unable to get any entity after training a blank spacy model - machine-learning

Question

I have been working on a legal data to recognize the custom entities within a legal document. I am training empty spacy model on my cleaned training dataset(JSON format as mentioned on spacy documentation). I have tried to remove punctuation, special character, brackets etc from the training dataset. I have labeled the new entity by name 'dictkey' and mentioned the startindex and endindex in it's JSON in order to create the training dataset.
Below is the links for training dataset and the code which i am using. Can you please have a look on the attached training dataset if there is any issue or further cleaning required for this dataset?
https://techmailer.online/TRAIN_DATA3json.txt
https://techmailer.online/train_ner%20-%20Copy.py
from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import spacy
from spacy.util import minibatch, compounding
import re
#import createtrainingdataset_updated_v2 as traindataset
# training data
#TRAIN_DATA = [
# ("Who is Shaka Khan?", {"entities": [(7, 17, "PERSON")]}),
# ("I like London and Berlin.", {"entities": [(7, 13, "LOC"), (18, 24, "LOC")]}),
#]
with open('/Users/modis1/Desktop/24-01/TRAIN_DATA3json.txt', 'r', encoding='utf-8') as openfile:
TRAIN_DATA = openfile.read()
#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='/Users/A-GUPTA50/Desktop/ShubhamModi/NewSavedModel/', 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
pipe_exceptions = ["ner", "trf_wordpiecer", "trf_tok2vec"]
other_pipes = [pipe for pipe in nlp.pipe_names if pipe not in pipe_exceptions]
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:
texts, annotations = zip(*batch)
nlp.update(
texts, # batch of texts
annotations, # batch of annotations
drop=0.5, # dropout - make it harder to memorise data
losses=losses,
)
print("Losses", losses)
# test the trained model
for text, _ in TRAIN_DATA:
# text = re.sub(r'\\u\d{4,}','', text.rstrip())
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)