spacy_ner_custom_entities.py

#!/usr/bin/env python
# coding: utf8

# Training additional entity types using spaCy
from __future__ import unicode_literals, print_function
import pickle
import plac
import random
from pathlib import Path
import spacy
from spacy.util import minibatch, compounding


# New entity labels
# Specify the new entity labels which you want to add here
LABEL = ['I-geo', 'B-geo', 'I-art', 'B-art', 'B-tim', 'B-nat', 'B-eve', 'O', 'I-per', 'I-tim', 'I-nat', 'I-eve', 'B-per', 'I-org', 'B-gpe', 'B-org', 'I-gpe']

"""
geo = Geographical Entity
org = Organization
per = Person
gpe = Geopolitical Entity
tim = Time indicator
art = Artifact
eve = Event
nat = Natural Phenomenon
"""
# Loading training data 
with open ('Data/ner_corpus_260', 'rb') as fp:
    TRAIN_DATA = pickle.load(fp)

@plac.annotations(
    model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
    new_model_name=("New model name for model meta.", "option", "nm", str),
    output_dir=("Optional output directory", "option", "o", Path),
    n_iter=("Number of training iterations", "option", "n", int))

def main(model=None, new_model_name='new_model', output_dir=None, n_iter=10):
    """Setting up the pipeline and entity recognizer, and training the new entity."""
    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")
    if 'ner' not in nlp.pipe_names:
        ner = nlp.create_pipe('ner')
        nlp.add_pipe(ner)
    else:
        ner = nlp.get_pipe('ner')

    for i in LABEL:
        ner.add_label(i)   # Add new entity labels to entity recognizer

    if model is None:
        optimizer = nlp.begin_training()
    else:
        optimizer = nlp.entity.create_optimizer()

    # Get names of other pipes to disable them during training to train only NER
    other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'ner']
    with nlp.disable_pipes(*other_pipes):  # only train NER
        for itn in range(n_iter):
            random.shuffle(TRAIN_DATA)
            losses = {}
            batches = minibatch(TRAIN_DATA, size=compounding(4., 32., 1.001))
            for batch in batches:
                texts, annotations = zip(*batch)
                nlp.update(texts, annotations, sgd=optimizer, drop=0.35,
                           losses=losses)
            print('Losses', losses)

    # Test the trained model
    test_text = 'Gianni Infantino is the president of FIFA.'
    doc = nlp(test_text)
    print("Entities in '%s'" % test_text)
    for ent in doc.ents:
        print(ent.label_, ent.text)

    # Save model 
    if output_dir is not None:
        output_dir = Path(output_dir)
        if not output_dir.exists():
            output_dir.mkdir()
        nlp.meta['name'] = new_model_name  # rename model
        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)
        doc2 = nlp2(test_text)
        for ent in doc2.ents:
            print(ent.label_, ent.text)


if __name__ == '__main__':
    plac.call(main)

hi,
while running this code I am getting error as- 'KeyError: "[E022] Could not find a transition with the name 'U-Tag' in the NER model."'
Could you please let me know solution for this or what could be the problem for this error. I have followed your steps for creating the training dataset. I am using the same dataset as yours.
Thank you.

Hi @mgrove6,
You will have to include all the labels that you are using to train your dataset in the LABEL field (Line 16) in your code. The error is basically trying to say that you have trained your model with a label that is not a valid custom label. To make the label (U-Tag) a valid one, include the same to the LABEL list as is in line 16 in the above code.

Hi, I was able to fix this. I added
ner.add_label("Tag")

@ line 51