JP Morgan Quantitative training task3.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load Libreries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "from scipy import stats \n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.dates as mdates\n",
    "from matplotlib import pyplot\n",
    "from scipy.stats import norm\n",
    "import datetime as dt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import data\n",
    "Loans_df = pd.read_csv(\"Loan_Data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>default</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8153374</td>\n",
       "      <td>0</td>\n",
       "      <td>5221.545193</td>\n",
       "      <td>3915.471226</td>\n",
       "      <td>78039.38546</td>\n",
       "      <td>5</td>\n",
       "      <td>605</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7442532</td>\n",
       "      <td>5</td>\n",
       "      <td>1958.928726</td>\n",
       "      <td>8228.752520</td>\n",
       "      <td>26648.43525</td>\n",
       "      <td>2</td>\n",
       "      <td>572</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2256073</td>\n",
       "      <td>0</td>\n",
       "      <td>3363.009259</td>\n",
       "      <td>2027.830850</td>\n",
       "      <td>65866.71246</td>\n",
       "      <td>4</td>\n",
       "      <td>602</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4885975</td>\n",
       "      <td>0</td>\n",
       "      <td>4766.648001</td>\n",
       "      <td>2501.730397</td>\n",
       "      <td>74356.88347</td>\n",
       "      <td>5</td>\n",
       "      <td>612</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4700614</td>\n",
       "      <td>1</td>\n",
       "      <td>1345.827718</td>\n",
       "      <td>1768.826187</td>\n",
       "      <td>23448.32631</td>\n",
       "      <td>6</td>\n",
       "      <td>631</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "0      8153374                         0           5221.545193   \n",
       "1      7442532                         5           1958.928726   \n",
       "2      2256073                         0           3363.009259   \n",
       "3      4885975                         0           4766.648001   \n",
       "4      4700614                         1           1345.827718   \n",
       "\n",
       "   total_debt_outstanding       income  years_employed  fico_score  default  \n",
       "0             3915.471226  78039.38546               5         605        0  \n",
       "1             8228.752520  26648.43525               2         572        1  \n",
       "2             2027.830850  65866.71246               4         602        0  \n",
       "3             2501.730397  74356.88347               5         612        0  \n",
       "4             1768.826187  23448.32631               6         631        0  "
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 10000 entries, 0 to 9999\n",
      "Data columns (total 8 columns):\n",
      " #   Column                    Non-Null Count  Dtype  \n",
      "---  ------                    --------------  -----  \n",
      " 0   customer_id               10000 non-null  int64  \n",
      " 1   credit_lines_outstanding  10000 non-null  int64  \n",
      " 2   loan_amt_outstanding      10000 non-null  float64\n",
      " 3   total_debt_outstanding    10000 non-null  float64\n",
      " 4   income                    10000 non-null  float64\n",
      " 5   years_employed            10000 non-null  int64  \n",
      " 6   fico_score                10000 non-null  int64  \n",
      " 7   default                   10000 non-null  int64  \n",
      "dtypes: float64(3), int64(5)\n",
      "memory usage: 625.1 KB\n"
     ]
    }
   ],
   "source": [
    "Loans_df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>default</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1.000000e+04</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "      <td>10000.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.974577e+06</td>\n",
       "      <td>1.461200</td>\n",
       "      <td>4159.677034</td>\n",
       "      <td>8718.916797</td>\n",
       "      <td>70039.901401</td>\n",
       "      <td>4.552800</td>\n",
       "      <td>637.557700</td>\n",
       "      <td>0.185100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.293890e+06</td>\n",
       "      <td>1.743846</td>\n",
       "      <td>1421.399078</td>\n",
       "      <td>6627.164762</td>\n",
       "      <td>20072.214143</td>\n",
       "      <td>1.566862</td>\n",
       "      <td>60.657906</td>\n",
       "      <td>0.388398</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000324e+06</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>46.783973</td>\n",
       "      <td>31.652732</td>\n",
       "      <td>1000.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>408.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.977661e+06</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3154.235371</td>\n",
       "      <td>4199.836020</td>\n",
       "      <td>56539.867903</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>597.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>4.989502e+06</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>4052.377228</td>\n",
       "      <td>6732.407217</td>\n",
       "      <td>70085.826330</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>638.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>6.967210e+06</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>5052.898103</td>\n",
       "      <td>11272.263740</td>\n",
       "      <td>83429.166133</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>679.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>8.999789e+06</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>10750.677810</td>\n",
       "      <td>43688.784100</td>\n",
       "      <td>148412.180500</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>850.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "count  1.000000e+04              10000.000000          10000.000000   \n",
       "mean   4.974577e+06                  1.461200           4159.677034   \n",
       "std    2.293890e+06                  1.743846           1421.399078   \n",
       "min    1.000324e+06                  0.000000             46.783973   \n",
       "25%    2.977661e+06                  0.000000           3154.235371   \n",
       "50%    4.989502e+06                  1.000000           4052.377228   \n",
       "75%    6.967210e+06                  2.000000           5052.898103   \n",
       "max    8.999789e+06                  5.000000          10750.677810   \n",
       "\n",
       "       total_debt_outstanding         income  years_employed    fico_score  \\\n",
       "count            10000.000000   10000.000000    10000.000000  10000.000000   \n",
       "mean              8718.916797   70039.901401        4.552800    637.557700   \n",
       "std               6627.164762   20072.214143        1.566862     60.657906   \n",
       "min                 31.652732    1000.000000        0.000000    408.000000   \n",
       "25%               4199.836020   56539.867903        3.000000    597.000000   \n",
       "50%               6732.407217   70085.826330        5.000000    638.000000   \n",
       "75%              11272.263740   83429.166133        6.000000    679.000000   \n",
       "max              43688.784100  148412.180500       10.000000    850.000000   \n",
       "\n",
       "            default  \n",
       "count  10000.000000  \n",
       "mean       0.185100  \n",
       "std        0.388398  \n",
       "min        0.000000  \n",
       "25%        0.000000  \n",
       "50%        0.000000  \n",
       "75%        0.000000  \n",
       "max        1.000000  "
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>default</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9990</th>\n",
       "      <td>4988839</td>\n",
       "      <td>3</td>\n",
       "      <td>5414.335510</td>\n",
       "      <td>13448.430230</td>\n",
       "      <td>81748.34618</td>\n",
       "      <td>6</td>\n",
       "      <td>559</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9991</th>\n",
       "      <td>2243629</td>\n",
       "      <td>5</td>\n",
       "      <td>5181.244374</td>\n",
       "      <td>23957.565560</td>\n",
       "      <td>82865.37500</td>\n",
       "      <td>2</td>\n",
       "      <td>559</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9992</th>\n",
       "      <td>2360357</td>\n",
       "      <td>1</td>\n",
       "      <td>2730.172218</td>\n",
       "      <td>4015.958697</td>\n",
       "      <td>50767.13518</td>\n",
       "      <td>6</td>\n",
       "      <td>569</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9993</th>\n",
       "      <td>4668682</td>\n",
       "      <td>1</td>\n",
       "      <td>4337.978847</td>\n",
       "      <td>7277.852831</td>\n",
       "      <td>74551.25247</td>\n",
       "      <td>6</td>\n",
       "      <td>728</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9994</th>\n",
       "      <td>4826911</td>\n",
       "      <td>1</td>\n",
       "      <td>2167.752325</td>\n",
       "      <td>4913.969275</td>\n",
       "      <td>51726.62423</td>\n",
       "      <td>6</td>\n",
       "      <td>672</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9995</th>\n",
       "      <td>3972488</td>\n",
       "      <td>0</td>\n",
       "      <td>3033.647103</td>\n",
       "      <td>2553.733144</td>\n",
       "      <td>42691.62787</td>\n",
       "      <td>5</td>\n",
       "      <td>697</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9996</th>\n",
       "      <td>6184073</td>\n",
       "      <td>1</td>\n",
       "      <td>4146.239304</td>\n",
       "      <td>5458.163525</td>\n",
       "      <td>79969.50521</td>\n",
       "      <td>8</td>\n",
       "      <td>615</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9997</th>\n",
       "      <td>6694516</td>\n",
       "      <td>2</td>\n",
       "      <td>3088.223727</td>\n",
       "      <td>4813.090925</td>\n",
       "      <td>38192.67591</td>\n",
       "      <td>5</td>\n",
       "      <td>596</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9998</th>\n",
       "      <td>3942961</td>\n",
       "      <td>0</td>\n",
       "      <td>3288.901666</td>\n",
       "      <td>1043.099660</td>\n",
       "      <td>50929.37206</td>\n",
       "      <td>2</td>\n",
       "      <td>647</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9999</th>\n",
       "      <td>5533570</td>\n",
       "      <td>1</td>\n",
       "      <td>1917.652480</td>\n",
       "      <td>3050.248203</td>\n",
       "      <td>30611.62821</td>\n",
       "      <td>6</td>\n",
       "      <td>757</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "9990      4988839                         3           5414.335510   \n",
       "9991      2243629                         5           5181.244374   \n",
       "9992      2360357                         1           2730.172218   \n",
       "9993      4668682                         1           4337.978847   \n",
       "9994      4826911                         1           2167.752325   \n",
       "9995      3972488                         0           3033.647103   \n",
       "9996      6184073                         1           4146.239304   \n",
       "9997      6694516                         2           3088.223727   \n",
       "9998      3942961                         0           3288.901666   \n",
       "9999      5533570                         1           1917.652480   \n",
       "\n",
       "      total_debt_outstanding       income  years_employed  fico_score  default  \n",
       "9990            13448.430230  81748.34618               6         559        0  \n",
       "9991            23957.565560  82865.37500               2         559        1  \n",
       "9992             4015.958697  50767.13518               6         569        0  \n",
       "9993             7277.852831  74551.25247               6         728        0  \n",
       "9994             4913.969275  51726.62423               6         672        0  \n",
       "9995             2553.733144  42691.62787               5         697        0  \n",
       "9996             5458.163525  79969.50521               8         615        0  \n",
       "9997             4813.090925  38192.67591               5         596        0  \n",
       "9998             1043.099660  50929.37206               2         647        0  \n",
       "9999             3050.248203  30611.62821               6         757        0  "
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df.tail(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "default\n",
       "0    8149\n",
       "1    1851\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df['default'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exploratory Data Analysis\n",
    "\n",
    "\n",
    "Using quick visualisations, we can explore the relationship between different variables in the dataset.\n",
    "\n",
    "Let's start with a dual histogram of the FICO score of the borrowers, depending on the deafault (i.e. if a borrower defaults)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'FICO')"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df['fico_score'].hist(bins=30,alpha=0.6,label='default=1')\n",
