project_Loan_Application-checkpoint.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e36a6ef9",
   "metadata": {},
   "source": [
    "# Problem Statement:\n",
    "    \n",
    "Loan Application Status Prediction\n",
    "\n",
    "This dataset includes details of applicants who have applied for loan. The dataset includes details like credit history, loan amount, their income, dependents etc. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0b197e46",
   "metadata": {},
   "source": [
    "# DataSet Description\n",
    "\n",
    "Loan_ID : Unique Loan ID\n",
    "\n",
    "Gender : Male/ Female\n",
    "\n",
    "Married : Applicant married (Y/N)\n",
    "\n",
    "Dependents : Number of dependents\n",
    "\n",
    "Education : Applicant Education (Graduate/ Under Graduate)\n",
    "\n",
    "Self_Employed : Self employed (Y/N)\n",
    "\n",
    "ApplicantIncome : Applicant income\n",
    "\n",
    "CoapplicantIncome : Coapplicant income\n",
    "\n",
    "LoanAmount : Loan amount in thousands of dollars\n",
    "\n",
    "Loan_Amount_Term : Term of loan in months\n",
    "\n",
    "Credit_History : credit history meets guidelines yes or no\n",
    "\n",
    "Property_Area : Urban/ Semi Urban/ Rural\n",
    "\n",
    "Loan_Status : Loan approved (Y/N) this is the target variable\n",
    "\n",
    "Target Variable - Loan_Status"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "be1af68c",
   "metadata": {},
   "source": [
    "# Dependent Variable (Target Variable):\n",
    "\n",
    "- Loan_Status\n",
    "\n",
    "You have to build a model that can predict whether the loan of the applicant will be approved or not on the basis of the details provided in the dataset. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "34434b57",
   "metadata": {},
   "source": [
    "# Importing All Requaired Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f6069878",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Importing required packages.\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import scipy.stats as st\n",
    "\n",
    "#ploting libraries\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "\n",
    "#feature engineering\n",
    "\n",
    "from sklearn.preprocessing import StandardScaler, LabelEncoder\n",
    "\n",
    "#train test split and cross validation\n",
    "from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score\n",
    "from scipy.stats import zscore\n",
    "\n",
    "#metrics\n",
    "from sklearn import metrics\n",
    "from sklearn.metrics import confusion_matrix, classification_report,accuracy_score\n",
    "from sklearn.metrics import r2_score,mean_squared_error\n",
    "from sklearn.metrics import roc_curve, roc_auc_score\n",
    "from sklearn.metrics import plot_roc_curve\n",
    "\n",
    "#ML models for classification\n",
    "import sklearn\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6b139368",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(614, 13)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#loading data sets\n",
    "df = pd.read_csv('loan.csv')\n",
    "\n",
    "# No. of rows and columns \n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "18e64a9d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Loan_ID', 'Gender', 'Married', 'Dependents', 'Education',\n",
       "       'Self_Employed', 'ApplicantIncome', 'CoapplicantIncome', 'LoanAmount',\n",
       "       'Loan_Amount_Term', 'Credit_History', 'Property_Area', 'Loan_Status'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# column names\n",
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "579f76d4",
   "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>Loan_ID</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Education</th>\n",
       "      <th>Self_Employed</th>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <th>LoanAmount</th>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <th>Credit_History</th>\n",
       "      <th>Property_Area</th>\n",
       "      <th>Loan_Status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>LP001002</td>\n",
       "      <td>Male</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>5849</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>LP001003</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>4583</td>\n",
       "      <td>1508.0</td>\n",
       "      <td>128.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Rural</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>LP001005</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>Yes</td>\n",
       "      <td>3000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>66.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>LP001006</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>0</td>\n",
       "      <td>Not Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>2583</td>\n",
       "      <td>2358.0</td>\n",
       "      <td>120.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>LP001008</td>\n",
       "      <td>Male</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>6000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>141.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Loan_ID Gender Married Dependents     Education Self_Employed  \\\n",
       "0  LP001002   Male      No          0      Graduate            No   \n",
       "1  LP001003   Male     Yes          1      Graduate            No   \n",
       "2  LP001005   Male     Yes          0      Graduate           Yes   \n",
       "3  LP001006   Male     Yes          0  Not Graduate            No   \n",
       "4  LP001008   Male      No          0      Graduate            No   \n",
       "\n",
       "   ApplicantIncome  CoapplicantIncome  LoanAmount  Loan_Amount_Term  \\\n",
       "0             5849                0.0         NaN             360.0   \n",
       "1             4583             1508.0       128.0             360.0   \n",
       "2             3000                0.0        66.0             360.0   \n",
       "3             2583             2358.0       120.0             360.0   \n",
       "4             6000                0.0       141.0             360.0   \n",
       "\n",
       "   Credit_History Property_Area Loan_Status  \n",
       "0             1.0         Urban           Y  \n",
       "1             1.0         Rural           N  \n",
       "2             1.0         Urban           Y  \n",
       "3             1.0         Urban           Y  \n",
       "4             1.0         Urban           Y  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#show all columns in dataframe\n",
    "pd.set_option('display.max_columns', None)\n",
    "\n",
    "df.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2e20222f",
   "metadata": {},
   "source": [
    "# Statistical data analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5f838298",
   "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>count</th>\n",
       "      <th>unique</th>\n",
       "      <th>top</th>\n",
       "      <th>freq</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Loan_ID</th>\n",
       "      <td>614</td>\n",
       "      <td>614</td>\n",
       "      <td>LP001002</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gender</th>\n",
       "      <td>601</td>\n",
       "      <td>2</td>\n",
       "      <td>Male</td>\n",
       "      <td>489</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Married</th>\n",
       "      <td>611</td>\n",
       "      <td>2</td>\n",
       "      <td>Yes</td>\n",
       "      <td>398</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Dependents</th>\n",
       "      <td>599</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>345</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Education</th>\n",
       "      <td>614</td>\n",
       "      <td>2</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>480</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Self_Employed</th>\n",
       "      <td>582</td>\n",
       "      <td>2</td>\n",
       "      <td>No</td>\n",
       "      <td>500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <td>614.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5403.459283</td>\n",
       "      <td>6109.041673</td>\n",
       "      <td>150.0</td>\n",
       "      <td>2877.5</td>\n",
       "      <td>3812.5</td>\n",
       "      <td>5795.0</td>\n",
       "      <td>81000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <td>614.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1621.245798</td>\n",
       "      <td>2926.248369</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1188.5</td>\n",
       "      <td>2297.25</td>\n",
       "      <td>41667.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LoanAmount</th>\n",
       "      <td>592.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>146.412162</td>\n",
       "      <td>85.587325</td>\n",
       "      <td>9.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>128.0</td>\n",
       "      <td>168.0</td>\n",
       "      <td>700.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <td>600.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>342.0</td>\n",
       "      <td>65.12041</td>\n",
       "      <td>12.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>480.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Credit_History</th>\n",
       "      <td>564.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.842199</td>\n",
       "      <td>0.364878</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Property_Area</th>\n",
       "      <td>614</td>\n",
       "      <td>3</td>\n",
       "      <td>Semiurban</td>\n",
       "      <td>233</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Loan_Status</th>\n",
       "      <td>614</td>\n",
       "      <td>2</td>\n",
       "      <td>Y</td>\n",
       "      <td>422</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   count unique        top freq         mean          std  \\\n",
       "Loan_ID              614    614   LP001002    1          NaN          NaN   \n",
       "Gender               601      2       Male  489          NaN          NaN   \n",
       "Married              611      2        Yes  398          NaN          NaN   \n",
       "Dependents           599      4          0  345          NaN          NaN   \n",
       "Education            614      2   Graduate  480          NaN          NaN   \n",
       "Self_Employed        582      2         No  500          NaN          NaN   \n",
       "ApplicantIncome    614.0    NaN        NaN  NaN  5403.459283  6109.041673   \n",
       "CoapplicantIncome  614.0    NaN        NaN  NaN  1621.245798  2926.248369   \n",
       "LoanAmount         592.0    NaN        NaN  NaN   146.412162    85.587325   \n",
       "Loan_Amount_Term   600.0    NaN        NaN  NaN        342.0     65.12041   \n",
       "Credit_History     564.0    NaN        NaN  NaN     0.842199     0.364878   \n",
       "Property_Area        614      3  Semiurban  233          NaN          NaN   \n",
       "Loan_Status          614      2          Y  422          NaN          NaN   \n",
       "\n",
       "                     min     25%     50%      75%      max  \n",
       "Loan_ID              NaN     NaN     NaN      NaN      NaN  \n",
       "Gender               NaN     NaN     NaN      NaN      NaN  \n",
       "Married              NaN     NaN     NaN      NaN      NaN  \n",
       "Dependents           NaN     NaN     NaN      NaN      NaN  \n",
       "Education            NaN     NaN     NaN      NaN      NaN  \n",
       "Self_Employed        NaN     NaN     NaN      NaN      NaN  \n",
       "ApplicantIncome    150.0  2877.5  3812.5   5795.0  81000.0  \n",
       "CoapplicantIncome    0.0     0.0  1188.5  2297.25  41667.0  \n",
       "LoanAmount           9.0   100.0   128.0    168.0    700.0  \n",
       "Loan_Amount_Term    12.0   360.0   360.0    360.0    480.0  \n",
       "Credit_History       0.0     1.0     1.0      1.0      1.0  \n",
       "Property_Area        NaN     NaN     NaN      NaN      NaN  \n",
       "Loan_Status          NaN     NaN     NaN      NaN      NaN  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe(include='all').T"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e62c02a2",
   "metadata": {},
   "source": [
    "1. The count value is not same for all columns so we can say that null value are present in some column It will solve later.\n",
    "\n",
    "2. Some outliers are present because higher diffecence between 75%  and max value of income columns.\n",
    "\n",
    "3. Here we can see that the minimum value of CoApplicant is 0 so we ca replce it by mean value."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9d0559b5",
   "metadata": {},
   "source": [
    "# Checking for null value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ec58b2b8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Loan_ID               0\n",
       "Gender               13\n",
       "Married               3\n",
       "Dependents           15\n",
       "Education             0\n",
       "Self_Employed        32\n",
       "ApplicantIncome       0\n",
       "CoapplicantIncome     0\n",
       "LoanAmount           22\n",
       "Loan_Amount_Term     14\n",
       "Credit_History       50\n",
       "Property_Area         0\n",
       "Loan_Status           0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check for null values\n",
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dcce2e2c",
   "metadata": {},
   "source": [
    "Null value present in most of the column so we have to fill it by using simple imputer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "71dfddb6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(df.isnull())##check missing value through visualization"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eeeb4d69",
   "metadata": {},
   "source": [
    "The above heat map also shows there are null values"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "47bce583",
   "metadata": {},
   "source": [
    "# checking Duplicate¶ records"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "dcb1f808",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a31c3613",
   "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>Loan_ID</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Education</th>\n",
       "      <th>Self_Employed</th>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <th>LoanAmount</th>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <th>Credit_History</th>\n",
       "      <th>Property_Area</th>\n",
       "      <th>Loan_Status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>LP001002</td>\n",
       "      <td>Male</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>5849</td>\n",
       "      <td>0.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>LP001003</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>4583</td>\n",
       "      <td>1508.0</td>\n",
       "      <td>128.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Rural</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>LP001005</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>Yes</td>\n",
       "      <td>3000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>66.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>LP001006</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>0</td>\n",
       "      <td>Not Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>2583</td>\n",
       "      <td>2358.0</td>\n",
       "      <td>120.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>LP001008</td>\n",
       "      <td>Male</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>6000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>141.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>609</th>\n",
       "      <td>LP002978</td>\n",
       "      <td>Female</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>2900</td>\n",
       "      <td>0.0</td>\n",
       "      <td>71.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>610</th>\n",
       "      <td>LP002979</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>3+</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>4106</td>\n",
       "      <td>0.0</td>\n",
       "      <td>40.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>611</th>\n",
       "      <td>LP002983</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>8072</td>\n",
       "      <td>240.0</td>\n",
       "      <td>253.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>612</th>\n",
       "      <td>LP002984</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>2</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>7583</td>\n",
       "      <td>0.0</td>\n",
       "      <td>187.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>613</th>\n",
       "      <td>LP002990</td>\n",
       "      <td>Female</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>Yes</td>\n",
       "      <td>4583</td>\n",
       "      <td>0.0</td>\n",
       "      <td>133.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Semiurban</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>614 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Loan_ID  Gender Married Dependents     Education Self_Employed  \\\n",
       "0    LP001002    Male      No          0      Graduate            No   \n",
       "1    LP001003    Male     Yes          1      Graduate            No   \n",
       "2    LP001005    Male     Yes          0      Graduate           Yes   \n",
       "3    LP001006    Male     Yes          0  Not Graduate            No   \n",
       "4    LP001008    Male      No          0      Graduate            No   \n",
       "..        ...     ...     ...        ...           ...           ...   \n",
       "609  LP002978  Female      No          0      Graduate            No   \n",
       "610  LP002979    Male     Yes         3+      Graduate            No   \n",
       "611  LP002983    Male     Yes          1      Graduate            No   \n",
       "612  LP002984    Male     Yes          2      Graduate            No   \n",
       "613  LP002990  Female      No          0      Graduate           Yes   \n",
       "\n",
       "     ApplicantIncome  CoapplicantIncome  LoanAmount  Loan_Amount_Term  \\\n",
       "0               5849                0.0         NaN             360.0   \n",
       "1               4583             1508.0       128.0             360.0   \n",
       "2               3000                0.0        66.0             360.0   \n",
       "3               2583             2358.0       120.0             360.0   \n",
       "4               6000                0.0       141.0             360.0   \n",
       "..               ...                ...         ...               ...   \n",
       "609             2900                0.0        71.0             360.0   \n",
       "610             4106                0.0        40.0             180.0   \n",
       "611             8072              240.0       253.0             360.0   \n",
       "612             7583                0.0       187.0             360.0   \n",
       "613             4583                0.0       133.0             360.0   \n",
       "\n",
       "     Credit_History Property_Area Loan_Status  \n",
       "0               1.0         Urban           Y  \n",
       "1               1.0         Rural           N  \n",
       "2               1.0         Urban           Y  \n",
       "3               1.0         Urban           Y  \n",
       "4               1.0         Urban           Y  \n",
       "..              ...           ...         ...  \n",
       "609             1.0         Rural           Y  \n",
       "610             1.0         Rural           Y  \n",
       "611             1.0         Urban           Y  \n",
       "612             1.0         Urban           Y  \n",
       "613             0.0     Semiurban           N  \n",
       "\n",
       "[614 rows x 13 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# if duplicate value present drop this row\n",
    "df.drop_duplicates() "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4a6dfd20",
   "metadata": {},
   "source": [
    "no duplicate present there because the row and column value is same"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a08411a6",
   "metadata": {},
   "source": [
    "# Checking datatypes of columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "5be21e6c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 614 entries, 0 to 613\n",
      "Data columns (total 13 columns):\n",
      " #   Column             Non-Null Count  Dtype  \n",
      "---  ------             --------------  -----  \n",
      " 0   Loan_ID            614 non-null    object \n",
      " 1   Gender             601 non-null    object \n",
      " 2   Married            611 non-null    object \n",
      " 3   Dependents         599 non-null    object \n",
      " 4   Education          614 non-null    object \n",
      " 5   Self_Employed      582 non-null    object \n",
      " 6   ApplicantIncome    614 non-null    int64  \n",
      " 7   CoapplicantIncome  614 non-null    float64\n",
      " 8   LoanAmount         592 non-null    float64\n",
      " 9   Loan_Amount_Term   600 non-null    float64\n",
      " 10  Credit_History     564 non-null    float64\n",
      " 11  Property_Area      614 non-null    object \n",
      " 12  Loan_Status        614 non-null    object \n",
      "dtypes: float64(4), int64(1), object(8)\n",
      "memory usage: 62.5+ KB\n"
     ]
    }
   ],
   "source": [
    "# check datatypes and memory captured\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "255c1ed7",
   "metadata": {},
   "source": [
    "Both categorical and Numerica type data are present:\n",
    "    \n",
    "1. categorical:-Loan_ID ,Gender,Married,Dependents ,Education,Self_Employed,Property_Area,Loan_Status\n",
    "2.Numerical:- ApplicantIncoGender,me ,CoapplicantIncome, LoanAmount,Loan_Amount_Term, Credit_History\n",
    "\n",
    "The numerical data has both int and float type .\n",
    "\n",
    "int-ApplicantIncome\n",
    "\n",
    "float-CoapplicantIncome,LoanAmount,Loan_Amount_Term,Credit_History\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4e69797b",
   "metadata": {},
   "source": [
    "# Check unique values present in each Column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "278a4099",
   "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>Unique Values</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Loan_ID</th>\n",
       "      <td>614</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gender</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Married</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Dependents</th>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Education</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Self_Employed</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <td>505</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <td>287</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LoanAmount</th>\n",
       "      <td>203</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Credit_History</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Property_Area</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Loan_Status</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Unique Values\n",
       "Loan_ID                      614\n",
       "Gender                         2\n",
       "Married                        2\n",
       "Dependents                     4\n",
       "Education                      2\n",
       "Self_Employed                  2\n",
       "ApplicantIncome              505\n",
       "CoapplicantIncome            287\n",
       "LoanAmount                   203\n",
       "Loan_Amount_Term              10\n",
       "Credit_History                 2\n",
       "Property_Area                  3\n",
       "Loan_Status                    2"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.nunique().to_frame(\"Unique Values\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "14c72e8c",
   "metadata": {},
   "source": [
    "there is all values of column Loan_ID is unique as expected, but this will not help us in analysis\n",
    "\n",
    "Income of Applicant and Coapplicant is also contain higher unique value but this column is necessary for load prediction so we can remove outliers from it.\n",
    "\n",
    "Loan status has two unique values and it is a target variable so we can use binary classification model for prediction ."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "cffa5b3e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loan_ID\n",
      "LP001002    1\n",
      "LP002328    1\n",
      "LP002305    1\n",
      "LP002308    1\n",
      "LP002314    1\n",
      "           ..\n",
      "LP001692    1\n",
      "LP001693    1\n",
      "LP001698    1\n",
      "LP001699    1\n",
      "LP002990    1\n",
      "Name: Loan_ID, Length: 614, dtype: int64\n",
      "************************************************\n",
      "Gender\n",
      "Male      489\n",
      "Female    112\n",
      "Name: Gender, dtype: int64\n",
      "************************************************\n",
      "Married\n",
      "Yes    398\n",
      "No     213\n",
      "Name: Married, dtype: int64\n",
      "************************************************\n",
      "Dependents\n",
      "0     345\n",
      "1     102\n",
      "2     101\n",
      "3+     51\n",
      "Name: Dependents, dtype: int64\n",
