CreditApprovals.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "48e46b44",
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>b</td>\n",
       "      <td>30.83</td>\n",
       "      <td>0.000</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>1.25</td>\n",
       "      <td>t</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00202</td>\n",
       "      <td>0</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a</td>\n",
       "      <td>58.67</td>\n",
       "      <td>4.460</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>3.04</td>\n",
       "      <td>t</td>\n",
       "      <td>t</td>\n",
       "      <td>6</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00043</td>\n",
       "      <td>560</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a</td>\n",
       "      <td>24.50</td>\n",
       "      <td>0.500</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>1.50</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>824</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>b</td>\n",
       "      <td>27.83</td>\n",
       "      <td>1.540</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>3.75</td>\n",
       "      <td>t</td>\n",
       "      <td>t</td>\n",
       "      <td>5</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00100</td>\n",
       "      <td>3</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>b</td>\n",
       "      <td>20.17</td>\n",
       "      <td>5.625</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>1.71</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>s</td>\n",
       "      <td>00120</td>\n",
       "      <td>0</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  0      1      2  3  4  5  6     7  8  9   10 11 12     13   14 15\n",
       "0  b  30.83  0.000  u  g  w  v  1.25  t  t   1  f  g  00202    0  +\n",
       "1  a  58.67  4.460  u  g  q  h  3.04  t  t   6  f  g  00043  560  +\n",
       "2  a  24.50  0.500  u  g  q  h  1.50  t  f   0  f  g  00280  824  +\n",
       "3  b  27.83  1.540  u  g  w  v  3.75  t  t   5  t  g  00100    3  +\n",
       "4  b  20.17  5.625  u  g  w  v  1.71  t  f   0  f  s  00120    0  +"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "# Load dataset\n",
    "cc_apps = pd.read_csv(\"cc_approvals.data\", header = None)\n",
    "cc_apps.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "03e4bc5a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "             Debt  YearsEmployed  CreditScore         Income\n",
      "count  690.000000     690.000000    690.00000     690.000000\n",
      "mean     4.758725       2.223406      2.40000    1017.385507\n",
      "std      4.978163       3.346513      4.86294    5210.102598\n",
      "min      0.000000       0.000000      0.00000       0.000000\n",
      "25%      1.000000       0.165000      0.00000       0.000000\n",
      "50%      2.750000       1.000000      0.00000       5.000000\n",
      "75%      7.207500       2.625000      3.00000     395.500000\n",
      "max     28.000000      28.500000     67.00000  100000.000000\n",
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 690 entries, 0 to 689\n",
      "Data columns (total 16 columns):\n",
      " #   Column          Non-Null Count  Dtype  \n",
      "---  ------          --------------  -----  \n",
      " 0   Gender          690 non-null    object \n",
      " 1   Age             690 non-null    object \n",
      " 2   Debt            690 non-null    float64\n",
      " 3   Married         690 non-null    object \n",
      " 4   BankCustomer    690 non-null    object \n",
      " 5   EducationLevel  690 non-null    object \n",
      " 6   Ethnicity       690 non-null    object \n",
      " 7   YearsEmployed   690 non-null    float64\n",
      " 8   PriorDefault    690 non-null    object \n",
      " 9   Employed        690 non-null    object \n",
      " 10  CreditScore     690 non-null    int64  \n",
      " 11  DriversLicense  690 non-null    object \n",
      " 12  Citizen         690 non-null    object \n",
      " 13  ZipCode         690 non-null    object \n",
      " 14  Income          690 non-null    int64  \n",
      " 15  ApprovalStatus  690 non-null    object \n",
      "dtypes: float64(2), int64(2), object(12)\n",
      "memory usage: 86.4+ KB\n",
      "None\n",
      "\n",
      "\n"
     ]
    },
    {
     "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>Age</th>\n",
       "      <th>Debt</th>\n",
       "      <th>Married</th>\n",
       "      <th>BankCustomer</th>\n",
       "      <th>EducationLevel</th>\n",
       "      <th>Ethnicity</th>\n",
       "      <th>YearsEmployed</th>\n",
       "      <th>PriorDefault</th>\n",
       "      <th>Employed</th>\n",
       "      <th>CreditScore</th>\n",
       "      <th>DriversLicense</th>\n",
       "      <th>Citizen</th>\n",
       "      <th>ZipCode</th>\n",
       "      <th>Income</th>\n",
       "      <th>ApprovalStatus</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>673</th>\n",
       "      <td>?</td>\n",
       "      <td>29.50</td>\n",
       "      <td>2.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00256</td>\n",
       "      <td>17</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>674</th>\n",
       "      <td>a</td>\n",
       "      <td>37.33</td>\n",
       "      <td>2.500</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>h</td>\n",
       "      <td>0.210</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>246</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>675</th>\n",
       "      <td>a</td>\n",
       "      <td>41.58</td>\n",
