Career Guidance2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4883e48c-fb1f-48d4-a034-8d48f1cb7f86",
   "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>id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>email</th>\n",
       "      <th>gender</th>\n",
       "      <th>part_time_job</th>\n",
       "      <th>absence_days</th>\n",
       "      <th>extracurricular_activities</th>\n",
       "      <th>weekly_self_study_hours</th>\n",
       "      <th>career_aspiration</th>\n",
       "      <th>math_score</th>\n",
       "      <th>history_score</th>\n",
       "      <th>physics_score</th>\n",
       "      <th>chemistry_score</th>\n",
       "      <th>biology_score</th>\n",
       "      <th>english_score</th>\n",
       "      <th>geography_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Paul</td>\n",
       "      <td>Casey</td>\n",
       "      <td>paul.casey.1@gslingacademy.com</td>\n",
       "      <td>male</td>\n",
       "      <td>False</td>\n",
       "      <td>3</td>\n",
       "      <td>False</td>\n",
       "      <td>27</td>\n",
       "      <td>Lawyer</td>\n",
       "      <td>73</td>\n",
       "      <td>81</td>\n",
       "      <td>93</td>\n",
       "      <td>97</td>\n",
       "      <td>63</td>\n",
       "      <td>80</td>\n",
       "      <td>87</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Danielle</td>\n",
       "      <td>Sandoval</td>\n",
       "      <td>danielle.sandoval.2@gslingacademy.com</td>\n",
       "      <td>female</td>\n",
       "      <td>False</td>\n",
       "      <td>2</td>\n",
       "      <td>False</td>\n",
       "      <td>47</td>\n",
       "      <td>Doctor</td>\n",
       "      <td>90</td>\n",
       "      <td>86</td>\n",
       "      <td>96</td>\n",
       "      <td>100</td>\n",
       "      <td>90</td>\n",
       "      <td>88</td>\n",
       "      <td>90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Tina</td>\n",
       "      <td>Andrews</td>\n",
       "      <td>tina.andrews.3@gslingacademy.com</td>\n",
       "      <td>female</td>\n",
       "      <td>False</td>\n",
       "      <td>9</td>\n",
       "      <td>True</td>\n",
       "      <td>13</td>\n",
       "      <td>Government Officer</td>\n",
       "      <td>81</td>\n",
       "      <td>97</td>\n",
       "      <td>95</td>\n",
       "      <td>96</td>\n",
       "      <td>65</td>\n",
       "      <td>77</td>\n",
       "      <td>94</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>Tara</td>\n",
       "      <td>Clark</td>\n",
       "      <td>tara.clark.4@gslingacademy.com</td>\n",
       "      <td>female</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>False</td>\n",
       "      <td>3</td>\n",
       "      <td>Artist</td>\n",
       "      <td>71</td>\n",
       "      <td>74</td>\n",
       "      <td>88</td>\n",
       "      <td>80</td>\n",
       "      <td>89</td>\n",
       "      <td>63</td>\n",
       "      <td>86</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>Anthony</td>\n",
       "      <td>Campos</td>\n",
       "      <td>anthony.campos.5@gslingacademy.com</td>\n",
       "      <td>male</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>False</td>\n",
       "      <td>10</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>84</td>\n",
       "      <td>77</td>\n",
       "      <td>65</td>\n",
       "      <td>65</td>\n",
       "      <td>80</td>\n",
       "      <td>74</td>\n",
       "      <td>76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1995</th>\n",
       "      <td>1996</td>\n",
       "      <td>Alan</td>\n",
       "      <td>Reynolds</td>\n",
       "      <td>alan.reynolds.1996@gslingacademy.com</td>\n",
       "      <td>male</td>\n",
       "      <td>False</td>\n",
       "      <td>2</td>\n",
       "      <td>False</td>\n",
       "      <td>30</td>\n",
       "      <td>Construction Engineer</td>\n",
       "      <td>83</td>\n",
       "      <td>77</td>\n",
       "      <td>84</td>\n",
       "      <td>73</td>\n",
       "      <td>75</td>\n",
       "      <td>84</td>\n",
       "      <td>82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1996</th>\n",
       "      <td>1997</td>\n",
       "      <td>Thomas</td>\n",
       "      <td>Gilbert</td>\n",
       "      <td>thomas.gilbert.1997@gslingacademy.com</td>\n",
       "      <td>male</td>\n",
       "      <td>False</td>\n",
       "      <td>2</td>\n",
       "      <td>False</td>\n",
       "      <td>20</td>\n",
       "      <td>Software Engineer</td>\n",
       "      <td>89</td>\n",
       "      <td>65</td>\n",
       "      <td>73</td>\n",
       "      <td>80</td>\n",
       "      <td>87</td>\n",
       "      <td>67</td>\n",
       "      <td>73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1997</th>\n",
       "      <td>1998</td>\n",
       "      <td>Madison</td>\n",
       "      <td>Cross</td>\n",
       "      <td>madison.cross.1998@gslingacademy.com</td>\n",
       "      <td>female</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>False</td>\n",
       "      <td>14</td>\n",
       "      <td>Software Engineer</td>\n",
       "      <td>97</td>\n",
       "      <td>85</td>\n",
       "      <td>63</td>\n",
       "      <td>93</td>\n",
       "      <td>68</td>\n",
       "      <td>94</td>\n",
       "      <td>78</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1998</th>\n",
       "      <td>1999</td>\n",
       "      <td>Brittany</td>\n",
       "      <td>Compton</td>\n",
       "      <td>brittany.compton.1999@gslingacademy.com</td>\n",
       "      <td>female</td>\n",
       "      <td>True</td>\n",
       "      <td>10</td>\n",
       "      <td>True</td>\n",
       "      <td>5</td>\n",
       "      <td>Business Owner</td>\n",
       "      <td>51</td>\n",
       "      <td>96</td>\n",
       "      <td>72</td>\n",
       "      <td>89</td>\n",
       "      <td>95</td>\n",
       "      <td>88</td>\n",
       "      <td>75</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1999</th>\n",
       "      <td>2000</td>\n",
       "      <td>Natalie</td>\n",
       "      <td>Smith</td>\n",
       "      <td>natalie.smith.2000@gslingacademy.com</td>\n",
       "      <td>female</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>False</td>\n",
       "      <td>27</td>\n",
       "      <td>Accountant</td>\n",
       "      <td>82</td>\n",
       "      <td>99</td>\n",
       "      <td>91</td>\n",
       "      <td>69</td>\n",
       "      <td>83</td>\n",
       "      <td>93</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2000 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        id first_name last_name                                    email  \\\n",
       "0        1       Paul     Casey           paul.casey.1@gslingacademy.com   \n",
       "1        2   Danielle  Sandoval    danielle.sandoval.2@gslingacademy.com   \n",
       "2        3       Tina   Andrews         tina.andrews.3@gslingacademy.com   \n",
       "3        4       Tara     Clark           tara.clark.4@gslingacademy.com   \n",
       "4        5    Anthony    Campos       anthony.campos.5@gslingacademy.com   \n",
       "...    ...        ...       ...                                      ...   \n",
       "1995  1996       Alan  Reynolds     alan.reynolds.1996@gslingacademy.com   \n",
       "1996  1997     Thomas   Gilbert    thomas.gilbert.1997@gslingacademy.com   \n",
       "1997  1998    Madison     Cross     madison.cross.1998@gslingacademy.com   \n",
       "1998  1999   Brittany   Compton  brittany.compton.1999@gslingacademy.com   \n",
       "1999  2000    Natalie     Smith     natalie.smith.2000@gslingacademy.com   \n",
       "\n",
       "      gender  part_time_job  absence_days  extracurricular_activities  \\\n",
       "0       male          False             3                       False   \n",
       "1     female          False             2                       False   \n",
       "2     female          False             9                        True   \n",
       "3     female          False             5                       False   \n",
       "4       male          False             5                       False   \n",
       "...      ...            ...           ...                         ...   \n",
       "1995    male          False             2                       False   \n",
       "1996    male          False             2                       False   \n",