    "plt.xlabel('FICO')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'FICO')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAEGCAYAAACevtWaAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8/fFQqAAAACXBIWXMAAAsTAAALEwEAmpwYAAAXFklEQVR4nO3df5CV1Z3n8fdXQHpAFhQnxAVruxMxRmNA7DhGjdUbnI1mEM0UGiazRqfYsGuc0UxtMMlspcwmJjMaXQfKrBlKZ6IpNkSJAprJaBbSVdl1BwVD/AEaMSShCSoQf4ARBfvsH/eADd3Yt+F23+5z36+qrn6e55zn3nMPzadPn/vc80RKCUlSWY6odwMkSbVnuEtSgQx3SSqQ4S5JBTLcJalAw+vdAIBjjz02NTc391rvtddeY/To0f3foCHEPunOPtmf/dFdKX2yZs2abSmlP+ypbFCEe3NzM6tXr+61Xnt7O21tbf3foCHEPunOPtmf/dFdKX0SEb8+WJnTMpJUIMNdkgpkuEtSgQbFnLukcuzevZuOjg527dpV76Yc1NixY1m/fn29m1G1pqYmJk2axIgRI6o+x3CXVFMdHR2MGTOG5uZmIqLezenRjh07GDNmTL2bUZWUEtu3b6ejo4OWlpaqz3NaRlJN7dq1i/Hjxw/aYB9qIoLx48f3+S8hw11SzRnstXUo/Wm4S1KBnHOX1K++dO8TNX28v/3TU/tU/ytf+QpHHXUUn//853ss37p1KzNmzODNN99kwYIFfOQjH+nT43/nO99h9erV3HrrrSxdupQTTzyRk08+uapzt2/fzqxZs3j00Ue54ooruPXWW/v03O/EcJdq5f5rqqt34fz+bYf6ZMWKFZx66qncfvvth/1YS5cuZcaMGVWHe1NTE1/72td48sknefLJJw/7+btyWkZScb7+9a9z4okncs455/DMM88A8Nxzz3H++edz+umn87GPfYynn36atWvXcu2117Js2TKmTp3K66+/zpVXXklrayunnHIK11133b7HbG5uZtu2bQCsXr262/IFDz/8MMuXL2fevHlMnTqV5557rtd2jh49mnPOOYempqbavfjMkbukoqxZs4bFixezdu1a9uzZw7Rp0zj99NOZO3cu3/72t5k8eTIrV67ks5/9LCtXruSrX/3qvmkVqPxiOOaYY3jrrbeYPn06jz/+OB/84Ad7fd6zzjqLmTNnMmPGDGbNmgXAN7/5TRYtWtSt7rnnnsuCBQtq+8IPYLhLKspPf/pTPvGJTzBq1CgAZs6cya5du3j44Ye55JJLAOjs7GT37t09nn/33XezcOFC9uzZw5YtW1i3bl1V4d6TefPmMW/evEN7IYfJcJdUvM7OTsaNG8fatWuBg3+IaePGjdx00008+uijHH300VxxxRX7ri8fPnw4nZ2dAFVfc17Pkbtz7pKKcu6557J06VJef/11duzYwf3338+oUaNoaWnhnnvuASqf+vz5z3/e7dxXX32V0aNHM3bsWF544QV+9KMf7Strbm5mzZo1APzgBz/o8bnHjBnDjh079u3PmzePtWvXdvvq72AHR+6S+llfL108XNOmTeOTn/wkU6ZM4V3vehcf+tCHAFi0aBFXXnkl119/PW+88Qaf+tSnmDJlyn7nTpkyhdNOO42TTjqJ448/nrPPPntf2XXXXcecOXP48pe/fNC14GfPns1nPvMZFixYwJIlS3jve9/ba3ubm5t59dVXefPNN1m6dCkPPfRQ1VfbvJNIKR32gxyu1tbW5M06Do190l3d+mSQXgo50P2xfv163v/+9w/Y8x2KobS2zF499WtErEkptfZU35G79E6qDWxpkHHOXZIKZLhLUoGqCveI+OuIeCoinoyI70VEU0S0RMSqiNgQEd+PiCNz3ZF5f0Mub+7XVyBJ6qbXOfeImAhcDZycUno9Iu4GZgMfB25JKS2OiG8Dc4Db8veXUkonRMRs4Abgk/32CqShZpC+8aqyVDstMxz4g4gYDowCtgAfBZbk8juBi/P2RXmfXD49XNxZkgZUryP3lNLmiLgJ+A3wOvAQsAZ4OaW0J1frACbm7YnApnzunoh4BRgPbOv6uBExF5gLMGHCBNrb23tt7M6dO6uq10jsk+5q2iedPV5lNjBq9BoG+mdk7Nix+32QZ+SPv1DTx3/jj2/oU/1vfOMbHHXUUVx99dX7jr311lv72rht2zYuueQSdu/ezY033shZZ53Vp8dftGgRjz32GDfffDMPPPAAJ5xwAieddFLV5998883cddddDBs2jBtvvJHzzjuvx3q7du3q079jNdMyR1MZjbcALwP3AOdX/QwHkVJaCCyEynXu1VyH6zXd3dkn3dW0T+p5KWTbZTV5mHpc577fNeR9uKlzNY7s4/XpI0eOZOTIkfu1qet17j/84Q+ZOnXqIS/529TUxJFHHsmYMWN48MEHGTFixL4PTvVm3bp13Hfffaxfv57f/va3nHfeefziF79g2LBhPT7PaaedVnW7qpmWOQ/YmFLamlLaDdwLnA2My9M0AJOAzXl7M3A8QC4fC2yvukWSdJiGypK/y5YtY/bs2YwcOZKWlhZOOOEEHnnkkZr0QTUfYvoNcGZEjKIyLTMdWA38BJgFLAYuB5bl+svz/v/L5SvTYPgYrKSGMJSW/N28eTNnnnnmvuOTJk1i8+bN3eofimrm3FdFxBLgMWAP8DMq0yk/BBZHxPX52B35lDuA70bEBuB3VK6skaQB4ZK/FVUtP5BSug647oDDvwTO6KHuLuCSw2+aJNXGYF3yd+LEiWzatGnf8Y6ODiZOnNit/qHwE6qSijKUlvydOXMmixcv5o033mDjxo08++yznHFGtzHzIXHhMEn9a4A/jDWUlvw95ZRTuPTSSzn55JMZPnw43/rWt3q8UuZQuOTvEGefdFfMpZA1CkWX/O2uEZb8dVpGkgpkuEtSgQx3STU3GKZ7S3Io/Wm4S6qppqYmtm/fbsDXSEqJ7du309TU1KfzvFpGjcnb5/WbSZMm0dHRwdatW+vdlIPatWtXn8Oynpqampg0aVKfzjHcJdXUiBEjaGlpqXcz3lF7e3ufFuEaipyWkaQCGe6SVCDDXZIKZLhLUoEMd0kqkOEuSQUy3CWpQIa7JBXIcJekAhnuklQgw12SCmS4S1KBDHdJKpDhLkkFMtwlqUCGuyQVyHCXpAIZ7pJUIMNdkgrkPVSlwaram3hfOL9/26EhyZG7JBXIcJekAjkto7Lcfw10tlY/pSEVypG7JBXIcJekAhnuklQgw12SCmS4S1KBDHdJKpDhLkkFqircI2JcRCyJiKcjYn1EfDgijomIH0fEs/n70bluRMSCiNgQEY9HxLT+fQmSpANVO3KfD/xLSukkYAqwHvgisCKlNBlYkfcBLgAm56+5wG01bbEkqVe9hntEjAXOBe4ASCm9mVJ6GbgIuDNXuxO4OG9fBNyVKv4VGBcRx9W43ZKkd1DN8gMtwFbgnyJiCrAGuAaYkFLakus8D0zI2xOBTV3O78jHtnQ5RkTMpTKyZ8KECbS3t/fakJ07d1ZVr5HYJwfobGUno2nvbK13SwZOL//+/ox01wh9Uk24DwemAX+VUloVEfN5ewoGgJRSiojUlydOKS0EFgK0tramtra2Xs9pb2+nmnqNxD45wP3X0N7ZStsRq+vdkoHTdtk7Fvsz0l0j9Ek1c+4dQEdKaVXeX0Il7F/YO92Sv7+YyzcDx3c5f1I+JkkaIL2Ge0rpeWBTRLwvH5oOrAOWA5fnY5cDy/L2cuDT+aqZM4FXukzfSJIGQLVL/v4VsCgijgR+CfwFlV8Md0fEHODXwKW57j8DHwc2AL/PdSVJA6iqcE8prQV6eodqeg91E3DV4TVLknQ4vFmHNNT1dmOSvTcv8V6rDcXlBySpQIa7JBXIcJekAhnuklQg31DV0NDbm4aS9uPIXZIKZLhLUoEMd0kqkOEuSQUy3CWpQIa7JBXIcJekAhnuklQgw12SCmS4S1KBDHdJKpDhLkkFMtwlqUCGuyQVyHCXpAIZ7pJUIMNdkgpkuEtSgQx3SSqQ4S5JBfIG2VKjqPYm4xfO7992aEA4cpekAhnuklQgw12SCmS4S1KBDHdJKpDhLkkFMtwlqUCGuyQVyHCXpAIZ7pJUIMNdkgpkuEtSgaoO94gYFhE/i4gH8n5LRKyKiA0R8f2IODIfH5n3N+Ty5n5quyTpIPoycr8GWN9l/wbglpTSCcBLwJx8fA7wUj5+S64nSRpAVYV7REwC/gS4Pe8H8FFgSa5yJ3Bx3r4o75PLp+f6kqQBUu3I/e+Ba4HOvD8eeDmltCfvdwAT8/ZEYBNALn8l15ckDZBeb9YRETOAF1NKayKirVZPHBFzgbkAEyZMoL29vddzdu7cWVW9RtIwfdLZWnXVnYymvQ/1S9fn/miAn6dG+H9TzZ2YzgZmRsTHgSbg3wDzgXERMTyPzicBm3P9zcDxQEdEDAfGAtsPfNCU0kJgIUBra2tqa2vrtSHt7e1UU6+RNEyfVHsXIaC9s5W2I1b3Y2OGlj73R9tl/deYQaIR/t/0Oi2TUvpSSmlSSqkZmA2sTCn9OfATYFaudjmwLG8vz/vk8pUppVTTVkuS3tHh3EP1C8DiiLge+BlwRz5+B/DdiNgA/I7KLwSpZ30YkUuqXp/CPaXUDrTn7V8CZ/RQZxdwSQ3aJkk6RH5CVZIKZLhLUoEMd0kqkOEuSQUy3CWpQIa7JBXIcJekAh3Oh5gklajaD5ZdOL9/26HD4shdkgpkuEtSgQx3SSqQ4S5JBTLcJalAhrskFchwl6QCGe6SVCDDXZIKZLhLUoEMd0kqkOEuSQUy3CWpQIa7JBXIJX/VP6pdNlZSv3DkLkkFMtwlqUCGuyQVyHCXpAIZ7pJUIMNdkgpkuEtSgQx3SSqQ4S5JBTLcJalAhrskFchwl6QCGe6SVCDDXZIKZLhLUoFcz13SoenLmv0Xzu+/dqhHjtwlqUC9hntEHB8RP4mIdRHxVERck48fExE/john8/ej8/GIiAURsSEiHo+Iaf39IiRJ+6tm5L4H+K8ppZOBM4GrIuJk4IvAipTSZGBF3ge4AJicv+YCt9W81ZKkd9RruKeUtqSUHsvbO4D1wETgIuDOXO1O4OK8fRFwV6r4V2BcRBxX64ZLkg6uT2+oRkQzcBqwCpiQUtqSi54HJuTticCmLqd15GNbuhwjIuZSGdkzYcIE2tvbe33+nTt3VlWvkQzaPulsrdtT72Q07XV8/sFmUPTHIPsZHbT/b2qo6nCPiKOAHwCfSym9GhH7ylJKKSJSX544pbQQWAjQ2tqa2traej2nvb2dauo1kkHbJ325kqLG2jtbaTtidd2ef7AZFP3Rdll9n/8Ag/b/TQ1VdbVMRIygEuyLUkr35sMv7J1uyd9fzMc3A8d3OX1SPiZJGiDVXC0TwB3A+pTS/+hStBy4PG9fDizrcvzT+aqZM4FXukzfSJIGQDXTMmcDlwFPRMTafOxvgL8D7o6IOcCvgUtz2T8DHwc2AL8H/qKWDVad1XG6RVL1eg33lNL/AeIgxdN7qJ+Aqw6zXZKkw+AnVCWpQK4to0Fv1cbf9Vrnj1qOGYCWSEOHI3dJKpAjdxWh6+j+tXfvYdXz3Uf7ju7VSAx3qQungFQKw111U02QSjo0hrsahr9M1Eh8Q1WSCuTIXf3CUbL2U+0nm70dX804cpekAhnuklQgp2XUZ40+5VLt6/eSSdWTI3dJKpDhLkkFMtwlqUDOucsbcEgFcuQuSQUy3CWpQIa7JBXIcJekAvmGqvbT6B9QkkphuEv9xBt/qJ4Md6mO/AWg/uKcuyQVyJF7A/nSvU/0ePziDufZNUi47nvNOHKXpAI5ci/ZAaMgR+hS43DkLkkFcuQuDXJeUdMD5+Z7ZbgPcgd7E3SvDxzx+gC1RNJQYrgXwKtgJB3IcJcK8E5TN6+9ew+rnv9d403dNDjfUJWkAjlyH4Iu7rhx3/a2d3+Ui5//X3VsjaTByHCvo97eLJWkQ2W4Sw2i2uWcnZsvg+EuqVwHux6+s3X/sgKvhzfc+4lTLpLqyXAfRLq+USrVi5+ILUO/hHtEnA/MB4YBt6eU/q4/nqde+joqN7SlQa7a5Qz6os5TPTUP94gYBnwL+GOgA3g0IpanlNbV+rkk1Yej+8GvP0buZwAbUkq/BIiIxcBFQL+FezUj6b/901OrfpzeRtoXV9UqqbH5C6C+IqVU2weMmAWcn1L6T3n/MuCPUkp/eUC9ucDcvPs+4JkqHv5YYFsNm1sC+6Q7+2R/9kd3pfTJv0sp/WFPBXV7QzWltBBY2JdzImJ1Sqm1n5o0JNkn3dkn+7M/umuEPumPtWU2A8d32Z+Uj0mSBkh/hPujwOSIaImII4HZwPJ+eB5J0kHUfFompbQnIv4SeJDKpZD/mFJ6qkYP36dpnAZhn3Rnn+zP/uiu+D6p+RuqkqT6cz13SSqQ4S5JBRp04R4RwyLiZxHxQN5viYhVEbEhIr6f36QlIkbm/Q25vLmuDe8nEfGriHgiItZGxOp87JiI+HFEPJu/H52PR0QsyH3yeERMq2/r+0dEjIuIJRHxdESsj4gPN3KfRMT78s/H3q9XI+JzDd4nfx0RT0XEkxHxvYhoarQsGXThDlwDrO+yfwNwS0rpBOAlYE4+Pgd4KR+/Jdcr1b9PKU3tcl3uF4EVKaXJwIq8D3ABMDl/zQVuG/CWDoz5wL+klE4CplD5eWnYPkkpPZN/PqYCpwO/B+6jQfskIiYCVwOtKaUPULmwYzaNliUppUHzReWa+BXAR4EHgKDyKbLhufzDwIN5+0Hgw3l7eK4X9X4N/dAnvwKOPeDYM8Bxefs44Jm8/Q/An/VUr5QvYCyw8cB/60bukwP64T8A/7eR+wSYCGwCjsnZ8ADwsUbLksE2cv974FqgM++PB15OKe3J+x1U/uHg7X9AcvkruX5pEvBQRKzJSzYATEgpbcnbzwMT8va+Psm69lcpWoCtwD/l6bvbI2I0jd0nXc0Gvpe3G7JPUkqbgZuA3wBbqGTDGhosSwZNuEfEDODFlNKaerdlkDknpTSNyp/SV0XEuV0LU2W40UjXsw4HpgG3pZROA17j7ekGoCH7BIA8hzwTuOfAskbqk/zewkVUBgL/FhgNnF/XRtXBoAl34GxgZkT8ClhMZWpmPjAuIvZ+2KrrUgb7ljnI5WOB7QPZ4IGQRyGklF6kMo96BvBCRBwHkL+/mKs3wtIPHUBHSmlV3l9CJewbuU/2ugB4LKX0Qt5v1D45D9iYUtqaUtoN3EslXxoqSwZNuKeUvpRSmpRSaqbyp+XKlNKfAz8BZuVqlwPL8vbyvE8uX5lHJ8WIiNERMWbvNpX51CfZ/7Uf2CefzldDnAm80uXP8iKklJ4HNkXE+/Kh6VSWk27YPuniz3h7SgYat09+A5wZEaMiInj7Z6SxsqTek/4HeUOkDXggb78HeATYQOXPzZH5eFPe35DL31PvdvdDP7wH+Hn+egr4b/n4eCpvPD8L/G/gmHw8qNwo5TngCSpXC9T9dfRDv0wFVgOPA0uBo+0TRlMZbY7tcqxh+wT478DTVAZD3wVGNlqWuPyAJBVo0EzLSJJqx3CXpAIZ7pJUIMNdkgpkuEtSgQx3NaSIeOuAlRSbI6It8mqkuc4FEbE6ItblpQ5u7lI2N69K+XREPBIR59TnlUg9q/lt9qQh4vVUWUVxn65LvUbEB4BbgT9JKT0dEcOorKC4d6mM/0xlaYhtecncpRFxRqp8yEqqO0fuUs+uBb6eUnoaIKX0Vkpp79K4XwDmpZS25bLHgDuBq+rSUqkHhrsa1R90mZK5r4fyD1BZSbAnp/RQtjoflwYFp2XUqLpNy0glceQu9ewpKnc16sm6HspOz+dIg4LhLvXsm8DfRMSJABFxRET8l1x2I3BDRIzPZVOBK4D/WYd2Sj1yWkbqQUrp8Yj4HPC9iBhF5UYXD+Sy5fk+nQ9HRAJ2AP8xlbVsroY4V4WUpAI5LSNJBTLcJalAhrskFchwl6QCGe6SVCDDXZIKZLhLUoH+P9uZZ3B/HFzJAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df[Loans_df['default']==1]['fico_score'].hist(bins=30,alpha=0.6,label='default=1')\n",
    "Loans_df[Loans_df['default']==0]['fico_score'].hist(bins=30,alpha=0.6,label='default=0')\n",
    "plt.legend()\n",
    "plt.xlabel('FICO')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'income')"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df[Loans_df['default']==1]['income'].hist(bins=30,alpha=0.6,label='default=1')\n",
    "Loans_df[Loans_df['default']==0]['income'].hist(bins=30,alpha=0.6,label='default=0')\n",
    "plt.legend()\n",
    "plt.xlabel('income')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.JointGrid at 0x1da89e80>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x432 with 3 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.jointplot(x='fico_score',y='income',data=Loans_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'loan_amt_outstanding')"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df[Loans_df['default']==1]['loan_amt_outstanding'].hist(bins=30,alpha=0.6,label='default=1')\n",
    "Loans_df[Loans_df['default']==0]['loan_amt_outstanding'].hist(bins=30,alpha=0.6,label='default=0')\n",
    "plt.legend()\n",
    "plt.xlabel('loan_amt_outstanding')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'income')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df[Loans_df['fico_score']>=600]['income'].hist(bins=30,alpha=0.6,label='fico_score >= 600')\n",
    "Loans_df[Loans_df['fico_score']<600]['income'].hist(bins=30,alpha=0.6,label='fico_score < 600')\n",
    "plt.legend()\n",
    "plt.xlabel('income')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'loan_amt_outstanding')"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df[Loans_df['fico_score']>=600]['loan_amt_outstanding'].hist(bins=30,alpha=0.6,label='fico_score >= 600')\n",
    "Loans_df[Loans_df['fico_score']<600]['loan_amt_outstanding'].hist(bins=30,alpha=0.6,label='fico_score < 600')\n",
    "plt.legend()\n",
    "plt.xlabel('loan_amt_outstanding')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Total Employee Length')"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#emp_length variable\n",
    "df = Loans_df.groupby('years_employed')['years_employed'].count().reset_index(name='count').sort_values('years_employed',ascending=True)\n",
    "fig, ax = plt.subplots()\n",
    "fig.set_size_inches(14,6)\n",
    "q = sns.barplot(x=\"years_employed\", y=\"count\", data=df)\n",
    "q.set_xticklabels(q.get_xticklabels(),rotation=30)\n",
    "plt.title('Total Employee Length')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'credit lines outstanding ')"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#credit_lines_outstanding variable\n",
    "df = Loans_df.groupby('credit_lines_outstanding')['credit_lines_outstanding'].count().reset_index(name='count').sort_values('credit_lines_outstanding',ascending=True)\n",
    "fig, ax = plt.subplots()\n",
    "fig.set_size_inches(14,6)\n",
    "q = sns.barplot(x=\"credit_lines_outstanding\", y=\"count\", data=df)\n",
    "q.set_xticklabels(q.get_xticklabels(),rotation=30)\n",
    "plt.title('credit lines outstanding ')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 648x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(9,5))\n",
    "sns.countplot(x=Loans_df['years_employed'],hue=Loans_df['default'])\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 648x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(9,5))\n",
    "sns.countplot(x=Loans_df['credit_lines_outstanding'],hue=Loans_df['default'])\n",
    "plt.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "scrolled": true
   },
   "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>credit_lines_outstanding</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>4128</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2590</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>902</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>599</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>484</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5</td>\n",
       "      <td>1297</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   credit_lines_outstanding  count\n",
       "0                         0   4128\n",
       "1                         1   2590\n",
       "2                         2    902\n",
       "3                         3    599\n",
       "4                         4    484\n",
       "5                         5   1297"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df.groupby('credit_lines_outstanding')['default'].count().reset_index(name='count').sort_values('credit_lines_outstanding',ascending=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [],
   "source": [
    "Loans_df['ratio_income_Totdebt'] = Loans_df['income']/Loans_df['total_debt_outstanding']\n",
    "Loans_df['ratio_income_loan_amt'] = Loans_df['income']/Loans_df['loan_amt_outstanding']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>default</th>\n",
       "      <th>ratio_income_Totdebt</th>\n",
