{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "file_path='https://raw.githubusercontent.com/aaubs/ds-master/main/apps/M1-attrition-streamlit/HR-Employee-Attrition-synth.csv'\n",
    "\n",
    "data=pd.read_csv(file_path)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 2000 entries, 0 to 1999\n",
      "Data columns (total 36 columns):\n",
      " #   Column                    Non-Null Count  Dtype \n",
      "---  ------                    --------------  ----- \n",
      " 0   Unnamed: 0                2000 non-null   int64 \n",
      " 1   Age                       2000 non-null   int64 \n",
      " 2   Attrition                 2000 non-null   object\n",
      " 3   BusinessTravel            2000 non-null   object\n",
      " 4   DailyRate                 2000 non-null   int64 \n",
      " 5   Department                2000 non-null   object\n",
      " 6   DistanceFromHome          2000 non-null   int64 \n",
      " 7   Education                 2000 non-null   int64 \n",
      " 8   EducationField            2000 non-null   object\n",
      " 9   EmployeeCount             2000 non-null   int64 \n",
      " 10  EmployeeNumber            2000 non-null   int64 \n",
      " 11  EnvironmentSatisfaction   2000 non-null   int64 \n",
      " 12  Gender                    2000 non-null   object\n",
      " 13  HourlyRate                2000 non-null   int64 \n",
      " 14  JobInvolvement            2000 non-null   int64 \n",
      " 15  JobLevel                  2000 non-null   int64 \n",
      " 16  JobRole                   2000 non-null   object\n",
      " 17  JobSatisfaction           2000 non-null   int64 \n",
      " 18  MaritalStatus             2000 non-null   object\n",
      " 19  MonthlyIncome             2000 non-null   int64 \n",
      " 20  MonthlyRate               2000 non-null   int64 \n",
      " 21  NumCompaniesWorked        2000 non-null   int64 \n",
      " 22  Over18                    2000 non-null   object\n",
      " 23  OverTime                  2000 non-null   object\n",
      " 24  PercentSalaryHike         2000 non-null   int64 \n",
      " 25  PerformanceRating         2000 non-null   int64 \n",
      " 26  RelationshipSatisfaction  2000 non-null   int64 \n",
      " 27  StandardHours             2000 non-null   int64 \n",
      " 28  StockOptionLevel          2000 non-null   int64 \n",
      " 29  TotalWorkingYears         2000 non-null   int64 \n",
      " 30  TrainingTimesLastYear     2000 non-null   int64 \n",
      " 31  WorkLifeBalance           2000 non-null   int64 \n",
      " 32  YearsAtCompany            2000 non-null   int64 \n",
      " 33  YearsInCurrentRole        2000 non-null   int64 \n",
      " 34  YearsSinceLastPromotion   2000 non-null   int64 \n",
      " 35  YearsWithCurrManager      2000 non-null   int64 \n",
      "dtypes: int64(27), object(9)\n",
      "memory usage: 562.6+ KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Attrition\n",
       "No     8033.23208\n",
       "Yes    8676.02349\n",
       "Name: MonthlyIncome, dtype: float64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.groupby('Attrition')['MonthlyIncome'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Attrition  Department            \n",
       "No         Human Resources           8212.311828\n",
       "           Research & Development    8018.842391\n",
       "           Sales                     8028.274311\n",
       "Yes        Human Resources           7557.600000\n",
       "           Research & Development    8908.348315\n",
       "           Sales                     8401.754545\n",
       "Name: MonthlyIncome, dtype: float64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.groupby(['Attrition','Department'])['MonthlyIncome'].mean()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}