{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "e3cf6fb7-e4e7-4cd7-baa7-03209328631c",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark.sql import SparkSession\n",
    "import pyspark.sql.functions as F\n",
    "\n",
    "spark = SparkSession.builder.appName(\"some_name\").getOrCreate()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f0f1fb08-2373-48b2-99d9-1424a4ceb0c0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+---------+\n",
      "|log_level|\n",
      "+---------+\n",
      "|INFO     |\n",
      "|DEBUG    |\n",
      "|ERROR    |\n",
      "|INFO     |\n",
      "|ERROR    |\n",
      "|DEBUG    |\n",
      "|ERROR    |\n",
      "+---------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "parts = F.split(F.col(\"value\"), \" \", 2)\n",
    "df_logs = spark.read.text(\"logs.txt\").select(parts[0].alias(\"log_level\"))\n",
    "df_logs.show(truncate=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "6d784b52-9369-4051-8084-a7f705c001fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_error_logs = df_logs.filter(F.col(\"log_level\") == \"ERROR\").count()\n",
    "count_error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "592dc010-5700-4cc1-b0bf-8738c3b1567e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.42857142857142855"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "total = df_logs.count()\n",
    "count_error / total"
   ]
  }
 ],
 "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
}