       "      <th>ratio_income_loan_amt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8153374</td>\n",
       "      <td>0</td>\n",
       "      <td>5221.545193</td>\n",
       "      <td>3915.471226</td>\n",
       "      <td>78039.38546</td>\n",
       "      <td>5</td>\n",
       "      <td>605</td>\n",
       "      <td>0</td>\n",
       "      <td>19.931033</td>\n",
       "      <td>14.945650</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7442532</td>\n",
       "      <td>5</td>\n",
       "      <td>1958.928726</td>\n",
       "      <td>8228.752520</td>\n",
       "      <td>26648.43525</td>\n",
       "      <td>2</td>\n",
       "      <td>572</td>\n",
       "      <td>1</td>\n",
       "      <td>3.238454</td>\n",
       "      <td>13.603576</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2256073</td>\n",
       "      <td>0</td>\n",
       "      <td>3363.009259</td>\n",
       "      <td>2027.830850</td>\n",
       "      <td>65866.71246</td>\n",
       "      <td>4</td>\n",
       "      <td>602</td>\n",
       "      <td>0</td>\n",
       "      <td>32.481364</td>\n",
       "      <td>19.585647</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4885975</td>\n",
       "      <td>0</td>\n",
       "      <td>4766.648001</td>\n",
       "      <td>2501.730397</td>\n",
       "      <td>74356.88347</td>\n",
       "      <td>5</td>\n",
       "      <td>612</td>\n",
       "      <td>0</td>\n",
       "      <td>29.722181</td>\n",
       "      <td>15.599407</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4700614</td>\n",
       "      <td>1</td>\n",
       "      <td>1345.827718</td>\n",
       "      <td>1768.826187</td>\n",
       "      <td>23448.32631</td>\n",
       "      <td>6</td>\n",
       "      <td>631</td>\n",
       "      <td>0</td>\n",
       "      <td>13.256433</td>\n",
       "      <td>17.422978</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9995</th>\n",
       "      <td>3972488</td>\n",
       "      <td>0</td>\n",
       "      <td>3033.647103</td>\n",
       "      <td>2553.733144</td>\n",
       "      <td>42691.62787</td>\n",
       "      <td>5</td>\n",
       "      <td>697</td>\n",
       "      <td>0</td>\n",
       "      <td>16.717341</td>\n",
       "      <td>14.072707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9996</th>\n",
       "      <td>6184073</td>\n",
       "      <td>1</td>\n",
       "      <td>4146.239304</td>\n",
       "      <td>5458.163525</td>\n",
       "      <td>79969.50521</td>\n",
       "      <td>8</td>\n",
       "      <td>615</td>\n",
       "      <td>0</td>\n",
       "      <td>14.651358</td>\n",
       "      <td>19.287238</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9997</th>\n",
       "      <td>6694516</td>\n",
       "      <td>2</td>\n",
       "      <td>3088.223727</td>\n",
       "      <td>4813.090925</td>\n",
       "      <td>38192.67591</td>\n",
       "      <td>5</td>\n",
       "      <td>596</td>\n",
       "      <td>0</td>\n",
       "      <td>7.935166</td>\n",
       "      <td>12.367199</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9998</th>\n",
       "      <td>3942961</td>\n",
       "      <td>0</td>\n",
       "      <td>3288.901666</td>\n",
       "      <td>1043.099660</td>\n",
       "      <td>50929.37206</td>\n",
       "      <td>2</td>\n",
       "      <td>647</td>\n",
       "      <td>0</td>\n",
       "      <td>48.825030</td>\n",
       "      <td>15.485222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9999</th>\n",
       "      <td>5533570</td>\n",
       "      <td>1</td>\n",
       "      <td>1917.652480</td>\n",
       "      <td>3050.248203</td>\n",
       "      <td>30611.62821</td>\n",
       "      <td>6</td>\n",
       "      <td>757</td>\n",
       "      <td>0</td>\n",
       "      <td>10.035783</td>\n",
       "      <td>15.963074</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10000 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "0         8153374                         0           5221.545193   \n",
       "1         7442532                         5           1958.928726   \n",
       "2         2256073                         0           3363.009259   \n",
       "3         4885975                         0           4766.648001   \n",
       "4         4700614                         1           1345.827718   \n",
       "...           ...                       ...                   ...   \n",
       "9995      3972488                         0           3033.647103   \n",
       "9996      6184073                         1           4146.239304   \n",
       "9997      6694516                         2           3088.223727   \n",
       "9998      3942961                         0           3288.901666   \n",
       "9999      5533570                         1           1917.652480   \n",
       "\n",
       "      total_debt_outstanding       income  years_employed  fico_score  \\\n",
       "0                3915.471226  78039.38546               5         605   \n",
       "1                8228.752520  26648.43525               2         572   \n",
       "2                2027.830850  65866.71246               4         602   \n",
       "3                2501.730397  74356.88347               5         612   \n",
       "4                1768.826187  23448.32631               6         631   \n",
       "...                      ...          ...             ...         ...   \n",
       "9995             2553.733144  42691.62787               5         697   \n",
       "9996             5458.163525  79969.50521               8         615   \n",
       "9997             4813.090925  38192.67591               5         596   \n",
       "9998             1043.099660  50929.37206               2         647   \n",
       "9999             3050.248203  30611.62821               6         757   \n",
       "\n",
       "      default  ratio_income_Totdebt  ratio_income_loan_amt  \n",
       "0           0             19.931033              14.945650  \n",
       "1           1              3.238454              13.603576  \n",
       "2           0             32.481364              19.585647  \n",
       "3           0             29.722181              15.599407  \n",
       "4           0             13.256433              17.422978  \n",
       "...       ...                   ...                    ...  \n",
       "9995        0             16.717341              14.072707  \n",
       "9996        0             14.651358              19.287238  \n",
       "9997        0              7.935166              12.367199  \n",
       "9998        0             48.825030              15.485222  \n",
       "9999        0             10.035783              15.963074  \n",
       "\n",
       "[10000 rows x 10 columns]"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'ratio_income_Totdebt')"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df[Loans_df['default']==1]['ratio_income_Totdebt'].hist(bins=30,alpha=0.6,label='default=1')\n",
    "Loans_df[Loans_df['default']==0]['ratio_income_Totdebt'].hist(bins=30,alpha=0.6,label='default=0')\n",
    "plt.legend()\n",
    "plt.xlabel('ratio_income_Totdebt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'ratio_income_loan_amt')"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df[Loans_df['default']==1]['ratio_income_loan_amt'].hist(bins=30,alpha=0.6,label='default=1')\n",
    "Loans_df[Loans_df['default']==0]['ratio_income_loan_amt'].hist(bins=30,alpha=0.6,label='default=0')\n",
    "plt.legend()\n",
    "plt.xlabel('ratio_income_loan_amt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'ratio_income_Totdebt')"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df[Loans_df['fico_score']>=600]['ratio_income_Totdebt'].hist(bins=30,alpha=0.6,label='fico_score >= 600')\n",
    "Loans_df[Loans_df['fico_score']<600]['ratio_income_Totdebt'].hist(bins=30,alpha=0.6,label='fico_score < 600')\n",
    "plt.legend()\n",
    "plt.xlabel('ratio_income_Totdebt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 0, 'ratio_income_loan_amt')"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "Loans_df[Loans_df['fico_score']>=600]['ratio_income_loan_amt'].hist(bins=30,alpha=0.6,label='fico_score >= 600')\n",
    "Loans_df[Loans_df['fico_score']<600]['ratio_income_loan_amt'].hist(bins=30,alpha=0.6,label='fico_score < 600')\n",
    "plt.legend()\n",
    "plt.xlabel('ratio_income_loan_amt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'credit_lines_outstanding to mean total debt')"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1AAAAGGCAYAAAB142AqAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8/fFQqAAAACXBIWXMAAAsTAAALEwEAmpwYAAArl0lEQVR4nO3de7hdVX3v//fHBBAFBSRSTMBQjFawNmpEjlalVTFoFbReoB4Bj4pU0LZHPWL1VxClR1svPagFUSPgDfAeLYqIt3pBCMhdKRFFEgMEERC1UeD7+2OOLYvN3skM7LVXkv1+Pc969lxjjjnnGGvNnazPmmOOnapCkiRJkrRu9xp1AyRJkiRpY2GAkiRJkqSeDFCSJEmS1JMBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqyQAlSUOQpJI8pC0fn+T/uxv7OCrJR9vyzkluSTJrqts6UyTZK8mKgeeXJtlrdC3SoCTz2+/N7J71T0zy1p51f5rkqfeshZLUMUBJ0pBV1aFV9Ra464f49djHz6pqq6q6bepbODyDIbBH3YOTfHvYbRpTVbtX1Temer/T3Y/psr792lheh7v7Oylp5jJASdI69P1GXJIkbfoMUJJmrCQ7JflMktVJfpHkva384CTfSfLuJL8AjkqyRZJ3JPlZkmvbsLwtB/b1uiSrkvw8yf8ad5wTk7w1yX2BLwEPasPxbknyoJ5tvdPwpiTfSPKW1s5fJflKku0H6u+Z5LtJbkxy4eBQtda/K9t2P0nyonUc+15J3pTkqiTXJTk5yf3burt8ez82XCrJYuAfgRe2vl442fGTPBw4Hvgfre6Nre4zk/wgyc1Jrk5y1ASvyUHtfbk+yRsH1m/ZXvtfJrkMeOxE7WzLRyU5rfXtV21436KBuo9u7fhVkk8mOXWi4WNr6cf9275Xt9fxTUkm/D+4teWTST7ajndxkocmeUN7/a9OsvdA/fsn+VA7/1a2c21WW7drkq+18/v6JB9Lss241+C1SS5KclPr173vab/uzvu5LkkeleT89pqcCtx73Pq/SnJBO+e/m+SR43bx2CSXtfPhw0nunXvwOylp5jJASZqR2gfMLwJXAfOBucApA1UeB1wJ7AAcA7wNeCiwEHhIq/9PbV+LgdcCTwMWABPea1FVvwb2AX7ehuNtVVU/vwfd+BvgJcADgc1bG0gyF/gP4K3Adq3800nmtA+MxwL7VNXWwOOBC9ZxnIPb4y+APwa2At67rsZV1ZeBfwZObX39s8mOX1U/BA4FvtfqbtN282vgQGAb4JnA3ybZb9yh/hx4GPAU4J/ah3eAI4Fd2+PpwEHraPKz6c6BbYClY31MsjnwWeBEutfzE8BzJunzZP14D3B/utfvya1PL1lLW54FfATYFvgBcAbd/9lzgaOB9w/UPRG4le68fBSwN/Cyti7A/wUeBDwc2Ak4atyxXgAsBnYBHkn3Xt+jft3D9/Mu2nvwufaabAd8EvjrgfWPApYArwAeQPf6LE2yxcBuXkR3HuxK97v8piH8TkqaAQxQkmaqPeg+VL6uqn5dVf9dVYP3a/y8qt5TVbcC/w0cAvxDVd1QVb+iCwb7t7ovAD5cVZe0D2RHTVMfPlxV/1VVvwVOowt3AP8TOL2qTq+q26vqTGAZ8Iy2/nbgEUm2rKpVVXXpOo7zIuBdVXVlVd0CvAHYP3d/aGPv41fVN6rq4taPi+jCy5PHVXtzVf22qi4ELgT+rJW/ADimvWdX0wW3tfl2e81uo/ugPrafPYHZwLFV9fuq+gxwTt/OtrC+P/CGqvpVVf0UeCfw4rVs9p9VdUY7/z4JzAHeVlW/pwt585Nsk2QHuvf179t5fB3w7nY8qmp5VZ1ZVWuqajXwLu76+h1bVT+vqhuAL3DHeTTl/er5fk5kT2Az4N/ae/Ap4NyB9YcA76+q71fVbVV1ErCmbTfmvVV1devnMcABffopSeMZoCTNVDsBV7UPqBO5emB5DnAf4Lw2POhG4MutHLogNlj/qilu62SuGVj+Dd2VIYAHA88fa2tr758DO7aA90K6qwOrkvxHkj9Zx3EexJ37dBVdoNhhfRu8vsdP8rgkX29DxG5q220/rtpkr8P6vi/j93PvFhIfBKysqhpYfzX9bU/34X/8azh3LdtcO7D8W+D6gQlEftt+bkX3Xm9G91qOvdfvp7sqSZIdkpzShvbdDHyU/q/flPer5/s5kYneg8HjPhh4zbhzfqe23Zjx54JD9STdLQYoSTPV1cDOa7mKMvhB7Xq6D627V9U27XH/qhr7oLmK7sPamJ3Xctxay7qpcjXwkYG2blNV962qtwG0KxtPA3YEfgR8YB37+zndB9QxO9MNGbuWbkjWfcZWtKsScwbq3qW/azn+RK/Nx+mG0+1UVfenu68m62jvmPV5X9a1n7lJBo+702SVuWs/rgd+z11fw5V3sz2Drqa70rL9wHt9v6rava3/59aeP62q+9Fdnez7+o23vv2ayvdzovdg8P28mu5q4+A5f5+q+sRAnfHnwthQven4nZS0CTFASZqpzqH7UPa2JPdtN5Q/YaKKVXU73Yf8dycZ+2Z/bpKntyqnAQcn2S3JfejuvZnMtcAD0iZhGJKPAs9K8vQks1rf9koyr12R2Lfdi7QGuIVuSN3afAL4hyS7JNmKO+5ruhX4L7orNc9MshnwJmDwvpNr6Yab3Qv+cEVksuNfC8xr97uM2Rq4oar+O8kedPd99XUa8IYk2yaZB7xqPbYd9D3gNuDwJLOT7Es3BHQyd+pHu3J0GnBMkq2TPBj433Tv0z1SVauArwDvTHK/NoHDrknGhsVtTfca39TujXvdPTjc+vZrKt/P79GF9lcn2SzJc7nze/AB4NB2hSvtd/qZSbYeqHNY+x3YDngjcOpAO4f9OylpE2KAkjQjtQ9/z6K78f5nwAq6oWWTeT2wHDi7DYX6Kt3EBVTVl4B/A77W6nxtLcf9EV0gubINNZryYUTtfp996WbAW0337fzr6P7Nvxfdh9yfAzfQ3X/yt+vY5RK6e4K+BfyE7p6wV7Vj3QS8Evgg3ZWHX9O9lmM+2X7+Isn56zj+14BLgWuSXN/KXgkcneRXdJN2nNb/leDNdEO1fkIXMj6yHtv+QVX9Dngu8FLgRrqrOF+kC4ATmagfr6J7ba4Evk13JWbJ3WnPBA6km0TkMuCXwKforu5B9xo8GriJbmKRz9yD46xvv6bs/Rx4Dw6mO29eONiXqloGvJxu4o9f0v0eHjxuNx+nOw+uBH5MN8nKtPxOStq05M7DiSVJ0rok+T5wfFV9eNRtkSRNL69ASZK0DkmenOSP2hC+g+im+/7yqNslSZp+BihJGqEkX8odf8Bz8PGP09yO4ydpx/HT2Y4N2MPopki/EXgN8Lx2/5EkaYZxCJ8kSZIk9eQVKEmSJEnqyQAlSZIkST1N9gckN1nbb799zZ8/f9TNkCRJkrSBOu+8866vqjkTrZtxAWr+/PksW7Zs1M2QJEmStIFKctVk6xzCJ0mSJEk9GaAkSZIkqScDlCRJkiT1ZICSJEmSpJ4MUJIkSZLUkwFKkiRJknoyQEmSJElSTwYoSZIkSerJACVJkiRJPRmgJEmSJKknA5QkSZIk9WSAkiRJkqSeDFCSJEmS1NPsUTdAkiRJ2pgd8z+fN+omaC3e+NFPTen+vAIlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkSZKkngxQkiRJktTT0AJUkp2SfD3JZUkuTfJ3rXy7JGcmuaL93LaVJ8mxSZYnuSjJowf2dVCrf0WSgwbKH5Pk4rbNsUkyrP5IkiRJ0jCvQN0KvKaqdgP2BA5LshtwBHBWVS0AzmrPAfYBFrTHIcBx0AUu4EjgccAewJFjoavVefnAdouH2B9JkiRJM9zQAlRVraqq89vyr4AfAnOBfYGTWrWTgP3a8r7AydU5G9gmyY7A04Ezq+qGqvolcCawuK27X1WdXVUFnDywL0mSJEmactNyD1SS+cCjgO8DO1TVqrbqGmCHtjwXuHpgsxWtbG3lKyYon+j4hyRZlmTZ6tWr71lnJEmSJM1YQw9QSbYCPg38fVXdPLiuXTmqYbehqk6oqkVVtWjOnDnDPpwkSZKkTdRQA1SSzejC08eq6jOt+No2/I7287pWvhLYaWDzea1sbeXzJiiXJEmSpKEY5ix8AT4E/LCq3jWwaikwNpPeQcDnB8oPbLPx7Qnc1Ib6nQHsnWTbNnnE3sAZbd3NSfZsxzpwYF+SJEmSNOVmD3HfTwBeDFyc5IJW9o/A24DTkrwUuAp4QVt3OvAMYDnwG+AlAFV1Q5K3AOe2ekdX1Q1t+ZXAicCWwJfaQ5IkSZKGYmgBqqq+DUz2d5meMkH9Ag6bZF9LgCUTlC8DHnEPmilJkiRJvU3LLHySJEmStCkwQEmSJElSTwYoSZIkSerJACVJkiRJPRmgJEmSJKknA5QkSZIk9WSAkiRJkqSeDFCSJEmS1JMBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqyQAlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkSZKkngxQkiRJktSTAUqSJEmSejJASZIkSVJPBihJkiRJ6skAJUmSJEk9GaAkSZIkqScDlCRJkiT1ZICSJEmSpJ4MUJIkSZLUkwFKkiRJknoyQEmSJElSTwYoSZIkSerJACVJkiRJPQ0tQCVZkuS6JJcMlJ2a5IL2+GmSC1r5/CS/HVh3/MA2j0lycZLlSY5Nkla+XZIzk1zRfm47rL5IkiRJEgz3CtSJwOLBgqp6YVUtrKqFwKeBzwys/vHYuqo6dKD8OODlwIL2GNvnEcBZVbUAOKs9lyRJkqShGVqAqqpvATdMtK5dRXoB8Im17SPJjsD9qursqirgZGC/tnpf4KS2fNJAuSRJkiQNxajugXoicG1VXTFQtkuSHyT5ZpIntrK5wIqBOitaGcAOVbWqLV8D7DDUFkuSJEma8WaP6LgHcOerT6uAnavqF0keA3wuye59d1ZVlaQmW5/kEOAQgJ133vluNlmSJEnSTDftV6CSzAaeC5w6VlZVa6rqF235PODHwEOBlcC8gc3ntTKAa9sQv7GhftdNdsyqOqGqFlXVojlz5kxldyRJkiTNIKMYwvdU4EdV9YeheUnmJJnVlv+YbrKIK9sQvZuT7NnumzoQ+HzbbClwUFs+aKBckiRJkoZimNOYfwL4HvCwJCuSvLSt2p+7Th7xJOCiNq35p4BDq2psAopXAh8EltNdmfpSK38b8LQkV9CFsrcNqy+SJEmSBEO8B6qqDpik/OAJyj5NN635RPWXAY+YoPwXwFPuWSslSZIkqb9RzcInSZIkSRsdA5QkSZIk9WSAkiRJkqSeDFCSJEmS1JMBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqyQAlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkSZKkngxQkiRJktTT7FE3QJIkaWP13td8YdRN0Foc/s5njboJ2gR5BUqSJEmSejJASZIkSVJPBihJkiRJ6skAJUmSJEk9GaAkSZIkqScDlCRJkiT1ZICSJEmSpJ4MUJIkSZLUkwFKkiRJknoyQEmSJElSTwYoSZIkSerJACVJkiRJPRmgJEmSJKknA5QkSZIk9WSAkiRJkqSeDFCSJEmS1NPQAlSSJUmuS3LJQNlRSVYmuaA9njGw7g1Jlie5PMnTB8oXt7LlSY4YKN8lyfdb+alJNh9WXyRJkiQJhnsF6kRg8QTl766qhe1xOkCS3YD9gd3bNv+eZFaSWcD7gH2A3YADWl2At7d9PQT4JfDSIfZFkiRJkoYXoKrqW8ANPavvC5xSVWuq6ifAcmCP9lheVVdW1e+AU4B9kwT4S+BTbfuTgP2msv2SJEmSNN4o7oE6PMlFbYjftq1sLnD1QJ0VrWyy8gcAN1bVrePKJUmSJGlopjtAHQfsCiwEVgHvnI6DJjkkybIky1avXj0dh5QkSZK0CZrWAFVV11bVbVV1O/ABuiF6ACuBnQaqzmtlk5X/Atgmyexx5ZMd94SqWlRVi+bMmTM1nZEkSZI040xrgEqy48DT5wBjM/QtBfZPskWSXYAFwDnAucCCNuPe5nQTTSytqgK+DjyvbX8Q8Pnp6IMkSZKkmWv2uqvcPUk+AewFbJ9kBXAksFeShUABPwVeAVBVlyY5DbgMuBU4rKpua/s5HDgDmAUsqapL2yFeD5yS5K3AD4APDasvkiRJkgRDDFBVdcAExZOGnKo6BjhmgvLTgdMnKL+SO4YASpIkSdLQjWIWPkmSJEnaKBmgJEmSJKknA5QkSZIk9WSAkiRJkqSeDFCSJEmS1JMBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqyQAlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkSZKkngxQkiRJktSTAUqSJEmSejJASZIkSVJPBihJkiRJ6skAJUmSJEk9GaAkSZIkqScDlCRJkiT1ZICSJEmSpJ4MUJIkSZLU0+xRN0CSpI3NN5/05FE3Qevw5G99c9RNkLSJ8gqUJEmSJPVkgJIkSZKkngxQkiRJktSTAUqSJEmSejJASZIkSVJPBihJkiRJ6skAJUmSJEk9DS1AJVmS5LoklwyU/WuSHyW5KMlnk2zTyucn+W2SC9rj+IFtHpPk4iTLkxybJK18uyRnJrmi/dx2WH2RJEmSJBjuFagTgcXjys4EHlFVjwT+C3jDwLofV9XC9jh0oPw44OXAgvYY2+cRwFlVtQA4qz2XJEmSpKEZWoCqqm8BN4wr+0pV3dqeng3MW9s+kuwI3K+qzq6qAk4G9mur9wVOassnDZRLkiRJ0lCM8h6o/wV8aeD5Lkl+kOSbSZ7YyuYCKwbqrGhlADtU1aq2fA2ww2QHSnJIkmVJlq1evXqKmi9JkiRpphlJgEryRuBW4GOtaBWwc1U9CvjfwMeT3K/v/trVqVrL+hOqalFVLZozZ849aLkkSZKkmWz2dB8wycHAXwFPacGHqloDrGnL5yX5MfBQYCV3HuY3r5UBXJtkx6pa1Yb6XTdNXZAkSZI0Q03rFagki4H/Azy7qn4zUD4nyay2/Md0k0Vc2Ybo3Zxkzzb73oHA59tmS4GD2vJBA+WSJEmSNBRDuwKV5BPAXsD2SVYAR9LNurcFcGabjfzsNuPek4Cjk/weuB04tKrGJqB4Jd2MflvS3TM1dt/U24DTkrwUuAp4wbD6IkmSJEkwxABVVQdMUPyhSep+Gvj0JOuWAY+YoPwXwFPuSRslSZIkaX2MchY+SZIkSdqoGKAkSZIkqScDlCRJkiT1ZICSJEmSpJ4MUJIkSZLUkwFKkiRJknoyQEmSJElSTwYoSZIkSeqp9x/STfJ4YP7gNlV18hDaJEmSJEkbpF4BKslHgF2BC4DbWnEBBihJkiRJM0bfK1CLgN2qqobZGEmSJEnakPW9B+oS4I+G2RBJkiRJ2tD1vQK1PXBZknOANWOFVfXsobRKkiRJkjZAfQPUUcNshCRJkiRtDHoFqKr65rAbIkmSJEkbul73QCXZM8m5SW5J8rsktyW5ediNkyRJkqQNSd9JJN4LHABcAWwJvAx437AaJUmSJEkbor4BiqpaDsyqqtuq6sPA4uE1S5IkSZI2PH0nkfhNks2BC5L8C7CK9QhfkiRJkrQp6BuCXtzqHg78GtgJ+OthNUqSJEmSNkR9Z+G7KsmWwI5V9eYht0mSJEmSNkh9Z+F7FnAB8OX2fGGSpUNslyRJkiRtcPoO4TsK2AO4EaCqLgB2GUqLJEmSJGkD1TdA/b6qbhpXVlPdGEmSJEnakPWdhe/SJH8DzEqyAHg18N3hNUuSJEmSNjx9r0C9CtgdWAN8HLgJ+LthNUqSJEmSNkR9A9Ru7TEbuDewL3DusBolSZIkSRuivkP4Pga8FrgEuH14zZEkSZKkDVffK1Crq+oLVfWTqrpq7LGujZIsSXJdkksGyrZLcmaSK9rPbVt5khybZHmSi5I8emCbg1r9K5IcNFD+mCQXt22OTZL16LskSZIkrZe+AerIJB9MckCS5449emx3IrB4XNkRwFlVtQA4qz0H2AdY0B6HAMdBF7iAI4HH0U2lfuRY6Gp1Xj6w3fhjSZIkSdKU6TuE7yXAnwCbcccQvgI+s7aNqupbSeaPK94X2KstnwR8A3h9Kz+5qgo4O8k2SXZsdc+sqhsAkpwJLE7yDeB+VXV2Kz8Z2A/4Us8+SdJ6e8J7njDqJmgtvvOq74y6CZKkTVzfAPXYqnrYFB1zh6pa1ZavAXZoy3OBqwfqrWhlaytfMUG5JEmSJA1F3yF8302y21QfvF1tGvof5E1ySJJlSZatXr162IeTJEmStInqG6D2BC5Icnmb4OHiJBfdzWNe24bm0X5e18pXAjsN1JvXytZWPm+C8ruoqhOqalFVLZozZ87dbLYkSZKkma5vgFpMN0nD3sCzgL9qP++OpcDYTHoHAZ8fKD+wzca3J3BTG+p3BrB3km3b5BF7A2e0dTcn2bPNvnfgwL4kSZIkacr1ugeqz5TlE0nyCbpJILZPsoJuNr23AacleSlwFfCCVv104BnAcuA3dBNXUFU3JHkLd/zh3qPHJpQAXkk309+WdJNHOIGEJEmSpKHpO4nE3VJVB0yy6ikT1C3gsEn2swRYMkH5MuAR96SNkiRJktRX3yF8kiRJkjTjGaAkSZIkqScDlCRJkiT1ZICSJEmSpJ4MUJIkSZLUkwFKkiRJknoyQEmSJElSTwYoSZIkSerJACVJkiRJPRmgJEmSJKknA5QkSZIk9WSAkiRJkqSeDFCSJEmS1JMBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqyQAlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkSZKkngxQkiRJktSTAUqSJEmSejJASZIkSVJPBihJkiRJ6skAJUmSJEk9GaAkSZIkqScDlCRJkiT1ZICSJEmSpJ4MUJIkSZLU07QHqCQPS3LBwOPmJH+f5KgkKwfKnzGwzRuSLE9yeZKnD5QvbmXLkxwx3X2RJEmSNLPMnu4DVtXlwEKAJLOAlcBngZcA766qdwzWT7IbsD+wO/Ag4KtJHtpWvw94GrACODfJ0qq6bDr6IUmSJGnmmfYANc5TgB9X1VVJJquzL3BKVa0BfpJkObBHW7e8qq4ESHJKq2uAkiRJkjQUo74Han/gEwPPD09yUZIlSbZtZXOBqwfqrGhlk5VLkiRJ0lCMLEAl2Rx4NvDJVnQcsCvd8L5VwDun8FiHJFmWZNnq1aunareSJEmSZphRXoHaBzi/qq4FqKprq+q2qrod+AB3DNNbCew0sN28VjZZ+V1U1QlVtaiqFs2ZM2eKuyFJkiRpphhlgDqAgeF7SXYcWPcc4JK2vBTYP8kWSXYBFgDnAOcCC5Ls0q5m7d/qSpIkSdJQjGQSiST3pZs97xUDxf+SZCFQwE/H1lXVpUlOo5sc4lbgsKq6re3ncOAMYBawpKouna4+SJIkSZp5RhKgqurXwAPGlb14LfWPAY6ZoPx04PQpb6AkSZIkTWDU05hLG42fHf2no26C1mLnf7p41E2QJEkzwKinMZckSZKkjYYBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqyQAlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkSZKkngxQkiRJktSTAUqSJEmSejJASZIkSVJPBihJkiRJ6skAJUmSJEk9GaAkSZIkqScDlCRJkiT1ZICSJEmSpJ4MUJIkSZLUkwFKkiRJknoyQEmSJElSTwYoSZIkSerJACVJkiRJPRmgJEmSJKknA5QkSZIk9WSAkiRJkqSeDFCSJEmS1JMBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqaWQBKslPk1yc5IIky1rZdknOTHJF+7ltK0+SY5MsT3JRkkcP7OegVv+KJAeNqj+SJEmSNn2jvgL1F1W1sKoWtedHAGdV1QLgrPYcYB9gQXscAhwHXeACjgQeB+wBHDkWuiRJkiRpqo06QI23L3BSWz4J2G+g/OTqnA1sk2RH4OnAmVV1Q1X9EjgTWDzNbZYkSZI0Q4wyQBXwlSTnJTmkle1QVava8jXADm15LnD1wLYrWtlk5ZIkSZI05WaP8Nh/XlUrkzwQODPJjwZXVlUlqak4UAtohwDsvPPOU7FLSZIkSTPQyK5AVdXK9vM64LN09zBd24bm0X5e16qvBHYa2HxeK5usfPyxTqiqRVW1aM6cOVPdFUmSJEkzxEgCVJL7Jtl6bBnYG7gEWAqMzaR3EPD5trwUOLDNxrcncFMb6ncGsHeSbdvkEXu3MkmSJEmacqMawrcD8NkkY234eFV9Ocm5wGlJXgpcBbyg1T8deAawHPgN8BKAqrohyVuAc1u9o6vqhunrhiRJkqSZZCQBqqquBP5sgvJfAE+ZoLyAwybZ1xJgyVS3UZIkSZLG29CmMZckSZKkDZYBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqyQAlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkSZKknkbyh3Q3No953cmjboLW4rx/PXDUTZAkSdIM4RUoSZIkSerJACVJkiRJPRmgJEmSJKknA5QkSZIk9WSAkiRJkqSeDFCSJEmS1JMBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqyQAlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkSZKkngxQkiRJktSTAUqSJEmSejJASZIkSVJPBihJkiRJ6skAJUmSJEk9GaAkSZIkqScDlCRJkiT1NO0BKslOSb6e5LIklyb5u1Z+VJKVSS5oj2cMbPOGJMuTXJ7k6QPli1vZ8iRHTHdfJEmSJM0ss0dwzFuB11TV+Um2Bs5LcmZb9+6qesdg5SS7AfsDuwMPAr6a5KFt9fuApwErgHOTLK2qy6alF5IkSZJmnGkPUFW1CljVln+V5IfA3LVssi9wSlWtAX6SZDmwR1u3vKquBEhySqtrgJIkSZI0FCO9ByrJfOBRwPdb0eFJLkqyJMm2rWwucPXAZita2WTlEx3nkCTLkixbvXr1VHZBkiRJ0gwysgCVZCvg08DfV9XNwHHArsBCuitU75yqY1XVCVW1qKoWzZkzZ6p2K0mSJGmGGcU9UCTZjC48fayqPgNQVdcOrP8A8MX2dCWw08Dm81oZaymXJEmSpCk3iln4AnwI+GFVvWugfMeBas8BLmnLS4H9k2yRZBdgAXAOcC6wIMkuSTanm2hi6XT0QZIkSdLMNIorUE8AXgxcnOSCVvaPwAFJFgIF/BR4BUBVXZrkNLrJIW4FDquq2wCSHA6cAcwCllTVpdPXDUmSJEkzzShm4fs2kAlWnb6WbY4Bjpmg/PS1bSdJkiRJU2mks/BJkiRJ0sbEACVJkiRJPRmgJEmSJKknA5QkSZIk9WSAkiRJkqSeDFCSJEmS1JMBSpIkSZJ6MkBJkiRJUk8GKEmSJEnqyQAlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkSZKkngxQkiRJktSTAUqSJEmSejJASZIkSVJPBihJkiRJ6skAJUmSJEk9GaAkSZIkqScDlCRJkiT1ZICSJEmSpJ4MUJIkSZLUkwFKkiRJknoyQEmSJElSTwYoSZIkSerJACVJkiRJPRmgJEmSJKknA5QkSZIk9bTRB6gki5NcnmR5kiNG3R5JkiRJm66NOkAlmQW8D9gH2A04IMluo22VJEmSpE3VRh2ggD2A5VV1ZVX9DjgF2HfEbZIkSZK0idrYA9Rc4OqB5ytamSRJkiRNuVTVqNtwtyV5HrC4ql7Wnr8YeFxVHT6u3iHAIe3pw4DLp7WhG57tgetH3QiNnOeBwPNAd/BcEHgeqON5AA+uqjkTrZg93S2ZYiuBnQaez2tld1JVJwAnTFejNnRJllXVolG3Q6PleSDwPNAdPBcEngfqeB6s3cY+hO9cYEGSXZJsDuwPLB1xmyRJkiRtojbqK1BVdWuSw4EzgFnAkqq6dMTNkiRJkrSJ2qgDFEBVnQ6cPup2bGQczijwPFDH80BjPBcEngfqeB6sxUY9iYQkSZIkTaeN/R4oSZIkSZo2BqgZJMlGP2RT91ySjLoN2jAkmTXqNmj02iRMmuGS3G/UbdDoJZlw2m7dmQFqBkgyO8k7gHcmeeqo26PRSXIvIAPLmoGSzEryz8A/J3naqNuj0Rg4D96T5K8M1DNXksOAbyZ5THvuF20zTPv34Gjgu0kePOr2bOj8ALWJa/8IHgvsCJwDvD7JYUm2GG3LNN2SvARYAbx51G3R6CR5MnAesC1wBXBMksePtlWabu3LtIuAbYCvAf8CPGKUbdL0GwhKWwO/AQ4BKG+Qn1GSPJHu/4OtgSdW1VUjbtIGzwC16dsaWAgcWlUfA94BPBR4/igbpemVZCtgX+DtwDOTPKSqbvcq1Ix0O/DOqvrbqvog8D3g2SNuk6bf1cBhVfXKqjoVuJju/wvNIFVV7f+BHYDj6TLVi8AhvjPMzcDWVfUPVXVN+/uq2466URsy74nZxFXVzUl+ChwMvAf4Dt3VqMcn+WpVXTPC5mmaVNUtSV5dVT9LsiNwNPA3VXX7qNumaXcecE6SWVV1G3A28KgRt0nTrKouBy5v972cCuwOf7gf6hv+2zAzJLlX+zLteuDXwNeBZyX5T7oP1TeOsn2aHlV1YZLPJjkN+CXwMGBNkg8An23/V2iA3z7PDJ8FFibZsapuofumcQ1dkNIMUVU/a4v/Bjwkyd7gt4wzTVX9pqrWDPyH+HTgZ2vbRpuuqroZWFpVOwOfobsa+djRtkrTZSAo/ylwBvBlYDe6L1sf4b1QM8rrgEcCP6+qvYBTgCfiF2wTMkDNDN8Grqe7CkVVnUf3H+SWI2yTRqRddfwQ8Mb2/LYkm422VZpu7YbhsaE7X2pluztb58wx9uG4qo5rP08FdqU7JzSzXAj8O/ANuitPPwIu816omaOqbgL2qqo3t+cfBhYAfzTShm2gDFAzQFWtAj4P7JPk+UnmA/8N3DrShmkk2pCN9wOrk/y/JO/Bb5hmotuBzei+XHlkki8Ar8UvVmaM8R+Ok/wxsAXdOaGZ5V7AA4FXV9WTgPOBl422SZpug7d1JNmV7laf1aNr0YYrfrkwcyTZh27yiMcD762q9464SRqRJPehG6rxcOAtVXXsiJukEUiyJ/Dd9vhwVX1oxE3SNGtXIecCb6Wbhe/4qvrAaFul6ZZky6r6bVsO8MCqunbEzdI0a+/9dsC76YZynlBVJ4y2VRsmA9QM04ZqVVV59WkGS/JaYB7w+qpaM+r2aDSSzANeDLzL82DmSvJA4Ll0IdrzYAZLMtvPBzNbm7X3RcCJ/nswOQOUNAONzbw06nZIkiRtbAxQkiRJktSTk0hIkiRJUk8GKEmSJEnqyQAlSZIkST0ZoCRJkiSpJwOUJEmSJPVkgJIkDU2SW9rPByX5VFtemOQZ69ju4CTvbcuHJjlw+K1dP0n2S7LbOursleTxU3jMo9rfcSPJ0UmeOlX7liT1M3vUDZAkbVzuzh/brKqfA89rTxcCi4DTe257/Ho1cPrsB3wRuGwtdfYCbgG+O9UHr6p/mup9SpLWzStQkqS7SHJgkouSXJjkI0lOTHJ8ku8D/5Jk1yRfTnJekv9M8idtu12SfC/JxUneOrC/+UkuSbI5cDTwwiQXJHlhj7YMXnX5RpK3JzknyX8leWIrn5XkX5Oc29r9ila+Y5JvtWNdMlZ/kuMc0Np9SZK3D5TfMrD8vPZaPB54NvCvbd+7Jnl1ksva8U9JMh84FPiHVueJSZ6V5PtJfpDkq0l2GOjjkta/K5O8euCYb2x9/TbwsIHyE5M8ry3/NMmbk5zf+jD2fsxJcmaSS5N8MMlVSbZf12suSZqcV6AkSXeSZHfgTcDjq+r6JNsB7wLmtbLbkpwFHFpVVyR5HPDvwF8C/w84rqpOTnLY+H1X1e+S/BOwqKoOv5tNnF1Ve7RhgEcCTwVeCtxUVY9NsgXwnSRfAZ4LnFFVxySZBdxnkj4/CHg78Bjgl8BXkuxXVZ+bqH5VfTfJUuCLVTU2NPEIYJeqWpNkm6q6McnxwC1V9Y5WZ1tgz6qqJC8D/g/wmrbbPwH+AtgauDzJccAjgf3prtrNBs4Hzpvkdbm+qh6d5JXAa4GXtdfna1X1f5Msbq+TJOkeMEBJksb7S+CTVXU9QFXdkIRWdluSrYDHA59s5QBbtJ9PAP66LX+ELpRMtc+0n+cB89vy3sAjx67IAPcHFgDnAkuSbAZ8rqoumGSfjwW+UVWrAZJ8DHgS8Ln1aNdFwMeSfG4t280DTk2yI7A58JOBdf9RVWuANUmuA3YAngh8tqp+09q1dC3HH3xdntuW/xx4DkBVfTnJL9ejP5KkCTiET5LU16/bz3sBN1bVwoHHwwfq1ZDbsab9vI07vggM8KqB9uxSVV+pqm/RBaGVwIl3czKKwf7cey31ngm8D3g0cG6Sib6kfA/w3qr6U+AV4/a3ZmB5sG99TfS6SJKmmAFKkjTe14DnJ3kAQBvC9wdVdTPwkyTPb+uT5M/a6u/QDTkDeNEk+/8V3TC1qXQG8LftShNJHprkvkkeDFxbVR8APkgXbiZyDvDkJNu3oX4HAN9s665N8vAk96JdzRnfj7Zup6r6OvB6uitgW3HXvt6fLswBHNSjX98C9kuyZZKtgWf12GbQd4AXtDbuDWy7nttLksYxQEmS7qSqLgWOAb6Z5EK6+5/GexHw0rb+UmDfVv53wGFJLgbmTnKIrwO79Z1EoqcP0s2Gd36SS4D3012F2Qu4MMkPgBfS3aN1F1W1Cjiite1C4Lyq+nxbfQTdbHvfBVYNbHYK8Lq27wXAR1u/fwAcW1U3Al8AnjM2iQRwFN3Qx/OA69fVqao6Hzi1telLdEMS18ebgb3ba/J84Bq6UCdJuptSNeyRFpIkaRTahBq3VdWtSf4H3QQfC0fcLEnaqDlGWpKkTdfOwGltiOHvgJePuD2StNHzCpQkaWSSvIRu2N+g71TVXaZAn8Jjfp87Zg0c8+KqunhYx5QkbToMUJIkSZLUk5NISJIkSVJPBihJkiRJ6skAJUmSJEk9GaAkSZIkqScDlCRJkiT19P8DO0KEQlz0PD0AAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1008x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df=Loans_df.groupby(['credit_lines_outstanding'])['total_debt_outstanding'].mean().reset_index(name='mean').sort_values('credit_lines_outstanding',ascending=True)\n",
    "fig, ax = plt.subplots()\n",
    "fig.set_size_inches(14,6)\n",
    "q = sns.barplot(x=\"credit_lines_outstanding\", y=\"mean\", data=df)\n",
    "q.set_xticklabels(q.get_xticklabels(),rotation=30)\n",
    "plt.title('credit_lines_outstanding to mean total debt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'credit_lines_outstanding to mean ratio income/Total debt')"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df=Loans_df.groupby(['credit_lines_outstanding'])['ratio_income_Totdebt'].mean().reset_index(name='mean').sort_values('credit_lines_outstanding',ascending=True)\n",
    "fig, ax = plt.subplots()\n",
    "fig.set_size_inches(14,6)\n",
    "q = sns.barplot(x=\"credit_lines_outstanding\", y=\"mean\", data=df)\n",
    "q.set_xticklabels(q.get_xticklabels(),rotation=30)\n",
    "plt.title('credit_lines_outstanding to mean ratio income/Total debt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'credit_lines_outstanding to mean ratio income/loan amount')"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df=Loans_df.groupby(['credit_lines_outstanding'])['ratio_income_loan_amt'].mean().reset_index(name='mean').sort_values('credit_lines_outstanding',ascending=True)\n",
    "fig, ax = plt.subplots()\n",
    "fig.set_size_inches(14,6)\n",
    "q = sns.barplot(x=\"credit_lines_outstanding\", y=\"mean\", data=df)\n",
    "q.set_xticklabels(q.get_xticklabels(),rotation=30)\n",
    "plt.title('credit_lines_outstanding to mean ratio income/loan amount')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'credit_lines_outstanding to mean fico score')"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "df=Loans_df.groupby(['credit_lines_outstanding'])['fico_score'].mean().reset_index(name='mean').sort_values('credit_lines_outstanding',ascending=True)\n",
    "fig, ax = plt.subplots()\n",
    "fig.set_size_inches(14,6)\n",
    "q = sns.barplot(x=\"credit_lines_outstanding\", y=\"mean\", data=df)\n",
    "q.set_xticklabels(q.get_xticklabels(),rotation=30)\n",
    "plt.title('credit_lines_outstanding to mean fico score')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Correlation in Credit Features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x720 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Sample figsize in inches\n",
    "fig, ax = plt.subplots(figsize=(20,10))\n",
    "\n",
    "# Imbalanced DataFrame Correlation\n",
    "corr = Loans_df.corr()\n",
    "sns.heatmap(corr, cmap='YlGnBu', annot_kws={'size':30}, ax=ax)\n",
