explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-04 12:20:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

move preset_spans_suggester test to spancat tests

Browse Source
This commit is contained in:
kadarakos 2023-06-02 10:08:16 +00:00
parent 3ec1cb5e30
commit 9372b22d32
2 changed files with 17 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
spacy/tests/pipeline/test_span_finder.py
View File

@ -1,6 +1,5 @@
import pytest import pytest
from thinc.api import Config from thinc.api import Config
from thinc.types import Ragged
from spacy.language import Language from spacy.language import Language
from spacy.lang.en import English from spacy.lang.en import English
@ -193,23 +192,6 @@ def test_set_annotations_span_lengths(min_length, max_length, span_count):
assert all(min_length <= len(span) <= max_length for span in doc.spans[SPANS_KEY]) assert all(min_length <= len(span) <= max_length for span in doc.spans[SPANS_KEY])
def test_span_finder_suggester():
nlp = Language()
docs = [nlp("This is an example."), nlp("This is the second example.")]
docs[0].spans[SPANS_KEY] = [docs[0][3:4]]
docs[1].spans[SPANS_KEY] = [docs[1][0:4], docs[1][3:5]]
suggester = registry.misc.get("spacy.preset_spans_suggester.v1")(
spans_key=SPANS_KEY
)
candidates = suggester(docs)
assert type(candidates) == Ragged
assert len(candidates) == 2
assert list(candidates.dataXd[0]) == [3, 4]
assert list(candidates.dataXd[1]) == [0, 4]
assert list(candidates.dataXd[2]) == [3, 5]
assert list(candidates.lengths) == [1, 2]
def test_overfitting_IO(): def test_overfitting_IO():
# Simple test to try and quickly overfit the span_finder component - ensuring the ML models work correctly # Simple test to try and quickly overfit the span_finder component - ensuring the ML models work correctly
fix_random_seed(0) fix_random_seed(0)

17
spacy/tests/pipeline/test_spancat.py
View File

@ -406,6 +406,23 @@ def test_ngram_sizes(en_tokenizer):
assert_array_equal(OPS.to_numpy(ngrams_3.lengths), [0, 1, 3, 6, 9]) assert_array_equal(OPS.to_numpy(ngrams_3.lengths), [0, 1, 3, 6, 9])
def test_preset_spans_suggester():
nlp = Language()
docs = [nlp("This is an example."), nlp("This is the second example.")]
docs[0].spans[SPAN_KEY] = [docs[0][3:4]]
docs[1].spans[SPAN_KEY] = [docs[1][0:4], docs[1][3:5]]
suggester = registry.misc.get("spacy.preset_spans_suggester.v1")(
spans_key=SPAN_KEY
)
candidates = suggester(docs)
assert type(candidates) == Ragged
assert len(candidates) == 2
assert list(candidates.dataXd[0]) == [3, 4]
assert list(candidates.dataXd[1]) == [0, 4]
assert list(candidates.dataXd[2]) == [3, 5]
assert list(candidates.lengths) == [1, 2]
def test_overfitting_IO(): def test_overfitting_IO():
# Simple test to try and quickly overfit the spancat component - ensuring the ML models work correctly # Simple test to try and quickly overfit the spancat component - ensuring the ML models work correctly
fix_random_seed(0) fix_random_seed(0)