{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "cf148030-7287-4c9e-ae32-8d1e1c47be30",
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import Dataset, DatasetDict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5161b4ba-e8cf-43e1-b67e-503c29aa4271",
   "metadata": {},
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: '/home/yeb/grouped_dataset/dataset_dict.json'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m/tmp/ipykernel_574434/3668239933.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdatasets\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mDatasetDict\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload_from_disk\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"/home/yeb/grouped_dataset\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/datasets/src/datasets/dataset_dict.py\u001b[0m in \u001b[0;36mload_from_disk\u001b[0;34m(dataset_dict_path, fs, keep_in_memory)\u001b[0m\n\u001b[1;32m    727\u001b[0m                 \u001b[0;34mf\"No such file or directory: '{dataset_dict_json_path}'. Expected to load a DatasetDict object, but got a Dataset. Please use datasets.load_from_disk instead.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    728\u001b[0m             )\n\u001b[0;32m--> 729\u001b[0;31m         \u001b[0;32mfor\u001b[0m \u001b[0mk\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset_dict_json_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"r\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mencoding\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"utf-8\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"splits\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    730\u001b[0m             dataset_dict_split_path = (\n\u001b[1;32m    731\u001b[0m                 \u001b[0mdataset_dict_path\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"://\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m\"://\"\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mPath\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdest_dataset_dict_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mas_posix\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/venv/lib/python3.8/site-packages/fsspec/spec.py\u001b[0m in \u001b[0;36mopen\u001b[0;34m(self, path, mode, block_size, cache_options, **kwargs)\u001b[0m\n\u001b[1;32m    956\u001b[0m             }\n\u001b[1;32m    957\u001b[0m             return io.TextIOWrapper(\n\u001b[0;32m--> 958\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mblock_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mtext_kwargs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    959\u001b[0m             )\n\u001b[1;32m    960\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/venv/lib/python3.8/site-packages/fsspec/spec.py\u001b[0m in \u001b[0;36mopen\u001b[0;34m(self, path, mode, block_size, cache_options, **kwargs)\u001b[0m\n\u001b[1;32m    960\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    961\u001b[0m             \u001b[0mac\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpop\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"autocommit\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_intrans\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 962\u001b[0;31m             f = self._open(\n\u001b[0m\u001b[1;32m    963\u001b[0m                 \u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    964\u001b[0m                 \u001b[0mmode\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/venv/lib/python3.8/site-packages/fsspec/implementations/local.py\u001b[0m in \u001b[0;36m_open\u001b[0;34m(self, path, mode, block_size, **kwargs)\u001b[0m\n\u001b[1;32m    142\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mauto_mkdir\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;34m\"w\"\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    143\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmakedirs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parent\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexist_ok\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 144\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mLocalFileOpener\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    145\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    146\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mtouch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/venv/lib/python3.8/site-packages/fsspec/implementations/local.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, path, mode, autocommit, fs, compression, **kwargs)\u001b[0m\n\u001b[1;32m    233\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompression\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_compression\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcompression\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    234\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mblocksize\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mio\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDEFAULT_BUFFER_SIZE\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 235\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_open\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    236\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    237\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_open\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/venv/lib/python3.8/site-packages/fsspec/implementations/local.py\u001b[0m in \u001b[0;36m_open\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    238\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mf\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclosed\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    239\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mautocommit\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0;34m\"w\"\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 240\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    241\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompression\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    242\u001b[0m                     \u001b[0mcompress\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcompr\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompression\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '/home/yeb/grouped_dataset/dataset_dict.json'"
     ]
    }
   ],
   "source": [
    "datasets = DatasetDict.load_from_disk(\"/home/yeb/grouped_dataset\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "15f9d047-ac35-43d7-ab55-9f9afe96dd07",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatasetDict({\n",
       "    train: Dataset({\n",
       "        features: ['input_ids'],\n",
       "        num_rows: 86438919\n",
       "    })\n",
       "    validation: Dataset({\n",
       "        features: ['input_ids'],\n",
       "        num_rows: 4735324\n",
       "    })\n",
       "})"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d1d1218e-142e-441a-b20d-d300b13b172a",
   "metadata": {},
   "outputs": [],
   "source": [
    "train = datasets['train']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9eaddfb1-242f-4a25-8789-efe97b2a5712",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "8aabb26f-19ca-467a-b383-3a693be70cac",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "86438919\n"
     ]
    }
   ],
   "source": [
    "print(len(train))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f3176986-5b34-4ed6-a643-e342db9a2ce8",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "1205bbef-ba9d-4ddc-af2e-602d56b7dd64",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'input_ids': [256, 3, 20, 18452, 6690, 7757, 1286, 43, 10, 4942, 1286, 80, 12, 4782, 5442, 39, 5385, 33, 4, 5, 3, 2924, 117, 5669, 228, 21, 193, 9030, 511, 24, 11, 5, 665, 165, 4218, 7, 26, 264, 1528, 35, 105, 3, 19653, 12, 9661, 17156, 13955, 4, 132, 5, 611, 959, 961, 146, 6522, 7757, 1286, 89, 7500, 9716, 11, 5, 4868, 107, 13604, 12, 12836, 13368, 11, 611, 959, 4, 3, 69, 99, 12, 13132, 6690, 590, 5, 1803, 1867, 69, 7, 924, 10, 1762, 4, 3, 69, 538, 489, 14, 1149, 16, 3, 11384, 199, 116, 399, 4782, 291, 3, 6, 237, 13, 2629, 3, 8987, 291, 4, 69, 5, 3, 27, 72, 20, 325, 3, 2924, 133, 21, 105, 9030, 10, 1149, 242, 16, 144, 13572, 11, 9, 13401, 20, 7951, 8, 165, 4218, 4, 5, 1910]}\n"
     ]
    }
   ],
   "source": [
    "it = iter(train)\n",
    "\n",
    "print(next(it))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f5d4e8de-419c-4c70-896e-fbd640bb7321",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}