{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "9fdccc99-04bd-4d5b-b632-101b669ffb7e",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "import pandas as pd\n",
    "import pyarrow as pa\n",
    "import pyarrow.parquet as pq\n",
    "import pyarrow.dataset as ds\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "a10bff4c-f5f6-4102-8151-2c4020b9d2d6",
   "metadata": {},
   "outputs": [],
   "source": [
    "n = 10000\n",
    "df = ds.dataset('data/').scanner().head(n).to_pandas()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "b07c097e-6857-4fad-900a-a9643fb5dc9d",
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(n):\n",
    "    row = df.iloc[i]\n",
    "    with open(f'corpus/{i}.jpg', 'wb') as f:\n",
    "        f.write(row.image['bytes'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "2080bb6f-44df-4b45-8bc2-308105b89e09",
   "metadata": {},
   "outputs": [],
   "source": [
    "artists = {\n",
    "    i: int(df.iloc[i].artist) for i in range(n)\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "e91afe69-1722-426f-862e-b3ce98207d35",
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "with open(f'artists.js', 'w') as f:\n",
    "    f.write('var artists = ' + json.dumps(artists))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f44450c8-30c5-4fc1-90a8-53e33b94ee65",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "649daac5-2a2c-4af2-8120-e5b80838bd9b",
   "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}