       "1997  female          False             5                       False   \n",
       "1998  female           True            10                        True   \n",
       "1999  female          False             5                       False   \n",
       "\n",
       "      weekly_self_study_hours      career_aspiration  math_score  \\\n",
       "0                          27                 Lawyer          73   \n",
       "1                          47                 Doctor          90   \n",
       "2                          13     Government Officer          81   \n",
       "3                           3                 Artist          71   \n",
       "4                          10                Unknown          84   \n",
       "...                       ...                    ...         ...   \n",
       "1995                       30  Construction Engineer          83   \n",
       "1996                       20      Software Engineer          89   \n",
       "1997                       14      Software Engineer          97   \n",
       "1998                        5         Business Owner          51   \n",
       "1999                       27             Accountant          82   \n",
       "\n",
       "      history_score  physics_score  chemistry_score  biology_score  \\\n",
       "0                81             93               97             63   \n",
       "1                86             96              100             90   \n",
       "2                97             95               96             65   \n",
       "3                74             88               80             89   \n",
       "4                77             65               65             80   \n",
       "...             ...            ...              ...            ...   \n",
       "1995             77             84               73             75   \n",
       "1996             65             73               80             87   \n",
       "1997             85             63               93             68   \n",
       "1998             96             72               89             95   \n",
       "1999             99             91               69             83   \n",
       "\n",
       "      english_score  geography_score  \n",
       "0                80               87  \n",
       "1                88               90  \n",
       "2                77               94  \n",
       "3                63               86  \n",
       "4                74               76  \n",
       "...             ...              ...  \n",
       "1995             84               82  \n",
       "1996             67               73  \n",
       "1997             94               78  \n",
       "1998             88               75  \n",
       "1999             93              100  \n",
       "\n",
       "[2000 rows x 17 columns]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "df1=pd.read_csv(\"C:\\\\Users\\\\MRINMOY\\\\Documents\\\\student-scores.csv\")\n",
    "df=df1.copy()\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7bafb2bc-f2b6-463b-aca6-8b4eb5042916",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop(columns=['id','first_name','last_name','email'],axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1da38eb7-9055-43bd-96d6-638ea307fdd0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['gender', 'part_time_job', 'absence_days', 'extracurricular_activities',\n",
       "       'weekly_self_study_hours', 'career_aspiration', 'math_score',\n",
       "       'history_score', 'physics_score', 'chemistry_score', 'biology_score',\n",
       "       'english_score', 'geography_score'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "642ce097-ac3f-4caf-8f90-0d27cf1f8382",
   "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>part_time_job</th>\n",
       "      <th>absence_days</th>\n",
       "      <th>extracurricular_activities</th>\n",
       "      <th>weekly_self_study_hours</th>\n",
       "      <th>career_aspiration</th>\n",
       "      <th>math_score</th>\n",
       "      <th>history_score</th>\n",
       "      <th>physics_score</th>\n",
       "      <th>chemistry_score</th>\n",
       "      <th>biology_score</th>\n",
       "      <th>english_score</th>\n",
       "      <th>geography_score</th>\n",
       "      <th>total_score</th>\n",
       "      <th>average_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>male</td>\n",
       "      <td>False</td>\n",
       "      <td>3</td>\n",
       "      <td>False</td>\n",
       "      <td>27</td>\n",
       "      <td>Lawyer</td>\n",
       "      <td>73</td>\n",
       "      <td>81</td>\n",
       "      <td>93</td>\n",
       "      <td>97</td>\n",
       "      <td>63</td>\n",
       "      <td>80</td>\n",
       "      <td>87</td>\n",
       "      <td>574</td>\n",
       "      <td>82.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>female</td>\n",
       "      <td>False</td>\n",
       "      <td>2</td>\n",
       "      <td>False</td>\n",
       "      <td>47</td>\n",
       "      <td>Doctor</td>\n",
       "      <td>90</td>\n",
       "      <td>86</td>\n",
       "      <td>96</td>\n",
       "      <td>100</td>\n",
       "      <td>90</td>\n",
       "      <td>88</td>\n",
       "      <td>90</td>\n",
       "      <td>640</td>\n",
       "      <td>91.428571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>female</td>\n",
       "      <td>False</td>\n",
       "      <td>9</td>\n",
       "      <td>True</td>\n",
       "      <td>13</td>\n",
       "      <td>Government Officer</td>\n",
       "      <td>81</td>\n",
       "      <td>97</td>\n",
       "      <td>95</td>\n",
       "      <td>96</td>\n",
       "      <td>65</td>\n",
       "      <td>77</td>\n",
       "      <td>94</td>\n",
       "      <td>605</td>\n",
       "      <td>86.428571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>female</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>False</td>\n",
       "      <td>3</td>\n",
       "      <td>Artist</td>\n",
       "      <td>71</td>\n",
       "      <td>74</td>\n",
       "      <td>88</td>\n",
       "      <td>80</td>\n",
       "      <td>89</td>\n",
       "      <td>63</td>\n",
       "      <td>86</td>\n",
       "      <td>551</td>\n",
       "      <td>78.714286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>male</td>\n",
       "      <td>False</td>\n",
       "      <td>5</td>\n",
       "      <td>False</td>\n",
       "      <td>10</td>\n",
       "      <td>Unknown</td>\n",
       "      <td>84</td>\n",
       "      <td>77</td>\n",
       "      <td>65</td>\n",
       "      <td>65</td>\n",
       "      <td>80</td>\n",
       "      <td>74</td>\n",
       "      <td>76</td>\n",
       "      <td>521</td>\n",
       "      <td>74.428571</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender  part_time_job  absence_days  extracurricular_activities  \\\n",
       "0    male          False             3                       False   \n",
       "1  female          False             2                       False   \n",
       "2  female          False             9                        True   \n",
       "3  female          False             5                       False   \n",
       "4    male          False             5                       False   \n",
       "\n",
       "   weekly_self_study_hours   career_aspiration  math_score  history_score  \\\n",
       "0                       27              Lawyer          73             81   \n",
       "1                       47              Doctor          90             86   \n",
       "2                       13  Government Officer          81             97   \n",
       "3                        3              Artist          71             74   \n",
       "4                       10             Unknown          84             77   \n",
       "\n",
       "   physics_score  chemistry_score  biology_score  english_score  \\\n",
       "0             93               97             63             80   \n",
       "1             96              100             90             88   \n",
       "2             95               96             65             77   \n",
       "3             88               80             89             63   \n",
       "4             65               65             80             74   \n",
       "\n",