    "ax.set_title(\"Correlation Matrix\", fontsize=14)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Create predictions of probability for loan status using test data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.dummy import DummyClassifier\n",
    "from sklearn.metrics import accuracy_score, f1_score, confusion_matrix, recall_score, roc_auc_score\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = Loans_df.drop(['default'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "Y = Loans_df['default']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.6, random_state=123)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create, train, and fit a logistic regression model\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "clf_logistic = LogisticRegression(solver='lbfgs').fit(X_train, np.ravel(Y_train))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create predictions of probability for loan status using test data\n",
    "# .predict_proba creates an array of probabilities of default: [[non-defualt-0, default-1]]\n",
    "lr_preds = clf_logistic.predict_proba(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "# # Create dataframes of predictions and true labels\n",
    "lr_preds_df = pd.DataFrame(lr_preds[:,1][0:], columns = ['lr_pred_PD'])\n",
    "true_df = Y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      default    lr_pred_PD\n",
      "0           0  1.921681e-01\n",
      "1           0  3.158252e-03\n",
      "2           0  8.001060e-06\n",
      "3           0  5.715621e-04\n",
      "4           0  1.011647e-02\n",
      "...       ...           ...\n",
      "5995        0  5.925136e-07\n",
      "5996        0  1.458321e-05\n",
      "5997        0  1.692793e-02\n",
      "5998        0  6.280797e-07\n",
      "5999        0  7.617845e-01\n",
      "\n",
      "[6000 rows x 2 columns]\n"
     ]
    }
   ],
   "source": [
    "# Concatenate and print the two data frames for comparison\n",
    "print(pd.concat([true_df.reset_index(drop = True), lr_preds_df], axis = 1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "import math"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "lr_pred_PD\n",
       "0.00          4441\n",
       "1.00           734\n",
       "0.01           131\n",
       "0.99            73\n",
       "0.02            47\n",
       "              ... \n",
       "0.39             1\n",
       "0.40             1\n",
       "0.79             1\n",
       "0.44             1\n",
       "0.74             1\n",
       "Name: count, Length: 99, dtype: int64"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr_preds_df.round(decimals=2).value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "default\n",
       "0    4932\n",
       "1    1068\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_test.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Non-Default / Default predictions at 60% Threshhold: \n",
      "lr_pred_loan_status_60\n",
      "0    4966\n",
      "1    1034\n",
      "Name: count, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# Reassign loan status based on the threshold and print the predictions\n",
    "lr_preds_df['lr_pred_loan_status_60'] = lr_preds_df['lr_pred_PD'].apply(lambda x: 1 if x > 0.60 else 0)\n",
    "print(\"Non-Default / Default predictions at 60% Threshhold: \")\n",
    "print(lr_preds_df['lr_pred_loan_status_60'].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Confusion Matrix at 60% Threshhold: \n",
      "[[4898   34]\n",
      " [  68 1000]]\n"
     ]
    }
   ],
   "source": [
    "# Print the confusion matrix\n",
    "from sklearn.metrics import confusion_matrix\n",
    "print(\"Confusion Matrix at 60% Threshhold: \")\n",
    "print(confusion_matrix(Y_test, lr_preds_df['lr_pred_loan_status_60']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      " Non-Default       0.99      0.99      0.99      4932\n",
      "     Default       0.97      0.94      0.95      1068\n",
      "\n",
      "    accuracy                           0.98      6000\n",
      "   macro avg       0.98      0.96      0.97      6000\n",
      "weighted avg       0.98      0.98      0.98      6000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Print the classification report\n",
    "from sklearn.metrics import classification_report\n",
    "target_names = ['Non-Default', 'Default']\n",
    "print(classification_report(Y_test, lr_preds_df['lr_pred_loan_status_60'], target_names=target_names))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9835\n"
     ]
    }
   ],
   "source": [
    "# Print the accuracy score the model\n",
    "print(clf_logistic.score(X_test, Y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Plot the ROC curve of the probabilities of default\n",
    "from sklearn.metrics import roc_curve"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "lr_prob_default = lr_preds[:, 1]\n",
    "fallout, sensitivity, thresholds = roc_curve(Y_test, lr_prob_default)\n",
    "plt.plot(fallout, sensitivity, color = 'darkorange')\n",
    "plt.plot([0, 1], [0, 1], linestyle='--')\n",
    "plt.title(\"ROC Chart for LR on PD\")\n",
    "plt.xlabel(\"Fall-out\")\n",
    "plt.ylabel(\"Sensitivity\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "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>lr_pred_PD</th>\n",
       "      <th>lr_pred_loan_status_60</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.19</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.01</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5995</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5996</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5997</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5998</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5999</th>\n",
       "      <td>0.76</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>6000 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      lr_pred_PD  lr_pred_loan_status_60\n",
       "0           0.19                       0\n",
       "1           0.00                       0\n",
       "2           0.00                       0\n",
       "3           0.00                       0\n",
       "4           0.01                       0\n",
       "...          ...                     ...\n",
       "5995        0.00                       0\n",
       "5996        0.00                       0\n",
       "5997        0.02                       0\n",
       "5998        0.00                       0\n",
       "5999        0.76                       1\n",
       "\n",
       "[6000 rows x 2 columns]"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr_preds_df.round(decimals=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>default</th>\n",
       "      <th>ratio_income_Totdebt</th>\n",
       "      <th>ratio_income_loan_amt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8153374</td>\n",
       "      <td>0</td>\n",
       "      <td>5221.545193</td>\n",
       "      <td>3915.471226</td>\n",
       "      <td>78039.38546</td>\n",
       "      <td>5</td>\n",
       "      <td>605</td>\n",
       "      <td>0</td>\n",
       "      <td>19.931033</td>\n",
       "      <td>14.945650</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7442532</td>\n",
       "      <td>5</td>\n",
       "      <td>1958.928726</td>\n",
       "      <td>8228.752520</td>\n",
       "      <td>26648.43525</td>\n",
       "      <td>2</td>\n",
       "      <td>572</td>\n",
       "      <td>1</td>\n",
       "      <td>3.238454</td>\n",
       "      <td>13.603576</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2256073</td>\n",
       "      <td>0</td>\n",
       "      <td>3363.009259</td>\n",
       "      <td>2027.830850</td>\n",
       "      <td>65866.71246</td>\n",
       "      <td>4</td>\n",
       "      <td>602</td>\n",
       "      <td>0</td>\n",
       "      <td>32.481364</td>\n",
       "      <td>19.585647</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4885975</td>\n",
       "      <td>0</td>\n",
       "      <td>4766.648001</td>\n",
       "      <td>2501.730397</td>\n",
       "      <td>74356.88347</td>\n",
       "      <td>5</td>\n",
       "      <td>612</td>\n",
       "      <td>0</td>\n",
       "      <td>29.722181</td>\n",
       "      <td>15.599407</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4700614</td>\n",
       "      <td>1</td>\n",
       "      <td>1345.827718</td>\n",
       "      <td>1768.826187</td>\n",
       "      <td>23448.32631</td>\n",
       "      <td>6</td>\n",
       "      <td>631</td>\n",
       "      <td>0</td>\n",
       "      <td>13.256433</td>\n",
       "      <td>17.422978</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "0      8153374                         0           5221.545193   \n",
       "1      7442532                         5           1958.928726   \n",
       "2      2256073                         0           3363.009259   \n",
       "3      4885975                         0           4766.648001   \n",
       "4      4700614                         1           1345.827718   \n",
       "\n",
       "   total_debt_outstanding       income  years_employed  fico_score  default  \\\n",
       "0             3915.471226  78039.38546               5         605        0   \n",
       "1             8228.752520  26648.43525               2         572        1   \n",
       "2             2027.830850  65866.71246               4         602        0   \n",
       "3             2501.730397  74356.88347               5         612        0   \n",
       "4             1768.826187  23448.32631               6         631        0   \n",
       "\n",
       "   ratio_income_Totdebt  ratio_income_loan_amt  \n",
       "0             19.931033              14.945650  \n",
       "1              3.238454              13.603576  \n",
       "2             32.481364              19.585647  \n",
       "3             29.722181              15.599407  \n",
       "4             13.256433              17.422978  "
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [],
   "source": [
    "Loans_df.drop(['default'], axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>ratio_income_Totdebt</th>\n",
       "      <th>ratio_income_loan_amt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8153374</td>\n",
       "      <td>0</td>\n",
       "      <td>5221.545193</td>\n",
       "      <td>3915.471226</td>\n",
       "      <td>78039.38546</td>\n",
       "      <td>5</td>\n",
       "      <td>605</td>\n",
       "      <td>19.931033</td>\n",
       "      <td>14.945650</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7442532</td>\n",
       "      <td>5</td>\n",
       "      <td>1958.928726</td>\n",
       "      <td>8228.752520</td>\n",
       "      <td>26648.43525</td>\n",
       "      <td>2</td>\n",
       "      <td>572</td>\n",
       "      <td>3.238454</td>\n",
       "      <td>13.603576</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2256073</td>\n",
       "      <td>0</td>\n",
       "      <td>3363.009259</td>\n",
       "      <td>2027.830850</td>\n",
       "      <td>65866.71246</td>\n",
       "      <td>4</td>\n",
       "      <td>602</td>\n",
       "      <td>32.481364</td>\n",
       "      <td>19.585647</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4885975</td>\n",
       "      <td>0</td>\n",
       "      <td>4766.648001</td>\n",
       "      <td>2501.730397</td>\n",
       "      <td>74356.88347</td>\n",
       "      <td>5</td>\n",
       "      <td>612</td>\n",
       "      <td>29.722181</td>\n",
       "      <td>15.599407</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4700614</td>\n",
       "      <td>1</td>\n",
       "      <td>1345.827718</td>\n",
       "      <td>1768.826187</td>\n",
       "      <td>23448.32631</td>\n",
       "      <td>6</td>\n",
       "      <td>631</td>\n",
       "      <td>13.256433</td>\n",
       "      <td>17.422978</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9995</th>\n",
       "      <td>3972488</td>\n",
       "      <td>0</td>\n",
       "      <td>3033.647103</td>\n",
       "      <td>2553.733144</td>\n",
       "      <td>42691.62787</td>\n",
       "      <td>5</td>\n",
       "      <td>697</td>\n",
       "      <td>16.717341</td>\n",
       "      <td>14.072707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9996</th>\n",
       "      <td>6184073</td>\n",
       "      <td>1</td>\n",
       "      <td>4146.239304</td>\n",
       "      <td>5458.163525</td>\n",
       "      <td>79969.50521</td>\n",
       "      <td>8</td>\n",
       "      <td>615</td>\n",
       "      <td>14.651358</td>\n",
       "      <td>19.287238</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9997</th>\n",
       "      <td>6694516</td>\n",
       "      <td>2</td>\n",
       "      <td>3088.223727</td>\n",
       "      <td>4813.090925</td>\n",
       "      <td>38192.67591</td>\n",
       "      <td>5</td>\n",
       "      <td>596</td>\n",
       "      <td>7.935166</td>\n",
       "      <td>12.367199</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9998</th>\n",
       "      <td>3942961</td>\n",
       "      <td>0</td>\n",
       "      <td>3288.901666</td>\n",
       "      <td>1043.099660</td>\n",
       "      <td>50929.37206</td>\n",
