mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
37c7c85a86
* Support nowrap setting in util.prints * Tidy up and fix whitespace * Simplify script and use read_jsonl helper * Add JSON schemas (see #2928) * Deprecate Doc.print_tree Will be replaced with Doc.to_json, which will produce a unified format * Add Doc.to_json() method (see #2928) Converts Doc objects to JSON using the same unified format as the training data. Method also supports serializing selected custom attributes in the doc._. space. * Remove outdated test * Add write_json and write_jsonl helpers * WIP: Update spacy train * Tidy up spacy train * WIP: Use wasabi for formatting * Add GoldParse helpers for JSON format * WIP: add debug-data command * Fix typo * Add missing import * Update wasabi pin * Add missing import * 💫 Refactor CLI (#2943) To be merged into #2932. ## Description - [x] refactor CLI To use [`wasabi`](https://github.com/ines/wasabi) - [x] use [`black`](https://github.com/ambv/black) for auto-formatting - [x] add `flake8` config - [x] move all messy UD-related scripts to `cli.ud` - [x] make converters function that take the opened file and return the converted data (instead of having them handle the IO) ### Types of change enhancement ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information. * Update wasabi pin * Delete old test * Update errors * Fix typo * Tidy up and format remaining code * Fix formatting * Improve formatting of messages * Auto-format remaining code * Add tok2vec stuff to spacy.train * Fix typo * Update wasabi pin * Fix path checks for when train() is called as function * Reformat and tidy up pretrain script * Update argument annotations * Raise error if model language doesn't match lang * Document new train command
53 lines
2.1 KiB
Python
53 lines
2.1 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from spacy.gold import biluo_tags_from_offsets, offsets_from_biluo_tags
|
|
from spacy.tokens import Doc
|
|
|
|
|
|
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_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
|