       "   geography_score  total_score  average_score  \n",
       "0               87          574      82.000000  \n",
       "1               90          640      91.428571  \n",
       "2               94          605      86.428571  \n",
       "3               86          551      78.714286  \n",
       "4               76          521      74.428571  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"total_score\"] =df[\"math_score\"]+df[\"history_score\"]+df[\"physics_score\"]+df[\"chemistry_score\"]+df[\"biology_score\"]+df[\"english_score\"]+df[\"geography_score\"]\n",
    "df[\"average_score\"]=df[\"total_score\"]/7\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1b2efe94-0fa6-4626-a23f-fc2de7951f6f",
   "metadata": {},
   "outputs": [],
   "source": [
    "gender_map = {'male':0, 'female':1}\n",
    "part_time_job_map = {False:0, True:1}\n",
    "extracurricular_activities_map = {False:0, True:1}\n",
    "career_aspiration_map = {\n",
    "        'Lawyer': 0, 'Doctor':1, 'Government Officer':2, 'Artist':3, 'Unknown':4,\n",
    "        'Software Engineer':5, 'Teacher':6, 'Business Owner':7, 'Scientist':8,\n",
    "        'Banker':9, 'Writer':10, 'Accountant':11, 'Designer':12,\n",
    "        'Construction Engineer':13, 'Game Developer':14, 'Stock Investor':15,\n",
    "        'Real Estate Developer':16\n",
    "    }\n",
    "# Apply mapping to the DataFrame\n",
    "df['gender'] = df['gender'].map(gender_map)\n",
    "df['part_time_job'] = df['part_time_job'].map(part_time_job_map)\n",
    "df['extracurricular_activities'] = df['extracurricular_activities'].map(extracurricular_activities_map)\n",
    "df['career_aspiration'] = df['career_aspiration'].map(career_aspiration_map)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "a0d53a52-b7bf-4be6-9cae-5754dd31deb9",
   "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>part_time_job</th>\n",
       "      <th>absence_days</th>\n",
       "      <th>extracurricular_activities</th>\n",
       "      <th>weekly_self_study_hours</th>\n",
       "      <th>career_aspiration</th>\n",
       "      <th>math_score</th>\n",
       "      <th>history_score</th>\n",
       "      <th>physics_score</th>\n",
       "      <th>chemistry_score</th>\n",
       "      <th>biology_score</th>\n",
       "      <th>english_score</th>\n",
       "      <th>geography_score</th>\n",
       "      <th>total_score</th>\n",
       "      <th>average_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>73</td>\n",
       "      <td>81</td>\n",
       "      <td>93</td>\n",
       "      <td>97</td>\n",
       "      <td>63</td>\n",
       "      <td>80</td>\n",
       "      <td>87</td>\n",
       "      <td>574</td>\n",
       "      <td>82.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>47</td>\n",
       "      <td>1</td>\n",
       "      <td>90</td>\n",
       "      <td>86</td>\n",
       "      <td>96</td>\n",
       "      <td>100</td>\n",
       "      <td>90</td>\n",
       "      <td>88</td>\n",
       "      <td>90</td>\n",
       "      <td>640</td>\n",
       "      <td>91.428571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "      <td>13</td>\n",
       "      <td>2</td>\n",
       "      <td>81</td>\n",
       "      <td>97</td>\n",
       "      <td>95</td>\n",
       "      <td>96</td>\n",
       "      <td>65</td>\n",
       "      <td>77</td>\n",
       "      <td>94</td>\n",
       "      <td>605</td>\n",
       "      <td>86.428571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>71</td>\n",
       "      <td>74</td>\n",
       "      <td>88</td>\n",
       "      <td>80</td>\n",
       "      <td>89</td>\n",
       "      <td>63</td>\n",
       "      <td>86</td>\n",
       "      <td>551</td>\n",
       "      <td>78.714286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "      <td>4</td>\n",
       "      <td>84</td>\n",
       "      <td>77</td>\n",
       "      <td>65</td>\n",
       "      <td>65</td>\n",
       "      <td>80</td>\n",
       "      <td>74</td>\n",
       "      <td>76</td>\n",
       "      <td>521</td>\n",
       "      <td>74.428571</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1995</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>13</td>\n",
       "      <td>83</td>\n",
       "      <td>77</td>\n",
       "      <td>84</td>\n",
       "      <td>73</td>\n",
       "      <td>75</td>\n",
       "      <td>84</td>\n",
       "      <td>82</td>\n",
       "      <td>558</td>\n",
       "      <td>79.714286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1996</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "      <td>5</td>\n",
       "      <td>89</td>\n",
       "      <td>65</td>\n",
       "      <td>73</td>\n",
       "      <td>80</td>\n",
       "      <td>87</td>\n",
       "      <td>67</td>\n",
       "      <td>73</td>\n",
       "      <td>534</td>\n",
       "      <td>76.285714</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1997</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>14</td>\n",
       "      <td>5</td>\n",
       "      <td>97</td>\n",
       "      <td>85</td>\n",
       "      <td>63</td>\n",
       "      <td>93</td>\n",
       "      <td>68</td>\n",
       "      <td>94</td>\n",
       "      <td>78</td>\n",
       "      <td>578</td>\n",
       "      <td>82.571429</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1998</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>51</td>\n",
       "      <td>96</td>\n",
       "      <td>72</td>\n",
       "      <td>89</td>\n",
       "      <td>95</td>\n",
       "      <td>88</td>\n",
       "      <td>75</td>\n",
       "      <td>566</td>\n",
       "      <td>80.857143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1999</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>11</td>\n",
       "      <td>82</td>\n",
       "      <td>99</td>\n",
       "      <td>91</td>\n",
       "      <td>69</td>\n",
       "      <td>83</td>\n",
       "      <td>93</td>\n",
       "      <td>100</td>\n",
       "      <td>617</td>\n",
       "      <td>88.142857</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2000 rows × 15 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      gender  part_time_job  absence_days  extracurricular_activities  \\\n",
       "0          0              0             3                           0   \n",
       "1          1              0             2                           0   \n",
       "2          1              0             9                           1   \n",
       "3          1              0             5                           0   \n",
       "4          0              0             5                           0   \n",
       "...      ...            ...           ...                         ...   \n",
       "1995       0              0             2                           0   \n",
       "1996       0              0             2                           0   \n",
       "1997       1              0             5                           0   \n",
       "1998       1              1            10                           1   \n",
       "1999       1              0             5                           0   \n",
       "\n",
       "      weekly_self_study_hours  career_aspiration  math_score  history_score  \\\n",
       "0                          27                  0          73             81   \n",
       "1                          47                  1          90             86   \n",
       "2                          13                  2          81             97   \n",
       "3                           3                  3          71             74   \n",
       "4                          10                  4          84             77   \n",
       "...                       ...                ...         ...            ...   \n",
       "1995                       30                 13          83             77   \n",
       "1996                       20                  5          89             65   \n",
       "1997                       14                  5          97             85   \n",
       "1998                        5                  7          51             96   \n",
       "1999                       27                 11          82             99   \n",
       "\n",
       "      physics_score  chemistry_score  biology_score  english_score  \\\n",
       "0                93               97             63             80   \n",
