pree62/MLR_50_Startups.ipynb

## MLR_50_Startups.ipynb
{
  "cells": [
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:45.022692Z",
          "start_time": "2023-01-16T08:22:44.999341Z"
        },
        "trusted": false
      },
      "id": "b1b6c0da",
      "cell_type": "code",
      "source": "import pandas as pd \nimport numpy as np \nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport statsmodels.formula.api as smf\nfrom statsmodels.graphics.regressionplots import influence_plot",
      "execution_count": 133,
      "outputs": []
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:45.111269Z",
          "start_time": "2023-01-16T08:22:45.028160Z"
        },
        "trusted": false
      },
      "id": "eacb567f",
      "cell_type": "code",
      "source": "df=pd.read_csv('50_Startups.csv')\ndf.head()",
      "execution_count": 134,
      "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>R&amp;D Spend</th>\n      <th>Administration</th>\n      <th>Marketing Spend</th>\n      <th>State</th>\n      <th>Profit</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>165349.20</td>\n      <td>136897.80</td>\n      <td>471784.10</td>\n      <td>New York</td>\n      <td>192261.83</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>162597.70</td>\n      <td>151377.59</td>\n      <td>443898.53</td>\n      <td>California</td>\n      <td>191792.06</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>153441.51</td>\n      <td>101145.55</td>\n      <td>407934.54</td>\n      <td>Florida</td>\n      <td>191050.39</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>144372.41</td>\n      <td>118671.85</td>\n      <td>383199.62</td>\n      <td>New York</td>\n      <td>182901.99</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>142107.34</td>\n      <td>91391.77</td>\n      <td>366168.42</td>\n      <td>Florida</td>\n      <td>166187.94</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "   R&D Spend  Administration  Marketing Spend       State     Profit\n0  165349.20       136897.80        471784.10    New York  192261.83\n1  162597.70       151377.59        443898.53  California  191792.06\n2  153441.51       101145.55        407934.54     Florida  191050.39\n3  144372.41       118671.85        383199.62    New York  182901.99\n4  142107.34        91391.77        366168.42     Florida  166187.94"
          },
          "execution_count": 134,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:45.143354Z",
          "start_time": "2023-01-16T08:22:45.111779Z"
        },
        "trusted": false
      },
      "id": "23a152e7",
      "cell_type": "code",
      "source": "df.info()",
      "execution_count": 135,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 50 entries, 0 to 49\nData columns (total 5 columns):\n #   Column           Non-Null Count  Dtype  \n---  ------           --------------  -----  \n 0   R&D Spend        50 non-null     float64\n 1   Administration   50 non-null     float64\n 2   Marketing Spend  50 non-null     float64\n 3   State            50 non-null     object \n 4   Profit           50 non-null     float64\ndtypes: float64(4), object(1)\nmemory usage: 2.1+ KB\n"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:45.203396Z",
          "start_time": "2023-01-16T08:22:45.147909Z"
        },
        "trusted": false
      },
      "id": "d4a2c805",
      "cell_type": "code",
      "source": "df.describe()",
      "execution_count": 136,
      "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>R&amp;D Spend</th>\n      <th>Administration</th>\n      <th>Marketing Spend</th>\n      <th>Profit</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>50.000000</td>\n      <td>50.000000</td>\n      <td>50.000000</td>\n      <td>50.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>73721.615600</td>\n      <td>121344.639600</td>\n      <td>211025.097800</td>\n      <td>112012.639200</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>45902.256482</td>\n      <td>28017.802755</td>\n      <td>122290.310726</td>\n      <td>40306.180338</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>0.000000</td>\n      <td>51283.140000</td>\n      <td>0.000000</td>\n      <td>14681.400000</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>39936.370000</td>\n      <td>103730.875000</td>\n      <td>129300.132500</td>\n      <td>90138.902500</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>73051.080000</td>\n      <td>122699.795000</td>\n      <td>212716.240000</td>\n      <td>107978.190000</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>101602.800000</td>\n      <td>144842.180000</td>\n      <td>299469.085000</td>\n      <td>139765.977500</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>165349.200000</td>\n      <td>182645.560000</td>\n      <td>471784.100000</td>\n      <td>192261.830000</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "           R&D Spend  Administration  Marketing Spend         Profit\ncount      50.000000       50.000000        50.000000      50.000000\nmean    73721.615600   121344.639600    211025.097800  112012.639200\nstd     45902.256482    28017.802755    122290.310726   40306.180338\nmin         0.000000    51283.140000         0.000000   14681.400000\n25%     39936.370000   103730.875000    129300.132500   90138.902500\n50%     73051.080000   122699.795000    212716.240000  107978.190000\n75%    101602.800000   144842.180000    299469.085000  139765.977500\nmax    165349.200000   182645.560000    471784.100000  192261.830000"
          },
          "execution_count": 136,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:45.218716Z",
          "start_time": "2023-01-16T08:22:45.204381Z"
        },
        "trusted": false
      },
      "id": "96ea3edd",
      "cell_type": "code",
      "source": "#dropping state column as it is of object type\ndf.drop([\"State\"],inplace=True,axis = 1)",
      "execution_count": 137,
      "outputs": []
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:45.250868Z",
          "start_time": "2023-01-16T08:22:45.220666Z"
        },
        "trusted": false
      },
      "id": "65c1aae5",
      "cell_type": "code",
      "source": "#Y(dependent variable is profit) rest all are independent variable \ndf.isnull().sum()\n#there are no null values",
      "execution_count": 138,
      "outputs": [
        {
          "data": {
            "text/plain": "R&D Spend          0\nAdministration     0\nMarketing Spend    0\nProfit             0\ndtype: int64"
          },
          "execution_count": 138,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:45.287481Z",
          "start_time": "2023-01-16T08:22:45.250868Z"
        },
        "trusted": false
      },
      "id": "d6dca241",
      "cell_type": "code",
      "source": "df.corr()",
      "execution_count": 139,
      "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>R&amp;D Spend</th>\n      <th>Administration</th>\n      <th>Marketing Spend</th>\n      <th>Profit</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>R&amp;D Spend</th>\n      <td>1.000000</td>\n      <td>0.241955</td>\n      <td>0.724248</td>\n      <td>0.972900</td>\n    </tr>\n    <tr>\n      <th>Administration</th>\n      <td>0.241955</td>\n      <td>1.000000</td>\n      <td>-0.032154</td>\n      <td>0.200717</td>\n    </tr>\n    <tr>\n      <th>Marketing Spend</th>\n      <td>0.724248</td>\n      <td>-0.032154</td>\n      <td>1.000000</td>\n      <td>0.747766</td>\n    </tr>\n    <tr>\n      <th>Profit</th>\n      <td>0.972900</td>\n      <td>0.200717</td>\n      <td>0.747766</td>\n      <td>1.000000</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "                 R&D Spend  Administration  Marketing Spend    Profit\nR&D Spend         1.000000        0.241955         0.724248  0.972900\nAdministration    0.241955        1.000000        -0.032154  0.200717\nMarketing Spend   0.724248       -0.032154         1.000000  0.747766\nProfit            0.972900        0.200717         0.747766  1.000000"
          },
          "execution_count": 139,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.397277Z",
          "start_time": "2023-01-16T08:22:45.287481Z"
        },
        "trusted": false
      },
      "id": "00f5b920",
      "cell_type": "code",
      "source": "sns.set_style(\"darkgrid\")\nsns.pairplot(df)",
      "execution_count": 140,
      "outputs": [
        {
          "data": {
            "text/plain": "<seaborn.axisgrid.PairGrid at 0x16d3dc6f7f0>"
          },
          "execution_count": 140,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.438897Z",
          "start_time": "2023-01-16T08:22:48.401658Z"
        },
        "trusted": false
      },
      "id": "a28ed570",
      "cell_type": "code",
      "source": "df=df.rename({'R&D Spend':'RS','Administration':'Ad','Marketing Spend':'MS','Profit':'P'},axis=1)\ndf.head()",
      "execution_count": 141,
      "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>RS</th>\n      <th>Ad</th>\n      <th>MS</th>\n      <th>P</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>165349.20</td>\n      <td>136897.80</td>\n      <td>471784.10</td>\n      <td>192261.83</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>162597.70</td>\n      <td>151377.59</td>\n      <td>443898.53</td>\n      <td>191792.06</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>153441.51</td>\n      <td>101145.55</td>\n      <td>407934.54</td>\n      <td>191050.39</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>144372.41</td>\n      <td>118671.85</td>\n      <td>383199.62</td>\n      <td>182901.99</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>142107.34</td>\n      <td>91391.77</td>\n      <td>366168.42</td>\n      <td>166187.94</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "          RS         Ad         MS          P\n0  165349.20  136897.80  471784.10  192261.83\n1  162597.70  151377.59  443898.53  191792.06\n2  153441.51  101145.55  407934.54  191050.39\n3  144372.41  118671.85  383199.62  182901.99\n4  142107.34   91391.77  366168.42  166187.94"
          },
          "execution_count": 141,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.509785Z",
          "start_time": "2023-01-16T08:22:48.444513Z"
        },
        "trusted": false
      },
      "id": "3075d36a",
      "cell_type": "code",
      "source": "model1=smf.ols('P~RS+Ad+MS',data=df).fit()\nmodel1.summary()",
      "execution_count": 142,
      "outputs": [
        {
          "data": {
            "text/html": "<table class=\"simpletable\">\n<caption>OLS Regression Results</caption>\n<tr>\n  <th>Dep. Variable:</th>            <td>P</td>        <th>  R-squared:         </th> <td>   0.951</td>\n</tr>\n<tr>\n  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.948</td>\n</tr>\n<tr>\n  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   296.0</td>\n</tr>\n<tr>\n  <th>Date:</th>             <td>Mon, 16 Jan 2023</td> <th>  Prob (F-statistic):</th> <td>4.53e-30</td>\n</tr>\n<tr>\n  <th>Time:</th>                 <td>13:52:48</td>     <th>  Log-Likelihood:    </th> <td> -525.39</td>\n</tr>\n<tr>\n  <th>No. Observations:</th>      <td>    50</td>      <th>  AIC:               </th> <td>   1059.</td>\n</tr>\n<tr>\n  <th>Df Residuals:</th>          <td>    46</td>      <th>  BIC:               </th> <td>   1066.</td>\n</tr>\n<tr>\n  <th>Df Model:</th>              <td>     3</td>      <th>                     </th>     <td> </td>   \n</tr>\n<tr>\n  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n</tr>\n<tr>\n  <th>Intercept</th> <td> 5.012e+04</td> <td> 6572.353</td> <td>    7.626</td> <td> 0.000</td> <td> 3.69e+04</td> <td> 6.34e+04</td>\n</tr>\n<tr>\n  <th>RS</th>        <td>    0.8057</td> <td>    0.045</td> <td>   17.846</td> <td> 0.000</td> <td>    0.715</td> <td>    0.897</td>\n</tr>\n<tr>\n  <th>Ad</th>        <td>   -0.0268</td> <td>    0.051</td> <td>   -0.526</td> <td> 0.602</td> <td>   -0.130</td> <td>    0.076</td>\n</tr>\n<tr>\n  <th>MS</th>        <td>    0.0272</td> <td>    0.016</td> <td>    1.655</td> <td> 0.105</td> <td>   -0.006</td> <td>    0.060</td>\n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n  <th>Omnibus:</th>       <td>14.838</td> <th>  Durbin-Watson:     </th> <td>   1.282</td>\n</tr>\n<tr>\n  <th>Prob(Omnibus):</th> <td> 0.001</td> <th>  Jarque-Bera (JB):  </th> <td>  21.442</td>\n</tr>\n<tr>\n  <th>Skew:</th>          <td>-0.949</td> <th>  Prob(JB):          </th> <td>2.21e-05</td>\n</tr>\n<tr>\n  <th>Kurtosis:</th>      <td> 5.586</td> <th>  Cond. No.          </th> <td>1.40e+06</td>\n</tr>\n</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 1.4e+06. This might indicate that there are<br/>strong multicollinearity or other numerical problems.",
