spaCy/spacy/pipeline/senter.pyx

152 lines
4.8 KiB
Cython
Raw Normal View History

Refactor pipeline components, config and language data (#5759) * Update with WIP * Update with WIP * Update with pipeline serialization * Update types and pipe factories * Add deep merge, tidy up and add tests * Fix pipe creation from config * Don't validate default configs on load * Update spacy/language.py Co-authored-by: Ines Montani <ines@ines.io> * Adjust factory/component meta error * Clean up factory args and remove defaults * Add test for failing empty dict defaults * Update pipeline handling and methods * provide KB as registry function instead of as object * small change in test to make functionality more clear * update example script for EL configuration * Fix typo * Simplify test * Simplify test * splitting pipes.pyx into separate files * moving default configs to each component file * fix batch_size type * removing default values from component constructors where possible (TODO: test 4725) * skip instead of xfail * Add test for config -> nlp with multiple instances * pipeline.pipes -> pipeline.pipe * Tidy up, document, remove kwargs * small cleanup/generalization for Tok2VecListener * use DEFAULT_UPSTREAM field * revert to avoid circular imports * Fix tests * Replace deprecated arg * Make model dirs require config * fix pickling of keyword-only arguments in constructor * WIP: clean up and integrate full config * Add helper to handle function args more reliably Now also includes keyword-only args * Fix config composition and serialization * Improve config debugging and add visual diff * Remove unused defaults and fix type * Remove pipeline and factories from meta * Update spacy/default_config.cfg Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update spacy/default_config.cfg * small UX edits * avoid printing stack trace for debug CLI commands * Add support for language-specific factories * specify the section of the config which holds the model to debug * WIP: add Language.from_config * Update with language data refactor WIP * Auto-format * Add backwards-compat handling for Language.factories * Update morphologizer.pyx * Fix morphologizer * Update and simplify lemmatizers * Fix Japanese tests * Port over tagger changes * Fix Chinese and tests * Update to latest Thinc * WIP: xfail first Russian lemmatizer test * Fix component-specific overrides * fix nO for output layers in debug_model * Fix default value * Fix tests and don't pass objects in config * Fix deep merging * Fix lemma lookup data registry Only load the lookups if an entry is available in the registry (and if spacy-lookups-data is installed) * Add types * Add Vocab.from_config * Fix typo * Fix tests * Make config copying more elegant * Fix pipe analysis * Fix lemmatizers and is_base_form * WIP: move language defaults to config * Fix morphology type * Fix vocab * Remove comment * Update to latest Thinc * Add morph rules to config * Tidy up * Remove set_morphology option from tagger factory * Hack use_gpu * Move [pipeline] to top-level block and make [nlp.pipeline] list Allows separating component blocks from component order – otherwise, ordering the config would mean a changed component order, which is bad. Also allows initial config to define more components and not use all of them * Fix use_gpu and resume in CLI * Auto-format * Remove resume from config * Fix formatting and error * [pipeline] -> [components] * Fix types * Fix tagger test: requires set_morphology? Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com> Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
2020-07-22 11:42:59 +00:00
# cython: infer_types=True, profile=True, binding=True
import srsly
from thinc.api import Model, SequenceCategoricalCrossentropy, Config
from ..tokens.doc cimport Doc
from .pipe import deserialize_config
from .tagger import Tagger
from ..language import Language
from ..errors import Errors
from .. import util
default_model_config = """
[model]
@architectures = "spacy.Tagger.v1"
[model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v1"
pretrained_vectors = null
width = 12
depth = 1
embed_size = 2000
window_size = 1
maxout_pieces = 2
subword_features = true
dropout = null
"""
DEFAULT_SENTER_MODEL = Config().from_str(default_model_config)["model"]
@Language.factory(
"senter",
assigns=["token.is_sent_start"],
default_config={"model": DEFAULT_SENTER_MODEL}
)
def make_senter(nlp: Language, name: str, model: Model):
return SentenceRecognizer(nlp.vocab, model, name)
class SentenceRecognizer(Tagger):
"""Pipeline component for sentence segmentation.
DOCS: https://spacy.io/api/sentencerecognizer
"""
def __init__(self, vocab, model, name="senter"):
self.vocab = vocab
self.model = model
self.name = name
self._rehearsal_model = None
self.cfg = {}
@property
def labels(self):
# labels are numbered by index internally, so this matches GoldParse
# and Example where the sentence-initial tag is 1 and other positions
# are 0
return tuple(["I", "S"])
def set_annotations(self, docs, batch_tag_ids):
if isinstance(docs, Doc):
docs = [docs]
cdef Doc doc
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 existing sentence boundaries
if doc.c[j].sent_start == 0:
if tag_id == 1:
doc.c[j].sent_start = 1
else:
doc.c[j].sent_start = -1
def get_loss(self, examples, scores):
labels = self.labels
loss_func = SequenceCategoricalCrossentropy(names=labels, normalize=False)
truths = []
for eg in examples:
eg_truth = []
for x in eg.get_aligned("sent_start"):
if x == None:
eg_truth.append(None)
elif x == 1:
eg_truth.append(labels[1])
else:
# anything other than 1: 0, -1, -1 as uint64
eg_truth.append(labels[0])
truths.append(eg_truth)
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=lambda: [], pipeline=None, sgd=None):
self.set_output(len(self.labels))
self.model.initialize()
util.link_vectors_to_models(self.vocab)
if sgd is None:
sgd = self.create_optimizer()
return sgd
def add_label(self, label, values=None):
raise NotImplementedError
def to_bytes(self, exclude=tuple()):
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()):
def load_model(b):
try:
self.model.from_bytes(b)
except AttributeError:
raise ValueError(Errors.E149)
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 = {
"vocab": lambda p: self.vocab.to_disk(p),
"model": lambda p: p.open("wb").write(self.model.to_bytes()),
"cfg": lambda p: srsly.write_json(p, self.cfg),
}
util.to_disk(path, serialize, exclude)
def from_disk(self, path, exclude=tuple()):
def load_model(p):
with p.open("rb") as file_:
try:
self.model.from_bytes(file_.read())
except AttributeError:
raise ValueError(Errors.E149)
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