       "1                96              100             90             88   \n",
       "2                95               96             65             77   \n",
       "3                88               80             89             63   \n",
       "4                65               65             80             74   \n",
       "...             ...              ...            ...            ...   \n",
       "1995             84               73             75             84   \n",
       "1996             73               80             87             67   \n",
       "1997             63               93             68             94   \n",
       "1998             72               89             95             88   \n",
       "1999             91               69             83             93   \n",
       "\n",
       "      geography_score  total_score  average_score  \n",
       "0                  87          574      82.000000  \n",
       "1                  90          640      91.428571  \n",
       "2                  94          605      86.428571  \n",
       "3                  86          551      78.714286  \n",
       "4                  76          521      74.428571  \n",
       "...               ...          ...            ...  \n",
       "1995               82          558      79.714286  \n",
       "1996               73          534      76.285714  \n",
       "1997               78          578      82.571429  \n",
       "1998               75          566      80.857143  \n",
       "1999              100          617      88.142857  \n",
       "\n",
       "[2000 rows x 15 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3678e7ee-9dfc-449c-8002-147c4d224eaa",
   "metadata": {},
   "outputs": [],
   "source": [
    "from imblearn.over_sampling import SMOTE\n",
    "\n",
    "# Create SMOTE object\n",
    "smote = SMOTE(random_state=42)\n",
    "\n",
    "# Separate features and target variable\n",
    "X = df.drop('career_aspiration', axis=1)\n",
    "y = df['career_aspiration']\n",
    "\n",
    "# Apply SMOTE to the data\n",
    "X_resampled, y_resampled = smote.fit_resample(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "14adf26c-8d6e-4f33-a546-5ea6910f003f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train,X_test,y_train,y_test = train_test_split(X_resampled,y_resampled,test_size=0.2, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "fedf10ec-16c3-48fc-8ecf-0740776c9156",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4284, 14)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "01a29fae-88d9-4808-864c-3f943c8ab095",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# Initialize the StandardScaler\n",
    "scaler = StandardScaler()\n",
    "\n",
    "# Fit the scaler to the training data and transform both training and testing data\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "7c56f6a5-6ca6-46ec-be85-0a6bde66d9d7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4284, 14)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_scaled.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "e4526c27-63fd-4134-808b-d2f8fec0b642",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "==================================================\n",
      "Model: Logistic Regression\n",
      "Accuracy: 0.48739495798319327\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.45      0.54      0.49        68\n",
      "           1       0.49      0.62      0.55        72\n",
      "           2       0.42      0.44      0.43        57\n",
      "           3       0.52      0.57      0.55        58\n",
      "           4       0.31      0.17      0.22        66\n",
      "           5       0.32      0.32      0.32        76\n",
      "           6       0.58      0.92      0.71        71\n",
      "           7       0.83      0.90      0.87        61\n",
      "           8       0.41      0.45      0.43        53\n",
      "           9       0.29      0.10      0.15        61\n",
      "          10       0.59      0.71      0.65        63\n",
      "          11       0.44      0.45      0.45        53\n",
      "          12       0.31      0.16      0.21        68\n",
      "          13       0.38      0.49      0.43        55\n",
      "          14       0.61      0.93      0.74        57\n",
      "          15       0.37      0.24      0.29        63\n",
      "          16       0.55      0.32      0.40        69\n",
      "\n",
      "    accuracy                           0.49      1071\n",
      "   macro avg       0.46      0.49      0.46      1071\n",
      "weighted avg       0.46      0.49      0.46      1071\n",
      "\n",
      "Confusion Matrix:\n",
      " [[37  4  0  0  0  7  0  0  4  1 10  3  0  2  0  0  0]\n",
      " [ 2 45  0  0  0  7  0  0 13  0  0  0  0  5  0  0  0]\n",
      " [ 0  0 25  5  1  1  9  1  0  0  2  0  4  1  2  2  4]\n",
      " [ 0  0  2 33  0  0  2  1  0  0  0  0  0  0 11  0  9]\n",
      " [ 6  5  7  3 11  9  7  1  2  3  0  3  3  2  1  2  1]\n",
      " [ 8  9  0  0  1 24  1  0  1  7  1  5  3 12  0  4  0]\n",
      " [ 0  0  0  0  1  2 65  0  0  1  2  0  0  0  0  0  0]\n",
      " [ 0  0  0  3  0  0  0 55  0  0  0  0  0  0  3  0  0]\n",
      " [ 4 18  0  0  0  1  0  0 24  0  6  0  0  0  0  0  0]\n",
      " [10  1  0  0  3  8  8  0  1  6  2  8  6  6  0  2  0]\n",
      " [ 8  2  0  0  1  0  4  0  2  1 45  0  0  0  0  0  0]\n",
      " [ 0  1  0  0  4  6  3  0  4  1  0 24  1  3  0  6  0]\n",
      " [ 2  2  8  3  5  2  7  0  3  0  4  0 11  6  8  5  2]\n",
      " [ 1  2  2  0  3  0  0  0  5  1  1  4  4 27  0  5  0]\n",
      " [ 0  0  0  3  0  0  0  0  0  0  0  0  0  0 53  0  1]\n",
      " [ 4  3  3  0  5  8  1  2  0  0  2  7  4  7  1 15  1]\n",
      " [ 0  0 13 13  0  1  5  6  0  0  1  0  0  0  8  0 22]]\n",
      "==================================================\n",
      "Model: Support Vector Classifier\n",
      "Accuracy: 0.6470588235294118\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.55      0.62      0.58        68\n",
      "           1       0.60      0.83      0.70        72\n",
      "           2       0.60      0.74      0.66        57\n",
      "           3       0.69      0.86      0.77        58\n",
      "           4       0.55      0.18      0.27        66\n",
      "           5       0.41      0.32      0.36        76\n",
      "           6       0.70      0.93      0.80        71\n",
      "           7       0.86      0.93      0.90        61\n",
      "           8       0.65      0.81      0.72        53\n",
      "           9       0.38      0.33      0.35        61\n",
      "          10       0.84      0.86      0.85        63\n",
      "          11       0.82      0.51      0.63        53\n",
      "          12       0.65      0.51      0.57        68\n",
      "          13       0.53      0.85      0.65        55\n",
      "          14       0.77      0.93      0.84        57\n",
      "          15       0.67      0.44      0.53        63\n",
      "          16       0.77      0.48      0.59        69\n",
      "\n",
      "    accuracy                           0.65      1071\n",
      "   macro avg       0.65      0.66      0.63      1071\n",
      "weighted avg       0.65      0.65      0.63      1071\n",
      "\n",
      "Confusion Matrix:\n",
      " [[42  6  0  0  0  4  0  0  2  4  6  0  0  3  0  1  0]\n",
      " [ 1 60  0  0  0  1  0  0  5  0  0  0  1  3  0  1  0]\n",
      " [ 0  0 42  2  2  1  4  0  0  0  0  0  2  0  0  3  1]\n",
      " [ 0  0  2 50  0  0  0  1  0  0  0  0  0  0  3  0  2]\n",
      " [ 5  8  7  1 12  7  5  2  1  7  0  2  4  3  1  1  0]\n",
      " [10  7  1  0  1 24  1  1  5 12  0  1  1 11  0  1  0]\n",
      " [ 0  0  0  0  0  1 66  0  0  2  1  0  0  0  0  0  1]\n",
      " [ 0  0  0  1  0  0  1 57  0  0  0  0  0  0  1  0  1]\n",
      " [ 1  8  0  0  0  1  0  0 43  0  0  0  0  0  0  0  0]\n",
      " [ 8  1  1  0  0  7  6  1  3 20  1  0  4  5  0  4  0]\n",
      " [ 2  1  4  0  0  0  0  0  0  1 54  0  0  1  0  0  0]\n",
      " [ 0  3  1  0  3  5  0  1  3  2  1 27  1  3  0  3  0]\n",
      " [ 2  1  0  3  2  1  8  0  2  0  1  1 35  4  4  0  4]\n",
      " [ 0  3  0  0  0  1  0  0  2  1  0  1  0 47  0  0  0]\n",
      " [ 0  0  0  0  0  0  1  2  0  0  0  0  1  0 53  0  0]\n",
      " [ 5  2  3  0  2  4  0  0  0  3  0  1  4  9  1 28  1]\n",
      " [ 0  0  9 15  0  2  2  1  0  0  0  0  1  0  6  0 33]]\n",