            "text/plain": "<class 'statsmodels.iolib.summary.Summary'>\n\"\"\"\n                            OLS Regression Results                            \n==============================================================================\nDep. Variable:                      P   R-squared:                       0.951\nModel:                            OLS   Adj. R-squared:                  0.948\nMethod:                 Least Squares   F-statistic:                     296.0\nDate:                Mon, 16 Jan 2023   Prob (F-statistic):           4.53e-30\nTime:                        13:52:48   Log-Likelihood:                -525.39\nNo. Observations:                  50   AIC:                             1059.\nDf Residuals:                      46   BIC:                             1066.\nDf Model:                           3                                         \nCovariance Type:            nonrobust                                         \n==============================================================================\n                 coef    std err          t      P>|t|      [0.025      0.975]\n------------------------------------------------------------------------------\nIntercept   5.012e+04   6572.353      7.626      0.000    3.69e+04    6.34e+04\nRS             0.8057      0.045     17.846      0.000       0.715       0.897\nAd            -0.0268      0.051     -0.526      0.602      -0.130       0.076\nMS             0.0272      0.016      1.655      0.105      -0.006       0.060\n==============================================================================\nOmnibus:                       14.838   Durbin-Watson:                   1.282\nProb(Omnibus):                  0.001   Jarque-Bera (JB):               21.442\nSkew:                          -0.949   Prob(JB):                     2.21e-05\nKurtosis:                       5.586   Cond. No.                     1.40e+06\n==============================================================================\n\nNotes:\n[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n[2] The condition number is large, 1.4e+06. This might indicate that there are\nstrong multicollinearity or other numerical problems.\n\"\"\""
          },
          "execution_count": 142,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.536066Z",
          "start_time": "2023-01-16T08:22:48.509785Z"
        },
        "trusted": false
      },
      "id": "fdccde1f",
      "cell_type": "code",
      "source": "model1.resid",
      "execution_count": 143,
      "outputs": [
        {
          "data": {
            "text/plain": "0      -259.422890\n1      2635.291768\n2      8903.110904\n3      9205.289974\n4     -5951.574183\n5     -6589.660571\n6     -1991.586669\n7     -4268.763048\n8       470.070301\n9     -5124.724110\n10    10612.933633\n11     8685.687039\n12    12447.465818\n13     6819.358337\n14   -16945.996335\n15   -16318.119985\n16    10077.524599\n17    -4822.077208\n18    -4747.326806\n19     7141.643633\n20     1834.360769\n21    -6006.431640\n22    -4354.731717\n23    -1262.625221\n24    -4810.926113\n25     5166.614935\n26    -4867.035350\n27    -9399.761457\n28     1622.353995\n29     -790.343452\n30      485.217064\n31     -204.296276\n32    -1573.488985\n33    -1136.087805\n34     7673.526259\n35     5967.910432\n36    15422.015415\n37      329.602292\n38    11531.629352\n39    -2723.251977\n40     3423.956009\n41     2996.273761\n42      878.078179\n43     9591.940037\n44      588.975084\n45    17275.430313\n46    -6675.456853\n47    -3930.858983\n48   -13497.978158\n49   -33533.734111\ndtype: float64"
          },
          "execution_count": 143,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.554374Z",
          "start_time": "2023-01-16T08:22:48.540776Z"
        },
        "trusted": false
      },
      "id": "afe44439",
      "cell_type": "code",
      "source": "#t and p values\nprint(model1.tvalues,'\\n',model1.pvalues)",
      "execution_count": 144,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "Intercept     7.626218\nRS           17.846374\nAd           -0.525507\nMS            1.655077\ndtype: float64 \n Intercept    1.057379e-09\nRS           2.634968e-22\nAd           6.017551e-01\nMS           1.047168e-01\ndtype: float64\n"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.616928Z",
          "start_time": "2023-01-16T08:22:48.560649Z"
        },
        "trusted": false
      },
      "id": "a2bae41d",
      "cell_type": "code",
      "source": "ml_ad=smf.ols('P~Ad',data=df).fit()\nml_ad.summary()",
      "execution_count": 145,
      "outputs": [
        {
          "data": {
            "text/html": "<table class=\"simpletable\">\n<caption>OLS Regression Results</caption>\n<tr>\n  <th>Dep. Variable:</th>            <td>P</td>        <th>  R-squared:         </th> <td>   0.040</td>\n</tr>\n<tr>\n  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.020</td>\n</tr>\n<tr>\n  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   2.015</td>\n</tr>\n<tr>\n  <th>Date:</th>             <td>Mon, 16 Jan 2023</td> <th>  Prob (F-statistic):</th>  <td> 0.162</td> \n</tr>\n<tr>\n  <th>Time:</th>                 <td>13:52:48</td>     <th>  Log-Likelihood:    </th> <td> -599.63</td>\n</tr>\n<tr>\n  <th>No. Observations:</th>      <td>    50</td>      <th>  AIC:               </th> <td>   1203.</td>\n</tr>\n<tr>\n  <th>Df Residuals:</th>          <td>    48</td>      <th>  BIC:               </th> <td>   1207.</td>\n</tr>\n<tr>\n  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>   \n</tr>\n<tr>\n  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n</tr>\n<tr>\n  <th>Intercept</th> <td> 7.697e+04</td> <td> 2.53e+04</td> <td>    3.040</td> <td> 0.004</td> <td> 2.61e+04</td> <td> 1.28e+05</td>\n</tr>\n<tr>\n  <th>Ad</th>        <td>    0.2887</td> <td>    0.203</td> <td>    1.419</td> <td> 0.162</td> <td>   -0.120</td> <td>    0.698</td>\n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n  <th>Omnibus:</th>       <td> 0.126</td> <th>  Durbin-Watson:     </th> <td>   0.099</td>\n</tr>\n<tr>\n  <th>Prob(Omnibus):</th> <td> 0.939</td> <th>  Jarque-Bera (JB):  </th> <td>   0.110</td>\n</tr>\n<tr>\n  <th>Skew:</th>          <td> 0.093</td> <th>  Prob(JB):          </th> <td>   0.947</td>\n</tr>\n<tr>\n  <th>Kurtosis:</th>      <td> 2.866</td> <th>  Cond. No.          </th> <td>5.59e+05</td>\n</tr>\n</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 5.59e+05. This might indicate that there are<br/>strong multicollinearity or other numerical problems.",
            "text/plain": "<class 'statsmodels.iolib.summary.Summary'>\n\"\"\"\n                            OLS Regression Results                            \n==============================================================================\nDep. Variable:                      P   R-squared:                       0.040\nModel:                            OLS   Adj. R-squared:                  0.020\nMethod:                 Least Squares   F-statistic:                     2.015\nDate:                Mon, 16 Jan 2023   Prob (F-statistic):              0.162\nTime:                        13:52:48   Log-Likelihood:                -599.63\nNo. Observations:                  50   AIC:                             1203.\nDf Residuals:                      48   BIC:                             1207.\nDf Model:                           1                                         \nCovariance Type:            nonrobust                                         \n==============================================================================\n                 coef    std err          t      P>|t|      [0.025      0.975]\n------------------------------------------------------------------------------\nIntercept   7.697e+04   2.53e+04      3.040      0.004    2.61e+04    1.28e+05\nAd             0.2887      0.203      1.419      0.162      -0.120       0.698\n==============================================================================\nOmnibus:                        0.126   Durbin-Watson:                   0.099\nProb(Omnibus):                  0.939   Jarque-Bera (JB):                0.110\nSkew:                           0.093   Prob(JB):                        0.947\nKurtosis:                       2.866   Cond. No.                     5.59e+05\n==============================================================================\n\nNotes:\n[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n[2] The condition number is large, 5.59e+05. This might indicate that there are\nstrong multicollinearity or other numerical problems.\n\"\"\""
          },
          "execution_count": 145,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.675022Z",
          "start_time": "2023-01-16T08:22:48.620732Z"
        },
        "trusted": false
      },
      "id": "80733603",
      "cell_type": "code",
      "source": "ml_ms=smf.ols('P~MS',data=df).fit()\nml_ms.summary()",
      "execution_count": 146,
      "outputs": [
        {
          "data": {
            "text/html": "<table class=\"simpletable\">\n<caption>OLS Regression Results</caption>\n<tr>\n  <th>Dep. Variable:</th>            <td>P</td>        <th>  R-squared:         </th> <td>   0.559</td>\n</tr>\n<tr>\n  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.550</td>\n</tr>\n<tr>\n  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   60.88</td>\n</tr>\n<tr>\n  <th>Date:</th>             <td>Mon, 16 Jan 2023</td> <th>  Prob (F-statistic):</th> <td>4.38e-10</td>\n</tr>\n<tr>\n  <th>Time:</th>                 <td>13:52:48</td>     <th>  Log-Likelihood:    </th> <td> -580.18</td>\n</tr>\n<tr>\n  <th>No. Observations:</th>      <td>    50</td>      <th>  AIC:               </th> <td>   1164.</td>\n</tr>\n<tr>\n  <th>Df Residuals:</th>          <td>    48</td>      <th>  BIC:               </th> <td>   1168.</td>\n</tr>\n<tr>\n  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>   \n</tr>\n<tr>\n  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n</tr>\n<tr>\n  <th>Intercept</th> <td>     6e+04</td> <td> 7684.530</td> <td>    7.808</td> <td> 0.000</td> <td> 4.46e+04</td> <td> 7.55e+04</td>\n</tr>\n<tr>\n  <th>MS</th>        <td>    0.2465</td> <td>    0.032</td> <td>    7.803</td> <td> 0.000</td> <td>    0.183</td> <td>    0.310</td>\n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n  <th>Omnibus:</th>       <td> 4.420</td> <th>  Durbin-Watson:     </th> <td>   1.178</td>\n</tr>\n<tr>\n  <th>Prob(Omnibus):</th> <td> 0.110</td> <th>  Jarque-Bera (JB):  </th> <td>   3.882</td>\n</tr>\n<tr>\n  <th>Skew:</th>          <td>-0.336</td> <th>  Prob(JB):          </th> <td>   0.144</td>\n</tr>\n<tr>\n  <th>Kurtosis:</th>      <td> 4.188</td> <th>  Cond. No.          </th> <td>4.89e+05</td>\n</tr>\n</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 4.89e+05. This might indicate that there are<br/>strong multicollinearity or other numerical problems.",