       "      <td>1.040</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.665</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>237</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>676</th>\n",
       "      <td>a</td>\n",
       "      <td>30.58</td>\n",
       "      <td>10.665</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>0.085</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>12</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00129</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>677</th>\n",
       "      <td>b</td>\n",
       "      <td>19.42</td>\n",
       "      <td>7.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00100</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>678</th>\n",
       "      <td>a</td>\n",
       "      <td>17.92</td>\n",
       "      <td>10.210</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>50</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>679</th>\n",
       "      <td>a</td>\n",
       "      <td>20.08</td>\n",
       "      <td>1.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>680</th>\n",
       "      <td>b</td>\n",
       "      <td>19.50</td>\n",
       "      <td>0.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>k</td>\n",
       "      <td>v</td>\n",
       "      <td>0.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>364</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>b</td>\n",
       "      <td>27.83</td>\n",
       "      <td>1.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>h</td>\n",
       "      <td>3.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00176</td>\n",
       "      <td>537</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>682</th>\n",
       "      <td>b</td>\n",
       "      <td>17.08</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>v</td>\n",
       "      <td>0.335</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00140</td>\n",
       "      <td>2</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>b</td>\n",
       "      <td>36.42</td>\n",
       "      <td>0.750</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>v</td>\n",
       "      <td>0.585</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>684</th>\n",
       "      <td>b</td>\n",
       "      <td>40.58</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>3.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>s</td>\n",
       "      <td>00400</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>685</th>\n",
       "      <td>b</td>\n",
       "      <td>21.08</td>\n",
       "      <td>10.085</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>1.250</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>686</th>\n",
       "      <td>a</td>\n",
       "      <td>22.67</td>\n",
       "      <td>0.750</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>2</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>394</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>687</th>\n",
       "      <td>a</td>\n",
       "      <td>25.25</td>\n",
       "      <td>13.500</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>688</th>\n",
       "      <td>b</td>\n",
       "      <td>17.92</td>\n",
       "      <td>0.205</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>750</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>689</th>\n",
       "      <td>b</td>\n",
       "      <td>35.00</td>\n",
       "      <td>3.375</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>h</td>\n",
       "      <td>8.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Gender    Age    Debt Married BankCustomer EducationLevel Ethnicity  \\\n",
       "673      ?  29.50   2.000       y            p              e         h   \n",
       "674      a  37.33   2.500       u            g              i         h   \n",
       "675      a  41.58   1.040       u            g             aa         v   \n",
       "676      a  30.58  10.665       u            g              q         h   \n",
       "677      b  19.42   7.250       u            g              m         v   \n",
       "678      a  17.92  10.210       u            g             ff        ff   \n",
       "679      a  20.08   1.250       u            g              c         v   \n",
       "680      b  19.50   0.290       u            g              k         v   \n",
       "681      b  27.83   1.000       y            p              d         h   \n",
       "682      b  17.08   3.290       u            g              i         v   \n",
       "683      b  36.42   0.750       y            p              d         v   \n",
       "684      b  40.58   3.290       u            g              m         v   \n",
       "685      b  21.08  10.085       y            p              e         h   \n",
       "686      a  22.67   0.750       u            g              c         v   \n",
       "687      a  25.25  13.500       y            p             ff        ff   \n",
       "688      b  17.92   0.205       u            g             aa         v   \n",
       "689      b  35.00   3.375       u            g              c         h   \n",
       "\n",
       "     YearsEmployed PriorDefault Employed  CreditScore DriversLicense Citizen  \\\n",
       "673          2.000            f        f            0              f       g   \n",
       "674          0.210            f        f            0              f       g   \n",
       "675          0.665            f        f            0              f       g   \n",
       "676          0.085            f        t           12              t       g   \n",
       "677          0.040            f        t            1              f       g   \n",
       "678          0.000            f        f            0              f       g   \n",