      "==================================================\n",
      "Model: Random Forest Classifier\n",
      "Accuracy: 0.8300653594771242\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.72      0.87      0.79        68\n",
      "           1       0.80      1.00      0.89        72\n",
      "           2       0.73      0.93      0.82        57\n",
      "           3       0.92      0.95      0.93        58\n",
      "           4       0.81      0.39      0.53        66\n",
      "           5       0.59      0.39      0.47        76\n",
      "           6       0.88      1.00      0.93        71\n",
      "           7       0.98      0.93      0.96        61\n",
      "           8       0.76      1.00      0.86        53\n",
      "           9       0.69      0.67      0.68        61\n",
      "          10       0.91      0.97      0.94        63\n",
      "          11       0.93      0.75      0.83        53\n",
      "          12       0.91      0.87      0.89        68\n",
      "          13       0.82      0.91      0.86        55\n",
      "          14       0.90      1.00      0.95        57\n",
      "          15       0.92      0.75      0.82        63\n",
      "          16       0.89      0.84      0.87        69\n",
      "\n",
      "    accuracy                           0.83      1071\n",
      "   macro avg       0.83      0.84      0.82      1071\n",
      "weighted avg       0.83      0.83      0.82      1071\n",
      "\n",
      "Confusion Matrix:\n",
      " [[59  5  0  0  1  0  0  0  0  1  1  1  0  0  0  0  0]\n",
      " [ 0 72  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0 53  0  0  0  2  0  0  0  0  0  0  0  0  0  2]\n",
      " [ 0  0  0 55  0  0  0  0  0  0  0  0  0  0  2  0  1]\n",
      " [ 6  5  8  0 26  8  2  0  3  2  1  1  1  0  1  0  2]\n",
      " [11  3  0  0  2 30  2  0  7 10  0  0  1  7  0  3  0]\n",
      " [ 0  0  0  0  0  0 71  0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  1  0  0  0 57  0  0  0  0  0  0  2  0  1]\n",
      " [ 0  0  0  0  0  0  0  0 53  0  0  0  0  0  0  0  0]\n",
      " [ 3  1  1  0  0  5  1  0  2 41  3  0  4  0  0  0  0]\n",
      " [ 0  0  2  0  0  0  0  0  0  0 61  0  0  0  0  0  0]\n",
      " [ 0  2  0  0  1  4  1  0  2  2  0 40  0  1  0  0  0]\n",
      " [ 0  0  2  0  1  1  2  0  0  0  1  0 59  0  1  0  1]\n",
      " [ 0  0  2  0  0  0  0  0  2  0  0  0  0 50  0  1  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0  0  0  0  0 57  0  0]\n",
      " [ 3  2  1  0  1  3  0  0  0  2  0  1  0  3  0 47  0]\n",
      " [ 0  0  4  4  0  0  0  1  1  1  0  0  0  0  0  0 58]]\n",
      "==================================================\n",
      "Model: K Nearest Neighbors\n",
      "Accuracy: 0.6778711484593838\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.59      0.68      0.63        68\n",
      "           1       0.73      0.78      0.75        72\n",
      "           2       0.63      0.86      0.73        57\n",
      "           3       0.60      0.81      0.69        58\n",
      "           4       0.35      0.17      0.23        66\n",
      "           5       0.35      0.14      0.21        76\n",
      "           6       0.83      0.92      0.87        71\n",
      "           7       0.90      0.72      0.80        61\n",
      "           8       0.67      0.91      0.77        53\n",
      "           9       0.44      0.48      0.46        61\n",
      "          10       0.81      0.92      0.86        63\n",
      "          11       0.71      0.64      0.67        53\n",
      "          12       0.71      0.79      0.75        68\n",
      "          13       0.69      0.80      0.74        55\n",
      "          14       0.82      0.89      0.86        57\n",
      "          15       0.65      0.62      0.63        63\n",
      "          16       0.78      0.58      0.67        69\n",
      "\n",
      "    accuracy                           0.68      1071\n",
      "   macro avg       0.66      0.69      0.67      1071\n",
      "weighted avg       0.66      0.68      0.66      1071\n",
      "\n",
      "Confusion Matrix:\n",
      " [[46  2  0  0  0  3  0  0  1  8  6  0  0  0  0  2  0]\n",
      " [ 4 56  0  0  1  0  0  0  4  1  1  0  1  1  0  3  0]\n",
      " [ 0  0 49  1  0  0  0  0  0  0  2  0  0  0  1  1  3]\n",
      " [ 0  0  4 47  0  0  0  1  0  1  0  0  0  0  3  0  2]\n",
      " [ 4  5  5  5 11  6  6  1  2  7  1  1  6  1  1  1  3]\n",
      " [10  6  2  0  7 11  1  1  6  9  0  3  6 10  0  4  0]\n",
      " [ 0  0  1  2  0  0 65  0  0  2  0  0  0  0  1  0  0]\n",
      " [ 0  0  1  3  2  0  1 44  0  2  0  1  2  1  1  1  2]\n",
      " [ 1  4  0  0  0  0  0  0 48  0  0  0  0  0  0  0  0]\n",
      " [ 6  0  2  1  3  3  1  1  2 29  1  4  4  0  0  3  1]\n",
      " [ 2  0  2  0  0  0  0  0  0  1 58  0  0  0  0  0  0]\n",
      " [ 0  2  2  0  0  5  0  0  3  2  1 34  1  2  1  0  0]\n",
      " [ 1  1  2  2  0  0  1  0  0  2  1  1 54  0  0  3  0]\n",
      " [ 2  0  0  0  4  0  0  0  3  0  0  0  0 44  1  1  0]\n",
      " [ 0  0  1  1  0  1  0  0  0  0  0  0  1  1 51  1  0]\n",
      " [ 2  1  1  4  2  1  1  0  3  2  0  4  0  3  0 39  0]\n",
      " [ 0  0  6 12  1  1  2  1  0  0  1  0  1  1  2  1 40]]\n",
      "==================================================\n",
      "Model: Decision Tree Classifier\n",
      "Accuracy: 0.6862745098039216\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.62      0.63      0.63        68\n",
      "           1       0.78      0.88      0.82        72\n",
      "           2       0.66      0.70      0.68        57\n",
      "           3       0.81      0.76      0.79        58\n",
      "           4       0.40      0.39      0.40        66\n",
      "           5       0.40      0.25      0.31        76\n",
      "           6       0.86      0.80      0.83        71\n",
      "           7       0.94      0.80      0.87        61\n",
      "           8       0.81      0.89      0.85        53\n",
      "           9       0.49      0.59      0.53        61\n",
      "          10       0.76      0.86      0.81        63\n",
      "          11       0.60      0.66      0.63        53\n",
      "          12       0.69      0.74      0.71        68\n",
      "          13       0.66      0.73      0.69        55\n",
      "          14       0.84      0.91      0.87        57\n",
      "          15       0.58      0.49      0.53        63\n",
      "          16       0.73      0.71      0.72        69\n",
      "\n",
      "    accuracy                           0.69      1071\n",
      "   macro avg       0.69      0.69      0.69      1071\n",
      "weighted avg       0.68      0.69      0.68      1071\n",
      "\n",
      "Confusion Matrix:\n",
      " [[43  3  0  0  1  7  0  0  1  2  6  0  2  1  0  2  0]\n",
      " [ 2 63  0  0  0  1  0  0  1  1  0  1  1  0  0  2  0]\n",
      " [ 0  0 40  1  3  0  1  0  0  3  0  0  3  1  0  1  4]\n",
      " [ 0  0  2 44  2  0  0  2  0  0  0  0  1  0  4  0  3]\n",
      " [ 3  2  8  0 26  3  1  0  2  8  2  3  2  1  1  0  4]\n",
      " [ 8  7  0  0 10 19  1  0  2 10  2  6  3  5  0  3  0]\n",
      " [ 0  0  2  0  3  2 57  0  0  4  1  0  2  0  0  0  0]\n",
      " [ 0  0  0  1  4  0  0 49  0  0  0  0  0  0  3  0  4]\n",
      " [ 2  1  0  0  0  0  0  0 47  0  1  2  0  0  0  0  0]\n",
      " [ 5  0  0  0  1  2  2  0  2 36  2  4  1  1  0  4  1]\n",
      " [ 0  1  0  0  0  1  0  0  1  4 54  0  1  1  0  0  0]\n",
      " [ 2  1  0  0  4  1  2  0  2  1  0 35  2  1  0  2  0]\n",
      " [ 0  1  1  1  4  3  1  0  0  2  0  1 50  0  1  2  1]\n",
      " [ 3  1  2  0  0  0  0  0  0  2  1  2  0 40  0  4  0]\n",
      " [ 0  0  1  1  0  0  0  0  0  0  0  0  2  0 52  0  1]\n",
      " [ 1  1  1  0  3  7  0  0  0  1  2  4  2 10  0 31  0]\n",
      " [ 0  0  4  6  4  1  1  1  0  0  0  0  0  0  1  2 49]]\n",
      "==================================================\n",
      "Model: Gaussian Naive Bayes\n",
      "Accuracy: 0.3099906629318394\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.56      0.22      0.32        68\n",
      "           1       0.64      0.53      0.58        72\n",
      "           2       0.18      0.05      0.08        57\n",
      "           3       0.30      0.05      0.09        58\n",
      "           4       0.50      0.06      0.11        66\n",
      "           5       0.45      0.18      0.26        76\n",
      "           6       0.31      1.00      0.47        71\n",
