save_oscar.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stderr",
     "text": [
      "100%|██████████| 28522082/28522082 [33:32<00:00, 14173.48it/s]\n"
     ]
    }
   ],
   "source": [
    "from tqdm.auto import tqdm\n",
    "\n",
    "text_data = []\n",
    "file_count = 0\n",
    "\n",
    "for sample in tqdm(dataset['train']):\n",
    "    sample = sample['text'].replace('\\n', '')\n",
    "    text_data.append(sample)\n",
    "    if len(text_data) == 10_000:\n",
    "        # once we git the 10K mark, save to file\n",
    "        with open(f'../../data/text/oscar_it/text_{file_count}.txt', 'w', encoding='utf-8') as fp:\n",
    "            fp.write('\\n'.join(text_data))\n",
    "        text_data = []\n",
    "        file_count += 1\n",
    "# after saving in 10K chunks, we will have ~2082 leftover samples, we save those now too\n",
    "with open(f'../../data/text/oscar_it/text_{file_count}.txt', 'w', encoding='utf-8') as fp:\n",
    "    fp.write('\\n'.join(text_data))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "ML",
   "language": "python",
   "name": "ml"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}