spaCy/examples/training/train_ner.py

116 lines
4.0 KiB
Python
Raw Normal View History

#!/usr/bin/env python
# coding: utf8
2017-10-31 23:43:22 +00:00
"""Example of training spaCy's named entity recognizer, starting off with an
existing model or a blank model.
For more details, see the documentation:
2017-11-07 11:00:43 +00:00
* Training: https://spacy.io/usage/training
* NER: https://spacy.io/usage/linguistic-features#named-entities
2017-11-07 00:22:30 +00:00
Compatible with: spaCy v2.0.0+
Last tested with: v2.2.4
"""
from __future__ import unicode_literals, print_function
2017-10-26 14:10:56 +00:00
import plac
import random
import warnings
from pathlib import Path
import spacy
from spacy.util import minibatch, compounding
2017-01-27 11:27:10 +00:00
# training data
TRAIN_DATA = [
2018-12-17 12:44:38 +00:00
("Who is Shaka Khan?", {"entities": [(7, 17, "PERSON")]}),
("I like London and Berlin.", {"entities": [(7, 13, "LOC"), (18, 24, "LOC")]}),
]
2017-10-26 14:10:56 +00:00
@plac.annotations(
model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
output_dir=("Optional output directory", "option", "o", Path),
2018-12-17 12:44:38 +00:00
n_iter=("Number of training iterations", "option", "n", int),
)
def main(model=None, output_dir=None, n_iter=100):
2017-10-26 14:10:56 +00:00
"""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:
2018-12-17 12:44:38 +00:00
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
2017-10-26 13:15:08 +00:00
# nlp.create_pipe works for built-ins that are registered with spaCy
Adapt parser and NER for transformers (#5449) * Draft layer for BILUO actions * Fixes to biluo layer * WIP on BILUO layer * Add tests for BILUO layer * Format * Fix transitions * Update test * Link in the simple_ner * Update BILUO tagger * Update __init__ * Import simple_ner * Update test * Import * Add files * Add config * Fix label passing for BILUO and tagger * Fix label handling for simple_ner component * Update simple NER test * Update config * Hack train script * Update BILUO layer * Fix SimpleNER component * Update train_from_config * Add biluo_to_iob helper * Add IOB layer * Add IOBTagger model * Update biluo layer * Update SimpleNER tagger * Update BILUO * Read random seed in train-from-config * Update use of normal_init * Fix normalization of gradient in SimpleNER * Update IOBTagger * Remove print * Tweak masking in BILUO * Add dropout in SimpleNER * Update thinc * Tidy up simple_ner * Fix biluo model * Unhack train-from-config * Update setup.cfg and requirements * Add tb_framework.py for parser model * Try to avoid memory leak in BILUO * Move ParserModel into spacy.ml, avoid need for subclass. * Use updated parser model * Remove incorrect call to model.initializre in PrecomputableAffine * Update parser model * Avoid divide by zero in tagger * Add extra dropout layer in tagger * Refine minibatch_by_words function to avoid oom * Fix parser model after refactor * Try to avoid div-by-zero in SimpleNER * Fix infinite loop in minibatch_by_words * Use SequenceCategoricalCrossentropy in Tagger * Fix parser model when hidden layer * Remove extra dropout from tagger * Add extra nan check in tagger * Fix thinc version * Update tests and imports * Fix test * Update test * Update tests * Fix tests * Fix test Co-authored-by: Ines Montani <ines@ines.io>
2020-05-18 20:23:33 +00:00
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:
Adapt parser and NER for transformers (#5449) * Draft layer for BILUO actions * Fixes to biluo layer * WIP on BILUO layer * Add tests for BILUO layer * Format * Fix transitions * Update test * Link in the simple_ner * Update BILUO tagger * Update __init__ * Import simple_ner * Update test * Import * Add files * Add config * Fix label passing for BILUO and tagger * Fix label handling for simple_ner component * Update simple NER test * Update config * Hack train script * Update BILUO layer * Fix SimpleNER component * Update train_from_config * Add biluo_to_iob helper * Add IOB layer * Add IOBTagger model * Update biluo layer * Update SimpleNER tagger * Update BILUO * Read random seed in train-from-config * Update use of normal_init * Fix normalization of gradient in SimpleNER * Update IOBTagger * Remove print * Tweak masking in BILUO * Add dropout in SimpleNER * Update thinc * Tidy up simple_ner * Fix biluo model * Unhack train-from-config * Update setup.cfg and requirements * Add tb_framework.py for parser model * Try to avoid memory leak in BILUO * Move ParserModel into spacy.ml, avoid need for subclass. * Use updated parser model * Remove incorrect call to model.initializre in PrecomputableAffine * Update parser model * Avoid divide by zero in tagger * Add extra dropout layer in tagger * Refine minibatch_by_words function to avoid oom * Fix parser model after refactor * Try to avoid div-by-zero in SimpleNER * Fix infinite loop in minibatch_by_words * Use SequenceCategoricalCrossentropy in Tagger * Fix parser model when hidden layer * Remove extra dropout from tagger * Add extra nan check in tagger * Fix thinc version * Update tests and imports * Fix test * Update test * Update tests * Fix tests * Fix test Co-authored-by: Ines Montani <ines@ines.io>
