explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-09 15:52:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add spans in spacy benchmark

Browse Source 
The current implementation of spaCy benchmark accuracy / spacy evaluate
doesn't include the "spans" type, so calling the command doesn't render
the HTML displaCy file needed.

This PR attempts to fix that by creating a new parameter for "spans"
and calling the appropriate displaCy value.
This commit is contained in:
Lj Miranda 2023-04-26 09:38:10 +08:00
parent 070fa16545
commit e3de12fd1e
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/cli/evaluate.py
View File

@ -122,6 +122,8 @@ def evaluate(
docs = list(nlp.pipe(ex.reference.text for ex in dev_dataset[:displacy_limit])) docs = list(nlp.pipe(ex.reference.text for ex in dev_dataset[:displacy_limit]))
render_deps = "parser" in factory_names render_deps = "parser" in factory_names
render_ents = "ner" in factory_names render_ents = "ner" in factory_names
render_spans = "spancat" in factory_names
render_parses( render_parses(
docs, docs,
displacy_path, displacy_path,
@ -129,6 +131,7 @@ def evaluate(
limit=displacy_limit, limit=displacy_limit,
deps=render_deps, deps=render_deps,
ents=render_ents, ents=render_ents,
spans=render_spans,
) )
msg.good(f"Generated {displacy_limit} parses as HTML", displacy_path) msg.good(f"Generated {displacy_limit} parses as HTML", displacy_path)
@ -182,6 +185,7 @@ def render_parses(
limit: int = 250, limit: int = 250,
deps: bool = True, deps: bool = True,
ents: bool = True, ents: bool = True,
spans: bool = True,
): ):
docs[0].user_data["title"] = model_name docs[0].user_data["title"] = model_name
if ents: if ents:
@ -195,6 +199,11 @@ def render_parses(
with (output_path / "parses.html").open("w", encoding="utf8") as file_: with (output_path / "parses.html").open("w", encoding="utf8") as file_:
file_.write(html) file_.write(html)
if spans:
html = displacy.render(docs[:limit], style="spans", page=True)
with (output_path / "spans.html").open("w", encoding="utf8") as file_:
file_.write(html)
def print_prf_per_type( def print_prf_per_type(
msg: Printer, scores: Dict[str, Dict[str, float]], name: str, type: str msg: Printer, scores: Dict[str, Dict[str, float]], name: str, type: str