      "************************************************\n",
      "Education\n",
      "Graduate        480\n",
      "Not Graduate    134\n",
      "Name: Education, dtype: int64\n",
      "************************************************\n",
      "Self_Employed\n",
      "No     500\n",
      "Yes     82\n",
      "Name: Self_Employed, dtype: int64\n",
      "************************************************\n",
      "ApplicantIncome\n",
      "2500    9\n",
      "4583    6\n",
      "6000    6\n",
      "2600    6\n",
      "3333    5\n",
      "       ..\n",
      "3244    1\n",
      "4408    1\n",
      "3917    1\n",
      "3992    1\n",
      "7583    1\n",
      "Name: ApplicantIncome, Length: 505, dtype: int64\n",
      "************************************************\n",
      "CoapplicantIncome\n",
      "0.0       273\n",
      "2500.0      5\n",
      "2083.0      5\n",
      "1666.0      5\n",
      "2250.0      3\n",
      "         ... \n",
      "2791.0      1\n",
      "1010.0      1\n",
      "1695.0      1\n",
      "2598.0      1\n",
      "240.0       1\n",
      "Name: CoapplicantIncome, Length: 287, dtype: int64\n",
      "************************************************\n",
      "LoanAmount\n",
      "120.0    20\n",
      "110.0    17\n",
      "100.0    15\n",
      "160.0    12\n",
      "187.0    12\n",
      "         ..\n",
      "240.0     1\n",
      "214.0     1\n",
      "59.0      1\n",
      "166.0     1\n",
      "253.0     1\n",
      "Name: LoanAmount, Length: 203, dtype: int64\n",
      "************************************************\n",
      "Loan_Amount_Term\n",
      "360.0    512\n",
      "180.0     44\n",
      "480.0     15\n",
      "300.0     13\n",
      "240.0      4\n",
      "84.0       4\n",
      "120.0      3\n",
      "60.0       2\n",
      "36.0       2\n",
      "12.0       1\n",
      "Name: Loan_Amount_Term, dtype: int64\n",
      "************************************************\n",
      "Credit_History\n",
      "1.0    475\n",
      "0.0     89\n",
      "Name: Credit_History, dtype: int64\n",
      "************************************************\n",
      "Property_Area\n",
      "Semiurban    233\n",
      "Urban        202\n",
      "Rural        179\n",
      "Name: Property_Area, dtype: int64\n",
      "************************************************\n",
      "Loan_Status\n",
      "Y    422\n",
      "N    192\n",
      "Name: Loan_Status, dtype: int64\n",
      "************************************************\n"
     ]
    }
   ],
   "source": [
    "#Lets check the value count of each column to see if there are any unexpected and unwanted entries present in the column.\n",
    "for i in df:\n",
    "        print(i)\n",
    "        print(df[i].value_counts())\n",
    "        print('************************************************')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c03ab21a",
   "metadata": {},
   "source": [
    "Observation:\n",
    "\n",
    "1.We  will change float type of column like CoapplicantIncome,LoanAmount,Loan_Amount_Term,Credit_History into int type because we saw that only 0 is present after decimal point means its a integer type data.\n",
    "\n",
    "2.In dependents columns 3+ is present that is invalid type of data so we need to change it by 3 and we consider 3 is the maximum dependence value.\n",
    "\n",
    "3.I observed that the datatype of dependents is object but value is 0,1,2,3+ is intiger type .The datatype is object because of 3+ so fistly we replace it by intiger value then convert data type of dependens column inti int type.\n",
    "\n",
    "\n",
    "4.Loan_Amount_Term is given in monthly bases we can convert it in yearly for better understanding\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "04a1c6cd",
   "metadata": {},
   "source": [
    "# DATA CLEANING"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6c18eb6d",
   "metadata": {},
   "source": [
    "# Dealing With Null Value"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "741e9d69",
   "metadata": {},
   "source": [
    "Firstly we replace zeros value of coapplicantIncome column with mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "7a4a117b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"CoapplicantIncome\"].min()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "f05c0083",
   "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>Loan_ID</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Education</th>\n",
       "      <th>Self_Employed</th>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <th>LoanAmount</th>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <th>Credit_History</th>\n",
       "      <th>Property_Area</th>\n",
       "      <th>Loan_Status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>LP001002</td>\n",
       "      <td>Male</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>5849</td>\n",
       "      <td>1621.245798</td>\n",
       "      <td>NaN</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>LP001003</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>4583</td>\n",
       "      <td>1508.000000</td>\n",
       "      <td>128.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Rural</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>LP001005</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>Yes</td>\n",
       "      <td>3000</td>\n",
       "      <td>1621.245798</td>\n",
       "      <td>66.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>LP001006</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>0</td>\n",
       "      <td>Not Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>2583</td>\n",
       "      <td>2358.000000</td>\n",
       "      <td>120.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>LP001008</td>\n",
       "      <td>Male</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>6000</td>\n",
       "      <td>1621.245798</td>\n",
       "      <td>141.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>609</th>\n",
       "      <td>LP002978</td>\n",
       "      <td>Female</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>2900</td>\n",
       "      <td>1621.245798</td>\n",
       "      <td>71.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>610</th>\n",
       "      <td>LP002979</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>3+</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>4106</td>\n",
       "      <td>1621.245798</td>\n",
       "      <td>40.0</td>\n",
       "      <td>180.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>611</th>\n",
       "      <td>LP002983</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>8072</td>\n",
       "      <td>240.000000</td>\n",
       "      <td>253.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>612</th>\n",
       "      <td>LP002984</td>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>2</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>7583</td>\n",
       "      <td>1621.245798</td>\n",
       "      <td>187.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>613</th>\n",
       "      <td>LP002990</td>\n",
       "      <td>Female</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>Yes</td>\n",
       "      <td>4583</td>\n",
       "      <td>1621.245798</td>\n",
       "      <td>133.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Semiurban</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>614 rows × 13 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Loan_ID  Gender Married Dependents     Education Self_Employed  \\\n",
       "0    LP001002    Male      No          0      Graduate            No   \n",
       "1    LP001003    Male     Yes          1      Graduate            No   \n",
       "2    LP001005    Male     Yes          0      Graduate           Yes   \n",
       "3    LP001006    Male     Yes          0  Not Graduate            No   \n",
       "4    LP001008    Male      No          0      Graduate            No   \n",
       "..        ...     ...     ...        ...           ...           ...   \n",
       "609  LP002978  Female      No          0      Graduate            No   \n",
       "610  LP002979    Male     Yes         3+      Graduate            No   \n",
       "611  LP002983    Male     Yes          1      Graduate            No   \n",
       "612  LP002984    Male     Yes          2      Graduate            No   \n",
       "613  LP002990  Female      No          0      Graduate           Yes   \n",
       "\n",
       "     ApplicantIncome  CoapplicantIncome  LoanAmount  Loan_Amount_Term  \\\n",
       "0               5849        1621.245798         NaN             360.0   \n",
       "1               4583        1508.000000       128.0             360.0   \n",
       "2               3000        1621.245798        66.0             360.0   \n",
       "3               2583        2358.000000       120.0             360.0   \n",
       "4               6000        1621.245798       141.0             360.0   \n",
       "..               ...                ...         ...               ...   \n",
       "609             2900        1621.245798        71.0             360.0   \n",
       "610             4106        1621.245798        40.0             180.0   \n",
       "611             8072         240.000000       253.0             360.0   \n",
       "612             7583        1621.245798       187.0             360.0   \n",
       "613             4583        1621.245798       133.0             360.0   \n",
       "\n",
       "     Credit_History Property_Area Loan_Status  \n",
       "0               1.0         Urban           Y  \n",
       "1               1.0         Rural           N  \n",
       "2               1.0         Urban           Y  \n",
       "3               1.0         Urban           Y  \n",
       "4               1.0         Urban           Y  \n",
       "..              ...           ...         ...  \n",
       "609             1.0         Rural           Y  \n",
       "610             1.0         Rural           Y  \n",
       "611             1.0         Urban           Y  \n",
       "612             1.0         Urban           Y  \n",
       "613             0.0     Semiurban           N  \n",
       "\n",
       "[614 rows x 13 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "df[\"CoapplicantIncome\"].replace(0,df[\"CoapplicantIncome\"].mean(),inplace=True)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "3c2cf630",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "16.12000084"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"CoapplicantIncome\"].min()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9816833b",
   "metadata": {},
   "source": [
    "# Now we replace the missing value of numerical column with mean and mediam and categorical with mode value."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "63a6d2f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Replacing NaN values in LoanAmount column with median value\n",
    "\n",
    "df[\"LoanAmount\"] = df[\"LoanAmount\"].fillna(df[\"LoanAmount\"].median())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "83774d7e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# replacing Nan Or Null values in all other categorical columns with mode of that column\n",
    "df[\"Gender\"]=df[\"Gender\"].fillna(df[\"Gender\"].mode()[0])\n",
    "df[\"Married\"]=df[\"Married\"].fillna(df[\"Married\"].mode()[0])\n",
    "df[\"Dependents\"]=df[\"Dependents\"].fillna(df[\"Dependents\"].mode()[0])\n",
    "df[\"Self_Employed\"]=df[\"Self_Employed\"].fillna(df[\"Self_Employed\"].mode()[0])\n",
    "df[\"Credit_History\"]=df[\"Credit_History\"].fillna(df[\"Credit_History\"].mode()[0])\n",
    "df[\"Loan_Amount_Term\"]=df[\"Loan_Amount_Term\"].fillna(df[\"Loan_Amount_Term\"].mode()[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6c24c379",
   "metadata": {},
   "source": [
    "# Check for null value "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "1eb738f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "c57b76db",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(df.isnull())##check missing value through visualization"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f6aa18f4",
   "metadata": {},
   "source": [
    "Here we can see  are successfully  handle NaN value ."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "516d42ff",
   "metadata": {},
   "source": [
    "# Lets check if there is any empty observation present in the dataset\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "5bb5e041",
   "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>Loan_ID</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Education</th>\n",
       "      <th>Self_Employed</th>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <th>LoanAmount</th>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <th>Credit_History</th>\n",
       "      <th>Property_Area</th>\n",
       "      <th>Loan_Status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [Loan_ID, Gender, Married, Dependents, Education, Self_Employed, ApplicantIncome, CoapplicantIncome, LoanAmount, Loan_Amount_Term, Credit_History, Property_Area, Loan_Status]\n",
       "Index: []"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "df.loc[df[\"Loan_Status\"]== \"  \"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "71ad2085",
   "metadata": {},
   "source": [
    "# Type converston from float to int :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "2026ad64",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Loan_Amount_Term']=df['Loan_Amount_Term'].astype('int')\n",
    "df['Credit_History']=df['Credit_History'].astype('int')\n",
    "df['CoapplicantIncome']=df['CoapplicantIncome'].astype('int')\n",
    "df['LoanAmount']=df['LoanAmount'].astype('int')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "dce5a8aa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 614 entries, 0 to 613\n",
      "Data columns (total 13 columns):\n",
      " #   Column             Non-Null Count  Dtype \n",
      "---  ------             --------------  ----- \n",
      " 0   Loan_ID            614 non-null    object\n",
      " 1   Gender             614 non-null    object\n",
      " 2   Married            614 non-null    object\n",
      " 3   Dependents         614 non-null    object\n",
      " 4   Education          614 non-null    object\n",
      " 5   Self_Employed      614 non-null    object\n",
      " 6   ApplicantIncome    614 non-null    int64 \n",
      " 7   CoapplicantIncome  614 non-null    int32 \n",
      " 8   LoanAmount         614 non-null    int32 \n",
      " 9   Loan_Amount_Term   614 non-null    int32 \n",
      " 10  Credit_History     614 non-null    int32 \n",
      " 11  Property_Area      614 non-null    object\n",
      " 12  Loan_Status        614 non-null    object\n",
      "dtypes: int32(4), int64(1), object(8)\n",
      "memory usage: 52.9+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5e3e62b2",
   "metadata": {},
   "source": [
    "# Covert monthly value of Loan_Amount_Term  into  yearly"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "93b22724",
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"Loan_Amount_Term\"]=df[\"Loan_Amount_Term\"]/12"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "190c6105",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([30., 10., 20., 15.,  5., 25., 40.,  3.,  7.,  1.])"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Loan_Amount_Term\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "27017724",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Loan_Amount_Term']=df['Loan_Amount_Term'].astype('int')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "e912e91a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([30, 10, 20, 15,  5, 25, 40,  3,  7,  1])"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Loan_Amount_Term\"].unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "94d45fb1",
   "metadata": {},
   "source": [
    "# Replace invalid data :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "f3f00da6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['0', '1', '2', '3+'], dtype=object)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Dependents'].unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "65e01add",
   "metadata": {},
   "source": [
    "3+ is invalid type data so can replace with 3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "37cbdeb0",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Dependents'].replace('3+',3,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "67317f9f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['0', '1', '2', 3], dtype=object)"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Dependents'].unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0e3ea3c6",
   "metadata": {},
   "source": [
    "now conver datatype of dependents column into int,"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "5f9cd927",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Dependents']=df['Dependents'].astype('int')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "59ca37fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype('int32')"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Dependents'].dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "83a3c62d",
   "metadata": {},
   "source": [
    "# Drop unnecessary columns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1bad2275",
   "metadata": {},
   "source": [
    "load_id, this is very important column for banks as there are many people with same name and age apply for loans with loan ID it is simpler for banks to find the right person.but we need this data for analysis purpose only, so we don't require this column in our project analysis as id might complicate our project and we might not get proper predictions.so we will drop this column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "6882406f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop(\"Loan_ID\",inplace = True, axis = 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c9c77e63",
   "metadata": {},
   "source": [
    "# Segregate the numerical and Categorical variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "81b7a770",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>Education</th>\n",
       "      <th>Self_Employed</th>\n",
       "      <th>Property_Area</th>\n",
       "      <th>Loan_Status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>381</th>\n",
       "      <td>Male</td>\n",
       "      <td>No</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>Semiurban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>263</th>\n",
       "      <td>Female</td>\n",
       "      <td>No</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>83</th>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>Semiurban</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>342</th>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Not Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>574</th>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>Semiurban</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Gender Married     Education Self_Employed Property_Area Loan_Status\n",
       "381    Male      No      Graduate            No     Semiurban           Y\n",
       "263  Female      No      Graduate            No         Rural           Y\n",
       "83     Male     Yes      Graduate            No     Semiurban           N\n",
       "342    Male     Yes  Not Graduate            No         Urban           Y\n",
       "574    Male     Yes      Graduate            No     Semiurban           N"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "categorical = [feature for feature in df.columns if df[feature].dtypes=='object']\n",
    "df[categorical].sample(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "2c43015c",
   "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>Dependents</th>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <th>LoanAmount</th>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <th>Credit_History</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>552</th>\n",
       "      <td>1</td>\n",
       "      <td>3333</td>\n",
       "      <td>3250</td>\n",
       "      <td>158</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>170</th>\n",
       "      <td>0</td>\n",
       "      <td>1820</td>\n",
       "      <td>1769</td>\n",
       "      <td>95</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>308</th>\n",
       "      <td>0</td>\n",
       "      <td>20233</td>\n",
       "      <td>1621</td>\n",
       "      <td>480</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>417</th>\n",
       "      <td>2</td>\n",
       "      <td>1600</td>\n",
       "      <td>20000</td>\n",
       "      <td>239</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>370</th>\n",
       "      <td>0</td>\n",
       "      <td>15759</td>\n",
       "      <td>1621</td>\n",
       "      <td>55</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Dependents  ApplicantIncome  CoapplicantIncome  LoanAmount  \\\n",
       "552           1             3333               3250         158   \n",
       "170           0             1820               1769          95   \n",
       "308           0            20233               1621         480   \n",
       "417           2             1600              20000         239   \n",
       "370           0            15759               1621          55   \n",
       "\n",
       "     Loan_Amount_Term  Credit_History  \n",
       "552                30               1  \n",
       "170                30               1  \n",
       "308                30               1  \n",
       "417                30               1  \n",
       "370                30               1  "
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "numerical = [feature for feature in df.columns if df[feature].dtypes!='object']\n",
    "df[numerical].sample(5)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f583cb6",
   "metadata": {},
   "source": [
    "# Univariate Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d3e785e5",
   "metadata": {},
   "source": [
    "# check outliers in numerical values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "ddc1c205",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x504 with 3 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "f, axes = plt.subplots( ncols=3, figsize=(15, 7))\n",
    "sns.boxplot(data=df[\"ApplicantIncome\"],ax = axes[0])\n",
    "sns.boxplot(data=df[\"CoapplicantIncome\"],ax = axes[1])\n",
    "sns.boxplot(data=df[\"LoanAmount\"],ax = axes[2])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0582ca2",
   "metadata": {},
   "source": [
    "outliers present in all above three columns later it will be remove."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "56233076",
   "metadata": {},
   "source": [
    "# Distribution plot for all numerical columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "fad02ee7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Distribution plot for all numerical columns\n",
    "for i in df.describe():              \n",
    "    plt.figure(figsize = (8, 4))\n",
    "    sns.distplot(df[i], bins = 10, color=\"g\")\n",
    "    plt.title(i)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ad9c48a3",
   "metadata": {},
   "source": [
    "Here also we can see that skewness is present in all the Numerical columns.we have to remove it later."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "55626780",
   "metadata": {},
   "source": [
    "# Count PLot for categorical data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "489aee79",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "for i in df[categorical]:              \n",
    "    plt.figure(figsize = (8, 4))\n",
    "    sns.countplot(x=df[i],data=df[categorical])\n",
    "    plt.title(i)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "82fc572b",
   "metadata": {},
   "source": [
    "Key Observations:\n",
    "\n",
    "* we can  see that most of the applicants are Male.\n",
    "\n",
    "* we can see that most of the applicants are Married.\n",
    "\n",
    "* we can  see that most of the applicants have 0 dependents.\n",
    "\n",
    "*  we can  see that most of the applicants are minimum Graduate.\n",
    "\n",
    "* we can see that most of the applicants are salaried.\n",
    "\n",
    "* we can csee that most of the properties are from semiurban than urban and least in Rural Area.\n",
    "\n",
    "* In Our Target column Loan_Status most of the applicants are elidgible for loan."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4ea40a23",
   "metadata": {},
   "source": [
    "# Bivariate Visualization"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2ac9972e",
   "metadata": {},
   "source": [
    "# Bivariate Analysis of numericalvariable wirh respect to target variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "818a45d0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Gender', 'Married', 'Dependents', 'Education', 'Self_Employed',\n",
       "       'ApplicantIncome', 'CoapplicantIncome', 'LoanAmount',\n",
       "       'Loan_Amount_Term', 'Credit_History', 'Property_Area', 'Loan_Status'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "6de83de9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Loan_Status', ylabel='Loan_Amount_Term'>"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x720 with 4 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "f, axes = plt.subplots(nrows=2, ncols=2, figsize=(15,10))\n",
