{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c8dca847-54af-4284-97d8-0682e88a6e8d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting default log level to \"WARN\".\n",
      "To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
      "23/10/27 01:41:45 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n"
     ]
    }
   ],
   "source": [
    "from pyspark.sql import SparkSession\n",
    "spark = (SparkSession.builder.appName(\"cs544\")\n",
    "         .master(\"spark://boss:7077\")\n",
    "         .config(\"spark.executor.memory\", \"2G\")\n",
    "         .config(\"spark.sql.warehouse.dir\", \"hdfs://nn:9000/user/hive/warehouse\")\n",
    "         .enableHiveSupport()\n",
    "         .getOrCreate())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "2294e4e0-ab19-496c-980f-31df757e7837",
   "metadata": {},
   "outputs": [],
   "source": [
    "!hdfs dfs -cp sf.csv hdfs://nn:9000/sf.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "cb54bacc-b52a-4c25-93d2-2ba0f61de9b0",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                \r"
     ]
    }
   ],
   "source": [
    "df = (spark.read.format(\"csv\")\n",
    "      .option(\"header\", True)\n",
    "      .option(\"inferSchema\", True)\n",
    "      .load(\"hdfs://nn:9000/sf.csv\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c1298818-83f6-444b-b8a0-4be5b16fd6fb",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "23/10/27 01:43:57 WARN SparkStringUtils: Truncated the string representation of a plan since it was too large. This behavior can be adjusted by setting 'spark.sql.debug.maxToStringFields'.\n",
      "                                                                                \r"
     ]
    }
   ],
   "source": [
    "from pyspark.sql.functions import col, expr\n",
    "cols = [col(c).alias(c.replace(\" \", \"_\")) for c in df.columns]\n",
    "df.select(cols).write.format(\"parquet\").save(\"hdfs://nn:9000/sf.parquet\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "37d1ded3-ed8a-4e39-94cb-dd3a3272af91",
   "metadata": {},
   "outputs": [],
   "source": [
    "!hdfs dfs -rm hdfs://nn:9000/sf.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "abea48b5-e012-4ae2-a53a-e40350f94e20",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = spark.read.format(\"parquet\").load(\"hdfs://nn:9000/sf.parquet\")"
   ]
  }
 ],
 "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}