            "text/plain": "<class 'statsmodels.iolib.summary.Summary'>\n\"\"\"\n                            OLS Regression Results                            \n==============================================================================\nDep. Variable:                      P   R-squared:                       0.559\nModel:                            OLS   Adj. R-squared:                  0.550\nMethod:                 Least Squares   F-statistic:                     60.88\nDate:                Mon, 16 Jan 2023   Prob (F-statistic):           4.38e-10\nTime:                        13:52:48   Log-Likelihood:                -580.18\nNo. Observations:                  50   AIC:                             1164.\nDf Residuals:                      48   BIC:                             1168.\nDf Model:                           1                                         \nCovariance Type:            nonrobust                                         \n==============================================================================\n                 coef    std err          t      P>|t|      [0.025      0.975]\n------------------------------------------------------------------------------\nIntercept       6e+04   7684.530      7.808      0.000    4.46e+04    7.55e+04\nMS             0.2465      0.032      7.803      0.000       0.183       0.310\n==============================================================================\nOmnibus:                        4.420   Durbin-Watson:                   1.178\nProb(Omnibus):                  0.110   Jarque-Bera (JB):                3.882\nSkew:                          -0.336   Prob(JB):                        0.144\nKurtosis:                       4.188   Cond. No.                     4.89e+05\n==============================================================================\n\nNotes:\n[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n[2] The condition number is large, 4.89e+05. This might indicate that there are\nstrong multicollinearity or other numerical problems.\n\"\"\""
          },
          "execution_count": 146,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {},
      "id": "748510fb",
      "cell_type": "markdown",
      "source": "# Caluculating VIF"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.720605Z",
          "start_time": "2023-01-16T08:22:48.675022Z"
        },
        "trusted": false
      },
      "id": "c39e57bd",
      "cell_type": "code",
      "source": "rsq_MS = smf.ols('MS~Ad+RS',data=df).fit().rsquared\nvif_ms=1/(1-rsq_MS)\nvif_ms",
      "execution_count": 147,
      "outputs": [
        {
          "data": {
            "text/plain": "2.3267732905308773"
          },
          "execution_count": 147,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.760256Z",
          "start_time": "2023-01-16T08:22:48.724631Z"
        },
        "trusted": false
      },
      "id": "e2c89c2f",
      "cell_type": "code",
      "source": "rsq_Ad = smf.ols('Ad~RS+MS',data=df).fit().rsquared\nvif_ad=1/(1-rsq_Ad)\nvif_ad",
      "execution_count": 148,
      "outputs": [
        {
          "data": {
            "text/plain": "1.1750910070550453"
          },
          "execution_count": 148,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.803242Z",
          "start_time": "2023-01-16T08:22:48.760256Z"
        },
        "trusted": false
      },
      "id": "adf7b116",
      "cell_type": "code",
      "source": "rsq_RS = smf.ols('RS~Ad+MS',data=df).fit().rsquared\nvif_RS=1/(1-rsq_RS)\nvif_RS",
      "execution_count": 149,
      "outputs": [
        {
          "data": {
            "text/plain": "2.4689030699947017"
          },
          "execution_count": 149,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:48.842172Z",
          "start_time": "2023-01-16T08:22:48.803242Z"
        },
        "trusted": false
      },
      "id": "f9b4d470",
      "cell_type": "code",
      "source": "d1= {'Variables':['MS','Ad','RS'],'VIF':[vif_ms,vif_ad,vif_RS]}\nvif_frame=pd.DataFrame(d1)\nvif_frame",
      "execution_count": 150,
      "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</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>MS</td>\n      <td>2.326773</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Ad</td>\n      <td>1.175091</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>RS</td>\n      <td>2.468903</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "  Variables       VIF\n0        MS  2.326773\n1        Ad  1.175091\n2        RS  2.468903"
          },
          "execution_count": 150,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {},
      "id": "f0fa59c8",
      "cell_type": "markdown",
      "source": "# Residual Analysis"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:51.210678Z",
          "start_time": "2023-01-16T08:22:48.842172Z"
        },
        "trusted": false
      },
      "id": "6901dc22",
      "cell_type": "code",
      "source": "import statsmodels.api as sm\nqqplot=sm.qqplot(model1.resid,line='q') # line = 45 to draw the diagnoal line\nplt.title(\"Normal Q-Q plot of residuals\")\nplt.show()",
      "execution_count": 151,
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 1000x1000 with 20 Axes>"
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 640x480 with 1 Axes>"
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:51.227002Z",
          "start_time": "2023-01-16T08:22:51.210678Z"
        },
        "trusted": false
      },
      "id": "fefa0735",
      "cell_type": "code",
      "source": "def get_standardized_values(vals):\n    return (vals-vals.mean())/vals.std()\n    ",
      "execution_count": 152,
      "outputs": []
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:51.626211Z",
          "start_time": "2023-01-16T08:22:51.230157Z"
        },
        "trusted": false
      },
      "id": "75ddf9ca",
      "cell_type": "code",
      "source": "plt.scatter(get_standardized_values(model1.fittedvalues),\n           get_standardized_values(model1.resid))\nplt.title('Residual plot')\nplt.xlabel('Standardized Fitted values')\nplt.ylabel('Standardized Resid values')\nplt.show()",
      "execution_count": 153,
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 640x480 with 1 Axes>"
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ]
    },
    {
      "metadata": {},
      "id": "067ace44",
      "cell_type": "markdown",
      "source": "# Detecting outliers\n# Cook's Distance"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:51.644276Z",
          "start_time": "2023-01-16T08:22:51.626211Z"
        },
        "trusted": false
      },
      "id": "d039db9d",
      "cell_type": "code",
      "source": "model_influence = model1.get_influence()\n(c,_) = model_influence.cooks_distance",
      "execution_count": 154,
      "outputs": []
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:52.062286Z",
          "start_time": "2023-01-16T08:22:51.650400Z"
        },
        "trusted": false
      },
      "id": "120ccc59",
      "cell_type": "code",
      "source": "#plot the values using stem plot\nfig = plt.subplots(figsize=(20, 7))\nplt.stem(np.arange(len(df)),np.round(c, 3))\nplt.xlabel('Row index')\nplt.ylabel('Cooks distance')\nplt.show()",
      "execution_count": 155,
      "outputs": [
        {
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 2000x700 with 1 Axes>"
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:52.094189Z",
          "start_time": "2023-01-16T08:22:52.062286Z"
        },
        "trusted": false
      },
      "id": "f00908f7",
      "cell_type": "code",
      "source": "np.argmax(c),np.max(c)",
      "execution_count": 156,
      "outputs": [
        {
          "data": {
            "text/plain": "(49, 0.2880822927543263)"
          },
          "execution_count": 156,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {},
      "id": "d2123e75",
      "cell_type": "markdown",
      "source": "# High Influence points"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:52.506545Z",
          "start_time": "2023-01-16T08:22:52.100941Z"
        },
        "trusted": false
      },
      "id": "13a6a78c",
      "cell_type": "code",
      "source": "influence_plot(model1)\nplt.show()",
      "execution_count": 157,
      "outputs": [
        {
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkEAAAHOCAYAAACfCt09AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAA9hAAAPYQGoP6dpAADBbUlEQVR4nOzdd3xb1fn48c8dmpb3dmzHduIMVsgihEAGhDJbCFDgC3yBtkCBthRaKC20P1pavh3QltKyZ4EuKNBJCyF7khDCSELiJHYcJ/GekjXvvef3h2wTEzte8orP+/XKCyzJuke6svTonOc8jyKEEEiSJEmSJI0x6nAPQJIkSZIkaTjIIEiSJEmSpDFJBkGSJEmSJI1JMgiSJEmSJGlMkkGQJEmSJEljkgyCJEmSJEkak2QQJEmSJEnSmCSDIEmSJEmSxiQZBEmSJEmSNCbJIEga037+858zefJk3n333U6Xv/rqq0yePLnLf5dffvkwjVaSekc2ApCk3pFBkDRmffTRR/z+97/v8rpdu3YBcOONN/L1r3+9078vfvGLQznMPikoKEBRFFauXDng+3rllVc48cQTcblcpKSk8Nvf/paFCxeiKArvvPPOwAd7DLr++utRFOWIf6qq4nK5yM/P54tf/CKrVq3q9Hv79u1DURRyc3MHdHzTNHn00Uf55je/OaD7kaSxQh/uAUjScAiHw9x7772Yptnl9bt27SIxMZE777xziEc2MpSUlHDVVVdhmibz588nIyODE088kddee224hzYqnHjiiZx00kmdLguFQuzZs4e//vWvvPbaazz22GPcfPPNMT3uH/7wB77+9a9z9dVXx/R+JelYJYMgaUx64oknKCsrY968eaxbt+6I60tKSpg0adIwjGxk2LJlC6ZpsmDBgpjMKo01l1xyCT/84Q+7vO7pp5/mpptu4o477mDJkiVkZmbG7LiWZcXsviRpLJDLYdKYs3PnTp566iluuOEGJk+efMT1VVVVNDU1UVxcPAyjGxlCoRDAgJdnpCPdeOONzJgxg2AwyL///e/hHo4kjWkyCJLGFNM0ueeee8jLy+PWW2/t8jbt+UCmafK1r32NuXPnMn36dL7yla/wwQcfDOFoY2PlypUoisLtt9/Orl27uOyyy0hLS8PlcjFz5kyef/75jtu256Z86UtfAqLLK4qisHDhwm7v/2h5Qi+88AKKonD99dcfcV1JSQnXXXcd48aNw263k5ubyw033EB5efkRty0oKCApKYlQKMQPf/hDJk6ciMPhIC8vj9tuu436+voux/bGG29w9tlnk5aWRmJiIrNmzeKJJ57AMIwjbrt582Yuu+wyMjIycDgcFBUV8a1vfYu6urpuH3t/TZgwAYDq6uoeb1teXs7NN99MQUEBdrud9PR0lixZwsaNGzvdbuHChUect66ed0mSPiWDIGlMefbZZ9mxYwc/+clPsNvtXd6mPQj6y1/+QjAY5JJLLuH0009nw4YNXHPNNUcktY4W27ZtY/bs2axZs4bTTjuN6dOn8/777/PlL3+ZX/7ylwB4PB6uvvpq5s6dC0BhYSFXX301Z599dkzH8vbbbzN9+nRefPFFUlJS+PznP09KSgrPPvssM2bMYMuWLUf8jmVZXHjhhTzwwAPk5ORw7rnn0tTUxG9/+1sWL158RGDzta99jUsuuYTVq1dz8skns3DhQvbu3cstt9zCtdde22kH1e9//3vmzp3L66+/Tn5+Pp///OdRVZVf//rXzJo1i3379sX08W/fvh2A/Pz8o97u3Xff5aSTTuLJJ5/EZrNx0UUXMXHiRP72t78xb948nnrqqY7bnn322Uect9NOOy2m45akY46QpDGitLRUnHjiieJHP/pRx2U/+9nPxKRJk8TGjRs7Lnv88cfFokWLxN///vdOv//uu++KqVOninnz5olgMDhk4+6L8ePHC0CsWLGi47IVK1YIQADisssuE16vt+O6Rx55RAAiPT1dWJbVcfnzzz8vAHH11Vd3uv8FCxYIQCxduvSol332fq677rqOy2pra0VycrLQNE386U9/6nT7J598UgCiqKhIhEKhIx5XZmam+OCDDzou37dvn0hJSRGA+Oc//9lx+euvvy4AMW7cOPHJJ590OvaUKVMEIN544w0hhBA7duwQdrtdeDwesWzZso7bmqYp7r33XgGIefPmHfHYunLdddcJQNx3331dXm9ZlvjJT34iAJGYmCgaGxuFEEKUlZV1jLddIBAQ48aNE4D40Y9+1On8vPnmm8LpdApd18X777/fcXl3502SpK7JmSBpTBBCcO+995KSksK3vvWto9725ptvZvny5XzhC1/odPkpp5zC5z//eWpra9m0adNgDndQ6LrOE088gcfj6bjsq1/9Kg6Hg9ra2l4tzcTCs88+S2NjIzfffDNXXnllp+tuuukmLrjgAkpLS3n99deP+N3vfe97TJs2rePn8ePHc9FFFwHRma52jz32GAC/+tWvmDJlSsflaWlpPPDAA0yZMoWysjIAHnnkEcLhMPfddx9nnnlmx21VVeXHP/4xJ554IuvWrTti+eloXn/9da655ppO/77whS+Qn5/P97//fWw2G08//TRJSUnd3scrr7zCwYMHmT9/Pv/v//0/FEXpuO68887j7rvvxjAMfvWrX/V6XJIkdSaDIGlM+MMf/sCWLVv40Y9+1CkI6KvjjjsOgAMHDsRqaEOmuLiY1NTUTpfZ7XbS0tIA8Pv9QzKO5cuXA3DWWWd1ef35558P0OWutPblnsPl5OQAn45fCMHq1atRVZULL7zwiNtfcsklfPLJJ9xxxx09jkdRFM4999xux9Odjz/+mD/84Q8d//74xz+yfPlyPB4PX/nKV9i0aVOP9abal127K87ZHkDK3XuS1H9yi7w0Jrz11ltAdKahK9deey0Ay5Yto7m5Gb/fz+zZs4+4XfuuKYfDMUgjHTzJycldXq7r0beBodpeXVFRAUSDkd7c7nBdPYbPjr++vp5wOEx6ejput7vX45kxY0afx9Od++67r9st8r116NAhIJoU3pXCwkIguptRkqT+kUGQNCYsWbKEU0455YjL161bx9atW1myZAnjxo0jISGB//3f/6Wqqop169aRkpLS6fbtCbsnnHDCkIw7lg5fThkqXRWjbL/swgsvJDExsdvfbZ91O1xvHkNXO7+Opn08V155JZqmdXu7w5fhhoJoS9zu7jG3X99dgr8kST2TQZA0JnQ36+D3+zuCoDlz5gBw7rnn8txzz/HrX/+a+++/v+ND6D//+Q8rV65k9uzZY7qQ4mepanRVvauAp6Gh4YjLsrOzKSkp4Zvf/CaLFy+O+XhSU1Ox2Ww0NDQQCARwuVydrg8Ggzz77LMcd9xxLFq0iOzsbMrLy/nxj3/MxIkTYz6e/mpf5mvPXfqs0tJSgJgWW5SksUbmBEnSZ9xyyy1MmDCBV155hSuuuIKf//zn3Hzzzdxxxx2kp6fz05/+dLiHOKK051jV1NQccd369euPuGzBggUAvPnmm13e3/e+9z1mzZrFM88806/x2Gw25syZg2mavP3220dcv2LFCr7+9a/z6KOP9mo81157Laeeeir//Oc/+zWe/po/fz4Af/3rX7u8/i9/+QtApxpOwzHbJ0mjmQyCJOkzEhIS+POf/8x1111HbW0tL730Etu2beOyyy7j9ddfJy8vb7iHOKK0LxM9/vjjHTlTEP2Q/vvf/37E7W+66Sbi4uL47W9/y5///OdO1/3rX//iV7/6FVu2bGHWrFn9HtM3vvENAL797W93Kr5YW1vLXXfdBcA111wDwG233YamafzgBz9g2bJlne7nySef5KWXXuKDDz7ocjl1MF1++eXk5OSwcuVKHnjggU51jf773//yi1/8Ak3TOvUfczqdADQ3Nw/pWCVp1BrWDfqSJMXU0eoEdVfrpv13du/e3XFZX+oElZeXi6SkJAGIvLw8cemll4rp06d31AfiM3WChBDitddeE3a7XQBi6tSpYsmSJWLWrFkd9Yx+/etf9zjGdvfdd58AxL333tvp8ptvvlkAwuVyifPOO09ccMEFIjExUQDipptu6nTb3/72t0JRFAGI6dOni0suuUQcf/zxAhCapolXX321y+fus3qqE9SdruoECSHEunXrOsZcXFwsvvjFL4q5c+d2jOvRRx/tdPstW7YIQCiKIi644ALxwAMP9GkckjTWyJkgSZIGJD8/nw0bNnDZZZfR2trKm2++ia7rvPrqq9x5551d/s4ll1zCe++9xzXXXENzczP/+te/qKqq4oILLmDFihXcfvvtAx7X448/zh/+8AdmzpzJmjVreOeddygsLOSxxx7jiSee6HTbr3/966xZs4YlS5Zw4MAB/vWvf9Ha2srll1/e0U5jOJx22mls3bqVG2+8kWAwyN///nfKy8u54oorWL9+/RGtX2bMmMHPfvYzsrOzWbp0aZetTCRJ+pQixGFzrJIkSZIkSWOEnAmSJEmSJGlMkkGQJEmSJEljkgyCJEmSJEkak2QQJEmSJEnSmCSDIEmSJEmSxiQZBEmSJEmSNCbJIEiSJEmSpDFJBkGSJEmSJI1JY7aLfH29F1kmsmeKAqmp8WPy+WoNGzy/sYIN+xoQAlLj7GhqbBpUBg2ThtYIyW4bV84Yx8KJqf1ufjmWz9FoIM/PyCbPz8h2+PmB6P/H0pgNgoRAvuD7YKw9Xy3BCA8t38vWA80kuXQ8Tp2waYEZu2MkuXRqfSF+t7qMhtYwS07KHlAX8LF2jkYbeX5GNnl+RrbBOjdyOUySPqM1bPDgsmgAlOaxE+cYnO8KiqKQ7nGgqQovv3eQv39cNSjHkSRJkromgyBJOowQgkfXlPHBoWgA5NAH/08k2W3Dpin8YcsB1pbWD/rxJEmSpCgZBEnSYVbsrmNDWSPJLtuQBEDtkt02DFPwwqYK6lvDQ3ZcSZKksUwGQZLUptob4uX3DqAo4LZrQ378dI+d6pYQv99UgZDJCZIkSYNOBkGS1ObFTRXU+MKkeezDcnxVVUhy66wtrWfDvsZhGYMkSdJYIoMgSQL2NwZ4r6KJRKeOOoAdWgMVZ9cxLcF/PqmWs0GSJEmDTAZBkgSs3lOHP2zicQz9MthnJbh0dlb72FvnH+6hSJIkHdNkECSNef6wyfLddTht6oDq9MSK26YRjFis3FM33EORJEk6pskgSBrztlW2UO+PkOgcGbVDFUXBZVNZX9aAacklMUmSpMEigyBpzCtvDIAQ6NrI+XNw2jR8IZPKluBwD0WSJOmYNTK++kpSH/nD0QAhZFgIwKGpZCU48PSjunNZfSsjbb7Fqas0BSKUNwbITXIN93AkSZKOSaMyCNq5cyc///nP2b59OzabjXnz5vHd736XlJSU4R6aNEiEEOyo9rGhrIFdNT4ONgcJGxZm2w4qVVFw6NFAaEqGhznjkzkhO6HHhqdCCHbXtuIcwsKIvaGqCgpQ3uBnXqF8XUuSJA2GURcEBYNBbrjhBi6//HKefPJJWltbufvuu7nnnnt44oknhnt4UoyZlmDV3nr+u6Oa0no/IcPCpik4bSrxTp32GMcSEDIsyhv87K5p5b+f1FKQ4uKcKRmcNSmt26WukGHRGjaxjaClsHaWgOZAZLiHIUmSdMwadUHQoUOHmDJlCl/72tfQNA273c4VV1zBd77zneEemhRjlS1BntlQzpaKZoQQJLltpMbZut3BFW1zEX1JByMmpfV+Hl+3j7Wl9dwwdzzjU9xH/E7YtBBCoPYwYzQcFAWChjXcw5AkSTpmjbogqKioiGeeeabTZW+99RbHH398n+5nBOyEHhXan6ehfr7Wljbw1Pp9NLRGSImz4bL1rX6P06aRZdMIGRYfHGzh3n9/wvWn5HP2lPROt4sWRhy5LwZNUXp87ofrHEm9I8/PyCbPz8g22Odn1AVBhxNC8PDDD7NixQpefvnlPv1uamr8II3q2DSUz9d/Pq7ksXX7CEUs8tPcA6rgbLNpxDl1arwhnn53P5rTxuWz8jqujwub2Gxqx21HElVVSEpwkpbWu+devqZHNnl+RjZ5fka2wTo/ozYI8vl8fO9732P79u28/PLLTJ48uU+/X1/vRXYl6JmiRF98Q/V8bdzXwK9WlGJYFmlxdkzDwozB/aa4bDS0hnls+W5EOMJZk6IzQkII4nSN2tYQ7hGWHC0sgVuBujrvUW831OdI6ht5fkY2eX5GtsPPD8Q+GBqVQdD+/fu58cYbycnJ4a9//Wu/doUJgXzB98FQPF91vhBPrd9PyLDIjLfHvHpzSpydGm+IF96tYFK6p23rucLkjDgO7g7E9FgDFS2SqJCf7Or18y5f0yObPD8jmzw/I9tgnZuR9dW3F5qbm7nuuuuYMWMGzz77rNwWf4wQQvDCpgpqvCEyPLEPgNqle+w0+iM8s2E/Rls15oIuEqaHW9AwcdrULpO5JUmSpNgYdTNBr7/+OocOHeI///kP//3vfztdt3Xr1mEalTRQWyqaWV/WSLLbNqg7tRRFITXOxgcHm1lXWs+CiWkUpLjRVIWwYWEfIUtigbBFapydDI99uIciSZJ0zBp1QdCXvvQlvvSlLw33MKQYe6ekFsOycNsH/0PfadMQ/ghv7axl/oRUjs+OJyveQbU3REa8Y9CP3xMhBCHDYsHE1BHR0FWSJOlYNTK+9kpj2oGmAFsPNBPfj5YX/ZXosrG71kdJbSs2TeXsyekYlsAaAUkBvpBJnF1jwcTU4R6KJEnSMU0GQdKw21LRRCBi4nEM3RZ1l00lZFhsqWgCYP6EVDwOnZagMWRj6IoQgpaQwfTcRMYlyp5hkiRJg0kGQdKwK6v3Awzp0o/SVoRwb10rAGkeBwsnptEaMjsSpodDS9DApWtccHzmsI1BkiRprJBBkDSshBCU1LQOS0KyU9fYW+fvCHr+Z8Y48pNd1HpDiGFYFjNMC1/I5NzjMjghO2HIjy9JkjTWyCBIGlb+iEljMIJjGBqYOnSVQMSkvjUMQLxT58un5mPXVbyhWJRo7D0hBDW+MEVpbq6YnjOkx5YkSRqrZBAkDauw0dbAdBg2QakKWEIQMT9tUjozL4lzp2bgCxn4w0MTCLUHQB6Hzk1zxxNnH3WbNiVJkkYl+W4rDav2PKDhyMJpP+ZnU5Gum51HS9Bgxe46BGJQgxIhBLW+MA5d5WtnFHK8XAaTJEkaMjIIkoaVU1fRFGVYtqZblkBTlSM61OuaytdOL0RTFJbtriNsCJJceswTtw1LUOsNEefQ+drphcwrlNXPJUmShpJcDpOGldOmkZXgIBixer5xjAUNi0SnjWSX7Yjr7LrKrWcUctWMcSgKVLaECBuxGaMQAm/QoLolRF6yi7vPmsi8IhkASZIkDTU5EyQNu8kZHnbXtg75cUOGxaT0uG5neHRV4YoZ4zg5N5FnNpSzq8aHTVNIctmw9SORWwiBP2LSHDBw6CoXHp/JVTNziXfKP0NJkqThIN99pWFXlBoHKJhty1NDoX35bWJ6XI+3nZzh4cfnT+HNHdW8tbOW6rYt9B6HjtOmoqtKt4GUEIKwadEaNgmELZw2lZPHJXLxSVnMyE2K5UOSJEmS+kgGQdKwm52fRJIrWq052X3k0tRg8IUM4uw6pxb0bhnKadO4ZFoOFx6fxeaKJt7ZVcsn1V4aWiOYbQGVpiq0h0KW+DTQsmsqcQ6Nz03OYGFxGhNS3aO2J5glBJYATRna4paSJEmDQQZB0rBLdNk4Y0Iq//i4alASkD8rmpNjsqg4jcw+Nky16yrzClOYV5hCkz9CeaOf8sYA++r9NPjDhA0LRVVw6iq5SS7GJ7vIT3aTm+TEaRu6tiCxEDYsPjjYTFm9n711reyt9xM0TBCgqgrjEpwUZ8QxPtnNyeMSSPMMf/NZSZKkvpBBkDQinD0pneUltTQFBn82yBsycNk0zpmaMaD7SXLbSHInMm1cYoxGNjLU+UKs2FPPO7uiS3+WECiAwxbdyacoEDEFu2p97Kj2AuBx6MwtSGZRcRrHZ8XLWSJJkkYFGQRJI0JBqpuLT8zmD1sOEGdog9ZGwzAtvCGTi0/M4vis+EE5xmhlWoJ3dtXyxy0HaPBHsOsKqXE9J4Fbbbvd3t5Zy6o99cyfkMq1s/NIGqKlTUmSpP6SQZA0Ylx8UjZbDjTxSZWP7AQHaoyTpC0hqPaFKUhxc+WMcTG979Guzhfi8XXlbKloQlMhO9GB2svZHFVRSHTZSHDqtIZNlu6qZXuVlxvnjmdWftLgDlySJGkAZJ2gGDAtQYM/zMHmADXeEMHI0PadOlY4dJVvnFFEdqKDKm8IK4bd3C0hqGoJkRZn57b5hbI1xWEqW4L8+O0S3i1vJNGlk+7pfQB0OEVR8Dh0shKi5++hFXtYsbtuEEYsSZIUG/KTYAAa/GHW7K1n6a5a6nxhTCFQFQW7pjK3MJofMSXDI/Mj+iBaPLCYXyzbw6HmIGkeO44BLo2FTYtab5h0j507z5xIcbonRqMd/ep8IX72zm5K6/xkJTjQYzD7pqkKWfF26lrDPLFuHzZN4fSi1BiMVpIkKbZkENQPYcPiD+8d4J2SWrwhA11ViLNrOFQVIaJF+P7zSQ3LS+ooTo/j5nkFjE9xD/ewR40JaXH84JxJPLZ2H9srW7DrKiluW5+DSSEETQGDQMRkcqaHW+YVMCGt57pAY4VpCR5bt4/SOj+ZMQqA2imKQlqcnRpfmCfXlzM+2U1esitm9y9JkhQLcjmsj4IRk1+u2MMbH1diWIKseAcZ8Q7iHDoum4bbrpHstpGT4MBt19hW6eX+t0rY2baLRuqd3CQXPzpvMtedkoddUznUEqK+NYxh9ty6wrAEDa1hDjWHUBS4csY4fnL+FBkAfcbbu2p4v6KZ1DhbTAOgdoqikOGx0+SP8MzGcowYLm9Kw6+urpZzzlnAK6/88Yjr/H4/jz/+Wy677POceeY8rrrqUl566XlCodAwjFSSuidngvrAtARPrNvH+n2NpLhtRzTePJyiKLjtGk6bSlVLiF+u2Mt9504mN0l+G+4tm6ZyybQc5hQks2pPPctK6qhtDSFEtPO7o635KkSLE4YMC9FWoDDFbef841JZVJwmZ+G6UOMN8ectB9FUZVDrFylKdIfZBwdbWLqrhvOmZg7asaSh4/f7ueeeu2htPbLdTSgU5Lbbbmbnzh0UFhZx8cWXcODAAZ588lHefXcDv/zlIzgczmEYtSQdSQZBfbCloonVe+tJculHDYAOpyoKWfEOKltC/Pn9g9x55sRBHuWxZ1yii6tm5nLJSdlsPax4X1l9gLAZTUJ3aSpTMz1MTPdQkOLi5HGJeBzy5d2dlXvqaAhEyE4Y/AKHTpuGGjT4z44azp6cMSizTtLQqaqq4p577qSkZGeX17/88u/ZuXMHCxYs4oc//D9stmiphDfe+Cu//OXPePnl3/OVr3x1KIcsSd2SnxJ9sHx3HYYl+ryzSFUV4p0671U0UdkSJDtBfgvqD6dNY25BCnMPa3UhhEBAv3YzjVUhw+Kdkjrsmjpkz1uSy0ZFU4APDzYzMy9pSI4pxd4rr/yRZ555klAoyMyZs9myZfMRt1m27G0UReGOO+7uCIAALr74Ul555Y+89torXHfdV9B1+fEjDT+ZE9RLB5oCbD3QTHw/ZxfiHRqtIZPVe+pjPLKxTVEUGQD10dYDTdR4QyS5hu5DyKGrmJZg9V75+h/NXnnlT2RlZfG73z3FOeec3+VtKisPkZmZRVpaWqfLFUVhwoSJtLQ0U16+bwhGK0k9k0FQL314sIVAxMTj6F/+hKIo2DSFDfsaYzwySeqb0no/QogeK0HHmkNX+aTK15G3JY0+d911D88//0dOPHFat7ex2eyEw+Eur/P5fABUVVUOyvgkqa9kENRLvpCBgjKgmj82TaU5GInhqCSp7/bWtcIwTJ459ejrv8bX9QekNPLNmTMXTTv6F8EpU6bS0FDPRx990OnyhoZ6duzYDkBrq2+whihJfSIXZXvJFAIY2DdYRYlWLhZCDGoBRW/QYMO+BqpaQgQiJjZNxePQmZ6bwMS0OFm8cQwTQlBa78epD31He4dNwxsKc6ApQGa87Dh/rLriiqt5//33+OEP7+Wuu77HtGnTOXCggl/+8ucIES1xIWcDpZFCBkG9FGfXEDCgAMawBCl2fdCCkL11razYXcfqvfU0BSIoRLeOtx/u1Q9UpmR4WDw5nTnjkwd1a7Q0MhmWIGxYDPFKGACaEi0zEZBtZY5p8+adwa23fpMnn/wdd911e8fls2fP4corr+H555/G6ZSbQ6SRQQZBvVSc7sGuqQQjFi5734MHIQQhw2JaTkLMxyaE4G8fV/GX9w/SGjZx2zUy4x1oh21FFkLgj1h8dKiFjw61cHx2At9aNIG0OHvMxyONXJZon88cvtlAWTPx2HfVVf/LggWL2LhxHaFQiKlTj2f69Jk8+uhvAEhOTunhHiRpaMggqJeiNWji+KTa168gKBCxcOoqi4rTer5xHwgh+MN7B3jto0psmkJOoqPLmSZFibb2iLNrhI1oMHT/f3fx/86ZRJpHLk2MFTZNQW2bkRlqguispF2Ty7FjwbhxuVx66RWdLtu5cweKolBQUDhMo5KkzmRidC8pisLiSelAtCFnX0R7WEUoTvdQnB7b1g1v7azl9Y+qcOoqKW57r5ba7LpKVoKDsno/v1yxd0QvT4QNi9L6VtbsreedXbWs2lPHzmovrWFjuIc2KqmKQma8g5DRt9dwLIQNC7umki6D7mPaY4/9hnPPXURjY+edsA0N9Xz88YdMmTKVhITEYRqdJHUmZ4L6YF5RCkt31bKjynvUhpNCCLwhk5BhYVkW/oiJQ9dYcmJWTPOB/GGTV7YeRFEEia6+LWvpqkK6x86OKi9rSxs4e3J6zMYVC/sa/KzYXceqPfX4QgYh0+pYwNFVFZdNZVZ+EmcWp3FSToJM9u6DSekedtce2e4gYgqChkkoYkU3AohoR3iHruK0qQPeUh80LJw2jTzZOuaYVlg4AZ/Py9///hrXX38DAIZh8NOf3o9hGFxzzfXDO0BJOowMgvrAZdP49qIJ/PjtEvbV+0mNs3VKLjYsQZM/QoM/TNiM7gIzrWgidYJT4bl397O/KcBZxekkuW1HOVLvbNzXQF1rmAxP//J67LoKCizdWcPiSWkjIpAIRkxe/6iSf2yrojVk4rKpeBwaqXq0i7wQgogp8EdMlpfUsa60gXlFKVx3Sh4p7q6fh2DEZG9dK+WNARr9EQTRRPf8ZBdFqW6Su/m9Y1VBWy81SwgUFLwhg0Z/hNawQXSS87NLZQqqGn3Okl12Epw6/XmpBCMWJ2THRV930jHr7LPP5fXXX+XZZ59k9+5djBuXx6ZNG9mzp4QLL7yI+fMXDfcQJamDDIL6KCPewX3nTuZXK/bySbWXBn8Ej0NHVxUONgcJRsxo7oMAlOi24JwEJy6bSo0vxO83VbBydz3fPnNCx4dRfwgheHtXLYqioA/gG3qSy0ZpvZ8d1T6Oz4rv9/3EQnMgwkPL9/LhoWZcNq3L/CZFUbDrCnZdJcllozVksLykjpKaVu4+ayIFqZ8+p3W+EG/vqmV5SR0N/jCGJdpmkxRAdORJzRmfzDlTMpic6RnKhztspo1LIM6u09AawRsyaA2bCCHQ1GhBz88+50JEAyZv0MAbNImza2QnOnrdPw/AsgSWEMwZnxzrhyONMLqu86tf/Y5nnnmcdevWsGnTRvLy8rn77u9zwQVfGBFftiSpnSLGaMGGujovA3nkhiX48GAzy0vqeLe8gcqWEIYl0BRQVRWHrpLitpHotKEflghqWIJqb4hxCU7uO29yv/uIVTQG+PbftuO0qbj7kajdTgjBoeYQl52cw3Wn5B1xvaJAWlr8gJ+vngQjJg+8vZsPDjaT5rHj6MNsgWkJqlpCjEty8sNzJ5MZ72DFnnpe3lxBrS+MQ1dJcOpHfMAblqA1ZERnnOwa5x+XweXTx/Xpw30k6M85uuP1bWwsb0RVQNdUetvTVAiImBaaGs0tSnXbe7XRrMkfQddUfnfpiTGZBR1NhupvSOofeX5GtsPPD0T/P5bkTFA/6arCzLwkZuYlcc+/PsEbMkl06uiaiq4quGxal0sGuhrtKn+wOchja8q4//wp/fpm1BIyiFgW8T1Ub+2JoigoCrQMcyXr1z+q5MNDfQ+AIJq3kpXg4GBTkKc3lDMu0cm/tlcDkJ3gQO3mE15XFRJdNhKcOi1Bg9c+rGRPrZ87z5xAouvY/aB+e2cNe+qiFXs1Vel1AARtu7t0lYgpqGwJIQSk9bAca1mC1rDJBceljbkASJKkkU0uzg/Qvno/e2pbSffYSYmL5ku47V0HQO00VSHZbWNnjY+SLhJUeyNsWAgRm+7pCgzrDrF99X7+sa0Kt03DoasIEX18gYhJIGJ2PNaj0VSFlDgbq/bU85eth3DaNDLiuw+ADqco0WAoLc7OBweb+eWKvYSHYffUUPjwYDPPbdyPXYvOVJqW6Ff1XpumoADV3hAtwaPv1KtrDZPusXPpydn9HLUkSdLgkDNBA7RyTx2BiEmyu2/bfl02lUZ/hJW765ic0fdcFJdNRVUUTCHQBlj4zgLi7MP3Uli2u5bWkEm6x06dL0yDP0LEtDrScxWifdeS3TaSXDZs3dSZsQS0hk0cukp8Pxrd2nWVNE80EPr7tiq+eHJO/x/UCNQaNnh24378EZPsBEd0OTBsEjEtbBp9npHUNYWwIahsCeK2xXVa9j38mAK4Znae3BovSdKII2eCBmh9WQMOm9rnDxBFUXDZVdbva+jXN/E0jwOHrhIc4AxO+7EzhqmXUzBisnJ3PUHDZE9dK5UtQcKmhaoo6Gr0n6oohE2LqpYgu2t9HGwKHlHsTwiobA4CAsMSBCP9m8lp3w7+xkeVHGgKxOARjhz/2lbNvgY/GZ5oPSmbpkaXCxUFo58zQnZNIWxY1LYe2RQ1GDFpDhicUZTKoompsXgI0ihmtVXNj5iW7B0mjRhyJmgADEvQGjGx9SWp4jA2Ve3Y7t3XmZi0ODuz85NYuaeOBGf/8yy8oehun9OLhqeM/ceVLexvDBAxTTRNxa6pRyTaKgqoKICCaQnq/WGChkl+squjdo0vbBA0LGyaGu1PZZj9quwNkOyycag5xKo99Vw9K3eAj3BkCEZM3impxa6pnXYTJrpsmEJQ2RxN7NfVPs4IKdEl2SZ/hAyPvaNVS2vYpDkQ4dSCZG49vUDuCBqDwobF+wea2FXTyu5aH/sbAx07NJ02jeL0OIpS3UzLSWRShmzsLA0PGQSNYouK01hbWk8wYva7GaovZHB6UUq/d6kNhC9k8MS6fQQNE6eu9ip/R2ubGfKHTfY3BihIcaOpCi0BI7rNuy0IGkhFZEVRcNhUVuyu44oZ47otijmc2r9J9/aDY/P+Jmp9YVLjjgyYU9x2FBQqW4JETIGu9S3XTFcVwqagOWCQ5Nap84URAhZOTOPW0wtko94xpjVs8J8dNbxTUktVSwhLCLS2vylVURAIvKEIG8oaWF/WwCvaISalezj3uAxOL0qJSZ6jJPXWqA6CGhoauOKKK/jJT37CnDlzhvz4uqrgsevUd7EU0BsR08Jt13H380PipJwExqe42VvXSnZC35fkvCEDm6Zy1qThqRb94uYKyhsD0cCmD4GGokRzhPxhk8rmELlJTlrDZqfHP9DWWHE2jeZghKqWILkjoMJxUyDC+rIGdtX4KKlpxRuK7uZLjbMzOcPD3EkZHJfixKF3/VraU9eKJUS3VZ+T3TZcNpVDzUFawyYoomMpskcKCGHRGAgTiERzu66Zlcui4pFRgFMaOh8ebOaZDfspb/Rj06KbFexHqWMmhCAQsdhe7eWTGi/rShv48qn5ZA7T8rw09ozaIGjLli1897vfZf/+/cM6jnmFKbz6wSGEEH16w2//4z97Skq/Pyg0VeHm0wp4YGkJ1d4QmfFdN0/tij9s4g0aXHBcJjNyh76PT50vxNrSBly6SqCtWF9fngdFiT7+llCEgGHDsKxOW70H+tHr0FUaAxEONAWGNQhqDRu89kElS0tqaQ5EOsamqwoCONAUpKzezzsldaS6bVx0YhbnTs08YvaqpMbXsVTVHadNoyDVTYM/QkNrmJAhACu6HKlEt9K3nyMhBAKwrGiuhwWEDcGSkzK4bFrOsOWYScNDCMFfP6zk1a2HCBkmGR57r4q4KoqC267htmv4wybryxrYXdvKNxcUMm2c7C8mDb5RmRj9xhtvcOedd3LHHXcM91BYWJyG265Fvz33gT9i4bSpLBxgwujkTA/fmF9IvMNGZUuox63dlhA0+iM0Bw0WTkzjy6fmD8u39dWlDXiDRlsLBuWIRg29oanRHKEmfwQhQEHpWCYaaGuG9pkpfz8TrGNhT20r9/zrE1794BBhwyIz3kFOopPUODuJruhOuXSPnZxEJxkJDhr8YZ7ZsJ8f/3cXdb5Qp/uqbAkd9Rt5O1VRSIuzMzE9jvEpzmixT1VtK5IoCBsWYcMiYgpMKxqMxtk1Ut12shIc3HDqeBkAjTFCCP7y/kH+tOUAigJZCY5+VbF3t1Uir28N8dCKvXx4sHkQRitJnY3KIOj0009n6dKlnH/++cM9FPKTXZw8LpHmgIHRyzWY9g/u47LimZg28K7ys/OTuedzxeQnR7/FH2oO4g0ZHTVg2ndl1HhDVLaE0FSFL07L5rYFRQNuitkfhmnxzq5abJqCy66jKv1fvlIUheaOOjXR2QlFUXAOMAgSQiAEw5YPtKvGxwNLSyit85MRbyfZbTvqTI6trTt7kkvn/QPN/Pjtko5ASIjojrm+xLqqopDgtJGf4mJyRlxbUOQmL9lFXpKro+/alAwPRWlxJLmi4zPlrp8xZ9Weel79sBK7Hi1jMZAvVaoSLXzaEojwm1WlVLYEYzhSSTrSqFwOS08feA5LLCc/vjpvPJUt0WWJjHj7UQMLw7So9obJS3bxtTMK+5QLczTHZcXz8CXHs6WimWUltXx4sIXaUBhTCFRAU1WyEpwsnpzGggmppPWyZkv78xTL56vaF6LOFyK+reeax67THIzQp9LFbTQ1ur27PZASQmDXBtZKBCBsCuy62rbEOKC76rMmf4Rfr9xLfWuY7ERHnxJFnTaNzHiF0jo/v1ldyg/PnYyuqdg1hf5WU1AUBYeuHLWStyUEqqpg15Qhf75GusH4Gxopan0hXnzvAEIIklyxaUSsKAqZCQ4qm0M8t3E/93yueFCTpY/l83MsGOzzMyqDoFhITY1d/5G0NHjoyun86B/b2VHZgqpASpy9066YYMSk0R/BMAVTxyXwo8+fQH5q/xuodufCzEQunJVPRYOfg00B/GEDu6aR4NKZkpXQ72WiWD5f1WELVAWHQ8emq6QlOPCGDISgx7yVrpgInDaN1pABikKqx4FjgMUffRETj1Nn+sR04hxD92cihOCpTTup9IbIbdv51lu2ttebzaaRpalsr/Kxan8zV8zOZ2JWAlvKGzpuE2uGP8KE1DiyMmUeR3di+Tc0Ujy+sYJ6f4TcJFfMvtC1y0iE9w+28H51K+eeMPjVxo/F83MsGazzM2aDoPr62DbLcwD3nDWBlXvqWbqzhv2NgU+XBkQ0xyQ30cnnpmSwsDgVtzA7GsINBhcwMcEOfPrtrKWp7y06FCX64ovl89XY6Mc0BEbERBUCl6YQ79BpCkawc2QX86NpH5NTU2i2BHF2lSSnTmSARSRb/BHOKEoh4A0QGLzTdISyej9Lt1fhsWlYpoXVy4dhs2mdHrNGdK375fX7OHVcPHnxdjYa1oCfl+6EIiaFic5BfU2PVoPxNzQSVDYHWbmzmjibimlamDF+adkUBcM0+cu75czMHLw6Qsfq+TlWHH5+IPbB0JgNgoQg5i/4OLvOBcdlcu6UDD4+1MLB5iCBiInTppKd4GTauMSOHJPR9scWy+fLbdNQVTqCRKUtDyBgRPuE9aWFgyA6e2KKaF6M2671azbpcIGwia6qnDkpfcjP04rdbW1YEgaeXJzktlHrDbG+tJEpmR40RSFkWH1uUNuTiGmhAFMy40fd63ooDcZ7znBasaee1rBJTgxeq91JctnYW+dne6WX47MTBu04cOydn2PNYJ2bUZkYPdJpqsLJuYlccHwml52cw4XHZzEzL2lEFt0bDpnxDpJdNlpDn351tOsqeUku7JpK2Iwmc/eGaUabq3ocOhedmIWmKANqJWIJQYM/wsy8RKYPcekAIQTv7W/CofW95lNXdFXBIlqVe/q4RMYlOTu22cdSc8AgPd7BnPFJMb9vaeTaUNbQlgM2eO9rTl0lYlpsPdgyaMeQxrZRHwTt2rVrWAolSv1n16MFGkOf6SHktmsUpLqId+gYbduxrW56WllCEDEtIpYgO9HJPWcXc8fCCUwbl0h9a7QBa18JIahuCZHusfOVU/OHvHJtYyBCvT+M0xa7P0unrrKrrUbQuVMzBlxN+7MipkXYtPjc5HRZGXoMaQ5EqPWFcXZTnDNWFCVasHNvbd+X8iWpN8bscthQqfaGWFdaH63hY1okOHWm5yZyUk7imJ4ZWjAxlTc+rsQbMklwfvoydOgaBSkuGgMRGlojBA0LYQnat79DtBBi+5tjskvnpxdOZVKGB4DbFxbxwNsllNS0kuK29bp/mGFa1PjCJLls3L5wAlnD0EakoTVCxBS4YhhM2DSVlqBByLD43OQM1pU2sK3SS05i7wtrdkcIQa0vzMS0OL5wQlaMRiyNBhVNAYKGSYq7/30Le8uhq5Q2tLb1thu775nS4BhQEHTw4EHcbjfJyckA7Nu3j1/84hdUVFQwZ84cvvnNbxIfPzYz7ut8IV7cfIDN+5toDUd3PilKdF3z39uryUt2cem0HOZPGJvdtbMSnJySn8yK3XW4bZ2beiqKQorbTrLLRiBiEYiYhAwrug1bUdqagCr4ggbzJ6Z2BEAQ7YP1/c9N4ol1+9hU3kRLyCDZZet2V5xpCZqDEQJhi8JUN7eeXsCUzOF5zbaHebF8m1egI3i06yo3njaeH/5nF1XeMFnx9n4HQkIIanxhPA6dG+aOl7NAY0x7HbKhCEp0TSFsCIIRE88Q7tSUxoZ+vaIsy+KrX/0qzz//PC+++CJXXXUVzc3NzJs3j6qqKoQQvPnmm7zyyits2LCBuLiBFwQcTQ41B/m/pSXsawiQ4NTISuhc6yVkmOxr8PPIqlLqWsNcctLgb/8cib58aj4HmgLsrm0lM/7IMvuHl9Q/nGFFl60mpMdxw9zxR9xvstvO3YuLWV5Sx98+ruRgUxBTCDRVwaYpKCgYVrTqMSgkuXQ+f3wWl0zLJm6AW+sHwuPQ0ZRo3aPYVFyJPlduu9YRBBalxvHNBUX8euVeqlpCZMQ7+pxIblmCam8It13na6cXclzW2PyiM5ZZQ5hE3P7qlEnL0mDoV/LBU089xbPPPktiYiIej6fjssrKSmbNmsXf/vY3rrjiCrZt28ZDDz0U0wGPdIGIyUPL91DeECA7wUGC03ZEbolD18hOcKKpCn987wDrShuGabSDx7AELcEIzYFIt5W0k1w27jprIhPT46j2hvEGjS7zf9oJIfCFDKpbQhSmurnrzImkuLsOF1RFYfHkdB5ecgLfO7uYJSdlMzUzngSHjTi7Tl6Si3OnZvCN+YU8etlJ/O/svGENgCCaMO5x6ASN2O01DhomE9LcnV6DM/OS+M5ZxWQnOqlqCfX4vLdrf/4rW0Kkxzv41qIi5hWlxGys0ujh0FRUVRlwo+LeiM4Ag02TS2FS7PXrXf+ll17C5XLx3nvvUVhYCMBf//pXFEXhV7/6FfPmzeOCCy5g/fr1vPbaa9x3330xHfRItqGsgb11rWTE23v8hp3stlHZHOSNjyqZW5g85Im4sSaEYG+dn5V76lhb2kDIMBFE3zDnFqawqDiNSemd631kJzj5f+dM4ukN5WypaOZQcwinTW2bFQGUaH8wX8ggGLFw2zXmFqbw1dPGkxrX83yJrqmcMj6ZU8YnD94DjxFVUTg+O55Ve+picn+WEFgCpnaxvHdSTgI/+/xxvLy5gjWlDRxqCeHUVVw2DaeudhS+s9oSqQMRk0Bbv7tFxWlcd0per55/6diUnejAoamEDGvA1dl7EjIsxie75ZKrNCj6FQRt376dBQsWdARAdXV1vPfeeyQlJTFv3jwANE1jxowZvP3227Eb7QgnhODtXbWgKL3uyZXstlHWEK2DcWLO4NbBGEwtwQi/W7OPrQeaCEYsXHa1o2Fn0LD49/Zq3tlVy0k5CXxjfiHJh83gJLvtfOesYg40BVi1p57lu+toCkSiO8OIlhxIdOp84YQ0FkxMIz95+Lq6D7aFE1NZW1pPyDBxDHDnjS9k4LFrzCvserYmyWXj6/OLuPCELFbtqWP13mhT26bPbKN36CrxDp1zpqawcGIaRanuYWm6K40cWfFOPA4NX9gY9CAoYgompY+tlApp6PQrCDIMA7f705YPS5cuRQjBokWLOt0uFAr1apr9WFHtDVFW7yfB0fs3BYeu0uCP8OGhllEbBDUHIjywtIRPqnwkuXRSumiimOTSCUQsNu9v4sdvlfCDcyZ1CoQAcpNcXD0rl0umZXOgKYA/HF0Wcts1xiW6Bv3NdiSYNi6RSekedlR5yUnsf70g0xJ4QybnTsnocadbQYqbglPyuWZWHpUtQSqaArSGorN4brtGfpKL7ESn3JkjddBUhROyE1gZo1nL7kQb/ypMGqbNCtKxr19BUFFRER999FHHz6+//jqKonDeeed1XOb1etm4cSMFBQUDHuRo0Ro2OxJRe0tRFISIfmsfjYQQ/G5NGZ9U+Y7aPLY9ydmuKeyubeXhlaXcd97kLpcAXTaN4nRPF/dy7NNVhRvm5nPfm7uo90dI68eSkxCCGm+InAQnV8/M7fXvaapCbpKL3KRjd6ZNip2FxbGbtexOcyBCqtsmC3FKg6ZfidGLFy9m7969XHfddXzve9/jtddew+l0smTJEgDWrl3LBRdcQFNTExdffHEsxzui2TQ1uiW5j7NfikLH0tFoU1LTytYDzSS5bb1aAtQ1lZQ4G9uqvGyvlH2mulKc7uGa2bkgoL413KfXkyUE1d7o1vVbTy8gaQjquEhj00k5ieQnu2hojX0VcojOZgYjFgsmpg77pgXp2NWvV9b/+3//j40bN/LSSy91XPbTn/6UlJRo7sHll19OVVUVc+bM4bvf/W5sRjoKpHvsxDt1fCGj10l8Ztv2iuzE7vvvCCFoDESifch0rcvlpuGyYk8dIcMiNa73H7bOtiXA5bvrRu0S4GA7b2oGAC9urqCyJURqnP2oPb+EEPjDJo3+CGkeO18/o5Bp42RHd2nw6KrCVTNz+cWyPXiDBvHO2AYqtb4w2QkOWYhTGlT9etUmJSWxYsUKXn31VSorK5k/f36n1hXXXHMNubm53HzzzdjtY2cHicumsWBCKq99WIkQoleBSkvQIMll47SCI5NXAxGTDWUNLN1VS1mDH8sCVYG8ZBdnT07ntMKUYS0eFjYs1pU14LZrfQrKFEUhzq6xeX8jrWFDfsvrgqIonH9cJhNS43hmYzm7a1uxRHSp1amr6KqCIJo0GjRMwiboCpxakMxXTs0florX0tgzOz+JMyel8Z8dNThtaq83hPSkJWigqQrXzck/IndQkmKp358+DoeDa665psvrfvGLX/R7QKPdwuI0/ruzhgZ/pMctxBHTwh82OXtyOomuzjMpB5oCPLR8L2X1raAoxDs0ND26XXx3rY9dNT7+/nEV3z5zAkWpw7Nzwhc2CBsWdr3vs1IOTSUQsWgJyiDoaCZnevi/C6fyfkUzK/bUsaPKG809MwUoYFNVPE6d04szmJMbz3GZ8SNmllA69imKwv/OymN/Y4Dtld6j5gX2ljdk0Bo2ueiETE4rGPmlLaTRTX76xFhBipurZuby+3crqG8Nd7t0FTJM6nwRpmR6uHx6Tqfrarwhfrp0N/sbA12+qXgcOoYlqGgK8LOlu/l/504elmTWARVKa3tKxtDmwX6zaSpzCpKZU5BMxLQ42BzEFzJQgCS3jewEJ5kZCdTVeeXzKQ25eKfOd86ayC+W7WF7pZdEl96vGWohBPWt0eKqFxyXwbWn5MuAXhp0vXql5ufn9/sAiqJQXl7e798fjT5/fCaqAn/YcpBDLSEcmtq2ZBRdvvCFDFRFYdq4BL61aAIJzs6zQH9+/yD7GwNkJXTf0kBXFbLiHRxqCfHi5gruOXvSUDy0Tjx2DZum9qtje8S00DWFeNkLqE9smkpBirvTZfJzQhpuKW479549id9v2s+KPfV4QyFS3Laj5rG1a89nawoYJLltXDE9h/OPyxz1xWOl0aFXn0AHDhzo9wHGYiSvKAoXHp/FyeMSWb23nuUldbSEoq0JdFXl1IJkzpqUzszcxCP6ZdX5Qmwsb8Tj0HqsOK2qCokunQ8PtlDRGCBviIsIOm0as/OTeGdXLUmuvu1C8oVMTi9KiXkypSRJwyPeqfO1MwqZnZ/MS+9VdPTsc9s1HLqKQ1c7AhvTiuayBSMWwbZK5KeMT+L6U/KH/H1MGtt69QlUVlY22OM4JuUmubhqZi6XTcuhMRAhYlp4HPpRA4aN5Y34QgZZCd3vFjucx65xqCXEhn0N5CWPi9XQe21RcRqr99QTiJi4erkjLmRYaKrCWZPSB3l0kiQNJUVRmFOQzMy8RN4/0MyK3XVsr/J27FyE6BK4qio4dZUkl41TpybLSuTSsOlVEDR+/JGduqXes+sqmfG9C2oaWiMo0Oup4PY3jXr/4NTq6MkJ2fFMzvTw8aEWshLUHmevTEtQ5wszJdMjt3BL0jHq8J59hmlxoDnIweZg9AuQQrSJcbKLDI9dBj7SsBrUCn2hUIg33nhjMA8hDTNVUbhjYRHjU1xUtYQIGd3nB4UMi6qWELlJLr61aIJswyBJY4Delsc2rzCFM4uj/f9m5SeRGe+QAZA07PqdkPHPf/6T3/3ud5SVlR3RI8yyLILBIM3NzViWhWmaMRnsWJAaZ0cQrfzbm9mg9uc9dRgrA6d7HPzgnMn8euVedtX4MC2Bx6Fj16LjD7clg2uKwuRMD99eNIFsWcdGkiRJGmb9CoKWLl3KxRdf3GM5f4/Hc0RTVeno5hQk84ctB/AGjSNqB3XFFzJx2zRO66ZTeH8YpkUgYmHTFFy97IOWGe/gJxdM5cODzSwrqWXrgRZa2xqg6qrK3IIUzpqUxowuksElSZIkaTj0Kwh6+OGHEUJw6623ctNNN/H666/zk5/8hE2bNqGqKm+99RY//vGPSUtL69RaQ+pZWpyduQXJvLWzFo9DP2qOjWUJmoMG8wpTBlwnSAjBjmofK3bX8e6+xrbuzVCcHscls/KZkuzosUmirirMzEtiZl4STYEILcFoU9h4hyarvkqSJEkjTr+CoM2bN1NQUMBvf/tbFEUhFApx//33U15ezpIlSzj55JMpLi7msssu46GHHuL++++P9biPaVfOGMeuGh/lDV0XS4TobE2NL0xOgoP/nd37TuFdCRkWT6/fx8o99YQMC7ddw6YpWEKw9UAzH1dupyjVzZ2LJvS6HUOSy9bnbfOSJEmSNJT6tS7R1NTEtGnTOpLaTjjhBBRFYcuWLR23ueSSS5g8eTL/+c9/YjPSMSTd4+C7i4uZmB5HnS9MZUsIX8ggEDbxhQyqWoLU+MLkJbn43tmTBjQLZAnBk+v28fauWpw2lZxEB8luGx6HToLTRk6ik/R4B7uqffz0nd00+MMxfKTdCxkWa/bW84tlu/nOP3Zw778/4fl397O3rrVPXdUlSZIkqTv9mgmKj4/v9EHkcrnIysrik08+6XS7448/ntWrVw9shGNUbpKLn144lQ37Glm6q5bS+lbClkBVoTjdw9mT05lXlDLgvltbDzSzck89iU6duG6qN0e3+NsprfPzj4+ruH5O/yuI98am8kae3bifKm+orcBktFnoRwdbeHNHNSePS+RrpxeSNIzJ4NLACSH4pNrHh4daaA0Z2DWVvGQXpxYk97rmlCRJ0kD06xN06tSpbNmyBcuyUNXoZFJxcXGnmSCIzhgFg8GBj3KMcto0FhWnsXBiKk2BCIG2yqrJrq77kfXHspJaDMsiznH0nB1dU3HZVFbuqeeyk3MGrXv9+rIGHlldSiBskubpvBTYXl5/475GGgMRfvC5Sb1KHpdGnvf2N/HXDw+xp7aV8GFtVxQgNc7B2VPSufSkbOy9aLsgSZLUX/16h7nkkks4ePAgV1xxBbt37wZg4cKFVFRU8NRTTwGwZs0aVq1axYQJE2I32jFKURSS3XZyEp2kuGNXXKw5EOGDgy14HL371p3gstHoD/PhoZaYHP+z6lvDPLluH6GIRVaC44hcKEVRiHPoZMTb2VXt4+X3+t/ORRo+b++s4cHle9he5cVt18hOcJCT6IwuvXrseEMR/rTlAD9ftptgRJbXkCRp8PQrCLr11luZPXs2r732Gt/61rc6LnO73dxyyy2kpqaycOFCLMvipptuiumApdjxhgwiptVl4nVX2pelvG27vmJtzd56GgIR0uOPHujZNJU4h8b6sgbqWocmR0mKjQ8ONPPsxv2YliAnwdHWWPjTc61rKqlxdlLcNjaVN/H0hrHVfFmSpKHVryDI6XSyevVqfvnLX3LuuecCkJGRwT//+U8KCgpobGzEZrPxjW98g5tvvjmmA5Zix6apKIpCb/OM2/PAbFrsq7wKIXinpBabqvSqSGSCU8cbMlhf1hDzsUiDQwjB3z6uIhAxSY07+pKu06YR79RZW9rAgabAEI5SkqSxpN+JHQ6HgzvuuKPTZQsXLmTv3r1UV1eTmJiI0ymrAo9kqXF20uLsVLUEcfeiKKI/YuLQVcanuGM+lpBh0eCP4OxlQmx7oFTnkzNBo0V5Q4AdVV4SnHqvlnTjHdHmwKv31nPVzIGVgZAkSerKoGQdZmZmygBoCIUMi3VlDfz1g0O8+sEhVu+t71Uuha4qLJ6cTsQUWFbP00HNAYMpmR4mpMY+CGrX1zkmgdwuP1psr/ISNEzielmFXFEU7JrC5v1NnS4PRkwa/WH8YZkvJEnSwPRrJqgvxQ8VReEHP/hBfw4j9cASgn9tr+Zf26up8YaiAYEAUEjz2DlvagYXn5R91EalCyem8p8d1VR5Q2QlOLpdimr0R3DoKhcelzUoTQ8dukqSy0ZVS5B4Z88vS6ttaS49zhHzsUiDwx8xURSlT68fTVVoDRlYQvDhwZa2lizNmG299SZneFg8OZ3ZeUlyJ5kkSX2miH5UnlPV9lySzr/62Tc3IQSKoozIBqp1dd5e58KMREIIntm4n39tr0ZXoxWa2xOcDdOiKRBNej5rUjq3nlF41EBoR5WXB5fvodYXJtGp43FoHec3aFh4QyYqcPWsXJaclD1oj+n1Dw/xwqaKowZj7ZoDERRF4TeXnEC6Z2wHQooCaWnxI/41/Y+Pq3hmYznZCb3vHl7nC5MZ72BCWhxrSxswrLaK5qqCKQStoWhgNS0ngTsWTRiRVcpHy/kZq+T5GdkOPz8Q/f9Y6tdM0H333dfl5aZp0tDQwIYNG9i6dSvXXnstX/ziFwc0QKlrq/fW858d1Xjs2hEzJ7qmkuax0xo2WL67jonpcZx/XGa393VcVjz3nTOZv2w9yNYDzVS2hDqWpXRNZWp2AudPTmNeUeogPiKYPyGVNz6qos4XJt3T/Q4xw7TwhUwWT04f8wHQaFKU5samqQQNq1fFEIUQBCMmrWGTlXvqSHTpxNk717NKcNoIGSbvH2jml8v3cu/ninudVyZJkhTTIOhwDz74IN/73vf48pe/3J9DSEchhOC/n9RgCo66dBRn1/GFTN7aWcPnpmQcdTaoINXN3YuLOdgc4IMDLbSGoxV8izPimH98Dg0NvkH/lpTmcXDD3PE8traMGm+Y1Dhbp47zQggCEYtGf4SJ6XFcO8CeadLQOi4rnqJUN7trfb0KggIRC5Ro/agkl95tdXSHrpHmUfiosoU1pQ2cPTk91kOXJOkYNThlf4G77rqL5557jvvvv5933nlnsA4zJpXW+9lT10piL3Jnklw2KhqD7Kz2ckJ2Qo+3H5foYlzip73IFAXUowRPwYhJIGLismkx+Qa+YGIquqbw3Mb91PpCQHQrvyUEEVPg0FVm5iXxjfmFsjP9KKMqCucdl8me1a20BA0SjvL6NczobkGXTSNoWN22dGnn0FUQgqU7a1g8KW1Q8taOZW+//R9effVPlJbuxePxcOKJ07jppq+Rnz9+uIcmSYNq0IIgiDZWfeuttwbzEGNSUyBC2BQkuXpOBLVrCpG2D5RYEULwwcEWlpfU8n5bkqqmKJw8LpEzJ6UxIzdxQB9C8wpTmJGbyIZ9jawrraehNYKuKUxMi2PhxDQmZcTJD7lRatHEVPY1RHvQhU2LZJcN7bAgWwhBa9ikOWBQmOqi1hfu9W6yBJfOvoYAlS0hchLl7tTeeuqpx3jxxecYNy6XJUu+SG1tDStXLmPLlvd47rmXyc7OGe4hStKgGdQg6OOPP0bT5Pp8rGmKgkJ78cKegwFFodMHzUAYluDZDeW8vauWiGkR15akaliCNaX1bCxv5KxJadw0d3ynpay+ctk0zixO48zitJiM+1gghGBXjY+S2lYipkWC08bsvCSS40ZeMnB3FEXh+lPySHbZ+PvHVVR7o7N9uhot2mlYArddY25hClfNHMf3/rmj169dXVXxCwO/bLXRa598sp2XXnqeadOm88tf/rajtMmKFe/wgx98l+eff5p77uk5/UGSRqt+BUGlpaXdXmeaJjU1NTzyyCPs3r27o6K0FDv5KS7i7Bq+sNnjbJAvZOK2aRSkuI56u97685YDvPlJDR6HRoJTpykQoTVsYlkCSwiEgL+8f5AdlV6+Pr+QyRkeOWsTAx8fauGPWw6wu63hqKIAAuKdNuZPSOEb50wZ7iH2mqooLDkpm7Mnp7O+rIH3KpppCUZLMExIjWPBxFTGp7gJGRaqomD2ooYVgGkJVAWcI2CrvGFFk7qduoptBIynO6+99goAd9/9/U613RYtWswXvrCEzMys4RqaJA2JfgVBEydO7PGDTQiB3W7nhz/8YX8OIR1FitvO3MIU3vqkhsSjVN8VQtASNDi9KKVTnk9/1flCvPlJDQ5dxRcyafAHMK1o4GNancsWvlfRxHf/+Qkn5STwjfmFchfXAGwqb+ThVaV4gwbJbhuptmjLCcuKnt9/bqvmkC/CXQsLu00eHok8Dp3PTcngc1MyurzeoauckJ3Ahn0NJPZi67s3aDA+xUV2wvAshbXP1C3fXcfGfY1ELIGuKMzIS+SS2fmMj9PpeznQwbVx43qKiiZ2mfvzne/cOwwjkqSh1a93zPz8/G4/eFVVxePxMG3aNL75zW8yc+bMAQ1Q6tqFx2WyqbyRKm+YrC4ajgohqPGGSXDqXHRibL7NrSltwBsyQAga/JGOZTnDEtEEaqK1Gi0R/RcyTLYeaOYnb5dw37mTSZGJzH3W4A/z2Np9+MMGOYmd6+uoqkKS24bbrvFBRSMvbbZx87yC4RvsIDhrUhqbyhujsypHSbyPmBamEJw9OSNmS799IYTgT+8f5G8fRXujue0auqoQsSxW7K5jY3kTiyamcsOp+QNaJo6lxsYGmpoamTXrFPbv38cTTzzK++9vRgjB7Nmncuutt5GTM264hylJg6pfQdC+fftiPAyprwpS3Xxr4QQeXlXKoeYQTpva0f8rEDYJRCyS3Da+dnoBUzJjU1xqb10rhinwhgw0VUFBwWhbmmn/2FEAVYkGQb6QyeQMJ6V1fl77sJIb58qdJn21Zm89Df4wWfHdFxi06ypxDp01pfVcMT3nmNo1NyMviRl5SWwqbyQ1ji4DoYhpUeMNMykjupQ2HP7+cRWvbj2Ew6YeEawmuWwEDIv/7KjGqatcPyd/WMb4WXV1tR3/vfHG6xg3LpcLLvgC+/eXs3LlMj78cCtPP/17srIGr0CqJA230TN3Lh3h5NxEfvr5qSwrqWN5SR2+kIFAEGfXOf+4VM6clE5+cmxygeDTPAchBJqmEjYshIgGPYdT2v5FTAtLgNuusWZvPZefnNOrZY2O45kW7x9oZuWeOvY3BlBQKEpzs2hiGifmJAzLN/6htnJPPZqqHLVMAUCiy8aBBj+b9zd1u7w00u2r9/NRZQvBSDThfkZeItkJTm5fUMSvVu7l/QPN4I8Q79SxaQqmBS3BaEuNyRke7jprIp4ettIPBl/I4I2PKtFUpduK1QkuG6FItGbXuVMzyBqmJbvDBQIBAD744H3OOed87rnnvo6NLK+++md+85uHeOSRX/F///fgcA5TkgZVr94xjpYI3RtFRUUD+v3Pqq+v5wc/+AGbNm1C0zS+8IUvcPfdd6PrYy+my05wcs2sXC6blk2DP4JAkOK296oYXV9leOxtyarRn9uXwT6rvaiiAFrDJglOnWpviO1VXk4rTOnVsaq9IX61Yi8lNT5MEa0PJASUN/pZs7eBk3LiuX3BBJLco2dnVH80tIajNXB6EJ2Zi5ZPGG32Nfh5cVMF2yqjDVbbW7a47Rozc5O49pQ8vre4mPVlDby9q5a9da0EI9Gk6aJUN2dPSeeMotRhCYAA1pc10BiIkBl/9Ly3RKfOoZYQq/fWc/n04V9mUtXo60rTNG677VuddvJeeunlvPrqn1i/fg3BYFA2xJaOWb161+hNInR3FEXBMIx+/W53br/9djIzM1mzZg11dXXccsstvPDCC9xwww0xPc5o4rRp5CQObjmCOQUpPLNxf3Sap6cNO0r7spjomLEJ9HLrclMgwk+X7mZvXStpHvsRQUAgYrKlopkHl+/h++dMGpSAb6Sw6Wqvnrf2Pn4jJd+kt/bWtfLA0t3UekMkunSS3Y6OIMgbMlm1t559DX5+cM4kFhansWBiKjW+MIGwicOmkuFxDPuMYGm9HyF6LkOhKAqqAiW1rUM0sqOLi/MAkJmZRWJiUqfrVFVlwoRiDh06SHV1FePHFwz9ACVpCPQqCOoqEbqlpYXGxkYACgsLKSwsRNd1Dh06xI4dO7Asi8mTJ5ObG9vWBuXl5WzatInVq1fjcrnIy8vj1ltv5cEHHxzTQdBQOC7Tg8eu0xI00NWuoyDR1sheJRoraeqnW5zbc5YONQfZVN5IS9DApqtMSo9j2rjEjrYeb31Sw976VjLj7V1+qLtsGukehY8rvazcU8d5U7vvizbanZSdwNJdtR3NiLsTjFjoWvS5HC0M0+KR1aXU+UJkJ3ZumqsoCglOnTi7RnljgMfX7eOH505GUZQeZ1yGWm+38AOoRIuXjgQ5OePQNK3bL6mmGb3c4ZCzQNKxq1dB0GcToffv38/cuXOZPn06zz33HNOmTet0fVlZGV/60pfYtm0br7/+eswGC7B7926SkpLIzPz0g2/ChAkcOnSIlpYWEhJ6bg0BdLmMIx2p/Xlqb59xyUlZvPTeAcJmtCaLYYGmdF4CU5Vo8TtNVfA4dJqDEZJdNnITnTy0fA/vVTThD5sdE0q6qpCX7OKaWblMG5fIspJaHJp61FkNu66iKvDOrlrOnZrRY9f50erMSWms2luPP2x22zpCCEGdL0JxmpsTsuNHzWt768Fm9jcESI2zd3v+NFUh2a2zo8pLab2fiSMwyEuNs6Mo9BioAhhCtCW5D9HgjsLpdDB58lR27NjGwYMV5ObmdVxnGAZ79uwmMTGRjIz0ETHewXL4e5w08gz2+enXIvp3vvMdAoEAb7/9NqmpR+7GKCws5J///CcTJ07kzjvv5N///veAB9qutbUVl6tzsm/7z36/v9dBUGpqbHZMDZQ/bLC6pI6PDjTRGjJIjrMztyiVmeOTR9TSRvvz9b9nTGBVaQP1rWGCERPTsjBFWzK0AjZVQdcUDFOQ4rGj6yphE849IYPfri+npMpHgksn7bDdTsGIyf6mIA+vLuOqU/JpCpkke+zYeljmSvbYqfSGMe02MmJQB2kkWpDiYXF5E29tr0a3iSPyXiwhqG4O4XHq3HJmMenpvXv9jwQfbjqAUBQ8PSTLJ+oq3sYg2+r8nDp15BXvu2BGLv/YXk3IEkdtaGwIcNl1LpiRS1rayHj/ufrq/+Hee+/lscce5rHHHuvIq3zqqaeoqanm+uuvJzMzaXgHOURGymeC1LXBOj/9CoLeeustzjzzzC4DoHbx8fHMnz+ft99+u9+D64rb7e7Y1dCu/ee4uN5/S6yv9w56V/SerNxTx0ubD1DrDWERXUKyBLz2XgXjU9x87YwCitM9wzpGRYm++Nqfr6amAEUpbg40BjBMq2M7vKZGAyChKERMgdum4dJUDjYEmJQRR01TgE8OtnQscRnGp0sCGpARZ6PWF+b5dWVEDAvLrtJTiq8wLSKGSVWNF1sktnlnI8mXZ40jEIiwrqyBOm8It01DVSBkWBiWIMll4zvnTmFiop26Ou9wD7fXDtT5UIQg0oucJ9OyqKxvHZGPL0GBadnxrC1tQCPa8PezFE2hujnICdnx5Ln1EfM4Fiz4HPPnL2XVqpVceOHnOfXU09i3r4wNG9aRl5fP//zP9SNmrIPls+9x0shy+PmB2AdD/QqCFEWhqampx9tVVlbicMR2/b64uJimpibq6upIS4v2ldq7dy9ZWVnEx/f+yRGCYX3BLy+p5Yl15UQsi3RP59yXkGGyt66Vn7y1m++fM4mJacO/BGBZgn9sq+ZPWw7iDUaId+h4QwaGFX0iDautbYEKDk3BoatELMEp45O4fHoOP/zPLuKdWrezW4qikOaxU9EURAgIm1aXHyaHC5vRPBiPQx/0cymE4GBzkEDExKlr5CQ6hywh16Fr3L6wiLMmpbFidx0fHWohbFqMS3KxcGIqCyamMrUgjbq60fUm7rRpmL0dsACbpozYx/fV0wqoaw2zs9qHy6aS2NYYtr2qd8C0GJ/i4rYFRSiMpMehcP/9P+O11/7CP//5d1577RUSEhK5+OLLuPHGm4mL84ygsQ6u4f5MkI5usM5Nv4KgmTNnsnLlSlatWsWCBQu6vM3rr7/O+vXrufjiiwcyviMUFBQwc+ZM/u///o/777+fxsZGHnvsMS677LKYHmcwNfrDPP9uBYZldZnk6dA1shNUDrWEeGZDOT+9cOqw9996a2ctv99UgarAuCRntG2DEHiD0YaVwbBFwDApTHFzcm4i6R4HcwuSKUp18+aOGlrDJlkJRw+IVUXBqSkEDYuWgNFjCwhfyGT+hNRua7PEQtiwWL23nqW7aimr92OKaC7UuEQXZ09OZ1FxWkfC92BSFYVp4xKZNi4R6Jx/MlpzGY7Limd9WQOWJY5aByliWmiqwuSM4Z0VPZokt40fnDOJ1z+sZOWeemq8oY4NlAlOG5dOy+GCSamkxo2spG4AXde54oqrueKKq4d7KJI05PoVBH33u99lxYoVnHfeedxyyy2cd955HbvA9u3bxxtvvMFzzz2H0+nk+9//fkwHDPDII49w//33c9ZZZ6GqKhdffDG33nprzI8zWNaUNtAcjJB1lF0uiqKQ4rKxp7aVT6p9HJc1fOvVvpDBX94/CIhOb+KqopDosnUUQGwORAgaFktOzKYg1d1xu5aQgYLSq+Rlu66hKNEGHN6QQXw3ycBNgWjDzbMmpQ/osR1Na9jgVytK2VLRhAASnDo2VcGwBOUNfp5cv4+1pfXcddbEIW8JMtxBcSycUZTCK1sP0RiIkBrX9fMnhKC+NVqDZ3Z+8hCPsG8SnDaun5PPZSfnsK2yhdZwtNXHCdnxTMxLGXUzdZI0FvQrCDrrrLN44okn+OY3v8mvf/1rHn744U7XCyFISUnh+eefZ8aMGbEYZydpaWk88sgjMb/fobJxXyOq0nMVYKdNpTEQYeuB5mENglbtqqXeH+6xCWqCU+dQc4iVe+q4PvXT1gAOTUEgerV7xhKCtDgbM/OSePOTGkIRi0SX3rE0FjYsmgIRBHD5yTmcPG5wEoGFEDy6pqytXYOtU7sGO9Ht/mHDYlull1+v2Mt9504eUYnso0Gy287lJ+fwwqb9NPjDJLtsnV4flhDUt4axayrXzMrtVdHIkcDj0Dm14NOioKMpXq32Ros5vl/RhC9s4tJVjs+OZ+HENManuHu+A0kaZfpdYvWGG27g3HPP5YUXXmD16tUcOnQIRVHIzc1l8eLFXHfddR05O1Jn3pCBrvX8zqgoCgLwh3tXZHCwbD/UjGXRUcenO4qiYNcVPjzU0unyKZnx2DWVYMTCdZSlIyEEIcNiRl4SN8wdT0a8gzd3VFPjC9NenVFBISvBwZITs/nclPRBmxEpqWllU3kTSS6928addl0lzWNjW6WXLQeamTN+ZM9UjESfPyETQwhe3XqIQ80hbJrS1nhUYFqCBKeNL83J44wJw9MTbKwIGxYvbq5gWUkdvrDRUeLCsgSfVPv4944aZuclcfO8gqPugJOOHb/73cP8+c8v88gjTzBjxqxO123cuJ6XX36BkpJd2Gw6kycfx4033szUqccP02j7b0Cv5tzc3EFZ7jrWeewaptm7eXEFjho4DIVAxOz1t1lVUQgZnYvBTc30MCEtjh1VXnJsareBiy9k4tBVFhWnoakKS07K5rypGbxX0URVS6gjF2d6biL2QZ4VWLGnjpBhkRp39Hwjh65higjLSmplENQPiqJwyUnZnDo+mVV769lU3oi/rdXK3MIU5helkNbDDKQ0MIYleGR1Kav31uO2a2QndC5cKYSgNWyyem89jYEI936uuMd8PWl027FjG6+++qcur/vHP97gF794gNTUVC644Au0tvp45523ufXWG3jssWdGXSAkX8nDYHZ+EtuqvFhCHDVPJhgxsWkqJ+UMb+2XFLe9xy4Z7SKmRepn+nkpisL/zs7lp0t3U+UNk+Gxd9pZJUR0B40vZHLB8Zmdqh47bRqnFw39LMAn1V4cevcB2+FcNo2d1b5eLfdJXctJdPI/M8bxPzOGv6fWWPPv7VWsKW0gyWXrMslfUaJFT+2ayseVLby8+QBfnVcw9AOVhkQkEuFnP/sxpnnkCkRVVRW/+c1DjB9fwO9+9zTJydEvfhdddCm33PJlHn/8tzzyyBNDPeQB6VPbjJUrV1JYWEh+fn7Pv9RGURTKy8v7PcBj0fwJqbz2YSUNrRHSPN0nhDb4IxSnx3FC9vAW8ZpXnMar71UQjJjdLg1BdIu8JWBeF0HLCdkJfGvRBB5dU0a1N4SqKOgq+MMW3lC0E7jHofPBwWZe2XqIBRNTh7XTdsTsujlsV9p7pFkiWj1bkkaLiGnx1s5aNIUedznadZU4u9bWADaH5CHeDCANjRdffI79+8uZPXsOmze/2+m6f//774RCIW6//a6OAAjg+ONP4KqrriUSCQ/1cAesV0HQgQMHUBSFSCTS8XNvyW/GR0rzOLhqZi7PvbufWl+YFLet08xIxLSo9YVJdNn4yqnjh70lxMm5SRSlutlZ4yM7Qe1yPEIIan1hUuPszOumU/zMvCQevuQE1pU18NYnNXx8yEvItLBrCkmuaKPUWl+Il987wN+3VXHNrFzOm5oxLK+htDg7B5sCPd+QaNHCoawbJEmx8v6BZiqbgyS7e1dmIsGhU+UNsba0gc+fMPKqd0sDs2fPbl566Xmuvvo6QqHQEUHQxo3riI9PYObM2Uf87s03f32ohhlTvQqCysrKABg3blynn6X+O/+4DFQV/rTlINXeEArR3lymFV0iG5fo4mtnFAzrrrB2qqrw9TMK+fFbJVQ2h0hy23AfltsTjJg0+CN4HDq39JA4meC0MSM3iX98XI3brlEQ7zqiKKIQgnp/hOc27kdTFM6ZmjGoj68r8yek8uHBZgxLHDUh3BKCiClYVCw3AUijz8GmABb0OsdOVaObNQ40Bwd1XNLQM02Tn/70fsaNy+W6677CU0891ul6IQT79pUxYUIxDQ31PPnko2zYsJZgMMhJJ53MLbd8g+LiycM0+v7rVRA0fvz4o/4s9Z2iKJw3NZPTClJYV9bAR4da8IdNklw25hQkMzsvadCTf/uiINXND86ZxNMbytlV46M58GlTC11VmJAWx3Wz8zg5N7HH+3r1g0McaAqQleDocvZEURTS4uzU+sK8/N4BThmfNORT73MLk/nz+w5qfWGy4u1dzkZFG5eGSXLZmC93L0mjUMQU0OuMvyiF6G4y6djypz+9REnJTh599Gns9iPfb30+H4FAgHA4xE03XY/D4WDx4nOpr69j9eoV3HrrDfz2t08yZcpxwzD6/otpYrRhGLz++utUVFRwyimncMYZZ8Ty7o9JiS4b5x+XyfnHZQ73UHo0PsXNj8+fwp66Vt6vaMYXNnDoGsdnxXNSTkKvloPqWsNsKGsgzqH1ePtUt40qb4g1pQ18YYin3uPsOl87o5CHlu+hsiVEirtzraCwYVHfGsZp07hh7vgeayhJ0kgU79Tb2kX0Pqm/vXCodOzYv7+c5557miVLLuOkk07u8jbBYDQ9oKRkFzNnnsIvfvErHI5o3ubatav47ne/zS9+8QDPPfeHoRp2TPT7lfzyyy9z//338/Of/5wlS5ZgWRaLFy9mzZo1Hbe55ppr+P3vfx+TgUojg6IoFKd7+t3YdeuBZrwho8cWGhCdelcVhfVlQx8EAUzPTeS7i4t57t39lDcEaPBHOir+6qpCXrKLa2bldiqMJ0mjyfTcRNx2DW/I7FVgE4yY2FWVGb2Y8ZVGByEEP/vZj0lKSjpqXk+0kn/U17/+zY4ACOD00xcwffpMtm7dQkXFfvLyer95arj1KwhaunQp1157LQDV1dUA/PGPf2T16tWkpaVxzTXX8Oabb/Lyyy+zcOFCvvSlL8VuxNKo5g0ZKErvWmgA2DWFRn9P/eQHz4k5CTx00fF8dKiFDw42E4hEaxmdkJ3AzNzEQasSHYyYbN7fxEeHWjpahGQlODm9KIUCWblXipHsBCez8pJYuaeeeId21Nmgw3esnjjMZTuk2Hn99Vf46KMPePDBh3G7u2/W7fFEv/jquk5R0cQjri8unsTWrVs4ePDAsR8EPfLIIyiKwuuvv85FF10EwJ/+9CcUReHxxx/n0ksv5fvf/z5FRUU899xzMgiSOtg1BSF610IDwBK9T9ocLJqqMD03kelD8O3XsAT/3FbVVik7hGWBpkY7KFsC/rGtihOz47lqZi4T0rp/w5Kk3rpkWjbbKr1UtYTI/EyhxHbtuz/dNo3/mZE77DtWpdhZsWIZAHfddXuX1992280AvPrqP0hLS6ehoR7RRRM8wzAAcDqHr7RJf/QrCNq0aROnnXZaRwAUDAZZvnw5drudCy64AICUlBTmzZvH+vXrYzdaadAEIyYVTQFChoXLpjE+2RWzWY4DTQHWlDZQWtdKtTeEL2RQ41VI+0zRxM9qb6NxXObw75AbCoZp8eiafSzfXYuuqaTF2TvtnGuv3PtueRN76/x8a9GEYS+kKY1+Ralx3LGwiN+sKqWyOYTLrpLg0KNtM0R09rY1bBLv0Llx7nhm5ScN95ClGDr//M8zffrMIy7fvPldtm37iPPOu5CsrGw8nnimTTuZZcuWsnXrFmbPntPp9rt27UTTNAoKioZq6DHRryCoubmZnJycjp9XrVpFKBRi0aJFnaJAh8OB3+8f+CilQVPZEmRZSR0rdtfRFIhgCYGmRPtzLZ6UzqLiNPq7+bvRH+aZDfvZUtFEa9ik/fM8bAoqW4Id3cPT4uxdFib0ty09nTlGtp+//N4Blu2uJdGld9mWoL1yb5xdo6olxMMr9/Kj86aQn+IahtFKx5Jp4xK5//wpLN1Vy8rdddS1RtrKdUQbwp4zJYPPTU5nUkb/cgGlkev88z/f5eWBQKAjCGrvHfaFL1zCsmVLefzx33L88SfidkeX5pcte5vt2z9m/vxFJCUlDdXQY6JfQVBeXl6nKtBvvvkmiqJwzjnndFxmWRYffPAB2dnZAx/lMcy0BGHTwqF3XYRwMG2paOKR1aU0+CM4dZUEp46qRMd0qDnIs+/uZ2lJLf936Ukk9XFSqK41zE/eKmFvXSsJTp2cREfH8pfLplHRFCRkWFS1hIiYFjkJzuje2zYhw6LRbzC3IJni9GM/B6baG+KtnbW47VqPfZkURSEzwUFlc4h/b6/mljMKhmaQ0jEtN8nFl+bkc9m0HEpqffjD0S8hE9LiSI2T1aElmDlzNpdddiV//eufufbaK1iwYBE1NTWsWrWclJRUbrvtW8M9xD7rVxA0a9YsXnnlFZ599llyc3N59tlnAbj00ksBCIVC3HPPPZSXl3ckUEufMizBhwebWVZSy0eHWtraLSjMyEvkzOI0TsxJiHlA5A0arCtr4P0DTVQ0BvCHTQ42B9EUhfwUJ5r6aZRj06I9u0xLsL8hwPf/to3vL55IZnzv1nqFEDyyqpS9da1kxtuPWFZLdNmImIJqbwjDsqjzhbFrCmkeBxHDosYX7uhk/XFlC1/64wcUpLo5szidOeOTjtq6Y7RataceX9gguxe75iDaqDbOrrG2rIH/mTmu37N1kvRZ8U6dmXlJwz0MaYS6/fY7mTRpMq+99gpvvPEabrebs88+hxtvvJWsrNE36aGIrjKcerBz507mz59PfX09EP3Qu/baa3nhhReAaGXpqqoqUlNTWb9+PRMnHplJPtzq6rz0/ZEPXJM/wq9X7uWjyhZMS+C2a2iKgmEJ/GETu6YyKz+Rb8wvwuMYeC0Ow7T4y9ZD/HNbFVXeICEjmpTc3sReAWyaQma8g7Q4O+pncnRMS1DjC3PulHRuOb2wx+MFIyYrdtfx6Noy4mwaCS5bt3k/3qBBfWuY5qCBqkCSy4YvZGIKgUNTSXJHmzYKIBCONvPLTHByw6n5nHKMdWy/9dWPqPYG+1RvyLIEVd4Q35hfyFWnTxi217R0dIoCaWnx8vyMUPL8jGyHnx+I/n8s9etTdsqUKWzcuJEHHniAqqoqFixYwLe+9ek02OTJk5kzZw4PPfQQRUWjK0lqMPlCBj9btpvtlV5S42xHzGgku234wybryxoJm3u5+6yJA5r1MEyLh1eV8k5JLb6QgWVF69soQNAUKER3HYVNwcHmIK1hk/xkV6egRVMVPE6dtWUNXDljXLeVmw80BVi1p57lu+soq/fjDxs0aSrVvjCJTp1k95GPN96p43FoeEMGdb4wDl3FMAXp8Xbi7J236ya5bERMi2pviF+t3MvXzygclu7ygyFiWjS3bYPvC1VVUBSFpoAxSCOTJEk6tvV7qqGoqKhjGeyzli1bJhunduHNHdXsqPKS7rF3u+3bbdfQ1Ghjw2UldVxwfP8rSb/6wSGW767DHzYRAux69EMzbIho2Vcl2gFdEN1+3RyIcFBRyEt2djp/iS4bBxv8vFfRzNmT0484zorddTyzoZyWkIFTVzEsC11V0FSiy12tYRoDETLjHaS4bZ3uW1EU4h06FU1BIlaECWlx3fbqsmkqWfHRdhpPrCsnN8l1TNTMGdC3z7ZyA5IkSVLfDXgPdCQSYdOmTbz22musW7cOgIqKigEP7FgTMizeKanDpqk91r1x6BoqsHRXDabVvw84X8jgrZ21hA0L0xLYNKUj+Gi/R+Ww/6pKNBBqCRn425ae2mmqAgo0BY4sWrhqTz2Pr91HIGKSk+AgtW2mqL3as01TsWkKlhBUtoRo7OI+/GGTiClw6epRm5VCNGhK99hpDkRYVlLbp+dkpLLrKh6HHg1O+8ASAkE0SJUkSZL6rt8zQYZhcP/99/O73/2O5uZmAK6++mrmzZvHtddei8/n489//vOIzAcaDh8daqbGGyI1rncfWImu6OzIrhpfvzrJry9roK41RNi0UBWlx5k5BbAAwxQ0BiLEHZGPpByR29PgD/PsxnIilkWG59Mmo6qidAreFEXBpilEzOhusDi73mnppzEQQQiBvZd1iRRFwWVXWbWnnstPHnfUrvVDSQiBP2ISiERnwjwOvcegrt2Cian86f2Dferh5A0aeBw6s/JiU8TRsAQfHWrmo4Mt+EIGEUvgsevkJbuYV5gyYp5nSZKkWOnXu5phGFx44YUsXboUm83GrFmz2Lx5c8f1Xq+XrVu3Mn/+fLZu3Upm5shvDjrYmgIGlhCdit8djUNXafBHupw56Y3dta2EDpsFOlx055loXxHroAAoAm8wOtb2HWphw0IBsuI7J+2u3dtAUyBCVryj0we3x661jbvzcXVVIWwKmgMRMtruSwhBS9BAQcHdh0TwBKeNWl+YnTVeZucPb5K0L2SwYV8jS3fVcqApgGkJFCVaCmD+hFQWTEylMMV91OBm/oRU/v5xFd6QQYKz50BZCIEvZHL25HTSBti81Rs0WLW3jqW7aqloDGBYAiGiCYntr5E/bjnA/AmpnDkpjaJUWalakqTOhBA0Bwzq/WEMS6Cp0VSHw78gj0T9CoIeffRR3n77bc455xyee+45srOzUQ/bYr127VpuueUWXnzxRR566CEefPDBmA14tNLaPlB6+02/fR5F7+eLpzX8abLsZ4+nqwqR7u5WRGeELEugtgVPjf4wmfGOTttmTUvw9q4aNFU5YkdZkttGU9DAEtFltsPHoSqCRn+ENI8dVVEQIjr7ZNejfzC9pSnR5aDPLt0NJUsI/vZxFf/4uIoGfxhViXaft+tqtLpzyOD1Dyv5z44ajs+O56unjScroesyA7lJLhZMTOW/n9Rg19SjJsQLIaj2hkl22waUMwZQ0RjgoRV7KKv3o6kKSS4dh9752KYVDVT//nEVy0rq+PKp+SyelDai39gkSRp8wYjJu+WNfHiohZIaH3WtYQxTYLV9idJVhQSnTnF6HMdnJTCvMIUk98havu9XEPTCCy+QmprKq6++2tFU7XAul4unn36ad955hzfffFMGQUBWghO7phJsa0vRE3/YxKlrZCf2rw9LnF3viKQ+G3gpSjTPxzAFKJ+Zr2n7uf32ISOar7N4cnqnJazmYIS61jAe+5GPJc6u47ZptIYNbJraqRq02lYOIGIKHLrSEazFO/Quq0b3JJYNTKMzIL2brTMswVPr9/HWzlpsmkJGvOPIpS9H2xJZONoMtaolyN1nFVOQ2nUy91dOHU9TIMLGfY04bSaJzs7lBYQQBA2LhtYICU6dr51ROKD+YfsbA/zk7V1UNoe6rOfUTlMVkt02klw69a0Rnly3j5BhcuHxWf0+tiRJo1dTIMKbO6pZXlJHrS+EgLYvbyoumxbdeUx0Y0xzIMLa0gbWljbwp/cPcnphCucfn0l+8siodN+vIKikpIRzzjmnywConc1m45RTTuHtt9/u9+COJVMzPRSluimp9fUqCPIGDWbmJfX7hTI108O/NAUlQlsxxs7X2zUVS1hYlugUBSlEk5kVosstzQGD0yel84UTOs84hA0LywLls3dMNMjKTXJS3hggGDHR1E/ziZS2BGzDtPCFDMKmRU6ik4hl9enx+SMmTl09Yomur8ob/KzaU8+6sgZ8YQPaGraemJ3AouI0TspJOCIXSgjBn7Yc4K1Patq2+Xf/Z6QoCnEOHadN40BTkAeX7+GH503ush6QQ1e5c9FE/rz1IO/sqqXaG0IhGoRE31CieVNTMz1ce0oeJ2T3v2+YN2jwyxV7qGwOkZ3gOGI2r7vHkuaxU98a5qXNB8jwOI65ek2SJHVPCMG75Y288G4FB1uCODSVNI+92y+ODlTai41bbTPK/9pRzdqyBi6fnsP5x2X2Om9ysPQrCLLZbDQ1NfV4u/r6emy2kTX1NVwUReG8qRnsqWvFFzKO+sHZHIigayrnTMno9/FOLUghK96BP2x2rM92Hg84dTWaNyRExzZtgcCuKVS2hHHaVBZMTOUHXzieoDfQaSu30xbdyt/d7jW7rlKQ4uJQc7RhatiwUJToLjEhoN4fIS3OzmXTckh06Ty2dh9mF+PsTkvA4KRxCRR1M6vSk30Nfl7aXMG2Sm9He4DoDrroLNzKPXWsLa0nP9nFF08ex7yilI7fLWvw86/t1bjtWq8LWmpqtB9beWOA1z6s5OZ5BV3ezq6rXDs7jyUnZrO2rJ73K5ppDhrYNIXcRBfzJ6ZyXKZnwEtRq/ZG6zllxh9ZILMnKW4blS0hXv+oktn5SXJZTJLGgLBh8ezG/bxTUothCbLiHb1+v4bojuEkt41El069P8KzG8vZsr+JOxZOGNYlsn4FQSeffDKbNm2ivLyc8ePHd3mb0tJSNm/ezCmnnDKgAR5LFhWnsbu2lf98UkPIsEj6TDVlwxI0+aONCy+dls0p45P6fSy3XeP84zJ5euN+IkGjywBDUcBpU4mYgrBhoSpgU6OzK6cVpbJwYirF6XF4HDpBb+f7T3TqFKbGsb2ypdtdQzZNZXyKi2DEoikQIRAx8YdNktw2bjm9gDOKUol36vhCBn/Zeoi61mjuUU8CYRNFUVg8Kb1fH8DbKlv41YpSanwhklyd+5q1S8ZGMGJS1uDn4VV7qfaFWHJiFoqisGpPPf62kgB9oanRVhfr2gpPJh1la3u8U+e8qZmcNzX2mwoMS7B0Vy2aqvRrOVFRFJJdNvbUtvJJdf92L0qSNHqEDYtHVpeyem898U69T/mbn6UoCmlxdoIRk/cPNPOTt0v43tnFw9afrl8JFbfccgt+v5+LLrqIrVu3HnH9xx9/zKWXXkooFOKGG24Y8CCPFYqicMPc8Vw1cxwum0a1N8Sh5iBVLSEONgep9YaId+p86dR8rp6VO+Bv2Eum5XD+1AzsukrYiObhHF5Yrz0p2bIs3HaNglQ3D118HM9fPYMb546nOL37GQdFUToKJxrm0ZeynDaVrAQH+ckuktsCoPOPy+wInjwOnetPyUNXFep84aMW/wtETBoDEU4rTGZeYUq3t+tOaX0rv1yxl7rWEDmJDjwOvdvH6LRpZCc4URWFP7x3gLd2Ritvr9xdh8um9uv8JDh1mgMR1pU29Pl3Y+WjQ81UNAZIcvX/jcxpi84irthTF8ORSZI00ggheHL9PlbvrSfZZRtQAHQ4p00jI97OrhofDy7f02kzz1Dq16O54ooreOedd3j22WeZNWsWiYmJKIrCf//7X/Lz8zl4MFrv5Morr+Saa66J9ZhHNU1VuHz6OM6bmsnasnq2ty3HeBw6J+UkMLcwuccu4r2lqwpfn19ETqKTFzdXUN8aIdLWLqP981tRFNx2nfwUN7fOK2BWflKv739uQTKvJrk40BQgO+HI2ZTDRXc0hciId3QZvCyYmEbIsHju3f0cag4R59BIcOioqoIQgkDEojlooACnF6Xw9TOK+jyLIYTgyXXl1PnCZCc6et2kNtlto84X5sXNFSgImoIG6Z7+fWvR1OiS23v7mwa8s6u/PjrYgmGJI3aB9UV7raZN5Y3cOq9ALolJ0jFqZVs7pESnjquLjTADYdNUMuLtbK/y8peth/jynPyY3n9v9PvT9umnn2bu3Lk8+OCD7Nq1C4C6uui3wvz8fO644w5uu+222IzyGDSYyx2H09uCrs+fkMW/tlezck80F8S0BE6byqR0D+dMyehX8OW0adyxsIgH3t5NZUuItLiu24FETItaX5hEp43bFxR1W+H4c1MyGJ/i5p1dtawva6DKGwKiuwwcmsrxWfEsnpzO/KKUfi3j7KjysqeulZQ4W68DoHapcTYONYfYtL8JIcSAkvlsqkpzsH/1n2Khta2NykDZ1OhSam93PErSaPK73z3Mn//8Mo888gQzZszquDwUCvL888+wbNnb1NbWkJiYxLx5Z3DTTV8jKSlp+AY8COp8IV7afAAFuiigGxs2TcVj1/jvjhpm5iYybVxsir/21oAe1Ze//GW+/OUvU1VVRUVFBaZpkp2d3W2ekDR8XDaNL56cwxdPzgGieSGqQp+Dgc