       "      <td>2</td>\n",
       "      <td>647</td>\n",
       "      <td>48.825030</td>\n",
       "      <td>15.485222</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9999</th>\n",
       "      <td>5533570</td>\n",
       "      <td>1</td>\n",
       "      <td>1917.652480</td>\n",
       "      <td>3050.248203</td>\n",
       "      <td>30611.62821</td>\n",
       "      <td>6</td>\n",
       "      <td>757</td>\n",
       "      <td>10.035783</td>\n",
       "      <td>15.963074</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10000 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "0         8153374                         0           5221.545193   \n",
       "1         7442532                         5           1958.928726   \n",
       "2         2256073                         0           3363.009259   \n",
       "3         4885975                         0           4766.648001   \n",
       "4         4700614                         1           1345.827718   \n",
       "...           ...                       ...                   ...   \n",
       "9995      3972488                         0           3033.647103   \n",
       "9996      6184073                         1           4146.239304   \n",
       "9997      6694516                         2           3088.223727   \n",
       "9998      3942961                         0           3288.901666   \n",
       "9999      5533570                         1           1917.652480   \n",
       "\n",
       "      total_debt_outstanding       income  years_employed  fico_score  \\\n",
       "0                3915.471226  78039.38546               5         605   \n",
       "1                8228.752520  26648.43525               2         572   \n",
       "2                2027.830850  65866.71246               4         602   \n",
       "3                2501.730397  74356.88347               5         612   \n",
       "4                1768.826187  23448.32631               6         631   \n",
       "...                      ...          ...             ...         ...   \n",
       "9995             2553.733144  42691.62787               5         697   \n",
       "9996             5458.163525  79969.50521               8         615   \n",
       "9997             4813.090925  38192.67591               5         596   \n",
       "9998             1043.099660  50929.37206               2         647   \n",
       "9999             3050.248203  30611.62821               6         757   \n",
       "\n",
       "      ratio_income_Totdebt  ratio_income_loan_amt  \n",
       "0                19.931033              14.945650  \n",
       "1                 3.238454              13.603576  \n",
       "2                32.481364              19.585647  \n",
       "3                29.722181              15.599407  \n",
       "4                13.256433              17.422978  \n",
       "...                    ...                    ...  \n",
       "9995             16.717341              14.072707  \n",
       "9996             14.651358              19.287238  \n",
       "9997              7.935166              12.367199  \n",
       "9998             48.825030              15.485222  \n",
       "9999             10.035783              15.963074  \n",
       "\n",
       "[10000 rows x 9 columns]"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [],
   "source": [
    "Prob_to_default = clf_logistic.predict_proba(Loans_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [],
   "source": [
    "prob_data = pd.DataFrame(Prob_to_default[:,1][0:].round(decimals = 2), columns = ['Probability _to_Default'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [],
   "source": [
    "Loans_df=pd.concat([Loans_df, prob_data], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>ratio_income_Totdebt</th>\n",
       "      <th>ratio_income_loan_amt</th>\n",
       "      <th>Probability _to_Default</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8153374</td>\n",
       "      <td>0</td>\n",
       "      <td>5221.545193</td>\n",
       "      <td>3915.471226</td>\n",
       "      <td>78039.38546</td>\n",
       "      <td>5</td>\n",
       "      <td>605</td>\n",
       "      <td>19.931033</td>\n",
       "      <td>14.945650</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7442532</td>\n",
       "      <td>5</td>\n",
       "      <td>1958.928726</td>\n",
       "      <td>8228.752520</td>\n",
       "      <td>26648.43525</td>\n",
       "      <td>2</td>\n",
       "      <td>572</td>\n",
       "      <td>3.238454</td>\n",
       "      <td>13.603576</td>\n",
       "      <td>0.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2256073</td>\n",
       "      <td>0</td>\n",
       "      <td>3363.009259</td>\n",
       "      <td>2027.830850</td>\n",
       "      <td>65866.71246</td>\n",
       "      <td>4</td>\n",
       "      <td>602</td>\n",
       "      <td>32.481364</td>\n",
       "      <td>19.585647</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4885975</td>\n",
       "      <td>0</td>\n",
       "      <td>4766.648001</td>\n",
       "      <td>2501.730397</td>\n",
       "      <td>74356.88347</td>\n",
       "      <td>5</td>\n",
       "      <td>612</td>\n",
       "      <td>29.722181</td>\n",
       "      <td>15.599407</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4700614</td>\n",
       "      <td>1</td>\n",
       "      <td>1345.827718</td>\n",
       "      <td>1768.826187</td>\n",
       "      <td>23448.32631</td>\n",
       "      <td>6</td>\n",
       "      <td>631</td>\n",
       "      <td>13.256433</td>\n",
       "      <td>17.422978</td>\n",
       "      <td>0.00</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9995</th>\n",
       "      <td>3972488</td>\n",
       "      <td>0</td>\n",
       "      <td>3033.647103</td>\n",
       "      <td>2553.733144</td>\n",
       "      <td>42691.62787</td>\n",
       "      <td>5</td>\n",
       "      <td>697</td>\n",
       "      <td>16.717341</td>\n",
       "      <td>14.072707</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9996</th>\n",
       "      <td>6184073</td>\n",
       "      <td>1</td>\n",
       "      <td>4146.239304</td>\n",
       "      <td>5458.163525</td>\n",
       "      <td>79969.50521</td>\n",
       "      <td>8</td>\n",
       "      <td>615</td>\n",
       "      <td>14.651358</td>\n",
       "      <td>19.287238</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9997</th>\n",
       "      <td>6694516</td>\n",
       "      <td>2</td>\n",
       "      <td>3088.223727</td>\n",
       "      <td>4813.090925</td>\n",
       "      <td>38192.67591</td>\n",
       "      <td>5</td>\n",
       "      <td>596</td>\n",
       "      <td>7.935166</td>\n",
       "      <td>12.367199</td>\n",
       "      <td>0.01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9998</th>\n",
       "      <td>3942961</td>\n",
       "      <td>0</td>\n",
       "      <td>3288.901666</td>\n",
       "      <td>1043.099660</td>\n",
       "      <td>50929.37206</td>\n",
       "      <td>2</td>\n",
       "      <td>647</td>\n",
       "      <td>48.825030</td>\n",
       "      <td>15.485222</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9999</th>\n",
       "      <td>5533570</td>\n",
       "      <td>1</td>\n",
       "      <td>1917.652480</td>\n",
       "      <td>3050.248203</td>\n",
       "      <td>30611.62821</td>\n",
       "      <td>6</td>\n",
       "      <td>757</td>\n",
       "      <td>10.035783</td>\n",
       "      <td>15.963074</td>\n",
       "      <td>0.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10000 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "0         8153374                         0           5221.545193   \n",
       "1         7442532                         5           1958.928726   \n",
       "2         2256073                         0           3363.009259   \n",
       "3         4885975                         0           4766.648001   \n",
       "4         4700614                         1           1345.827718   \n",
       "...           ...                       ...                   ...   \n",
       "9995      3972488                         0           3033.647103   \n",
       "9996      6184073                         1           4146.239304   \n",
       "9997      6694516                         2           3088.223727   \n",
       "9998      3942961                         0           3288.901666   \n",
       "9999      5533570                         1           1917.652480   \n",
       "\n",
       "      total_debt_outstanding       income  years_employed  fico_score  \\\n",
       "0                3915.471226  78039.38546               5         605   \n",
       "1                8228.752520  26648.43525               2         572   \n",
       "2                2027.830850  65866.71246               4         602   \n",
       "3                2501.730397  74356.88347               5         612   \n",
       "4                1768.826187  23448.32631               6         631   \n",
       "...                      ...          ...             ...         ...   \n",
       "9995             2553.733144  42691.62787               5         697   \n",
       "9996             5458.163525  79969.50521               8         615   \n",
       "9997             4813.090925  38192.67591               5         596   \n",
       "9998             1043.099660  50929.37206               2         647   \n",
       "9999             3050.248203  30611.62821               6         757   \n",
       "\n",
       "      ratio_income_Totdebt  ratio_income_loan_amt  Probability _to_Default  \n",
       "0                19.931033              14.945650                     0.00  \n",
       "1                 3.238454              13.603576                     0.99  \n",
       "2                32.481364              19.585647                     0.00  \n",
       "3                29.722181              15.599407                     0.00  \n",
       "4                13.256433              17.422978                     0.00  \n",
       "...                    ...                    ...                      ...  \n",
       "9995             16.717341              14.072707                     0.00  \n",
       "9996             14.651358              19.287238                     0.00  \n",
       "9997              7.935166              12.367199                     0.01  \n",
       "9998             48.825030              15.485222                     0.00  \n",
       "9999             10.035783              15.963074                     0.00  \n",
       "\n",
       "[10000 rows x 10 columns]"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Assuming a recovery rate of 10%, this can be used to give the expected loss on a loan."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Recovery rate\n",
    "recovery_rate = 0.1  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Loss Given Default (LGD)\n",
    "Loans_df['lgd'] = (1 - recovery_rate) * Loans_df['loan_amt_outstanding']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " Expected Loss (EL)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [],
   "source": [
    "Loans_df['expected_loss'] = Loans_df['Probability _to_Default'] * Loans_df['lgd']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>ratio_income_Totdebt</th>\n",
       "      <th>ratio_income_loan_amt</th>\n",
       "      <th>Probability _to_Default</th>\n",
       "      <th>lgd</th>\n",
       "      <th>expected_loss</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>9995</th>\n",
       "      <td>3972488</td>\n",
       "      <td>0</td>\n",
       "      <td>3033.647103</td>\n",
       "      <td>2553.733144</td>\n",
       "      <td>42691.62787</td>\n",
       "      <td>5</td>\n",
       "      <td>697</td>\n",
       "      <td>16.717341</td>\n",
       "      <td>14.072707</td>\n",
       "      <td>0.00</td>\n",
       "      <td>2730.282393</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9996</th>\n",
       "      <td>6184073</td>\n",
       "      <td>1</td>\n",
       "      <td>4146.239304</td>\n",
       "      <td>5458.163525</td>\n",
       "      <td>79969.50521</td>\n",
       "      <td>8</td>\n",
       "      <td>615</td>\n",
       "      <td>14.651358</td>\n",
       "      <td>19.287238</td>\n",
       "      <td>0.00</td>\n",
       "      <td>3731.615374</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9997</th>\n",
       "      <td>6694516</td>\n",
       "      <td>2</td>\n",
       "      <td>3088.223727</td>\n",
       "      <td>4813.090925</td>\n",
       "      <td>38192.67591</td>\n",
       "      <td>5</td>\n",
       "      <td>596</td>\n",
       "      <td>7.935166</td>\n",
       "      <td>12.367199</td>\n",
       "      <td>0.01</td>\n",
       "      <td>2779.401354</td>\n",
       "      <td>27.794014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9998</th>\n",
       "      <td>3942961</td>\n",
       "      <td>0</td>\n",
       "      <td>3288.901666</td>\n",
       "      <td>1043.099660</td>\n",
       "      <td>50929.37206</td>\n",
       "      <td>2</td>\n",
       "      <td>647</td>\n",
       "      <td>48.825030</td>\n",