    "\n",
    "sns.barplot(x=\"Loan_Status\",y=\"ApplicantIncome\",data=df,ax = axes[0,0])\n",
    "sns.barplot(x=\"Loan_Status\",y=\"CoapplicantIncome\",data=df,ax = axes[0,1])\n",
    "sns.barplot(x=\"Loan_Status\",y=\"LoanAmount\",data=df,ax = axes[1,0])\n",
    "sns.barplot(x=\"Loan_Status\",y=\"Loan_Amount_Term\",data=df,ax = axes[1,1])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ffa00bfd",
   "metadata": {},
   "source": [
    "Observation for each plot :\n",
    "\n",
    "1.Chance of  loan approval is incresed for the Applicant whoes Income t is  between 5000 to 6000  dollar .\n",
    "\n",
    "2.If the income of Coapplicant is between 2000 to 2500 dollar the chances of loan aproval is higher.\n",
    "\n",
    "3.The maximum  loan amount is  142 thousand dollar for loan is approved.\n",
    "\n",
    "4.Higher no. of applicant preferred for loan amount term 25 to 30 years. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7fde20dc",
   "metadata": {},
   "source": [
    "# Bivariate Analysis of Categorical variable wirh respect to target variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "58fec42c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Loan_Status', ylabel='count'>"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA4MAAARvCAYAAACitjGNAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAACy3UlEQVR4nOzde5xVdbn48c8jIJhoiqChqJDhhZsjjlheUVSsvGYq5gXDQk94LS21U5HFOVaUpXk0PBpqKBKKkpUnb6QmqYMSgpewRJ3kh4hJYkIwPr8/ZjMNMOAAs2fPzP68X6957b2+6/td+9njvHh81vqu74rMRJIkSZJUXjYpdQCSJEmSpOZnMShJkiRJZchiUJIkSZLKkMWgJEmSJJUhi0FJkiRJKkMWg5IkSZJUhiwGJUlqRhHRKSKejIg/RcSciPh2ob1LRNwfEXMLr1vXG3NZRLwUES9GxNDSRS9JakvC5wxKktR8IiKAzTNzSUR0AB4DLgA+A7yVmVdGxKXA1pn5tYjoA9wODAK2Bx4Ads3MmhJ9BUlSG9G+1AFsjK5du2bPnj1LHYYkqRnMmDHjzczsVuo4NlbWnoVdUtjsUPhJ4FhgcKH9ZmAa8LVC+8TMXAa8HBEvUVsYTl/X55gjJak8bEx+bNXFYM+ePamqqip1GJKkZhARr5Q6hqYSEe2AGcDHgGsz84mI2C4z5wNk5vyI2LbQfQfgj/WGVxfa1skcKUnlYWPyo/cMSpLUzDKzJjMrgB7AoIjot47u0dAhGuwYMTIiqiKiauHChU0QqSSpLbMYlCSpRDLzbWqngx4JLIiI7gCF1zcK3aqBHesN6wG8vpbjjcvMysys7Nat1c+olSQVmcWgJEnNKCK6RcRWhfebAYcBLwBTgeGFbsOBewrvpwLDIqJjRPQCegNPNmvQkqQ2qVXfMyhJrdXy5cuprq5m6dKlpQ6lxenUqRM9evSgQ4cOpQ6lWLoDNxfuG9wEmJSZ90bEdGBSRJwFvAqcCJCZcyJiEvAcsAIY5UqiktQ4bSnfFiM/Fq0YjIhOwCNAx8LnTM7Mb0XEaOCLwMqbGS7PzN8UxlwGnAXUAOdn5v8VKz5JKqXq6mq22GILevbsSe2TBgSQmSxatIjq6mp69epV6nCKIjNnAXs10L4IGLKWMWOAMUUOTZLanLaSb4uVH4t5ZXAZcGj95yhFxG8L+67KzLH1OxeeozQM6EvhOUoR4XOUJLVJS5cubfWJqRgigm222QYXP5EkNYW2km+LlR+Lds9g1mroOUprU/ccpcx8GVj5HCVJapNae2IqFn8vkqSm1FbySjG+R1EXkImIdhExk9oV0e7PzCcKu86NiFkRcVNEbF1o2wF4rd7wBp+j5LLZkrSqBQsW8LnPfY6PfvSj7L333nziE59gypQpG33cadOmcdRRRzVBhJIktUwRwemnn163vWLFCrp167bR+e/111/ns5/97HqNOfPMM5k8efJGfe76KmoxuJbnKF0H7AJUAPOBHxa6N+o5Si6bLUn/lpkcd9xxHHTQQfz1r39lxowZTJw4kerq6maPZcWKFc3+mZIkbYzNN9+c2bNn89577wFw//33s8MOa1yPWqfV89+KFSvYfvvtm72w2xDNsppoZr4dEdOAI+vfKxgRNwD3FjYb/RylYtj7klua66PahBk/OKPUIUgCHnroITbddFPOOeecuradd96Z8847j5qaGi699FKmTZvGsmXLGDVqFGeffTbTpk1j9OjRdO3aldmzZ7P33nvzi1/8gojgvvvu48ILL6Rr164MHDiw7pjvvvsu5513Hs8++ywrVqxg9OjRHHvssYwfP55f//rXLF26lHfffZeHHnqoFL8GqUV59Yr+pQ6hVdnpm8+WOgSVuU9+8pP8+te/5rOf/Sy33347p5xyCo8++igATz75JBdeeCHvvfcem222GT//+c/Zbbfd1sh/Z5xxxirbN910E0cddRSzZ89eaz7OTM477zweeughevXqRea67qgrjmKuJtoNWF4oBFc+R+l7EdE9M+cXuh0PzC68nwrcFhE/onYBGZ+jJEkfYM6cOasUbfXdeOONfPjDH+app55i2bJl7L///hxxxBEAPPPMM8yZM4ftt9+e/fffnz/84Q9UVlbyxS9+kYceeoiPfexjnHzyyXXHGjNmDIceeig33XQTb7/9NoMGDeKwww4DYPr06cyaNYsuXboU/wtLktTEhg0bxhVXXMFRRx3FrFmzGDFiRF0xuPvuu/PII4/Qvn17HnjgAS6//HLuvPNOYNX8N378+FW2582bV3f8teXjZ555hhdffJFnn32WBQsW0KdPH0aMGNGs372YVwbX9hylWyOigtopoPOAs8HnKElSUxg1ahSPPfYYm266KTvvvDOzZs2qm6ayePFi5s6dy6abbsqgQYPo0aMHABUVFcybN4/OnTvTq1cvevfuDcBpp53GuHHjAPjd737H1KlTGTu2dnLH0qVLefXVVwE4/PDDLQQlSa3WgAEDmDdvHrfffjuf+tSnVtm3ePFihg8fzty5c4kIli9fXrdv9fy3tnz4u9/9rsF8/Mgjj3DKKafQrl07tt9+ew499NAifcO1K1oxuI7nKJ3eQPeV+3yOkiSth759+9adoQS49tprefPNN6msrGSnnXbimmuuYejQoauMmTZtGh07dqzbbteuXd39DmtbqSwzufPOO9ltt91WaX/iiSfYfPPNm+rrSJJUEscccwwXX3wx06ZNY9GiRXXt3/jGNzjkkEOYMmUK8+bNY/DgwXX7Vs9/a8uHmdlgPv7Nb35T8pVOi7qAjCSpuA499FCWLl3KddddV9f2z3/+E4ChQ4dy3XXX1Z3F/POf/8y777671mPtvvvuvPzyy/zlL38B4Pbbb6/bN3ToUK655pq6+xmeeeaZJv8ukiSVyogRI/jmN79J//6r3vO7ePHiugVlxo8fv0HHXls+Puigg5g4cSI1NTXMnz+fhx9+eKO+w4awGJSkViwiuPvuu/n9739Pr169GDRoEMOHD+d73/seX/jCF+jTpw8DBw6kX79+nH322etc8bNTp06MGzeOT3/60xxwwAHsvPPOdfu+8Y1vsHz5cgYMGEC/fv34xje+0RxfT5KkZtGjRw8uuOCCNdq/+tWvctlll7H//vtTU7Nhd7CtLR8ff/zx9O7dm/79+/Mf//EfHHzwwRv7NdZblGLVmqZSWVmZVVVVTXIsVxNdP64mKm2c559/nj322KPUYbRYDf1+ImJGZlaWKKRWpylzpNaPq4muH1cTVTG1tXzb1PnRK4OSJEmSVIYsBiVJkiSpDFkMSpIkSVIZshiUJEmSpDJkMShJkiRJZchiUJIkSZLKkMWgJJWpiOD000+v216xYgXdunXjqKOOWue4adOmfWAfSZJUKyL4yle+Urc9duxYRo8eXbqA6mlf6gAkSU3/rNPGPAt08803Z/bs2bz33ntsttlm3H///eywww5NGockSS1JKfJtx44dueuuu7jsssvo2rVrk37+xvLKoCSVsU9+8pP8+te/BuD222/nlFNOqdv35JNPst9++7HXXnux33778eKLL64x/t1332XEiBHss88+7LXXXtxzzz3NFrskSa1B+/btGTlyJFddddUa+1555RWGDBnCgAEDGDJkCK+++mqzxmYxKEllbNiwYUycOJGlS5cya9Ys9t1337p9u+++O4888gjPPPMMV1xxBZdffvka48eMGcOhhx7KU089xcMPP8wll1zCu+++25xfQZKkFm/UqFFMmDCBxYsXr9J+7rnncsYZZzBr1ixOPfVUzj///GaNy2miklTGBgwYwLx587j99tv51Kc+tcq+xYsXM3z4cObOnUtEsHz58jXG/+53v2Pq1KmMHTsWgKVLl/Lqq6+yxx57NEv8kiS1BltuuSVnnHEGV199NZtttlld+/Tp07nrrrsAOP300/nqV7/arHFZDEpSmTvmmGO4+OKLmTZtGosWLapr/8Y3vsEhhxzClClTmDdvHoMHD15jbGZy5513sttuuzVjxJIktT4XXnghAwcO5POf//xa+0REM0bkNFFJKnsjRozgm9/8Jv3791+lffHixXULyowfP77BsUOHDuWaa64hMwF45plnihqrJEmtVZcuXTjppJO48cYb69r2228/Jk6cCMCECRM44IADmjUmi0FJKnM9evTgggsuWKP9q1/9Kpdddhn7778/NTU1DY79xje+wfLlyxkwYAD9+vXjG9/4RrHDlSSp1frKV77Cm2++Wbd99dVX8/Of/5wBAwZw66238pOf/KRZ43GaqCS1AI1ZmrqpLVmyZI22wYMH100H/cQnPsGf//znun3f+c531uiz2Wab8bOf/azosUqS1BRKnW+32247/vnPf9Zt9+zZk4ceeqjZY1rJK4OSJEmSVIYsBiVJkiSpDFkMSpIkSVIZshiUJEmSpDJkMShJUjOKiB0j4uGIeD4i5kTEBYX20RHxt4iYWfj5VL0xl0XESxHxYkQMLV30kqS2pGjFYER0iognI+JPhWT37UJ7l4i4PyLmFl63rjfGZCdJautWAF/JzD2AjwOjIqJPYd9VmVlR+PkNQGHfMKAvcCTwPxHRrhSBS5LalmJeGVwGHJqZewIVwJER8XHgUuDBzOwNPFjYNtlJUjNr164dFRUVdT/z5s0r2mf17NlzlecqlbPMnJ+ZTxfevwM8D+ywjiHHAhMzc1lmvgy8BAwqfqSSpI2VmRxwwAH89re/rWubNGkSRx55ZAmj+reiPWcwMxNY+VCNDoWfpDapDS603wxMA75GvWQHvBwRK5Pd9GLFKEktxatX9G/S4+30zWc/sM9mm23GzJkzm/RztX4ioiewF/AEsD9wbkScAVRRe/Xw79QWin+sN6yadRePkqS1aO58GxFcf/31nHjiiRxyyCHU1NTw9a9/nfvuu69J49hQRb1nMCLaRcRM4A3g/sx8AtguM+dD7dlRYNtC9x2A1+oNbzDZRcTIiKiKiKqFCxcWM3xJKjszZszg4IMPZu+992bo0KHMnz8fqH3Q/EUXXcRBBx3EHnvswVNPPcVnPvMZevfuzX/+53/WjT/uuOPYe++96du3L+PGjWvwM37xi18waNAgKioqOPvss6mpqWmW79bSRERn4E7gwsz8B3AdsAu1s2nmAz9c2bWB4bmWY5ojJamF6devH0cffTTf+973+Pa3v81pp53GmDFj2Geffdhrr7245557AJgzZ05dfhwwYABz584temxFLQYzsyYzK4AewKCI6LeO7o1Kdpk5LjMrM7OyW7duTRSpJJWf9957r26K6PHHH8/y5cs577zzmDx5MjNmzGDEiBF8/etfr+u/6aab8sgjj3DOOedw7LHHcu211zJ79mzGjx/PokWLALjpppuYMWMGVVVVXH311XXtKz3//PPccccd/OEPf2DmzJm0a9eOCRMmNOv3bgkiogO1heCEzLwLIDMXFPLm+8AN/HsqaDWwY73hPYDXGzquOVKSWqZvfetb3Hbbbfz2t79l6dKlHHrooTz11FM8/PDDXHLJJbz77rtcf/31XHDBBcycOZOqqip69OhR9LiKNk20vsx8OyKmUXsv4IKI6J6Z8yOiO7VXDWE9kp0kaeOtPk109uzZzJ49m8MPPxyAmpoaunfvXrf/mGOOAaB///707du3bt9HP/pRXnvtNbbZZhuuvvpqpkyZAsBrr73G3Llz2WabbeqO8eCDDzJjxgz22WcfoLYg3XbbbSknERHAjcDzmfmjeu3dV86cAY4HZhfeTwVui4gfAdsDvYEnmzFkSdJG2nzzzTn55JPp3LkzkyZN4le/+hVjx44FYOnSpbz66qt84hOfYMyYMVRXV9fNvim2ohWDEdENWF4oBDcDDgO+R21SGw5cWXi9pzDEZCdJJZSZ9O3bl+nTG75Vu2PHjgBssskmde9Xbq9YsYJp06bxwAMPMH36dD70oQ8xePBgli5dusZnDB8+nP/+7/8u3hdp+fYHTgeeLdxKAXA5cEpEVFA7K2YecDZAZs6JiEnAc9SuRDoqM8tzbq0ktWKbbLIJm2yyCZnJnXfeyW677bbK/j322IN9992XX//61wwdOpT//d//5dBDDy1uTEU8dnfg4YiYBTxF7T2D91JbBB4eEXOBwwvbZOYcYGWyuw+TnSQ1q912242FCxfWFYPLly9nzpw5jR6/ePFitt56az70oQ/xwgsv8Mc//nGNPkOGDGHy5Mm88UbtpJC33nqLV155pWm+QCuRmY9lZmTmgPqPkcjM0zOzf6H9mHpXCcnMMZm5S2bulpm/XdfxJUkt29ChQ7nmmmuoXW8TnnnmGQD++te/8tGPfpTzzz+fY445hlmzZhU9lmKuJjqL2hXSVm9fBAxZy5gxwJhixSRJWrtNN92UyZMnc/7557N48WJWrFjBhRdeSN++fRs1/sgjj+T6669nwIAB7Lbbbnz84x9fo0+fPn347ne/yxFHHMH7779Phw4duPbaa9l5552b+utIktQifeMb3+DCCy9kwIABZCY9e/bk3nvv5Y477uAXv/gFHTp04CMf+Qjf/OY3ix5LrKxIW6PKysqsqqpqkmPtfcktTXKccjHjB2eUOgSpVXv++efZY489Sh1Gi9XQ7yciZmRmZYlCanWaMkdq/TT10vVtXWMehSNtqLaWb5s6PxZ1NVFJkiRJUstkMShJkiRJZchiUJIkSZLKkMWgJJVIa75nu5j8vUiSmlJbySvF+B4Wg5JUAp06dWLRokVtJkE1lcxk0aJFdOrUqdShSJLagLaSb4uVH4v2aAlJ0tr16NGD6upqFi5cWOpQWpxOnTrRo0ePUochSWoD2lK+LUZ+tBiUpBLo0KEDvXr1KnUYkiS1aebbdXOaqCRJkiSVIYtBSZIkSSpDFoOSJEmSVIYsBiVJkiSpDFkMSpIkSVIZshiUJEmSpDJkMShJkiRJZchiUJIkSZLKkMWgJEmSJJUhi0FJkiRJKkMWg5IkSZJUhiwGJUmSJKkMWQxKkiRJUhmyGJQkSZKkMmQxKEmSJEllyGJQkiRJkspQ0YrBiNgxIh6OiOcjYk5EXFBoHx0Rf4uImYWfT9Ubc1lEvBQRL0bE0GLFJkmSJEnlrn0Rj70C+EpmPh0RWwAzIuL+wr6rMnNs/c4R0QcYBvQFtgceiIhdM7OmiDFKkiRJUlkq2pXBzJyfmU8X3r8DPA/ssI4hxwITM3NZZr4MvAQMKlZ8kiRJklTOmuWewYjoCewFPFFoOjciZkXETRGxdaFtB+C1esOqaaB4jIiREVEVEVULFy4sZtiSJEmS1GYVvRiMiM7AncCFmfkP4DpgF6ACmA/8cGXXBobnGg2Z4zKzMjMru3XrVpygJUmSJKmNK2oxGBEdqC0EJ2TmXQCZuSAzazLzfeAG/j0VtBrYsd7wHsDrxYxPkqTmto4F1rpExP0RMbfwunW9MS6wJklqcsVcTTSAG4HnM/NH9dq71+t2PDC78H4qMCwiOkZEL6A38GSx4pMkqURWLrC2B/BxYFRhEbVLgQczszfwYGF79QXWjgT+JyLalSRySVKbUszVRPcHTgeejYiZhbbLgVMiooLaKaDzgLMBMnNOREwCnqM2UY5yJVFJUluTmfOpvU2CzHwnIlYusHYsMLjQ7WZgGvA16i2wBrwcESsXWJvevJFLktqaohWDmfkYDd8H+Jt1jBkDjClWTJIktSSrLbC2XaFQJDPnR8S2hW47AH+sN6zBBdYkSVpfzbKaqCRJWlUDC6yttWsDbWsssFY4pituS5IazWJQkqRm1tACa8CClffVF17fKLQ3eoE1V9yWJK0Pi0FJkprR2hZYo3YhteGF98OBe+q1u8CaJKnJFXMBGUmStKa1LbB2JTApIs4CXgVOBBdYkyQVj8WgJEnNaB0LrAEMWcsYF1iTJDU5p4lKkiRJUhmyGJQkSZKkMmQxKEmSJEllyGJQkiRJksqQxaAkSZIklSGLQUmSJEkqQxaDkiRJklSGLAYlSZIkqQxZDEqSJElSGbIYlCRJkqQyZDEoSZIkSWXIYlCSJEmSypDFoCRJkiSVIYtBSZIkSSpDFoOSJEmSVIYsBiVJkiSpDFkMSpIkSVIZshiUJEmSpDJUtGIwInaMiIcj4vmImBMRFxTau0TE/RExt/C6db0xl0XESxHxYkQMLVZskiRJklTuinllcAXwlczcA/g4MCoi+gCXAg9mZm/gwcI2hX3DgL7AkcD/RES7IsYnSZIkSWWraMVgZs7PzKcL798Bngd2AI4Fbi50uxk4rvD+WGBiZi7LzJeBl4BBxYpPkiRJkspZs9wzGBE9gb2AJ4DtMnM+1BaMwLaFbjsAr9UbVl1oW/1YIyOiKiKqFi5cWNS4JUmSJKmtalQxGBEPNqZtLWM7A3cCF2bmP9bVtYG2XKMhc1xmVmZmZbdu3RoTgiRJRbEx+VGSpFJrv66dEdEJ+BDQtbDQy8qCbUtg+w86eER0oLYQnJCZdxWaF0RE98ycHxHdgTcK7dXAjvWG9wBeb/Q3kSSpmWxsfpQkqSVYZzEInA1cSG1im8G/k90/gGvXNTAiArgReD4zf1Rv11RgOHBl4fWeeu23RcSPCp/XG3iysV9EkqRmtMH5UZKklmKdxWBm/gT4SUScl5nXrOex9wdOB56NiJmFtsupLQInRcRZwKvAiYXPmhMRk4DnqF2JdFRm1qznZ0qSVHQbmR8lSWoRPujKIACZeU1E7Af0rD8mM29Zx5jHaPg+QIAhaxkzBhjTmJgkSSq1DcmPkiS1FI0qBiPiVmAXYCaw8mpdAiY7SVLZMj9KklqzRhWDQCXQJzPXWN1TkqQyZn6UJLVajX3O4GzgI8UMRJKkVsj8KElqtRp7ZbAr8FxEPAksW9mYmccUJSpJklqHDcqPEXETcBTwRmb2K7SNBr4ILCx0uzwzf1PYdxlwFrVTUc/PzP9r4u8hSSpDjS0GRxczCEmSWqnRGzhuPPBT1ry38KrMHFu/ISL6AMOAvtQ+yuKBiNjVFbclSRursauJ/r7YgUiS1NpsaH7MzEciomcjux8LTMzMZcDLEfESMAiYviGfLUnSSo26ZzAi3omIfxR+lkZETUT8o9jBSZLUkhUhP54bEbMi4qaI2LrQtgPwWr0+1YU2SZI2SqOKwczcIjO3LPx0Ak6gdnqLJEllq4nz43XUPqaiApgP/LDQ3tAzextcvTQiRkZEVURULVy4sKEukiTVaexqoqvIzLuBQ5s2FEmSWreNyY+ZuSAzazLzfeAGaqeCQu2VwB3rde0BvL6WY4zLzMrMrOzWrduGhCFJKiONfej8Z+ptbkLtc5V8ppIkqaw1ZX6MiO6ZOb+weTy1j60AmArcFhE/onYBmd7AkxsWsSRJ/9bY1USPrvd+BTCP2hvaJUkqZxuUHyPidmAw0DUiqoFvAYMjooLaYnIecDZAZs6JiEnAc4XPGOVKopKkptDY1UQ/X+xAJElqbTY0P2bmKQ0037iO/mOAMRvyWZIkrU1jVxPtERFTIuKNiFgQEXdGRI9iBydJUktmfpQktWaNXUDm59Tes7A9tctZ/6rQJklSOTM/SpJarcYWg90y8+eZuaLwMx5wmTJJUrkzP0qSWq3GFoNvRsRpEdGu8HMasKiYgUmS1AqYHyVJrVZji8ERwEnA/6P2QbifBVxURpJU7syPkqRWq7GPlvgOMDwz/w4QEV2AsdQmQUmSypX5UZLUajX2yuCAlYkOIDPfAvYqTkiSJLUa5kdJUqvV2CuDm0TE1qud+WzsWEmS2qqyyI97X3JLqUNoVaZsUeoIJKlxGpuwfgg8HhGTgaT2/ggffitJKnfmR0lSq9WoYjAzb4mIKuBQIIDPZOZzRY1MkqQWzvwoSWrNGj2VpZDcTHCSJNVjfpQktVZFu68hIm4CjgLeyMx+hbbRwBeBhYVul2fmbwr7LgPOAmqA8zPz/4oVm6R/816g9TPjB2eUOgRJkqQm0djVRDfEeODIBtqvysyKws/KQrAPMAzoWxjzPxHRroixSZIkSVJZK1oxmJmPAG81svuxwMTMXJaZLwMvAYOKFZskSZIklbtiXhlcm3MjYlZE3BQRWxfadgBeq9enutAmSZIkSSqC5i4GrwN2ASqA+dQuyQ21K7CtLhs6QESMjIiqiKhauHBhQ10kSZIkSR+gWYvBzFyQmTWZ+T5wA/+eCloN7Fivaw/g9bUcY1xmVmZmZbdu3YobsCRJkiS1Uc1aDEZE93qbxwOzC++nAsMiomNE9AJ6A082Z2ySJEmSVE6K+WiJ24HBQNeIqAa+BQyOiApqp4DOA84GyMw5ETGJ2uc0rQBGZWZNsWKTJEmSpHJXtGIwM09poPnGdfQfA4wpVjySJEmSpH8rxWqikiRJkqQSsxiUJEmSpDJkMShJkiRJZchiUJIkSZLKUNEWkJEkSZJUHl69on+pQ2hVdvrms6UOAfDKoCRJkiSVJYtBSZIkSSpDFoOSJEmSVIYsBiVJkiSpDFkMSpIkSVIZshiUJEmSpDJkMShJUjOLiJsi4o2ImF2vrUtE3B8RcwuvW9fbd1lEvBQRL0bE0NJELUlqaywGJUlqfuOBI1druxR4MDN7Aw8WtomIPsAwoG9hzP9ERLvmC1WS1FZZDEqS1Mwy8xHgrdWajwVuLry/GTiuXvvEzFyWmS8DLwGDmiNOSVLbZjEoSVLLsF1mzgcovG5baN8BeK1ev+pC2xoiYmREVEVE1cKFC4sarCSp9bMYlCSpZYsG2rKhjpk5LjMrM7OyW7duRQ5LktTaWQxKktQyLIiI7gCF1zcK7dXAjvX69QBeb+bYJEltkMWgJEktw1RgeOH9cOCeeu3DIqJjRPQCegNPliA+SVIb077UAUiSVG4i4nZgMNA1IqqBbwFXApMi4izgVeBEgMycExGTgOeAFcCozKwpSeCSpDbFYlCSpGaWmaesZdeQtfQfA4wpXkSSpHLkNFFJkiRJKkMWg5IkSZJUhiwGJUmSJKkMWQxKkiRJUhkqWjEYETdFxBsRMbteW5eIuD8i5hZet66377KIeCkiXoyIocWKS5IkSZJU3CuD44EjV2u7FHgwM3sDDxa2iYg+wDCgb2HM/0REuyLGJkmSJEllrWjFYGY+Ary1WvOxwM2F9zcDx9Vrn5iZyzLzZeAlYFCxYpMkSZKkctfc9wxul5nzAQqv2xbadwBeq9evutC2hogYGRFVEVG1cOHCogYrSZIkSW1VS1lAJhpoy4Y6Zua4zKzMzMpu3boVOSxJkiRJapuauxhcEBHdAQqvbxTaq4Ed6/XrAbzezLFJkiRJUtlo38yfNxUYDlxZeL2nXvttEfEjYHugN/BkM8cmSZIkAbD3JbeUOoRWZcoWpY5AG6JoxWBE3A4MBrpGRDXwLWqLwEkRcRbwKnAiQGbOiYhJwHPACmBUZtYUKzZJkiRJKndFKwYz85S17Bqylv5jgDHFikeSJEmS9G8tZQEZSZIkSVIzshiUJEmSpDJkMShJkiRJZchiUJIkSZLKkMWgJEmSJJUhi0FJkiRJKkMWg5IkSZJUhiwGJUmSJKkMWQxKkiRJUhmyGJQkSZKkMtS+1AGodXr1iv6lDqHV2embz5Y6BEmSJKmOVwYlSZIkqQxZDEqSJElSGbIYlCRJkqQyZDEoSZIkSWXIYlCSJEmSypDFoCRJkiSVIR8tIUlSCxIR84B3gBpgRWZWRkQX4A6gJzAPOCkz/16qGCVJbYNXBiVJankOycyKzKwsbF8KPJiZvYEHC9uSJG0Ui0FJklq+Y4GbC+9vBo4rXSiSpLbCYlCSpJYlgd9FxIyIGFlo2y4z5wMUXrdtaGBEjIyIqoioWrhwYTOFK0lqrbxnUJKklmX/zHw9IrYF7o+IFxo7MDPHAeMAKisrs1gBSpLaBq8MSpLUgmTm64XXN4ApwCBgQUR0Byi8vlG6CCVJbUVJisGImBcRz0bEzIioKrR1iYj7I2Ju4XXrUsQmSVKpRMTmEbHFyvfAEcBsYCowvNBtOHBPaSKUJLUlpbwy6EppkiStajvgsYj4E/Ak8OvMvA+4Ejg8IuYChxe2JUnaKC3pnsFjgcGF9zcD04CvlSoYSZKaW2b+FdizgfZFwJDmj0iS1JaV6srgBq+UJkmSJEnaeKW6MrjBK6UViseRADvttFOx4pMkSZKkNq0kVwY3ZqW0zByXmZWZWdmtW7fmClmSJEmS2pRmLwZdKU2SJEmSSq8U00S3A6ZExMrPvy0z74uIp4BJEXEW8CpwYglikyRJkqSy0OzFoCulSZIkSVLplfI5g5IkSZKkErEYlCRJkqQyZDEoSZIkSWWoVM8ZlKRW6dUr+pc6hFZlp28+W+oQJEnSWnhlUJIkSZLKkMWgJEmSJJUhi0FJkiRJKkMWg5IkSZJUhiwGJUmSJKkMWQxKkiRJUhmyGJQkSZKkMmQxKEmSJEllyGJQkiRJksqQxaAkSZIklSGLQUmSJEkqQxaDkiRJklSGLAYlSZIkqQxZDEqSJElSGbIYlCRJkqQyZDEoSZIkSWXIYlCSJEmSypDFoCRJkiSVIYtBSZIkSSpDFoOSJEmSVIZaXDEYEUdGxIsR8VJEXFrqeCRJagnMj5KkptaiisGIaAdcC3wS6AOcEhF9ShuVJEmlZX6UJBVDiyoGgUHAS5n518z8FzAROLbEMUmSVGrmR0lSk2tf6gBWswPwWr3tamDf+h0iYiQwsrC5JCJebKbYVM/O0BV4s9RxtCrfilJHoCbg3/56atq/+52b8mCtzAfmRzBHthT+O7GezI9tgn/366mF5MeWVgw29FvJVTYyxwHjmiccrU1EVGVmZanjkJqbf/sqkQ/Mj2CObCn8d0LlyL/71qmlTROtBnast90DeL1EsUiS1FKYHyVJTa6lFYNPAb0joldEbAoMA6aWOCZJkkrN/ChJanItappoZq6IiHOB/wPaATdl5pwSh6WGOQ1J5cq/fTU782Or478TKkf+3bdCkbnGLQeSJEmSpDaupU0TlSRJkiQ1A4tBSZIkSSpDFoNqtKj1WER8sl7bSRFxXynjkootIjIiflhv++KIGF3CkCS1MOZIlSPzY+tnMahGy9obTM8BfhQRnSJic2AMMKq0kUlFtwz4TER0LXUgklomc6TKlPmxlbMY1HrJzNnAr4CvAd8CbsnMv5Q2KqnoVlC7StpFpQ5EUstljlQZMj+2ci3q0RJqNb4NPA38C6gscSxSc7kWmBUR3y91IJJaNHOkyo35sRWzGNR6y8x3I+IOYElmLit1PFJzyMx/RMQtwPnAe6WOR1LLZI5UuTE/tm5OE9WGer/wI5WTHwNnAZuXOA5JLZs5UuXmx5gfWyWLQUlqpMx8C5hEbcKTJEmYH1szi0FJWj8/BFw1TZKkVZkfW6GoXQlZkiRJklROvDIoSZIkSWXIYlCSJEmSypDFoCRJkiSVIYtBSZIkSSpDFoOSJEmSVIYsBiVJkiSpDFkMShshIpY08+dtEhFXR8TsiHg2Ip6KiF6FfZc38hiN6idJ0sYwR0otn88ZlDZCRCzJzM7N+HmnACcAJ2Xm+xHRA3g3M//e2FiaO2ZJUnkyR0otn1cGpSYWERUR8ceImBURUyJi60L7FwtnKf8UEXdGxIcK7eMLZzIfj4i/RsRn13H47sD8zHwfIDOrC0nuSmCziJgZERMKx707ImZExJyIGFloW6VfRPSMiNn1Yr84IkYX3p8fEc8VvsfEIvyqJEllxhwptSxeGZQ2QkNnECNiFnBeZv4+Iq4AtszMCyNim8xcVOjzXWBBZl4TEeOBzYGTgd2BqZn5sbV8Xg/gMeBt4EHgF5n5TEOxRESXzHwrIjYDngIOzsxF9ftFRE/g3szsV9i+GOicmaMj4nWgV2Yui4itMvPtpvidSZLKgzlSavm8Mig1oYj4MLBVZv6+0HQzcFDhfb+IeDQingVOBfrWG3p3Zr6fmc8B263t+JlZDewGXAa8DzwYEUPW0v38iPgT8EdgR6D3en6dWcCEiDgNWLGeYyVJWoU5Ump5LAal5jMeODcz+wPfBjrV27es3vtY10Eyc1lm/jYzLwH+Czhu9T4RMRg4DPhEZu4JPLPa5620glX/Hajf59PAtcDewIyIaL+uuCRJ2gjjMUdKzc5iUGpCmbkY+HtEHFhoOh1YeQZ0C2B+RHSg9qzneouIgRGxfeH9JsAA4JXC7uWFYwN8GPh7Zv4zInYHPl7vMPX7LQC2jYhtIqIjcFS9Y++YmQ8DXwW2AryhXpK0wcyRUsvjWQxp43woIqrrbf8IGA5cX7j5/a/A5wv7vgE8QW1iepbaxLe+tgVuKCQlgCeBnxbejwNmRcTTwAjgnMK9GS9SOw2G1ftl5qmFezaeAF4GXij0aQf8ojClJ4CrvB9CkrSezJFSC+cCMpIkSZJUhpwmKkmSJEllyGmiUgsUEf2BW1drXpaZ+5YiHkmSWgpzpNR0nCYqSZIkSWXIaaKSJEmSVIYsBiVJkiSpDFkMSpIkSVIZshiUJEmSpDJkMShJkiRJZchiUJIkSZLKkMWgJEmSJJUhi0FJkiRJKkMWg5IkSZJUhiwGJUmSJKkMWQxKkiRJUhmyGJQkSZKkMtS+1AFsjK5du2bPnj1LHYYkqRnMmDHjzczsVuo4WgtzpCSVh43Jj626GOzZsydVVVWlDkOS1Awi4pVSx9CamCMlqTxsTH4s2jTRiOgUEU9GxJ8iYk5EfLvQPjoi/hYRMws/n6o35rKIeCkiXoyIocWKTZIkSZLKXTGvDC4DDs3MJRHRAXgsIn5b2HdVZo6t3zki+gDDgL7A9sADEbFrZtYUMUZJkiRJKktFuzKYtZYUNjsUfnIdQ44FJmbmssx8GXgJGFSs+CRJkiSpnBX1nsGIaAfMAD4GXJuZT0TEJ4FzI+IMoAr4Smb+HdgB+GO94dWFttWPORIYCbDTTjsVM3xJbdjy5cuprq5m6dKlpQ5Fq+nUqRM9evSgQ4cOpQ5FktSEzL0bpxj5sajFYGGKZ0VEbAVMiYh+wHXAd6i9Svgd4IfACCAaOkQDxxwHjAOorKxc15VGSVqr6upqtthiC3r27ElEQ//8qBQyk0WLFlFdXU2vXr1KHY4kqQmZezdcsfJjszxnMDPfBqYBR2bmgsysycz3gRv491TQamDHesN6AK83R3ySys/SpUvZZpttTEYtTESwzTbbeNZYktogc++GK1Z+LOZqot0KVwSJiM2Aw4AXIqJ7vW7HA7ML76cCwyKiY0T0AnoDTxYrPkkyGbVM/neRpLbLf+M3XDF+d8WcJtoduLlw3+AmwKTMvDcibo2ICmqngM4DzgbIzDkRMQl4DlgBjHIlUUmSJEkqjqIVg5k5C9irgfbT1zFmDDCmWDFJUqm0a9eO/v37120PGzaMSy+9dJU+06ZNY+zYsdx7771N9rnTpk1j0003Zb/99gPg+uuv50Mf+hBnnHFGk32GJElqnZrlnkFJKnebbbYZM2fOrPtZvRAslmnTpvH444/XbZ9zzjkWgpKkFmXMmDH07duXAQMGUFFRwRNPPLHWvmeeeSaTJ08G4NFHH6Vv375UVFTw3nvvrdF33rx5bLbZZlRUVNT93HLLLU0Sc+fOnZvkOGtT/3sWU1FXE21N9r6kaf4wysWMH/g/k1JTuO+++7jwwgvp2rUrAwcOrGsfPXo0nTt35uKLLwagX79+3HvvvfTs2ZNbbrmFsWPHEhEMGDCAW2+9lV/96ld897vf5V//+hfbbLMNEyZM4L333uP666+nXbt2/OIXv+Caa67hwQcfrDvuzJkzOeecc/jnP//JLrvswk033cTWW2/N4MGD2XfffXn44Yd5++23ufHGGznwwANL9StSC2COXD/mSKnxpk+fzr333svTTz9Nx44defPNN/nXv/7VqLETJkzg4osv5vOf//xa++yyyy7MnDmziaJte7wyKEnN4L333lvlzOQdd9zB0qVL+eIXv8ivfvUrHn30Uf7f//t/H3icOXPmMGbMGB566CH+9Kc/8ZOf/ASAAw44gD/+8Y8888wzDBs2jO9///v07NmTc845h4suuoiZM2euUdCdccYZfO9732PWrFn079+fb3/723X7VqxYwZNPPsmPf/zjVdolSWpK8+fPp2vXrnTs2BGArl27sv322zNjxgwOPvhg9t57b4YOHcr8+fNXGfe///u/TJo0iSuuuIJTTz11vT+3c+fOfO1rX2PvvffmsMMO48knn2Tw4MF89KMfZerUqQCMHz+eY489liOPPJLddtutwXyYmVxyySX069eP/v37c8cddwBw+umnc88999T1O/XUU5k6dSo1NTVccskl7LPPPgwYMICf/exndcc599xz6dOnD5/+9Kd544031vs7bQiLQUlqBqtPEz355JN54YUX6NWrF7179yYiOO200z7wOA899BCf/exn6dq1KwBdunQBap/dNHToUPr3788PfvAD5syZs87jLF68mLfffpuDDz4YgOHDh/PII4/U7f/MZz4DwN577828efM25CtLkvSBjjjiCF577TV23XVXvvSlL/H73/+e5cuXc9555zF58mRmzJjBiBEj+PrXv77KuC984Qscc8wx/OAHP2DChAlrPf5f/vKXVU7GPvroowC8++67DB48mBkzZrDFFlvwn//5n9x///1MmTKFb37zm3Xjn3zySSZMmMDMmTP55S9/SVVV1SrHv+uuu5g5cyZ/+tOfeOCBB7jkkkuYP38+X/jCF/j5z38O1Obcxx9/nE996lPceOONfPjDH+app57iqaee4oYbbuDll19mypQpvPjiizz77LPccMMNq9ziUUxOE5WkElrbMtHt27fn/fffr9te+VyhzGxwzHnnnceXv/xljjnmGKZNm8bo0aM3Kq6VZ2jbtWvHihUrNupYkiStTefOnZkxYwaPPvooDz/8MCeffDL/+Z//yezZszn88MMBqKmpoXv37h9wpIatbZropptuypFHHglA//796dixIx06dKB///6rnAQ9/PDD2WabbYDaE6WPPfYYlZWVdfsfe+wxTjnlFNq1a8d2223HwQcfzFNPPcUxxxzDqFGjeOONN7jrrrs44YQTaN++Pb/73e+YNWtW3f2AixcvZu7cuTzyyCN1x9l+++059NBDN+j7ri+LQUkqkd13352XX36Zv/zlL+yyyy7cfvvtdft69uxZt6ro008/zcsvvwzAkCFDOP7447nooovYZptteOutt+jSpQuLFy9mhx12AODmm2+uO84WW2zBP/7xjzU++8Mf/jBbb701jz76KAceeCC33npr3VVCSZKaU7t27Rg8eDCDBw+mf//+XHvttfTt25fp06cX7TM7dOhQd3J1k002qTsJuskmm6xyEnT1E7Crb2fmWj/j9NNPZ8KECUycOJGbbrqprv8111zD0KFDV+n7m9/8piTPYHSaqCQ1g9XvGbz00kvp1KkT48aN49Of/jQHHHAAO++8c13/E044gbfeeouKigquu+46dt11VwD69u3L17/+dQ4++GD23HNPvvzlLwO1C86ceOKJHHjggXVTSAGOPvpopkyZssrUmJVuvvlmLrnkEgYMGMDMmTNXmRYjSVJzePHFF5k7d27d9syZM9ljjz1YuHBhXTG4fPnyD7z9oVjuv/9+3nrrLd577z3uvvtu9t9//1X2H3TQQdxxxx3U1NSwcOFCHnnkEQYNGgTUrgj64x//GKjN3wBDhw7luuuuY/ny5QD8+c9/5t133+Wggw5i4sSJ1NTUMH/+fB5++OFm+X5eGZSkZlBTU9Ng+5FHHskLL7ywRvtmm23G7373uwbHDB8+nOHDh6/Sduyxx3Lssceu0XfXXXdl1qxZddv1F5GpqKjgj3/84xpjpk2bVve+a9eu3jPYxCKiE/AI0JHaPDw5M78VEaOBLwILC10vz8zfFMZcBpwF1ADnZ+b/NXvgklQES5Ys4bzzzuPtt9+mffv2fOxjH2PcuHGMHDmS888/n8WLF7NixQouvPDCuoJqfay8Z3ClESNGcP755zd6/AEHHMDpp5/OSy+9xOc+97lVpogCHH/88UyfPp0999yTiOD73/8+H/nIRwDYbrvt2GOPPTjuuOPq+n/hC19g3rx5DBw4kMykW7du3H333Rx//PE89NBD9O/fn1133bXZZuvEui5ttnSVlZW5+k2cG8pls9ePy2artXv++efZY489Sh2G1qKh/z4RMSMzK9cypNWI2nlAm2fmkojoADwGXAAcCSzJzLGr9e8D3A4MArYHHgB2zcyGzzAUmCNLxxwpNay15d7x48dTVVXFT3/60w0a/89//pP+/fvz9NNP8+EPf7hJYmrq/Og0UUmSmlHWWlLY7FD4WdeZ2WOBiZm5LDNfBl6itjCUJLVQDzzwALvvvjvnnXdekxWCxeA0UUmSmllEtANmAB8Drs3MJyLik8C5EXEGUAV8JTP/DuwA1J/PW11oa+i4I4GRADvttFMRv4EktRzPPvssp59++iptHTt25Iknntio45555pmceeaZGzT2sMMO49VXX92oz28OFoOSJDWzwhTPiojYCpgSEf2A64DvUHuV8DvAD4ERQEPLyzV4JTEzxwHjoHaaaNNHLkktT//+/Rt8fIQ+mNNEJUkqkcx8G5gGHJmZCzKzJjPfB27g31NBq4Ed6w3rAbzenHFKktomi0FJkppRRHQrXBEkIjYDDgNeiIj6T1Q+HphdeD8VGBYRHSOiF9AbeLIZQ5YktVFOE5Ukmn61xMauJrhgwQIuuugi/vjHP7L11luz6aab8tWvfpXjjz9+gz539OjRdO7cmYsvvni9x86bN4/HH3+cz33ucxv02Wq07sDNhfsGNwEmZea9EXFrRFRQOwV0HnA2QGbOiYhJwHPACmDUB60kKklSY1gMSlKJZCbHHXccw4cP57bbbgPglVdeYerUqav0W7FiBe3bF/+f63nz5nHbbbdZDBZZZs4C9mqg/fQGuq/cNwYYU8y4JKk1KcVJ3Ijgy1/+Mj/84Q8BGDt2LEuWLGH06NFNGktzcpqoJJXIQw89xKabbso555xT17bzzjtz3nnnMX78eE488USOPvpojjjiCJYsWcKQIUMYOHAg/fv355577qkbM2bMGHbbbTcOO+wwXnzxxbr2wYMHs/I5c2+++SY9e/YEaou+Aw88kIEDBzJw4EAef/xxAC699FIeffRRKioquOqqq6ipqeGSSy5hn332YcCAAfzsZz9rht+KJEktU8eOHbnrrrt48803Sx1Kk/HKoCSVyJw5cxg4cOBa90+fPp1Zs2bRpUsXVqxYwZQpU9hyyy158803+fjHP84xxxzD008/zcSJE3nmmWdYsWIFAwcOZO+9917n52677bbcf//9dOrUiblz53LKKadQVVXFlVdeydixY7n33nsBGDduHB/+8Id56qmnWLZsGfvvvz9HHHEEvXr1atLfgyRJrUH79u0ZOXIkV111FWPGrDpZ45VXXmHEiBEsXLiQbt268fOf/7xVPOLHK4OS1EKMGjWKPffck3322QeAww8/nC5dugC1U0ovv/xyBgwYwGGHHcbf/vY3FixYwKOPPsrxxx/Phz70IbbcckuOOeaYD/yc5cuX88UvfpH+/ftz4okn8txzzzXY73e/+x233HILFRUV7LvvvixatIi5c+c23ReWJKmVGTVqFBMmTGDx4sWrtJ977rmcccYZzJo1i1NPPZXzzz+/RBGuH68MSlKJ9O3blzvvvLNu+9prr+XNN9+ksrISgM0337xu34QJE1i4cCEzZsygQ4cO9OzZk6VLlwK19zA0pH379rz//vsAdX0BrrrqKrbbbjv+9Kc/8f7779OpU6cGx2cm11xzDUOHDt24LypJUhux5ZZbcsYZZ3D11Vez2Wab1bVPnz6du+66C4DTTz+dr371q6UKcb14ZVCSSuTQQw9l6dKlXHfddXVt//znPxvsu3jxYrbddls6dOjAww8/zCuvvALAQQcdxJQpU3jvvfd45513+NWvflU3pmfPnsyYMQOAyZMnr3Ks7t27s8kmm3DrrbdSU1O7MOUWW2zBO++8U9dv6NChXHfddSxfvhyAP//5z7z77rtN9O0lSWqdLrzwQm688cZ15sS1nahtabwyKEk0/lEQTSkiuPvuu7nooov4/ve/T7du3dh888353ve+x3vvvbdK31NPPZWjjz6ayspKKioq2H333QEYOHAgJ598MhUVFey8884ceOCBdWMuvvhiTjrpJG699VYOPfTQuvYvfelLnHDCCfzyl7/kkEMOqbsCOWDAANq3b8+ee+7JmWeeyQUXXMC8efMYOHAgmUm3bt24++67i/+LkSSpBevSpQsnnXQSN954IyNGjABgv/32Y+LEiZx++ulMmDCBAw44oMRRNk5kZqlj2GCVlZW5cqW8jdXUy9O2daX4H2epKT3//PPssccepQ5Da9HQf5+ImJGZlSUKqdUxR5aOOVJqWGvPvZ07d2bJkiVA7XOCe/XqxVe/+lVGjx7NvHnzGDFiBG+++WZRF5Bp6vzolUFJkiRJ+gArC0GA7bbbbpVbO3r27MlDDz1UirA2StHuGYyIThHxZET8KSLmRMS3C+1dIuL+iJhbeN263pjLIuKliHgxIlyxQJIkSZKKpJgLyCwDDs3MPYEK4MiI+DhwKfBgZvYGHixsExF9gGFAX+BI4H8iol0R45MkSZKkslW0YjBrrbyW2qHwk8CxwM2F9puB4wrvjwUmZuayzHwZeAkYVKz4JEmSJKmcFfXREhHRLiJmAm8A92fmE8B2mTkfoPC6baH7DsBr9YZXF9pWP+bIiKiKiKqFCxcWM3xJkiRJarOKWgxmZk1mVgA9gEER0W8d3Rt6GMcaS51m5rjMrMzMym7dujVRpJIkSZJUXpplNdHMfDsiplF7L+CCiOiemfMjoju1Vw2h9krgjvWG9QBeb474JOnVK/o36fF2+uazH9gnIvjyl7/MD3/4QwDGjh3LkiVLGD169FrH3H333ey666706dOnwf2/+MUv+P73v09NTQ3t27dnn332YezYsWy11VYb8jWAVZfSXl/jx4/niCOOYPvtt9/gz5ckScVRtGIwIroBywuF4GbAYcD3gKnAcODKwus9hSFTgdsi4kfA9kBv4MlixSdJpdaxY0fuuusuLrvsMrp27dqoMXfffTdHHXVUg8Xgfffdx1VXXcVvf/tbdthhB2pqarj55ptZsGDBGsVgTU0N7doVf42u8ePH069fP4tBSVKTau6TuJnJgQceyNe//nU++clPAjBp0iRuuukm7rvvviaNpTkVc5pod+DhiJgFPEXtPYP3UlsEHh4Rc4HDC9tk5hxgEvAccB8wKjNrihifJJVU+/btGTlyJFddddUa+1555RWGDBnCgAEDGDJkCK+++iqPP/44U6dO5ZJLLqGiooK//OUvq4wZM2YMY8eOZYcdam+3bteuHSNGjGC33XYDap+BdMUVV3DAAQfwy1/+khtuuIF99tmHPffckxNOOKHueUkvv/wyn/jEJ9hnn334xje+UXf8adOmcdRRR9Vtn3vuuYwfPx6AK664gn322Yd+/foxcuRIMpPJkydTVVXFqaeeSkVFBe+99x4zZszg4IMPZu+992bo0KHMnz+/SX+nkiQVQ0Rw/fXX8+Uvf5mlS5fy7rvv8vWvf51rr7221KFtlGKuJjorM/fKzAGZ2S8zryi0L8rMIZnZu/D6Vr0xYzJzl8zcLTN/W6zYJKmlGDVqFBMmTGDx4sWrtJ977rmcccYZzJo1i1NPPZXzzz+f/fbbj2OOOYYf/OAHzJw5k1122WWVMXPmzGHgwIHr/LxOnTrx2GOPMWzYMD7zmc/w1FNP8ac//Yk99tiDG2+8EYALLriA//iP/+Cpp57iIx/5SKO+x7nnnstTTz3F7Nmzee+997j33nv57Gc/S2VlJRMmTGDmzJm0b9+e8847j8mTJzNjxgxGjBjB17/+9fX4bUmSVDr9+vXj6KOP5nvf+x7f/va3Oe200xgzZgz77LMPe+21F/fcUzvhcc6cOQwaNIiKigoGDBjA3LlzSxz52hV1ARlJ0rptueWWnHHGGVx99dWrtE+fPp3Pfe5zAJx++uk89thj63XcZ599loqKCnbZZRfuuOOOuvaTTz657v3s2bM58MAD6d+/PxMmTGDOnDkA/OEPf+CUU06p++zGePjhh9l3333p378/Dz30UN2x6nvxxReZPXs2hx9+OBUVFXz3u9+lurp6vb6XJEml9K1vfYvbbruN3/72tyxdupRDDz2Up556iocffphLLrmEd999l+uvv54LLriAmTNnUlVVRY8ePUod9lo1ywIykqS1u/DCCxk4cCCf//zn19onoqEFl1fVt29fnn76aQ455BD69+/PzJkzOffcc3nvvffq+my++eZ1788880zuvvtu9txzT8aPH8+0adPW+Xnt27fn/fffr9teunRp3euXvvQlqqqq2HHHHRk9enTdvvoyk759+zJ9+vQP/C6SJLVEm2++OSeffDKdO3dm0qRJ/OpXv2Ls2LFAbT589dVX+cQnPsGYMWOorq7mM5/5DL179y5x1GvnlUFJKrEuXbpw0kkn1U3TBNhvv/2YOHEiABMmTOCAAw4AYIsttuCdd95p8DiXXXYZF1988SpX2+oXgqt755136N69O8uXL2fChAl17fvvv/8qn73SzjvvzHPPPceyZctYvHgxDz74IPDvorBr164sWbKEyZMn142pH+9uu+3GwoUL64rB5cuXN3gFUZKklmyTTTZhk002ITO58847mTlzJjNnzuTVV19ljz324HOf+xxTp05ls802Y+jQoTz00EOlDnmtvDIoSTTuURDF9JWvfIWf/vSnddtXX301I0aM4Ac/+AHdunXj5z//OQDDhg3ji1/8IldffTWTJ09e5b7BT33qUyxcuJBPfvKT1NTUsNVWW9GvXz+GDh3a4Gd+5zvfYd9992XnnXemf//+dUXbT37yEz73uc/xk5/8hBNOOKGu/4477shJJ53EgAED6N27N3vttRcAW221FV/84hfp378/PXv2ZJ999qkbc+aZZ3LOOeew2WabMX36dCZPnsz555/P4sWLWbFiBRdeeCF9+/Ztul+kJEnNZOjQoVxzzTVcc801RATPPPMMe+21F3/961/56Ec/yvnnn89f//pXZs2axaGHHlrqcBsUmWs8173VqKyszKqqqiY51t6X3NIkxykXM35wRqlDkDbK888/zx577FHqMLQWDf33iYgZmVlZopBaHXNk6ZgjpYa1ldw7evRoOnfuzKhRo7jwwgt5/PHHyUx69uzJvffey3//93/zi1/8gg4dOvCRj3yE2267jS5dujTJZzd1fvTKoCRJzSgiOgGPAB2pzcOTM/NbEdEFuAPoCcwDTsrMvxfGXAacBdQA52fm/5UgdEkStcXgSj/72c/W2H/ZZZdx2WWXNWNEG857BiVJal7LgEMzc0+gAjgyIj4OXAo8mJm9gQcL20REH2AY0Bc4EvifiGhXisAlSW2LxaCkstWap8m3ZW39v0vWWlLY7FD4SeBY4OZC+83AcYX3xwITM3NZZr4MvAQMar6IJUltlcWgpLLUqVMnFi1a1OYLj9YmM1m0aBGdOnUqdShFFRHtImIm8AZwf2Y+AWyXmfMBCq/bFrrvALxWb3h1oa2h446MiKqIqFq4cGHR4pekDWXe3XDF+N15z6CkstSjRw+qq6vxf5hbnk6dOrXoB/Q2hcysASoiYitgSkT0W0f3hh4y2eD/EWTmOGAc1C4gs7FxSlJTWnkidptttmnU83P1b8U6WWoxKKksdejQgV69epU6DJW5zHw7IqZRey/ggojonpnzI6I7tVcNofZK4I71hvUAXm/eSCVp43kiduMU42SpxaAkSc0oIroBywuF4GbAYcD3gKnAcODKwus9hSFTgdsi4kfA9kBv4MlmD1ySNpInYlsei0FJkppXd+DmwoqgmwCTMvPeiJgOTIqIs4BXgRMBMnNOREwCngNWAKMK00wlSdooFoOSJDWjzJwF7NVA+yJgyFrGjAHGFDk0SVKZcTVRSZIkSSpDFoOSJEmSVIYsBiVJkiSpDFkMSpIkSVIZshiUJEmSpDJkMShJkiRJZchiUJIkSZLKkMWgJEmSJJUhi0FJkiRJKkMWg5IkSZJUhopWDEbEjhHxcEQ8HxFzIuKCQvvoiPhbRMws/Hyq3pjLIuKliHgxIoYWKzZJkiRJKnfti3jsFcBXMvPpiNgCmBER9xf2XZWZY+t3jog+wDCgL7A98EBE7JqZNUWMUZIkSZLKUtGuDGbm/Mx8uvD+HeB5YId1DDkWmJiZyzLzZeAlYFCx4pMkSZKkctYs9wxGRE9gL+CJQtO5ETErIm6KiK0LbTsAr9UbVk0DxWNEjIyIqoioWrhwYTHDliRJkqQ2q+jFYER0Bu4ELszMfwDXAbsAFcB84IcruzYwPNdoyByXmZWZWdmtW7fiBC1JkiRJbVxRi8GI6EBtITghM+8CyMwFmVmTme8DN/DvqaDVwI71hvcAXi9mfJIkSZJUroq5mmgANwLPZ+aP6rV3r9fteGB24f1UYFhEdIyIXkBv4MlixSdJkiRJ5ayYq4nuD5wOPBsRMwttlwOnREQFtVNA5wFnA2TmnIiYBDxH7Uqko1xJVJIkSZKKo2jFYGY+RsP3Af5mHWPGAGOKFZMkSZIkqVazrCYqSZIkSWpZLAYlSZIkqQxZDEqSJElSGbIYlCSpGUXEjhHxcEQ8HxFzIuKCQvvoiPhbRMws/Hyq3pjLIuKliHgxIoaWLnpJUltSzNVEJUnSmlYAX8nMpyNiC2BGRNxf2HdVZo6t3zki+gDDgL7A9sADEbGrK25LkjaWVwYlSWpGmTk/M58uvH8HeB7YYR1DjgUmZuayzHwZeAkYVPxIJUltncWgJEklEhE9gb2AJwpN50bErIi4KSK2LrTtALxWb1g1aykeI2JkRFRFRNXChQuLFbYkqY2wGJQkqQQiojNwJ3BhZv4DuA7YBagA5gM/XNm1geHZ0DEzc1xmVmZmZbdu3Zo+aElSm2IxKElSM4uIDtQWghMy8y6AzFyQmTWZ+T5wA/+eCloN7FhveA/g9eaMV5LUNlkMSpLUjCIigBuB5zPzR/Xau9frdjwwu/B+KjAsIjpGRC+gN/Bkc8UrSWq7XE1UkqTmtT9wOvBsRMwstF0OnBIRFdROAZ0HnA2QmXMiYhLwHLUrkY5yJVFJUlOwGJQkqRll5mM0fB/gb9YxZgwwpmhBSZLKktNEJUmSJKkMWQxKkiRJUhmyGJQkSZKkMmQxKEmSJEllyGJQkiRJksqQxaAkSZIklSGLQUmSJEkqQxaDkiRJklSGLAYlSZIkqQxZDEqSJElSGbIYlCRJkqQyZDEoSZIkSWWoaMVgROwYEQ9HxPMRMSciLii0d4mI+yNibuF163pjLouIlyLixYgYWqzYJEmSJKncFfPK4ArgK5m5B/BxYFRE9AEuBR7MzN7Ag4VtCvuGAX2BI4H/iYh2RYxPkiRJkspW0YrBzJyfmU8X3r8DPA/sABwL3FzodjNwXOH9scDEzFyWmS8DLwGDihWfJEmSJJWzZrlnMCJ6AnsBTwDbZeZ8qC0YgW0L3XYAXqs3rLrQtvqxRkZEVURULVy4sKhxS5IkSVJbVfRiMCI6A3cCF2bmP9bVtYG2XKMhc1xmVmZmZbdu3ZoqTEmSJEkqK0UtBiOiA7WF4ITMvKvQvCAiuhf2dwfeKLRXAzvWG94DeL2Y8UmSJElSuWpUMRgRDzambbX9AdwIPJ+ZP6q3ayowvPB+OHBPvfZhEdExInoBvYEnGxOfJEmlsCH5UZKklqL9unZGRCfgQ0DXwiMgVk7l3BLY/gOOvT9wOvBsRMwstF0OXAlMioizgFeBEwEyc05ETAKeo3Yl0lGZWbPe30iSpCLbyPwoSVKLsM5iEDgbuJDaxDaDfye7fwDXrmtgZj5Gw/cBAgxZy5gxwJgPiEmSpFLb4PwoSVJLsc5popn5k8zsBVycmR/NzF6Fnz0z86fNFKMkSS3KxuTHiNgxIh6OiOcjYk5EXFBo7xIR90fE3MLr1vXGXBYRL0XEixExtMhfT5JUJj7oyiAAmXlNROwH9Kw/JjNvKVJckiS1eBuYH1cAX8nMpyNiC2BGRNwPnAk8mJlXRsSlwKXA1yKiDzAM6EvtlcgHImJXb6WQJG2sRhWDEXErsAswE1iZfBKwGJQkla0NyY+FZ+yufN7uOxHxPLXP1T0WGFzodjMwDfhaoX1iZi4DXo6Il4BBwPSm/TaSpHLTqGIQqAT6ZOYaz/2TJKmMbVR+jIiewF7AE8B2hUKRzJwfEdsWuu0A/LHesOpCmyRJG6WxzxmcDXykmIFIktQKbXB+jIjO1D6L98LM/Me6ujbQ1mDxGREjI6IqIqoWLly4IWFJkspIY68MdgWei4gngWUrGzPzmKJEJUlS67BB+TEiOlBbCE7IzLsKzQsionvhqmB34I1CezWwY73hPYDXGzpuZo4DxgFUVlY6m0eStE6NLQZHFzMISZJaqdHrOyAiArgReD4zf1Rv11RgOLXP4x0O3FOv/baI+BG1C8j0Bp7ciJglSQIav5ro74sdiCRJrc0G5sf9gdOBZyNiZqHtcmqLwEkRcRbwKnBi4TPmRMQk4DlqVyId5UqikqSm0NjVRN/h3/cnbAp0AN7NzC2LFZgkSS3dhuTHzHyMhu8DBBiyljFjgDEbEaokSWto7JXBLepvR8Rx1C5rLUlS2TI/SpJas8auJrqKzLwbOLRpQ5EkqXUzP0qSWpPGThP9TL3NTah9rpKrlEmSypr5UZLUmjV2NdGj671fAcwDjm3yaCRJal3Mj5KkVqux9wx+vtiBSJLU2pgfJUmtWaPuGYyIHhExJSLeiIgFEXFnRPQodnCSJLVk5kdJUmvW2AVkfk7tQ2+3B3YAflVokySpnJkfJUmtVmOLwW6Z+fPMXFH4GQ90K2JckiS1BuZHSVKr1dhi8M2IOC0i2hV+TgMWFTMwSZJaAfOjJKnVamwxOAI4Cfh/wHzgs4A3zUuSyp35UZLUajX20RLfAYZn5t8BIqILMJbaJChJUrkyP0qSWq3GXhkcsDLRAWTmW8BexQlJkqRWw/woSWq1GlsMbhIRW6/cKJz5bOxVRUmS2irzoySp1Wpswvoh8HhETAaS2vsjxhQtKkmSWgfzoySp1WpUMZiZt0REFXAoEMBnMvO5okYmSVILZ36UJLVmjZ7KUkhujU5wEXETcBTwRmb2K7SNBr4ILCx0uzwzf1PYdxlwFlADnJ+Z/9fYz5IkqVTWNz9KktRSFPO+hvHAT4FbVmu/KjPH1m+IiD7AMKAvsD3wQETsmpk1RYxPkiRJatDel6z+v7Balxk/OKPUIWgDNHYBmfWWmY8AbzWy+7HAxMxclpkvAy8Bg4oVmyRJkiSVu6IVg+twbkTMioib6q3AtgPwWr0+1YW2NUTEyIioioiqhQsXNtRFkiRJkvQBmrsYvA7YBagA5lO7ChvU3nS/umzoAJk5LjMrM7OyW7duRQlSkiRJktq6Zi0GM3NBZtZk5vvADfx7Kmg1sGO9rj2A15szNkmSJEkqJ81aDEZE93qbxwOzC++nAsMiomNE9AJ6A082Z2ySJEmSVE6KVgxGxO3AdGC3iKiOiLOA70fEsxExCzgEuAggM+cAk6hdmvs+YJQriUqS2qrCffNvRMTsem2jI+JvETGz8POpevsui4iXIuLFiBhamqglSW1N0R4tkZmnNNB84zr6jwHGFCseSZJakPH4+CVJUomVYjVRSZLKmo9fkiS1BMV86LykVsCH6q4fH6qrIjs3Is4AqoCvZObfqX3U0h/r9Vnn45eAkQA77bRTkUOVJLV2XhmUJKll8PFLkqRmZTEoSVIL4OOXJEnNzWJQkqQWwMcvSZKam/cMSpLUzAqPXxoMdI2IauBbwOCIqKB2Cug84GyoffxSRKx8/NIKfPySJKmJWAxKktTMfPySJKklcJqoJEmSJJUhi0FJkiRJKkMWg5IkSZJUhiwGJUmSJKkMWQxKkiRJUhmyGJQkSZKkMmQxKEmSJEllyGJQkiRJksqQxaAkSZIklSGLQUmSJEkqQxaDkiRJklSGLAYlSZIkqQxZDEqSJElSGbIYlCRJkqQyZDEoSZIkSWXIYlCSJEmSypDFoCRJkiSVoaIVgxFxU0S8ERGz67V1iYj7I2Ju4XXrevsui4iXIuLFiBharLgkSZIkScW9MjgeOHK1tkuBBzOzN/BgYZuI6AMMA/oWxvxPRLQrYmySJEmSVNaKVgxm5iPAW6s1HwvcXHh/M3BcvfaJmbksM18GXgIGFSs2SZIkSSp3zX3P4HaZOR+g8LptoX0H4LV6/aoLbWuIiJERURURVQsXLixqsJIkSZLUVrWUBWSigbZsqGNmjsvMysys7NatW5HDkiRJkqS2qbmLwQUR0R2g8PpGob0a2LFevx7A680cmyRJzcJF1iRJLUFzF4NTgeGF98OBe+q1D4uIjhHRC+gNPNnMsUmS1FzG4yJrkqQSK+ajJW4HpgO7RUR1RJwFXAkcHhFzgcML22TmHGAS8BxwHzAqM2uKFZskSaXkImuSpJagfbEOnJmnrGXXkLX0HwOMKVY8kiS1cKssshYR9RdZ+2O9futcZA0YCbDTTjsVMVRJUlvQUhaQkSRJDXORNUlSUVgMSpLUMrjImiSpWVkMSpLUMrjImiSpWRXtnkFJktSwwiJrg4GuEVENfIvaRdUmFRZcexU4EWoXWYuIlYusrcBF1iRJTcRiUJKkZuYia5KklsBpopIkSZJUhrwyqA3y6hX9Sx1Cq7PTN58tdQiSJElSHa8MSpIkSVIZshiUJEmSpDJkMShJkiRJZchiUJIkSZLKkMWgJEmSJJUhi0FJkiRJKkMWg5IkSZJUhiwGJUmSJKkMWQxKkiRJUhmyGJQkSZKkMmQxKEmSJEllyGJQkiRJksqQxaAkSZIklSGLQUmSJEkqQxaDkiRJklSGLAYlSZIkqQxZDEqSJElSGWpfig+NiHnAO0ANsCIzKyOiC3AH0BOYB5yUmX8vRXySJEmS1NaV8srgIZlZkZmVhe1LgQczszfwYGFbkiRJklQEJbkyuBbHAoML728GpgFfK1UwktSQV6/oX+oQWpWdvvlsqUOQmp3/Tqwf/52QSqdUVwYT+F1EzIiIkYW27TJzPkDhddsSxSZJUslExLyIeDYiZkZEVaGtS0TcHxFzC69blzpOSVLrV6picP/MHAh8EhgVEQc1dmBEjIyIqoioWrhwYfEilCSpdLyVQpJUdCUpBjPz9cLrG8AUYBCwICK6AxRe31jL2HGZWZmZld26dWuukCVJKqVjqb2FgsLrcaULRZLUVjR7MRgRm0fEFivfA0cAs4GpwPBCt+HAPc0dmyRJLcAG30rh7BlJ0vooxQIy2wFTImLl59+WmfdFxFPApIg4C3gVOLEEsUmSVGr7Z+brEbEtcH9EvNDYgZk5DhgHUFlZmcUKUJLUNjR7MZiZfwX2bKB9ETCkueORJKklqX8rRUSscitFZs5f160UkiStj1I+Z1CSJNXjrRSSpObUkp4zKElSufNWCklSs7EYlCSphfBWCklSc3KaqCRJkiSVIYtBSZIkSSpDFoOSJEmSVIYsBiVJkiSpDFkMSpIkSVIZshiUJEmSpDJkMShJkiRJZchiUJIkSZLKkMWgJEmSJJWh9qUOQJIkSVLr9uoV/UsdQquy0zefLXUIgFcGJUmSJKksWQxKkiRJUhmyGJQkSZKkMmQxKEmSJEllyGJQkiRJksqQxaAkSZIklSGLQUmSJEkqQxaDkiRJklSGLAYlSZIkqQxZDEqSJElSGbIYlCRJkqQy1OKKwYg4MiJejIiXIuLSUscjSVJLYH6UJDW1FlUMRkQ74Frgk0Af4JSI6FPaqCRJKi3zoySpGFpUMQgMAl7KzL9m5r+AicCxJY5JkqRSMz9KkppcSysGdwBeq7ddXWiTJKmcmR8lSU2ufakDWE000JardIgYCYwsbC6JiBeLHpXWsDN0Bd4sdRytyrca+vNWa+Pf/npq2r/7nZvyYK3MB+ZHMEe2FP47sZ7Mj22Cf/frqYXkx5ZWDFYDO9bb7gG8Xr9DZo4DxjVnUFpTRFRlZmWp45Cam3/7KpEPzI9gjmwp/HdC5ci/+9appU0TfQroHRG9ImJTYBgwtcQxSZJUauZHSVKTa1FXBjNzRUScC/wf0A64KTPnlDgsSZJKyvwoSSqGFlUMAmTmb4DflDoOfSCnIalc+bevkjA/tir+O6Fy5N99KxSZa9x/LkmSJElq41raPYOSJEmSpGZgMahGi1qPRcQn67WdFBH3lTIuqdgiIiPih/W2L46I0SUMSVILY45UOTI/tn4Wg2q0rJ1TfA7wo4joFBGbA2OAUaWNTCq6ZcBnIqJrqQOR1DKZI1WmzI+tnMWg1ktmzgZ+BXwN+BZwS2b+pbRRSUW3gtob4y8qdSCSWi5zpMqQ+bGVa3GriapV+DbwNPAvwIeLqlxcC8yKiO+XOhBJLZo5UuXG/NiKWQxqvWXmuxFxB7AkM5eVOh6pOWTmPyLiFuB84L1SxyOpZTJHqtyYH1s3p4lqQ71f+JHKyY+Bs4DNSxyHpJbNHKly82PMj62SxaAkNVJmvgVMojbhSZIkzI+tmcWgJK2fHwKumiZJ0qrMj61Q1K6ELEmSJEkqJ14ZlCRJkqQyZDEoSZIkSWXIYlCSJEmSypDFoCRJkiSVIYtBSZIkSSpDFoOSJEmSVIYsBqWNEBFLmvnzNomIqyNidkQ8GxFPRUSvwr7LG3mMRvWTJGljmCOlls/nDEobISKWZGbnZvy8U4ATgJMy8/2I6AG8m5l/b2wszR2zJKk8mSOlls8rg1ITi4iKiPhjRMyKiCkRsXWh/YuFs5R/iog7I+JDhfbxhTOZj0fEXyPis+s4fHdgfma+D5CZ1YUkdyWwWUTMjIgJhePeHREzImJORIwstK3SLyJ6RsTserFfHBGjC+/Pj4jnCt9jYhF+VZKkMmOOlFoWrwxKG6GhM4gRMQs4LzN/HxFXAFtm5oURsU1mLir0+S6wIDOviYjxwObAycDuwNTM/NhaPq8H8BjwNvAg8IvMfKahWCKiS2a+FRGbAU8BB2fmovr9IqIncG9m9itsXwx0zszREfE60Cszl0XEVpn5dlP8ziRJ5cEcKbV8XhmUmlBEfBjYKjN/X2i6GTio8L5fRDwaEc8CpwJ96w29OzPfz8zngO3WdvzMrAZ2Ay4D3gcejIgha+l+fkT8CfgjsCPQez2/zixgQkScBqxYz7GSJK3CHCm1PBaDUvMZD5ybmf2BbwOd6u1bVu99rOsgmbksM3+bmZcA/wUct3qfiBgMHAZ8IjP3BJ5Z7fNWWsGq/w7U7/Np4Fpgb2BGRLRfV1ySJG2E8ZgjpWZnMSg1ocxcDPw9Ig4sNJ0OrDwDugUwPyI6UHvWc71FxMCI2L7wfhNgAPBKYffywrEBPgz8PTP/GRG7Ax+vd5j6/RYA20bENhHRETiq3rF3zMyHga8CWwHeUC9J2mDmSKnl8SyGtHE+FBHV9bZ/BAwHri/c/P5X4POFfd8AnqA2MT1LbeJbX9sCNxSSEsCTwE8L78cBsyLiaWAEcE7h3owXqZ0Gw+r9MvPUwj0bTwAvAy8U+rQDflGY0hPAVd4PIUlaT+ZIqYVzARlJkiRJKkNOE5UkSZKkMuQ0UakFioj+wK2rNS/LzH1LEY8kSS2FOVJqOk4TlSRJkqQy5DRRSZIkSSpDFoOSJEmSVIYsBiVJkiSpDFkMSpIkSVIZshiUJEmSpDJkMShJkiRJZchiUJIkSZLKkMWgJEmSJJUhi0FJkiRJKkMWg5IkSZJUhiwGJUmSJKkMWQxKkiRJUhmyGJQkSZKkMtS+1AFsjK5du2bPnj1LHYYkqRnMmDHjzczsVuo4WgtzpCSVh43Jj626GOzZsydVVVWlDkOS1Awi4pVSx9CamCMlqTxsTH50mqgkSZIklSGLQUmSJEkqQxaDkiRJklSGWvU9g5LUki1fvpzq6mqWLl1a6lBalU6dOtGjRw86dOhQ6lAkSY1kziu+YuRHi0FJKpLq6mq22GILevbsSUSUOpxWITNZtGgR1dXV9OrVq9ThSJIayZxXXMXKj04TlaQiWbp0Kdtss41JcT1EBNtss41nliWplTHnFVex8qPFoCQVkUlx/fk7k6TWyX+/i6sYv1+LQUmSJEkqQxaDktTM/t//+38MGzaMXXbZhT59+vCpT32KP//5zxt0rDPPPJPJkycD8IUvfIHnnnsOgP/6r//6wLGdO3deZXv8+PGce+65AFx//fXccsstax07bdo0Hn/88Q2KWZJU3tq1a0dFRQX9+vXjxBNP5J///Gezfv6Pf/zjjfrMKVOmEBG88MILTRhVabiAjDbIq1f0L3UIrc5O33y21CGoBchMjj/+eIYPH87EiRMBmDlzJgsWLGDXXXcFoKamhnbt2q33sf/3f/+37v1//dd/cfnll29wnOecc84690+bNo3OnTuz3377NfqYK1asoH17047UFPa/Zv9Sh9Bk/nDeH0odgprZZpttxsyZMwE49dRTuf766/nyl79ct39D82Bj1NTU8OMf/5jTTjuND33oQxt0jNtvv50DDjiAiRMnMnr06AY/o1jxNzWvDEpSM3r44Yfp0KHDKsVWRUUFNTU1HHLIIXzuc5+jf//+1NTUcMkll7DPPvswYMAAfvaznwG1xeS5555Lnz59+PSnP80bb7xRd5zBgwdTVVXFpZdeynvvvUdFRQWnnnrqBsU5evRoxo4dC8DVV19Nnz59GDBgAMOGDWPevHlcf/31XHXVVVRUVPDoo4/yyiuvMGTIEAYMGMCQIUN49dVXgdorl1/+8pc55JBDuOSSS+jduzcLFy4E4P333+djH/sYb7755gbFKElq/Q488EBeeuklpk2btkoeXLp0KZ///Ofp378/e+21Fw8//DBQO4vl2GOP5cgjj2S33Xbj29/+dt2xfvGLXzBo0CAqKio4++yzqampAWpnwnzzm99k3333ZcyYMbz++usccsghHHLIIdx4441cdNFFdce44YYbVilMV7dkyRL+8Ic/cOONN9ad1AXWiH9teXzJkiUMGTKEgQMH0r9/f+65554m/X2uL0/RSlIzmj17NnvvvXeD+5588klmz55Nr169GDduHB/+8Id56qmnWLZsGfvvvz9HHHEEzzzzDC+++CLPPvssCxYsoE+fPowYMWKV41x55ZX89Kc/rTvrujYrC8aV3nrrLY455pg1+l155ZW8/PLLdOzYkbfffputttqKc845h86dO3PxxRcDcPTRR3PGGWcwfPhwbrrpJs4//3zuvvtuAP785z/zwAMP0K5dO7baaismTJjAhRdeyAMPPMCee+5J165dG/8LbCMi4ibgKOCNzOxXaLsD2K3QZSvg7cysiIiewPPAi4V9f8zMdV+6laRWYMWKFfz2t7/lyCOPBFbNgz/84Q8BePbZZ3nhhRc44ogj6m6pWNnvQx/6EPvssw+f/vSn2Xzzzbnjjjv4wx/+QIcOHfjSl77EhAkTOOOMM3j33Xfp168fV1xxBQA33XQTDz/8MF27duXdd99lwIABfP/736dDhw78/Oc/ryvcGnL33Xdz5JFHsuuuu9KlSxeefvppBg4cuEb8a8vjO+64I1OmTGHLLbfkzTff5OMf/zjHHHNMyRbfsRiUpBZi0KBBdc8O+t3vfsesWbPq7gdcvHgxc+fO5ZFHHuGUU06hXbt2bL/99hx66KEb/Hn1p+lA7dnWqqqqNfoNGDCAU089leOOO47jjjuuwWNNnz6du+66C4DTTz+dr371q3X7TjzxxLrpMiNGjODYY4/lwgsv5KabbuLzn//8Bsffyo0HfgrU3ZiZmSevfB8RPwQW1+v/l8ysaK7gJKmY6p+MPPDAAznrrLN4/PHHV8mDjz32GOeddx4Au+++OzvvvHNdMXj44YezzTbbAPCZz3yGxx57jPbt2zNjxgz22Wefus/Ydtttgdp7FE844YQGY9l888059NBDuffee9ljjz1Yvnw5/fuv/Xao22+/nQsvvBCAYcOGcfvtt9cVg43J4z169ODyyy/nkUceYZNNNuFvf/sbCxYs4CMf+cgG/S43lsWgJDWjvn371iWG1W2++eZ17zOTa665hqFDh67S5ze/+U2znz389a9/zSOPPMLUqVP5zne+w5w5cz5wTP0Y63+vHXfcke22246HHnqIJ554ggkTJhQl5pYuMx8pXPFbQ9T+8k4CNrzSl6QWbPWTkSutngfXZvU8GBFkJsOHD+e///u/1+jfqVOndd7D94UvfIH/+q//Yvfdd1/nScpFixbx0EMPMXv2bCKCmpoaIoLvf//7DcbfUB4fP348CxcuZMaMGXTo0IGePXuW9Nm6Rb9nMCLaRcQzEXFvYbtLRNwfEXMLr1vX63tZRLwUES9GxNC1H1WSWqdDDz2UZcuWccMNN9S1PfXUU/z+979fpd/QoUO57rrrWL58OVA71fLdd9/loIMOYuLEidTU1DB//vy6eyhW16FDh7qxG+P999/ntdde45BDDuH73/8+b7/9NkuWLGGLLbbgnXfeqeu333771d07MWHCBA444IC1HvMLX/gCp512GieddFKrucG+mR0ILMjMufXaehVy6e8j4sC1DYyIkRFRFRFVK+/NlKTW6KCDDqo7YfjnP/+ZV199ld12q51Jf//99/PWW2/x3nvvcffdd7P//vszZMgQJk+eXHcv/VtvvcUrr7zS4LFXz2H77rsvr732GrfddhunnHLKWmOaPHkyZ5xxBq+88grz5s3jtddeo1evXjz22GNr9F1bHl+8eDHbbrstHTp04OGHH15rjM2lORaQuYDaex1WuhR4MDN7Aw8WtomIPsAwoC9wJPA/EeH/JUhqUyKCKVOmcP/997PLLrvQt29fRo8ezfbbb79Kvy984Qv06dOHgQMH0q9fP84++2xWrFjB8ccfT+/evenfvz//8R//wcEHH9zg54wcObJueufGqKmp4bTTTqu7gf+iiy5iq6224uijj2bKlCl1C8hcffXV/PznP2fAgAHceuut/OQnP1nrMY855hiWLFlSzlNEP8gpwO31tucDO2XmXsCXgdsiYsuGBmbmuMyszMzKbt26NUOoklQcX/rSl6ipqaF///6cfPLJjB8/no4dOwJwwAEHcPrpp1NRUcEJJ5xAZWUlffr04bvf/S5HHHEEAwYM4PDDD2f+/PkNHnvkyJF88pOf5JBDDqlrO+mkk9h///3ZeuutGxwDtVNEjz/++FXaTjjhBG677bY1+q4tj5966qlUVVVRWVnJhAkT2H333Tfk19NkYl2XYDf64BE9gJuBMcCXM/OoiHgRGJyZ8yOiOzAtM3eLiMsAMvO/C2P/DxidmdPXdvzKysps6P4WFZ+Pllh/Plqi/Dz//PPssccepQ6jxamqquKiiy7i0UcfXWufhn53ETEjMyuLHV9zKUwTvXflAjKFtvbA34C9M7N6LeOmARdn5joToDmybfPREmppmivnrby//ac//WmTHveoo47ioosuYsiQIU163KbW1Pmx2FcGfwx8FXi/Xtt2mTkfoPC6baF9B+C1ev2qC22rcAqMJLVeV155JSeccEKD93QIgMOAF+oXghHRbeVMmYj4KNAb+GuJ4pOkNuXtt99m1113ZbPNNmvxhWAxFG0BmYhYuWT2jIgY3JghDbStcdkyM8cB46D2rOfGxChJbd2iRYsaTG4PPvhg3UpszenSSy/l0ksvbfbPbWki4nZgMNA1IqqBb2XmjdTeLnH7at0PAq6IiBVADXBOZr7VnPFKUktx5plncuaZZzbZ8bbaaqu6VUpXamm5s5iKuZro/sAxEfEpoBOwZUT8AlgQEd3rTRNd+cTkamDHeuN7AK8XMT5JavO22WabD3zeoJpfZja4QkFmntlA253AncWOSZJUq5xyZ9GmiWbmZZnZIzN7Unum86HMPA2YCgwvdBsO3FN4PxUYFhEdI6IXtdNgnixWfJIkSZJUzkrxnMErgUkRcRbwKnAiQGbOiYhJwHPACmBUZtaUID5JkiRJavOapRjMzGnAtML7RUCDd2dm5hhqVx6VJEmSJBVRczxnUJLUBtx3333stttufOxjH+PKK68sdTiSJK1i3rx59OvXb5W20aNHM3bs2DX6nnnmmUyePLm5QmuxSjFNVJK0Efa+5JYmPd6MH5zxgX1qamoYNWoU999/Pz169GCfffbhmGOOoU+fPk0aiySpbShFrmqsFStWNNmxWjuvDEqSPtCTTz7Jxz72MT760Y+y6aabMmzYMO65554PHihJUgswePBgLr/8cg4++GB+8pOfAPDAAw9w4IEHsuuuu3LvvfcCtVcXDzzwQAYOHMjAgQN5/PHHAZg2bRqDBw/ms5/9LLvvvjunnnoqma3/KXdeGZQkfaC//e1v7Ljjv5/+06NHD5544okSRiRJ0vp5++23+f3vfw/UThOdN28ev//97/nLX/7CIYccwksvvcS2227L/fffT6dOnZg7dy6nnHIKVVVVADzzzDPMmTOH7bffnv33358//OEPHHDAAaX8ShvNK4OSpA/U0NnPiChBJJIkNWxteWll+8knn7xK+0knncQmm2xC7969+ehHP8oLL7zA8uXL+eIXv0j//v058cQTee655+r6Dxo0iB49erDJJptQUVHBvHnzivZdmotXBiVJH6hHjx689tprddvV1dVsv/32JYxIkqRVbbPNNvz9739fpe2tt96iV69eAGy++ear7Fu9eIwIrrrqKrbbbjv+9Kc/8f7779OpU6e6/R07dqx7365duzZx76FXBiVJH2ifffZh7ty5vPzyy/zrX/9i4sSJHHPMMaUOS5KkOp07d6Z79+48+OCDQG0heN999611Kucvf/lL3n//ff7yl7/w17/+ld12243FixfTvXt3NtlkE2699VZqatr2Y8+9MihJ+kDt27fnpz/9KUOHDqWmpoYRI0bQt2/fUoclSdIqbrnlFkaNGsVXvvIVAL71rW+xyy67NNh3t9124+CDD2bBggVcf/31dOrUiS996UuccMIJ/PKXv+SQQw5Z42piWxOteRWcysrKXHlDp5rXq1f0L3UIrc5O33y21CGomT3//PPssccepQ6jVWrodxcRMzKzskQhtTrmyLZt/2v2L3UITeYP5/2h1CGoCZjzmkdT50eniUqSJElSGbIYlCRJkqQyZDEoSZIkSWXIYlCSJEmSypDFoCRJkiSVIYtBSZIkSSpDFoOSpA80YsQItt12W/r161fqUCRJalC7du2oqKigX79+HH300bz99ttNduzOnTs32bFaEh86L0mtTFM/57Mxz8A888wzOffccznjjDOa9LMlSW1TKXLVZpttxsyZMwEYPnw41157LV//+tcbdfwVK1bQvn35lUZeGZQkfaCDDjqILl26lDoMSZIa5ROf+AR/+9vfABg8eDBVVVUAvPnmm/Ts2ROA8ePHc+KJJ3L00UdzxBFHsGTJEoYMGcLAgQPp378/99xzT6nCbzZFK38johPwCNCx8DmTM/NbETEa+CKwsND18sz8TWHMZcBZQA1wfmb+X7HikyRJktT21NTU8OCDD3LWWWd9YN/p06cza9YsunTpwooVK5gyZQpbbrklb775Jh//+Mc55phjiIhmiLo0inllcBlwaGbuCVQAR0bExwv7rsrMisLPykKwDzAM6AscCfxPRLQrYnySJJVERNwUEW9ExOx6baMj4m8RMbPw86l6+y6LiJci4sWIGFqaqCWpZXvvvfeoqKhgm2224a233uLwww//wDGHH3543cyXzOTyyy9nwIABHHbYYfztb39jwYIFxQ67pIpWDGatJYXNDoWfXMeQY4GJmbksM18GXgIGFSs+SZJKaDy1Jz5X58lSSdpAK+8ZfOWVV/jXv/7FtddeC0D79u15//33AVi6dOkqYzbffPO69xMmTGDhwoXMmDGDmTNnst12263Rv60p6j2DEdEuImYCbwD3Z+YThV3nRsSswpnRrQttOwCv1RteXWhb/ZgjI6IqIqoWLly4+m5Jklq8zHwEeKuR3T1ZKknr4cMf/jBXX301Y8eOZfny5fTs2ZMZM2YAMHny5LWOW7x4Mdtuuy0dOnTg4Ycf5pVXXmmukEumqMVgZtZkZgXQAxgUEf2A64BdqJ06Oh/4YaF7Q5Nx17iSmJnjMrMyMyu7detWlLglSas65ZRT+MQnPsGLL75Ijx49uPHGG0sdUlu1wSdLJUn/ttdee7HnnnsyceJELr74Yq677jr2228/3nzzzbWOOfXUU6mqqqKyspIJEyaw++67N2PEpdEs66dm5tsRMQ04MjPHrmyPiBuAewub1cCO9Yb1AF5vjvgkqTVpzPLaTe32229v9s8sQ9cB36H2ROh3qD1ZOoJGniyF2tkzwEiAnXbaqThRSlIjlCJXLVmyZJXtX/3qV3XvZ82aVff+u9/9LlD72KQzzzyzrr1r165Mnz69UcduK4p2ZTAiukXEVoX3mwGHAS9ERPd63Y4HVt48PxUYFhEdI6IX0Bt4sljxSZLUkmTmgsKMmveBG/j3VNBGnyx19owkaX0U88pgd+Dmwk3umwCTMvPeiLg1IiqoPas5DzgbIDPnRMQk4DlgBTAqM2uKGJ8kSS1GRHTPzPmFzdVPlt4WET8CtseTpZKkJlK0YjAzZwF7NdB++jrGjAHGFCsmSZJagoi4HRgMdI2IauBbwGBPlkqSmlOz3DMoSeUqM9v0w2qLIXNdTyFqGzLzlAaa17oqjydLJUnFUNTVRCWpnHXq1IlFixaVRXHTVDKTRYsW0alTp1KHIklSm+eVQUkqkh49elBdXY3PRF0/nTp1okePHqUOQ5KkNs9iUJKKpEOHDvTq1avUYUiSVDbGjBnDbbfdRrt27dhkk0342c9+xr777rtRx9xvv/14/PHH12vM4MGDGTt2LJWVlRv12cVmMShJkiSpSe1/zf5Nerw/nPeHD+wzffp07r33Xp5++mk6duzIm2++yb/+9a+N/uz1LQRralrPGl/eMyhJkiSp1Zs/fz5du3alY8eOQO1D5LfffntmzJjBwQcfzN57783QoUOZP7/2KT6DBw/moosu4qCDDmKPPf5/e/ceZkdZ5nv/e5MAUYMcE3YkwUSMQiIQoQUEBoNs5DBugqiYjKMZYYzsAdQ5qOjMCKLsYavgEeQNAwbUIaCARAdRZAQEB0MCMSeMREDSkE1COKOGHO73j1WBReiE1Z1eq1av+n6uq6+ueuqpWr+UTT/eXVVP7cWdd97JCSecwNixY/mXf/mX5487dOhQAG6++Wbe+c53Pt9+2mmnMWPGDABGjx7N2WefzaGHHsr3v/99AL773e9y8MEH86Y3vYnZs2tvBJo9ezYHH3wwb37zmzn44INZsmQJADNmzOCEE07g6KOPZuzYsXzyk59s7skqWAxKkiRJGvDe8Y53sGzZMt7whjfwd3/3d9xyyy2sWbOG008/nR/84AfMnTuXk046iX/+539+fp9tttmGW2+9lVNOOYVJkyZxwQUXsHDhQmbMmMGqVat69flDhgzhtttuY/LkyQA8++yz/OpXv+LCCy/kpJNOAmDPPffk1ltv5e677+bss8/mM5/5zPP7z5s3jyuvvJIFCxZw5ZVXsmzZsn44K5vnbaKSJEmSBryhQ4cyd+5cfvnLX/KLX/yC973vffzLv/wLCxcu5MgjjwRqt3COGDHi+X2OO+44APbee2/Gjx///LbXve51LFu2jJ133rnhz3/f+973ovUpU2pvETrssMN46qmneOKJJ3j66aeZOnUq9957LxHBmjVrnu9/xBFHsP322wMwbtw4/vCHPzBq1Kg+nInGWQxKkiRJ6giDBg1i4sSJTJw4kb333psLLriA8ePH89///d899t9wS+lWW231/PKG9bVr176o7+DBg1m/fv3z63/+859ftP1Vr3rVi9Y3fs9wRPCv//qvHH744Vx77bU88MADTJw48SVZNvw7Nv78ZvA2UUmSJEkD3pIlS7j33nufX583bx577bUXK1eufL4YXLNmDYsWLerT8V/72teyePFiVq9ezZNPPslNN9202f5XXnklALfddhvbb78922+/PU8++SS77bYbwPPPG5bJK4OSJEmSBrxnnnmG008/nSeeeILBgwfz+te/nunTpzNt2jQ++tGP8uSTT7J27Vo+/vGPM378+F4ff9SoUZx44onss88+jB07lje/+c2b7b/jjjty8MEH89RTT3HppZcC8MlPfpKpU6dy/vnn8/a3v71P/87+FJlZdoY+6+rqyjlz5pQdo5IePHvvsiMMOLt/dkHZEaQBLSLmZmZ7v7CpjThGdrb+nra/TI28MkDt75577mGvvfYqO0bH6+k8b8n46G2ikiRJklRBFoOSJEmSVEEWg5IkSZJUQRaDkiRJkrbYQJ6LZCBoxvm1GJQkSZK0RYYMGcKqVassCJskM1m1ahVDhgzp1+P6aglJkrRZ+3/i8rIj9Ju5X/pg2RGkjjRy5Ei6u7tZuXJl2VE61pAhQxg5cmS/HrNpxWBEDAFuBbYtPucHmXlmROwEXAmMBh4ATszMx4t9Pg2cDKwDPpqZP21WPkmSJEn9Y+utt2bMmDFlx1AvNfM20dXA2zNzX2ACcHREHAScAdyUmWOBm4p1ImIcMBkYDxwNXBgRg5qYT5IkSZIqq2nFYNY8U6xuXXwlMAm4rGi/DDi+WJ4EzMzM1Zl5P7AUOKBZ+SRJkiSpypo6gUxEDIqIecAK4MbM/DWwa2YuByi+Dy+67wYsq9u9u2iTJEmSJPWzphaDmbkuMycAI4EDIuJNm+kePR3iJZ0ipkXEnIiY4wOqkiRJktQ3LXm1RGY+AdxM7VnARyJiBEDxfUXRrRsYVbfbSODhHo41PTO7MrNr2LBhzYwtSZIkSR2racVgRAyLiB2K5VcA/xP4LTALmFp0mwpcVyzPAiZHxLYRMQYYC8xuVj5JksoSEZdGxIqIWFjX9qWI+G1EzI+Ia+vG0NER8aeImFd8XVRacElSR2nmlcERwC8iYj5wJ7VnBn8MnAscGRH3AkcW62TmIuAqYDFwA3BqZq5rYj5Jksoyg9rdMvVuBN6UmfsAvwM+Xbft95k5ofg6pUUZJUkdrmnvGczM+cCbe2hfBRyxiX3OAc5pViZJktpBZt4aEaM3avtZ3eodwHtaGkqSVDkteWZQkiT1yknAT+rWx0TE3RFxS0T8xaZ2cpI1SVJvWAxKktRGIuKfgbXA94qm5cDumflm4B+A/4iIV/e0r5OsSZJ6w2JQkqQ2ERFTgXcC78/MBMjM1cUjFmTmXOD3wBvKSylJ6hQWg5IktYGIOBr4FHBcZv6xrn1YRAwqll9Hbbbt+8pJKUnqJE2bQEaSJPUsIq4AJgK7REQ3cCa12UO3BW6MCIA7iplDDwPOjoi1wDrglMx8rJTgkqSOYjEoSVKLZeaUHpov2UTfq4Grm5tIklRF3iYqSZIkSRVkMShJkiRJFWQxKEmSJEkVZDEoSZIkSRVkMShJkiRJFWQxKEmSJEkVZDEoSZIkSRVkMShJkiRJFWQxKEmSJEkVZDEoSZIkSRVkMShJkiRJFWQxKEmSJEkV1LRiMCJGRcQvIuKeiFgUER8r2s+KiIciYl7xdWzdPp+OiKURsSQijmpWNkmSJEmqusFNPPZa4B8z866I2A6YGxE3Ftu+kplfru8cEeOAycB44DXAzyPiDZm5rokZJUlShTx49t5lR+gfO7667ASSOkDTrgxm5vLMvKtYfhq4B9htM7tMAmZm5urMvB9YChzQrHySJEmSVGUteWYwIkYDbwZ+XTSdFhHzI+LSiNixaNsNWFa3WzebLx4lSZIkSX3U9GIwIoYCVwMfz8yngG8BewATgOXAeRu69rB79nC8aRExJyLmrFy5sjmhJUmSJKnDNbUYjIitqRWC38vMawAy85HMXJeZ64GLeeFW0G5gVN3uI4GHNz5mZk7PzK7M7Bo2bFgz40uSJElSx2rmbKIBXALck5nn17WPqOv2LmBhsTwLmBwR20bEGGAsMLtZ+SRJkiSpypo5m+ghwAeABRExr2j7DDAlIiZQuwX0AeAjAJm5KCKuAhZTm4n0VGcSlSRJkqTmaFoxmJm30fNzgNdvZp9zgHOalUmSJEmSVNOS2UQlSZIkSe2loWIwIm5qpE2SpCrp6/hYvFppRUQsrGvbKSJujIh7i+871m37dEQsjYglEXFU//0LJElVttliMCKGRMROwC4RsWMxUO1UvDfwNS1JKElSm+mH8XEGcPRGbWcAN2XmWOCmYp2IGAdMBsYX+1wYEYP6518iSaqyl3tm8CPAx6kNbHN54RnAp4ALmhdLkqS2tkXjY2beWhSO9SYBE4vly4CbgU8V7TMzczVwf0QspfZapv/ekn+AJEmbLQYz82vA1yLi9Mz8RosySZLU1po0Pu6amcuL4y+PiOFF+27AHXX9uos2SZK2SEOziWbmNyLiYGB0/T6ZeXmTckmS1PZaND72NDN39tgxYhowDWD33XfvxwiSpE7UUDEYEd8B9gDmARve/ZeAxaAkqbL6eXx8JCJGFFcFRwArivZuYFRdv5HAwz0dIDOnA9MBurq6eiwYJUnaoNH3DHYB4zLTgUWSpBf05/g4C5gKnFt8v66u/T8i4nxqzyiOBWb3w+dJkiqu0fcMLgT+RzODSJI0APVpfIyIK6hNAPPGiOiOiJOpFYFHRsS9wJHFOpm5CLgKWAzcAJyamet6PrIkSY1r9MrgLsDiiJgNrN7QmJnHNSWVJEkDQ5/Gx8ycsolNR2yi/znAOX0NKUlSTxotBs9qZghJkgaos8oOIElSXzU6m+gtzQ4iSdJA4/goSRrIGp1N9GlemMZ6G2Br4NnMfHWzgkmS1O4cHyVJA1mjVwa3q1+PiOOBA5oRSJKkgcLxUZI0kDU6m+iLZOYPgbf3bxRJkgY2x0dJ0kDS6G2iJ9StbkXtvUq+c1CSVGmOj5KkgazR2UT/V93yWuABYFK/p5EkaWBxfJQkDViNPjP4oWYHkSRpoHF8lCQNZA09MxgRIyPi2ohYERGPRMTVETHyZfYZFRG/iIh7ImJRRHysaN8pIm6MiHuL7zvW7fPpiFgaEUsi4qgt+6dJktRcfRkfJUlqF41OIPNtYBbwGmA34EdF2+asBf4xM/cCDgJOjYhxwBnATZk5FripWKfYNhkYDxwNXBgRg3r3z5EkqaX6Mj5KktQWGi0Gh2XmtzNzbfE1Axi2uR0yc3lm3lUsPw3cQ22gnARcVnS7DDi+WJ4EzMzM1Zl5P7AUp+eWJLW3Xo+PkiS1i0aLwUcj4q8jYlDx9dfAqkY/JCJGA28Gfg3smpnLoVYwAsOLbrsBy+p26y7aJElqV1s0PkqSVKZGi8GTgBOB/wcsB94DNPTQfEQMBa4GPp6ZT22uaw9tL5meOyKmRcSciJizcuXKRiJIktQsfR4fJUkqW6PF4OeBqZk5LDOHUxv8znq5nSJia2qF4Pcy85qi+ZGIGFFsHwGsKNq7gVF1u48EHt74mJk5PTO7MrNr2DDvxJEklapP46MkSe2g0WJwn8x8fMNKZj5G7bbPTYqIAC4B7snM8+s2zQKmFstTgevq2idHxLYRMQYYC8xuMJ8kSWXo9fgoSVK7aPSl81tFxI4bBryI2KmBfQ8BPgAsiIh5RdtngHOBqyLiZOBB4L0AmbkoIq4CFlObifTUzFzXm3+MJEkt1pfxUZKkttDogHUe8KuI+AG15/hOBM7Z3A6ZeRs9PwcIcMQm9jnn5Y4rSVIb6fX4KElSu2ioGMzMyyNiDvB2agXeCZm5uKnJJElqc46PkqSBrOFbWYrBzQFOkqQ6jo+SpIGq0QlkJEmSJEkdxGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyHchSZLUJiLijcCVdU2vAz4L7AB8GFhZtH8mM69vbTpJUqexGJQkqU1k5hJgAkBEDAIeAq4FPgR8JTO/XF46SVKn8TZRSZLa0xHA7zPzD2UHkSR1JotBSZLa02Tgirr10yJifkRcGhE79rRDREyLiDkRMWflypU9dZEk6XkWg5IktZmI2AY4Dvh+0fQtYA9qt5AuB87rab/MnJ6ZXZnZNWzYsFZElSQNYBaDkiS1n2OAuzLzEYDMfCQz12XmeuBi4IBS00mSOoLFoCRJ7WcKdbeIRsSIum3vAha2PJEkqeM4m6gkSW0kIl4JHAl8pK75ixExAUjggY22SZLUJxaDkiS1kcz8I7DzRm0fKCmOJKmDeZuoJEmSJFWQxaAkSZIkVZC3iUqSJEkb2f8Tl5cdod9cu92Xyo7Qb3b/7IKyI3QUrwxKkiRJUgU1rRiMiEsjYkVELKxrOysiHoqIecXXsXXbPh0RSyNiSUQc1axckiRJkqTmXhmcARzdQ/tXMnNC8XU9QESMAyYD44t9LoyIQU3MJkmSJEmV1rRiMDNvBR5rsPskYGZmrs7M+4GlwAHNyiZJkiRJVVfGM4OnRcT84jbSHYu23YBldX26i7aXiIhpETEnIuasXLmy2VklSZIkqSO1uhj8FrAHMAFYDpxXtEcPfbOnA2Tm9MzsysyuYcOGNSWkJEmSJHW6lhaDmflIZq7LzPXAxbxwK2g3MKqu60jg4VZmkyRJkqQqaWkxGBEj6lbfBWyYaXQWMDkito2IMcBYYHYrs0mSJElSlTTtpfMRcQUwEdglIrqBM4GJETGB2i2gDwAfAcjMRRFxFbAYWAucmpnrmpVNkiRJkqquacVgZk7pofmSzfQ/BzinWXkkSZIkSS8oYzZRSZIkSVLJLAYlSZIkqYIsBiVJkiSpgiwGJUmSJKmCLAYlSZIkqYIsBiVJkiSpgiwGJUmSJKmCmvaeQUmSJEnqT4d845CyI/SL20+/vewIgFcGJUmSJKmSvDIoSVIbiYgHgKeBdcDazOyKiJ2AK4HRwAPAiZn5eFkZJUmdwSuDkiS1n8Mzc0JmdhXrZwA3ZeZY4KZiXZKkLWIxKElS+5sEXFYsXwYcX14USVKnsBiUJKm9JPCziJgbEdOKtl0zczlA8X14TztGxLSImBMRc1auXNmiuJKkgcpnBiVJai+HZObDETEcuDEiftvojpk5HZgO0NXVlc0KKEnqDF4ZlCSpjWTmw8X3FcC1wAHAIxExAqD4vqK8hJKkTmExKElSm4iIV0XEdhuWgXcAC4FZwNSi21TgunISSpI6ibeJSlIvPHj23mVHGFB2/+yCsiMMNLsC10YE1Mbo/8jMGyLiTuCqiDgZeBB4b4kZJUkdwmJQkqQ2kZn3Afv20L4KOKL1iSRJnaxpt4lGxKURsSIiFta17RQRN0bEvcX3Heu2fToilkbEkog4qlm5JEmSJEnNfWZwBnD0Rm09vjQ3IsYBk4HxxT4XRsSgJmaTJEmSpEprWjGYmbcCj23UvKmX5k4CZmbm6sy8H1hKbfY0SZIkSVITtHo20U29NHc3YFldv+6i7SV8oa4kSZIkbbl2ebVE9NDW48tyM3N6ZnZlZtewYcOaHEuSJEmSOlOri8FNvTS3GxhV128k8HCLs0mSJElSZbS6GNzUS3NnAZMjYtuIGAOMBWa3OJskSZIkVUbT3jMYEVcAE4FdIqIbOBM4lx5empuZiyLiKmAxsBY4NTPXNSubJEmSJFVd04rBzJyyiU09vjQ3M88BzmlWHkmSJEnSC9plAhlJkiRJUgtZDEqSJElSBVkMSpIkSVIFWQxKkiRJUgU1bQIZSQPD/p+4vOwIA8q125WdQJIkqX94ZVCSJEmSKshiUJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyGJQkqQ2ERGjIuIXEXFPRCyKiI8V7WdFxEMRMa/4OrbsrJKkgW9w2QEkSdLz1gL/mJl3RcR2wNyIuLHY9pXM/HKJ2SRJHcZiUJKkNpGZy4HlxfLTEXEPsFu5qSRJncrbRCVJakMRMRp4M/Droum0iJgfEZdGxI7lJZMkdQqLQUmS2kxEDAWuBj6emU8B3wL2ACZQu3J43ib2mxYRcyJizsqVK1sVV5I0QJVSDEbEAxGxoHgIfk7RtlNE3BgR9xbf/aunJKlyImJraoXg9zLzGoDMfCQz12XmeuBi4ICe9s3M6ZnZlZldw4YNa11oSdKAVOaVwcMzc0JmdhXrZwA3ZeZY4KZiXZKkyoiIAC4B7snM8+vaR9R1exewsNXZJEmdp50mkJkETCyWLwNuBj5VVhhJkkpwCPABYEFEzCvaPgNMiYgJQAIPAB8pI5wkqbOUVQwm8LOISOD/y8zpwK7FLGpk5vKIGN7TjhExDZgGsPvuu7cqryRJTZeZtwHRw6brW51FktT5yioGD8nMh4uC78aI+G2jOxaF43SArq6ubFZASZIkSepkpTwzmJkPF99XANdSexD+kQ3PRBTfV5SRTZIkSZKqoOXFYES8KiK227AMvIPag/CzgKlFt6nAda3OJkmSJElVUcZtorsC19YmTGMw8B+ZeUNE3AlcFREnAw8C7y0hmyRJkiRVQsuLwcy8D9i3h/ZVwBGtziNJkiRJVVTmewYlSZIkSSWxGJQkSZKkCrIYlCRJkqQKshiUJEmSpAqyGJQkSZKkCrIYlCRJkqQKshiUJEmSpAqyGJQkSZKkCrIYlCRJkqQKshiUJEmSpAqyGJQkSZKkCrIYlCRJkqQKshiUJEmSpAqyGJQkSZKkCrIYlCRJkqQKshiUJEmSpAqyGJQkSZKkChpcdoB2sf8nLi87woBy7XZlJ5AkSZK0JdruymBEHB0RSyJiaUScUXYeSZLageOjJKm/tVUxGBGDgAuAY4BxwJSIGFduKkmSyuX4KElqhrYqBoEDgKWZeV9mPgfMBCaVnEmSpLI5PkqS+l27PTO4G7Csbr0bOLC+Q0RMA6YVq89ExJIWZVOd18IuwKNl5xhQzoyyE6gf+LPfS/37c//a/jzYAPOy4yM4RjaiRT9E/p7ohfio42Oz+XPffvr5577P/xO3WzHY01nJF61kTgemtyaONiUi5mRmV9k5pFbzZ18lednxERwj24W/J1RF/twPTO12m2g3MKpufSTwcElZJElqF46PkqR+127F4J3A2IgYExHbAJOBWSVnkiSpbI6PkqR+11a3iWbm2og4DfgpMAi4NDMXlRxLPfM2JFWVP/tqOcfHAcffE6oif+4HoMh8ySMHkiRJkqQO1263iUqSJEmSWsBiUJIkSZIqyGJQDYua2yLimLq2EyPihjJzSc0WERkR59Wt/1NEnFViJEltxjFSVeT4OPBZDKphWXvA9BTg/IgYEhGvAs4BTi03mdR0q4ETImKXsoNIak+Okaoox8cBzmJQvZKZC4EfAZ8CzgQuz8zfl5tKarq11GZJ+/uyg0hqX46RqiDHxwGurV4toQHjc8BdwHNAV8lZpFa5AJgfEV8sO4iktuYYqapxfBzALAbVa5n5bERcCTyTmavLziO1QmY+FRGXAx8F/lR2HkntyTFSVeP4OLB5m6j6an3xJVXJV4GTgVeVnENSe3OMVNV8FcfHAcliUJIalJmPAVdRG/AkSRKOjwOZxaAk9c55gLOmSZL0Yo6PA1DUZkKWJEmSJFWJVwYlSZIkqYIsBiVJkiSpgiwGJUmSJKmCLAYlSZIkqYIsBiVJkiSpgiwGJUmSJKmCLAalLRARz7T487aKiK9HxMKIWBARd0bEmGLbZxo8RkP9JEnaEo6RUvvzPYPSFoiIZzJzaAs/bwrwbuDEzFwfESOBZzPz8UaztDqzJKmaHCOl9ueVQamfRcSEiLgjIuZHxLURsWPR/uHir5S/iYirI+KVRfuM4i+Zv4qI+yLiPZs5/AhgeWauB8jM7mKQOxd4RUTMi4jvFcf9YUTMjYhFETGtaHtRv4gYHREL67L/U0ScVSx/NCIWF/+OmU04VZKkinGMlNqLVwalLdDTXxAjYj5wembeEhFnA6/OzI9HxM6Zuaro8wXgkcz8RkTMAF4FvA/YE5iVma/fxOeNBG4DngBuAr6bmXf3lCUidsrMxyLiFcCdwNsyc1V9v4gYDfw4M99UrP8TMDQzz4qIh4Exmbk6InbIzCf645xJkqrBMVJqf14ZlPpRRGwP7JCZtxRNlwGHFctviohfRsQC4P3A+Lpdf5iZ6zNzMbDrpo6fmd3AG4FPA+uBmyLiiE10/2hE/Aa4AxgFjO3lP2c+8L2I+GtgbS/3lSTpRRwjpfZjMSi1zgzgtMzcG/gcMKRu2+q65djcQTJzdWb+JDM/Afwf4PiN+0TEROB/Am/NzH2Buzf6vA3W8uLfA/V9/hK4ANgfmBsRgzeXS5KkLTADx0ip5SwGpX6UmU8Cj0fEXxRNHwA2/AV0O2B5RGxN7a+evRYR+0XEa4rlrYB9gD8Um9cUxwbYHng8M/8YEXsCB9Udpr7fI8DwiNg5IrYF3ll37FGZ+Qvgk8AOgA/US5L6zDFSaj/+FUPaMq+MiO669fOBqcBFxcPv9wEfKrb9K/BragPTAmoDX28NBy4uBiWA2cA3i+XpwPyIuAs4CTileDZjCbXbYNi4X2a+v3hm49fA/cBviz6DgO8Wt/QE8BWfh5Ak9ZJjpNTmnEBGkiRJkirI20QlSZIkqYK8TVRqQxGxN/CdjZpXZ+aBZeSRJKldOEZK/cfbRCVJkiSpgrxNVJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJKkEkXEpRGxIiIWbmJ7RMTXI2JpRMyPiP1anVGS1JksBiVJKtcM4OjNbD8GGFt8TQO+1YJMkqQKsBiUJKlEmXkr8NhmukwCLs+aO4AdImJEa9JJkjqZxaAkSe1tN2BZ3Xp30SZJ0hYZXHaALbHLLrvk6NGjy44hSWqBuXPnPpqZw8rOUYLooS177BgxjdqtpLzqVa/af88992xmLklSG9iS8XFAF4OjR49mzpw5ZceQJLVARPyh7Awl6QZG1a2PBB7uqWNmTgemA3R1daVjpCR1vi0ZH71NVJKk9jYL+GAxq+hBwJOZubzsUJKkgW9AXxmUJGmgi4grgInALhHRDZwJbA2QmRcB1wPHAkuBPwIfKiepJKnTWAxKklSizJzyMtsTOLVFcSRJFdK0YjAiRgGXA/8DWA9Mz8yvRcRZwIeBlUXXz2Tm9cU+nwZOBtYBH83MnzYrnyS1izVr1tDd3c2f//znsqO0hSFDhjBy5Ei23nrrsqNIktTRmnllcC3wj5l5V0RsB8yNiBuLbV/JzC/Xd46IccBkYDzwGuDnEfGGzFzXxIySVLru7m622247Ro8eTURPE0dWR2ayatUquru7GTNmTNlxJEnqaE2bQCYzl2fmXcXy08A9bP69SJOAmZm5OjPvp/ZsxAHNyidJ7eLPf/4zO++8c+ULQYCIYOedd/YqqSRJLdCS2UQjYjTwZuDXRdNpETE/Ii6NiB2LtoZeqhsR0yJiTkTMWbly5cabJWlAshB8gedCkqTWaHoxGBFDgauBj2fmU8C3gD2ACcBy4LwNXXvY/SUv1c3M6ZnZlZldw4ZV8d3Dkqpg0KBBTJgwgfHjx7Pvvvty/vnns379+tLyjB49mkcffbRP+/7whz9k8eLF/ZxIkiRtqaYWgxGxNbVC8HuZeQ1AZj6Smesycz1wMS/cCtrwS3UlqdO94hWvYN68eSxatIgbb7yR66+/ns997nNlx+oTi0FJktpTM2cTDeAS4J7MPL+ufUTdy3LfBSwslmcB/xER51ObQGYsMLtZ+Ta2/ycub9VH9crcL32w7AiSSjZ8+HCmT5/OW97yFs466yzWr1/PGWecwc0338zq1as59dRT+chHPsLNN9/MZz/7WXbeeWeWLFnCYYcdxoUXXshWW23Fz372M84880xWr17NHnvswbe//W2GDh3K6NGjmTp1Kj/60Y9Ys2YN3//+99lzzz1ZtWoVU6ZMYeXKlRxwwAHU3m5Q893vfpevf/3rPPfccxx44IFceOGFDBo0iKFDh/Kxj32MH//4x7ziFa/guuuu4/e//z2zZs3illtu4Qtf+AJXX301//mf/8lFF13E4MGDGTduHDNnzizx7EqSVF3NvDJ4CPAB4O0RMa/4Ohb4YkQsiIj5wOHA3wNk5iLgKmAxcANwqjOJSlLN6173OtavX8