{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "53b1885e-2dff-41ec-9a50-3f1bba298349",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark.sql import SparkSession, functions as F\n",
    "\n",
    "spark = SparkSession.builder.appName(\"some_name\").getOrCreate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "61b1708d-9227-4200-afce-be808286e6b4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+------------------------------------------------+\n",
      "|message                                         |\n",
      "+------------------------------------------------+\n",
      "|Database connection failed                      |\n",
      "|Timeout while waiting for response response user|\n",
      "|NullPointerException                            |\n",
      "+------------------------------------------------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df = spark.read.text(\"logs.txt\")\n",
    "\n",
    "errors_df = df.filter(F.col(\"value\").startswith(\"ERROR \"))\n",
    "\n",
    "parts = F.split(F.col(\"value\"), \" \", 4)\n",
    "messages_df = errors_df.select(parts[3].alias(\"message\"))\n",
    "\n",
    "messages_df.show(truncate=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "0ee49042-a0d8-4f2a-b9bf-9818dad3c61f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+------------------------------------------------+\n",
      "|message                                         |\n",
      "+------------------------------------------------+\n",
      "|database connection failed                      |\n",
      "|timeout while waiting for response response user|\n",
      "|nullpointerexception                            |\n",
      "+------------------------------------------------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "lower_messages_df = messages_df.select(F.lower(F.col(\"message\")).alias(\"message\"))\n",
    "lower_messages_df.show(truncate=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "ed957bf8-6ba2-452c-85d7-28162452ed2b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+------------------------------------------------+---------------+\n",
      "|message                                         |user_in_message|\n",
      "+------------------------------------------------+---------------+\n",
      "|database connection failed                      |false          |\n",
      "|timeout while waiting for response response user|true           |\n",
      "|nullpointerexception                            |false          |\n",
      "+------------------------------------------------+---------------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "lower_messages_df = lower_messages_df.withColumn(\"user_in_message\", F.col(\"message\").contains(\"user\"))\n",
    "lower_messages_df.show(truncate=False)"
   ]
  }
 ],
 "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
}