      "           7       0.95      0.85      0.90        61\n",
      "           8       0.64      0.17      0.27        53\n",
      "           9       0.20      0.03      0.06        61\n",
      "          10       0.69      0.35      0.46        63\n",
      "          11       0.60      0.23      0.33        53\n",
      "          12       0.50      0.13      0.21        68\n",
      "          13       0.11      0.96      0.20        55\n",
      "          14       0.00      0.00      0.00        57\n",
      "          15       0.50      0.06      0.11        63\n",
      "          16       0.47      0.30      0.37        69\n",
      "\n",
      "    accuracy                           0.31      1071\n",
      "   macro avg       0.45      0.31      0.28      1071\n",
      "weighted avg       0.45      0.31      0.29      1071\n",
      "\n",
      "Confusion Matrix:\n",
      " [[15  0  0  0  0  3  4  0  1  0  4  2  0 39  0  0  0]\n",
      " [ 0 38  0  0  0  2  3  0  3  0  0  0  2 24  0  0  0]\n",
      " [ 0  0  3  0  1  1 16  0  0  0  0  0  0 31  0  2  3]\n",
      " [ 0  0  0  3  0  0 15  1  0  0  0  0  0 23  3  0 13]\n",
      " [ 3  3  0  3  4  3 13  0  0  2  0  3  3 26  0  0  3]\n",
      " [ 4  6  0  0  1 14 12  0  0  2  0  1  1 34  0  1  0]\n",
      " [ 0  0  0  0  0  0 71  0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  1  0  0  3 52  0  0  0  0  0  3  0  0  2]\n",
      " [ 0  3  0  0  0  0  0  0  9  1  1  0  0 39  0  0  0]\n",
      " [ 2  1  1  0  1  2 16  0  0  2  4  1  1 30  0  0  0]\n",
      " [ 3  6  0  0  0  0  9  0  0  1 22  0  0 22  0  0  0]\n",
      " [ 0  0  0  0  0  1 13  0  0  0  0 12  1 25  0  1  0]\n",
      " [ 0  1  7  0  0  0 21  0  1  0  1  0  9 27  0  0  1]\n",
      " [ 0  1  0  0  0  1  0  0  0  0  0  0  0 53  0  0  0]\n",
      " [ 0  0  0  0  0  0 11  1  0  0  0  0  0 45  0  0  0]\n",
      " [ 0  0  1  0  1  2  6  0  0  1  0  1  1 44  0  4  2]\n",
      " [ 0  0  5  3  0  2 16  1  0  1  0  0  0 20  0  0 21]]\n",
      "==================================================\n",
      "Model: AdaBoost Classifier\n",
      "Accuracy: 0.2334267040149393\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.00      0.00      0.00        68\n",
      "           1       1.00      0.61      0.76        72\n",
      "           2       0.28      0.56      0.37        57\n",
      "           3       0.00      0.00      0.00        58\n",
      "           4       0.00      0.00      0.00        66\n",
      "           5       0.00      0.00      0.00        76\n",
      "           6       0.29      0.79      0.42        71\n",
      "           7       0.00      0.00      0.00        61\n",
      "           8       0.15      1.00      0.27        53\n",
      "           9       0.00      0.00      0.00        61\n",
      "          10       0.18      0.38      0.25        63\n",
      "          11       0.00      0.00      0.00        53\n",
      "          12       0.00      0.00      0.00        68\n",
      "          13       0.00      0.00      0.00        55\n",
      "          14       0.00      0.00      0.00        57\n",
      "          15       0.00      0.00      0.00        63\n",
      "          16       0.17      0.59      0.27        69\n",
      "\n",
      "    accuracy                           0.23      1071\n",
      "   macro avg       0.12      0.23      0.14      1071\n",
      "weighted avg       0.13      0.23      0.14      1071\n",
      "\n",
      "Confusion Matrix:\n",
      " [[ 0  0  0  0  0  0  0  0 68  0  0  0  0  0  0  0  0]\n",
      " [ 0 44  0  0  0  0  0  0 20  0  8  0  0  0  0  0  0]\n",
      " [ 0  0 32  0  0  0 15  0  0  0  0  0  0  0  0  0 10]\n",
      " [ 0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0 58]\n",
      " [ 0  0 14  0  0  0  9  0 27  0 11  0  0  0  0  0  5]\n",
      " [ 0  0  0  0  0  0 10  0 45  0 21  0  0  0  0  0  0]\n",
      " [ 0  0 14  0  0  0 56  0  0  0  1  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0 61]\n",
      " [ 0  0  0  0  0  0  0  0 53  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  3  0  0  0 18  0 24  0 16  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  8  0 31  0 24  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0 15  0 22  0 16  0  0  0  0  0  0]\n",
      " [ 0  0 16  0  0  0 24  0 12  0  8  0  0  0  0  0  8]\n",
      " [ 0  0  1  0  0  0 25  0 14  0 15  0  0  0  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0 57]\n",
      " [ 0  0  8  0  0  0 15  0 28  0 12  0  0  0  0  0  0]\n",
      " [ 0  0 28  0  0  0  0  0  0  0  0  0  0  0  0  0 41]]\n",
      "==================================================\n",
      "Model: Gradient Boosting Classifier\n",
      "Accuracy: 0.746031746031746\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.68      0.79      0.73        68\n",
      "           1       0.79      0.97      0.87        72\n",
      "           2       0.63      0.88      0.74        57\n",
      "           3       0.81      0.90      0.85        58\n",
      "           4       0.48      0.15      0.23        66\n",
      "           5       0.50      0.46      0.48        76\n",
      "           6       0.85      0.99      0.92        71\n",
      "           7       0.97      0.95      0.96        61\n",
      "           8       0.78      0.98      0.87        53\n",
      "           9       0.49      0.44      0.47        61\n",
      "          10       0.90      0.95      0.92        63\n",
      "          11       0.80      0.62      0.70        53\n",
      "          12       0.76      0.60      0.67        68\n",
      "          13       0.65      0.87      0.74        55\n",
      "          14       0.89      0.98      0.93        57\n",
      "          15       0.75      0.57      0.65        63\n",
      "          16       0.82      0.68      0.75        69\n",
      "\n",
      "    accuracy                           0.75      1071\n",
      "   macro avg       0.74      0.75      0.73      1071\n",
      "weighted avg       0.73      0.75      0.73      1071\n",
      "\n",
      "Confusion Matrix:\n",
      " [[54  4  0  0  2  5  0  0  0  1  0  2  0  0  0  0  0]\n",
      " [ 1 70  0  0  0  0  0  0  0  0  0  0  0  1  0  0  0]\n",
      " [ 0  0 50  1  0  1  3  0  0  0  0  0  0  0  0  0  2]\n",
      " [ 0  0  0 52  0  0  0  1  0  0  0  0  1  0  2  0  2]\n",
      " [ 5  4 11  0 10 10  1  0  1  8  2  1  3  4  1  3  2]\n",
      " [ 7  3  0  0  1 35  0  0  3 11  0  1  0 12  0  3  0]\n",
      " [ 0  0  0  0  1  0 70  0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  2  0  0  0 58  0  0  0  0  0  0  1  0  0]\n",
      " [ 0  1  0  0  0  0  0  0 52  0  0  0  0  0  0  0  0]\n",
      " [ 5  0  3  0  2  5  3  0  4 27  3  0  4  1  0  4  0]\n",
      " [ 2  1  0  0  0  0  0  0  0  0 60  0  0  0  0  0  0]\n",
      " [ 1  3  1  0  1  3  2  0  3  4  0 33  0  2  0  0  0]\n",
      " [ 1  0  5  1  1  3  1  0  1  3  1  1 41  2  2  2  3]\n",
      " [ 1  1  2  0  0  1  0  0  2  0  0  0  0 48  0  0  0]\n",
      " [ 0  0  0  0  0  0  0  0  0  0  0  0  1  0 56  0  0]\n",
      " [ 3  2  2  0  1  7  0  0  1  1  1  3  1  4  0 36  1]\n",
      " [ 0  0  5  8  2  0  2  1  0  0  0  0  3  0  1  0 47]]\n",
      "==================================================\n",
      "Model: XGBoost Classifier\n",
      "Accuracy: 0.8272642390289449\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "           0       0.78      0.85      0.82        68\n",
      "           1       0.83      0.94      0.88        72\n",
      "           2       0.81      0.91      0.86        57\n",
      "           3       0.87      0.91      0.89        58\n",
      "           4       0.88      0.42      0.57        66\n",
      "           5       0.55      0.42      0.48        76\n",
      "           6       0.92      0.97      0.95        71\n",
      "           7       0.95      0.93      0.94        61\n",
      "           8       0.84      1.00      0.91        53\n",
      "           9       0.61      0.70      0.66        61\n",
      "          10       0.98      0.97      0.98        63\n",
      "          11       0.75      0.72      0.73        53\n",
      "          12       0.91      0.93      0.92        68\n",
      "          13       0.75      0.91      0.82        55\n",
      "          14       0.92      0.98      0.95        57\n",
      "          15       0.78      0.71      0.74        63\n",
