spaCy/spacy/pipeline/sentencizer.pyx
Adriane Boyd 2bcceb80c4
Refactor the Scorer to improve flexibility (#5731)
* Refactor the Scorer to improve flexibility

Refactor the `Scorer` to improve flexibility for arbitrary pipeline
components.

* Individual pipeline components provide their own `evaluate` methods
that score a list of `Example`s and return a dictionary of scores
* `Scorer` is initialized either:
  * with a provided pipeline containing components to be scored
  * with a default pipeline containing the built-in statistical
    components (senter, tagger, morphologizer, parser, ner)
* `Scorer.score` evaluates a list of `Example`s and returns a dictionary
of scores referring to the scores provided by the components in the
pipeline

Significant differences:

* `tags_acc` is renamed to `tag_acc` to be consistent with `token_acc`
and the new `morph_acc`, `pos_acc`, and `lemma_acc`
* Scoring is no longer cumulative: `Scorer.score` scores a list of
examples rather than a single example and does not retain any state
about previously scored examples
* PRF values in the returned scores are no longer multiplied by 100

* Add kwargs to Morphologizer.evaluate

* Create generalized scoring methods in Scorer

* Generalized static scoring methods are added to `Scorer`
  * Methods require an attribute (either on Token or Doc) that is
used to key the returned scores

Naming differences:

* `uas`, `las`, and `las_per_type` in the scores dict are renamed to
`dep_uas`, `dep_las`, and `dep_las_per_type`

Scoring differences:

* `Doc.sents` is now scored as spans rather than on sentence-initial
token positions so that `Doc.sents` and `Doc.ents` can be scored with
the same method (this lowers scores since a single incorrect sentence
start results in two incorrect spans)

* Simplify / extend hasattr check for eval method

* Add hasattr check to tokenizer scoring
* Simplify to hasattr check for component scoring

* Reset Example alignment if docs are set

Reset the Example alignment if either doc is set in case the
tokenization has changed.

* Add PRF tokenization scoring for tokens as spans

Add PRF scores for tokens as character spans. The scores are:

* token_acc: # correct tokens / # gold tokens
* token_p/r/f: PRF for (token.idx, token.idx + len(token))

* Add docstring to Scorer.score_tokenization

* Rename component.evaluate() to component.score()

