spaCy/spacy/pipeline/tagger.pyx
Sofie Van Landeghem 358cbb21e3
Define candidate generator in EL config (#5876)
* candidate generator as separate part of EL config

* update comment

* ent instead of str as input for candidate generation

* Span instead of str: correct type indication

* fix types

* unit test to create new candidate generator

* fix replace_pipe argument passing

* move error message, general cleanup

* add vocab back to KB constructor

* provide KB as callable from Vocab arg

* rename to kb_loader, fix KB serialization as part of the EL pipe

* fix typo

* reformatting

* cleanup

* fix comment

* fix wrongly duplicated code from merge conflict

* rename dump to to_disk

* from_disk instead of load_bulk

* update test after recent removal of set_morphology in tagger

* remove old doc
2020-08-18 16:10:36 +02:00

392 lines
14 KiB
Cython

# cython: infer_types=True, profile=True, binding=True
from typing import List
import numpy
import srsly
from thinc.api import Model, set_dropout_rate, SequenceCategoricalCrossentropy, Config
from thinc.types import Floats2d
import warnings
from ..tokens.doc cimport Doc
from ..morphology cimport Morphology
from ..vocab cimport Vocab
from .pipe import Pipe, deserialize_config
from ..language import Language
from ..attrs import POS, ID
from ..parts_of_speech import X
from ..errors import Errors, TempErrors, Warnings
from ..scorer import Scorer
from ..gold import validate_examples
from .. import util
default_model_config = """
[model]
@architectures = "spacy.Tagger.v1"
[model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v1"
pretrained_vectors = null
width = 96
depth = 4
embed_size = 2000
window_size = 1
maxout_pieces = 3
subword_features = true
"""
DEFAULT_TAGGER_MODEL = Config().from_str(default_model_config)["model"]
@Language.factory(
"tagger",
assigns=["token.tag"],
default_config={"model": DEFAULT_TAGGER_MODEL},
scores=["tag_acc"],
default_score_weights={"tag_acc": 1.0},
)
def make_tagger(nlp: Language, name: str, model: Model):
"""Construct a part-of-speech tagger component.
model (Model[List[Doc], List[Floats2d]]): A model instance that predicts
the tag probabilities. The output vectors should match the number of tags
in size, and be normalized as probabilities (all scores between 0 and 1,
with the rows summing to 1).
"""
return Tagger(nlp.vocab, model, name)
class Tagger(Pipe):
"""Pipeline component for part-of-speech tagging.
DOCS: https://spacy.io/api/tagger
"""
def __init__(self, vocab, model, name="tagger", *, labels=None):
"""Initialize a part-of-speech tagger.
vocab (Vocab): The shared vocabulary.
model (thinc.api.Model): The Thinc Model powering the pipeline component.
name (str): The component instance name, used to add entries to the
losses during training.
labels (List): The set of labels. Defaults to None.
DOCS: https://spacy.io/api/tagger#init
"""
self.vocab = vocab
self.model = model
self.name = name
self._rehearsal_model = None
cfg = {"labels": labels or []}
self.cfg = dict(sorted(cfg.items()))
@property
def labels(self):
"""The labels currently added to the component. Note that even for a
blank component, this will always include the built-in coarse-grained
part-of-speech tags by default.
RETURNS (Tuple[str]): The labels.
DOCS: https://spacy.io/api/tagger#labels
"""
return tuple(self.cfg["labels"])
def __call__(self, doc):
"""Apply the pipe to a Doc.
doc (Doc): The document to process.
RETURNS (Doc): The processed Doc.
DOCS: https://spacy.io/api/tagger#call
"""
tags = self.predict([doc])
self.set_annotations([doc], tags)
return doc
def pipe(self, stream, *, batch_size=128):
"""Apply the pipe to a stream of documents. This usually happens under
the hood when the nlp object is called on a text and all components are
applied to the Doc.
stream (Iterable[Doc]): A stream of documents.
batch_size (int): The number of documents to buffer.
YIELDS (Doc): Processed documents in order.
DOCS: https://spacy.io/api/tagger#pipe
"""
for docs in util.minibatch(stream, size=batch_size):
tag_ids = self.predict(docs)
self.set_annotations(docs, tag_ids)
yield from docs
def predict(self, docs):
"""Apply the pipeline's model to a batch of docs, without modifying them.
docs (Iterable[Doc]): The documents to predict.