      "          16       0.94      0.87      0.90        69\n",
      "\n",
      "    accuracy                           0.83      1071\n",
      "   macro avg       0.83      0.83      0.82      1071\n",
      "weighted avg       0.83      0.83      0.82      1071\n",
      "\n",
      "Confusion Matrix:\n",
      " [[58  3  0  0  2  1  0  0  0  1  0  1  0  1  0  1  0]\n",
      " [ 1 68  0  0  0  0  0  0  1  1  0  0  1  0  0  0  0]\n",
      " [ 0  0 52  0  0  1  1  0  0  1  0  0  1  0  0  0  1]\n",
      " [ 0  0  0 53  0  0  0  1  0  0  0  0  0  0  2  0  2]\n",
      " [ 4  3  6  0 28  9  2  0  2  6  1  0  2  0  1  2  0]\n",
      " [ 8  4  0  0  0 32  0  0  2 10  0  4  0 11  0  5  0]\n",
      " [ 0  0  0  0  0  0 69  0  0  2  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  3  0  0  0 57  0  0  0  0  0  0  0  0  1]\n",
      " [ 0  0  0  0  0  0  0  0 53  0  0  0  0  0  0  0  0]\n",
      " [ 1  0  2  0  0  4  1  0  2 43  0  3  2  0  0  3  0]\n",
      " [ 0  0  0  0  0  0  0  0  1  0 61  0  0  1  0  0  0]\n",
      " [ 1  2  0  0  0  4  2  0  2  3  0 38  0  1  0  0  0]\n",
      " [ 0  1  1  0  0  0  0  0  0  0  0  1 63  0  2  0  0]\n",
      " [ 0  0  1  0  0  2  0  0  0  0  0  0  0 50  0  2  0]\n",
      " [ 0  0  0  0  0  0  0  1  0  0  0  0  0  0 56  0  0]\n",
      " [ 1  1  0  0  1  5  0  0  0  3  0  4  0  3  0 45  0]\n",
      " [ 0  0  2  5  1  0  0  1  0  0  0  0  0  0  0  0 60]]\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "from xgboost import XGBClassifier\n",
    "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "# Define models\n",
    "models = {\n",
    "    \"Logistic Regression\": LogisticRegression(),\n",
    "    \"Support Vector Classifier\": SVC(),\n",
    "    \"Random Forest Classifier\": RandomForestClassifier(),\n",
    "    \"K Nearest Neighbors\": KNeighborsClassifier(),\n",
    "    \"Decision Tree Classifier\": DecisionTreeClassifier(),\n",
    "    \"Gaussian Naive Bayes\": GaussianNB(),\n",
    "    \"AdaBoost Classifier\": AdaBoostClassifier(),\n",
    "    \"Gradient Boosting Classifier\": GradientBoostingClassifier(),\n",
    "    \"XGBoost Classifier\": XGBClassifier(use_label_encoder=False, eval_metric='mlogloss')\n",
    "}\n",
    "\n",
    "# Train and evaluate each model\n",
    "for name, model in models.items():\n",
    "    print(\"=\"*50)\n",
    "    print(\"Model:\", name)\n",
    "    # Train the model\n",
    "    model.fit(X_train_scaled, y_train)\n",
    "    \n",
    "    # Predict on test set\n",
    "    y_pred = model.predict(X_test_scaled)\n",
    "    \n",
    "    # Calculate metrics\n",
    "    accuracy = accuracy_score(y_test, y_pred)\n",
    "    classification_rep = classification_report(y_test, y_pred)\n",
    "    conf_matrix = confusion_matrix(y_test, y_pred)\n",
    "    \n",
    "    # Print metrics\n",
    "    print(\"Accuracy:\", accuracy)\n",
    "    print(\"Classification Report:\\n\", classification_rep)\n",
    "    print(\"Confusion Matrix:\\n\", conf_matrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "71fff568-848c-49c5-9b76-92bf2cd0e0d4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy:  0.834733893557423\n",
      "Report:                precision    recall  f1-score   support\n",
      "\n",
      "           0       0.78      0.90      0.84        68\n",
      "           1       0.81      1.00      0.89        72\n",
      "           2       0.75      0.96      0.85        57\n",
      "           3       0.87      0.95      0.91        58\n",
      "           4       0.82      0.42      0.56        66\n",
      "           5       0.56      0.39      0.46        76\n",
      "           6       0.95      1.00      0.97        71\n",
      "           7       0.93      0.92      0.93        61\n",
      "           8       0.76      0.98      0.86        53\n",
      "           9       0.71      0.74      0.73        61\n",
      "          10       0.94      0.95      0.94        63\n",
      "          11       0.85      0.74      0.79        53\n",
      "          12       0.93      0.84      0.88        68\n",
      "          13       0.78      0.91      0.84        55\n",
      "          14       0.90      0.98      0.94        57\n",
      "          15       0.88      0.78      0.82        63\n",
      "          16       0.95      0.84      0.89        69\n",
      "\n",
      "    accuracy                           0.83      1071\n",
      "   macro avg       0.83      0.84      0.83      1071\n",
      "weighted avg       0.83      0.83      0.83      1071\n",
      "\n",
      "Confusion Matrix:  [[61  4  0  0  0  1  0  0  0  0  1  0  0  0  0  1  0]\n",
      " [ 0 72  0  0  0  0  0  0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0 55  0  0  0  1  0  0  0  0  0  0  0  0  0  1]\n",
      " [ 0  0  0 55  0  0  0  1  0  0  0  0  0  0  2  0  0]\n",
      " [ 4  2  7  1 28  9  0  0  1  5  1  2  2  0  1  2  1]\n",
      " [ 5  6  0  0  2 30  1  0  7 11  0  1  1 10  0  2  0]\n",
      " [ 0  0  0  0  0  0 71  0  0  0  0  0  0  0  0  0  0]\n",
      " [ 0  0  0  3  0  0  0 56  0  0  0  0  0  0  2  0  0]\n",
      " [ 0  1  0  0  0  0  0  0 52  0  0  0  0  0  0  0  0]\n",
      " [ 2  1  1  0  0  4  1  0  2 45  1  3  1  0  0  0  0]\n",
      " [ 1  0  1  0  1  0  0  0  0  0 60  0  0  0  0  0  0]\n",
      " [ 0  2  0  0  2  6  0  0  2  1  0 39  0  1  0  0  0]\n",
      " [ 0  0  2  0  1  1  1  0  1  0  1  1 57  0  1  1  1]\n",
      " [ 0  0  2  0  0  0  0  0  2  0  0  0  0 50  0  1  0]\n",
      " [ 0  0  0  0  0  0  0  1  0  0  0  0  0  0 56  0  0]\n",
      " [ 5  1  1  0  0  3  0  0  0  1  0  0  0  3  0 49  0]\n",
      " [ 0  0  4  4  0  0  0  2  1  0  0  0  0  0  0  0 58]]\n"
     ]
    }
   ],
   "source": [
    "model = RandomForestClassifier()\n",
    "\n",
    "model.fit(X_train_scaled, y_train)\n",
    "# Predict on test set\n",
    "y_pred = model.predict(X_test_scaled)\n",
    "\n",
    "# Calculate metrics\n",
    "print(\"Accuracy: \",accuracy_score(y_test, y_pred))\n",
    "print(\"Report: \",classification_report(y_test, y_pred))\n",
    "print(\"Confusion Matrix: \",confusion_matrix(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "12033999-0d54-4c74-9b6a-0e7d2709831e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Actual Label : 12\n",
      "Model Prediction : 12\n",
      "Wow! Model doing well.....\n"
     ]
    }
   ],
   "source": [
    "# test 1\n",
    "print(\"Actual Label :\", y_test.iloc[10])\n",
    "print(\"Model Prediction :\",model.predict(X_test_scaled[10].reshape(1,-1))[0])\n",
    "if y_test.iloc[10]==model.predict(X_test_scaled[10].reshape(1,-1)):\n",
    "    print(\"Wow! Model doing well.....\")\n",
    "else:\n",
    "    print(\"not sure......\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "209fb122-aae8-4878-b112-7b91f9541d25",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Actual Label : 0\n",
      "Model Prediction : 0\n",
      "Wow! Model doing well.....\n"
     ]
    }
   ],
   "source": [
    "# test 2\n",
    "print(\"Actual Label :\", y_test.iloc[300])\n",
    "print(\"Model Prediction :\",model.predict(X_test_scaled[300].reshape(1,-1))[0])\n",
    "if y_test.iloc[10]==model.predict(X_test_scaled[10].reshape(1,-1)):\n",
    "    print(\"Wow! Model doing well.....\")\n",
    "else:\n",
    "    print(\"not sure......\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "bbb84d3e-0c6e-40ce-8017-f6b174122fa1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Actual Label : 3\n",
      "Model Prediction : 3\n",
      "Wow! Model doing well.....\n"
     ]
    }
   ],
   "source": [
    "# test 2\n",
    "print(\"Actual Label :\", y_test.iloc[23])\n",
    "print(\"Model Prediction :\",model.predict(X_test_scaled[23].reshape(1,-1))[0])\n",
    "if y_test.iloc[10]==model.predict(X_test_scaled[10].reshape(1,-1)):\n",
    "    print(\"Wow! Model doing well.....\")\n",
    "else:\n",
    "    print(\"not sure......\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "d25b3118-ee0a-4e22-9677-52823d8ca22b",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "import pickle\n",
    "import os\n",
    "\n",
    "# Step 1: Define and fit the scaler\n",
    "scaler = StandardScaler()  # Create a scaler object\n",
    "X_train = [[1, 2], [3, 4], [5, 6]]  # Sample training data\n",
    "scaler.fit(X_train)  # Fit the scaler to the data\n",
    "\n",
    "# Step 2: Ensure the 'Models' directory exists\n",
    "os.makedirs(\"Models\", exist_ok=True)\n",
