convert Reuters dataset on kaggle to json file

reuters-json.py

import logging
import os
import sys
import json
from typing import Dict, Optional
from tqdm.auto import tqdm
import timeit
import numpy as np
test = []
train = []
with open("cats.txt") as f:
    content = f.readlines()

    for line in tqdm(content):
        line = line.replace("\n","")
        line = line.split(" ")
        file = line[0]
        labels = line[1:]

        with open(file, encoding="utf8", errors='ignore') as f:
            data = f.read().replace('\n', '')
            if 'test' in file:
                test.append({"text" : data, "labels" : labels})

            elif 'train' in file:
                train.append({"text" : data, "labels" : labels})

            else:
                print("invalid file ", file)

with open('test.json', 'w') as outFile:
    for d in test:
        outFile.write(json.dumps(d))
        outFile.write('\n')

with open('train.json', 'w') as outFile:
    for d in train:
        outFile.write(json.dumps(d))
        outFile.write('\n')