{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "os.chdir(\"D:\\ml_project\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gender</th>\n",
       "      <th>race_ethnicity</th>\n",
       "      <th>parental_level_of_education</th>\n",
       "      <th>lunch</th>\n",
       "      <th>test_preparation_course</th>\n",
       "      <th>math_score</th>\n",
       "      <th>reading_score</th>\n",
       "      <th>writing_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>female</td>\n",
       "      <td>group B</td>\n",
       "      <td>bachelor's degree</td>\n",
       "      <td>standard</td>\n",
       "      <td>none</td>\n",
       "      <td>72</td>\n",
       "      <td>72</td>\n",
       "      <td>74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>female</td>\n",
       "      <td>group C</td>\n",
       "      <td>some college</td>\n",
       "      <td>standard</td>\n",
       "      <td>completed</td>\n",
       "      <td>69</td>\n",
       "      <td>90</td>\n",
       "      <td>88</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>female</td>\n",
       "      <td>group B</td>\n",
       "      <td>master's degree</td>\n",
       "      <td>standard</td>\n",
       "      <td>none</td>\n",
       "      <td>90</td>\n",
       "      <td>95</td>\n",
       "      <td>93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>male</td>\n",
       "      <td>group A</td>\n",
       "      <td>associate's degree</td>\n",
       "      <td>free/reduced</td>\n",
       "      <td>none</td>\n",
       "      <td>47</td>\n",
       "      <td>57</td>\n",
       "      <td>44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>male</td>\n",
       "      <td>group C</td>\n",
       "      <td>some college</td>\n",
       "      <td>standard</td>\n",
       "      <td>none</td>\n",
       "      <td>76</td>\n",
       "      <td>78</td>\n",
       "      <td>75</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender race_ethnicity parental_level_of_education         lunch  \\\n",
       "0  female        group B           bachelor's degree      standard   \n",
       "1  female        group C                some college      standard   \n",
       "2  female        group B             master's degree      standard   \n",
       "3    male        group A          associate's degree  free/reduced   \n",
       "4    male        group C                some college      standard   \n",
       "\n",
       "  test_preparation_course  math_score  reading_score  writing_score  \n",
       "0                    none          72             72             74  \n",
       "1               completed          69             90             88  \n",
       "2                    none          90             95             93  \n",
       "3                    none          47             57             44  \n",
       "4                    none          76             78             75  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df  = pd.read_csv(\"data.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>math_score</th>\n",
       "      <th>reading_score</th>\n",
       "      <th>writing_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1000.00000</td>\n",
       "      <td>1000.000000</td>\n",
       "      <td>1000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>66.08900</td>\n",
       "      <td>69.169000</td>\n",
       "      <td>68.054000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>15.16308</td>\n",
       "      <td>14.600192</td>\n",
       "      <td>15.195657</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.00000</td>\n",
       "      <td>17.000000</td>\n",
       "      <td>10.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>57.00000</td>\n",
       "      <td>59.000000</td>\n",
       "      <td>57.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>66.00000</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>69.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>77.00000</td>\n",
       "      <td>79.000000</td>\n",
       "      <td>79.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>100.00000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       math_score  reading_score  writing_score\n",
       "count  1000.00000    1000.000000    1000.000000\n",
       "mean     66.08900      69.169000      68.054000\n",
       "std      15.16308      14.600192      15.195657\n",
       "min       0.00000      17.000000      10.000000\n",
       "25%      57.00000      59.000000      57.750000\n",
       "50%      66.00000      70.000000      69.000000\n",
       "75%      77.00000      79.000000      79.000000\n",
       "max     100.00000     100.000000     100.000000"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 1000 entries, 0 to 999\n",
      "Data columns (total 8 columns):\n",
      " #   Column                       Non-Null Count  Dtype \n",
      "---  ------                       --------------  ----- \n",
      " 0   gender                       1000 non-null   object\n",
      " 1   race_ethnicity               1000 non-null   object\n",
      " 2   parental_level_of_education  1000 non-null   object\n",
      " 3   lunch                        1000 non-null   object\n",
      " 4   test_preparation_course      1000 non-null   object\n",
      " 5   math_score                   1000 non-null   int64 \n",
      " 6   reading_score                1000 non-null   int64 \n",
      " 7   writing_score                1000 non-null   int64 \n",
      "dtypes: int64(3), object(5)\n",
      "memory usage: 62.6+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.9.7"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}