8qTvfw/c9N4jerSqloCmAJQZxdQ1UVLEvQGjZRFBiX6OTr84s4vof8kckZHiZnePifmeP4pMqHP2Ji1xSyE5wUp8cNaMZhxZ56IqaFU+97Ep6iKDh0lY8OtcQkgBjOdl8RU/SrHMERFBBWdEkVuf9BOobs2LGNV1/90xGXCyH4znfuYMuWzUyZchwLFpxJaeke/vGPN3j//S0888yLR901Pdq88sEhan3RHaSDKcGpU9kS4sVNFfzioiN35A6mmIR2WVlZZGV1XTNk7dq1nH766bE4jBRDsdyWODE9jl9efDzvVTSxrKSWnTU+LCsaYE0fl8jiyenMzk86agHAz0px2zvtyBoof9hk474G3J/pTt8XiS6dg01BUOjTTrbPMixBwgDycQYqzqERixjMsgSqqsR8ilyShlMkEuFnP/sxpnlkIdZ161azZctm5s9fxE9+8vOOIsFPPfUYL774HK+++ie+9KUbh3rIg6LBH2ZdaQNxDq3PO0j7SlEUUtw2yhoCbKtsGdLZoD6/E+/du5f6+nomT55MYmL3A62vr+fOO+/kxRdf7PLFJB1b7LrKaYUpnFaYgmEJgm11fGJZzHAgvCGDsClw9tC89mhsWrTBq66ptAQNkvuxrdMSAlMIpg/xlO/h8pNcKAwskINoYHlCTsKw1/mQpFh68cXn2L+/nNmz57B587udrvvkkx0AnH/+hZ26JFx88aW8+OJzbNv28ZCOdTCt3duAN2QMuBZbbzltGg3+CMtK6oY0COr1J8Lq1as54YQTmDRpEnPnziUjI4M777wTq4sid8888wxTpkzhxRdfjOlgpdGho3noCAmAIJqXFK2cPbD7UVWF4vQ4/BHzqLvYutMSNEhw6JwxIXVgAxmA0wpTSHLZaAn2fzdGdEegwtmT0mM3MEkaZnv27Oall57n6quvY8KE4iOuj4+PLudXVVV2ury2thaApKTh+3ITaxv2NaAqR7ZFGkxuu8aWiqYhbYfUq0+pjz76iLPPPpsdO3agqiopKSlEIhF+/etfc/fdd3fcrqysjPnz5/PVr36V+vp60tLSeP755wdt8JLUWy6bhqZE85T6S7QVepyem4hTV/GF+vaHalnRKtxzC1OGrSYGRJPy509IxR/uXyAHdOyQO7VAVoyWjg2mafLTn97PuHG5XHfdV7q8zVlnfQ6PJ54XXniGDRvWEggE2LVrJ7/4xU/QdZ0lS744xKMeHMGISUVTAJdtaL/IumwaQcOiojEwZMfs1SP8v//7PyKRCFdeeSUNDQ3U1taydu1aMjMzeeSRR6ivr2fFihXMmDGDdevWAXDjjTeyc+dOrr322kF9AJLUG4kuG2keO60D+IbhD5u4bBqnjk9m8aR0vCGj199YLCGo8obISXCw5KTh77l11qR04p3RXmB9FYyYhA2Lsyen9ynPS5JGsj/96SVKSnZy993fx27v+ktKenoGjz76NElJKdx11+2cffYZfOUr11BTU8Ovf/0oJ5xw0hCPenBUNAUIRKwh//u2awoR06K80T9kx+xVEPTuu++SmprK008/3TEdeNppp/Hggw9iGAaPP/44F110Ec3NzUyZMoW1a9fy5JNPkpwsvyVKI4OuRos7Gpbo92xQS9DguKx4ClPdfPnUfOZPSKUpEKHRH+n2PoWI5kdFSwg4+NaiCYxLHP7GgYWp7o6aHPWtRy9QebhgxKS+NcKpBcksOSl7MIcoSUOmrKyMZ599miVLLuOkk07u9naBQIBnnnmCfftKmTFjFldeeQ3z5p2Bz+fll7/8OdXVVUM36EFU4wsTNi3sXfSGHEyKoqC0HX+o9CoxuqqqitNPP524uM4dqxcvXowQgvvvvx/DMLjjjjv46U9/2m0ULUnD6YwJqbyy9RAtQaPPvWrChgWKwuLJaSiKgk1TuH1BERnxDt76pIZKbwibGm2WqinR2kYhw6I1bGLXVKZkePjaGYUUpHTf60wIQY0vjDcUbeTqcWhkxPe+qGNfnTUpWqDyxc0VVLaESHLZuq2EHTEtmgPRhrdzC5O5bX5RlzWhJGm0EUJw7733kpycxM03f/2ot/3Nbx5izZqV3HLLN7j66us6Ll+zZiXf+96d/OAH3+Wpp14YxNEOjYhhgWBYiqAKou83Q6VXQVAoFOpyC3xaWhoQXUv93e9+x6233hrb0UlSDKW47SyelM4bH1fijKi9nuo1LUGtL8ykjDhm5386u6lr0WanFxyXyZq99SzdVUtdaxjTEqhtgdLiSemcWZzG8dnxXQYzYcNic0UT60rrKalpxRsyMNpmlTRVId6hMyk9jtMKUzhlfDKOGAYeiqJwwfGZZMY7+OuHh9hT20qjP4LLrmJTVVCieUzRJT+FdI+dsyens+SkbBkASceM1157hS1btvDggw/jdsd1ezvTNHnrrTfJzs7hqqs6p3mcccZC5s6dx4YN6ygrK6WwsGiwhz2o2oOf6GaSoQ+EtCE8Zq+3yHf1RGha9ENk6tSpMgCSRoWrZ+VS6Q2yYV8jSS6I66HGjWFaVHvDjEtycueZE7sMQlLj7Fx8UjYXnpBFQ2u4rcCjSoJT77bLvBCC1Xvr+fP7h6hsCWKJaAVvh67hbtuNYVoCbyjCurIG1u9rJCvewRXTc1hUnBbTN6ZZ+UnMzEtkZ42PFbvr2FTeRNi0EFZ0N9yJOQmcPTmdOeOTZQ6QdMxZuXIZAHfddXuX1992280APPHEc0QiEfLyxnf591dQUMSGDeuorq4a9UFQR8FbAUO8IgYwpLXHYlKxbdq0abG4G0kadHZd5VsLJ/DEumhDwOZAhHiHjsfRuYhiMGLSFDCwhGBiehx3njmB7ATnUe9bVxUyelFTwxs0eHL9PtaXNSAEpMTZsHdTTsDd9mYQMS1qfCF+u7qMTfubuPm0gj4v6R2NoihMzYxnamY8t8wThAwLwxLRXXWyDpB0DDvvvM8zb95p+P2hTpXcN29+l23bPuK88y4kKyub7OwcbDYbFRX7u7yfAweil6emDl/5i1jJTXLi1FWChtXjF8VYMttmwfOSjv5eG0sxCYLaZ4QkaTRw2jS+Mb+IuQUpLNtdy4cHW6hsCXH4R72uqhSlujl7SjpnFKV2O6PTV02BCD97ZzfbK70kuW29foOxaSqZ8Q78YZN1pQ3UtYa55+xiUtyxz79TFEXO+EhjxgUXfJ60tHjq6rydgqBAINARBLX3Dps37wxWrlzOX//6Zy677MqO227evJF169ZQUFDIxImThvohxFxmvIMEp05zIDKkQVDIsHDqGuOPkjsZa8NXu3+AAoEA119/PVdccQWXXHLJcA9HGmU0VWFOQTJzCpI50BTg/QPN+EIGphXtfTYhLY4TcxJimpQcMS1+tWIv2yu9ZMTbsfWjmKTbrmHTFHZV+3hw2R5+eN4UnENcy0OSxqrbbvs2O3Zs5+GHH2Lt2tVMmjSFgwcrWLNmFU6ni3vv/eGw5NDEmqIoHJcVz4rddUN6XF/IICvBSeYQVamGPgRBGzZs4Mtf/nKfr1MUhWeffbZ/o+vG7t27ufvuu9m+fTtXXHFFTO9bGntyk1zkJg3+tvV/bqviw4PNpHn6FwC1s2kq6R4726u8/O2jSq6cOS6Go5QkqTsZGZk888yLPP/8M6xbt5qtW7eQkJDIWWd9ji996Uby84+d5uHzJ6SyZm89IcOK6YaM7lhCYFiCxZPSBm1HbFcU0YsCIYf3SOnzARQlpr3DNmzYwLe//W1uueUWnnvuOb7xjW/0aybos1OfUtcUhS6niqW+Odgc4Dt/30HYtGJWLbrRH0FR4OdfOI5ZkzLlORqh5N/QyCbPT9cMS/Dtv22jvCFA1iB3kQdoDkRQFIXfXHIC6Z5Pj3f4+YHo/8dSr2aC7rvvvpge9GiCwSDV1dVdXpeens6UKVNYsWIFDodDtuSQRo0Vu+tpCRrkJMbuzSTJpXOoOcTykjpmTcqM2f1KkiTpqsLnj8/i0TVlBCLRavmDxWhrKXThCZmdAqChMOKCoA8//LDbVhuPPvooixcvjslxjoFl2yHR/jzJ56v/ghGT5bvrcHZTiLC/FEXBZVdZtaeOW0OGPEcjlPwbGtnk+eneWZPTeLe8kY37GslOVAdtmarWFyI/xcXVM3OPOA+DfX5GXGL0nDlz2LVr16AfJzU1tlNqxzr5fPXftoPN+MImyXF2bDH+NpUc56C+NUxJtZcZhxVylEYe+Tc0ssnz07W7LjiOr/3hfepbQ2QnOmOe+F3vC+N22Ljjc1MozO3+PWywzs+IC4KGSn29XP/tDUWJvvjk89V/H5bVEQwbKE6NSCR2+XEACEE4YlJW28r4OF2eoxFI/g2NbPL8HJ0DuPW0fB5avpcDDQEy4+0xC4Qa/REMU3DtKbkUJ9o78n4Od/j5gdgHQ2M2CBIC+YLvA/l89V+tN4yiDE4fnvb7rGoJIkSiPEcjmPwbGtnk+ene9Nwkbl9YxCOryzjUHOp3iY927a2IdFXh6lnj+MIJWT0+94N1bmSBEUkaZGY/u9aPtGNIkjR2zc5P5vufm8SkjDhqfWEa/RGsPkYmQgh8IYOqlhDpHju3Lyzikmk5w1pbaVTPBC1fvny4hyBJPbLpKojB+yNXQDY0lSRp0E3O8PDABVN5/aNK/rW9msqWEHZNIcFpw64pXQYzoq3+jzdkEAhbuGwai4rTuH5O3qBUvO+rUR0ESdJokJPgQCAGpSOzEAIB5CYPfrFHSZIkp03jqpm5nDUpndV761m2q5ba1jAR0wJAVRQUJbp81T5TpKkKCQ6dc6dksGBiGkWp7hFTWVsGQZI0yPKT3di1aDPCWNfaCJsCm6ZSmBYX0/uVJEk6msx4B188OYeLTsiitL6V/Y0B9jX4qfGFiRgWuqaQ5LIzPsXF+GQXE9LiYtaDMZZ6NSLLsgZ0kIFUnJak0S4v2UV2opMDTYGYB0EtwQgZHgcTMzx4m/wxvW9JkgaXaQkqW4KUNwYob/BTVu+nMRAhbFhETAtdVbHrKolOnaK0OPKTXeQnu8hNdKIPIDE5luy6ypTMeKZkjs4SA70Kgmw2W78PoCgKhmH0+/clabTTVYWzJ6fzzIZyTEugqbGZBrYsQdgQLJ6cjkPXOHJzqSRJI03YsNi8v4k1pfXsqvHhCxmEjOhEg6JE3y8URaH9XcISYFoW71U0AeDQVdw2jYnpccwrSuXU8cm4h7DT+7GmV0FQT+3F7HY7ubm56LpOZWUlXm/07TgzMxOPxzPwUUrSKDd/Qir/2lZFjS8csz48da1h0j12FhanxeT+JEkaPFUtQVbvbeCdklpqvCEsIXDZNFw2jWSXDbUXX44sIQgZFqGIxXv7m3hvfxMvx9k5c1I6CyakkidzA/usX8thDQ0NzJ8/n9bWVh5++GEuuOACdP3Tu1q9ejW33norwWCQVatWxXbEkjQKJbls/O/sPH69shRfyBjw2nhryEAA18zOIy1GDVn/f3v3HR5VmbYB/D7TS0I6IQkklNBbgCBEpUcUREHFCoKCLiv2grru6vrtiuiqu6srVooNcUVhxbIg0kEhKEVqIJBKSC+kTTvzfn+EZIkJkEzOlGTu33VxXeScM3OemSdn8sx73kJEysuvsGLlLznYlVmKKpsMnVqFMLPWpXl2VJJUXzgFQwuH7ES5xYF/7zuNrw/lISEmCDMSOyOWxVCzufRJ/Ic//AEZGRk4dOgQunbt2mj/6NGj8cMPP6B37954/PHHsXLlytbGSdTmXdk9FAfPnMW6owWQJMCsc60QqrbJKLc4MKFXBMbFhykcJREpQQiBTSeKsOLnHBRU2tDBoEZ0B72io6I0ahXCzDoIIVBlk/FjRgmO5FXg5iHRmNwvEhqFbr23Zy59Cq9Zswbjx49vsgCq06lTJ4wfPx7r1693NTaidkWSJNybFAe7LLD5RBEsdidCTdpmfygKIVBaY4fV7sToHmH4/RVdfWaYKRH9T36FFct3Z2F3RikkCYgO0rtt8VGg9rMlQK+BWadGcbUdS3dl4uesMtyTFMdWoUtwqQiyWq3N6uxc1zeIiGpp1SrcP6obuoQY8eX+XOSWW9HBoEGAXn3BgqZ2llUZZy0OBOo1uHl4DKYN7NSqaeuJyD12Z5Ti3R8zUFBpQ6hJ69FOy5IkIdysg8UuY19OOf74zVHMvqwLkntHeCyGtsalImjAgAHYvHkzDh8+jP79+zd5zM6dO7F161aMGzeuVQEStTcalYQbB0VhaEwQPt9/GntzynHmrBVA7ciPuiZs2SlgOTdqxKhVI6lbCG4ZEoN4zglE5JM2nSjCez9mwGKX3d76czEGrRrRQSoUVdnwzs4MVFodmDqwE1uOm+BSEfTII4/g1ltvxdixY/Hcc89h0qRJ6Ny5MwAgIyMDa9aswaJFiyCEwNNPP61owETtRdcwE56c0BO55RbsyizFqaIqpBZUovrcSvMBeg0SI8zoEW7GiLgQdA5mszaRr9qQWoj3f8yELJyIDFS2748rJElCRIAeJdU2fLQnG3anwPTBUV6Py9dI4lLj3y/gueeew8KFC5vcJ4SATqfD66+/jnnz5rUqQHcpKqrgisHNIElAeHgg3y8Pkp21S2E0t1Mjc+TbmB/fpkR+tp8sxpvb0yE7BcLMze/n5yllNXbYZYE5I2Jxbf9Ib4fTIufnB6j9v5Jc7lTwl7/8Bbt378bdd9+NHj16wGg0wmQyoVevXrj//vuxf/9+ny2AiHyZWiVxVAdRG3EkrwJv78yAXXb6ZAEE1E7RoZKAD1OysSujxNvh+JRWTVaSmJiIJUuWKBULERFRm1Fjl/H+T5motDoQpfDwd6WFmrTIr7Bi2a4s9O4YgBAfWMHdF7R6eIndbkdKSgq+/PJL7Ny5EwCQlZXV6sCIiIh82ap9uThZVIWIAJ1PF0DA//oInTlrxUd7ci65EoS/cLkIcjgceO655xAZGYmkpCTccsstePfddwEAs2bNQmJiItLS0hQLlIiIyFccPnMW3x7Jh0mnbjPTVahVEoKMGmw7WYwfM0q9HY5PcClzDocDU6ZMwcKFC1FdXY3ExMQGVWVFRQX27t2L0aNHIz8/X7FgiYiIvM1il7FkVxZq7DKCDK1bAsfTAvQayE4nPtydhbJqu7fD8TqXiqDFixfj+++/x8SJE5Geno7du3c32L9jxw7MmjULeXl5ePXVVxUJlIiIyBdsP1WCU23kNlhT6m6LbThe6O1QvM6lIuiDDz5AWFgYVq1ahaioqEb7jUYj3n//fURHR+O7775rdZBERES+QAiBDccKAAlt5jbYb6lVEnQaCRuPF8LmcF76Ae2YSxk8fvw4Ro0ahYCAgAseo9VqcdlllyEzM9Pl4IiIiHzJkfxKnCyuRrBR6+1QWiXIqEXeWSv2ZJd5OxSvcqkI0mq1KCsru+RxxcXF0Grb9i8KERFRnc0nimCTnTBo2mYrUB2dWgUhBDam+vctMZeymJCQgJSUlIu28pw6dQp79uzB4MGDXQ6OiIjIV5RU2/BTegnMugsveNyWBBo0OHSmAhnF1d4OxWtcKoLuu+8+VFdXY+rUqdi3b1+j/QcPHsRNN90Eq9WKe+65p9VBEhERedvhMxWosDrQQd+2RoRdiFmnhsUh4+CZs94OxWtcyuStt96KH374AUuXLkViYiKCgoIgSRLWrVuH2NhYnD59GkII3HbbbZg5c6bSMRMREXlcZmkNAEDVTpa1qWvNyiip8XIk3uPyTc33338fS5YsQa9evVBWVgYhBIqKipCTk4MuXbrgH//4B1asWKFkrERERF5zsrAK7aT+qadTq3C8sNLbYXhNq9r05syZgzlz5iAvLw/Z2dmQZRlRUVGIi4tTKj66BJvDiVPFVcgqrUFOmQUWhwwJQKBBi9gQI7qGmtAl2NAu7l8TEXmLwylwqqQKeo3a26EoSq9VoajShrIae5sf8eYKRW5sdurUCZ06dWq0fefOnTh58iRmzZqlxGnoPEVVNmxNK8KG1EIUVthgd9bO9VA3cbdKAgQAg0aN+AgzJvaOQFK3UOjb+IgGIiJvyC23oNomw6RrX0WQQaNCSbUdWaU1LIKaS61Wo3///vjqq6/QrVu3Cx73zjvv4NNPP2URpCCnENh0vAgrfslBUaUNOo2EDkYtdGqpUWuPUwjU2GUcPnMWh/Mq8O2RfNybFIdeHS88v5OnOZwCx/IrkFFSjYySGpwsqkK1TYYQAlq1Cp2DjegRbkJsiBF9IwMR5IcXKRF5X95ZC2wOJ0La2WeQRiVBdgrknbVgUHQHb4fjcS4VQUIIHDp0CMOHD8dnn32G5ORkpeOiJtTYZby5LR0/ppdAkoCoID1UF7nNpZIkmHUamHUa2BxOpBZU4rn/HsOMYZ0xpX+kV2+RlVTbsP1kMTakFiK33ArHuZYsrVqCWpIAqbZVK6esBrsySgAAHYxajOoeirHx4egZYeYtPiLyGJvshFMA7e1jR5IkSBJgl/1zVXmXb4d17doVubm5mDRpEl5++WU89thjSsZFv2Gxy3h1UxpSMssQYtK2uElWp1EhqoMeJdV2LN+dDbtT4MZBjZc8cTeHU+C7I/n4Yn8uymrs0KgkBF2gJet8slPgrMWBrw/lY0NqIZK6hmL2ZV0QZtZ5MHoi8lc2WUCS0E6/fEmwyf65fIbLHUSuvPJKbNiwAUFBQViwYAFmzZoFq9WqZGx0jhACy3ZnYU9WGcLMLS+A6kiShDCzDlq1hJW/5ODH9BKFI7247NIa/GVdKpbuykS1TUanQD06Buqh16gu+cGiVkkIMWkRHVR7/OYTRXj66yPYfrIYQvjnNxgiIqX46+doq3rJjho1CikpKejTpw9WrFiBUaNGIScnp35/+6yYPW9PVhk2HS9CoEEDg7b1nfJCTFrYZYEPU7JRVm1XIMJLO5pfgT+vS8W+nHKEGLUID9C5NNeGJEkI0GvQqYMeRZU2vL71FFbtz/XbC5iIPEOrkiBEOy0WzvXB9EetftXdu3fHrl27MHHiRPz8888YPnw4du7cCQBcN0wBNocTH6TU3r4KVHCW0ogAHXLLLVh1IFex57yQ1PxKvPxDGoorrYgK0itSyKlVEiI76KFRS/hs72kWQkTkVlp1bd+Z9vopo2MR5LrAwEB8++23ePDBB5Gfn48JEyZgyZIlMJlMSjy9X9uTXYbccgvCzcoWlGqVBJNOjW0ni1Fe477WoKJKK17bnIaSahs6dbh4R25XBBu10GlU+Pe+XGw7WazocxMR1YkI0EOnVsHmaF99ZxyyE5IkITzAP/tXKlb6qVQqvP7663j77bfhdDoxb948rF69Wqmn91ubjhfWDxdXWgeDBuU1dux0U98gIQQ+SMnGmbNWdArUu+32aLBRCyEEPkzJQVEl+6URkfK6BBth0KphaWdFkMXhhEGrQlyI0duheIXif1nnzZuHdevWITg4GGfOnFH66f2KxS4jtaDSbZNzqc/1yTmW754p07edLMbO9BIEm7RuX2sn3KxDYaUVy3Zn8bYYESlOp1EhLtQIazsrgqwOJ4KNWr8daetSEbR8+XL87ne/u+D+8ePHY9euXUhMTERsbKzLwfm77LIa1NidivShuRC9RoXjBZWKFw4O2Xmun07tSsXuplJJCDZpkJJZhsN5FW4/HxH5n57hZsjO9vUly+pwonfHAL8dyORST9vZs2df8piePXsiJSXFlaenc/IrrLDJTujU7vvl1GlUKLc4UGmVEWhQruP13pxynC6zINTkuc7xJq0a5TUObEkrxoAo/5v5lIjcKza0tp+rEKJdFA11X367hvpv/91m/dXbtGkTAODyyy+HwWCo/7m5xo8f3/LIqHZyLrh3qgEVAFmI+rXHlLLxeBFkIaDz4FplklTb2fun9BLcPjTGb5t3icg9+kYGwKRTK/6l0Vtq7E7o1Cr0jfSdpZQ8rVlZTE5OhiRJOHr0KHr16lX/c3PJsuxygP5Mc968FO4qhAQASKhdqkIhlVYHDp45iwC95xca7GDQIO+sFYfOnMWY+HCPn5+I2q+oDgYM7RyEHadK2kURVG5xoG9kAHr70HqSntasLI4ePbr2W/a5Ie91P5N7hZt10KpVsMsCOo173m+b7ESgXqvoBZ1VWgOLXfbKisR1Q/AzS2o8fm4iav8m9IrATxmlsDqc0HuwpVtpDtkJCIGrekf49d/zZv3l27Jly0V/JveIDTHCoFXB4nC67baS1e7E0M5mRefvySythsMpoHVjX6aLUUkSThRVeeXcRNS+DY4JQudgI3LKahAZqPd2OC4rtzgQZtZhZNcQb4fiVS79Zd22bRtSU1Mvedzu3buxZMkSV05xQTk5OXjggQcwcuRIjBgxAvPnz0d2drai5/AVAXoNuoYaUWVzz+1EpxAQgOJNoQUVNrf3ZboYvUaF02VsCSIi5WlUEq7qHQHZKdrsSDGnELDYnRgbHw6zru3f1msNl4qgsWPH4sUXX7zkca+++ioef/xxV05xQffffz+CgoKwadMmbNq0CcHBwZg/f76i5/Al43tGAELA4YaLrcLigFmnwRXdQhV9XpvshDdn0pCk2hg4XxARucOYHmGI6mBAYaXN26G4pLjKjhCTFlf1ifB2KF7XrBJw8+bNjf6gnDlz5qKjxMrLy7Fz505F/xCVl5cjPDwcDz/8cH3/pFmzZmHq1KkoLy9HUFCQYufyFUndQrByrx4lVTZ0VLDp1SkEKq0yJvQKV/R5AdS2Ain6jK7E4O0IiKi9CjJqcdeILnh100lUWh0IUHBdR3erscuQnQK3D4tBVAeDt8PxumZlbtmyZfj000/rf5YkCRs3bsTGjRsv+jghBKZOndqigCwWC/Lz85vcFxERgaVLlzbYtn79esTExLS4AGor/cAC9BrcMSwGb25LR7VNVmz26OIqG0LNWtw2NOai70Xdvpa8X0at2qsliFMIGLQqt89S7StcyRF5DvPj21zNT1LXEIyND8P3xwph1KrrZ+D3ZU4hUFJlx2Vxwbi6T8c28Tvp7uunWUXQ3/72N5w+fbq+VWfr1q3o2LEj+vbt2+TxkiTBYDCgZ8+eePbZZ1sU0IEDBzBr1qwm9y1evBjJycn1P69cuRLLli3D22+/3aJzAEBYWGCLH+Mtt4QG4GBBFTanFsBk0LR6HbGzNXZIkgrzxsZjYI/mNYe25P3q0yUYqgNnoNGovNIvyO4E+sYEITy87eRYCW3pd9ofMT++zZX8PHJNX6QWVeNMeQ2ig31/7a38sxZ0DDJgweR+iGxjEyS66/ppVhEUFRXV4NaXSqXCxIkT8dFHHyke0IgRIy7Z6dpms2HRokX47rvv8O6772LkyJEtPk9xcQXaUpeRu4fFIKe4CsfyK9ExQOfyaLGzFgeqbDKu7dcRSTGBKCq6+BITklT7y9eS9ytYLUEtAZU1drcu+XEhTtmJmADdJV9be+FKjshzmB/f1tr83DksGq9uOomCcgtCPDhDfkudtTjgcDhx86BOMDrlNvP5eH5+AOWLIZduZKanpyMgwDuTK5WUlOC+++6DzWbDF198gS5durj0PLWTECocnBsFGbV45qqeeGVjGg7nVcCoVSPYqGl2S4vsFCistEKtUmHqgEjMuiwWEqRmvwcteb86Bxth1Krdvu5ZUxxybZfsuBBjm8qvEtra77S/YX58m6v5GREXihnDrPhoTzbKa+wI8sL8aJdSaXWgyirjhkGdcHWfjm3y99BdMbvUnBAXF4ewsLAG25xO5wX/KcVut+Oee+5BQEAAVq5c6XIB1FaFmnT48zW96/vx5JZbUVZjh/MiI8fsshOFlVbkVVgRGWjAY+N64O4RsdC48f61XqNCUrcQVNtkj4/Qqpv7YlB0++skT0S+aerATpieEA2Lw4myGru3w2mgwuJAhcWBq/tG4M7hXfx6YsSmuNylffXq1XjppZdw6NAhWK3WCx4nSRIcDoerp2lg8+bNOHz4MPR6PZKSkhrs+/bbbxEdHa3IeXyZQavGHcM647LYEKxPLcCPp0qQV1H7/