mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
Tidy up and auto-format [ci skip]
This commit is contained in:
parent
cd90752193
commit
dad5621166
|
@ -16,9 +16,9 @@ class KerasSimilarityShim(object):
|
|||
if get_features is None:
|
||||
get_features = get_word_ids
|
||||
|
||||
with (path / 'config.json').open() as file_:
|
||||
with (path / "config.json").open() as file_:
|
||||
model = model_from_json(file_.read())
|
||||
with (path / 'model').open('rb') as file_:
|
||||
with (path / "model").open("rb") as file_:
|
||||
weights = pickle.load(file_)
|
||||
|
||||
embeddings = get_embeddings(nlp.vocab)
|
||||
|
@ -33,8 +33,8 @@ class KerasSimilarityShim(object):
|
|||
self.max_length = max_length
|
||||
|
||||
def __call__(self, doc):
|
||||
doc.user_hooks['similarity'] = self.predict
|
||||
doc.user_span_hooks['similarity'] = self.predict
|
||||
doc.user_hooks["similarity"] = self.predict
|
||||
doc.user_span_hooks["similarity"] = self.predict
|
||||
|
||||
return doc
|
||||
|
||||
|
@ -54,8 +54,8 @@ def get_embeddings(vocab, nr_unk=100):
|
|||
oov = np.random.normal(size=(nr_unk, vocab.vectors_length))
|
||||
oov = oov / oov.sum(axis=1, keepdims=True)
|
||||
|
||||
vectors = np.zeros((num_vectors + nr_unk, vocab.vectors_length), dtype='float32')
|
||||
vectors[1:(nr_unk + 1), ] = oov
|
||||
vectors = np.zeros((num_vectors + nr_unk, vocab.vectors_length), dtype="float32")
|
||||
vectors[1 : (nr_unk + 1),] = oov
|
||||
for lex in vocab:
|
||||
if lex.has_vector and lex.vector_norm > 0:
|
||||
vectors[nr_unk + lex.rank + 1] = lex.vector / lex.vector_norm
|
||||
|
@ -64,7 +64,7 @@ def get_embeddings(vocab, nr_unk=100):
|
|||
|
||||
|
||||
def get_word_ids(docs, max_length=100, nr_unk=100):
|
||||
Xs = np.zeros((len(docs), max_length), dtype='int32')
|
||||
Xs = np.zeros((len(docs), max_length), dtype="int32")
|
||||
|
||||
for i, doc in enumerate(docs):
|
||||
for j, token in enumerate(doc):
|
||||
|
|
|
@ -80,7 +80,7 @@ def main(model_name, unlabelled_loc):
|
|||
nlp.rehearse(raw_batch, sgd=optimizer, losses=r_losses)
|
||||
print("Losses", losses)
|
||||
print("R. Losses", r_losses)
|
||||
print(nlp.get_pipe('ner').model.unseen_classes)
|
||||
print(nlp.get_pipe("ner").model.unseen_classes)
|
||||
test_text = "Do you like horses?"
|
||||
doc = nlp(test_text)
|
||||
print("Entities in '%s'" % test_text)
|
||||
|
@ -88,7 +88,5 @@ def main(model_name, unlabelled_loc):
|
|||
print(ent.label_, ent.text)
|
||||
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
plac.call(main)
|
||||
|
|
|
@ -24,7 +24,7 @@ from spacy.util import minibatch, compounding
|
|||
output_dir=("Optional output directory", "option", "o", Path),
|
||||
n_texts=("Number of texts to train from", "option", "t", int),
|
||||
n_iter=("Number of training iterations", "option", "n", int),
|
||||
init_tok2vec=("Pretrained tok2vec weights", "option", "t2v", Path)
|
||||
init_tok2vec=("Pretrained tok2vec weights", "option", "t2v", Path),
|
||||
)
|
||||
def main(model=None, output_dir=None, n_iter=20, n_texts=2000, init_tok2vec=None):
|
||||
if output_dir is not None:
|
||||
|
@ -43,11 +43,7 @@ def main(model=None, output_dir=None, n_iter=20, n_texts=2000, init_tok2vec=None
|
|||
# nlp.create_pipe works for built-ins that are registered with spaCy
|
||||
if "textcat" not in nlp.pipe_names:
|
||||
textcat = nlp.create_pipe(
|
||||
"textcat",
|
||||
config={
|
||||
"exclusive_classes": True,
|
||||
"architecture": "simple_cnn",
|
||||
}
|
||||
"textcat", config={"exclusive_classes": True, "architecture": "simple_cnn"}
|
||||
)
|
||||
nlp.add_pipe(textcat, last=True)
|
||||
# otherwise, get it, so we can add labels to it
|
||||
|
|
Loading…
Reference in New Issue
Block a user