+KFSu45JJL2H777bnzzju58847ufjii7n//vsBmD17Nueddx4LFizg97//Pddccw2PPvooX/jCF/j5z3/OXXfdRVdXF+ef//zf6Nhll1246667+N//+3/z5S/XJnr+3Oc+x6GHHsrdd9/Ncccdx4MPPgjAPffcw5VXXsntt9/OvHnzGDRoEN/73vcAePbZZznooIP4zW9+w2GHHcbFF1/MwQcfzHHHHceXvvQl5s2bxx577MG5557L3Xffzfz587noootafCYlSdIGTbsymJm30fNzgNdvZp9zgHOalUmSBrINV+d+9rOfMX/+fH7wgx8A8OSTT3LvvfeyzTbbcMABB/C6170OgClTpnDbbbcxZMgQFi9ezCGHHALAc889x1vf+tbnj3vCCScAsP/++3PNNdcAcOuttz6//Jd/+ZfsuGNtrq+bbrqJuXPn8pa3vAWAP/3pTwwfPhyAbbbZhne+853PH+vGG2+kJ/vssw/vf//7Of744zn++OP75+RIkqRea+Z7BiVJ/eS+++5j0KBBDB8+nMzkG9/4BkcdddSL+tx8880vmYkzIshMjjzySK644ooej73tttsCtUlr1q5d+6J9N5aZTJ06lX/7t397ybatt976+X02Pla9//zP/+TWW29l1qxZfP7zn2fRokUMHuxwJElSq7Xk1RKSpL5buXIlp5xyCqeddhoRwVFHHcW3vvUt1qxZA8Dvfvc7nn32WaB2m+j999/P+vXrufLKKzn00EM56KCDuP3221m6dCkAf/zjH/nd73632c887LDDnr/98yc/+QmPP/44AEcccQQ/+MEPWLFiBQCPPfYYf/jDHzZ7rO22246nn34agPXr17Ns2TIOP/xwvvjFL/LEE0/wzDPP9PHMSJKkLeGfYiWpDf3pT39iwoQJrFmzhsGDB/OBD3yAf/iHfwDgb//2b3nggQfYb7/9yEyGDRvGD3/4QwDe+ta3csYZZ7BgwQIOO+ww3vWud7HVVlsxY8YMpkyZwurVqwH4whe+wBve8IZNfv6ZZ57JlClT2G+//Xjb297G7rvvDsC4ceP4whe+wDve8Q7Wr1/P1ltvzQUXXMBrX/vaTR5r8uTJfPjDH+brX/86M2fO5OSTT+bJJ58kM/n7v/97dthhh/45aZIkqVeifoa4gaarqyvnzJnTL8dyNlFJZbnnnnvYa6+9tvg4N998M1/+8pf58Y9/3A+pytXTOYmIuZnZVVKkAac/x0hJUvvakvHR20QlSZIkqYK8TVSSOsTEiROZOHFi2TEkSdIA4ZVBSZIkSaogi0FJkiRJqiCLQUmSJEmqIItBSZIkSaogi0FJUp/dcMMNvPGNb+T1r3895557btlxJElSLzibqCR1gP5+V2oj7zhdt24dp556KjfeeCMjR47kLW95C8cddxzjxo3r1yySJKk5vDIoSeqT2bNn8/rXv57Xve51bLPNNkyePJnrrruu7FiSJKlBFoOSpD556KGHGDVq1PPrI0eO5KGHHioxkSRJ6g2LQUlSn2TmS9oiooQkkiSpLywGJUl9MnLkSJYtW/b8end3N695zWtKTCRJknrDYlCS1CdvectbuPfee7n//vt57rnnmDlzJscdd1zZsSRJUoOcTVSS1CeDBw/mm9/8JkcddRTr1q3jpJNOYvz48WXHkiRJDbIYlKQO0MirIJrh2GOP5dhjjy3lsyVJ0pbxNlFJkiRJqiCLQUmSJEmqIItBSZIkSaogi0FJkiRJqiCLQUmSJEmqIItBSZIkSaogi0FJUp+cdNJJDB8+nDe96U1lR5EkSX3gewYlqQM8ePbe/Xq83T+74GX7/M3f/A2nnXYaH/xgOe84lCRJW8Yrg5KkPjnssMPYaaedyo4hSZL6yGJQkiRJkirIYlCSpBJFxNERsSQilkbEGT1s3z4ifhQRv4mIRRHxoTJySpI6j8WgJEkliYhBwAXAMcA4YEpEjNuo26nA4szcF5gInBcR27Q0qCSpI1kMSpJUngOApZl5X2Y+B8wEJm3UJ4HtIiKAocBjwNrWxpQkdSKLQUlSn0yZMoW3vvWtLFmyhJEjR3LJJZeUHWkg2g1YVrfeXbTV+yawF/AwsAD4WGaub008SVIn89USktQBGnkVRH+74oorWv6ZHSh6aMuN1o8C5gFvB/YAboyIX2bmUy85WMQ0YBrA7rvv3r9JJUkdxyuDkiSVpxsYVbc+ktoVwHofAq7JmqXA/cCePR0sM6dnZldmdg0bNqwpgSVJncNiUJKk8twJjI2IMcWkMJOBWRv1eRA4AiAidgXeCNzX0pSSpI7UtGIwIkZFxC8i4p5iKuyPFe07RcSNEXFv8X3Hun0+XUytvSQijmpWNkmS2kFmrgVOA34K3ANclZmLIuKUiDil6PZ54OCIWADcBHwqMx8tJ7EkqZM085nBtcA/ZuZdEbEdMDcibgT+BrgpM88t3qd0BvCpYirtycB44DXAzyPiDZm5rokZJUkqVWZeD1y/UdtFdcsPA+9odS5JUudr2pXBzFyemXcVy09T+4vnbtSmzL6s6HYZcHyxPAmYmZmrM/N+YCm1KbclSZIkSf2sJc8MRsRo4M3Ar4FdM3M51ApGYHjRrZHptSVJkiRJ/aDpxWBEDAWuBj7e0zTY9V17aNt4em0iYlpEzImIOStXruyvmJKkXlq2bBmHH344e+21F+PHj+drX/ta2ZEkSVIvNPU9gxGxNbVC8HuZeU3R/EhEjMjM5RExAlhRtDcyvTaZOR2YDtDV1fWSYlGSquiQbxzSr8e7/fTbX7bP4MGDOe+889hvv/14+umn2X///TnyyCMZN25cv2aRJEnN0czZRAO4BLgnM8+v2zQLmFosTwWuq2ufHBHbRsQYYCwwu1n5JElbZsSIEey3334AbLfdduy111489NBDJaeSJEmNauaVwUOADwALImJe0fYZ4Fzgqog4mdq7k94LUEylfRWwmNpMpKc6k6gkDQwPPPAAd999NwceeGDZUSRJUoOaVgxm5m30/BwgFC/P7WGfc4BzmpVJktT/nnnmGd797nfz1a9+lVe/+tVlx5EkSQ1qyWyikqTOtGbNGt797nfz/ve/nxNOOKHsOJIkqRcsBiVJfZKZnHzyyey11178wz/8Q9lxJElSL1kMSpL65Pbbb+c73/kO//Vf/8WECROYMGEC119/fdmxJElSg5r6aglJUms08iqI/nbooYeS6Rt+JEkaqLwyKEmSJEkVZDEoSZIkSRVkMShJkiRJFWQxKEmSJEkVZDEoSZIkSRVkMShJkiRJFWQxKEnqkz//+c8ccMAB7LvvvowfP54zzzyz7EiSJKkXfM+gJHWAWw57W78e72233vKyfbbddlv+67/+i6FDh7JmzRoOPfRQjjnmGA466KB+zSJJkprDK4OSpD6JCIYOHQrAmjVrWLNmDRFRcipJktQoi0FJUp+tW7eOCRMmMHz4cI488kgOPPDAsiNJkqQGWQxKkvps0KBBzJs3j+7ubmbPns3ChQvLjiRJkhpkMShJ2mI77LADEydO5IYbbig7iiRJapDFoCSpT1auXMkTTzwBwJ/+9Cd+/vOfs+eee5YbSpIkNczZRCVJfbJ8+XKmTp3KunXrWL9+PSeeeCLvfOc7y44lSZIaZDEoSR2gkVdB9Ld99tmHu+++u+WfK0mS+oe3iUqSJElSBVkMSpIkSVIFWQxKkiRJUgVZDEpSG8jMsiO0Dc+FJEmtYTEoSSUbMmQIq1atsgiiVgiuWrWKIUOGlB1FkqSO52yiklSykSNH0t3dzcqVK8uO0haGDBnCyJEjy44hSVLHsxiUpJJtvfXWjBkzpuwYkiSpYrxNVJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJKkEkXE0RGxJCKWRsQZm+gzMSLmRcSiiLil1RklSZ3J9wxKklSSiBgEXAAcCXQDd0bErMxcXNdnB+BC4OjMfDAihpcSVpLUcbwyKElSeQ4AlmbmfZn5HDATmLRRn78CrsnMBwEyc0WLM0qSOpTFoCRJ5dkNWFa33l201XsDsGNE3BwRcyPig5s6WERMi4g5ETFn5cqVTYgrSeokFoOSJJUnemjLjdYHA/sDfwkcBfxrRLyhp4Nl5vTM7MrMrmHDhvVvUklSx2laMRgRl0bEiohYWNd2VkQ8VDwEPy8ijq3b9uni4fklEXFUs3JJktRGuoFRdesjgYd76HNDZj6bmY8CtwL7tiifJKmDNfPK4Azg6B7av5KZE4qv6wEiYhwwGRhf7HNh8VC9JEmd7E5gbESMiYhtqI2Fszbqcx3wFxExOCJeCRwI3NPinJKkDtS0YjAzbwUea7D7JGBmZq7OzPuBpdQeqpckqWNl5lrgNOCn1Aq8qzJzUUScEhGnFH3uAW4A5gOzgX/PzIWbOqYkSY0q49USpxUPv88B/jEzH6f2sPwddX16eoAeqD0cD0wD2H333ZscVZKk5irukrl+o7aLNlr/EvClVuaSJHW+Vk8g8y1gD2ACsBw4r2hv5AH6WqMPx0uSJEnSFmtpMZiZj2TmusxcD1zMC7eCNvIAvSRJkiSpn7S0GIyIEXWr7wI2PPMwC5gcEdtGxBhgLLXnIiRJkiRJTdC0ZwYj4gpgIrBLRHQDZwITI2ICtVtAHwA+AlA8LH8VsBhYC5yameualU2SJEmSqq5pxWBmTumh+ZLN9D8HOKdZeSRJkiRJL2j1BDKSJEmSpDbQUDEYETc10iZJkiRJGhg2e5toRAwBXkntub8deeEVEK8GXtPkbJIkSZKkJnm5ZwY/AnycWuE3lxeKwaeAC5oXS5IkSZLUTJstBjPza8DXIuL0zPxGizJJkiRJkpqsodlEM/MbEXEwMLp+n8y8vEm5JEmSJElN1FAxGBHfAfYA5gEb3v+XgMWgJEmSJA1Ajb5nsAsYl5nZzDCSJEmSpNZo9D2DC4H/0cwgkiRJkqTWafTK4C7A4oiYDaze0JiZxzUllSRJkiSpqRotBs9qZghJkiRJUms1OpvoLc0OIkmSJElqnUZnE32a2uyhANsAWwPPZuarmxVMkiRJktQ8jV4Z3K5+PSKOBw5oRiBJkiRJUvM1Opvoi2TmD4G3928USZIkSVKrNHqb6Al1q1tRe++g7xyUJEmSpAGq0dlE/1fd8lrgAWBSv6eRJEmSJLVEo88MfqjZQSRJkiRJrdPQM4MRMTIiro2IFRHxSERcHREjmx1OkiRJktQcjU4g821gFvAaYDfgR0WbJEmSJGkAarQYHJaZ387MtcXXDGBYE3NJkiRJkpqo0WLw0Yj464gYVHz9NbCqmcEkSZIkSc3TaDF4EnAi8P+A5cB7ACeVkSRJkqQBqtFXS3wemJqZjwNExE7Al6kViZIkSZKkAabRK4P7bCgEATLzMeDNzYkkSZIkSWq2RovBrSJixw0rxZXBRq8qSpIkSZLaTKMF3XnAryLiB0BSe37wnKalkiRJkiQ1VUPFYGZeHhFzgLcDAZyQmYubmkySJEmS1DQN3+pZFH8WgFKH2f8Tl5cdoUdzv/TBsiNIkiR1tEafGZQkSZIkdRCLQUmSJEmqIItBSZIkSaogi0FJkiRJqiCLQUmSShQRR0fEkohYGhFnbKbfWyJiXUS8p5X5JEmdy2JQkqSSRMQg4ALgGGAcMCUixm2i3/8FftrahJKkTmYxKElSeQ4AlmbmfZn5HDATmNRDv9OBq4EVrQwnSepsTSsGI+LSiFgREQvr2naKiBsj4t7i+4512z5d3CKzJCKOalYuSZLayG7Asrr17qLteRGxG/Au4KKXO1hETIuIORExZ+XKlf0aVJLUeZp5ZXAGcPRGbWcAN2XmWOCmYp3ilpjJwPhinwuLW2IkSepk0UNbbrT+VeBTmbnu5Q6WmdMzsyszu4YNG9Yf+SRJHaxpxWBm3go8tlHzJOCyYvky4Pi69pmZuToz7weWUrt1RpKkTtYNjKpbHwk8vFGfLmBmRDwAvIfaH0yPb0k6SVJHG9ziz9s1M5cDZObyiBhetO8G3FHX7yW3yUiS1IHuBMZGxBjgIWp3yfxVfYfMHLNhOSJmAD/OzB+2MKMkqUO1uhjclEZuk6l1jJgGTAPYfffdm5lJkqSmysy1EXEatVlCBwGXZuaiiDil2P6yzwlKktRXrS4GH4mIEcVVwRG8MCtaI7fJALXnIYDpAF1dXT0WjJIkDRSZeT1w/UZtPRaBmfk3rcgkSaqGVr9aYhYwtVieClxX1z45IrYtbpUZC8xucTZJkiRJqoymXRmMiCuAicAuEdENnAmcC1wVEScDDwLvBShuibkKWAysBU5tZNY0SZIkSVLfNK0YzMwpm9h0xCb6nwOc06w8kiRJkqQXtPo2UUmSJElSG7AYlCRJkqQKshiUJEmSpAqyGJQkSZKkCrIYlCRJkqQKshiUJEmSpAqyGJQkSZKkCrIYlCRJkqQKshiUJEmSpAqyGJQkSZKkCrIYlCRJkqQKshiUJEmSpAqyGJQkSZKkCrIYlCRJkqQKshiUJEmSpAqyGJQkSZKkCrIYlCRJkqQKGlx2AA1Mh3zjkLIj9Oj2028vO4IkSZI0IHhlUJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyGJQkiRJkirIl863uQfP3rvsCD3b8dVlJ5AkSZK0BbwyKEmSJEkVZDEoSZIkSRVkMShJkiRJFWQxKEmSJEkVZDEoSZIkSRVkMShJkiRJFWQxKEmSJEkVZDEoSZIkSRVkMShJUoki4uiIWBIRSyPijB62vz8i5hdfv4qIfcvIKUnqPBaDkiSVJCIGARcAxwDjgCkRMW6jbvcDb8vMfYDPA9Nbm1KS1KkGl/GhEfEA8DSwDlibmV0RsRNwJTAaeAA4MTMfLyOfJEktcgCwNDPvA4iImcAkYPGGDpn5q7r+dwAjW5pQktSxyrwyeHhmTsjMrmL9DOCmzBwL3FSsS5LUyXYDltWtdxdtm3Iy8JOmJpIkVUY73SY6CbisWL4MOL68KJIktUT00JY9dow4nFox+KlNHixiWkTMiYg5K1eu7KeIkqROVVYxmMDPImJuREwr2nbNzOUAxffhPe3oQCdJ6iDdwKi69ZHAwxt3ioh9gH8HJmXmqk0dLDOnZ2ZXZnYNGzas38NKkjpLKc8MAodk5sMRMRy4MSJ+2+iOmTmd4uH5rq6uHv96KknSAHEnMDYixgAPAZOBv6rvEBG7A9cAH8jM37U+oiSpU5VSDGbmw8X3FRFxLbUH6B+JiBGZuTwiRgArysgmSVKrZObaiDgN+CkwCLg0MxdFxCnF9ouAzwI7AxdGBBQTr5WVWZLUOVpeDEbEq4CtMvPpYvkdwNnALGAqcG7x/bpWZ5MkqdUy83rg+o3aLqpb/lvgb1udS5LU+cq4MrgrcG3x183BwH9k5g0RcSdwVUScDDwIvLeEbJIkSZJUCS0vBot3Ke3bQ/sq4IhW55EkSZKkKmqnV0tIkiRJklrEYlCSJEmSKshiUJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyGJQkiRJkiqojJfOS9LLevDsvcuO0KPdP7ug7AiSJEn9wiuDkiRJklRBFoOSJEmSVEHeJqqOcsthbys7wia97dZbyo4gSZIkPc8rg5IkSZJUQRaDkiRJklRBFoOSJEmSVEEWg5IkSZJUQRaDkiRJklRBFoOSJEmSVEG+WkKSeuGQbxxSdoQe3X767WVHkCRJA4xXBiVJkiSpgiwGJUmSJKmCLAYlSZIkqYIsBiVJkiSpgiwGJUmSJKmCnE1UkjrALYe9rewIPXrbrbeUHUGSJG2CVwYlSZIkqYIsBiVJkiSpgiwGJUmSJKmCLAYlSZIkqYIsBiVJkiSpgiwGJUmSJKmCLAYlSZIkqYIsBiVJkiSpgiwGJUmSJKmCLAYlSZIkqYIsBiVJkiSpgiwGJUmSJKmCLAYlSZIkqYLarhiMiKMjYklELI2IM8rOI0lSM73cuBc1Xy+2z4+I/crIKUnqPG1VDEbEIOAC4BhgHDAlIsaVm0qSpOZocNw7BhhbfE0DvtXSkJKkjtVWxSBwALA0M+/LzOeAmcCkkjNJktQsjYx7k4DLs+YOYIeIGNHqoJKkzjO47AAb2Q1YVrfeDRxY3yEiplH7yyjAMxGxpEXZSvHasgNs2i7Ao2WH2NjEsgNsTkTZCQYUf/Z7Z2LZATalf3/u2/jHos9edtzbRJ/dgOUbH2yjMXJ1RCzsv6gdry3/225jnq/e8Xz1juerd97Y1x3brRjs6f815ItWMqcD01sTR5sSEXMys6vsHFKr+bOvfvay416DfWqNdWOkP6u94/nqHc9X73i+esfz1TsRMaev+7bbbaLdwKi69ZHAwyVlkSSp2RoZ9xwbJUlN0W7F4J3A2IgYExHbAJOBWSVnkiSpWRoZ92YBHyxmFT0IeDIzX3KLqCRJvdVWt4lm5tqIOA34KTAIuDQzF5UcSz3zVl1VlT/76jebGvci4pRi+0XA9cCxwFLgj8CHGjy8P6u94/nqHc9X73i+esfz1Tt9Pl+R2eNjB5IkSZKkDtZut4lKkiRJklrAYlCSJEmSKshiUA0rJi+4LSKOqWs7MSJuKDOX1GwRkRFxXt36P0XEWSVGkgCIiKMjYklELI2IM3rYHhHx9WL7/IjYr4yc7aSBc/b+4lzNj4hfRcS+ZeRsFy93vur6vSUi1kXEe1qZr900cr4iYmJEzIuIRRFxS6sztpMG/nvcPiJ+FBG/Kc5Xo89Md5yIuDQiVmzq/bF9/X1vMaiGZe0B01OA8yNiSES8CjgHOLXcZFLTrQZOiIhdyg4ibRARg4ALgGOAccCUiBi3UbdjgLHF1zTgWy0N2WYaPGf3A2/LzH2Az1PhiSwaPF8b+v1fahMhVVYj5ysidgAuBI7LzPHAe1uds100+PN1KrA4M/cFJgLnFTMvV9EM4OjNbO/T73uLQfVKZi4EfgR8CjgTuDwzf19uKqnp1lL7P4R/X3YQqc4BwNLMvC8znwNmApM26jOJ2u/pzMw7gB0iYkSrg7aRlz1nmfmrzHy8WL2D2nsdq6qRnzGA04GrgRWtDNeGGjlffwVck5kPAmRmlc9ZI+crge0iIoChwGPUxuTKycxbqf37N6VPv+8tBtUXn6P2y+wY4IslZ5Fa5QLg/RGxfdlBpMJuwLK69e6irbd9qqS35+Nk4CdNTdTeXvZ8RcRuwLuAi1qYq1018vP1BmDHiLg5IuZGxAdblq79NHK+vgnsBTwMLAA+lpnrWxNvwOnT7/u2es+gBobMfDYirgSeyczVZeeRWiEzn4qIy4GPAn8qO48ERA9tG78vqpE+VdLw+YiIw6kVg4c2NVF7a+R8fRX4VGauq128qbRGztdgYH/gCOAVwH9HxB2Z+btmh2tDjZyvo4B5wNuBPYAbI+KXmflUk7MNRH36fW8xqL5aX3xJVfJV4C7g2yXnkKD2V99Rdesjqf31vLd9qqSh8xER+wD/DhyTmatalK0dNXK+uoCZRSG4C3BsRKzNzB+2JGF7afS/yUcz81ng2Yi4FdgXqGIx2Mj5+hBwbjFvxdKIuB/YE5jdmogDSp9+33ubqCQ1KDMfA66idrVAKtudwNiIGFNMqDAZmLVRn1nAB4tZ5g4CnszM5a0O2kZe9pxFxO7ANcAHKnq1pt7Lnq/MHJOZozNzNPAD4O8qWghCY/9NXgf8RUQMjohXAgcC97Q4Z7to5Hw9SO0qKhGxK/BG4L6Wphw4+vT73iuDktQ75wGnlR1Cysy1EXEatRkcBwGXZuaiiDil2H4RcD1wLLAU+CO1v7JXVoPn7LPAzsCFxdWutZnZVVbmMjV4vlRo5Hxl5j1ReyXXfGp3WP17MTlf5TT48/V5YEZELKB2G+SnMvPR0kKXKCKuoDaj6i4R0U1tIsetYct+30ftqqskSZIkqUq8TVSSJEmSKshiUJIkSZIqyGJQkiRJkirIYlCSJEmSKshiUJIkSZIqyGJQ2gIR8UyLP2+riPh6RCyMiAURcWdEjCm2fabBYzTUT5IkSZ3NV0tIWyAinsnMoS38vCnAu4ETM3N9RIwEns3MxxvN0urMkiRJak9eGZT6WURMiIg7ImJ+RFwbETsW7R8uruT9JiKujohXFu0ziqt9v4qI+yLiPZs5/AhgeWauB8jM7qIQPBd4RUTMi4jvFcf9YUTMjYhFETGtaHtRv4gYHRHPv+w2Iv4pIs4qlj8aEYuLf8fMJpwqSZIklcgrg9IW6OkqW0TMB07PzFsi4mzg1Zn58YjYOTNXFX2+ADySmd+IiBnAq4D3AXsCszLz9Zv4vJHAbcATwE3AdzPz7p6yRMROmflYRLwCuBN4W2auqu8XEaOBH2fmm4r1fwKGZuZZEfEwMCYzV0fEDpn5RH+cM0mSJLUHrwxK/Sgitgd2yMxbiqbLgMOK5TdFxC8jYgHwfmB83a4/zMz1mbkY2HVTx8/MbuCNwKeB9cBNEXHEJrp/NCJ+A9wBjALG9vKfMx/4XkT8NbC2l/tKkiSpzVkMSq0zAzgtM/cGPgcMqdu2um45NneQzFydmT/JzE8A/wc4fuM+ETER+J/AWzNzX+DujT5vg7W8+PdAfZ+/BC4A9gfmRsTgzeWSJEnSwGIxKPWjzHwSeDwi/qJo+gCw4SrhdsDyiNia2pXBXouI/SLiNcXyVsA+wB+KzWuKYwNsDzyemX+MiD2Bg+oOU9/vEWB4ROwcEdsC76w79qjM/AXwSWAHwElnJEmSOoh/6Ze2zCsjortu/XxgKnBRMUHMfcCHim3/CvyaWvG2gFpx2FvDgYuLwg1gNvDNYnk6MD8i7gJOAk4pnl9cQu1WUTbul5nvL55r/DVwP/Dbos8g4LvFba8BfMVnBiVJkjqLE8hIkiRJUgV5m6gkSZIkVZC3iUptKCL2Br6zUfPqzDywjDySJEnqPN4mKkmSJEkV5G2ikiRJklRBFoOSJEmSVEEWg5IkSZJUQRaDkiRJklRBFoOSJEmSVEH/PzPK87fTP5VsAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 1080x1440 with 8 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "f, axes = plt.subplots(nrows=4, ncols=2, figsize=(15,20))\n",
    "\n",
    "sns.countplot(df[\"Loan_Status\"],hue = df[\"Gender\"],ax = axes[0,0])\n",
    "sns.countplot(df[\"Loan_Status\"],hue = df[\"Married\"],ax = axes[0,1])\n",
    "sns.countplot(df[\"Loan_Status\"],hue = df[\"Education\"],ax = axes[1,0])\n",
    "sns.countplot(df[\"Loan_Status\"],hue = df[\"Self_Employed\"],ax = axes[1,1])\n",
    "sns.countplot(df[\"Loan_Status\"],hue = df[\"Credit_History\"],ax = axes[2,0])\n",
    "sns.countplot(df[\"Loan_Status\"],hue = df[\"Property_Area\"],ax = axes[2,1])\n",
    "sns.countplot(df[\"Loan_Status\"],hue = df[\"Dependents\"],ax = axes[3,0])\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e9cdbe43",
   "metadata": {},
   "source": [
    "Observation of each Graph:\n",
    "    \n",
    "1.The count of male is higher than felame but the loan approval pecentage is almost same for both  .\n",
    "\n",
    "2.The married person is higher chance to get loan easily\n",
    "\n",
    "3.The no. of graduate applicant  is higher and  chance to get loan also higher.\n",
    "\n",
    "4.The Applicant who are self_employee  higher chance for getting loan.\n",
    "\n",
    "5.The Applicant whoes credit_histry is present has  higher chance for getting loan because  credit_histry shows the persone records of his past loan .\n",
    "\n",
    "6.The Applicant who belong from semiurban area has chance to get loan higher.\n",
    "\n",
    "7.If no dependents are present then higher chance to get loan."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "bc5ebe59",
   "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": [
    "sns.scatterplot(x = \"ApplicantIncome\", y= \"LoanAmount\", data=df,hue=\"Loan_Status\");"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ce31be3",
   "metadata": {},
   "source": [
    "when ApplicantIncome is increse the LoanAmount is also  incresed and chance of loan approvel is greater."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "7d7c3926",
   "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": [
    "sns.scatterplot(x = \"CoapplicantIncome\", y= \"LoanAmount\", data=df,hue=\"Loan_Status\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "c28a48d7",
   "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": [
    "sns.scatterplot(x = \"Loan_Amount_Term\", y= \"LoanAmount\", data=df,hue=\"Loan_Status\");"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eec20fcb",
   "metadata": {},
   "source": [
    "Maximum applicant who appled for loan want to pay loan within  15 to 30 years because the age when they applied for loan is approx 25 to 40 year and then want to pay their loan before they tern to 60 year."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "25d24755",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Dependents', ylabel='LoanAmount'>"
      ]
     },
     "execution_count": 45,
     "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": [
    "sns.scatterplot(y=\"LoanAmount\",x='Dependents',data=df,hue=\"Loan_Status\")#regration plot"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "979e617f",
   "metadata": {},
   "source": [
    "If no dependents are there the loan amount is less but when dependents are increse the loan amount also increase."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2875e5b8",
   "metadata": {},
   "source": [
    "# Multivariate Analysis:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "5e9479c1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x17440d83400>"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1148.62x1080 with 42 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pairplot(df,hue=\"Loan_Status\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1d545b6a",
   "metadata": {},
   "source": [
    "# Correlation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "54d8f293",
   "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>Dependents</th>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <th>LoanAmount</th>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <th>Credit_History</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Dependents</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.118202</td>\n",
       "      <td>0.031776</td>\n",
       "      <td>0.163103</td>\n",
       "      <td>-0.103864</td>\n",
       "      <td>-0.040160</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <td>0.118202</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.050745</td>\n",
       "      <td>0.565181</td>\n",
       "      <td>-0.046531</td>\n",
       "      <td>-0.018615</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <td>0.031776</td>\n",
       "      <td>-0.050745</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.206452</td>\n",
       "      <td>-0.073207</td>\n",
       "      <td>0.008339</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LoanAmount</th>\n",
       "      <td>0.163103</td>\n",
       "      <td>0.565181</td>\n",
       "      <td>0.206452</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.036960</td>\n",
       "      <td>-0.000607</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <td>-0.103864</td>\n",
       "      <td>-0.046531</td>\n",
       "      <td>-0.073207</td>\n",
       "      <td>0.036960</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.004705</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Credit_History</th>\n",
       "      <td>-0.040160</td>\n",
       "      <td>-0.018615</td>\n",
       "      <td>0.008339</td>\n",
       "      <td>-0.000607</td>\n",
       "      <td>-0.004705</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Dependents  ApplicantIncome  CoapplicantIncome  LoanAmount  \\\n",
       "Dependents           1.000000         0.118202           0.031776    0.163103   \n",
       "ApplicantIncome      0.118202         1.000000          -0.050745    0.565181   \n",
       "CoapplicantIncome    0.031776        -0.050745           1.000000    0.206452   \n",
       "LoanAmount           0.163103         0.565181           0.206452    1.000000   \n",
       "Loan_Amount_Term    -0.103864        -0.046531          -0.073207    0.036960   \n",
       "Credit_History      -0.040160        -0.018615           0.008339   -0.000607   \n",
       "\n",
       "                   Loan_Amount_Term  Credit_History  \n",
       "Dependents                -0.103864       -0.040160  \n",
       "ApplicantIncome           -0.046531       -0.018615  \n",
       "CoapplicantIncome         -0.073207        0.008339  \n",
       "LoanAmount                 0.036960       -0.000607  \n",
       "Loan_Amount_Term           1.000000       -0.004705  \n",
       "Credit_History            -0.004705        1.000000  "
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#correlation between numerical variable\n",
    "df.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "628edac3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAbQAAAFTCAYAAABRdfl8AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAABz+0lEQVR4nO3dd3gU1dfA8e9JAfRHr0lAQLBLFxCQHnoRsAGKomIv2LArCKKA+KJiQ0RUFGlK770pSC9iAwGlJIReJJQk5/1jJsumbyBhN/F8fOZxZ+bOzNlhs3dvmXtFVTHGGGNyuiB/B2CMMcZkBcvQjDHG5AqWoRljjMkVLEMzxhiTK1iGZowxJlewDM0YY0yuYBmaMcaYi05ERopIjIj8ksZ+EZGhIrJNRDaJSI2MzmkZmjHGGH/4CmiVzv7WwJXu8hDwaUYntAzNGGPMRaeqS4FD6STpAIxSx0qgsIiEp3fOkKwM0FxcZw9sz3HDvNxSo6e/Q8iUf86k9/cWmKrkDfN3CJk2Jupnf4eQKcUuKeDvEDJt39Hf5ULPkZnvnDwlKj6MU7JKNFxVh2ficqWBXV7ru91tUWkdYBmaMcYY3yTE+5zUzbwyk4Ell1oGnG6GahmaMcYY32jCxbzabuAyr/UywN70DrA2NGOMMb5JSPB9uXBTgXvc3o51gKOqmmZ1I1gJzRhjjI80C0toIjIGaAwUF5HdQB8g1LmODgNmAm2AbcBJ4L6MzmkZmjHGGN/Ex2XZqVS1awb7FXg8M+e0DM0YY4xvMtEpxB8sQzPGGOObi9spJNMsQzPGGOObrOnskW0sQzPGGOOTrOwUkh0sQzPGGOMbK6EZY4zJFeLP+juCdFmGZowxxjdW5WiMMSZXCPAqxxw59JWIxIvIBhHZIiIbReRZEfHbexGRnSJS/DyP7Sgi12V1TOfjtbeH0LBtFzp2e8TfoSRRo1ENPl00jM+WDue2x25Lsb9MxTIMnvQuE7dOotNDnTzbi4cX562xb/PJgk/5eP7HtL//5myLsV6TG5myfAzTVozn/ifuTjXNi/2fYdqK8UxYOIprKl8FQJ68eRg9awTjF3zNxCXf8ujzPTzpn+n9OJOXjWHCwlG8N3IABQrmz7b4KzeqzjsLP+TdJR/T7tFOKfaHVyxN70kDGPnnONo81CHJvksLXsqTnz7PoAVDGbhgKFfUuCrb4kzPe0P68fuvy1m3dh7Vq1VKNc1jj97L778uJ+7MHooVK3KRI4S3Br3KyvVzWPTjFCpXTf3Pvmy50sxaMI4V62Yz/MshhIaGJtlfrUYl9h7aQrsOLS9GyElpgu+LH+TIDA2IVdVqqno90BxneJQ+fo7pfHUEAiJD69imOcOG9Pd3GEkEBQXxSP9HeaN7Hx6PfIyGNzfisisvS5Lm+JHjDO/zGZOGT0yyPT4+npH9v+CxyEfp1aEXbe9pm+LYrIrxlQG9eOzO5+jU8E5adWpGhavKJ0lTP7IuZSuUoX3dO+jXaxCvDXoegDOnz/DArU9yR2R37ojszk1N6lC5xvUArFyymlsbd+P2pvfw9/Zd9Oh5T5bHDiBBQXR/80EGd+/Pi82eou7NDYi4skySNP8eOcE3fb5g5udTUhzfrU8PNi1Zz4uRPXm11bPs3bY7W+JMT+tWTbnyisu55rr6PProi3z80YBU0/20YjUtW3dh585dqe7PTpHNG3J5xXLUqd6SXk/15p0hqX9lvda3F5998jV1a7TiyJFj3HnPrZ59QUFBvN63F4sWLL9YYSd1ccdyzLScmqF5qGoMzpw7T7iDWAaLyGARWe1O2/0wgIg0FpGlIjJJRH4VkWGJpToRaSEiK0RknYhMEJH87vadItLX3b5ZRK5xtxcTkbkisl5EPsNrmgMR6SYiq9wS5GciEuxuPyEib7klypUiUkpE6gE3A4Pd9BVFpKcb3yYRGXsx72XNapUpVDCw5nm6stpVRO2MYt8/+4g7G8fSaUu5sUWdJGmOHjzK1k1biYtLOorB4ZjD/PXLXwDE/hvLrm27KBZWLMtjrFT9Onbt2M2ef/YSdzaO2ZPn07hlgyRpmrRswLTxswHYvG4LBQrmp3hJJ5bYk7EAhISGEBISAurMkLFiySri4533tGntL5QML5HlsQNUrHYF+3ZGsX/XPuLPxrFy2nJuaF47SZpjB4+yY9M24s8mvcf58l/CNTdex5Kx8wGIPxvHyWMnsyXO9LRv35JvRn8PwM+r1lGocCHCwkqmSLdhwxb+/vviZ7gArdpGMmGM84Ng7ZqNFCxUkJKlUv6b1m9Yh2mT5wAw/rvJtG7bzLPvgYe7MX3KXA7s9888fZpw1ufFH3J8hgagqttx3ktJoAfOqMy1gFrAgyJyuZu0NvAcUBmoCNziVhW+BjRT1RrAGuBZr9MfcLd/CvRyt/UBlqtqdZwRocsCiMi1QGfgJlWtBsQDd7nH/A9YqapVgaXAg6r6k3v8826J8y/gJaC6qlYBAqvuzw+KhRXjwN79nvWDUQcoVirzmVLJMiWpeH0F/lj/R1aG55w7vATRe/d51mOi9lMqWeZTMrwE+7zS7Iva78mggoKCGDf/Kxb9MoOVS1ezef2vKa7RsWs7fly4MstjBygSVoxDUQc964eiDlIkrKhPx5YsW4pjB4/x0LtP8ObMd+kx6DHyXpI3W+JMT+mIMHbvOjezyJ7dUZSOCKyJTsPDS7Fnz7nB4qP2RhMeUSpJmqJFC3Ps6DHPD5m9e6MJD3cy5rDwkrRu15yvR17U37lJWQntokksJbXAmXJgA/AzUAy40t23SlW3q2o8MAaoD9TBqfL70T2mO1DO67yJ9VhrgfLu64bAtwCqOgM47G6PBG4AVrvnigQquPvOANNTOVdym4DRItINSDESqIg8JCJrRGTNiFFj0jhF7iGpTPGnmrmJuvNdmo+XP3uFz/t+TuyJ2CyK7ByfYkwlUWKahIQEOje7lxbVO1Kp+rVccU2FJOkeeKo78XHxzPhhTpbFnCS0VLb5eouDg4MpX6kCC76dw+ttenH65CnaPXZLlsbnC0nn/gYMHz4nqb8P5/9vDnyF/n3eJcGfHTMCvA0tV/RyFJEKOKWhGJyPzZOqOidZmsaknO1U3fTz0hn5+bT7/3iS3q/U/loE+FpVX05l31k99+lNfi5vbXEyzJuB10XkelX1ZGzes8BmZjr0nOpA1EGKR5wr7RQLL86hGN+rW4JDgnn5s1dYPGkxK2avyI4Q2bd3P2Fev7RLhpcgJvpAkjQxe2Mo5ZWmVHgJ9idLc/zYCVb/tJ56TW5k2+/bAWh/R2saNr+Jh25/MltiBzgUfZCi4edKvUXDi3Fkn2/3+FD0QQ5FHeSvDVsBWDVzBe0vUob26CPd6dHDqQBZs2YDZS6L8OwrXSacvVH70jr0ornvgTvp1v12ADas30zp0uGefeERYURHxSRJf/DgYQoWKkhwcDDx8fFERIQRHe2kqVa9EsNGDgGgWLHCNGvRkPi4OGbNWHCR3g0BPzhxji+hiUgJYBjwkZthzAEeFZFQd/9VIvI/N3ltEbncbTvrDCwHVgI3icgVbvpLRSSjblpLcasSRaQ1kNhdagFwm4iUdPcVFZFyqZ/C4zhQwE0fBFymqouAF4DCQPZ1bcsBtm78k4jLIyh1WSlCQkNo2L4hq+b97PPxPQc/xa5tu5gyYnK2xbhlw2+UrVCG0mXDCQkNoVXHZiyZm7TRfvHc5bS/oxUAlWtcz4nj/3Ig5iBFihX29F7Mmy8PdRrUZOe2vwGn5+R9T3Tjqe4vcCr2NNll+8ZthF0eTonLShIcGkKd9vVZN2+1T8ce3X+EQ1EHCKvgZCbX31SFPVsvToeLT4d9Tc1aLahZqwVTp87h7rucHrA31q7BsaPHPBmBP3054jsiG3QiskEnZk1fwO1dnR6iN9SsyvFjx4nZtz/FMT8u+5n2HZ0ejHfc2ZHZM50Mq1aVZtSqEkmtKpFMmzKXF5/rd3EzM7ASWja5xK3SC8WplvsGGOLuG4FTnbdOnPL7fpyehAArgIE4bWhLgUmqmiAi9wJjRCSx8v814M90rt/XTb8OWAL8A6Cqv4rIa8BcN3M6izOfz9/pnGss8LmI9AS6AF+ISCGc0t57qnoko5uRVZ7vM5DV6zdx5MgxIjt247Eed3Nrez90DfaSEJ/AsNeH0febfgQFBzF/3Dz++fMfWnVrDcDsb2dRuERh3pv+Ppfmv5SEhARu7tGBxyIf5fJrL6fprU3Z8dsOPpg1FIBR74xi7aI1WRpjfHw8A14Zwqdj3iMoOJjJY6bz1x87uP2ejgBMGDWZZfN/on5kXaavnMCp2FP0fvotAIqXLEb/oa8TFBxEUFAQc6cuYOm8nwB4+e3nyJMnlGHj3gdg89ot9H9xcJbGDs49HtV7BM+P6k1QcBBLxy9gz9ZdNL2rBQALR8+lUInC9Js2mEvyX0JCgtLy/na82Kwnp07EMqrPCB794GlCQkPY/88+hvf6KMtjzMjMWQto1aopf/z2IydjY3nggXPN4NOmjOKhR54nKmofTzx+P72ee4ywsBKsXzufWbMX8vAjz1+UGOfPXUJki4b8vGEusSdP8dTjr3j2jZ7wGc8++Tr7omPo3+ddPhs5hJdee4rNm37ju1HfX5T4fBLgz6FJwNUzZxO3yrGXqrbzcyhZJidWOd5So6e/Q8iUf874pzfZhaiSN7A6Q/hiTJTvpe5AUOySwOoN7It9R39Prbk0U079ONrn75x8N911wdfLrJxaQjPGGHOxBXgJ7T+ToanqYmCxn8Mwxpgcy+kgHrj+MxmaMcaYC2QlNGOMMbmCjbZvjDEmV7ASmjHGmFwhPsXgRQHFMjRjjDG+sSpHY4wxuYJVORpjjMkVLEMzxhiTK1iVozHGmFzBOoUYY4zJFazK0RhjTK5gVY7GGGNyBSuhmeyS06ZiAZi4bqi/Q8iU8Aqt/B1Cps27PtTfIWTa7CM5ax7bvME57x5niSzM0ESkFfABEAyMUNWByfYXAr4FyuLkVe+q6pfpnTPHz1htjDHmIlH1fUmHiAQDHwOtgeuAriJyXbJkjwO/qmpVoDHwfyKSJ73zWgnNGGOMb+KyrJdjbWCbqm4HEJGxQAfgV680ChQQEQHyA4eAdAOwEpoxxhjfaILPi4g8JCJrvJaHvM5UGtjltb7b3ebtI+BaYC+wGXhKNf1eKVZCM8YY45tMtKGp6nBgeBq7JbVDkq23BDYATYGKwDwRWaaqx9K6ppXQjDHG+CaL2tBwSmSXea2XwSmJebsPmKiObcAO4Jr0TmoZmjHGGN8kJPi+pG81cKWIXO529OgCTE2W5h8gEkBESgFXA9vTO6lVORpjjPFNFnXbV9U4EXkCmIPTbX+kqm4RkUfc/cOAN4GvRGQzThXli6p6IL3zWoZmjDHGJxofn3XnUp0JzEy2bZjX671Ai8yc0zI0Y4wxvrGRQowxxuQKNpajMcaYXCEhw96LfmUZmjHGGN9YlaMxxphcIQs7hWSHbH0OTUQ6iYiKSLoPw2Vwjq9E5Db39YhUBrC8ICLySrL1E1l5/kBTo1ENPl00jM+WDue2x25Lsb9MxTIMnvQuE7dOotNDnTzbi4cX562xb/PJgk/5eP7HtL//5osZdppee3sIDdt2oWO3R/wdCm+/8xqrNsxjyU9TqVI19Y9p2XJlmLNwAqvWz2XEl+8TGuqM2n5T/dps37WWRcunsGj5FHq9+LjnmA8+fpvf/lrBspXTsy32PLVqU/Srbyg6ajSXdrkzxf7QqtUoPmUGRT4bQZHPRnDp3d0BCC5zmWdbkc9GUHzqTC65JeXnKqu8PehVVq2fy+If07/HsxeM5+d1c/j8y/c89zhRtRqViT70K+07tASg4hWXs2jZZM+yfddaHn60e5bF3HfASyxdM4M5y36gUpVrU01zWdnSTJk3miWrp/PxF4MJDXXKGhWvvJxJc75la9RaHnoiaUz3P3wX836cyPyfJtHjkW5ZFm+6su45tGyR3Q9WdwWW4zw0d8FU9QFV/TXjlJnySsZJcoegoCAe6f8ob3Tvw+ORj9Hw5kZcduVlSdIcP3Kc4X0+Y9LwiUm2x8fHM7L/FzwW+Si9OvSi7T1tUxzrDx3bNGfYkP7+DoNmLRpRoWJ5aldrzrNPvc7g9/qmmq53314M+/graldvwZEjR+l2z7kv/5Ur1tCkfgea1O/Au4M+9mwfO3oinW/pkX3BBwVRoOfTHHn5BQ7d3528TSMJLlcuRbKzv2zi8MMPcPjhBzj5zdcAxO/e5dl2+NGH0NOnOL18WbaE2ax5Q+ceV2/Bc0+9zjtD3kg1Xe++vRj2yVfcWKMlR44c4y6vexwUFETvvr1YtGC5Z9tf23bQpEFHmjToSGSjW4iNjWXG9HlZEnOTZg0oX7EcDWu25aVn+vLW/72WarqX33iGEZ9+Q6Na7Th65Bidu90CwJHDR+nz0gCGf/RVkvRXXXsFXe+5lfbN7qRlg9uIbNGI8hXKZknM6UpQ3xc/yLYMTUTyAzcBPXAzNBFpLCJLRWSSiPwqIsNEJMjdd0JE/k9E1onIAhEpkco5F4tITfd1KzftRhFZ4G6rLSI/ich69/9Xu9vvFZGJIjJbRLaKyDvu9oHAJSKyQURGJ7tWY/d634vI7yIy2h31GRGp5Z5/o4isEpECIpJPRL4Ukc3u9Zt4XXuyiEwTkR0i8oSIPOumWSkiRd10Fd341orIsgsp1ablympXEbUzin3/7CPubBxLpy3lxhZ1kqQ5evAoWzdtJS4uadXC4ZjD/PXLXwDE/hvLrm27KBZWLKtDzLSa1SpTqGABf4dB6zaRjB8zCYC1qzdSqFABSpVK8RGmQaO6TJ08G4CxYybRul2zDM+94qc1HD58NGsD9hJyzbXE7dlDQlQUxMVxetFC8tarn+nz5Kleg/i9e0mI2ZcNUUKrtpGMGzMZgLVrNlKoUMFU73H9hnWYNnkOAOO+m0SbtpGefQ8+fDfTp8zhwP6DqV6jYeO67Nyxi927ko/CdH5atGnCD2OdATDWr9lEwYIFKFmqeIp09RrUZuYUJxP9fuxUWrZtCsDBA4fYtH4LcclGub/yqgqsW7OJU7GniI+PZ+VPa2jl9T6zTSYGJ/aH7CyhdQRmq+qfwCERqeFurw08B1TGGXDyFnf7/4B1qloDWAL0SevEbmb3OXCrO1fO7e6u34GGqlod6A287XVYNaCze93OInKZqr4ExKpqNVW9K5VLVQeexpmvpwJwkztMyzickZ+rAs2AWJy5e1DVyjgl069FJJ97nkrAne57fws46ca4ArjHTTMceFJVbwB6AZ+k9f7PV7GwYhzYu9+zfjDqAMVKZT5TKlmmJBWvr8Af6//IyvBytPCIUuzZHe1Z37tnH+ERpZKkKVq0CEePHiPebYfYuyea8PBzaWrWrsbiH6cy9ocRXH3NFRcncCC4eHES9sd41hP27yeoeMov3dDrrqfI8C8oNOAdgsuVT7E/b5NITi9ckG1xhoeXYu8er3u8N5qwVO7xMe97vDeaMPceh4WXpE27Znw1cmya1+h0S1smfp91Vbth4SWJ8oo5eu8+wsJLJklTpGhhjh097ok5am90ijTJ/fHbVm6sewOFixQi3yX5aNK8AeGlw7Is7jQFeAktOzuFdAXed1+PdddnAKu85sAZA9QHvgcScDIKcGYpTVrnlVQdYKmq7gBQ1UPu9kI4GcmVOCM3e1eeL1DVo+51fwXKkXT6gtSsUtXd7jEbgPLAUSBKVVe71z7m7q8PfOhu+11E/gaucs+zSFWPA8dF5Cgwzd2+GajilmbrARPcQiBA3tQCcqdgeAigcpHKlMvvezWDpDK+tWY8iGgS+S7Nx8ufvcLnfT8n9kRspo7NzSSVm5v83qZ3/zdu3EL165vw778nadaiEd+M+YTa1TM1SMIFSC2wpKtxW//kYNfO6KlY8tS+kUL93uJQd6/fgCEh5K1XjxNfpDW4ehZEeYH3+K2Br9Kvz7skpNG+ExoaSss2Tenf9/8uPNh0Akr+J5f6+0r/tNv+3MGnQ0cyeuJwTv4by2+//OHJELOT/hd7OYpIMZwh/yuJiOKM1aU4w5wk/6dK658uvX9SSWP/mziZRycRKQ8s9tp32ut1PL6999SOSevaqU2HkNp5ErzWE9xzBgFHVLVaRgF5T8nQvmy7TOVGB6IOUjziXBVNsfDiHIo5lM4RSQWHBPPyZ6+weNJiVsxekZlL50r3P3gXd3e/A4AN6zZTusy5X8gRpUsRHRWTJP3Bg4cpVKggwcHBxMfHE1E6jOhoJ82J4/960s2fu4R3/q8PRYsW4dChw9n+PuIP7CeoxLkSQVCJEiQcTDpknp486Xl9ZtXPyFPBSMFC6DGnKjRP7RuJ27oVPZy18d7/wJ2ee7x+/WYivEohERFh7EvlHhf0vscRYexz73HV6pUYPnIIAMWKFSGyRSPi4uKYNcMpVUY2b8imjVvYn0Z1pK/u6dGFrvfcCsCm9b8kKTmFRZTyxJPo0MHDFCxUwBNzuFfM6Rn37STGfetUc7/wWk+i9mZPVW8S/9FejrcBo1S1nKqWV9XLcIb+rw/UdkdYDsKpAkxsnQ1yjwOnem558pN6WQE0EpHLARLboXBKaHvc1/f6GOtZEQnNOJnH70CEiNRyr11AREKApcBd7rargLKAT3Vybilvh4jc7h4vIlI1EzH5ZOvGP4m4PIJSl5UiJDSEhu0bsmrezz4f33PwU+zatospIyZndWg50sjPR3s6ccycMZ87ujq9Qm+oVZVjx06wb9/+FMcsX7qSmzu2AqBL106eL9OSJc9V8VW/oQpBQUEXJTMDiPv9d0JKlyEoLMwpaTVpyumffkySJqhIUc/rkKuvAQnyZGYA+ZpGciobqhtHjvjO02Fj1vT5dO7aEYAbalbl2LHjqd7jH5f9TPuOTg/Gznd2YtbMhQDUrBLJDe4ybcocXnyur+f+A9xyW1smfT/jgmMe9cVYWje6ndaNbmfOjIXc2sXpEVy9ZhWOHztBzL6U4+uuWL6aNh2aA3Bbl5uZO3NRhtcpVtz5N4koHUards2Y+sOsC449Q//RKseuwMBk234AHsXJjAbitGUtBSa5+/8FrheRtTjVep3TOrmq7ner3ia6GWMM0Bx4B6fK8VlgoY+xDgc2ici6NNrRkl/7jIh0Bj4UkUtw2s+a4bR5DXNHho4D7lXV06lVJ6ThLuBTEXkNp6p0LLDR14N9kRCfwLDXh9H3m34EBQcxf9w8/vnzH1p1aw3A7G9nUbhEYd6b/j6X5r+UhIQEbu7RgcciH+Xyay+n6a1N2fHbDj6YNRSAUe+MYu2iNVkZYqY932cgq9dv4siRY0R27MZjPe7m1vYtL3oc8+YsplmLRqzeOJ/Yk7H0fOxlz74x33/OM0+8SnR0DP36vMvnX77Hy68/zeaNvzJ61AQA2ndsxX09uhIXF8+pU6d48L5nPMcPHzmEm+rXpmixImz6bSmD3h7K6G++z7rgE+I5/uH7FB70LhIUROysmcT/vZN87Zwv4lPTp5K3YSMuubmDMzjt6dMc7e/VizNvXvLcUJPj72VhVV0q5s1dQrMWjVi1YZ5zjx8/10F5zIThPP3ka+yLjqFfn8EMH/ker7z2NJs3/ea5x+m55JJ8NGpSj+ee7p2lMS+ct4wmzRuybO1MYmNP0euJc70cvxr3CS8+1Yd90fsZ8MZ7fDTiHZ5/5Um2bP6dcd86LS4lShZj+sJx5C/wPxISEujxyN1E1u3AieP/8tnXQyhStDBnz8bx+gtvcfRomvNeZp0Ar3KUzLahXNDFRBoDvVS1XSr7Tqhq/osWTC6Q2SrHQDBx3VB/h5Ap4RVa+TuETPu1Vri/Q8i069dEZ5wogFwSnMffIWTaP4c2+/zrOi3/9u7i83fO//qNveDrZZaNFGKMMcY3NjjxOaq6mKQdNbz3WenMGGMCmQ1ObIwxJjfQuMDu5WgZmjHGGN9YCc0YY0yuYG1oxhhjcgUroRljjMkN1DI0Y4wxuYJ1CjHGGJMrWAnNGGNMrmAZmjHGmNzgYg6VeD4sQzPGGOMbK6EZY4zJFSxDM9nlnzO+T84ZKHLa6PVR22f7O4RMe67myxknCjCxZ//xdwiZUixvQX+H4BcaZw9WG2OMyQ0COz+zDM0YY4xvAv3B6iB/B2CMMSaHSFDflwyISCsR+UNEtonIS2mkaSwiG0Rki4gsyeicVkIzxhjjmyyqchSRYOBjoDmwG1gtIlNV9VevNIWBT4BWqvqPiJTM6LyWoRljjPFJFlY51ga2qep2ABEZC3QAfvVKcycwUVX/AVDVmIxOalWOxhhjfKJx6vMiIg+JyBqv5SGvU5UGdnmt73a3ebsKKCIii0VkrYjck1F8VkIzxhjjm0xUOarqcGB4GrsltUOSrYcANwCRwCXAChFZqap/pnVNy9CMMcb4JAvn99wNXOa1XgbYm0qaA6r6L/CviCwFqgJpZmhW5WiMMcY3CZlY0rcauFJELheRPEAXYGqyNFOABiISIiKXAjcCv6V3UiuhGWOM8UlWldBUNU5EngDmAMHASFXdIiKPuPuHqepvIjIb2ISTRY5Q1V/SO69laMYYY3yicVl4LtWZwMxk24YlWx8MDPb1nJahGWOM8UkWtqFlC8vQjDHG+CTQMzSfO4WISJiIjBWRv0TkVxGZKSJXZWdw7nXfEJFe7ut+ItIsi8//tNvgmLi+U0SKZ+U1/K1ekxuZsnwM01aM5/4n7k41zYv9n2HaivFMWDiKayo7/6x58uZh9KwRjF/wNROXfMujz/fwpH+m9+NMXjaGCQtH8d7IARQomD9LY377nddYtWEeS36aSpWq16Wapmy5MsxZOIFV6+cy4sv3CQ0NBeCm+rXZvmsti5ZPYdHyKfR68XHPMR98/Da//bWCZSunZ2m8mfHa20No2LYLHbs94rcYkru2UVVeXfAery/+gGaPdkixv2aH+rw46x1enPUOz/zQj4hry3n23fnOI7y1ZjgvzXk32+Mc/G4fNm5exMqfZ1G12vWppilXrgyLlkxiw6aFfD3qQ8/n4qmnH+KnlTP4aeUMVq2ezdHj2yhSpBB58+Zh8dLJrFg5k9Vr5vDqa09fUIz1m9Rl1k/fM+fniTz4ZPdU07z61nPM+XkiUxZ/x3WVr87w2GsqXcXYmSOZtHA038/9msrVnb+JytWvY9LC0UxaOJrJi0bTrE3jC4o9Qyq+L37gU4YmIgJMAharakVVvQ54BSiVncElp6q9VXV+Fp/2aeDSjBLlVEFBQbwyoBeP3fkcnRreSatOzahwVfkkaepH1qVshTK0r3sH/XoN4rVBzwNw5vQZHrj1Se6I7M4dkd25qUkdKtdwvkRWLlnNrY27cXvTe/h7+y569MzwmUefNWvRiAoVy1O7WnOefep1Br/XN9V0vfv2YtjHX1G7eguOHDlKt3tu8+xbuWINTep3oEn9Drw76GPP9rGjJ9L5lh6pne6i6dimOcOG9PdrDN4kSLi93/0Mu3cAbzd/lhtuvomwK5I+43pwVwxDO/dlUOsXmP3hRLoMeNCz7+fvl/Bp9wHZHmeLlo2peEV5qlZuwpNPvMz7H6R+D9/s/xIff/gF1ao05ciRo3S/9w4APnh/OPXqtKVenbb06TOY5ct+5vDho5w+fYa2re+kbp021K3TlmbNG1GrVrXzijEoKIjeg17gwa5P0a7+HbS9pQUVr7o8SZqGkfUoV6EsLW+8hd7PvU2fd17K8Njnez/Jx++OoFPTuxg66DOe790TgK2//8Vtze+hU9O7eLBzT/oOfpng4ODzit0XmuD74g++ltCaAGe9G+xUdQOwXEQGi8gvIrJZRDoDiEh+EVkgIuvc7R3c7eVF5HcR+VpENonI94mlI7dkNEhEVrnLFcmDEJGvROQ293UtEflJRDa66Qu451/mXnediNRz0zZ2nzb/3r3+aHH0BCKARSKyKNm1yovIbyLyuTsw5lwRucTdd4WIzHevvU5EKrrnS+1eNBaRJSIyXkT+FJGBInKXG/NmEanopishIj+IyGp3ucn3f8a0Vap+Hbt27GbPP3uJOxvH7MnzadyyQdJ/3JYNmDbemfdr87otFCiYn+IliwEQezIWgJDQEEJCQsCdgn3FklXEx8cDsGntL5QML5EV4QLQuk0k48dMAmDt6o0UKlSAUqVSnr9Bo7pMnezEPXbMJFq3y7jwvuKnNRw+fDTLYj0fNatVplDBAn6NwVu5alew/+99HNwVQ/zZeNZN+4nKLWolSbNj3Z/EHvsXgJ3rtlI4rJhn31+rfuPk0RPZHme7ds0ZM3oiAKtXb6BQoYKUCkv5uWjUqC6TJs0CYPS3P9CuXYsUaW6/vT0TJkzzrP/770kAQkNDCA0NSfGEr6+q1Lief3bsYvffezh7No6Zk+YR2apRkjSRrRsxZfwMADau/YWChQpQomSxdI9VVfIX+B8ABQrmJyZ6PwCnYk97/g7z5MuLnnfkvtEE8XnxB18ztErA2lS23wJUw3nYrRkwWETCgVNAJ1WtgZMZ/p9bygO4GhiuqlWAY8BjXuc7pqq1gY+A99MKxn1uYRzwlKomXjsWiAGau9ftDAz1Oqw6TmnsOqACcJOqDsV5mK+JqjZJ5VJXAh+r6vXAEeBWd/tod3tVoB4Qlc69wN32FFAZuBu4yn2fI4An3TQfAO+pai33OiPSev+ZUTK8BNF793nWY6L2UypZ5lMyvAT7vNLsi9rvyaCCgoIYN/8rFv0yg5VLV7N5/a8k17FrO35cuDIrwgUgPKIUe3ZHe9b37tlHeETSyoCiRYtw9Ogxzx/z3j3RhIefS1OzdjUW/ziVsT+M4OprUvw2Ml4KlyrKkb0HPetHog5SqFSRNNPX7dyE3xZvuAiRJRUeUYrdu6M863v3RBEREZYkTbFiRTji9bnYsyeaiGSfnUsuyUez5o2YMnmWZ1tQUBA/rZzBjr/XsHDBctas3nBeMZYKK0HUnnN/S9FR+1L8vZUKK0GU199b9N4YSoWXTPfYt18bwvN9erJo/XReeOMphrx1rtahSo3rmbZ0HFOXjOGN5wd63nt2SIgXnxd/uNAHq+sDY1Q1XlX3AUuAWjjDmrwtIpuA+ThjdCV+qnap6o/u62/dcyQa4/X/uulc92ogSlVXA6jqMVWNA0KBz0VkMzABJ/NKtEpVd6tqArABKO/D+9vhlkTBydDLi0gBoLSqTnKvfUpVT6ZzLwBWq2qUqp4G/gLmuts3e8XRDPhIRDbgPGBY0L1WEt7jox08uS/57hQklc+VqmaYKDFNQkICnZvdS4vqHalU/VquuKZCknQPPNWd+Lh4ZvwwJ8NYfCXpxJNOyJ40Gzduofr1TWh8082M+OwbvhnzSZbFliuler9TT3pl3eup07kpUwaOzuagUvLtc5FxmjZtIlm5cm2SknpCQgL16rTl6ivrUrNmVa677jy7B/hw/TTTpHNs13tvZWDvITSp3o4Br79H//df96TZtG4L7Rt25vYW3Xmo573kyZvn/GL3QW6pctyCM6ZWcmllw3cBJYAbVLUasA/I5+5L/qeiPrxO7bqp7X/GvVZVoCbg/S972ut1PL718EztmLTec3o/SbzPk+C1nuAVRxBQV1WruUtpVT2e/ESqOlxVa6pqzWKXZtyEuW/vfsK8fqGWDC9BTPSBJGli9sZQyitNqfAS7E+W5vixE6z+aT31mtzo2db+jtY0bH4TLz/+RoZxZOT+B+/ydOKIjoqhdJlzv7wjSpciOirpQNsHDx6mUKGCnvaCiNJhREc7aU4c/9dThTR/7hJCQkIoWjTtEsd/3ZHogxSOOFeFWDi8GMdiDqdIF3FNWboOfIjPHxzMySPZX8UI8NDDd3s6ckRFxVCmTLhnX0TpcKKikv6oO3DgEIW9PhelS4cRleyzc9vt7ZkwPvmgFI6jR4+zbNlKmjVvlOr+jOyLiiG89Lm/pbDwUin+3vZFxSSpcQiLKElM9P50j+3YuR1zpzutIrOnzqdK9ZQdpbZv3UnsyViuuqbiecXui9xS5bgQyCsinpZgEakFHAY6i0iwiJQAGgKrgEJAjKqeFZEmQDmvc5UVkcTSV1dgude+zl7/X5FOPL8DEW4MuO1nIe51o9xS2N04T6Bn5Djgc4OGqh4DdotIR/faed12wKWkfi98NRd4InFFRKpl4tg0bdnwG2UrlKF02XBCQkNo1bEZS+YuT5Jm8dzltL+jFQCVa1zPieP/ciDmIEWKFfb0XsybLw91GtRk57a/Aafn5H1PdOOp7i9wKvY0F2rk56M9nThmzpjPHV07AXBDraocO3aCffv2pzhm+dKV3NzRibtL107MmrEAgJIlz3VSrX5DFYKCgjh0KOUXtHH8s/EvSpQPo2iZEgSHBlOjfT02z1uTJE2RiGL0GPYc3zzzMft3RKVxpqw3/LNvPB05pk+bS9e7bgGgVq1qHDt2nH3RKT8XS5eupFOn1gDc1e1WZsyY59lXsGABbqp/IzOmn9tWvHhRChVyvgLy5ctLkyb1+fPPv84r3s3rf6VchbKULhtBaGgIbTo1Z+GcpUnSLJy9lA53tAWg6g2VOH7sBPtjDqZ7bEz0fmrXqwFAnQa1+Hu7M1B96bIR537UlQnj8ivKsXtX8iERs46q74s/+PQcmqqqiHQC3hdnZtFTwE6cNqn8wEacEtMLqhotIqOBaSKyBqd673ev0/0GdBeRz4CtwKde+/KKyM84GW3XdOI543a6+NDtqBGLU2X3CfCDiNwOLAL+9eHtDQdmiUhUGu1oqbkb+ExE+gFngdtxeoHWJeW9uMbHc/YEPnaraUNwMsgL7tcdHx/PgFeG8OmY9wgKDmbymOn89ccObr+nIwATRk1m2fyfqB9Zl+krJ3Aq9hS9n34LgOIli9F/6OsEBQcRFBTE3KkLWDrvJwBefvs58uQJZdi49wHYvHYL/V/0+YH+dM2bs5hmLRqxeuN8Yk/G0vOxlz37xnz/Oc888SrR0TH06/Mun3/5Hi+//jSbN/7K6FETAGjfsRX39ehKXFw8p06d4sH7nvEcP3zkEG6qX5uixYqw6belDHp7KKO/+T5L4vbV830Gsnr9Jo4cOUZkx2481uNubm3f8qLG4C0hPoHve4/ksVGvEBQcxMrxi4neupub7nI62fw4ej6tet7G/4rk5/b+Tg/RhLh43r35FQC6D+3JFXWuI3+RAvRb8Qkz35vAyvGL0rze+ZozexEtWzZh0y+LiT0ZyyOPvODZ98OkkTz+2EtER8Xw+msD+WrUh7ze5zk2bfyVr78a70nX/uYWLFywjJNuZyeAUmElGf75uwQHBRMUJEycOIPZsxaeV4zx8fG8+dI7fDFuKEHBwfzw3VS2/bGdzt2djHjc1xNZMv9HGja7ibmrJnHq5CleeapfuscCvP7cW7za/zmCQ4I5feoMvZ97G4AbbqzKg0/eS1xcHAkJCfR9cRBHDmVfpyd/lbx8JSnqd7PzYiLlgemqWimVfTuBmqp6IPk+k7qqYfX89Dvo/O05mbP+eaO2z/Z3CJn2XM2XM04UYEbGZKYyw//K5M95j6r+HrP6gnOjHVWb+/ydc/nGeRc997ORQowxxvgk0EtoFzVDU9WdOI8ApLav/MWMxRhjTOaon0YA8ZWV0Iwxxvgk0MdytAzNGGOMTxKshGaMMSY3sCpHY4wxuYK/hrTylWVoxhhjfGK9HI0xxuQK1oZmjDEmV7A2NGOMMbmCv8Zo9JVlaMYYY3xiVY7GGGNyhQTrFGKMMSY3sBKayTZV8oZlnCjAzLs+1N8hZEpOHLn+/9YM8HcImbas0t3+DiFTjsXFZpwoF7JOIcYYY3IFK6EZY4zJFQK8k6NlaMYYY3wTnxDk7xDSZRmaMcYYnwT47DGWoRljjPGNEthtaIFdfjTGGBMwEtT3JSMi0kpE/hCRbSLyUjrpaolIvIjcltE5rYRmjDHGJwlZVEITkWDgY6A5sBtYLSJTVfXXVNINAub4cl4roRljjPGJIj4vGagNbFPV7ap6BhgLdEgl3ZPAD0CML/FZhmaMMcYn8YjPSwZKA7u81ne72zxEpDTQCRjma3yWoRljjPFJQiYWEXlIRNZ4LQ95nSq1HC95y9v7wIuqGu9rfNaGZowxxieZ6bavqsOB4Wns3g1c5rVeBtibLE1NYKyIABQH2ohInKpOTuualqEZY4zxSRZ2218NXCkilwN7gC7AnUmupXp54msR+QqYnl5mBpahGWOM8VFWzR6jqnEi8gRO78VgYKSqbhGRR9z9PrebecsxGZqInFDV/Nl8jWeAAUApVT2andfKII5XVPXt7Dh35UbVubvP/QQFB7F47Hymfzopyf7wiqV58N0nKH99Bb5/9ztmDp/i2XdpwUvpMehxylx1GQqMeP4jtq37MzvCTCJPrdrkf/xJCAri1MwZnBz7XZL9oVWrUajfW8RHRwFwevkyTn7zNcFlLqPg63086YLDI/j3q5HETvw+W+O9tlFVbul9L0HBQawYt5D5n05Jsr9mh/pEPnIzAGdOnmLca1+w97e/AbjznUe4vmkNjh88xsCWvbI1Tl+99vYQlv64iqJFCjP52/P6nskS9ZrcyPNvPk1QcBCTR0/jy4++TZHmhf5Pc1NkXU7FnqLPU2/x++Y/yZM3D19M/pg8eUIJDglh/vRFDBv8BQADP+tH+YplAShQKD/Hj56gS7N7zyu+3m8/T+Nm9YmNPcULT/Zhy6bfU6QpUzaCDz4fQOEihdiy6Xeee/Q1zp6NS/f4hk3r8frbvQgOCmbct5P4bOhXnvPd80Bn7n6gM3Fx8Syet5xBfT+gcJFCfPzlO1Sudj0/jJ1G35cGndf7SU1WddsHUNWZwMxk21L9gKnqvb6cM8dkaBdJV5yicCfgKz/G8QqQ5RmaBAXR/c0HGXRXXw5FH6Tf1HdYN381e7fu9qT598gJvunzBTe0rJ3i+G59erBpyXo+fHQwwaEh5L0kT1aHmFJQEAV6Ps3hF54jYf9+inzyGadX/Ej8338nSXb2l00cfTXpVC/xu3dx+OEHPOcpNu57Ti9flq3hSpBwe7/7+bjbWxyJPkivqQP4Zd4aorft8aQ5uCuGoZ37EnvsX65tXI0uAx5kSMfXAPj5+yUs/XoO3YY8nq1xZkbHNs2589abeeXNd/0WQ1BQEC8NeI5H73iafVExjJ49giVzl7P9z52eNPUj61K2Qhk61O1M5RrX88qgXtzT5iHOnD7DQ7f2JPZkLCEhwYyc+ik/LljJ5nVbeOnh3p7jn33jCU4c+/e84mvc7CbKVyhL09odqHZDZfoNfplbW3ZPke6F3j35cthopk+ay5vvvsLt3Try3Zffp3l8UFAQbwx6ke63PUb03n1MmvctC2YvYdufO6hTvybNWjembcPOnDlzlmLFiwBw+vRphgz4lKuurchV11xxXu8nLT73zvCTHN3LUUSqichKEdkkIpNEpIi7/UERWS0iG0XkBxG51N3+lYgMFZGfRGS795PnIlIRyA+8hpOxJW6/V0Qmi8g0EdkhIk+IyLMist69dtEMYlksIjXd18VFZKfXeSeKyGwR2Soi77jbBwKXiMgGERmdlferYrUr2Lcziv279hF/No6V05ZzQ/OkGdexg0fZsWkb8WeTfnTz5b+Ea268jiVj5wMQfzaOk8dOZmV4qQq55lri9uwhISoK4uI4vWgheevVz/R58lSvQfzevSTE7MuGKM8pV+0K9v+9j4O7Yog/G8+6aT9RuUWtJGl2rPuTWPeLc+e6rRQOK+bZ99eq3zh59ES2xphZNatVplDBAn6NoVL1a9m1Yzd7/tlL3Nk45kxeQOOWDZKkadSyPtPHzwZg87otFChYgOIlnXsbe9KZvywkNISQkBBUUw5l0bx9U2ZPmnde8TVr3ZhJ46cDsGHtZgoWKkCJUsVTpKvboBazpi4AYOLY6TRv3STd46vWqMTfO3az6+89nD0bx/RJc2jWujEAd957G8M++JIzZ84CcPDAYfe9nmLtzxs4c+rMeb2X9CSI+Lz4Q47O0IBRON06qwCbgcT6pYmqWktVqwK/AT28jgkH6gPtgIFe27sCY4BlwNUiUtJrXyWcBsvawFvASVWtDqwA7skglvRUAzoDlYHOInKZqr4ExKpqNVW9y4dz+KxIWDEORR30rB+KOkiRsKI+HVuybCmOHTzGQ+8+wZsz36XHoMfIe0nerAwvVcHFi5Ow/9wzlQn79xNUPOUXReh111Nk+BcUGvAOweXKp9ift0kkpxcuyM5QAShcqihH9p67x0eiDlKoVJE009ft3ITfFm/I9rhyupLhJdi399znYF9UDCXCS6RIE50sTUk3TVBQEGPnf8WCX6azculqflmfZEAKatSpyqEDh/lnx27OR6nwkuzdc+7HUvTeGMKSxVekaGGOHz1BfHy8m2afJ01ax5cKL0HU3ugk20uFO19Nl1csR626Nfhhztd8N/VzKle/7rxizwzNxOIPOTZDE5FCQGFVXeJu+hpo6L6uJCLLRGQzcBdwvdehk1U1wR1ipZTX9i7AWFVNACYCt3vtW6Sqx1V1P3AUmOZu3wyUzyCW9CxQ1aOqegr4FSjnw/v2PNux9cQOHy7hdWwq21L5oZqq4OBgyleqwIJv5/B6m16cPnmKdo/dkqnrn59Uok4Wc9zWPznYtTOHH+pB7KQfKNTvraQJQkLIW68ep5YuzrYoPVL5ZZrWPb6y7vXU6dyUKQOztCCeO6X2iz/ZjZVU772TJiEhgS7N7qVl9U5Uqn4dFa+5PEm6Vp2an3fpzMfw0kij6R6f2ntKPHFISDCFChXg1pbdGdjnfT4ckXVtZWnJzHNo/pBjM7QMfAU8oaqVgb5APq99p71eC4CIVAGuBOa5VYJd8Kp2THZMgtd6Ahm3Q8Zx7j7nS7bP+7zxPpwLVR2uqjVVteaV+S/PKHkSh6IPUjT8XPVW0fBiHNl3yOdjD0Ud5K8NWwFYNXMF5StVyNT1z0f8gf0ElThXWA4qUYKEgweSpNGTJ9FTTpXSmVU/IyHBSMFCnv15at9I3Nat6OHD2R7vkeiDFI44d48LhxfjWEzK60ZcU5auAx/i8wcHc/JIYFUxBqKYvTGUijj3OSgVXpL90Uk/B/v2xhCWQZoTx06w5qd11GtSx7MtODiYpm0aMWdK5krw3e6/g2mLxjBt0RhiovcTUfrc7+OwiJLsi96fJP2hg0coUCg/wcHBbppS7HPji94bk+rx0XtjCI8IS/W80XtjmDNjIQCb1m8hISGBosUKZ+o9ZFaC+L74Q47N0NxeiIdFJLEi/W4gsYRUAIgSkVCcElpGugJvqGp5d4kASotIhiUmH2LZCdzgvs5wtGjXWTf2LLV94zbCLg+nxGUlCQ4NoU77+qybt9qnY4/uP8KhqAOEVYgA4PqbqrBn664Mjrpwcb//TkjpMgSFhTklrSZNOf3Tj0nSBBU5V20acvU1IEHosXOdVPM1jeTURahuBPhn41+UKB9G0TIlCA4Npkb7emyetyZJmiIRxegx7Dm+eeZj9u+Iuihx5XRbNvxO2QpliCgbTkhoCC07RrJ47vIkaZbMXU67O1oBULnG9Zw4foIDMQcpUqww+Qs6HaTz5svDjQ1qsXPbuU5FNzasyc5tfxMTlTQDysi3I8fTvklX2jfpytyZi+l0RzsAqt1QmePHTrB/34EUx6xcvobWN0cCcEuXdsyftRiA+bOXpHr8pvVbKF/hMsqUjSA0NIR2nVqyYLbz1TJ31iLqNnDaZ8tXLEuePKEcOngkU+8hs7Jw6KtskZN6OV4qIt4V3EOA7sAwt9PHduA+d9/rwM/A3zjVghm1aHcBWifbNsnd7msvgrRieRcYLyJ3Awt9PNdwYJOIrMvKdrSE+ARG9R7B86N6ExQcxNLxC9izdRdN72oBwMLRcylUojD9pg3mkvyXkJCgtLy/HS8268mpE7GM6jOCRz94mpDQEPb/s4/hvT7KqtDSC5rjH75P4UHvIkFBxM6aSfzfO8nXzun2fmr6VPI2bMQlN3dA4+Ph9GmO9u977vi8eclzQ02Ov/d/2R8rzj3+vvdIHhv1CkHBQawcv5jorbu56a5mAPw4ej6tet7G/4rk5/b+TtNuQlw87978CgDdh/bkijrXkb9IAfqt+ISZ701g5fhFFyX2tDzfZyCr12/iyJFjRHbsxmM97ubW9i0vagzx8fEMeuU9PhkzhKDgYKaMmc72P3Zw2z0dAfh+1GSWz19B/ci6TF05nlOxp3jjaaejcPGSxeg39DWCgoMICgpi3tSFLJv3k+fcLTs2Y/ak+RcU3+J5y2ncrD4LV0/hVOwpXuz5hmffF2OG8vIz/YiJPsA7/YbywecDePblx9my+XcmjJ6c7vHx8fH0fWkQX034mKCgIL7/bipb/9juvOfRUxg49A1mLRvPmbNnef6Jc832S9ZNJ3+B/xEaGkrzNo2597bHLuj9JfJXyctXklpvH5Mz3F3ulhz3j/d/VxzMOFEA6f9XWMaJAsz/rRng7xAyrXalu/0dQqYci4v1dwiZ9teBdRecHX1VupvP3zn37vn2omd/OamEZowxxo8C/Re0ZWjGGGN8EuhVjpahGWOM8Ym/uuP7yjI0Y4wxPom3EpoxxpjcwEpoxhhjcgXL0IwxxuQK1svRGGNMrmC9HI0xxuQKVuVojDEmVwj0CT4tQzPGGOMTq3I0xhiTK1iVozHGmFzBejmabDMm6md/h5Bps4/k93cImRJ79h9/h5Bpy3LYyPUAq375xt8hZMrV19zq7xD8IiHAszTL0IwxxvjEOoUYY4zJFawNzRhjTK5gvRyNMcbkCtaGZowxJlcI7OzMMjRjjDE+sjY0Y4wxuUJ8gJfRLEMzxhjjEyuhGWOMyRUCvVNIkL8DMMYYkzNoJpaMiEgrEflDRLaJyEup7L9LRDa5y08iUjWjc1oJzRhjjE+yqspRRIKBj4HmwG5gtYhMVdVfvZLtABqp6mERaQ0MB25M77yWoRljjPFJFnYKqQ1sU9XtACIyFugAeDI0Vf3JK/1KoExGJ7UqR2OMMT5JQH1eROQhEVnjtTzkdarSwC6v9d3utrT0AGZlFJ9laP9x7w3px++/Lmfd2nlUr1Yp1TSPPXovv/+6nLgzeyhWrMhFievtQa+yav1cFv84lSpVr0s1TdlyZZi9YDw/r5vD51++R2hoaJL91WpUJvrQr7Tv0BKAildczqJlkz3L9l1refjR7lkW8+B3+7Bx8yJW/jyLqtWuTzVNuXJlWLRkEhs2LeTrUR96Yn7q6Yf4aeUMflo5g1WrZ3P0+DaKFClE3rx5WLx0MitWzmT1mjm8+trTWRZvvSY3Mmn5GKasGMd9T3RLNc0L/Z9myopxjFv4NddUvgqAPHnz8M2szxm34Cu+X/Itjzzfw5N+4Gf9GDv/K8bO/4oZq79n7PyvsizezHjt7SE0bNuFjt0e8cv1e7/9AgtXTWHmknFcX+WaVNOUKRvBxDmjWLhqCkNHDCQ0NMSn44OCgpi2cAwjvvvAs23oiIFMXzSW6YvGsnTdDKYvGpst7yszbWiqOlxVa3otw71OldogWqkW/0SkCU6G9mJG8WWYoYnIiYzSZAcReUZETolIIX9c3yuOV9LZV0xENrhLtIjs8VrPczHjPB+tWzXlyisu55rr6vPooy/y8UcDUk3304rVtGzdhZ07d6W6P6s1a96QChXLU7t6C5576nXeGfJGqul69+3FsE++4sYaLTly5Bh33XObZ19QUBC9+/Zi0YLlnm1/bdtBkwYdadKgI5GNbiE2NpYZ0+dlScwtWjam4hXlqVq5CU8+8TLvf9A/1XRv9n+Jjz/8gmpVmnLkyFG633sHAB+8P5x6ddpSr05b+vQZzPJlP3P48FFOnz5D29Z3UrdOG+rWaUuz5o2oVavaBccbFBTESwOe44k7n+PWhnfRqlMzKlxVPkma+pF1KVuhDB3qdqZ/r3d4ZVAvAM6cPsNDt/akc+S9dInsTr0mN1K5hpOBv/Rwb7o0u5cuze5lwYzFLJy55IJjPR8d2zRn2JDU/w2yW+Nm9SlfoSxNa3fglWf78+bg1L9CXuz9FCOHjaZp7Q4cO3KcO7p18un4+x6+k7+27kiyrecDL9GuSRfaNenC7OkLmDNjYba8t8yU0DKwG7jMa70MsDd5IhGpAowAOqjqwYxOGsgltK7AaqCTn+NIM0NT1YOqWk1VqwHDgPcS11X1THonFRG/t1+2b9+Sb0Z/D8DPq9ZRqHAhwsJKpki3YcMW/v5790WLq1XbSMaNmQzA2jUbKVSoIKVKlUiRrn7DOkybPAeAcd9Nok3bSM++Bx++m+lT5nBgf+p/Aw0b12Xnjl3s3pXib+i8tGvXnDGjJwKwevUGJ+awlDE3alSXSZOcmpPR3/5Au3YtUqS5/fb2TJgwzbP+778nAQgNDSE0NCRLWjEqVb+WXTt2s+efvcSdjWPO5AU0btkgaawt6zN9/GwANq/bQoGCBSheshgAsSdjAQgJDSEkJATVlFE1b9+U2ZOy5gdDZtWsVplCBQv45drNWjdi0vjpAGxYu5mChQpQolTxFOnqNqjFrKnzAfhh7DSat26c4fFh4SVp0rw+476dlOb123RozrSJs7PyLXkkZGLJwGrgShG53P3x3wWY6p1ARMoCE4G7VfVPX+I7rwxNRKqJyEq3O+UkESnibn9QRFaLyEYR+UFELnW3fyUiQ92ul9tF5LYMzl8RyA+8hpOxJW6/V0Qmi8g0EdkhIk+IyLMist6Np2gG8S0WkZru6+IistPrvBNFZLaIbBWRd9ztA4FL3BLX6EzcnxtEZImIrBWROSIS7nX9t0VkCfCUu/6eiCwVkd9EpJYbx1YRyfafl6UjwpJ8oe/ZHUXpiLDsvmyGwsNLsXdPtGd9795owiJKJUlTtGgRjh09Rnx8/Lk04U6asPCStGnXjK9Gpl3t0umWtkz8fnrWxRxRit27o87FvCeKiGT3slixIhzxinnPnmgikr2vSy7JR7PmjZgy+VxzQVBQED+tnMGOv9ewcMFy1qzecMHxlgwvwb69MZ71fVExlAgvkSJNdLI0Jd00QUFBjJ3/FQt+mc7Kpav5Zf2vSY6tUacqhw4c5p8dF++HUKAICy9JlNfnN3rvPsLCk/5QLFK0MMeOHvd8FqL37qOUmya9419/63kG9v2AhITUs4xadWtwcP8hdm7PnolpNRP/pXse1TjgCWAO8BswXlW3iMgjIpJYT9wbKAZ84n4Hr8kovvMtoY0CXlTVKsBmoI+7faKq1lLVqm6QPbyOCQfqA+2AgRmcvyswBlgGXC0i3p+GSsCdOL1k3gJOqmp1YAVwTwbxpaca0BmoDHQWkctU9SUg1i1x3eXDORCRUOBD4DZVvQEY6caZqLCqNlLV/3PXz6hqQ5wS3hTgcfc93isixVI5v6ehNSHhX19CSi/WFNtS+6V9sfkSVypJPGneGvgq/fq8m+YffWhoKC3bNGXq5Kz7FetbzBmnadMmkpUr13L48FHPtoSEBOrVacvVV9alZs2qXHfdVVkRcMptmYg3ISGBLs3upWX1TlSqfh0Vr7k8SbpWnZr7rXTmb+f7WUi8/2kd37RFAw4eOMQvG39L89o339KKqdlUOgOnl6OvS0ZUdaaqXqWqFVX1LXfbMFUd5r5+QFWLeNV61czonJmu9nLbtAqramLl+NfABPd1JbdkURinhDXH69DJqpoA/CoiSX+WptQF6KSqCSIyEbgd55kFgEWqehw4LiJHgcS6mc1AlQziS88CVT3qvsdfgXIk7YXjq6txMqR57gczGIjy2j8uWfrEYvZmYIuqRrkxbMepY05SZ+Y2rA4HCMlTOtO5z6OPdKdHDydvXrNmA2Uui/DsK10mnL1R+zJ7yixx/wN3cnd3pz1p/frNRJQ+V7qJiAhjX1RMkvQHDx6mYKGCBAcHEx8f76SJdtJUrV6J4SOHAE6pKLJFI+Li4pg1YwEAkc0bsmnjFvanUR3pq4cevpt77+sCwNq1myhTJvxczKXDiUp2Lw8cOERhr5hLlw4jKtn7uu329kwYn6TmxePo0eMsW7aSZs0b8euvPtXApClmbwylIs79TiwVXpL90QeSpNm3N4awDNKcOHaCNT+to16TOvz1u9OuExwcTNM2jbizxf0XFGNOcvf9d9D57lsA2LRhC+Fen9+wiFLsi96fJP2hg4cpWKiA57PgnSZq775Uj2/dvhmRrRrRuFl98ubNQ/4C/2PIp/159tHXAOe+t2zblJsj78y29xnoQ19ldRvaV8ATqloZ6Avk89p32ut1mtPEuY2AV+JkCDtxMreuXkm8z5PgtZ5Axhl0HOfec75k+7zPG+/DudIiOBlT4q+Kyqrq3VCSvFjlHX/y95bl7WyfDvuamrVaULNWC6ZOncPddzm1vzfWrsGxo8eIjo7J4AzZY+SI7zwdNmZNn0/nrh0BuKFmVY4dO86+fftTHPPjsp9p39Hpwdj5zk7Mmuk0hNesEskN7jJtyhxefK6vJzMDuOW2tkz6fsYFxzz8s288HTmmT5tL17ucL7Ratao5MUenjHnp0pV06tQagLu63cqMGedKMQULFuCm+jcm6ahSvHhRChVy2oLy5ctLkyb1+fPPvy449i0bfqdshTJElA0nJDSElh0jWTx3eZI0S+Yup90drQCoXON6Thw/wYGYgxQpVpj8BfMDkDdfHm5sUIud2/72HHdjw5rs3PY3MVEp339u9c3I8Z5OGfNmLqLTHe0AqHZDZY4fO8H+fQdSHLNy+Rpa39wMgFu7tGf+rMUALJi9JNXjB/f/kJuqtKJhjbb0fOglVixf7cnMAG5qdCN/bdtJdFT2/Q0nqPq8+EOmMzS3FHNYRBJbkO8GEktDBYAot9rNpyq6VHQF3lDV8u4SAZQWkXJZEN9O4Ab3dbrteF7Ouu/HV38AJUSkLjhVkCKSeh9uP5s5awHbd/zDH7/9yLBh7/DEk+f6v0ybMopwt03qicfvZ+f2NZQpE876tfP5bNjgbI1r3twl/L1zF6s2zGPI0Dd54bm+nn1jJgynlNtxpV+fwTz6+H2sWj+XokULM3pUxgXxSy7JR6Mm9Zg+bW6Wxjxn9iJ27tjFpl8W89HHA3jm6dc9+36YNPJcG8hrA3mi5wNs3LyIokWL8PVX4z3p2t/cgoULlnHS7XABUCqsJDNnj2Hlz7NYumwKCxcuY/asC+/BFh8fz6BX3uOTMUOYuOw75k5dyPY/dnDbPR257Z6OACyfv4Ldf+9l6srxvP5/LzLgJaeWvHjJYnz+w4eMW/g1387+gp+XrmbZvHPPwLbs2IzZk+ZfcIwX4vk+A7nr4WfY+c9uIjt244dpczI+KIssmrecXX/vZtHqqQx473V6v3Cu9/DIMR9S0u0sNKjfB/R4tBsLV02hcJFCjB89OcPj09OuU8ts6wySKCuHvsoOklGbiYgkkLQ75RBgIU6bz6XAduA+d3iSR4EXgL9xqtAKqOq9IvIVMF1Vv3fPeUJV86dxvR1Aa1X93WvbEGCfu9RU1Sfc7Tvd9QMicm/iPhGplkZ81wDjgRPue+imquW9j3XPOx14V1UXi8gg4GZgXXrtaCLyBnBCVd91rz8UKIRTynpfVT8XkcVAL1Vd4x7jWReRxu7rdsn3pXXN86ly9Lcil6T6zx6wYs+m21k1IF1ZMCLjRAFm1S/f+DuETLn6mlv9HUKmbT+wPs2aMV/dWa6Tz9853/096YKvl1kZZmgmcFmGlv0sQ7s4LEPLflmRoXUt19Hn75wxf0++6Bma35+FMsYYkzPEBfj0MX7L0ESkMpD8Z9lpVU13NGV/cbvQL0hlV6QvT7AbY0xOl9HzZf7mtwxNVTfjPPuVI7iZVjV/x2GMMf4S6N32rcrRGGOMTwK9z4VlaMYYY3ziw6DDfmUZmjHGGJ9k4QSf2cIyNGOMMT6xEpoxxphcwdrQjDHG5ArWy9EYY0yuYM+hGWOMyRWsDc0YY0yuEK+BXeloGZoxxhifWJWjyTbFLing7xAyLW9wZqaW879ieQv6O4RMOxYXm3GiAJPTRq//4/cf/B2CX/hr4k5fWYZmjDHGJ4GdnVmGZowxxkfWKcQYY0yuYBmaMcaYXMF6ORpjjMkVrJejMcaYXMHGcjTGGJMrWBuaMcaYXMFKaMYYY3KF+AAfb98yNGOMMT6xkUKMMcbkCoHeyzHI3wEYY4zJGRJUfV4yIiKtROQPEdkmIi+lsl9EZKi7f5OI1MjonJahGWOM8Ylm4r/0iEgw8DHQGrgO6Coi1yVL1hq40l0eAj7NKL6AytBEJExExorIXyLyq4jMFJGrzvNcX4nIbe7rEYk3S0Re8eHYE8nW7xWRj9zXj4jIPekc21hE6p1PzBfLW4NeZeX6OSz6cQqVqyb/DDnKlivNrAXjWLFuNsO/HEJoaNJR8qvVqMTeQ1to16FltsTYd8BLLF0zgznLfqBSlWtTTXNZ2dJMmTeaJaun8/EXgwkNdWrQK155OZPmfMvWqLU89ET3JMfc//BdzPtxIvN/mkSPR7pdUIz1m9Rl1k/fM+fniTz4ZPdU07z61nPM+XkiUxZ/x3WVr87w2GsqXcXYmSOZtHA038/9msrVnX+fytWvY9LC0UxaOJrJi0bTrE1jn+Ps/fbzLFw1hRlLxnF9lWtSTVOmbAQ/zPmaBasmM3TEQM+9TO/4hk3rMW/lRBaumsLDPe9Ncr57HujMvJUTmbV8Ai/2eQqAwkUKMXryZ2zauZw+A1/MRPwvsHDVFGZmEP/EOaNYuGpKKvGnfXxQUBDTFo5hxHcfeLYNHTGQ6YvGMn3RWJaum8H0RWN9jvVCvPb2EBq27ULHbo9clOudjywsodUGtqnqdlU9A4wFOiRL0wEYpY6VQGERCU/vpAGToYmIAJOAxapaUVWvA14BSnmlCT6fc6vqA6r6q7uaYYaWwbmGqeqodJI0BjKVoYnIRWvLjGzekMsrlqNO9Zb0eqo37wzpk2q61/r24rNPvqZujVYcOXKMO+85N71HUFAQr/ftxaIFy7MlxibNGlC+Yjka1mzLS8/05a3/ey3VdC+/8QwjPv2GRrXacfTIMTp3uwWAI4eP0uelAQz/6Ksk6a+69gq63nMr7ZvdScsGtxHZohHlK5Q9rxiDgoLoPegFHuz6FO3q30HbW1pQ8arLk6RpGFmPchXK0vLGW+j93Nv0eeelDI99vveTfPzuCDo1vYuhgz7j+d49Adj6+1/c1vweOjW9iwc796Tv4JcJDs74z6Fxs5soX6EsTWt34NVn+9Nv8Muppnuhd0++HDaayNodOXrkGLd365ju8UFBQbwx6EXu7/wkLW+6lfa3tOIK9z3UqV+TZq0b07ZhZ1rXv50RHzt/LqdPn2bIgE8Z8MZ7Pt/nxs3qe67/yrP9eXNw6n++L/Z+ipHDRtO0dgeOHTnOHd06+XT8fQ/fyV9bdyTZ1vOBl2jXpAvtmnRh9vQFzJmx0Od4L0THNs0ZNqT/RbnW+YrXBJ8XEXlIRNZ4LQ95nao0sMtrfbe7jUymSSJgMjSgCXBWVYclblDVDUCwiCwSke+AzSISLCKDRWS1W6/6MHjqWz9yS3YzgJKJ5xGRxSJSU0QGApeIyAYRGX0+QYrIGyLSy33d073eJrdkWR54BHjGvUYDESknIgvcNAtEpKx77FciMkREFgGDRWSriJRw9wW59cbFzyfG9LRqG8mEMVMAWLtmIwULFaRkqRIp0tVvWIdpk+cAMP67ybRu28yz74GHuzF9ylwO7D+U1eEB0KJNE34YOxWA9Ws2UbBgAUqWSnkr6jWozcwp8wD4fuxUWrZtCsDBA4fYtH4LcXFxSdJfeVUF1q3ZxKnYU8THx7PypzW0aht5XjFWqXE9/+zYxe6/93D2bBwzJ80jslWjJGkiWzdiyvgZAGxc+wsFCxWgRMli6R6rquQv8D8AChTMT0z0fgBOxZ4mPj4egDz58vrcON+sdWMmjZ8OwIa1m50YUrmXdRvUYtbUBQBMHDud5q2bpHt81RqV+HvHbna572H6pDk0a90YgDvvvY1hH3zJmTNnATh44DAAsSdPsfbnDZw5dcan2J3rN8pE/PMB+GHsNJq7saR3fFh4SZo0r8+4byelef02HZozbeJsn+O9EDWrVaZQwcCe4zAzVY6qOlxVa3otw71OJamePilf0iQRSBlaJWBtGvtqA6+6pbYewFFVrQXUAh4UkcuBTsDVQGXgQVIpJanqS0CsqlZT1bvSiSUx09sgIhuAfmmkewmorqpVgEdUdScwDHjPvcYy4COcYnMVYDQw1Ov4q4BmqvoM8C2QGFMzYKOqHkgnxvMSHl6KPXuiPOtRe6MJjyiVJE3RooU5dvSY5wt0795owsOd3wdh4SVp3a45X4/MvmqYsPCSRO2J9qxH791HWHjJJGmKFC3MsaPHPTFG7Y1OkSa5P37byo11b6BwkULkuyQfTZo3ILx02HnFWCqsBFF79p2LMWofpcJLpEyz1yvN3hhKhZdM99i3XxvC8316smj9dF544ymGvPWxJ12VGtczbek4pi4ZwxvPD/S893TjDC/J3j1JYwhLFmeRooU5fvSE53zO/S6R7vGlwksQtTc6yfZS7v2/vGI5atWtwQ9zvua7qZ97qk3Px/l8FqL37vPEkt7xr7/1PAP7fkBCQurPVtWqW4OD+w+xc/s/5x1/bqOa4POSgd3AZV7rZYC955EmiUDK0NKzSlUT6wVaAPe4Gc3PQDGcRsOGwBhVjVfVvcCF1BMkZnrVVLUa0DuNdJuA0SLSDYhLI01d4Dv39TdAfa99E1Q18VtpJJDYNnc/8GVqJ/MuxseeOeLTm0l6gpSbkj/979T+Jk/j/P/Nga/Qv8+7aX4JZIl0rn8uScZpktv25w4+HTqS0ROH882EYfz2yx8+ZQq+x5giyNTTpHNs13tvZWDvITSp3o4Br79H//df96TZtG4L7Rt25vYW3Xmo573kyZvnfMJM5V6mlkbTPT61+5944pCQYAoVKsCtLbszsM/7fDhiUIZxpiX1f+eMP6944k/9+KYtGnDwwCF+2fhbmte++ZZWTL1IpbOcIgH1ecnAauBKEblcRPIAXYCpydJMxfmuFxGpg1OQiUp+Im+B9BzaFuC2NPb96/VagCdVdY53AhFpw8WfULUtTkZ6M/C6iFzvwzHeMXrel6ruEpF9ItIUuJFzpbWkBzvF9uEApQpd49P7ve+BO+nW/XYANqzfTOnS59pVwyPCiI6KSZL+4MHDFCxUkODgYOLj44mICCM62klTrXolho0cAkCxYoVp1qIh8XFxzJqxwJdQ0nRPjy50ddvpNq3/JUnJKSyiFPuik8Z46OBhChYq4IkxPCIsRZrUjPt2kqeK6YXXeiYpQWXGvqgYwkufK9mGhZciJvpAyjRepd+wiJLERO8nNE9omsd27NyOt179PwBmT51P//deTXHt7Vt3EnsylquuqZjqF3K3+++g891OG9LmDVuIKF3KU/URFlGSfW41ZqJDB49QoFB+z7107rcTT/TemFSPDw0NJTzC+9/o3Hmj98Z42p02rd9CQkICRYsV5tDBI6ney+Tuvv8OOt/ttIdu2rAllc9C8viTfha800Tt3Zfq8a3bNyOyVSMaN6tP3rx5yF/gfwz5tD/PPuq01wYHB9OybVNujrzTp5j/K7Jq6CtVjRORJ4A5QDAwUlW3iMgj7v5hwEygDbANOAncl9F5A6mEthDIKyIPJm4QkVpAo2Tp5gCPikiom+YqEfkfsBTo4raxheO0yaXmbOKxF0JEgoDLVHUR8AJQGMgPHAe8K8J/wvn1AU4mlV5PihE4VY/jvUpuF+zLEd8R2aATkQ06MWv6Am7v6nQmuqFmVY4fO07Mvv0pjvlx2c+07+j0YLzjzo7MnulkWLWqNKNWlUhqVYlk2pS5vPhcvwvOzABGfTGW1o1up3Wj25kzYyG3drkZgOo1q3D82Ali9qWsfV2xfDVtOjQH4LYuNzN35qIMr1OseFEAIkqH0apdM6b+MOu84t28/lfKVShL6bIRhIaG0KZTcxbOWZokzcLZS+lwR1sAqt5QiePHTrA/5mC6x8ZE76d2PedxmzoNavH3dqdNvHTZCE8nkIgyYVx+RTl270q99uXbkeNp36Qr7Zt0Ze7MxXS6ox0A1W6o7MSQyr1cuXwNrW922hNv6dKO+bMWAzB/9pJUj9+0fgvlK1xGGfc9tOvUkgWzlwAwd9Yi6jaoBUD5imXJkyfU58wM4JuR4z2dMubNXJSJ+J123lu7tPfEvyCN+Af3/5CbqrSiYY229HzoJVYsX+3JzABuanQjf23bmeLH3n9dFpbQUNWZqnqV2wnwLXfbsMR+FG7vxsfd/ZVVdU1G5wyYEpqqqoh0At53H7I7BewEJidLOgIoD6xze0buBzri9JBsCmwG/gSWpHGp4cAmEVmXQTtaRoKBb0WkEE6p8T1VPSIi04DvRaQD8CTQExgpIs+7sab3K2MqTlVjqtWNWWH+3CVEtmjIzxvmEnvyFE89fq7X1+gJn/Hsk6+zLzqG/n3e5bORQ3jptafYvOk3vhv1fXaFlMLCecto0rwhy9bOJDb2FL2eOPdF89W4T3jxqT7si97PgDfe46MR7/D8K0+yZfPvjPt2IgAlShZj+sJx5C/wPxISEujxyN1E1u3AieP/8tnXQyhStDBnz8bx+gtvcfTosfOKMT4+njdfeocvxg0lKDiYH76byrY/ttO5u1OyGPf1RJbM/5GGzW5i7qpJnDp5ilee6pfusQCvP/cWr/Z/juCQYE6fOkPv594G4IYbq/Lgk/cSFxdHQkICfV8cxJFDRzOMc/G85TRuVp+Fq6dwKvYUL/Z8w7PvizFDefmZfsREH+CdfkP54PMBPPvy42zZ/DsTRk9O9/j4+Hj6vjSIryZ8TFBQEN9/N5Wt7nv4fvQUBg59g1nLxnPm7Fmef+JcT9ol66aTv8D/CA0NpXmbxtx722Ns+zNpL0Nvi9zrL1o9lVOxp3jBK/6RYz7kpWf6ERO9n0H9PmDo5wN59uXH+HXzH4x340/v+PS069TyonUGSfR8n4GsXr+JI0eOEdmxG4/1uJtb22fPYzHnKz47mxqygAT66Mn/JSJSEydjbOBLel+rHANJ3uALLhxfVJeG5PN3CJl2NiHLCvcXTaAPqZTcH7//4O8QMi20eIXUeg1mSljha33+h4o+8tsFXy+zAqaE9l/nlkofJY22M2OM8bdALwD9ZzM0ESkGpNb4E6mqBy92PKo6EBh4sa9rjDG+sgk+A5SbaVXzdxzGGJNTWAnNGGNMrhDonUIsQzPGGOMTq3I0xhiTK1iVozHGmFzBl4k7/ckyNGOMMT4J9OcFLUMzxhjjEyuhGWOMyRUSMp4Wxq8sQzPGGOMT6xRijDEmV7AMzRhjTK4Q2NmZjbZv0iAiD7mTieYIOS1eyHkx57R4wWL+rwmkCT5NYHnI3wFkUk6LF3JezDktXrCY/1MsQzPGGJMrWIZmjDEmV7AMzaQlp9Xh57R4IefFnNPiBYv5P8U6hRhjjMkVrIRmjDEmV7AMzRhjTK5gGZoxxphcwTI0kyoRCRKRgv6OIzcSkf/5OwYTWESkqL9jyA0sQzMeIvKdiBR0v3B/Bf4Qkef9HVdqROQqEVkgIr+461VE5DV/x5UeEaknIr8Cv7nrVUXkEz+HlS4R+caXbYFIRIq4n4saiYu/Y0rHzyIyQUTaiIj4O5icyjI04+06VT0GdARmAmWBu/0aUdo+B14GzgKo6iagi18jyth7QEvgIICqbgQa+jWijF3vvSIiwcANforFZyLyJrAJGAr8n7u869eg0ncVTnf9u4FtIvK2iFzl55hyHBuc2HgLFZFQnAztI1U9G8A/Fi9V1VXJ4ovzVzC+UtVdyWKO91cs6RGRl4FXgEtE5FjiZuAMOeM5qTuAiqp6xt+B+EKd56fmAfNEpAnwLfCYiGwEXlLVFX4NMIewEprx9hmwE/gfsFREygFH/RpR2g6ISEXcAcBF5DYgyr8hZWiXiNQDVETyiEgv3OrHQKOqA1S1ADBYVQu6SwFVLaaqL/s7Ph/8AhT2dxC+EpFiIvKUiKwBegFPAsWB54Dv/BpcDmIPVhsPEblcVXd4rQtwhapu9WNYqRKRCjglhXrAYWAH0E1Vd/ozrvSISHHgA6AZTmlnLvCUqh70a2AZEJHSQDm8anRUdan/IsqYiNQEpuBkbKcTt6vqzX4LKh0i8ifwDfClqu5Otu9FVR3kn8hyFsvQjIeIrFPVGsm2rVXVgG0zcTuwBKnqcX/HkhuJyECctslfOVc9qoGaMSQSkS04NQ6bgYTE7aq6xG9BpcFtlxysqs/6O5acztrQDCJyDU7jfyERucVrV0Egn3+iSp+IFAbuAcoDIYntUqra039RpU9ELsepSipP0tJOIGcOnYCrVfV0hikDywFVHervIHyhqvEiUtXfceQGlqEZgKuBdjhtDu29th8HHvRHQD6YCawk2S/wADcZ+AKYRs6JeTsQile1XQ6xVkQGAFNJWuW4zn8hpWuDiEwFJgD/Jm5U1Yn+CynnsSpH4yEidXNKb6rUqkcDnYj8rKo3+juOzBCRH4CqwAKSZgwBWxIGEJFFqWxWVW160YPxgYh8mcpmVdX7L3owOZhlaMZDRErglMjKk7RKLOD+qETkGeAEMJ2kX7SH/BZUBkTkTuBKnM4gOaHUgIh0T227qn59sWPxldsm1VNV3/N3LObisgzNeIjIT8AyYC1ez0ep6g9+CyoNIvI48BZwBLfrPs4v2gp+CyoDbhXY3cBfnKtyDNhSQ04mIotUtYm/4/CViJQBPgRuwvk8L8fpAbs73QNNEpahGQ8R2aCq1fwdhy9E5C/gRlU94O9YfCUivwNVcsrDvgAisoNzPxg8AvmHA4CIvAUUAsaRtE0qIEvDIjIP53mzxGHFugF3qWpz/0WV81inEONtuoi0UdWZ/g7EB1uAk/4OIpM24nS8ifFzHJlR0+t1PuB2ICcMpFvP/X8/r20KBGppuISqerejfSUiT/srmJzKSmjGQ0SO44wScsZdBKdKLOBG3ReRSTiPGiwih3RWEJHFQBVgNTngYd+0iMhyVa3v7zhyExGZD3wFjHE3dQXuU9VIvwWVA1kJzXi4Qx3lFJPdJSfp4+8AMivZCPVBOCW2gP+ciEgp4G0gQlVbi8h1QF1V/cLPoaXlfuAjnAGsFfgJuM+vEeVAVkIzHu5QV3cBl6vqmyJyGRCuqqv8HFqqRCQPzijlAH+o6ll/xuML94u2lru6SlUDuvoxWff3OJyxPt9V1T/8E5FvRGQW8CXwqqpWFZEQYL2qVvZzaKkSkZtU9ceMtpn0WYZmPETkU5zed01V9VoRKQLMVdVaGRx60YlIY+BrnC9YAS4DugfyGIMicgcwGFiME3MD4HlV/d6fceVGIrJaVWuJyHpVre5uC9hOT2kMO5fjnrX0N6tyNN5uVNUaIrIeQFUPu6WgQPR/QIvEkoI7d9QYAnuurleBWomlMve5v/lAwGZoIlIIp6o0cd62JUA/VQ3IWRhEJERV44B/RaQY52ZjqEMAzhwhInVxOrCUEBHvsRwLAsH+iSrnsuljjLez7kOpiV8CJQjcIZpCvau9VPVPnCGaAllQsirGgwT+3+BInCHQ7nCXYzhVeYEqsXr8OZxhryqKyI/AKJxxNANNHiA/TuGigNdyDLjNj3HlSFblaDxE5C6gM1ADpzrvNuA1VZ3g18BSISIjcTLexOd27gJCVDVgG9JFZDBOL8fEnmydgc2q+oL/okpfatV0AV51513FGIIzTqkQ4G2sIlJOVf92XwcB+dWZPd5kgmVoJgl35P1InC+BBaoakBNQikhe4HGgPk6sS4FPAn1UeHc2A0/MqjrJzyGlS0RW4LTzLXfXb8LpFFLXv5GlTkR2A0PS2q+qae7zJxH5DngEZ4SetTgPhQ9R1cF+DSyHsQzNICLpPigbiOMjuvOgnVLVeHc9GMirqgH7sLU7fUyUqp5y1y8BSgX4pKTVcErrhXAy4UPAvaq60Z9xpUVEooBPcWJNQVX7XtyIfJNY6nVrSW4AXgTWqmoVP4eWo1inEAPOL0LF+RIoizMDtOCMavEPcLnfIkvbApyZn0+465fgDPpbL80j/G8CSeOLd7cFXC/SRKq6AagqIgXd9UCvBotS1X4ZJws4oSISCnQEPlLVsyJipY1MsgzNoKqXA4jIMGBq4tBXItIaJ9MIRPlUNTEzQ1VPiMil/gzIByHe4ziq6pkA7kUK5MiJVFMtmaVIJFJEVQ9ndzCZ8BnOIygbgaUiUg6nY4jJhEDvYWUurlre4ziq6iygkR/jSc+/3qNYiMgNQKwf4/HFfhHxDHMlIh2AQB9ceSZOZrYZpySfuAQqX4eKWpCtUWSSqg5V1dKq2kYdfwM5ZraAQGElNOPtgIi8BnyLUwXZDadreSB6GpggInvd9XCcXoOB7BFgtIh8hFOS2IVT+glk+VT12YyTBYZMtPf6VJLLbiLSTVW/TfYMmreA7MQSqCxDM9664jxEm9jzbqm7LeCo6mq3R2Zit+zfA7lbNoCq/gXUEZH8OB2yjvs7Jh98IyIPkoMmUvVRoLRP/c/9f8CPj5kTWC9Hk2OJSD1Szq49ym8BZcB91OBWUsYcsJ0YcuJEqr6wYaVyJyuhGQ93+KhepPzCDbg5pETkG6AisIFzs2srzogQgWoKzvBLa/Eq7QS4Z4ErctJEqj4KlCrHoentD+DONwHJMjTjbQIwDBjBuUwiUNUErtOcVcVQRlVb+TuITMqJE6kiIt+o6t3pbAuUeca8O9j0JQdOMRRILEMz3uJU9VN/B+GjX4AwIMrfgWTCTyJSWVU3+zuQTIgHNrjTyOSIiVRd13uvuA/eewauDpQ2QFX9OvG1iDztvW4yzzI0422aiDyG0ykk0DsAFAd+FZFV5JzZn+sD94rIDpyYE2cED+TRICaTciLVgC0Vi8jLwCvAJSKS+ByX4MzAPtxvgfkmYO9rTmGdQoyH+0WbXEB2ABCRVJ+PU9UlFzsWX7kPy6aQOChtTuBO+tol0McYFJEBqvqyv+PIDOuocuEsQzMmm+XEsTK9iUhx4HacRzhKA5NUtZd/o8qYiJQGypG0g1NATQArIsc5VzK7lHPtlYml94J+CSyHsipH4+EOHfUsUFZVHxKRK4GrVXW6n0Pz8PoCEJJW0QTyF4D3WJnJKRCIJeACQCfgTuAqnGroCqpaxq+B+UhEBgJdgF9J2gs2oDI0VfXp+bMAHKorIFkJzXiIyDicL997VLWSOxr8ikCd+8pkHxGJxZks8zVguaqqiGwPxOrn1IjIH0CVQJ9OyFdWHekbG8vReKuoqu8AZwFUNZYAeV4nOfc5tAy3BRIRSTF+YGrbAsQrQD6cqVheFpGKfo4ns7YT+DOYZ0ZA/h0GGqtyNN7OuKUyBXC/xAL1F27ybtkheHXLDiQikg9niKPiIlKEc19OBYEIvwWWDlV9D3hPRCrgtJ1NBiJE5EWcNrQ//RmfD07iPG6wgJz1uEFarCrNB5ahGW99gNnAZSIyGrgJuNevESWTQ7tlP4wzmHIETpVuYoZ2DPjYTzH5RFW34wx99ZaIVMZpU5uFM0pLIJvqLuY/xNrQTBIiUgyog/OluzJQhzzKod2yn1TVD/0dh8l5RGS9qlb3dxyBzjI0k4SI3ILzALDidAaYlMEhfpMTumUnlwMHVL4FGASUxPmRE8i9ST3cZypTfLkFaqeWjIbqEpGigf54RyCwKkfjISKfAFcAY9xND4tIM1V93I9hpSqndMv2lkMHVH4HaK+qv/k7kEyq6fU6H85zdOk+D+hnOWKorkBnJTTjISJbgEqJA/6KSBCwWVWvT//Iiy8ndssWkd/IYQMqi8iPqnqTv+PICiKyXFXr+zsOb95twiR9qPoMMDynVav7m5XQjLc/gLJA4lBMlwGb/BdOuhK7ZeeYDI2cOaDyGvf5xMkk7S040W8R+UBEvJ/ZCsIpsQXcJJqqOgAYkBPbhAORZWjGWzHgN3fAX4BawAoRmQoBN/BvTuyWnRMHVC6Ic69beG1TIKAzNOD/vF7HATuBO/wTStpE5BpV/R2YkCwTBkBV1/khrBzLqhyNR1oD/iYKpIF/RaR7atsDefqNnDigssleIvK5qj7oTs+TnAbi5LqBzDI0k4Q7IvyVqjrffcg6RFWP+zsu4x/uQ+E9cDot5Evcrqr3+y0oH4hIIZznKhu6m5YA/VT1qP+iMtnNqhyNh4g8CDyE0xusIlAGZwbrQJnd18MdOHkAcB1Jv2gDsls2gIjUAT4ErgXyAMHAvwHeBf4b4HegJdAPuAvICT0eR+K0WSZWM94NfAnc4reIUuE+FpGmQG+rDDSWoRlvjwO1gZ8BVHWriJT0b0hp+hLnF/h7QBPgPgJ/vLuPcB41mIDTSeEe4Eq/RpSxK1T1dhHpoKpfi8h3wBx/B+WDiqp6q9d6XxHZ4K9g0tHe/X9JoB6w0F1vAiwm8NsqA4oNTmy8nVbVM4kr7viIgVonfYmqLsCpNv9bVd8AAr69QVW3AcGqGq+qXwKN/RxSRs66/z8iIpWAQjgPhge6WBHxdNEXkZuAWD/GkypVvU9V78P5O7tOVW91M+KAe1QmJ7ASmvG2REQSx0lsDjwGTPNzTGk55T4nt1VEngD24PzKDWQnRSQPTu/Md3C67//PzzFlZLg7oPLrOGMj5ndfB7pHga/dtjQBDhFg45ImU15VvR/n2IczD53JBOsUYjzcDKIHThdtwalaGhGIDwKLSC2ctpzCwJs43csHq+pKf8aVHrfDzT6c9rNncEo7n7ilNpMNRKQggKoeyyitP4nIRzjVz2NwSmtdgG2q+qRfA8thLEMzSYhICQBV3e/vWHIbEfkfEKuqCe56MJBXVU+mf6T/uCWcN4AG7qbFwJuB3ltQRArjtFGWJ+m4mQH7nKKIdOJcr8ylgTyOaqCyNjSDON4QkQM4Pdr+EJH9ItLb37GlRUTmuV9aietFRCTQOyssAC71Wr8EmO+nWHw1Emeamzvc5ThOh5xANxMnM9uMM2VP4hLI1gEzVPUZYI6IBNzIJoHO2tAMOHN13QTUUtUdAO7Ejp+KyDPuZI+BpriqHklcUdXDAdwjM1E+VT2RuKKqJ0Tk0vQOCAA5pbdgcvlU9Vl/B+GrVB6ZKU2APjITyKyEZsCpmumamJmBZ2LHbu6+QJQgImUTV9z2qUCvP//Xe3gjEbmBAOx5l0yO6C2Yim9E5EERCReRoomLv4NKx+M4PyqPgfPIDIHfySngWAnNAISmNpGnqu4XkVB/BOSDV4HlIpI4bFRDnF+4gexpnDH79rrr4UBn/4Xjk0eAUW5bGsBhINVhxwLMGWAwzuck8YeOAoH64P1pVT0j4jxKGeCPzAQsy9AMOH/857PPb1R1tlvaSZxd+5lAnV07kaquFpFrgKtxYv5dVc9mcJhfqepGoKp3b0EReZrAnYUh0bM4D4UH9GfCS056ZCZgWS9Hg4jEA/+mtgunLSJgSmmJo5OnNjI5BObo5CLSVFUXpjXMUU4b3khE/lHVshmn9B93hogugdyD1Js4RbMHyAGPzAQyK6EZVDXY3zFkwnPAgySdHiSREpijhTTCGdKofSr7csJULMkF+hBj4MwIvsEdxT6gpxdyn//cpKqVgM/9HU9OZiU0Y0ym5JASWmrtfKqqoy56MD4QkdHAy6r6j79jycmshGZylJw4OrmIpNt9XFWHXKxYfCUix0m9U4LgPD8X0JLPiycil+GMvhGowoEt7uSvnur/AJ/8NeBYhmZymtSq7RIFavVdjntAVlVzXMzJiUhx4HagK85zXQE38oaIXAGUAvom29UIZ3xSkwlW5WiMyTXc0TU6AXfiDO47CeisqmX8GlgaRGQ68Iqqbkq2vSbQR1XT+wFnkrEHq02OJCLFRGSoiKwTkbUi8oGIFPN3XOkRkQoiMs0dVixGRKa4I7KYrBODM8D2WzijnDxHgD564iqfPDMDUNU15IxpegKKZWgmpxoL7AduBW5zX4/za0QZ+w4Yj9NeEoEz0ecYv0aU+7yCM4P5p8DLIlLRz/FkJF86+wK+rTLQWIZmcqqiqvqmqu5wl/44U8kEMlHVb1Q1zl2+xUaDyFKq+p6q3gjcjNOBZTIQISIvikggzi+22h3HMQkR6UHgD6YccKwNzeRIIvIusAanxANOKe16Ve3jv6jSJyIDgSM4pUvFGfYqL/AxgKoe8ltwuZiIVMbpGNJZVQOqxCYipXDa+c5wLgOriTNnXidVjfZXbDmRZWgmR3K7lf8PSHA3BXGuu7OqakG/BJYOEdmRzm5VVWtPu0hEZIWq1vV3HIlEpAlQyV3doqoL/RlPTmUZmjHmP0dE1qtqdX/HYbKWPYdmciz3Iev6ONV3y1R1sn8jSp+I5MMZdNYTMzBMVU/5NbD/JvslnwtZCc3kSCLyCXAF53oJdgb+UtXH/RdV+kRkPM6Mz9+6m7oCRVT1dv9F9d8kIutUNdUBrk3OZSU0k1M1AioljkYuIl8Dm/0bUoauVtWqXuuLRGSj36L5b8sJAyybTLJu+yan+gPwHiD3MgJ/jq71IlIncUVEbgR+9GM8/2V3+zsAk/WsytHkSO5M1bWAVe6mWsAK4CQE5qCuIvIbzuSeiSOqlwV+w+mpqapaxV+x5TZu++ogoCROaUwI0N6vJutYhmZyJBFp5L2K09GiK06nC1R1iT/iSo+IlEtvv6r+fbFiye1EZBvQXlV/83cs5uKxDM3kWCJSDWcQ2juAHcBEVf3Qr0H5QERK4jXkkc2BlfVE5EdVvcnfcZiLyzqFmBzFHb6oC05p7CDO+I2iqk38GpgPRORmnJm2I3AG0S2HU+V4vT/jyqXWiMg4nKGvvGesDsTphUwWsQzN5DS/4zy/1V5VtwGIyDP+DclnbwJ1gPmqWt0dHaKrn2PKrQritKe28NoWqPPlmSxiGZrJaW7FKaEtEpHZOOMi5pQu2GdV9aCIBIlIkKouEpFB/g4qN1LV+/wdg7n4LEMzOYqqTgImicj/gI7AM0ApEfkUmKSqc/0ZXwaOiEh+nBLmaBGJAeL8HFOu5I7K0gOnOte7vfJ+vwVlsp09h2ZyJFX9V1VHq2o7oAywAXjJv1FlqAMQCzwNzAb+AmxG4uzxDRAGtASW4HxGjvs1IpPtrJejMReRO11ILXd1larG+DOe3Cpx8GER2aSqVUQkFJijqk39HZvJPlZCM+YiEZE7cB4Evx3nUYOfReQ2/0aVa511/39ERCoBhYDy/gvHXAzWhmbMxfMqUCuxVCYiJYD5wPd+jSp3Gi4iRYDXgalAfve1ycWsytGYi0RENqtqZa/1IGCj9zZjzPmzEpoxF89sEZlD0ilvZvoxnlxLRAoBbwAN3E2LgTdV9ai/YjLZz0poxmQzEbkCKKWqP3pNSirAYWC0qv7l1wBzIRH5AfgF+NrddDdQVVVv8V9UJrtZhmZMNhOR6cArqrop2faaQB9Vta77WUxENqhqtYy2mdzFejkak/3KJ8/MAFR1DdbzLrvEikj9xBURuQnnGUCTi1kbmjHZL186+y65aFH8tzwCjHLb0sCp3u3ux3jMRWAlNGOy32oReTD5RhHpAaz1Qzy5nqpuVNWqQBWgiqpWB+yh6lzO2tCMyWbu6CCTgDOcy8BqAnmATqoa7a/Y/ktE5B9VLevvOEz2sQzNmIvEnS6mkru6RVUX+jOe/xoR2aWql/k7DpN9LEMzxvwnWAkt97NOIcaYXENEjuNM5JliF9YBJ9ezEpoxxphcwXo5GmOMyRUsQzPGGJMrWIZmjDEmV7AMzRhjTK7w//0lDsK59Tz3AAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(df.corr(),annot=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "51c79eda",
   "metadata": {},
   "source": [
    "Observation:\n",
    "\n",
    "Loan_amount is positive correlated with ApplicantIncome and less correlated to Coapplicant.\n",
    "\n",
    "ApplicantIncome is negative gorelated to loan_amount_term because when the Income is hige then the applicant is able to pay his loan in less time ."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af8975d9",
   "metadata": {},
   "source": [
    "# Remove outliers"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "27907469",
   "metadata": {},
   "source": [
    "firstly I create a list of columns to remove outliers from these columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "83cd1ea8",
   "metadata": {},
   "outputs": [],
   "source": [
    "outliers=df[[\"ApplicantIncome\",\"CoapplicantIncome\",\"LoanAmount\"]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "282c101d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Education</th>\n",
       "      <th>Self_Employed</th>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <th>LoanAmount</th>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <th>Credit_History</th>\n",
       "      <th>Property_Area</th>\n",
       "      <th>Loan_Status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Male</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>5849</td>\n",
       "      <td>1621</td>\n",
       "      <td>128</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>4583</td>\n",
       "      <td>1508</td>\n",
       "      <td>128</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "      <td>Rural</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>Yes</td>\n",
       "      <td>3000</td>\n",
       "      <td>1621</td>\n",
       "      <td>66</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>0</td>\n",
       "      <td>Not Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>2583</td>\n",
       "      <td>2358</td>\n",
       "      <td>120</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Male</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>6000</td>\n",
       "      <td>1621</td>\n",
       "      <td>141</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</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>609</th>\n",
       "      <td>Female</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>2900</td>\n",
       "      <td>1621</td>\n",
       "      <td>71</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>610</th>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>3</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>4106</td>\n",
       "      <td>1621</td>\n",
       "      <td>40</td>\n",
       "      <td>15</td>\n",
       "      <td>1</td>\n",
       "      <td>Rural</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>611</th>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>8072</td>\n",
       "      <td>240</td>\n",
       "      <td>253</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>612</th>\n",
       "      <td>Male</td>\n",
       "      <td>Yes</td>\n",
       "      <td>2</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>No</td>\n",
       "      <td>7583</td>\n",
       "      <td>1621</td>\n",
       "      <td>187</td>\n",
       "      <td>30</td>\n",
       "      <td>1</td>\n",
       "      <td>Urban</td>\n",
       "      <td>Y</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>613</th>\n",
       "      <td>Female</td>\n",
       "      <td>No</td>\n",
       "      <td>0</td>\n",
       "      <td>Graduate</td>\n",
       "      <td>Yes</td>\n",
       "      <td>4583</td>\n",
       "      <td>1621</td>\n",
       "      <td>133</td>\n",
       "      <td>30</td>\n",
       "      <td>0</td>\n",
       "      <td>Semiurban</td>\n",
       "      <td>N</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>589 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Gender Married  Dependents     Education Self_Employed  ApplicantIncome  \\\n",
       "0      Male      No           0      Graduate            No             5849   \n",
       "1      Male     Yes           1      Graduate            No             4583   \n",
       "2      Male     Yes           0      Graduate           Yes             3000   \n",
       "3      Male     Yes           0  Not Graduate            No             2583   \n",
       "4      Male      No           0      Graduate            No             6000   \n",
       "..      ...     ...         ...           ...           ...              ...   \n",
       "609  Female      No           0      Graduate            No             2900   \n",
       "610    Male     Yes           3      Graduate            No             4106   \n",
       "611    Male     Yes           1      Graduate            No             8072   \n",
       "612    Male     Yes           2      Graduate            No             7583   \n",
       "613  Female      No           0      Graduate           Yes             4583   \n",
       "\n",
       "     CoapplicantIncome  LoanAmount  Loan_Amount_Term  Credit_History  \\\n",
       "0                 1621         128                30               1   \n",
       "1                 1508         128                30               1   \n",
       "2                 1621          66                30               1   \n",
       "3                 2358         120                30               1   \n",
       "4                 1621         141                30               1   \n",
       "..                 ...         ...               ...             ...   \n",
       "609               1621          71                30               1   \n",
       "610               1621          40                15               1   \n",
       "611                240         253                30               1   \n",
       "612               1621         187                30               1   \n",
       "613               1621         133                30               0   \n",
       "\n",
       "    Property_Area Loan_Status  \n",
       "0           Urban           Y  \n",
       "1           Rural           N  \n",
       "2           Urban           Y  \n",
       "3           Urban           Y  \n",
       "4           Urban           Y  \n",
       "..            ...         ...  \n",
       "609         Rural           Y  \n",
       "610         Rural           Y  \n",
       "611         Urban           Y  \n",
       "612         Urban           Y  \n",
       "613     Semiurban           N  \n",
       "\n",
       "[589 rows x 12 columns]"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "z=np.abs(zscore(outliers))\n",
    "df1=df[(z<3).all(axis=1)]\n",
    "df1"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dc21d213",
   "metadata": {},
   "source": [
    "Now We have successfully removed outliers from the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "cdd81c7d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(589, 12)"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# checking the shape of new dataset\n",
    "df1.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "f896056e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "25\n"
     ]
    }
   ],
   "source": [
    "# Checking No. of outliers removed\n",
    "dataloss=print(df.shape[0]-df1.shape[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "137eeafb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4.071661237785016\n"
     ]
    }
   ],
   "source": [
    "# Checking the Percentage of dataloss using zscore\n",
    "datalossper=print(((df.shape[0]-df1.shape[0])/df.shape[0])*100)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "593106e3",
   "metadata": {},
   "source": [
    "We have just lost 4.07% of data which is quite good."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9456ca0d",
   "metadata": {},
   "source": [
    "# Skewness:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "f59c9e75",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Dependents           1.038787\n",
       "ApplicantIncome      2.164762\n",
       "CoapplicantIncome    2.554191\n",
       "LoanAmount           1.114173\n",
       "Loan_Amount_Term    -2.446026\n",
       "Credit_History      -2.010069\n",
       "dtype: float64"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Lets check skewness in new dataset\n",
    "df1.skew()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "31d720b2",
   "metadata": {},
   "source": [
    "We have to remove skewness of column \"ApplicantIncome\",\"CoapplicantIncome\",\"LoanAmount because because Dependents,Loan_Amount_Term,Credit_History is categorical type data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "369ec325",
   "metadata": {},
   "source": [
    "# Removing skewness using yeo-johnson method"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "037fcc1b",
   "metadata": {},
   "outputs": [],
   "source": [
    " #create a list of columns to remove skewness from these columns\n",
    "    \n",
    "skew=[\"ApplicantIncome\",\"CoapplicantIncome\",\"LoanAmount\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "24496933",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ApplicantIncome      0.028063\n",
       "CoapplicantIncome    0.203000\n",
       "LoanAmount           0.061412\n",
       "dtype: float64"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import PowerTransformer\n",
    "scaler = PowerTransformer(method=\"yeo-johnson\")\n",
    "df1[skew]=scaler.fit_transform(df1[skew].values)\n",
    "df1[skew].skew()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0076566d",
   "metadata": {},
   "source": [
    "Now we can see that we have successfully removed the skewness from all three columns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "844332dc",
   "metadata": {},
   "source": [
    "# check skewness are removed are not"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "4aa0e9d7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 3 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(ncols=3, nrows=1, figsize=(15,5))\n",
    "index = 0\n",
    "ax = ax.flatten()\n",
    "for col, value in df1[skew].items():\n",
    "    sns.distplot(value, ax=ax[index], hist=False, color=\"b\",kde_kws={\"shade\": True})\n",
    "    index += 1\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8204eaa5",
   "metadata": {},
   "source": [
    "# Data Preprocessing"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "68e84373",
   "metadata": {},
   "source": [
    "Dealing with the categorical variable:-\n",
    "    \n",
    "convert categorical data into numerical variable by using Label encoading or one_hot_encoading technique"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "96dd38d8",
   "metadata": {},
   "source": [
    "# Label Encoding:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "5b313d3e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import LabelEncoder\n",
    "le=LabelEncoder()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "f419107a",
   "metadata": {},
   "outputs": [],
   "source": [
    "#for changing all catigorical value into numeric value\n",
    "\n",
    "df1=df1.apply(le.fit_transform)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "d938dbf9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Education</th>\n",
       "      <th>Self_Employed</th>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <th>LoanAmount</th>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <th>Credit_History</th>\n",
       "      <th>Property_Area</th>\n",
       "      <th>Loan_Status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>372</td>\n",
       "      <td>71</td>\n",
       "      <td>81</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>303</td>\n",
       "      <td>59</td>\n",
       "      <td>81</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>136</td>\n",
       "      <td>71</td>\n",
       "      <td>26</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>87</td>\n",
       "      <td>160</td>\n",
       "      <td>73</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>377</td>\n",
       "      <td>71</td>\n",
       "      <td>94</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Gender  Married  Dependents  Education  Self_Employed  ApplicantIncome  \\\n",
       "0       1        0           0          0              0              372   \n",
       "1       1        1           1          0              0              303   \n",
       "2       1        1           0          0              1              136   \n",
       "3       1        1           0          1              0               87   \n",
       "4       1        0           0          0              0              377   \n",
       "\n",
       "   CoapplicantIncome  LoanAmount  Loan_Amount_Term  Credit_History  \\\n",
       "0                 71          81                 8               1   \n",
       "1                 59          81                 8               1   \n",
       "2                 71          26                 8               1   \n",
       "3                160          73                 8               1   \n",
       "4                 71          94                 8               1   \n",
       "\n",
       "   Property_Area  Loan_Status  \n",
       "0              2            1  \n",
       "1              0            0  \n",
       "2              2            1  \n",
       "3              2            1  \n",
       "4              2            1  "
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dec10c63",
   "metadata": {},
   "source": [
    "# Feature and Label Selection:¶"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "640fc57d",
   "metadata": {},
   "outputs": [],
   "source": [
    "x=df1.drop(\"Loan_Status\",axis=1)\n",
    "y=df1[\"Loan_Status\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "b6ca9c85",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(589, 11)\n",
      "(589,)\n"
     ]
    }
   ],
   "source": [
    "print(x.shape)\n",
    "print(y.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b76c3343",
   "metadata": {},
   "source": [
    "# Scalling using Standard Scaler:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "8a98264a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "scaler=StandardScaler()\n",
    "x=pd.DataFrame(scaler.fit_transform(x), columns=x.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "587b3cc3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Gender</th>\n",
       "      <th>Married</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>Education</th>\n",
       "      <th>Self_Employed</th>\n",
       "      <th>ApplicantIncome</th>\n",
       "      <th>CoapplicantIncome</th>\n",
       "      <th>LoanAmount</th>\n",
       "      <th>Loan_Amount_Term</th>\n",
       "      <th>Credit_History</th>\n",
       "      <th>Property_Area</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.476533</td>\n",
       "      <td>-1.363533</td>\n",
       "      <td>-0.728402</td>\n",
       "      <td>-0.542684</td>\n",
       "      <td>-0.384900</td>\n",
       "      <td>0.983959</td>\n",
       "      <td>-0.556886</td>\n",
       "      <td>-0.048781</td>\n",
       "      <td>0.297701</td>\n",
       "      <td>0.41349</td>\n",
       "      <td>1.222929</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.476533</td>\n",
       "      <td>0.733389</td>\n",
       "      <td>0.276349</td>\n",
       "      <td>-0.542684</td>\n",
       "      <td>-0.384900</td>\n",
       "      <td>0.481590</td>\n",
       "      <td>-0.735369</td>\n",
       "      <td>-0.048781</td>\n",
       "      <td>0.297701</td>\n",
       "      <td>0.41349</td>\n",
       "      <td>-1.313356</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.476533</td>\n",
       "      <td>0.733389</td>\n",
       "      <td>-0.728402</td>\n",
       "      <td>-0.542684</td>\n",
       "      <td>2.598076</td>\n",
       "      <td>-0.734288</td>\n",
       "      <td>-0.556886</td>\n",
       "      <td>-1.381204</td>\n",
       "      <td>0.297701</td>\n",
       "      <td>0.41349</td>\n",
       "      <td>1.222929</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.476533</td>\n",
       "      <td>0.733389</td>\n",
       "      <td>-0.728402</td>\n",
       "      <td>1.842694</td>\n",
       "      <td>-0.384900</td>\n",
       "      <td>-1.091043</td>\n",
       "      <td>0.766858</td>\n",
       "      <td>-0.242588</td>\n",
       "      <td>0.297701</td>\n",
       "      <td>0.41349</td>\n",
       "      <td>1.222929</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.476533</td>\n",
       "      <td>-1.363533</td>\n",
       "      <td>-0.728402</td>\n",
       "      <td>-0.542684</td>\n",
       "      <td>-0.384900</td>\n",
       "      <td>1.020362</td>\n",
       "      <td>-0.556886</td>\n",
       "      <td>0.266156</td>\n",
       "      <td>0.297701</td>\n",
       "      <td>0.41349</td>\n",
       "      <td>1.222929</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Gender   Married  Dependents  Education  Self_Employed  ApplicantIncome  \\\n",
       "0  0.476533 -1.363533   -0.728402  -0.542684      -0.384900         0.983959   \n",
       "1  0.476533  0.733389    0.276349  -0.542684      -0.384900         0.481590   \n",
       "2  0.476533  0.733389   -0.728402  -0.542684       2.598076        -0.734288   \n",
       "3  0.476533  0.733389   -0.728402   1.842694      -0.384900        -1.091043   \n",
       "4  0.476533 -1.363533   -0.728402  -0.542684      -0.384900         1.020362   \n",
       "\n",
       "   CoapplicantIncome  LoanAmount  Loan_Amount_Term  Credit_History  \\\n",
       "0          -0.556886   -0.048781          0.297701         0.41349   \n",
       "1          -0.735369   -0.048781          0.297701         0.41349   \n",
       "2          -0.556886   -1.381204          0.297701         0.41349   \n",
       "3           0.766858   -0.242588          0.297701         0.41349   \n",
       "4          -0.556886    0.266156          0.297701         0.41349   \n",
       "\n",
       "   Property_Area  \n",
       "0       1.222929  \n",
       "1      -1.313356  \n",
       "2       1.222929  \n",
       "3       1.222929  \n",
       "4       1.222929  "
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0f9014c4",
   "metadata": {},
   "source": [
    "# Balancing the target dataset using Oversampling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "c3da235f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    407\n",
       "0    182\n",
       "Name: Loan_Status, dtype: int64"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "y.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "490e85d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from imblearn.over_sampling import SMOTE\n",
    "\n",
    "smt=SMOTE()# instance of smote\n",
    "x,y=smt.fit_resample(x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "7e3ca327",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    407\n",