       "      <td>15.485222</td>\n",
       "      <td>0.00</td>\n",
       "      <td>2960.011499</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9999</th>\n",
       "      <td>5533570</td>\n",
       "      <td>1</td>\n",
       "      <td>1917.652480</td>\n",
       "      <td>3050.248203</td>\n",
       "      <td>30611.62821</td>\n",
       "      <td>6</td>\n",
       "      <td>757</td>\n",
       "      <td>10.035783</td>\n",
       "      <td>15.963074</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1725.887232</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "9995      3972488                         0           3033.647103   \n",
       "9996      6184073                         1           4146.239304   \n",
       "9997      6694516                         2           3088.223727   \n",
       "9998      3942961                         0           3288.901666   \n",
       "9999      5533570                         1           1917.652480   \n",
       "\n",
       "      total_debt_outstanding       income  years_employed  fico_score  \\\n",
       "9995             2553.733144  42691.62787               5         697   \n",
       "9996             5458.163525  79969.50521               8         615   \n",
       "9997             4813.090925  38192.67591               5         596   \n",
       "9998             1043.099660  50929.37206               2         647   \n",
       "9999             3050.248203  30611.62821               6         757   \n",
       "\n",
       "      ratio_income_Totdebt  ratio_income_loan_amt  Probability _to_Default  \\\n",
       "9995             16.717341              14.072707                     0.00   \n",
       "9996             14.651358              19.287238                     0.00   \n",
       "9997              7.935166              12.367199                     0.01   \n",
       "9998             48.825030              15.485222                     0.00   \n",
       "9999             10.035783              15.963074                     0.00   \n",
       "\n",
       "              lgd  expected_loss  \n",
       "9995  2730.282393       0.000000  \n",
       "9996  3731.615374       0.000000  \n",
       "9997  2779.401354      27.794014  \n",
       "9998  2960.011499       0.000000  \n",
       "9999  1725.887232       0.000000  "
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>ratio_income_Totdebt</th>\n",
       "      <th>ratio_income_loan_amt</th>\n",
       "      <th>Probability _to_Default</th>\n",
       "      <th>lgd</th>\n",
       "      <th>expected_loss</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1997</th>\n",
       "      <td>6597386</td>\n",
       "      <td>5</td>\n",
       "      <td>10210.746690</td>\n",
       "      <td>33515.971170</td>\n",
       "      <td>107870.38960</td>\n",
       "      <td>2</td>\n",
       "      <td>649</td>\n",
       "      <td>3.218477</td>\n",
       "      <td>10.564398</td>\n",
       "      <td>1.0</td>\n",
       "      <td>9189.672021</td>\n",
       "      <td>9189.672021</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2138</th>\n",
       "      <td>1998635</td>\n",
       "      <td>5</td>\n",
       "      <td>9563.693515</td>\n",
       "      <td>28825.601850</td>\n",
       "      <td>112120.62640</td>\n",
       "      <td>3</td>\n",
       "      <td>641</td>\n",
       "      <td>3.889620</td>\n",
       "      <td>11.723570</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8607.324164</td>\n",
       "      <td>8607.324164</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9203</th>\n",
       "      <td>4836461</td>\n",
       "      <td>5</td>\n",
       "      <td>9105.964213</td>\n",
       "      <td>42558.451490</td>\n",
       "      <td>133913.38230</td>\n",
       "      <td>3</td>\n",
       "      <td>601</td>\n",
       "      <td>3.146576</td>\n",
       "      <td>14.706118</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8195.367792</td>\n",
       "      <td>8195.367792</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9944</th>\n",
       "      <td>3983392</td>\n",
       "      <td>4</td>\n",
       "      <td>8989.178801</td>\n",
       "      <td>30103.662560</td>\n",
       "      <td>124197.63370</td>\n",
       "      <td>2</td>\n",
       "      <td>641</td>\n",
       "      <td>4.125665</td>\n",
       "      <td>13.816349</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8090.260921</td>\n",
       "      <td>8090.260921</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5460</th>\n",
       "      <td>2527305</td>\n",
       "      <td>5</td>\n",
       "      <td>8841.923630</td>\n",
       "      <td>32644.921580</td>\n",
       "      <td>115203.15190</td>\n",
       "      <td>2</td>\n",
       "      <td>541</td>\n",
       "      <td>3.528976</td>\n",
       "      <td>13.029196</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7957.731267</td>\n",
       "      <td>7957.731267</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3825</th>\n",
       "      <td>5644865</td>\n",
       "      <td>0</td>\n",
       "      <td>1906.390298</td>\n",
       "      <td>1799.098281</td>\n",
       "      <td>39298.79573</td>\n",
       "      <td>5</td>\n",
       "      <td>640</td>\n",
       "      <td>21.843607</td>\n",
       "      <td>20.614245</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1715.751268</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3824</th>\n",
       "      <td>5387202</td>\n",
       "      <td>0</td>\n",
       "      <td>5023.085666</td>\n",
       "      <td>8183.306718</td>\n",
       "      <td>97075.43796</td>\n",
       "      <td>3</td>\n",
       "      <td>698</td>\n",
       "      <td>11.862618</td>\n",
       "      <td>19.325858</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4520.777099</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3822</th>\n",
       "      <td>4852626</td>\n",
       "      <td>0</td>\n",
       "      <td>2347.870065</td>\n",
       "      <td>728.786824</td>\n",
       "      <td>72878.68237</td>\n",
       "      <td>5</td>\n",
       "      <td>636</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>31.040339</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2113.083059</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3821</th>\n",
       "      <td>1975554</td>\n",
       "      <td>0</td>\n",
       "      <td>5171.867325</td>\n",
       "      <td>4630.787898</td>\n",
       "      <td>85411.55172</td>\n",
       "      <td>4</td>\n",
       "      <td>634</td>\n",
       "      <td>18.444281</td>\n",
       "      <td>16.514645</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4654.680592</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9999</th>\n",
       "      <td>5533570</td>\n",
       "      <td>1</td>\n",
       "      <td>1917.652480</td>\n",
       "      <td>3050.248203</td>\n",
       "      <td>30611.62821</td>\n",
       "      <td>6</td>\n",
       "      <td>757</td>\n",
       "      <td>10.035783</td>\n",
       "      <td>15.963074</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1725.887232</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10000 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "1997      6597386                         5          10210.746690   \n",
       "2138      1998635                         5           9563.693515   \n",
       "9203      4836461                         5           9105.964213   \n",
       "9944      3983392                         4           8989.178801   \n",
       "5460      2527305                         5           8841.923630   \n",
       "...           ...                       ...                   ...   \n",
       "3825      5644865                         0           1906.390298   \n",
       "3824      5387202                         0           5023.085666   \n",
       "3822      4852626                         0           2347.870065   \n",
       "3821      1975554                         0           5171.867325   \n",
       "9999      5533570                         1           1917.652480   \n",
       "\n",
       "      total_debt_outstanding        income  years_employed  fico_score  \\\n",
       "1997            33515.971170  107870.38960               2         649   \n",
       "2138            28825.601850  112120.62640               3         641   \n",
       "9203            42558.451490  133913.38230               3         601   \n",
       "9944            30103.662560  124197.63370               2         641   \n",
       "5460            32644.921580  115203.15190               2         541   \n",
       "...                      ...           ...             ...         ...   \n",
       "3825             1799.098281   39298.79573               5         640   \n",
       "3824             8183.306718   97075.43796               3         698   \n",
       "3822              728.786824   72878.68237               5         636   \n",
       "3821             4630.787898   85411.55172               4         634   \n",
       "9999             3050.248203   30611.62821               6         757   \n",
       "\n",
       "      ratio_income_Totdebt  ratio_income_loan_amt  Probability _to_Default  \\\n",
       "1997              3.218477              10.564398                      1.0   \n",
       "2138              3.889620              11.723570                      1.0   \n",
       "9203              3.146576              14.706118                      1.0   \n",
       "9944              4.125665              13.816349                      1.0   \n",
       "5460              3.528976              13.029196                      1.0   \n",
       "...                    ...                    ...                      ...   \n",
       "3825             21.843607              20.614245                      0.0   \n",
       "3824             11.862618              19.325858                      0.0   \n",
       "3822            100.000000              31.040339                      0.0   \n",
       "3821             18.444281              16.514645                      0.0   \n",
       "9999             10.035783              15.963074                      0.0   \n",
       "\n",
       "              lgd  expected_loss  \n",
       "1997  9189.672021    9189.672021  \n",
       "2138  8607.324164    8607.324164  \n",
       "9203  8195.367792    8195.367792  \n",
       "9944  8090.260921    8090.260921  \n",
       "5460  7957.731267    7957.731267  \n",
       "...           ...            ...  \n",
       "3825  1715.751268       0.000000  \n",
       "3824  4520.777099       0.000000  \n",
       "3822  2113.083059       0.000000  \n",
       "3821  4654.680592       0.000000  \n",
       "9999  1725.887232       0.000000  \n",
       "\n",
       "[10000 rows x 12 columns]"
      ]
     },
     "execution_count": 129,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df.sort_values('expected_loss',ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Creating, Training, and Fitting a XGBoost Model to Oversampled Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "metadata": {},
   "outputs": [],
   "source": [
    "import xgboost as xgb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import data\n",
    "Loans_df = pd.read_csv(\"Loan_Data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = Loans_df.drop(['default'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [],
   "source": [
    "Y = Loans_df['default']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.3, random_state=123)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = xgb.XGBClassifier()\n",
    "clf_xgbt = model.fit(X_train, np.ravel(Y_train))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create predictions of probability for loan status using test data\n",
    "# .predict_proba creates an array of probabilities of default: [[non-defualt-0, default-1]]\n",
    "xgbt_preds = clf_xgbt.predict_proba(X_test)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 145,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create dataframes of predictions and labels\n",
    "xgbt_preds_df = pd.DataFrame(xgbt_preds[:,1][0:], columns = ['xgbt_pred_PD'])\n",
    "true_df = Y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      default  xgbt_pred_PD\n",
      "0           0      0.029665\n",
      "1           0      0.000056\n",
      "2           0      0.000002\n",
      "3           0      0.000012\n",
      "4           0      0.000077\n",
      "...       ...           ...\n",
      "2995        0      0.000043\n",
      "2996        1      0.999410\n",
      "2997        0      0.000028\n",
      "2998        0      0.000003\n",
      "2999        1      0.999972\n",
      "\n",
      "[3000 rows x 2 columns]\n"
     ]
    }
   ],
   "source": [
    "# Concatenate and print the two data frames for comparison\n",
    "print(pd.concat([true_df.reset_index(drop = True), xgbt_preds_df], axis = 1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Non-Default / Default  predictions at 60% Threshhold: \n",
      "xgbt_pred_loan_status_60\n",
      "0    2475\n",
      "1     525\n",
      "Name: count, dtype: int64\n",
      "Confusion Matrix at 60% Threshhold: \n",
      "[[2466    6]\n",
