{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask.dataframe as dd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                               image  label\n",
      "0  {'bytes': b'\\xff\\xd8\\xff\\xe0\\x00\\x10JFIF\\x00\\x...      0\n",
      "1  {'bytes': b'\\xff\\xd8\\xff\\xe0\\x00\\x10JFIF\\x00\\x...      0\n",
      "2  {'bytes': b'\\xff\\xd8\\xff\\xe0\\x00\\x10JFIF\\x00\\x...      0\n",
      "3  {'bytes': b'\\xff\\xd8\\xff\\xe0\\x00\\x10JFIF\\x00\\x...      0\n",
      "4  {'bytes': b'\\xff\\xd8\\xff\\xe0\\x00\\x10JFIF\\x00\\x...      0\n"
     ]
    }
   ],
   "source": [
    "df = dd.read_parquet(\"hf://datasets/edwinpalegre/trashnet_enhanced/data/train-*.parquet\")\n",
    "\n",
    "print(df.show())"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}