spaCy/examples/training/textcat_example_data/textcatjsonl_to_trainjson.py

from pathlib import Path
import plac
import spacy
from spacy.gold import docs_to_json
import srsly
import sys


@plac.annotations(
    model=("Model name. Defaults to 'en'.", "option", "m", str),
    input_file=("Input file (jsonl)", "positional", None, Path),
    output_dir=("Output directory", "positional", None, Path),
    n_texts=("Number of texts to convert", "option", "t", int),
)
def convert(model="en", input_file=None, output_dir=None, n_texts=0):
    # Load model with tokenizer + sentencizer only
    nlp = spacy.load(model)
    nlp.select_pipes(disable=nlp.pipe_names)
    sentencizer = nlp.create_pipe("sentencizer")
    nlp.add_pipe(sentencizer, first=True)

    texts = []
    cats = []
    count = 0

    if not input_file.exists():
        print("Input file not found:", input_file)
        sys.exit(1)
    else:
        with open(input_file) as fileh:
            for line in fileh:
                data = srsly.json_loads(line)
                texts.append(data["text"])
                cats.append(data["cats"])

    if output_dir is not None:
        output_dir = Path(output_dir)
        if not output_dir.exists():
            output_dir.mkdir()
    else:
        output_dir = Path(".")

    docs = []
    for i, doc in enumerate(nlp.pipe(texts)):
        doc.cats = cats[i]
        docs.append(doc)
        if n_texts > 0 and count == n_texts:
            break
        count += 1

    srsly.write_json(output_dir / input_file.with_suffix(".json"), [docs_to_json(docs)])


if __name__ == "__main__":
    plac.call(convert)