RETURNS: The models prediction for each document.
DOCS: https://spacy.io/api/tagger#predict
"""
if not any(len(doc) for doc in docs):
# Handle cases where there are no tokens in any docs.
n_labels = len(self.labels)
guesses = [self.model.ops.alloc((0, n_labels)) for doc in docs]
assert len(guesses) == len(docs)
return guesses
scores = self.model.predict(docs)
assert len(scores) == len(docs), (len(scores), len(docs))
guesses = self._scores2guesses(scores)
assert len(guesses) == len(docs)
return guesses
def _scores2guesses(self, scores):
guesses = []
for doc_scores in scores:
doc_guesses = doc_scores.argmax(axis=1)
if not isinstance(doc_guesses, numpy.ndarray):
doc_guesses = doc_guesses.get()
guesses.append(doc_guesses)
return guesses
def set_annotations(self, docs, batch_tag_ids):
"""Modify a batch of documents, using pre-computed scores.
docs (Iterable[Doc]): The documents to modify.
batch_tag_ids: The IDs to set, produced by Tagger.predict.
DOCS: https://spacy.io/api/tagger#set_annotations
"""
if isinstance(docs, Doc):
docs = [docs]
cdef Doc doc
cdef Vocab vocab = self.vocab
for i, doc in enumerate(docs):
doc_tag_ids = batch_tag_ids[i]
if hasattr(doc_tag_ids, "get"):
doc_tag_ids = doc_tag_ids.get()
for j, tag_id in enumerate(doc_tag_ids):
# Don't clobber preset POS tags
if doc.c[j].tag == 0:
doc.c[j].tag = self.vocab.strings[self.labels[tag_id]]
doc.is_tagged = True
def update(self, examples, *, drop=0., sgd=None, losses=None, set_annotations=False):
"""Learn from a batch of documents and gold-standard information,
updating the pipe's model. Delegates to predict and get_loss.
examples (Iterable[Example]): A batch of Example objects.
drop (float): The dropout rate.
set_annotations (bool): Whether or not to update the Example objects
with the predictions.
sgd (thinc.api.Optimizer): The optimizer.
losses (Dict[str, float]): Optional record of the loss during training.
Updated using the component name as the key.
RETURNS (Dict[str, float]): The updated losses dictionary.
DOCS: https://spacy.io/api/tagger#update
"""
if losses is None:
losses = {}
losses.setdefault(self.name, 0.0)
validate_examples(examples, "Tagger.update")
if not any(len(eg.predicted) if eg.predicted else 0 for eg in examples):
# Handle cases where there are no tokens in any docs.
return
set_dropout_rate(self.model, drop)
tag_scores, bp_tag_scores = self.model.begin_update([eg.predicted for eg in examples])
for sc in tag_scores:
if self.model.ops.xp.isnan(sc.sum()):
raise ValueError(Errors.E940)
loss, d_tag_scores = self.get_loss(examples, tag_scores)
bp_tag_scores(d_tag_scores)
if sgd not in (None, False):
self.model.finish_update(sgd)
losses[self.name] += loss
if set_annotations:
docs = [eg.predicted for eg in examples]
self.set_annotations(docs, self._scores2guesses(tag_scores))
return losses
def rehearse(self, examples, *, drop=0., sgd=None, losses=None):
"""Perform a "rehearsal" update from a batch of data. Rehearsal updates
teach the current model to make predictions similar to an initial model,
to try to address the "catastrophic forgetting" problem. This feature is
experimental.
examples (Iterable[Example]): A batch of Example objects.
drop (float): The dropout rate.
sgd (thinc.api.Optimizer): The optimizer.
losses (Dict[str, float]): Optional record of the loss during training.
Updated using the component name as the key.
RETURNS (Dict[str, float]): The updated losses dictionary.
DOCS: https://spacy.io/api/tagger#rehearse
"""
validate_examples(examples, "Tagger.rehearse")
docs = [eg.predicted for eg in examples]
if self._rehearsal_model is None:
return
if not any(len(doc) for doc in docs):
# Handle cases where there are no tokens in any docs.
return
set_dropout_rate(self.model, drop)
guesses, backprop = self.model.begin_update(docs)
target = self._rehearsal_model(examples)
gradient = guesses - target
backprop(gradient)
self.model.finish_update(sgd)
if losses is not None:
losses.setdefault(self.name, 0.0)
losses[self.name] += (gradient**2).sum()
def get_loss(self, examples, scores):
"""Find the loss and gradient of loss for the batch of documents and
their predicted scores.
examples (Iterable[Examples]): The batch of examples.
scores: Scores representing the model's predictions.
RETUTNRS (Tuple[float, float]): The loss and the gradient.
