{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a1d65d37-6a53-4473-beae-4c7d8a2ea3fa",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import ray\n",
    "import pyarrow as pa\n",
    "\n",
    "ray.shutdown()\n",
    "ray.init(address=\"ray://localhost:10001\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "390b8312-fbd8-462f-9534-dd48e5173447",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def cast(t: pa.Table) -> pa.Table: # work around for large_string issue with PyArrow\n",
    "    schema = t.schema\n",
    "    field_idx = schema.get_field_index(\"review_body\")\n",
    "    field = schema.field(field_idx)\n",
    "    new_field = field.with_type(pa.large_string())\n",
    "    new_schema = schema.set(field_idx, new_field)\n",
    "    return t.cast(new_schema)\n",
    "\n",
    "ds = ray.data.read_parquet(\"s3://amazon-reviews-pds/parquet/product_category=Digital_Software/\", _block_udf=cast)\n",
    "\n",
    "ds.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "406497ed-8b99-4bea-bde7-cbd32cfe5414",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}