{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7399a5ed-aea8-45cf-866f-2decd7097456",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from pyspark.sql import SparkSession\n",
    "spark = SparkSession.builder.appName(\"demo\").getOrCreate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6c0dfe01-9190-454c-9c52-216f74d339e1",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "df = spark.read.format(\"huggingface\").load(repo_id)\n",
    "df.show(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eec837ab-b3c6-4d4a-bc41-c63855b3af64",
   "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": "3.9.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}