explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6201 from svlandeg/fix/error_nr

Browse Source
This commit is contained in:
Ines Montani 2020-10-05 14:00:57 +02:00 committed by GitHub
commit 6260fa3c10
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/errors.py
View File

@ -456,10 +456,10 @@ class Errors:
"issue tracker: http://github.com/explosion/spaCy/issues") "issue tracker: http://github.com/explosion/spaCy/issues")
# TODO: fix numbering after merging develop into master # TODO: fix numbering after merging develop into master
E092 = ("The sentence-per-line IOB/IOB2 file is not formatted correctly. " E902 = ("The sentence-per-line IOB/IOB2 file is not formatted correctly. "
"Try checking whitespace and delimiters. See " "Try checking whitespace and delimiters. See "
"https://nightly.spacy.io/api/cli#convert") "https://nightly.spacy.io/api/cli#convert")
E093 = ("The token-per-line NER file is not formatted correctly. Try checking " E903 = ("The token-per-line NER file is not formatted correctly. Try checking "
"whitespace and delimiters. See https://nightly.spacy.io/api/cli#convert") "whitespace and delimiters. See https://nightly.spacy.io/api/cli#convert")
E904 = ("Cannot initialize StaticVectors layer: nO dimension unset. This " E904 = ("Cannot initialize StaticVectors layer: nO dimension unset. This "
"dimension refers to the output width, after the linear projection " "dimension refers to the output width, after the linear projection "

2
spacy/training/converters/conll_ner_to_docs.py
View File

@ -103,7 +103,7 @@ def conll_ner_to_docs(
lines = [line.strip() for line in conll_sent.split("\n") if line.strip()] lines = [line.strip() for line in conll_sent.split("\n") if line.strip()]
cols = list(zip(*[line.split() for line in lines])) cols = list(zip(*[line.split() for line in lines]))
if len(cols) < 2: if len(cols) < 2:
raise ValueError(Errors.E093) raise ValueError(Errors.E903)
length = len(cols[0]) length = len(cols[0])
words.extend(cols[0]) words.extend(cols[0])
sent_starts.extend([True] + [False] * (length - 1)) sent_starts.extend([True] + [False] * (length - 1))

2
spacy/training/converters/iob_to_docs.py
View File

@ -46,7 +46,7 @@ def read_iob(raw_sents, vocab, n_sents):
sent_words, sent_iob = zip(*sent_tokens) sent_words, sent_iob = zip(*sent_tokens)
sent_tags = ["-"] * len(sent_words) sent_tags = ["-"] * len(sent_words)
else: else:
raise ValueError(Errors.E092) raise ValueError(Errors.E902)
words.extend(sent_words) words.extend(sent_words)
tags.extend(sent_tags) tags.extend(sent_tags)
iob.extend(sent_iob) iob.extend(sent_iob)