       "679          0.000            f        f            0              f       g   \n",
       "680          0.290            f        f            0              f       g   \n",
       "681          3.000            f        f            0              f       g   \n",
       "682          0.335            f        f            0              t       g   \n",
       "683          0.585            f        f            0              f       g   \n",
       "684          3.500            f        f            0              t       s   \n",
       "685          1.250            f        f            0              f       g   \n",
       "686          2.000            f        t            2              t       g   \n",
       "687          2.000            f        t            1              t       g   \n",
       "688          0.040            f        f            0              f       g   \n",
       "689          8.290            f        f            0              t       g   \n",
       "\n",
       "    ZipCode  Income ApprovalStatus  \n",
       "673   00256      17              -  \n",
       "674   00260     246              -  \n",
       "675   00240     237              -  \n",
       "676   00129       3              -  \n",
       "677   00100       1              -  \n",
       "678   00000      50              -  \n",
       "679   00000       0              -  \n",
       "680   00280     364              -  \n",
       "681   00176     537              -  \n",
       "682   00140       2              -  \n",
       "683   00240       3              -  \n",
       "684   00400       0              -  \n",
       "685   00260       0              -  \n",
       "686   00200     394              -  \n",
       "687   00200       1              -  \n",
       "688   00280     750              -  \n",
       "689   00000       0              -  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Naming axis\n",
    "cc_apps.set_axis(['Gender', 'Age', 'Debt', 'Married', 'BankCustomer', 'EducationLevel', 'Ethnicity', 'YearsEmployed', \\\n",
    "                 'PriorDefault', 'Employed', 'CreditScore', 'DriversLicense', 'Citizen', 'ZipCode', 'Income', \\\n",
    "                 'ApprovalStatus'], axis=1, inplace=True)\n",
    "\n",
    "# Print summary statistics\n",
    "cc_apps_description = cc_apps.describe()\n",
    "print(cc_apps_description)\n",
    "\n",
    "print(\"\\n\")\n",
    "\n",
    "# Print DataFrame information\n",
    "cc_apps_info = cc_apps.info()\n",
    "print(cc_apps_info)\n",
    "\n",
    "print(\"\\n\")\n",
    "\n",
    "# Inspect missing values in the dataset\n",
    "cc_apps.tail(17)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2daec569",
   "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>Age</th>\n",
       "      <th>Debt</th>\n",
       "      <th>Married</th>\n",
       "      <th>BankCustomer</th>\n",
       "      <th>EducationLevel</th>\n",
       "      <th>Ethnicity</th>\n",
       "      <th>YearsEmployed</th>\n",
       "      <th>PriorDefault</th>\n",
       "      <th>Employed</th>\n",
       "      <th>CreditScore</th>\n",
       "      <th>DriversLicense</th>\n",
       "      <th>Citizen</th>\n",
       "      <th>ZipCode</th>\n",
       "      <th>Income</th>\n",
       "      <th>ApprovalStatus</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>673</th>\n",
       "      <td>NaN</td>\n",
       "      <td>29.50</td>\n",
       "      <td>2.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00256</td>\n",
       "      <td>17</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>674</th>\n",
       "      <td>a</td>\n",
       "      <td>37.33</td>\n",
       "      <td>2.500</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>h</td>\n",
       "      <td>0.210</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>246</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>675</th>\n",
       "      <td>a</td>\n",
       "      <td>41.58</td>\n",
       "      <td>1.040</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.665</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>237</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>676</th>\n",
       "      <td>a</td>\n",
       "      <td>30.58</td>\n",
       "      <td>10.665</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>0.085</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>12</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00129</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>677</th>\n",
       "      <td>b</td>\n",
       "      <td>19.42</td>\n",
       "      <td>7.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00100</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>678</th>\n",
       "      <td>a</td>\n",
       "      <td>17.92</td>\n",
       "      <td>10.210</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>50</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>679</th>\n",
       "      <td>a</td>\n",
       "      <td>20.08</td>\n",
       "      <td>1.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>680</th>\n",
       "      <td>b</td>\n",
       "      <td>19.50</td>\n",
       "      <td>0.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>k</td>\n",
       "      <td>v</td>\n",
       "      <td>0.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>364</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>b</td>\n",
       "      <td>27.83</td>\n",
       "      <td>1.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>h</td>\n",
       "      <td>3.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00176</td>\n",