       "0    407\n",
       "Name: Loan_Status, dtype: int64"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lets check the value count again\n",
    "y.value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "91466cd3",
   "metadata": {},
   "source": [
    "here we have successfully balanced the target variable"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5bee97b3",
   "metadata": {},
   "source": [
    "# Multicollinerity"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "6e0fd6bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "from statsmodels.stats.outliers_influence import variance_inflation_factor\n",
    "def cal_vif(x):\n",
    "    vif=pd.DataFrame()\n",
    "    vif['variables']=x.columns\n",
    "    vif[\"vif_factor\"]=[variance_inflation_factor(x.values,i) for i in range (x.shape[1])]\n",
    "    return(vif)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "28bea92d",
   "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>variables</th>\n",
       "      <th>vif_factor</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Gender</td>\n",
       "      <td>1.199985</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Married</td>\n",
       "      <td>1.357065</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Dependents</td>\n",
       "      <td>1.214761</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Education</td>\n",
       "      <td>1.118707</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Self_Employed</td>\n",
       "      <td>1.056718</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>ApplicantIncome</td>\n",
       "      <td>1.639877</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>CoapplicantIncome</td>\n",
       "      <td>1.357856</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>LoanAmount</td>\n",
       "      <td>1.756514</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Loan_Amount_Term</td>\n",
       "      <td>1.065846</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Credit_History</td>\n",
       "      <td>1.015797</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Property_Area</td>\n",
       "      <td>1.031614</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            variables  vif_factor\n",
       "0              Gender    1.199985\n",
       "1             Married    1.357065\n",
       "2          Dependents    1.214761\n",
       "3           Education    1.118707\n",
       "4       Self_Employed    1.056718\n",
       "5     ApplicantIncome    1.639877\n",
       "6   CoapplicantIncome    1.357856\n",
       "7          LoanAmount    1.756514\n",
       "8    Loan_Amount_Term    1.065846\n",
       "9      Credit_History    1.015797\n",
       "10      Property_Area    1.031614"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cal_vif(x)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "480a0e95",
   "metadata": {},
   "source": [
    "VIF  is not greater so no mulcollinearity is there."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af2388c8",
   "metadata": {},
   "source": [
    "# Finding Best Random State:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "5625702a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best accuracy is  0.7551020408163265  on Random_state  112\n"
     ]
    }
   ],
   "source": [
    "max_acc=0\n",
    "max_rs=0\n",
    "for i in range(1,200):\n",
    "    x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=.30, random_state =i)\n",
    "    mod = LogisticRegression()\n",
    "    mod.fit(x_train, y_train)\n",
    "    pred_mod = mod.predict(x_test)\n",
    "    acc=accuracy_score(y_test, pred_mod)\n",
    "    if acc>max_acc:\n",
    "        max_acc=acc\n",
    "        max_rs=i\n",
    "print(\"Best accuracy is \",max_acc,\" on Random_state \",max_rs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "01704a1c",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=.27,random_state=28)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4b651a5f",
   "metadata": {},
   "source": [
    "# Model building using Classification Algorithms\n",
    "\n",
    "since our target column loan_status is an object column this became classification problem"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "af8d4bb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# model_selection is function  created bcz when we want to use another model then only call this function\n",
    "x_train, x_test, y_train, y_test = train_test_split(x,y, test_size = 0.20, random_state=26)\n",
    "def model_selection(algorithm_instance,x_train, x_test, y_train, y_test):\n",
    "    algorithm_instance.fit(x_train,y_train)\n",
    "    model1_pred=algorithm_instance.predict(x_test)\n",
    "    \n",
    "    print(\"accuracy\",accuracy_score(y_test,model1_pred)*100)\n",
    "    print(confusion_matrix(y_test,model1_pred))\n",
    "    print(classification_report(y_test,model1_pred))\n",
    "    \n",
    "    \n",
    "    \n",
    "def model_cv(algorithm_instance,trainx,trainy):\n",
    "    for j in range(4,10):\n",
    "        lsscore=cross_val_score(algorithm_instance,trainx,trainy,cv=j)\n",
    "        print(lsscore)\n",
    "        lsc=lsscore.mean()\n",
    "        print(\" At cv =\",j)\n",
    "        print(\"cross validation score \",lsc*100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "c6ab0d2f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy 80.98159509202453\n",
      "[[51 27]\n",
      " [ 4 81]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.93      0.65      0.77        78\n",
      "           1       0.75      0.95      0.84        85\n",
      "\n",
      "    accuracy                           0.81       163\n",
      "   macro avg       0.84      0.80      0.80       163\n",
      "weighted avg       0.83      0.81      0.80       163\n",
      "\n",
      "[0.69607843 0.79411765 0.89162562 0.83743842]\n",
      " At cv = 4\n",
      "cross validation score  80.48150294600599\n",
      "[0.70552147 0.75460123 0.85889571 0.85276074 0.87037037]\n",
      " At cv = 5\n",
      "cross validation score  80.8429902294933\n",
      "[0.68382353 0.69852941 0.75735294 0.875      0.82222222 0.88888889]\n",
      " At cv = 6\n",
      "cross validation score  78.76361655773421\n",
      "[0.74358974 0.66666667 0.73275862 0.84482759 0.87068966 0.86206897\n",
      " 0.86206897]\n",
      " At cv = 7\n",
      "cross validation score  79.7524314765694\n",
      "[0.68627451 0.67647059 0.79411765 0.79411765 0.88235294 0.87254902\n",
      " 0.85148515 0.89108911]\n",
      " At cv = 8\n",
      "cross validation score  80.60570762958649\n",
      "[0.7032967  0.68131868 0.74725275 0.71428571 0.84444444 0.92222222\n",
      " 0.83333333 0.82222222 0.9       ]\n",
      " At cv = 9\n",
      "cross validation score  79.64862298195632\n"
     ]
    }
   ],
   "source": [
    "gbc=GradientBoostingClassifier()\n",
    "model_selection(gbc,x_train, x_test, y_train, y_test)\n",
    "model_cv(gbc,x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "785e3f63",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy 76.68711656441718\n",
      "[[54 24]\n",
      " [14 71]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.79      0.69      0.74        78\n",
      "           1       0.75      0.84      0.79        85\n",
      "\n",
      "    accuracy                           0.77       163\n",
      "   macro avg       0.77      0.76      0.76       163\n",
      "weighted avg       0.77      0.77      0.77       163\n",
      "\n",
      "[0.65686275 0.74509804 0.80295567 0.71428571]\n",
      " At cv = 4\n",
      "cross validation score  72.98005409060175\n",
      "[0.66871166 0.71165644 0.82822086 0.79141104 0.75308642]\n",
      " At cv = 5\n",
      "cross validation score  75.06172839506172\n",
      "[0.69117647 0.72794118 0.69117647 0.83823529 0.72592593 0.79259259]\n",
      " At cv = 6\n",
      "cross validation score  74.45079883805374\n",
      "[0.67521368 0.65811966 0.71551724 0.76724138 0.84482759 0.81034483\n",
      " 0.75862069]\n",
      " At cv = 7\n",
      "cross validation score  74.71264367816092\n",
      "[0.69607843 0.62745098 0.78431373 0.78431373 0.83333333 0.84313725\n",
      " 0.75247525 0.76237624]\n",
      " At cv = 8\n",
      "cross validation score  76.04348670161134\n",
      "[0.7032967  0.67032967 0.74725275 0.69230769 0.77777778 0.88888889\n",
      " 0.8        0.74444444 0.77777778]\n",
      " At cv = 9\n",
      "cross validation score  75.57861891195225\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "ad=AdaBoostClassifier()\n",
    "model_selection(ad,x_train, x_test, y_train, y_test)\n",
    "model_cv(ad,x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "c3369a7d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy 73.00613496932516\n",
      "[[58 20]\n",
      " [24 61]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.71      0.74      0.72        78\n",
      "           1       0.75      0.72      0.73        85\n",
      "\n",
      "    accuracy                           0.73       163\n",
      "   macro avg       0.73      0.73      0.73       163\n",
      "weighted avg       0.73      0.73      0.73       163\n",
      "\n",
      "[0.73039216 0.72058824 0.77339901 0.74384236]\n",
      " At cv = 4\n",
      "cross validation score  74.20554428668018\n",
      "[0.7791411  0.71165644 0.76687117 0.80368098 0.7345679 ]\n",
      " At cv = 5\n",
      "cross validation score  75.91835188972205\n",
      "[0.78676471 0.72794118 0.75       0.82352941 0.78518519 0.75555556]\n",
      " At cv = 6\n",
      "cross validation score  77.14960058097313\n",
      "[0.79487179 0.70940171 0.69827586 0.77586207 0.75       0.79310345\n",
      " 0.75      ]\n",
      " At cv = 7\n",
      "cross validation score  75.30735547976929\n",
      "[0.79411765 0.70588235 0.74509804 0.74509804 0.79411765 0.7745098\n",
      " 0.78217822 0.76237624]\n",
      " At cv = 8\n",
      "cross validation score  76.29222481071636\n",
      "[0.83516484 0.7032967  0.73626374 0.69230769 0.76666667 0.81111111\n",
      " 0.77777778 0.77777778 0.75555556]\n",
      " At cv = 9\n",
      "cross validation score  76.17690951024285\n"
     ]
    }
   ],
   "source": [
    "knn=KNeighborsClassifier()\n",
    "model_selection(knn,x_train, x_test, y_train, y_test)\n",
    "model_cv(knn,x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "206302f3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy 85.2760736196319\n",
      "[[59 19]\n",
      " [ 5 80]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.92      0.76      0.83        78\n",
      "           1       0.81      0.94      0.87        85\n",
      "\n",
      "    accuracy                           0.85       163\n",
      "   macro avg       0.86      0.85      0.85       163\n",
      "weighted avg       0.86      0.85      0.85       163\n",
      "\n",
      "[0.74509804 0.80882353 0.85221675 0.8817734 ]\n",
      " At cv = 4\n",
      "cross validation score  82.19779291026757\n",
      "[0.75460123 0.80981595 0.87116564 0.88957055 0.90123457]\n",
      " At cv = 5\n",
      "cross validation score  84.52775884268725\n",
      "[0.73529412 0.76470588 0.80882353 0.89705882 0.88148148 0.95555556]\n",
      " At cv = 6\n",
      "cross validation score  84.04865649963689\n",
      "[0.75213675 0.77777778 0.81896552 0.87931034 0.87068966 0.89655172\n",
      " 0.90517241]\n",
      " At cv = 7\n",
      "cross validation score  84.29434550124206\n",
      "[0.74509804 0.68627451 0.82352941 0.80392157 0.92156863 0.89215686\n",
      " 0.89108911 0.93069307]\n",
      " At cv = 8\n",
      "cross validation score  83.67913997282082\n",
      "[0.78021978 0.65934066 0.82417582 0.79120879 0.94444444 0.93333333\n",
      " 0.87777778 0.91111111 0.95555556]\n",
      " At cv = 9\n",
      "cross validation score  85.30185863519196\n"
     ]
    }
   ],
   "source": [
    "rf= RandomForestClassifier(random_state=90)\n",
    "model_selection(rf,x_train, x_test, y_train, y_test)\n",
    "model_cv(rf,x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "1c9b33bd",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy 76.07361963190185\n",
      "[[46 32]\n",
      " [ 7 78]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.87      0.59      0.70        78\n",
      "           1       0.71      0.92      0.80        85\n",
      "\n",
      "    accuracy                           0.76       163\n",
      "   macro avg       0.79      0.75      0.75       163\n",
      "weighted avg       0.79      0.76      0.75       163\n",
      "\n",
      "[0.66666667 0.75       0.78325123 0.69950739]\n",
      " At cv = 4\n",
      "cross validation score  72.48563218390804\n",
      "[0.70552147 0.74846626 0.79141104 0.76687117 0.70987654]\n",
      " At cv = 5\n",
      "cross validation score  74.44292963720368\n",
      "[0.69852941 0.71323529 0.72058824 0.80147059 0.71851852 0.74074074]\n",
      " At cv = 6\n",
      "cross validation score  73.21804647785038\n",
      "[0.71794872 0.69230769 0.74137931 0.75       0.80172414 0.71551724\n",
      " 0.71551724]\n",
      " At cv = 7\n",
      "cross validation score  73.34849058986991\n",
      "[0.68627451 0.67647059 0.78431373 0.69607843 0.80392157 0.7745098\n",
      " 0.73267327 0.72277228]\n",
      " At cv = 8\n",
      "cross validation score  73.46267715006796\n",
      "[0.71428571 0.68131868 0.75824176 0.7032967  0.72222222 0.82222222\n",
      " 0.76666667 0.63333333 0.74444444]\n",
      " At cv = 9\n",
      "cross validation score  72.73368606701939\n"
     ]
    }
   ],
   "source": [
    "sv=SVC()\n",
    "model_selection(sv,x_train, x_test, y_train, y_test)\n",
    "model_cv(sv,x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "85380f34",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy 76.07361963190185\n",
      "[[58 20]\n",
      " [19 66]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.75      0.74      0.75        78\n",
      "           1       0.77      0.78      0.77        85\n",
      "\n",
      "    accuracy                           0.76       163\n",
      "   macro avg       0.76      0.76      0.76       163\n",
      "weighted avg       0.76      0.76      0.76       163\n",
      "\n",
      "[0.71078431 0.76470588 0.82758621 0.8226601 ]\n",
      " At cv = 4\n",
      "cross validation score  78.14341253742876\n",
      "[0.72392638 0.76687117 0.80368098 0.79754601 0.79012346]\n",
      " At cv = 5\n",
      "cross validation score  77.64295993334848\n",
      "[0.69852941 0.76470588 0.77941176 0.89705882 0.85925926 0.78518519]\n",
      " At cv = 6\n",
      "cross validation score  79.73583877995644\n",
      "[0.66666667 0.67521368 0.74137931 0.81034483 0.86206897 0.85344828\n",
      " 0.81896552]\n",
      " At cv = 7\n",
      "cross validation score  77.54410340617238\n",
      "[0.66666667 0.73529412 0.76470588 0.78431373 0.8627451  0.83333333\n",
      " 0.83168317 0.79207921]\n",
      " At cv = 8\n",
      "cross validation score  78.38526499708794\n",
      "[0.71428571 0.71428571 0.79120879 0.7032967  0.77777778 0.86666667\n",
      " 0.86666667 0.8        0.77777778]\n",
      " At cv = 9\n",
      "cross validation score  77.91073124406458\n"
     ]
    }
   ],
   "source": [
    "# model dtc\n",
    "dtc=DecisionTreeClassifier(random_state=28)\n",
    "model_selection(dtc,x_train, x_test, y_train, y_test)\n",
    "model_cv(dtc,x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "cbf4d281",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy 73.61963190184049\n",
      "[[45 33]\n",
      " [10 75]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.82      0.58      0.68        78\n",
      "           1       0.69      0.88      0.78        85\n",
      "\n",
      "    accuracy                           0.74       163\n",
      "   macro avg       0.76      0.73      0.73       163\n",
      "weighted avg       0.75      0.74      0.73       163\n",
      "\n",
      "[0.67156863 0.74509804 0.74384236 0.67980296]\n",
      " At cv = 4\n",
      "cross validation score  71.00779967159276\n",
      "[0.68711656 0.73619632 0.71779141 0.6993865  0.67901235]\n",
      " At cv = 5\n",
      "cross validation score  70.39006286450049\n",
      "[0.67647059 0.69852941 0.73529412 0.74264706 0.71111111 0.6962963 ]\n",
      " At cv = 6\n",
      "cross validation score  71.00580973129993\n",
      "[0.7008547  0.69230769 0.75862069 0.72413793 0.75862069 0.72413793\n",
      " 0.67241379]\n",
      " At cv = 7\n",
      "cross validation score  71.8727632520736\n",
      "[0.69607843 0.65686275 0.76470588 0.73529412 0.74509804 0.75490196\n",
      " 0.67326733 0.69306931]\n",
      " At cv = 8\n",
      "cross validation score  71.49097262667443\n",
      "[0.7032967  0.67032967 0.76923077 0.73626374 0.72222222 0.76666667\n",
      " 0.76666667 0.61111111 0.71111111]\n",
      " At cv = 9\n",
      "cross validation score  71.74331840998508\n"
     ]
    }
   ],
   "source": [
    "# model dtc\n",
    "lr=LogisticRegression(random_state=28)\n",
    "model_selection(lr,x_train, x_test, y_train, y_test)\n",
    "model_cv(lr,x,y)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c75f83f",
   "metadata": {},
   "source": [
    "# ROC_AUC_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d1385de0",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"roc_auc_score for logistic model=   \",roc_auc_score(y_test,lr.predict(x_test)))\n",
    "print(\"roc_auc_score for DecesionTreeClassifier=   \",roc_auc_score(y_test,dtc.predict(x_test)))\n",
    "print(\"roc_auc_score for RandomFarestClassifier=   \",roc_auc_score(y_test,rf.predict(x_test)))\n",
    "print(\"roc_auc_score for knn=   \",roc_auc_score(y_test,knn.predict(x_test)))\n",
    "print(\"roc_auc_score for svc=   \",roc_auc_score(y_test,sv.predict(x_test)))\n",
    "print(\"roc_auc_score for AdaBoostClassifier=   \",roc_auc_score(y_test,ad.predict(x_test)))\n",
    "print(\"roc_auc_score for GradientBoostingClassifier=   \",roc_auc_score(y_test,gbc.predict(x_test)))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "92566c34",
   "metadata": {},
   "outputs": [],
   "source": [
    "disp = plot_roc_curve(sv,x_test,y_test)\n",
    "plot_roc_curve(knn, x_test, y_test, ax=disp.ax_)     # ax_=Axes with confusion matrix\n",
    "plot_roc_curve(lr, x_test,y_test, ax=disp.ax_)\n",
    "plot_roc_curve(rf, x_test,y_test, ax=disp.ax_)\n",
    "plot_roc_curve(dtc, x_test,y_test, ax=disp.ax_)\n",
    "plot_roc_curve(ad, x_test,y_test, ax=disp.ax_)\n",
    "plot_roc_curve(gbc, x_test,y_test, ax=disp.ax_)\n",
    "\n",
    "\n",
    "plt.legend(prop={'size':11}, loc='lower right')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "260c2b91",
   "metadata": {},
   "source": [
    "AUC - ROC curve is a performance measurement for the classification problems at various threshold settings RandomFarestClassifier has ROC AUC highest score, hence choosing it is our best model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2186a6bd",
   "metadata": {},
   "source": [
    "# Compare All Model Performance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "1ffaf71c",
   "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>Model</th>\n",
       "      <th>Model accuracy</th>\n",
       "      <th>Cross validation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>RandomForest classifier</td>\n",
       "      <td>85</td>\n",
       "      <td>85</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>DecisionTree classifier</td>\n",
       "      <td>70</td>\n",
       "      <td>77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>KNeighbour classifier</td>\n",
       "      <td>74</td>\n",
       "      <td>76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>svm</td>\n",
       "      <td>76</td>\n",
       "      <td>73</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>LogisticRegression</td>\n",
       "      <td>69</td>\n",
       "      <td>71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>AdaBoostClassifier</td>\n",
       "      <td>78</td>\n",
       "      <td>76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>GradientBoostingClassifier</td>\n",
       "      <td>81</td>\n",
       "      <td>80</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        Model  Model accuracy  Cross validation\n",
       "0     RandomForest classifier              85                85\n",
       "1     DecisionTree classifier              70                77\n",
       "2       KNeighbour classifier              74                76\n",
       "3                         svm              76                73\n",
       "4          LogisticRegression              69                71\n",
       "5          AdaBoostClassifier              78                76\n",
       "6  GradientBoostingClassifier              81                80"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "results = pd.DataFrame({\n",
    "\n",
    "    'Model': [\"RandomForest classifier\",\"DecisionTree classifier\",\"KNeighbour classifier\",\"svm\",\"LogisticRegression\",\"AdaBoostClassifier\",\"GradientBoostingClassifier\"],\n",
    "\n",
    "    'Model accuracy': [85,70,74,76,69,78,81],\n",
    "\n",
    "     \"Cross validation\":[85,77,76,73,71,76,80],\n",
    "    \n",
    "  \n",
    "    \n",
    "    })\n",
    "\n",
    "results"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e41ad29c",
   "metadata": {},
   "source": [
    "# Hyper Parameter Tuning For Best Model\n",
    "\n",
    "Choosing best model as RandomForest classifier\" Model\n",
    "\n",
    "minimum difference between cross validation and Accuracy score is 0\n",
    "\n",
    "Roc_auc score is maximum"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "e15b85bb",
   "metadata": {},
   "outputs": [],
   "source": [
    "parameter = {'criterion':['gini','entropy'],\n",
    "             'max_depth': [10,15,20,25],\n",
    "             'n_estimators':[100,200,300,400],\n",
    "             'max_features': [\"auto\",\"sqrt\",\"log2\"]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "5e5b189f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'criterion': 'gini',\n",
       " 'max_depth': 20,\n",
       " 'max_features': 'log2',\n",
       " 'n_estimators': 100}"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gcv=GridSearchCV(RandomForestClassifier(),parameter,cv=5)\n",
    "gcv.fit(x_train,y_train)\n",
    "gcv.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "2d2737c3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "85.88957055214725\n"
     ]
    }
   ],
   "source": [
    "final_model=RandomForestClassifier(criterion=\"gini\", max_depth=20 , max_features=\"log2\" ,n_estimators=100)\n",
    "final_model.fit(x_train,y_train)\n",
    "pred=final_model.predict(x_test)\n",
    "acc=accuracy_score(y_test,pred)\n",
    "\n",
    "print(acc*100)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8c4b885c",
   "metadata": {},
   "source": [
    "# Confusion_matrix for Best model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "ac66e32f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "cm= confusion_matrix(y_test,pred)\n",
    "\n",
    "x_axis_labels= [\"Yes\",\"No\"]\n",
    "y_axis_labels=[\"Yes\",\"No\"]\n",
    "\n",
    "f,ax=plt.subplots(figsize=(7,5))\n",
    "sns.heatmap(cm, annot=True, linewidth=0.2, linecolor=\"black\", fmt=\".0f\")\n",
    "plt.xlabel(\"Predicted\")\n",
    "plt.ylabel(\"Actual\")\n",
    "plt.title(\"Confusion Matrix for RFC\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d921d6b7",
   "metadata": {},
   "source": [
    "# Saving ,Loading and Prediction of the best Classification ML model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "61a81f47",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "filename_1=\"Loan_status.pkl\"\n",
    "pickle.dump(final_model,open(filename_1,\"wb\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "966eb3c1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "85.88957055214725\n"
     ]
    }
   ],
   "source": [
    "loaded_model=pickle.load(open(\"Loan_status.pkl\",\"rb\"))\n",
    "result=loaded_model.score(x_test,y_test)\n",
    "print(result*100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "0e4a6836",
   "metadata": {},
   "outputs": [],
   "source": [
    "result=pd.DataFrame([loaded_model.predict(x_test)[:],pred[:]],index=[\"predicted\",\"original\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "c422bc2b",
   "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>predicted</th>\n",
       "      <th>original</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>158</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>159</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>160</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>161</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>162</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>163 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     predicted  original\n",
       "0            0         0\n",
       "1            1         1\n",
       "2            0         0\n",
       "3            1         1\n",
       "4            0         0\n",
       "..         ...       ...\n",
       "158          1         1\n",
       "159          1         1\n",
       "160          1         1\n",
       "161          1         1\n",
       "162          1         1\n",
       "\n",
       "[163 rows x 2 columns]"
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result.T"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}