* Update Scorer API docs

* Update scoring for positive_label in textcat

* Fix TextCategorizer.score kwargs

* Update Language.evaluate docs

* Update score names in default config
2020-07-25 12:53:02 +02:00

178 lines
6.4 KiB
Cython
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# cython: infer_types=True, profile=True, binding=True
import srsly
from typing import Optional, List
from ..tokens.doc cimport Doc
from .pipe import Pipe
from ..language import Language
from ..scorer import Scorer
from .. import util
@Language.factory(
"sentencizer",
assigns=["token.is_sent_start", "doc.sents"],
default_config={"punct_chars": None}
)
def make_sentencizer(
nlp: Language,
name: str,
punct_chars: Optional[List[str]]
):
return Sentencizer(name, punct_chars=punct_chars)
class Sentencizer(Pipe):
"""Segment the Doc into sentences using a rule-based strategy.
DOCS: https://spacy.io/api/sentencizer
"""
default_punct_chars = ['!', '.', '?', '։', '؟', '۔', '܀', '܁', '܂', '߹',
'', '', '', '', '', '', '', '', '', '', '', '', '',
'', '', '', '', '', '', '', '', '', '', '', '', '᱿',
'', '', '', '', '', '', '', '', '', '', '', '', '',
'', '', '', '', '', '', '', '', '', '', '', '', '',
'', '', '', '', '', '𐩖', '𐩗', '𑁇', '𑁈', '𑂾', '𑂿', '𑃀',
'𑃁', '𑅁', '𑅂', '𑅃', '𑇅', '𑇆', '𑇍', '𑇞', '𑇟', '𑈸', '𑈹', '𑈻', '𑈼',
'𑊩', '𑑋', '𑑌', '𑗂', '𑗃', '𑗉', '𑗊', '𑗋', '𑗌', '𑗍', '𑗎', '𑗏', '𑗐',
'𑗑', '𑗒', '𑗓', '𑗔', '𑗕', '𑗖', '𑗗', '𑙁', '𑙂', '𑜼', '𑜽', '𑜾', '𑩂',
'𑩃', '𑪛', '𑪜', '𑱁', '𑱂', '𖩮', '𖩯', '𖫵', '𖬷', '𖬸', '𖭄', '𛲟', '𝪈',
'', '']
def __init__(self, name="sentencizer", *, punct_chars):
"""Initialize the sentencizer.
punct_chars (list): Punctuation characters to split on. Will be
serialized with the nlp object.
RETURNS (Sentencizer): The sentencizer component.
DOCS: https://spacy.io/api/sentencizer#init
"""
self.name = name
if punct_chars:
self.punct_chars = set(punct_chars)
else:
self.punct_chars = set(self.default_punct_chars)
def begin_training(self, get_examples=lambda: [], pipeline=None, sgd=None):
pass
def __call__(self, doc):
"""Apply the sentencizer to a Doc and set Token.is_sent_start.
example (Doc or Example): The document to process.
RETURNS (Doc or Example): The processed Doc or Example.
DOCS: https://spacy.io/api/sentencizer#call
"""
start = 0
seen_period = False
for i, token in enumerate(doc):
is_in_punct_chars = token.text in self.punct_chars
token.is_sent_start = i == 0
if seen_period and not token.is_punct and not is_in_punct_chars:
doc[start].is_sent_start = True
start = token.i
seen_period = False
elif is_in_punct_chars:
seen_period = True
if start < len(doc):
doc[start].is_sent_start = True
return doc
def pipe(self, stream, batch_size=128):
for docs in util.minibatch(stream, size=batch_size):
predictions = self.predict(docs)
self.set_annotations(docs, predictions)
yield from docs
def predict(self, docs):
"""Apply the pipeline's model to a batch of docs, without
modifying them.
"""
if not any(len(doc) for doc in docs):
# Handle cases where there are no tokens in any docs.
guesses = [[] for doc in docs]
return guesses
guesses = []
for doc in docs:
doc_guesses = [False] * len(doc)
if len(doc) > 0:
start = 0
seen_period = False
doc_guesses[0] = True
for i, token in enumerate(doc):
is_in_punct_chars = token.text in self.punct_chars
if seen_period and not token.is_punct and not is_in_punct_chars:
doc_guesses[start] = True
start = token.i
seen_period = False
elif is_in_punct_chars:
seen_period = True
if start < len(doc):
doc_guesses[start] = True
guesses.append(doc_guesses)
return guesses
def set_annotations(self, docs, batch_tag_ids):
if isinstance(docs, Doc):
docs = [docs]
cdef Doc doc
cdef int idx = 0
for i, doc in enumerate(docs):
doc_tag_ids = batch_tag_ids[i]
for j, tag_id in enumerate(doc_tag_ids):
# Don't clobber existing sentence boundaries
if doc.c[j].sent_start == 0:
if tag_id:
doc.c[j].sent_start = 1
else:
doc.c[j].sent_start = -1
def score(self, examples, **kwargs):
return Scorer.score_spans(examples, "sents", **kwargs)
def to_bytes(self, exclude=tuple()):
"""Serialize the sentencizer to a bytestring.
RETURNS (bytes): The serialized object.
DOCS: https://spacy.io/api/sentencizer#to_bytes
"""
return srsly.msgpack_dumps({"punct_chars": list(self.punct_chars)})
def from_bytes(self, bytes_data, exclude=tuple()):
"""Load the sentencizer from a bytestring.
bytes_data (bytes): The data to load.
returns (Sentencizer): The loaded object.
DOCS: https://spacy.io/api/sentencizer#from_bytes
"""
cfg = srsly.msgpack_loads(bytes_data)
self.punct_chars = set(cfg.get("punct_chars", self.default_punct_chars))
return self
def to_disk(self, path, exclude=tuple()):
"""Serialize the sentencizer to disk.
DOCS: https://spacy.io/api/sentencizer#to_disk
"""
path = util.ensure_path(path)
path = path.with_suffix(".json")
srsly.write_json(path, {"punct_chars": list(self.punct_chars)})
def from_disk(self, path, exclude=tuple()):
"""Load the sentencizer from disk.
DOCS: https://spacy.io/api/sentencizer#from_disk
"""
path = util.ensure_path(path)
path = path.with_suffix(".json")
cfg = srsly.read_json(path)
self.punct_chars = set(cfg.get("punct_chars", self.default_punct_chars))
return self