       "      <td>537</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>682</th>\n",
       "      <td>b</td>\n",
       "      <td>17.08</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>v</td>\n",
       "      <td>0.335</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00140</td>\n",
       "      <td>2</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>b</td>\n",
       "      <td>36.42</td>\n",
       "      <td>0.750</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>v</td>\n",
       "      <td>0.585</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>684</th>\n",
       "      <td>b</td>\n",
       "      <td>40.58</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>3.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>s</td>\n",
       "      <td>00400</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>685</th>\n",
       "      <td>b</td>\n",
       "      <td>21.08</td>\n",
       "      <td>10.085</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>1.250</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>686</th>\n",
       "      <td>a</td>\n",
       "      <td>22.67</td>\n",
       "      <td>0.750</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>2</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>394</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>687</th>\n",
       "      <td>a</td>\n",
       "      <td>25.25</td>\n",
       "      <td>13.500</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>688</th>\n",
       "      <td>b</td>\n",
       "      <td>17.92</td>\n",
       "      <td>0.205</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>750</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>689</th>\n",
       "      <td>b</td>\n",
       "      <td>35.00</td>\n",
       "      <td>3.375</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>h</td>\n",
       "      <td>8.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Gender    Age    Debt Married BankCustomer EducationLevel Ethnicity  \\\n",
       "673    NaN  29.50   2.000       y            p              e         h   \n",
       "674      a  37.33   2.500       u            g              i         h   \n",
       "675      a  41.58   1.040       u            g             aa         v   \n",
       "676      a  30.58  10.665       u            g              q         h   \n",
       "677      b  19.42   7.250       u            g              m         v   \n",
       "678      a  17.92  10.210       u            g             ff        ff   \n",
       "679      a  20.08   1.250       u            g              c         v   \n",
       "680      b  19.50   0.290       u            g              k         v   \n",
       "681      b  27.83   1.000       y            p              d         h   \n",
       "682      b  17.08   3.290       u            g              i         v   \n",
       "683      b  36.42   0.750       y            p              d         v   \n",
       "684      b  40.58   3.290       u            g              m         v   \n",
       "685      b  21.08  10.085       y            p              e         h   \n",
       "686      a  22.67   0.750       u            g              c         v   \n",
       "687      a  25.25  13.500       y            p             ff        ff   \n",
       "688      b  17.92   0.205       u            g             aa         v   \n",
       "689      b  35.00   3.375       u            g              c         h   \n",
       "\n",
       "     YearsEmployed PriorDefault Employed  CreditScore DriversLicense Citizen  \\\n",
       "673          2.000            f        f            0              f       g   \n",
       "674          0.210            f        f            0              f       g   \n",
       "675          0.665            f        f            0              f       g   \n",
       "676          0.085            f        t           12              t       g   \n",
       "677          0.040            f        t            1              f       g   \n",
       "678          0.000            f        f            0              f       g   \n",
       "679          0.000            f        f            0              f       g   \n",
       "680          0.290            f        f            0              f       g   \n",
       "681          3.000            f        f            0              f       g   \n",
       "682          0.335            f        f            0              t       g   \n",
       "683          0.585            f        f            0              f       g   \n",
       "684          3.500            f        f            0              t       s   \n",
       "685          1.250            f        f            0              f       g   \n",
       "686          2.000            f        t            2              t       g   \n",
       "687          2.000            f        t            1              t       g   \n",
       "688          0.040            f        f            0              f       g   \n",
       "689          8.290            f        f            0              t       g   \n",
       "\n",
       "    ZipCode  Income ApprovalStatus  \n",
       "673   00256      17              -  \n",
       "674   00260     246              -  \n",
       "675   00240     237              -  \n",
       "676   00129       3              -  \n",
       "677   00100       1              -  \n",
       "678   00000      50              -  \n",
       "679   00000       0              -  \n",
       "680   00280     364              -  \n",
       "681   00176     537              -  \n",
