explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 01:48:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

Auto-format example

Browse Source
This commit is contained in:
Ines Montani 2018-12-17 13:44:38 +01:00
parent 361554f629
commit 6f1438b5d9
1 changed files with 19 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
examples/training/train_ner.py
View File

@ -20,51 +20,48 @@ from spacy.util import minibatch, compounding
# training data
TRAIN_DATA = [
('Who is Shaka Khan?', {
'entities': [(7, 17, 'PERSON')]
}),
('I like London and Berlin.', {
'entities': [(7, 13, 'LOC'), (18, 24, 'LOC')]
})
("Who is Shaka Khan?", {"entities": [(7, 17, "PERSON")]}),
("I like London and Berlin.", {"entities": [(7, 13, "LOC"), (18, 24, "LOC")]}),
]
@plac.annotations(
model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
output_dir=("Optional output directory", "option", "o", Path),
n_iter=("Number of training iterations", "option", "n", int))
n_iter=("Number of training iterations", "option", "n", int),
)
def main(model=None, output_dir=None, n_iter=100):
"""Load the model, set up the pipeline and train the entity recognizer."""
if model is not None:
nlp = spacy.load(model) # load existing spaCy model
print("Loaded model '%s'" % model)
else:
nlp = spacy.blank('en') # create blank Language class
nlp = spacy.blank("en") # create blank Language class
print("Created blank 'en' model")
# create the built-in pipeline components and add them to the pipeline
# nlp.create_pipe works for built-ins that are registered with spaCy
if 'ner' not in nlp.pipe_names:
ner = nlp.create_pipe('ner')
if "ner" not in nlp.pipe_names:
ner = nlp.create_pipe("ner")
nlp.add_pipe(ner, last=True)
# otherwise, get it so we can add labels
else:
ner = nlp.get_pipe('ner')
ner = nlp.get_pipe("ner")
# add labels
for _, annotations in TRAIN_DATA:
for ent in annotations.get('entities'):
for ent in annotations.get("entities"):
ner.add_label(ent[2])
# get names of other pipes to disable them during training
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'ner']
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != "ner"]
with nlp.disable_pipes(*other_pipes): # only train NER
optimizer = nlp.begin_training()
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
# batch up the examples using spaCy's minibatch
batches = minibatch(TRAIN_DATA, size=compounding(4., 32., 1.001))
batches = minibatch(TRAIN_DATA, size=compounding(4.0, 32.0, 1.001))
for batch in batches:
texts, annotations = zip(*batch)
nlp.update(
@ -72,14 +69,15 @@ def main(model=None, output_dir=None, n_iter=100):
annotations, # batch of annotations
drop=0.5, # dropout - make it harder to memorise data
sgd=optimizer, # callable to update weights
losses=losses)
print('Losses', losses)
losses=losses,
)
print("Losses", losses)
# test the trained model
for text, _ in TRAIN_DATA:
doc = nlp(text)
print('Entities', [(ent.text, ent.label_) for ent in doc.ents])
print('Tokens', [(t.text, t.ent_type_, t.ent_iob) for t in doc])
print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
# save model to output directory
if output_dir is not None:
@ -94,11 +92,11 @@ def main(model=None, output_dir=None, n_iter=100):
nlp2 = spacy.load(output_dir)
for text, _ in TRAIN_DATA:
doc = nlp2(text)
print('Entities', [(ent.text, ent.label_) for ent in doc.ents])
print('Tokens', [(t.text, t.ent_type_, t.ent_iob) for t in doc])
print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
if __name__ == '__main__':
if __name__ == "__main__":
plac.call(main)
# Expected output: