explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

add spacy prefix to ngram_suggester.v1 (#8623)

Browse Source
This commit is contained in:
Sofie Van Landeghem 2021-07-07 08:09:30 +02:00 committed by GitHub
parent 733e8ceea9
commit 64fac754fe
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/pipeline/spancat.py
View File

@ -44,7 +44,7 @@ depth = 4
DEFAULT_SPANCAT_MODEL = Config().from_str(spancat_default_config)["model"]
@registry.misc("ngram_suggester.v1")
@registry.misc("spacy.ngram_suggester.v1")
def build_ngram_suggester(sizes: List[int]) -> Callable[[List[Doc]], Ragged]:
"""Suggest all spans of the given lengths. Spans are returned as a ragged
array of integers. The array has two columns, indicating the start and end
@ -86,7 +86,7 @@ def build_ngram_suggester(sizes: List[int]) -> Callable[[List[Doc]], Ragged]:
"spans_key": "sc",
"max_positive": None,
"model": DEFAULT_SPANCAT_MODEL,
"suggester": {"@misc": "ngram_suggester.v1", "sizes": [1, 2, 3]},
"suggester": {"@misc": "spacy.ngram_suggester.v1", "sizes": [1, 2, 3]},
},
default_score_weights={"spans_sc_f": 1.0, "spans_sc_p": 0.0, "spans_sc_r": 0.0},
)

8
spacy/tests/pipeline/test_spancat.py
View File

@ -92,7 +92,7 @@ def test_simple_train():
def test_ngram_suggester(en_tokenizer):
# test different n-gram lengths
for size in [1, 2, 3]:
ngram_suggester = registry.misc.get("ngram_suggester.v1")(sizes=[size])
ngram_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[size])
docs = [
en_tokenizer(text)
for text in [
@ -124,7 +124,7 @@ def test_ngram_suggester(en_tokenizer):
assert_equal(ngrams.lengths, [max(0, len(doc) - (size - 1)) for doc in docs])
# test 1-3-gram suggestions
ngram_suggester = registry.misc.get("ngram_suggester.v1")(sizes=[1, 2, 3])
ngram_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[1, 2, 3])
docs = [
en_tokenizer(text) for text in ["a", "a b", "a b c", "a b c d", "a b c d e"]
]
@ -173,13 +173,13 @@ def test_ngram_suggester(en_tokenizer):
)
# test some empty docs
ngram_suggester = registry.misc.get("ngram_suggester.v1")(sizes=[1])
ngram_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[1])
docs = [en_tokenizer(text) for text in ["", "a", ""]]
ngrams = ngram_suggester(docs)
assert_equal(ngrams.lengths, [len(doc) for doc in docs])
# test all empty docs
ngram_suggester = registry.misc.get("ngram_suggester.v1")(sizes=[1])
ngram_suggester = registry.misc.get("spacy.ngram_suggester.v1")(sizes=[1])
docs = [en_tokenizer(text) for text in ["", "", ""]]
ngrams = ngram_suggester(docs)
assert_equal(ngrams.lengths, [len(doc) for doc in docs])

2
website/docs/api/spancategorizer.md
View File

@ -31,7 +31,7 @@ architectures and their arguments and hyperparameters.
> "spans_key": "labeled_spans",
> "max_positive": None,
> "model": DEFAULT_SPANCAT_MODEL,
> "suggester": {"@misc": "ngram_suggester.v1", "sizes": [1, 2, 3]},
> "suggester": {"@misc": "spacy.ngram_suggester.v1", "sizes": [1, 2, 3]},
> }
> nlp.add_pipe("spancat", config=config)
> ```