Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Remove unneeded methods in senter and morphologizer (#6074) 

Now that the tagger doesn't manage the tag map, the child classes senter
and morphologizer don't need to override the serialization methods.
This commit is contained in:
Adriane Boyd 2020-09-16 17:39:41 +02:00 committed by GitHub
parent 87c329c711
commit d722a439aa
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 0 additions and 152 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

76
spacy/pipeline/morphologizer.pyx
View File

@ -259,79 +259,3 @@ class Morphologizer(Tagger):
results.update(Scorer.score_token_attr_per_feat(examples, results.update(Scorer.score_token_attr_per_feat(examples,
"morph", **kwargs)) "morph", **kwargs))
return results return results
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://nightly.spacy.io/api/morphologizer#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 (Morphologizer): The loaded Morphologizer.
DOCS: https://nightly.spacy.io/api/morphologizer#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://nightly.spacy.io/api/morphologizer#to_disk
"""
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()):
"""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 (Morphologizer): The modified Morphologizer object.
DOCS: https://nightly.spacy.io/api/morphologizer#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

76
spacy/pipeline/senter.pyx
View File

@ -170,79 +170,3 @@ class SentenceRecognizer(Tagger):
results = Scorer.score_spans(examples, "sents", **kwargs) results = Scorer.score_spans(examples, "sents", **kwargs)
del results["sents_per_type"] del results["sents_per_type"]
return results return results
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://nightly.spacy.io/api/sentencerecognizer#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 SentenceRecognizer.
DOCS: https://nightly.spacy.io/api/sentencerecognizer#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://nightly.spacy.io/api/sentencerecognizer#to_disk
"""
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()):
"""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 SentenceRecognizer object.
DOCS: https://nightly.spacy.io/api/sentencerecognizer#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