2020-05-18 20:23:33 +00:00
ner = nlp.get_pipe("simple_ner")
# add labels
for _, annotations in TRAIN_DATA:
2018-12-17 12:44:38 +00:00
for ent in annotations.get("entities"):
Adapt parser and NER for transformers (#5449) * Draft layer for BILUO actions * Fixes to biluo layer * WIP on BILUO layer * Add tests for BILUO layer * Format * Fix transitions * Update test * Link in the simple_ner * Update BILUO tagger * Update __init__ * Import simple_ner * Update test * Import * Add files * Add config * Fix label passing for BILUO and tagger * Fix label handling for simple_ner component * Update simple NER test * Update config * Hack train script * Update BILUO layer * Fix SimpleNER component * Update train_from_config * Add biluo_to_iob helper * Add IOB layer * Add IOBTagger model * Update biluo layer * Update SimpleNER tagger * Update BILUO * Read random seed in train-from-config * Update use of normal_init * Fix normalization of gradient in SimpleNER * Update IOBTagger * Remove print * Tweak masking in BILUO * Add dropout in SimpleNER * Update thinc * Tidy up simple_ner * Fix biluo model * Unhack train-from-config * Update setup.cfg and requirements * Add tb_framework.py for parser model * Try to avoid memory leak in BILUO * Move ParserModel into spacy.ml, avoid need for subclass. * Use updated parser model * Remove incorrect call to model.initializre in PrecomputableAffine * Update parser model * Avoid divide by zero in tagger * Add extra dropout layer in tagger * Refine minibatch_by_words function to avoid oom * Fix parser model after refactor * Try to avoid div-by-zero in SimpleNER * Fix infinite loop in minibatch_by_words * Use SequenceCategoricalCrossentropy in Tagger * Fix parser model when hidden layer * Remove extra dropout from tagger * Add extra nan check in tagger * Fix thinc version * Update tests and imports * Fix test * Update test * Update tests * Fix tests * Fix test Co-authored-by: Ines Montani <ines@ines.io>
2020-05-18 20:23:33 +00:00
print("Add label", ent[2])
ner.add_label(ent[2])
with nlp.select_pipes(enable="simple_ner") and warnings.catch_warnings():
# show warnings for misaligned entity spans once
2020-05-21 16:39:06 +00:00
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()
2020-05-21 16:39:06 +00:00
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
2018-12-17 12:44:38 +00:00
batches = minibatch(TRAIN_DATA, size=compounding(4.0, 32.0, 1.001))
for batch in batches:
nlp.update(
batch,
Adapt parser and NER for transformers (#5449) * Draft layer for BILUO actions * Fixes to biluo layer * WIP on BILUO layer * Add tests for BILUO layer * Format * Fix transitions * Update test * Link in the simple_ner * Update BILUO tagger * Update __init__ * Import simple_ner * Update test * Import * Add files * Add config * Fix label passing for BILUO and tagger * Fix label handling for simple_ner component * Update simple NER test * Update config * Hack train script * Update BILUO layer * Fix SimpleNER component * Update train_from_config * Add biluo_to_iob helper * Add IOB layer * Add IOBTagger model * Update biluo layer * Update SimpleNER tagger * Update BILUO * Read random seed in train-from-config * Update use of normal_init * Fix normalization of gradient in SimpleNER * Update IOBTagger * Remove print * Tweak masking in BILUO * Add dropout in SimpleNER * Update thinc * Tidy up simple_ner * Fix biluo model * Unhack train-from-config * Update setup.cfg and requirements * Add tb_framework.py for parser model * Try to avoid memory leak in BILUO * Move ParserModel into spacy.ml, avoid need for subclass. * Use updated parser model * Remove incorrect call to model.initializre in PrecomputableAffine * Update parser model * Avoid divide by zero in tagger * Add extra dropout layer in tagger * Refine minibatch_by_words function to avoid oom * Fix parser model after refactor * Try to avoid div-by-zero in SimpleNER * Fix infinite loop in minibatch_by_words * Use SequenceCategoricalCrossentropy in Tagger * Fix parser model when hidden layer * Remove extra dropout from tagger * Add extra nan check in tagger * Fix thinc version * Update tests and imports * Fix test * Update test * Update tests * Fix tests * Fix test Co-authored-by: Ines Montani <ines@ines.io>
2020-05-18 20:23:33 +00:00
drop=0.0, # dropout - make it harder to memorise data
2018-12-17 12:44:38 +00:00
losses=losses,
)
print("Losses", losses)
# test the trained model
for text, _ in TRAIN_DATA:
doc = nlp(text)
2018-12-17 12:44:38 +00:00
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)
2017-10-26 13:15:08 +00:00
nlp2 = spacy.load(output_dir)
for text, _ in TRAIN_DATA:
2017-10-26 13:15:08 +00:00
doc = nlp2(text)
2018-12-17 12:44:38 +00:00
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])
2018-12-17 12:44:38 +00:00
if __name__ == "__main__":
2017-05-31 11:42:12 +00:00
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)]