spaCy/website/docs/api/scorer.md

4.5 KiB

title teaser tag source
Scorer Compute evaluation scores class spacy/scorer.py

The Scorer computes and stores evaluation scores. It's typically created by Language.evaluate.

Scorer.__init__

Create a new Scorer.

Example

from spacy.scorer import Scorer

scorer = Scorer()
Name Type Description
eval_punct bool Evaluate the dependency attachments to and from punctuation.
RETURNS Scorer The newly created object.

Scorer.score

Update the evaluation scores from a single Doc / GoldParse pair.

Example

scorer = Scorer()
scorer.score(doc, gold)
Name Type Description
doc Doc The predicted annotations.
gold GoldParse The correct annotations.
verbose bool Print debugging information.
punct_labels tuple Dependency labels for punctuation. Used to evaluate dependency attachments to punctuation if eval_punct is True.

Properties

Name Type Description
token_acc float Tokenization accuracy.
tags_acc float Part-of-speech tag accuracy (fine grained tags, i.e. Token.tag).
uas float Unlabelled dependency score.
las float Labelled dependency score.
ents_p float Named entity accuracy (precision).
ents_r float Named entity accuracy (recall).
ents_f float Named entity accuracy (F-score).
ents_per_type 2.1.5 dict Scores per entity label. Keyed by label, mapped to a dict of p, r and f scores.
textcat_f 3.0 float F-score on positive label for binary classification, macro-averaged F-score otherwise.
textcat_auc <Tag variant="new"3.0 float Macro-averaged AUC ROC score for multilabel classification (-1 if undefined).
textcats_f_per_cat 3.0 dict F-scores per textcat label, keyed by label.
textcats_auc_per_cat 3.0 dict ROC AUC scores per textcat label, keyed by label.
las_per_type 2.2.3 dict Labelled dependency scores, keyed by label.
scores dict All scores, keyed by type.