spacy_train.py

from __future__ import unicode_literals, print_function

import plac
import random
from pathlib import Path
import spacy
#from spacy.gold import GoldParse
#from spacy.language import EntityRecognizer
#from spacy.util import minibatch, compounding

############################################  NOTE  ########################################################
#
#           Creates NER training data in Spacy format from JSON downloaded from Dataturks.
#
#           Outputs the Spacy training data which can be used for Spacy training.
#
############################################################################################################
import json
def convert_dataturks_to_spacy(dataturks_JSON_FilePath):
    try:
        training_data = []
        lines=[]
        with open(dataturks_JSON_FilePath, 'r') as f:
            lines = f.readlines()
            

        for line in lines:
            data = json.loads(line)
            
            text = data['content']
            entities = []
            for annotation in data['annotation']:
                #only a single point in text annotation.
                point = annotation['points'][0]
                labels = annotation['label']
                # handle both list of labels or a single label.
                if not isinstance(labels, list):
                    labels = [labels]

                for label in labels:
                    #dataturks indices are both inclusive [start, end] but spacy is not [start, end)
                    entities.append((point['start'], point['end'] + 1 ,label))


            training_data.append((text, {"entities" : entities}))

        return training_data
    except Exception as e:
        return e
    


@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='', n_iter=100):
    #If you want to train existing change None to model path 
    #Path of your annotated file 
    
    TRAIN_DATA = convert_dataturks_to_spacy(""); 
    """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 = {}
            for text, annotations in TRAIN_DATA:
                nlp.update(
                    [text],  # batch of texts
                    [annotations],  # batch of annotations
                    drop=0.35,  # 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)