    "\n",
    "# Step 3: Save the scaler to a file\n",
    "pickle.dump(scaler, open(\"Models/scaler.pkl\", 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "037f06db-44c3-4167-be9c-4505c09fbf93",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "# SAVE FILES\n",
    "pickle.dump(scaler,open(\"Models/scaler.pkl\",'wb'))\n",
    "pickle.dump(model,open(\"Models/model.pkl\",'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "6948b9c9-18e1-4b1f-bbe5-9146af9ef840",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the scaler, label encoder, and model\n",
    "scaler = pickle.load(open(\"Models/scaler.pkl\", 'rb'))\n",
    "model = pickle.load(open(\"Models/model.pkl\", 'rb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "59055f53-d44c-47c4-bdf3-535b414f6ddd",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "import numpy as np\n",
    "# Load the scaler, label encoder, model, and class names\n",
    "scaler = pickle.load(open(\"Models/scaler.pkl\", 'rb'))\n",
    "model = pickle.load(open(\"Models/model.pkl\", 'rb'))\n",
    "class_names = ['Lawyer[CLAT,LSAT,AILET]', 'Doctor[NEET]', 'Government Officer[UPSC,SSC CGL]', 'Artist[CEED]', 'Unknown',\n",
    "               'Software Engineer[JEE,WBJEE,MHT CET]', 'Teacher', 'Business Owner', 'Scientist[IAT]',\n",
    "               'Banker[MBA]', 'Writer', 'Accountant[CA]', 'Designer[CEED]',\n",
    "               'Construction Engineer[JEE]', 'Game Developer', 'Stock Investor',\n",
    "               'Real Estate Developer']\n",
    "\n",
    "def Recommendations(gender, part_time_job, absence_days, extracurricular_activities,\n",
    "                    weekly_self_study_hours, math_score, history_score, physics_score,\n",
    "                    chemistry_score, biology_score, english_score, geography_score,\n",
    "                    total_score,average_score):\n",
    "    \n",
    "    # Encode categorical variables\n",
    "    gender_encoded = 1 if gender.lower() == 'female' else 0\n",
    "    part_time_job_encoded = 1 if part_time_job else 0\n",
    "    extracurricular_activities_encoded = 1 if extracurricular_activities else 0\n",
    "    \n",
    "    # Create feature array\n",
    "    feature_array = np.array([[gender_encoded, part_time_job_encoded, absence_days, extracurricular_activities_encoded,\n",
    "                               weekly_self_study_hours, math_score, history_score, physics_score,\n",
    "                               chemistry_score, biology_score, english_score, geography_score,total_score,average_score]])\n",
    "     # Scale features\n",
    "    scaled_features = scaler.transform(feature_array)\n",
    "    \n",
    "    # Predict using the model\n",
    "    probabilities = model.predict_proba(scaled_features)\n",
    "    \n",
    "    # Get top five predicted classes along with their probabilities\n",
    "    top_classes_idx = np.argsort(-probabilities[0])[:5]\n",
    "    top_classes_names_probs = [(class_names[idx], probabilities[0][idx]) for idx in top_classes_idx]\n",
    "    \n",
    "    return top_classes_names_probs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "2f8fce69-b2c8-43cb-b140-bcf613e9d5ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "import numpy as np\n",
    "import pickle\n",
    "import os\n",
    "\n",
    "# Example data (replace with your actual data)\n",
    "X_train = np.array([[1, 2, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13],  # Sample training data with 14 features\n",
    "                    [2, 3, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14],\n",
    "                    [3, 4, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15]])\n",
    "\n",
    "# Step 1: Define and fit the scaler with 14 features\n",
    "scaler = StandardScaler()  \n",
    "scaler.fit(X_train)  # Fit the scaler to the training data with 14 features\n",
    "\n",
    "# Step 2: Save the scaler\n",
    "os.makedirs(\"Models\", exist_ok=True)  # Ensure the 'Models' directory exists\n",
    "pickle.dump(scaler, open(\"Models/scaler.pkl\", 'wb'))\n",
    "\n",
    "# Step 3: Use the same number of features for predictions\n",
    "feature_array = np.array([[0, 0, 2, 0, 7, 65, 60, 97, 94, 71, 81, 66, 534, 76.285714]])  # Example with 14 features\n",
    "\n",
    "# Step 4: Scale features\n",
    "scaled_features = scaler.transform(feature_array)\n",
    "\n",
    "# Continue with prediction (assuming you have a trained model)\n",
    "# probabilities = model.predict_proba(scaled_features)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "0e96932c-70b8-4b85-a6f3-1bdee8607595",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Top recommended studies with probabilities:\n",
      "==================================================\n",
      "Doctor[NEET] with probability 0.79\n",
      "Construction Engineer[JEE] with probability 0.08\n",
      "Unknown with probability 0.06\n",
      "Software Engineer[JEE,WBJEE,MHT CET] with probability 0.04\n",
      "Banker[MBA] with probability 0.02\n"
     ]
    }
   ],
   "source": [
    "# Example usage 1\n",
    "final_recommendations = Recommendations(gender='female',\n",
    "                                        part_time_job=False,\n",
    "                                        absence_days=2,\n",
    "                                        extracurricular_activities=False,\n",
    "                                        weekly_self_study_hours=7,\n",
    "                                        math_score=65,\n",
    "                                        history_score=60,\n",
    "                                        physics_score=97,\n",
    "                                        chemistry_score=94,\n",
    "                                        biology_score=71,\n",
    "                                        english_score=81,\n",
    "                                        geography_score=66,\n",
    "                                        total_score=534,\n",
    "                                        average_score=76.285714)\n",
    "\n",
    "print(\"Top recommended studies with probabilities:\")\n",
    "print(\"=\"*50)\n",
    "for class_name, probability in final_recommendations:\n",
    "    print(f\"{class_name} with probability {probability}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "63fd9948-0bc2-4512-a9d9-fea10f9a1e06",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Top recommended studies with probabilities:\n",
      "==================================================\n",
      "Artist[CEED] with probability 0.15\n",
      "Game Developer with probability 0.15\n",
      "Unknown with probability 0.14\n",
      "Construction Engineer[JEE] with probability 0.13\n",
      "Doctor[NEET] with probability 0.1\n"
     ]
    }
   ],
   "source": [
    "# Example usage 2\n",
    "final_recommendations = Recommendations(gender='female',\n",
    "                                        part_time_job=False,\n",
    "                                        absence_days=2,\n",
    "                                        extracurricular_activities=False,\n",
    "                                        weekly_self_study_hours=4,\n",
    "                                        math_score=87,\n",
    "                                        history_score=73,\n",
    "                                        physics_score=98,\n",
    "                                        chemistry_score=91,\n",
    "                                        biology_score=79,\n",
    "                                        english_score=60,\n",
    "                                        geography_score=77,\n",
    "                                        total_score=583,\n",
    "                                        average_score=83.285714)\n",
    "\n",
    "print(\"Top recommended studies with probabilities:\")\n",
    "print(\"=\"*50)\n",
    "for class_name, probability in final_recommendations:\n",
    "    print(f\"{class_name} with probability {probability}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "dba4f75b-867f-4004-9c58-4c147dc64f7f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.5.1\n"
     ]
    }
   ],
   "source": [
    "#sklear version in vs code \n",
    "import sklearn\n",
    "print(sklearn.__version__)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "40f67f0c-3b15-4299-a2a1-71ebb2604fc6",
   "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}