mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-15 22:27:12 +03:00
e48a09df4e
* OrigAnnot class instead of gold.orig_annot list of zipped tuples * from_orig to replace from_annot_tuples * rename to RawAnnot * some unit tests for GoldParse creation and internal format * removing orig_annot and switching to lists instead of tuple * rewriting tuples to use RawAnnot (+ debug statements, WIP) * fix pop() changing the data * small fixes * pop-append fixes * return RawAnnot for existing GoldParse to have uniform interface * clean up imports * fix merge_sents * add unit test for 4402 with new structure (not working yet) * introduce DocAnnot * typo fixes * add unit test for merge_sents * rename from_orig to from_raw * fixing unit tests * fix nn parser * read_annots to produce text, doc_annot pairs * _make_golds fix * rename golds_to_gold_annots * small fixes * fix encoding * have golds_to_gold_annots use DocAnnot * missed a spot * merge_sents as function in DocAnnot * allow specifying only part of the token-level annotations * refactor with Example class + underlying dicts * pipeline components to work with Example objects (wip) * input checking * fix yielding * fix calls to update * small fixes * fix scorer unit test with new format * fix kwargs order * fixes for ud and conllu scripts * fix reading data for conllu script * add in proper errors (not fixed numbering yet to avoid merge conflicts) * fixing few more small bugs * fix EL script
110 lines
3.8 KiB
Python
110 lines
3.8 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: v2.1.0
|
|
"""
|
|
from __future__ import unicode_literals, print_function
|
|
|
|
import plac
|
|
import random
|
|
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 "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")
|
|
|
|
# add labels
|
|
for _, annotations in TRAIN_DATA:
|
|
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"]
|
|
with nlp.disable_pipes(*other_pipes): # only train NER
|
|
# reset and initialize the weights randomly – but only if we're
|
|
# training a new model
|
|
if model is None:
|
|
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(4.0, 32.0, 1.001))
|
|
for batch in batches:
|
|
nlp.update(
|
|
batch,
|
|
drop=0.5, # 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)]
|