       "682   00140       2              -  \n",
       "683   00240       3              -  \n",
       "684   00400       0              -  \n",
       "685   00260       0              -  \n",
       "686   00200     394              -  \n",
       "687   00200       1              -  \n",
       "688   00280     750              -  \n",
       "689   00000       0              -  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Replace the '?'s with NaN\n",
    "cc_apps = cc_apps.replace('?', np.NaN)\n",
    "cc_apps.tail(17)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "df4185b9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Gender            12\n",
       "Age               12\n",
       "Debt               0\n",
       "Married            6\n",
       "BankCustomer       6\n",
       "EducationLevel     9\n",
       "Ethnicity          9\n",
       "YearsEmployed      0\n",
       "PriorDefault       0\n",
       "Employed           0\n",
       "CreditScore        0\n",
       "DriversLicense     0\n",
       "Citizen            0\n",
       "ZipCode           13\n",
       "Income             0\n",
       "ApprovalStatus     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Impute the missing values with mean imputation\n",
    "cc_apps.fillna(cc_apps.mean(), inplace=True)\n",
    "cc_apps.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "836e5702",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Gender            0\n",
       "Age               0\n",
       "Debt              0\n",
       "Married           0\n",
       "BankCustomer      0\n",
       "EducationLevel    0\n",
       "Ethnicity         0\n",
       "YearsEmployed     0\n",
       "PriorDefault      0\n",
       "Employed          0\n",
       "CreditScore       0\n",
       "DriversLicense    0\n",
       "Citizen           0\n",
       "ZipCode           0\n",
       "Income            0\n",
       "ApprovalStatus    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "for col in cc_apps.columns:\n",
    "    # Check if the column is of object type\n",
    "    if cc_apps[col].dtypes == 'object':\n",
    "        # Impute with the most frequent value\n",
    "        cc_apps = cc_apps.fillna(cc_apps[col].value_counts().index[0])\n",
    "\n",
    "cc_apps.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "845b287d",
   "metadata": {},
   "outputs": [],
   "source": [
    "le=LabelEncoder()\n",
    "\n",
    "for col in cc_apps.columns.to_numpy():\n",
    "    # Compare if the dtype is object\n",
    "    if cc_apps[col].dtypes=='object':\n",
    "    # Use LabelEncoder to do the numeric transformation\n",
    "        cc_apps[col]=le.fit_transform(cc_apps[col])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a87779e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_apps = cc_apps.drop(['DriversLicense', 'ZipCode'], axis=1)\n",
    "cc_apps = cc_apps.to_numpy()\n",
    "\n",
    "# Segregate features and labels into separate variables\n",
    "X,y = cc_apps[:,0:13] , cc_apps[:,13]\n",
    "\n",
    "# Split into train and test sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,\n",
    "                                                    y,\n",
    "                                                    test_size=0.33,\n",
    "                                                    random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "72cef13b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Instantiate MinMaxScaler and use it to rescale X_train and X_test\n",
    "scaler = MinMaxScaler(feature_range=(0, 1))\n",
    "rescaledX_train = scaler.fit_transform(X_train)\n",
    "rescaledX_test = scaler.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "ba1fe693",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logreg = LogisticRegression()\n",
    "\n",
    "logreg.fit(rescaledX_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "024ae8c2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of logistic regression classifier:  0.8421052631578947\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[94,  9],\n",
       "       [27, 98]], dtype=int64)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = logreg.predict(rescaledX_test)\n",
    "\n",
    "# Get the accuracy score of logreg model and print it\n",
    "print(\"Accuracy of logistic regression classifier: \", logreg.score(rescaledX_test, y_test))\n",
    "\n",
    "# Print the confusion matrix of the logreg model\n",
    "confusion_matrix(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "2a46c017",
   "metadata": {},
   "outputs": [],
   "source": [
    "tol = [0.01, 0.001, 0.0001]\n",
    "max_iter = [100, 150, 200]\n",
    "\n",
    "# Create a dictionary where tol and max_iter are keys and the lists of their values are corresponding values\n",
    "param_grid = dict(tol=tol, max_iter=max_iter)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "fa41c668",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best: 0.850725 using {'max_iter': 100, 'tol': 0.01}\n"
     ]
    }
   ],
   "source": [
    "# Instantiate GridSearchCV with the required parameters\n",
    "grid_model = GridSearchCV(estimator=logreg, param_grid=param_grid, cv=5)\n",
    "\n",
    "# Use scaler to rescale X and assign it to rescaledX\n",
    "rescaledX = scaler.fit_transform(X)\n",
    "\n",
    "# Fit data to grid_model\n",
    "grid_model_result = grid_model.fit(rescaledX, y)\n",
    "\n",
    "# Summarize results\n",
    "best_score, best_params = grid_model_result.best_score_, grid_model_result.best_params_\n",
    "print(\"Best: %f using %s\" % (best_score, best_params))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}