mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
116 lines
4.0 KiB
Python
116 lines
4.0 KiB
Python
#!/usr/bin/env python
|
||
# coding: utf8
|
||
"""Example of training spaCy's named entity recognizer, starting off with an
|
||
existing model or a blank model.
|
||
|
||
For more details, see the documentation:
|
||
* Training: https://spacy.io/usage/training
|
||
* NER: https://spacy.io/usage/linguistic-features#named-entities
|
||
|
||
Compatible with: spaCy v2.0.0+
|
||
Last tested with: v2.2.4
|
||
"""
|
||
from __future__ import unicode_literals, print_function
|
||
|
||
import plac
|
||
import random
|
||
import warnings
|
||
from pathlib import Path
|
||
import spacy
|
||
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")]}),
|
||
]
|
||
|
||
|
||
@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),
|
||
)
|
||
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
|
||
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 "simple_ner" not in nlp.pipe_names:
|
||
ner = nlp.create_pipe("simple_ner")
|
||
nlp.add_pipe(ner, last=True)
|
||
# otherwise, get it so we can add labels
|
||
else:
|
||
ner = nlp.get_pipe("simple_ner")
|
||
|
||
# add labels
|
||
for _, annotations in TRAIN_DATA:
|
||
for ent in annotations.get("entities"):
|
||
print("Add label", ent[2])
|
||
ner.add_label(ent[2])
|
||
|
||
with nlp.select_pipes(enable="ner") and warnings.catch_warnings():
|
||
# show warnings for misaligned entity spans once
|
||
warnings.filterwarnings("once", category=UserWarning, module="spacy")
|
||
|
||
# reset and initialize the weights randomly – but only if we're
|
||
# training a new model
|
||
if model is None:
|
||
nlp.begin_training()
|
||
print(
|
||
"Transitions", list(enumerate(nlp.get_pipe("simple_ner").get_tag_names()))
|
||
)
|
||
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(4.0, 32.0, 1.001))
|
||
for batch in batches:
|
||
nlp.update(
|
||
batch,
|
||
drop=0.0, # dropout - make it harder to memorise data
|
||
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])
|
||
|
||
# save model to output directory
|
||
if output_dir is not None:
|
||
output_dir = Path(output_dir)
|
||
if not output_dir.exists():
|
||
output_dir.mkdir()
|
||
nlp.to_disk(output_dir)
|
||
print("Saved model to", output_dir)
|
||
|
||
# test the saved model
|
||
print("Loading from", output_dir)
|
||
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])
|
||
|
||
|
||
if __name__ == "__main__":
|
||
plac.call(main)
|
||
|
||
# Expected output:
|
||
# Entities [('Shaka Khan', 'PERSON')]
|
||
# Tokens [('Who', '', 2), ('is', '', 2), ('Shaka', 'PERSON', 3),
|
||
# ('Khan', 'PERSON', 1), ('?', '', 2)]
|
||
# Entities [('London', 'LOC'), ('Berlin', 'LOC')]
|
||
# Tokens [('I', '', 2), ('like', '', 2), ('London', 'LOC', 3),
|
||
# ('and', '', 2), ('Berlin', 'LOC', 3), ('.', '', 2)]
|