DOCS: https://spacy.io/api/tagger#get_loss
"""
validate_examples(examples, "Tagger.get_loss")
loss_func = SequenceCategoricalCrossentropy(names=self.labels, normalize=False)
truths = [eg.get_aligned("TAG", as_string=True) for eg in examples]
d_scores, loss = loss_func(scores, truths)
if self.model.ops.xp.isnan(loss):
raise ValueError("nan value when computing loss")
return float(loss), d_scores
def begin_training(self, get_examples, *, pipeline=None, sgd=None):
"""Initialize the pipe for training, using data examples if available.
get_examples (Callable[[], Iterable[Example]]): Optional function that
returns gold-standard Example objects.
pipeline (List[Tuple[str, Callable]]): Optional list of pipeline
components that this component is part of. Corresponds to
nlp.pipeline.
sgd (thinc.api.Optimizer): Optional optimizer. Will be created with
create_optimizer if it doesn't exist.
RETURNS (thinc.api.Optimizer): The optimizer.
DOCS: https://spacy.io/api/tagger#begin_training
"""
if not hasattr(get_examples, "__call__"):
err = Errors.E930.format(name="Tagger", obj=type(get_examples))
raise ValueError(err)
tags = set()
for example in get_examples():
for token in example.y:
tags.add(token.tag_)
for tag in sorted(tags):
self.add_label(tag)
self.set_output(len(self.labels))
self.model.initialize()
if sgd is None:
sgd = self.create_optimizer()
return sgd
def add_label(self, label):
"""Add a new label to the pipe.
label (str): The label to add.
RETURNS (int): 0 if label is already present, otherwise 1.
DOCS: https://spacy.io/api/tagger#add_label
"""
if not isinstance(label, str):
raise ValueError(Errors.E187)
if label in self.labels:
return 0
self.cfg["labels"].append(label)
self.vocab.strings.add(label)
return 1
def score(self, examples, **kwargs):
"""Score a batch of examples.
examples (Iterable[Example]): The examples to score.
RETURNS (Dict[str, Any]): The scores, produced by
Scorer.score_token_attr for the attributes "tag", "pos" and "lemma".
DOCS: https://spacy.io/api/tagger#score
"""
validate_examples(examples, "Tagger.score")
return Scorer.score_token_attr(examples, "tag", **kwargs)
def to_bytes(self, *, exclude=tuple()):
"""Serialize the pipe to a bytestring.
exclude (Iterable[str]): String names of serialization fields to exclude.
RETURNS (bytes): The serialized object.
DOCS: https://spacy.io/api/tagger#to_bytes
"""
serialize = {}
serialize["model"] = self.model.to_bytes
serialize["vocab"] = self.vocab.to_bytes
serialize["cfg"] = lambda: srsly.json_dumps(self.cfg)
return util.to_bytes(serialize, exclude)
def from_bytes(self, bytes_data, *, exclude=tuple()):
"""Load the pipe from a bytestring.
bytes_data (bytes): The serialized pipe.
exclude (Iterable[str]): String names of serialization fields to exclude.
RETURNS (Tagger): The loaded Tagger.
DOCS: https://spacy.io/api/tagger#from_bytes
"""
def load_model(b):
try:
self.model.from_bytes(b)
except AttributeError:
raise ValueError(Errors.E149) from None
deserialize = {
"vocab": lambda b: self.vocab.from_bytes(b),
"cfg": lambda b: self.cfg.update(srsly.json_loads(b)),
"model": lambda b: load_model(b),
}
util.from_bytes(bytes_data, deserialize, exclude)
return self
def to_disk(self, path, *, exclude=tuple()):
"""Serialize the pipe to disk.
path (str / Path): Path to a directory.
exclude (Iterable[str]): String names of serialization fields to exclude.
DOCS: https://spacy.io/api/tagger#to_disk
"""
serialize = {
"vocab": lambda p: self.vocab.to_disk(p),
"model": lambda p: self.model.to_disk(p),
"cfg": lambda p: srsly.write_json(p, self.cfg),
}
util.to_disk(path, serialize, exclude)
def from_disk(self, path, *, exclude=tuple()):
"""Load the pipe from disk. Modifies the object in place and returns it.
path (str / Path): Path to a directory.
exclude (Iterable[str]): String names of serialization fields to exclude.
RETURNS (Tagger): The modified Tagger object.
DOCS: https://spacy.io/api/tagger#from_disk
"""
def load_model(p):
with p.open("rb") as file_:
try:
self.model.from_bytes(file_.read())
except AttributeError:
raise ValueError(Errors.E149) from None
deserialize = {
"vocab": lambda p: self.vocab.from_disk(p),
"cfg": lambda p: self.cfg.update(deserialize_config(p)),
"model": load_model,
}
util.from_disk(path, deserialize, exclude)
return self