spaCy/spacy/tests/test_gold.py
adrianeboyd f5c551a43a Checks/errors related to ill-formed IOB input in CLI convert and debug-data (#4487)
* Error for ill-formed input to iob_to_biluo()

Check for empty label in iob_to_biluo(), which can result from
ill-formed input.

* Check for empty NER label in debug-data
2019-10-21 12:20:28 +02:00

123 lines
4.6 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
from spacy.gold import biluo_tags_from_offsets, offsets_from_biluo_tags
from spacy.gold import spans_from_biluo_tags, GoldParse, iob_to_biluo
from spacy.gold import GoldCorpus, docs_to_json
from spacy.lang.en import English
from spacy.tokens import Doc
from .util import make_tempdir
import pytest
import srsly
def test_gold_biluo_U(en_vocab):
words = ["I", "flew", "to", "London", "."]
spaces = [True, True, True, False, True]
doc = Doc(en_vocab, words=words, spaces=spaces)
entities = [(len("I flew to "), len("I flew to London"), "LOC")]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ["O", "O", "O", "U-LOC", "O"]
def test_gold_biluo_BL(en_vocab):
words = ["I", "flew", "to", "San", "Francisco", "."]
spaces = [True, True, True, True, False, True]
doc = Doc(en_vocab, words=words, spaces=spaces)
entities = [(len("I flew to "), len("I flew to San Francisco"), "LOC")]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ["O", "O", "O", "B-LOC", "L-LOC", "O"]
def test_gold_biluo_BIL(en_vocab):
words = ["I", "flew", "to", "San", "Francisco", "Valley", "."]
spaces = [True, True, True, True, True, False, True]
doc = Doc(en_vocab, words=words, spaces=spaces)
entities = [(len("I flew to "), len("I flew to San Francisco Valley"), "LOC")]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ["O", "O", "O", "B-LOC", "I-LOC", "L-LOC", "O"]
def test_gold_biluo_overlap(en_vocab):
words = ["I", "flew", "to", "San", "Francisco", "Valley", "."]
spaces = [True, True, True, True, True, False, True]
doc = Doc(en_vocab, words=words, spaces=spaces)
entities = [
(len("I flew to "), len("I flew to San Francisco Valley"), "LOC"),
(len("I flew to "), len("I flew to San Francisco"), "LOC"),
]
with pytest.raises(ValueError):
biluo_tags_from_offsets(doc, entities)
def test_gold_biluo_misalign(en_vocab):
words = ["I", "flew", "to", "San", "Francisco", "Valley."]
spaces = [True, True, True, True, True, False]
doc = Doc(en_vocab, words=words, spaces=spaces)
entities = [(len("I flew to "), len("I flew to San Francisco Valley"), "LOC")]
tags = biluo_tags_from_offsets(doc, entities)
assert tags == ["O", "O", "O", "-", "-", "-"]
def test_roundtrip_offsets_biluo_conversion(en_tokenizer):
text = "I flew to Silicon Valley via London."
biluo_tags = ["O", "O", "O", "B-LOC", "L-LOC", "O", "U-GPE", "O"]
offsets = [(10, 24, "LOC"), (29, 35, "GPE")]
doc = en_tokenizer(text)
biluo_tags_converted = biluo_tags_from_offsets(doc, offsets)
assert biluo_tags_converted == biluo_tags
offsets_converted = offsets_from_biluo_tags(doc, biluo_tags)
assert offsets_converted == offsets
def test_biluo_spans(en_tokenizer):
doc = en_tokenizer("I flew to Silicon Valley via London.")
biluo_tags = ["O", "O", "O", "B-LOC", "L-LOC", "O", "U-GPE", "O"]
spans = spans_from_biluo_tags(doc, biluo_tags)
assert len(spans) == 2
assert spans[0].text == "Silicon Valley"
assert spans[0].label_ == "LOC"
assert spans[1].text == "London"
assert spans[1].label_ == "GPE"
def test_gold_ner_missing_tags(en_tokenizer):
doc = en_tokenizer("I flew to Silicon Valley via London.")
biluo_tags = [None, "O", "O", "B-LOC", "L-LOC", "O", "U-GPE", "O"]
gold = GoldParse(doc, entities=biluo_tags) # noqa: F841
def test_iob_to_biluo():
good_iob = ["O", "O", "B-LOC", "I-LOC", "O", "B-PERSON"]
good_biluo = ["O", "O", "B-LOC", "L-LOC", "O", "U-PERSON"]
bad_iob = ["O", "O", "\"", "B-LOC", "I-LOC"]
converted_biluo = iob_to_biluo(good_iob)
assert good_biluo == converted_biluo
with pytest.raises(ValueError):
iob_to_biluo(bad_iob)
def test_roundtrip_docs_to_json():
text = "I flew to Silicon Valley via London."
cats = {"TRAVEL": 1.0, "BAKING": 0.0}
nlp = English()
doc = nlp(text)
doc.cats = cats
doc[0].is_sent_start = True
for i in range(1, len(doc)):
doc[i].is_sent_start = False
with make_tempdir() as tmpdir:
json_file = tmpdir / "roundtrip.json"
srsly.write_json(json_file, [docs_to_json(doc)])
goldcorpus = GoldCorpus(str(json_file), str(json_file))
reloaded_doc, goldparse = next(goldcorpus.train_docs(nlp))
assert len(doc) == goldcorpus.count_train()
assert text == reloaded_doc.text
assert "TRAVEL" in goldparse.cats
assert "BAKING" in goldparse.cats
assert cats["TRAVEL"] == goldparse.cats["TRAVEL"]
assert cats["BAKING"] == goldparse.cats["BAKING"]