explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-29 09:23:12 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6273 from adrianeboyd/bugfix/detailed-scores-in-evaluate2

Browse Source
This commit is contained in:
Ines Montani 2020-10-20 10:03:09 +02:00 committed by GitHub
commit 6523f2daac
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 18 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
spacy/cli/evaluate.py
View File

@ -93,6 +93,7 @@ def evaluate(
"SPEED": "speed", "SPEED": "speed",
} }
results = {} results = {}
data = {}
for metric, key in metrics.items(): for metric, key in metrics.items():
if key in scores: if key in scores:
if key == "cats_score": if key == "cats_score":
@ -101,19 +102,30 @@ def evaluate(
results[metric] = f"{scores[key]:.0f}" results[metric] = f"{scores[key]:.0f}"
else: else:
results[metric] = f"{scores[key]*100:.2f}" results[metric] = f"{scores[key]*100:.2f}"
data = {re.sub(r"[\s/]", "_", k.lower()): v for k, v in results.items()} data[re.sub(r"[\s/]", "_", key.lower())] = scores[key]
msg.table(results, title="Results") msg.table(results, title="Results")
if "morph_per_feat" in scores:
if scores["morph_per_feat"]:
print_prf_per_type(msg, scores["morph_per_feat"], "MORPH", "feat")
data["morph_per_feat"] = scores["morph_per_feat"]
if "dep_las_per_type" in scores:
if scores["dep_las_per_type"]:
print_prf_per_type(msg, scores["dep_las_per_type"], "LAS", "type")
data["dep_las_per_type"] = scores["dep_las_per_type"]
if "ents_per_type" in scores: if "ents_per_type" in scores:
if scores["ents_per_type"]: if scores["ents_per_type"]:
print_ents_per_type(msg, scores["ents_per_type"]) print_prf_per_type(msg, scores["ents_per_type"], "NER", "type")
data["ents_per_type"] = scores["ents_per_type"]
if "cats_f_per_type" in scores: if "cats_f_per_type" in scores:
if scores["cats_f_per_type"]: if scores["cats_f_per_type"]:
print_textcats_f_per_cat(msg, scores["cats_f_per_type"]) print_prf_per_type(msg, scores["cats_f_per_type"], "Textcat F", "label")
data["cats_f_per_type"] = scores["cats_f_per_type"]
if "cats_auc_per_type" in scores: if "cats_auc_per_type" in scores:
if scores["cats_auc_per_type"]: if scores["cats_auc_per_type"]:
print_textcats_auc_per_cat(msg, scores["cats_auc_per_type"]) print_textcats_auc_per_cat(msg, scores["cats_auc_per_type"])
data["cats_auc_per_type"] = scores["cats_auc_per_type"]
if displacy_path: if displacy_path:
factory_names = [nlp.get_pipe_meta(pipe).factory for pipe in nlp.pipe_names] factory_names = [nlp.get_pipe_meta(pipe).factory for pipe in nlp.pipe_names]
@ -157,7 +169,7 @@ def render_parses(
file_.write(html) file_.write(html)
def print_ents_per_type(msg: Printer, scores: Dict[str, Dict[str, float]]) -> None: def print_prf_per_type(msg: Printer, scores: Dict[str, Dict[str, float]], name: str, type: str) -> None:
data = [ data = [
(k, f"{v['p']*100:.2f}", f"{v['r']*100:.2f}", f"{v['f']*100:.2f}") (k, f"{v['p']*100:.2f}", f"{v['r']*100:.2f}", f"{v['f']*100:.2f}")
for k, v in scores.items() for k, v in scores.items()
@ -166,20 +178,7 @@ def print_ents_per_type(msg: Printer, scores: Dict[str, Dict[str, float]]) -> No
data, data,
header=("", "P", "R", "F"), header=("", "P", "R", "F"),
aligns=("l", "r", "r", "r"), aligns=("l", "r", "r", "r"),
title="NER (per type)", title=f"{name} (per {type})",
)
def print_textcats_f_per_cat(msg: Printer, scores: Dict[str, Dict[str, float]]) -> None:
data = [
(k, f"{v['p']*100:.2f}", f"{v['r']*100:.2f}", f"{v['f']*100:.2f}")
for k, v in scores.items()
]
msg.table(
data,
header=("", "P", "R", "F"),
aligns=("l", "r", "r", "r"),
title="Textcat F (per label)",
) )

2
website/src/templates/models.js
View File

@ -120,7 +120,7 @@ function formatAccuracy(data) {
? null ? null
: { : {
label, label,
value: value.toFixed(2), value: (value * 100).toFixed(2),
help: MODEL_META[label], help: MODEL_META[label],
} }
}) })