mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 18:06:29 +03:00
b5d999e510
* Add doc.cats to spacy.gold at the paragraph level
Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in
the spacy JSON training format at the paragraph level.
* `spacy.gold.docs_to_json()` writes `docs.cats`
* `GoldCorpus` reads in cats in each `GoldParse`
* Update instances of gold_tuples to handle cats
Update iteration over gold_tuples / gold_parses to handle addition of
cats at the paragraph level.
* Add textcat to train CLI
* Add textcat options to train CLI
* Add textcat labels in `TextCategorizer.begin_training()`
* Add textcat evaluation to `Scorer`:
* For binary exclusive classes with provided label: F1 for label
* For 2+ exclusive classes: F1 macro average
* For multilabel (not exclusive): ROC AUC macro average (currently
relying on sklearn)
* Provide user info on textcat evaluation settings, potential
incompatibilities
* Provide pipeline to Scorer in `Language.evaluate` for textcat config
* Customize train CLI output to include only metrics relevant to current
pipeline
* Add textcat evaluation to evaluate CLI
* Fix handling of unset arguments and config params
Fix handling of unset arguments and model confiug parameters in Scorer
initialization.
* Temporarily add sklearn requirement
* Remove sklearn version number
* Improve Scorer handling of models without textcats
* Fixing Scorer handling of models without textcats
* Update Scorer output for python 2.7
* Modify inf in Scorer for python 2.7
* Auto-format
Also make small adjustments to make auto-formatting with black easier and produce nicer results
* Move error message to Errors
* Update documentation
* Add cats to annotation JSON format [ci skip]
* Fix tpl flag and docs [ci skip]
* Switch to internal roc_auc_score
Switch to internal `roc_auc_score()` adapted from scikit-learn.
* Add AUCROCScore tests and improve errors/warnings
* Add tests for AUCROCScore and roc_auc_score
* Add missing error for only positive/negative values
* Remove unnecessary warnings and errors
* Make reduced roc_auc_score functions private
Because most of the checks and warnings have been stripped for the
internal functions and access is only intended through `ROCAUCScore`,
make the functions for roc_auc_score adapted from scikit-learn private.
* Check that data corresponds with multilabel flag
Check that the training instances correspond with the multilabel flag,
adding the multilabel flag if required.
* Add textcat score to early stopping check
* Add more checks to debug-data for textcat
* Add example training data for textcat
* Add more checks to textcat train CLI
* Check configuration when extending base model
* Fix typos
* Update textcat example data
* Provide licensing details and licenses for data
* Remove two labels with no positive instances from jigsaw-toxic-comment
data.
Co-authored-by: Ines Montani <ines@ines.io>
113 lines
4.2 KiB
Python
113 lines
4.2 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
|
|
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_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"]
|