      " [   9  519]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      " Non-Default       1.00      1.00      1.00      2472\n",
      "     Default       0.99      0.98      0.99       528\n",
      "\n",
      "    accuracy                           0.99      3000\n",
      "   macro avg       0.99      0.99      0.99      3000\n",
      "weighted avg       0.99      0.99      0.99      3000\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Reassign loan status based on the threshold and print the predictions\n",
    "xgbt_preds_df['xgbt_pred_loan_status_60'] = xgbt_preds_df['xgbt_pred_PD'].apply(lambda x: 1 if x > 0.60 else 0)\n",
    "print(\"Non-Default / Default  predictions at 60% Threshhold: \")\n",
    "print(xgbt_preds_df['xgbt_pred_loan_status_60'].value_counts())\n",
    "\n",
    "# Print the confusion matrix\n",
    "print(\"Confusion Matrix at 60% Threshhold: \")\n",
    "print(confusion_matrix(Y_test, xgbt_preds_df['xgbt_pred_loan_status_60']))\n",
    "\n",
    "# Print the classification report\n",
    "target_names = ['Non-Default', 'Default']\n",
    "print(classification_report(Y_test, xgbt_preds_df['xgbt_pred_loan_status_60'], target_names=target_names))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 149,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.995\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Print the accuracy score the model\n",
    "print(clf_xgbt.score(X_test, Y_test))\n",
    "\n",
    "# Plot the ROC curve of the probabilities of default\n",
    "from sklearn.metrics import roc_curve\n",
    "\n",
    "xgb_prob_default = xgbt_preds[:, 1]\n",
    "fallout, sensitivity, thresholds = roc_curve(Y_test, xgb_prob_default)\n",
    "plt.plot(fallout, sensitivity, color = 'darkorange')\n",
    "plt.plot([0, 1], [0, 1], linestyle='--')\n",
    "plt.title(\"ROC Chart for XGBoost on PD\")\n",
    "plt.xlabel(\"Fall-out\")\n",
    "plt.ylabel(\"Sensitivity\")\n",
    "plt.show()\n",
    "\n",
    "# Compute the AUC and store it in a variable\n",
    "from sklearn.metrics import roc_auc_score\n",
    "\n",
    "xgb_auc = roc_auc_score(Y_test, xgb_prob_default)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 150,
   "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>xgbt_pred_PD</th>\n",
       "      <th>xgbt_pred_loan_status_60</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.029665</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.000056</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.000002</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.000012</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.000077</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2995</th>\n",
       "      <td>0.000043</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2996</th>\n",
       "      <td>0.999410</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2997</th>\n",
       "      <td>0.000028</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2998</th>\n",
       "      <td>0.000003</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2999</th>\n",
       "      <td>0.999972</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3000 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      xgbt_pred_PD  xgbt_pred_loan_status_60\n",
       "0         0.029665                         0\n",
       "1         0.000056                         0\n",
       "2         0.000002                         0\n",
       "3         0.000012                         0\n",
       "4         0.000077                         0\n",
       "...            ...                       ...\n",
       "2995      0.000043                         0\n",
       "2996      0.999410                         1\n",
       "2997      0.000028                         0\n",
       "2998      0.000003                         0\n",
       "2999      0.999972                         1\n",
       "\n",
       "[3000 rows x 2 columns]"
      ]
     },
     "execution_count": 150,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xgbt_preds_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 153,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "default\n",
       "0    8149\n",
       "1    1851\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 153,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df['default'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 154,
   "metadata": {},
   "outputs": [],
   "source": [
    "Loans_df.drop(['default'], axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 155,
   "metadata": {},
   "outputs": [],
   "source": [
    "Prob_to_default = clf_xgbt.predict_proba(Loans_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 159,
   "metadata": {},
   "outputs": [],
   "source": [
    "prob_data = pd.DataFrame(Prob_to_default[:,1][0:].round(decimals = 2), columns = ['Probability _to_Default'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Probability _to_Default\n",
       "0    8152\n",
       "1    1848\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 160,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prob_data['Probability _to_Default'].apply(lambda x: 1 if x > 0.60 else 0).value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 161,
   "metadata": {},
   "outputs": [],
   "source": [
    "Loans_df=pd.concat([Loans_df, prob_data], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Recovery rate\n",
    "recovery_rate = 0.1  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Loss Given Default (LGD)\n",
    "Loans_df['lgd'] = (1 - recovery_rate) * Loans_df['loan_amt_outstanding']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Expected Loss\n",
    "\n",
    "Loans_df['expected_loss'] = Loans_df['Probability _to_Default'] * Loans_df['lgd']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "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>customer_id</th>\n",
       "      <th>credit_lines_outstanding</th>\n",
       "      <th>loan_amt_outstanding</th>\n",
       "      <th>total_debt_outstanding</th>\n",
       "      <th>income</th>\n",
       "      <th>years_employed</th>\n",
       "      <th>fico_score</th>\n",
       "      <th>Probability _to_Default</th>\n",
       "      <th>lgd</th>\n",
       "      <th>expected_loss</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1997</th>\n",
       "      <td>6597386</td>\n",
       "      <td>5</td>\n",
       "      <td>10210.746690</td>\n",
       "      <td>33515.971170</td>\n",
       "      <td>107870.38960</td>\n",
       "      <td>2</td>\n",
       "      <td>649</td>\n",
       "      <td>1.0</td>\n",
       "      <td>9189.672021</td>\n",
       "      <td>9189.672021</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2138</th>\n",
       "      <td>1998635</td>\n",
       "      <td>5</td>\n",
       "      <td>9563.693515</td>\n",
       "      <td>28825.601850</td>\n",
       "      <td>112120.62640</td>\n",
       "      <td>3</td>\n",
       "      <td>641</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8607.324164</td>\n",
       "      <td>8607.324164</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9203</th>\n",
       "      <td>4836461</td>\n",
       "      <td>5</td>\n",
       "      <td>9105.964213</td>\n",
       "      <td>42558.451490</td>\n",
       "      <td>133913.38230</td>\n",
       "      <td>3</td>\n",
       "      <td>601</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8195.367792</td>\n",
       "      <td>8195.367792</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9944</th>\n",
       "      <td>3983392</td>\n",
       "      <td>4</td>\n",
       "      <td>8989.178801</td>\n",
       "      <td>30103.662560</td>\n",
       "      <td>124197.63370</td>\n",
       "      <td>2</td>\n",
       "      <td>641</td>\n",
       "      <td>1.0</td>\n",
       "      <td>8090.260921</td>\n",
       "      <td>8090.260921</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5460</th>\n",
       "      <td>2527305</td>\n",
       "      <td>5</td>\n",
       "      <td>8841.923630</td>\n",
       "      <td>32644.921580</td>\n",
       "      <td>115203.15190</td>\n",
       "      <td>2</td>\n",
       "      <td>541</td>\n",
       "      <td>1.0</td>\n",
       "      <td>7957.731267</td>\n",
       "      <td>7957.731267</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3687</th>\n",
       "      <td>4362545</td>\n",
       "      <td>0</td>\n",
       "      <td>3187.789761</td>\n",
       "      <td>2868.594545</td>\n",
       "      <td>52748.12582</td>\n",
       "      <td>4</td>\n",
       "      <td>669</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2869.010785</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3686</th>\n",
       "      <td>2432468</td>\n",
       "      <td>0</td>\n",
       "      <td>3570.845462</td>\n",
       "      <td>3645.659263</td>\n",
       "      <td>67239.68452</td>\n",
       "      <td>4</td>\n",
       "      <td>644</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3213.760916</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3685</th>\n",
       "      <td>1799861</td>\n",
       "      <td>0</td>\n",
       "      <td>2528.033133</td>\n",
       "      <td>2129.209250</td>\n",
       "      <td>43442.20361</td>\n",
       "      <td>5</td>\n",
       "      <td>728</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2275.229820</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3684</th>\n",
       "      <td>7530508</td>\n",
       "      <td>0</td>\n",
       "      <td>2614.065745</td>\n",
       "      <td>1530.457376</td>\n",
       "      <td>34018.83834</td>\n",
       "      <td>3</td>\n",
       "      <td>542</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2352.659171</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9999</th>\n",
       "      <td>5533570</td>\n",
       "      <td>1</td>\n",
       "      <td>1917.652480</td>\n",
       "      <td>3050.248203</td>\n",
       "      <td>30611.62821</td>\n",
       "      <td>6</td>\n",
       "      <td>757</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1725.887232</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10000 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      customer_id  credit_lines_outstanding  loan_amt_outstanding  \\\n",
       "1997      6597386                         5          10210.746690   \n",
       "2138      1998635                         5           9563.693515   \n",
       "9203      4836461                         5           9105.964213   \n",
       "9944      3983392                         4           8989.178801   \n",
       "5460      2527305                         5           8841.923630   \n",
       "...           ...                       ...                   ...   \n",
       "3687      4362545                         0           3187.789761   \n",
       "3686      2432468                         0           3570.845462   \n",
       "3685      1799861                         0           2528.033133   \n",
       "3684      7530508                         0           2614.065745   \n",
       "9999      5533570                         1           1917.652480   \n",
       "\n",
       "      total_debt_outstanding        income  years_employed  fico_score  \\\n",
       "1997            33515.971170  107870.38960               2         649   \n",
       "2138            28825.601850  112120.62640               3         641   \n",
       "9203            42558.451490  133913.38230               3         601   \n",
       "9944            30103.662560  124197.63370               2         641   \n",
       "5460            32644.921580  115203.15190               2         541   \n",
       "...                      ...           ...             ...         ...   \n",
       "3687             2868.594545   52748.12582               4         669   \n",
       "3686             3645.659263   67239.68452               4         644   \n",
       "3685             2129.209250   43442.20361               5         728   \n",
       "3684             1530.457376   34018.83834               3         542   \n",
       "9999             3050.248203   30611.62821               6         757   \n",
       "\n",
       "      Probability _to_Default          lgd  expected_loss  \n",
       "1997                      1.0  9189.672021    9189.672021  \n",
       "2138                      1.0  8607.324164    8607.324164  \n",
       "9203                      1.0  8195.367792    8195.367792  \n",
       "9944                      1.0  8090.260921    8090.260921  \n",
       "5460                      1.0  7957.731267    7957.731267  \n",
       "...                       ...          ...            ...  \n",
       "3687                      0.0  2869.010785       0.000000  \n",
       "3686                      0.0  3213.760916       0.000000  \n",
       "3685                      0.0  2275.229820       0.000000  \n",
       "3684                      0.0  2352.659171       0.000000  \n",
       "9999                      0.0  1725.887232       0.000000  \n",
       "\n",
       "[10000 rows x 10 columns]"
      ]
     },
     "execution_count": 165,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Loans_df.sort_values('expected_loss',ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}