205
commit 36d49a0f13
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/gold/new_example.pyx
View File

@ -8,7 +8,7 @@ from .align import Alignment
from ..errors import Errors, AlignmentError from ..errors import Errors, AlignmentError
cpdef Doc annotations2doc(Doc predicted, doc_annot, tok_annot): cpdef Doc annotations2doc(Doc predicted, tok_annot, doc_annot):
# TODO: Improve and test this # TODO: Improve and test this
words = tok_annot.get("ORTH", [tok.text for tok in predicted]) words = tok_annot.get("ORTH", [tok.text for tok in predicted])
attrs, array = _annot2array(predicted.vocab.strings, tok_annot, doc_annot) attrs, array = _annot2array(predicted.vocab.strings, tok_annot, doc_annot)
@ -83,16 +83,19 @@ def _annot2array(strings, tok_annot, doc_annot):
for key, value in tok_annot.items(): for key, value in tok_annot.items():
if key not in IDS: if key not in IDS:
raise ValueError(f"Unknown attr: {key}") raise ValueError(f"Unknown attr: {key}")
if key == "HEAD": elif key == "ORTH":
pass
elif key == "HEAD":
attrs.append(key)
values.append([h-i for i, h in enumerate(value)]) values.append([h-i for i, h in enumerate(value)])
else: else:
attrs.append(key)
values.append([strings.add(v) for v in value]) values.append([strings.add(v) for v in value])
attrs.append(key)
# TODO: Calculate token.ent_kb_id from doc_annot["links"]. # TODO: Calculate token.ent_kb_id from doc_annot["links"].
# We need to fix this and the doc.ents thing, both should be doc # We need to fix this and the doc.ents thing, both should be doc
# annotations. # annotations.
array = numpy.array(values, dtype="uint64") array = numpy.array(values, dtype="uint64")
return attrs, array return attrs, array.T
def _parse_example_dict_data(example_dict): def _parse_example_dict_data(example_dict):