quk/82YXDekXi1J6BioR3LvCFzVKwLBHmquHdczHJuOF6HG7lSsM/eliHNzX1w/INxj5yQikiQJtw+NgUYl4d/7cmsHnpi0Xi04hBAotzhgsTsxZUAn3D0itk103vY0l4qgb775BjfffHOzvuUr2RIwceLEZk3S6A/iI8yIj+iG24fG4PCZCmSW1iC9uArVNhmSJCHUpEX3MBPiQk0YGNXBowuZAkCfjgHoGWHGobwKGLWe6SBdbnHArFdzzTAi8jhJknBzQjTMOg0+/jkbZ85aER6gg66VA1lc4ZCdKKi0Qa9R4ZYh0bhtaIyiqwK0Jy4VQX/7298ghMBjjz2Ghx9+GNHR0VCr+c3bG0JNOozqEYZR3g7kNyRJwp3Du+D/1qWi3OJw+zpidtmJapuMmwZHITbE90dpEFH7I0kSru0fifgIM5b8lInUgsoW999sDSEEKqwOVFhkdA01Ye7IWCR0ZteAi3GpRN23bx8SEhLw6quvokuXLiyAqEn9OgViSv9IVNtk2GT3zSEthEBhpQ09ws24ZUiM285DRNQcvTsG4K+T++COc/03z5y1osbu3j6SVocTZ85aYZcFrh/YCYuu68sCqBlcagnSaDTo1q2b0rFQO3RzQjQOnanAkbwKRAbqoFG4aVgIgYIKGwL1GtybFAejF4bkExH9lkGrxm3DOmNIl2As352FE4VVKK2yw6xXI9CgUeT2VG3Lj4xKqwMalYTuYWbcdVkXFj8t4FIRNHLkSPzyyy+QZZmtQHRRBq0aCybE44X1x3GyqAodA3WtnuyxjhAC+RU2mLRqPDC6G/p14mR0RORbencMwKIpfXE4rwKbTxRhV0Yp8s5aoVFJMOnUMGhULfpyKDsFLHYZ1XYnbA4nzHo1RnUPw/he4RgcE+TWkb/tkSRcaJ9LSUnBlVdeifvvvx+vvvpqmyyEioo4cVlzSBIQHh7Y6verqNKKlzem4VhBJQJ0anQwtO4eudXhRFGlDSEmLR4Y1Q2XxYW4Hlwbp1SOyD2YH9/m6fwUVVqx/VQJNh0vRGGVDRa7E85zJ9ZpVNCoJKik2vUPBQSEqB3ta3U4z8UrwaBRIcSkxbj4cIyOD2vXa4Cdnx8Aiq8E4FIR9MYbb+CHH37At99+i4iICCQmJiIkJKTJP2qSJOHDDz9UJFgl8QOpeZT8gKiyObBqXy6+O1oAi11GqEnb4skUHU6Bsmo77E6BgVGBuCcpDl3b2PTvSuMfWd/G/Pg2b+VHCIGSajuySmuQWVKNjJJqHC+swlmLvXbiRpxbjFoCzDoNekaY0T3MhNgQE2JDjIgI0PnFnD8+WQSpVLVDnpvzUEmSIMuyS8G5Ez+QmscdHxAHc8/iw5RspBdXwyY7EaBXw6hVQ6uWmryo65p/z1plQAiEmnWYOqATpvSPVLyPUVvEP7K+jfnxbb6WHyEEHM7af2pJuuDnor9wdxHkUp+g5cuXKxoE+ZeB0R3wt6n9cDD3LDafKEJKVhnKauxwOGubfiHVfgMSODd88Vzzb5+OAbiqdwSSuoXArHN5nk8iIp8lnSt8OMbDM1z6SzJ79myl4yA/o5IkDI4JwuCYIFRYHMgqrUZmaQ1Ol1lgcchwOAUMGhXCA/SICzEiLtSEjn7S/EtERJ6hyNfpgoICZGdnIzAwEL169UJ1dTVMJv/up0HNF2jQoH9UB/SP6uDtUIiIyI+0qkPFsmXL0K9fP0RFReGyyy7DwoULAQDTpk3D9OnTUVhYqEiQREREREpzuSVozpw5+PDDDyGEQMeOHVFQUFDfUTo7Oxupqak4cuQIdu3ahQ4d+A2fiIiIfItLLUEfffQRPvjgAyQkJODnn39GXl5eg/0bN25EcnIyUlNT8cYbbygSKBEREZGSXCqC3nnnHQQGBmLdunUYOnRoo/3R0dFYs2YNQkJC8MUXX7Q6SCIiIiKluVQEHTx4EGPGjEFERMQFjzGbzbjiiiuQnp7ucnBERERE7uJSESRJEmw22yWPq6qqcuuquURERESucqkI6tu3L3bv3o3i4uILHlNYWIg9e/agX79+LgdHRERE5C4uFUF33303ysvLceuttzbqFA0A+fn5uP3221FZWYmZM2e2OkgiIiIipbk0RP53v/sd1q5di3Xr1qFbt27o06cPJEnC9u3bMXr0aOzfvx+VlZUYM2YMfv/73ysdMxEREVGrudQSpFKpsHbtWvzpT3+CwWDAgQMHIIRAZmYmduzYAVmW8fDDD+O///0vNBqu8URERES+x6VV5M9nt9vxyy+/IDs7G7IsIyoqCsOHD/f5ZTN8ZcVgX+drKyxTY8yRb2N+fBvz49t8chX582m1WowcORIjR45UIh4iIiIij2hWEXTq1KlWnaR79+6tejwRERGR0ppVBMXHx0OSJJdOIEkSHA6HS48lIiIicpdmFUGxsbGNiqCzZ8+itLQUANCtWzd069YNGo0Gubm5OHLkCJxOJ3r37o3OnTsrHzURERFRKzWrCMrIyGjwc1ZWFpKSkjBkyBAsW7YMgwcPbrA/PT0dd999Nw4dOoTVq1crFiwRERGRUlwaIv/kk0+ipqYG33//faMCCKhtGfr666+hVqvxxBNPtDpIIiIiIqW5VAStX78e48aNQ1hY2AWPCQwMxOjRo7Fjxw6XgyMiIiJyF5cXUC0rK7vkcWfOnIFer3flFERERERu5VIRNGzYMGzbtg1bt2694DGrV6/Gjz/+iCuvvNLl4IiIiIjcxaXJEp9++mls3rwZkyZNwn333YdJkybVjwLLyMjAmjVrsGzZMhgMBvzpT39SNGAiIiIiJbi8bMaSJUvw8MMPo6amptHweSEEQkNDsXz5clx33XWKBKo0TpHePJxS3vcxR76N+fFtzI9v89llM+655x5cc801+OCDD7Bt2zbk5uZCkiR07twZycnJmD17NsLDw5WMlYiIiEgxrVo7rHPnzrzdRURERG2SSx2jiYiIiNo6l1qCxo8f3+xjJUnCxo0bXTkNERERkdu4VARt2bLlksdIkgQhhMsLrxIRERG5k0tF0ObNm5vcLssySkpKsHPnTrz33nu49dZb8cYbb7QqQCIiIiJ3cKkIGjNmzEX3T58+HdOmTcP48eORlJSEe++916XgiIiIiNzFbR2jx4wZg6SkJLz55pvuOgURERGRy9w6OiwyMhInTpxw5ymIiIiIXOK2Iqi8vBzbt29HcHCwu05BRERE5DKX+gQtW7bsgvtkWUZBQQE+/PBDFBcX4+6773Y5uKYcPXoUixYtwuHDh6HRaDB69Gg888wzCAkJUfQ8RERE1L65tHaYSqW65NB3IQRiY2Px008/ISoqyuUAz2ez2TB+/HjcfvvtmDdvHqqrq/HQQw8hMjISL7/8couei+vENA/X1fF9zJFvY358G/Pj23xy7bBZs2ZdsAhSqVQICAjA4MGDceutt8JsNrcqwPPpdDp8//33MBgMUKlUKC8vR01NDUJDQxU7BxEREfkHl4qgDz74QOEw/sdisSA/P7/JfRERETCZTACA2267Dfv27UN8fDzmzp3b4vNwDsfmqXuf+H75LubItzE/vo358W3uzo9Lt8P+8pe/YNCgQZg2bdpFj1u6dCl27tx50T5Ev7V7927MmjWryX2LFy9GcnIygNpiyWq14vnnn0daWhr+85//QK1WN/s8RERE5N9c7hM0c+ZMfPTRRxc97sYbb8S6detQXV3tcoCXUlxcjMsvvxxr1qxBv379WvA43v9tDkkCwsIC+X75MObItzE/vo358W3n5weo/b+SmnU77KWXXmpUyBw4cADPPffcBR9TXl6OdevWITBQuYBzcnIwa9YsfPbZZ+jYsSOA2s7SABAUFNSi5xIC/IVvAb5fvo858m3Mj29jfnybu3LTrCLIbrfjhRdeaLAo6qFDh3Dw4MFLPnb+/PmtDrJOTEwMgoODsWjRIrzwwguwWq34v//7P4wePRoxMTGKnYeIiIjav2YVQU8++SQAwOl0QghR3yfohhtuaPJ4SZJgMBjQs2fPS/YbaglJkvDWW29h4cKFGD9+PHQ6HZKTk/HYY48pdg4iIiLyDy71CeratStuuukmvPbaa+6IySM4J0TzcA4N38cc+Tbmx7cxP77NJ+cJysjIUDQIIiIiIk9zqQiqqamB0WhssO3o0aP49NNPUVxcjIEDB2LWrFmKTpRIREREpKRmL6Bqt9uxYMECBAUF4Yknnmiw77333sOgQYPw4osv4p133sEDDzyAnj17Yt++fYoHTERERKSEZrcETZ06FevXr4cQAlartX774cOH8cADD0CWZSQlJWHGjBk4duwY3n33XUyZMgVHjx5Fhw4d3BI8ERERkauaVQStWrUK69atQ79+/fDxxx9jyJAh9fsWLlwIh8OBAQMGYMuWLdBqtQCAgQMHYt68eXjzzTfxzDPPuCd6IiIiIhc163bYypUrodFo8J///KdBAeRwOPDNN99AkiQ88sgj9QUQANxzzz2IjIzEV199pXzURERERK3UrCJoz549GDp0KOLj4xts3717NyorKwEAkyZNarBPkiQkJiYiLS1NoVCJiIiIlNOsIqioqAixsbGNtm/btg0AEB8fj6ioqEb7TSaTW9cNIyIiInJVs4ogg8EAu93eaPvWrVshSRLGjh3b5ONOnz6NkJCQVgVIRERE5A7NKoJ69OiBX3/9tcG2iooKbN26FQAwceLERo8pLS3Fnj170LNnTwXCpLbizTf/iSuvTMTevT832F5dXY233/4Xpk+/DuPHX4E77rgJH3+8vMFIQyIiIk9qVhE0adIkZGRk4N13363f9s9//hNWqxUBAQGN+gMBwDPPPAOHw9FkgUTt05Ejh7Bq1cpG261WCx566PdYseJDGI1GTJt2Izp3jsW77y7G448/CKvV4oVoiYjI3zVriPwjjzyCxYsXY/78+fj000+hVqvrb4U99dRTMJlMAABZlrFv3z68/vrrWLFiBUJCQnDfffe59QWQb7Db7Xjppb9CluVG+z755EMcO3YEY8aMw/PPv1g/inDNmi/w2msv4ZNPPsTcufM8HTIREfm5ZrUEhYWF4fvvv0dsbCy2b9+OLVu2QAiBu+++G08//XT9cVu3bsWIESOwYsUKGI1GrFy5EqGhoW4LnnzHRx8tQ1ZWJoYPH9Fo38aN30OSJDz66FMNplGYNu0mdOkSiy+//BwOh8OT4RIRETV/xui64e47duxAQUEBBg0ahN69ezc4JioqCvHx8bjiiivw1FNPNdpP7VNa2gl8/PFyzJgxG1arFXv27G6w/8yZXERGdkJ4eHiD7ZIkoUePeGzZsgmZmRno0aPhFAxERETu1KIFVNVqNcaMGXPB/X379kVqamqrg6K2Q5ZlLFr0F8TEdMbs2XPx3ntvNTpGq9XBZrM1+fi6eaby8s6wCCIiIo9q9gKqRE1ZufJjHD9+DE899SfodLomj+nTpy9KSorx66/7G2wvKSnGkSOHAQBVVZXuDpWIiKgBFkHksqysTCxb9j5uuGE6Bg1KuOBxt946AwDw/PN/xE8/7UB1dRWOHz+GP/zhCQjhBAAIITwRMhERUT0WQeQSIQReeumvCA4Oxu9//8BFj73iilGYP/9hFBcXYcGCRzBx4hjMmTMTJpMJt902E0DthJxERESe1KI+QUR1Vq/+HL/+uh+vvPJPmEzmSx5/xx13YsyYcdi1ayesViv69u2PIUOGYfHi1wEAISEcRUhERJ7FIohcsnnzRgDAggWPNLn/oYd+DwBYtWotoqKiAQAxMZ1x0023Njju2LEjkCQJXbt2c1+wRERETWARRC6ZPPk6DBkyrNH2PXt249ChXzFp0hR06hSFgIBAvPXW61i79j9YuXJ1g7XkSkqKcfDgAfTp0xcdOgR5MnwiIiIWQeSayZOva3J7TU1NfRE0dGgiAKBbtx6orKzAV199ibvuugcA4HA4sGjRX+BwODBz5l2eCpuIiKgeiyByu6uuugarV6/C0qXv4sSJVMTEdEFKyi6kpR3HlClTMXr0OG+HSEREfohFELmdRqPB3//+JpYseRs7d25HSsoudOkSi6ee+hOuvfZ6SJLk7RCJiMgPScJPJ2gpKqqAf77ylpEkIDw8kO+XD2OOfBvz49uYH992fn6A2v8rifMEERERkV9iEURERER+iUUQERER+SUWQUREROSXWAQRERGRX2IRRERERH6JRRARERH5JRZBRERE5JdYBBEREZFfYhFEREREfolFEBEREfklLqBK7Z4QArIA7LITdtkJIQCtWgWdWoJaJXEBVyIiP8UiiNoVpxDIr7Aiq6QGmaXVOFVcjbSiKtTYZAjUFkQCgEqSIAHQa1ToFmZCj3Az4kJMiA0xIirIAI2KhRERUXvHIojavBq7jF0ZpUjJLMXxwipUWB2w2muLHgmAXquCRiVBggTVueJGCEBAoMom4+fsMuzJKgNQWxSZdRr0CDchMTYYV3QLRQeD1muvjYiI3IdFELVZOWU12JpWjE0nilBUaYUAYNCqYNCoEWTQQN3s1pzaIsfpFLA6nKixy/g5q7YwWvnLaYzuEYaxPcPRI8zEW2dERO0IiyBqU2SnwC/ZZdh4vAj7T5ej2i5Dr1EhIkAHjbp1/fxVKglGnRpGnRqAFrJT4KzFga8O5mH9sQL0jQxEcu8IjIwLgU7DMQVERG1dmy6CFixYgLy8PHz88cfeDoU8ILfcgqW7MrE3pxyyUyBQr0F0B73bWmfUKgkhJi2CjRpU22UcOF2OA7nl6BsZiHtGxiE+wuyW8xIRkWe02a+zX3zxBb755htvh0EeIDsF/ns0H09/fQQpmWXoYNAgOsiAQIPGI7enJEmCWadBVJABYSYdDp+pwHPfHcPn+3Jhczjdfn4iInKPNtkSlJaWhrfeegs333wz0tPTvR0OuVFd688v2eVQq4CoID1UXuyXo9OoEB2kR2mNHZ/8nI29OWVsFSIiaqN8rgiyWCzIz89vcl9ERARUKhUeffRR/PnPf8avv/7qchHE/q3NU/c+efr9EkJg4/EifJSSjZJqO0LNWhi1as8GcQGSJCHUpIPN4axtFfrvMdw0OAo3Do7ySoHmrRxR8zA/vo358W3uzo/PFUEHDhzArFmzmty3ePFibNq0CVdccQXGjBmDX3/91eXzhIUFuvxYf+TJ90sIgRW7s7Dspyw4hUBsuMmrrT8XotWqYTJoUFxlw6d7c2EREh4YH9/qDtqu4u+0b2N+fBvz49vclR+fK4JGjBiB1NTUJvetXbsWx44dw2effdbq8xQXV0CIVj9NuydJtb98nnq/nELgkz05WP3rGejUKoSZtJAdTsjuP7XLgvQaVMCBz/dkobi8Bvdd2dWjo8c8nSNqGebHtzE/vu38/ADKF0M+VwRdzFdffYX09HRcfvnlAACr1QpZlpGYmIi1a9ciOjq62c8lBPgL3wKeeL+EEFjxcw6+PHAGRq0KQca2M0lhoF4DlQT8cLwQAsD9o7p5fNZp/k77NubHtzE/vs1duWlTRdDSpUsb/Pyvf/0LKSkpHCLfTqw5mIcvf217BVAds672ctp0vBAmrRpzk2J98jYeERHVarND5Kl92ZpWjE9/zoFO3TYLoDpmnQYBeg2+PZKP//x6xtvhEBHRRbSplqDfevDBB70dAimgsNKKD1Oy4RQC4Sadt8NptUCDBnanE18cOINBMUGID+fweSIiX8SWIPIqIQSW7cpCYaUV4ea2XwDVCTFqUWl1YMlPmZxQkYjIR7EIIq/aklaMXZmlCDFp61d4bw8kSUK4WYcjeRX46lCet8MhIqImsAgirymstOLjPTmQAJh0vjERopJ0GhUMWhXW/HoGaUVV3g6HiIh+g0UQeYUQAst3t7/bYL/F22JERL6LRRB5xbGCSqRkliHYqGlXt8F+S5IkhJl1OJZfiZSsUm+HQ0RE52ERRF6x+UQRrLKzXd4G+y29RgUhBDakFkJwNjYiIp/BIog8rrTahp2nSmDWqSH5yWSCHQwaHM2rRHpJtbdDISKic1gEkcdtP1WCCqsDHfRtepqqFjHp1Kixy9iaVuztUIiI6BwWQeRRDmftbSG1SmrXfYF+S5IkGHUqbDlRhEqrw9vhEBERWASRhx04XY6cshoEt+GlMVwVZNCitMaOnadKvB0KERGBRRB52P7T5XDIAnqN//3qqVUSJAA/Z5d5OxQiIgKLIPKw1IJKaNX+cxvstwxaNU4WVUF2cpQYEZG3sQgij7HYZZwus/hlK1AdvUaFSquMvAqLt0MhIvJ7/vvXiDwuq7QGFocTBm37nxvoQgwaFSwOGVmlNd4OhYjI77EIIo/JKq2BXXZC58e3w+pGxGWWsAgiIvI2FkHkMZmltRMF+ssEiRciATjJBVWJiLyORRB5zMmiaqj9aG6gC9FrVThZzJmjiYi8jUUQeUyVzQG1n7cCAYBakmB1yBwhRkTkZSyCyGNsDidYA9XeDhQCsMtOb4dCROTXWASRx9hlARWrIKgknCuC2BJERORNLILIc1j/AADqSh/Wg0RE3sUiiDxGp1bBKdj6IURtAaRT8/IjIvImfgqTx+jUtX1h/J0QAioJ0PjxfElERL6ARRB5TAeDFg6OiILDKWDWadg/iojIy1gEkcfEh5t5OwyA1eFEzwizt8MgIvJ7LILIY+JCjQBqbwf5u25hJm+HQETk91gEkcfEhpigU6tgdfjv/DiyU0CSJMSFsAgiIvI2FkHkMTFBBhi1alj8uAiy2GUYNCrEhhi9HQoRkd9jEUQeo9Oo0DXUCKvdj4sghxNBRi0iAnTeDoWIyO+xCCKP6hkRAIcQftsvyOpwoleEGRJHhhEReR2LIPKoxNhg6NUqWPywNcgu166dNiIuxNuhEBERWASRh/WNDECPcDPKLA5vh+Jx5TUOdAzQY3hssLdDISIisAgiD5MkCVf1jgCE8KuJE4UQsDqcSO4VAYNW7e1wiIgILILIC5K6hSDUrEN5jd3boXhMhVWGWa/G6Pgwb4dCRETnsAgijzPrNBgbHwaL3ek3HaQrrQ4kdglGVAeDt0MhIqJzWASRV4yJD4dJp0aFtf33Daq2ydCoVBjXM9zboRAR0Xk03g7AWzhCuXnq3iel369uYSZM7heJ747kQ6uWoFG1z3rcKQRKq+24snsIhnYJcsvvnbtyRMpgfnwb8+Pb3J0fSfjL/QgiIiKi87TPr99EREREl8AiiIiIiPwSiyAiIiLySyyCiIiIyC+xCCIiIiK/xCKIiIiI/BKLICIiIvJLLIKIiIjIL7EIIiIiIr/EIshPFRcXY/78+UhMTMSIESOwcOFCOBxNr+O1detWXHfddUhISMCkSZOwefPm+n1OpxNDhgxBQkIChgwZUv+vurraUy+lXWpJfuqsX78eEyZMaLT9/fffx+jRo5GQkIA777wTp06dclfYfkOp/PD6cY+W5GflypW4+uqrMWTIEFx99dVYsWJFg/28fpSnVH4UuX4E+aWZM2eKxx9/XFRXV4usrCxx7bXXivfff7/Rcenp6WLgwIFiw4YNwm63i2+//VYMGjRI5OXlCSGESE1NFf379xdWq9XTL6Fda25+hBDCZrOJ9957T/Tr10+MGzeuwb7Vq1eLUaNGiePHjwuLxSIWLVokrr32WuF0Oj3xMtotpfLD68c9mpufDRs2iMTERLFv3z7hdDrF3r17RWJioli3bp0QgtePuyiVHyWuH7YE+aHMzEykpKRgwYIFMBqN6NKlC+bPn9/oGxAArFmzBomJiUhOToZGo8HkyZMxfPhw/Pvf/wYAHDx4EL1794ZOp/P0y2i3WpIfAJgzZw52796Ne++9t9G+zz//HHfccQd69uwJvV6Pxx9/HLm5udi9e7e7X0a7pWR+eP0oryX5yc/Px7333ouEhARIkoQhQ4ZgxIgR2LNnDwBeP+6gZH6UuH5YBPmhEydOIDg4GJGRkfXbevTogdzcXJw9e7bBsWlpaejVq1eDbfHx8Th27BiA2l9Cq9WKm266CSNHjsSMGTOwd+9e97+Idqwl+QGAV155BUuWLEFsbGyjfb/Nn1arRdeuXevzRy2nZH54/SivJfmZMWMGfve739X/XFxcjD179mDAgAEAeP24g5L5UeL6YRHkh6qqqmA0Ghtsq/v5t/dSmzrWYDDUH2cwGDBo0CC89dZb2LJlC8aPH4+5c+ciOzvbja+gfWtJfgCgU6dOLXqu8/NHLadkfnj9KK+l+alTWFiIe++9FwMGDMCUKVMu+Fy8flpHyfwocf2wCPJDJpMJNTU1DbbV/Ww2mxtsNxqNsFgsDbZZLJb6455++mm8+OKLiIyMhMFgwNy5cxEdHY2tW7e68RW0by3Jz6VcKn/Uckrmh9eP8lzJz/79+zF9+nR069YNb7/9NjQaDQBeP+6gZH6UuH5YBPmhnj17oqysDEVFRfXbTp48iU6dOiEwMLDBsb169cKJEycabEtLS0PPnj0BAP/4xz9w5MiRBvttNhv0er2bom//WpKf5jzX+fmz2+3IyMhodIuTmk/J/PD6UV5L8/PFF1/grrvuwuzZs/Haa6816F/C60d5SuZHieuHRZAf6tq1K4YNG4YXX3wRlZWVyM7OxltvvYXp06c3Ovb6669HSkoKvvvuOzgcDnz33XdISUnB1KlTAQDHjx/HwoULUVhYCJvNhjfffBOVlZW46qqrPP2y2o2W5OdSbrrpJnzyySc4duwYrFYrXnvtNYSHhyMxMdENkfsHJfPD60d5LcnP+vXr8fzzz+Nf//oX5syZ02g/rx/lKZkfRa4fl8eVUZtWWFgoHnzwQXHZZZeJkSNHipdeekk4HA4hhBAJCQniq6++qj9227Zt4vrrrxcJCQni2muvFVu2bKnfV1paKp5++mmRlJQkEhISxJ133imOHj3q8dfT3rQkP3W+/PLLRkOwnU6nWLp0qRg/fnx9fk6dOuWR19CeKZUfXj/u0dz8TJkyRfTp00ckJCQ0+Pfss88KIXj9uItS+VHi+pGEEKI1VR0RERFRW8TbYUREROSXWAQRERGRX2IRRERERH6JRRARERH5JRZBRERE5JdYBBEREZFfYhFEREREfolFEJGf2bJlCyRJQteuXS95bNeuXSFJErZs2aLo8xIR+QIWQUREROSXWAQRERGRX2IRRERERH6JRRAReVVZWRmeeeYZ9OnTBwaDAWFhYZgyZQp27NjR4LhbbrkFkiRh6dKlTT7PK6+8AkmS8MQTTzTYvmHDBkyaNAlhYWEwGAzo27cvnn/+eVRVVTU4LiMjA5IkYdq0aVi1ahXi4uJgNBoxaNAgVFZWAgByc3PxxBNPYODAgQgMDIRer0dsbCxmz56N1NTUJuP65ptvMGbMGAQHByMkJATTp09HWloakpOTIUkSMjIyGhxfU1ODl156CYMHD4bJZEJQUBDGjx+Pr7/+uiVvKxE1h5IrwxKR79u8ebMAIOLi4i55bFxcnAAgNm/erOjz1snMzBTdu3cXAETnzp3F9ddfL0aPHi3UarVQqVRiyZIl9cd+/fXXAoBITk5u8rkSEhIEALF///76bS+88IIAIDQajUhKShI33nijiI6OFgBEQkKCKCkpqT82PT1dABDdu3cXGo1GDB8+XEyaNElcc801Qgghjh07JiIiIgQA0b9/f3HjjTeKiRMniuDgYAFABAUFiaysrAYx/f3vf68//4QJE8R1110nAgICRGhoqIiPjxcARHp6ev3xZWVlYtiwYQKAiIiIEJMnTxbJyclCr9cLAOK5555r9ntLRJfGIojIz9QVK2azWcyYMeOi/8xms1uLoFGjRgkA4pFHHhE2m61++65du0RwcLDQ6XTi8OHDQggh7Ha76Nixo1Cr1SI/P7/B8xw9elQAEAMHDqzf9sMPPwgAIiYmRuzbt69+u9VqFXfddZcAIGbMmFG/va4IAiDmz59fv12WZSGEENddd50AIF577bUG5y4rKxPDhw8XAMQLL7zQICaNRiM6dOggdu3aVb89JydH9O3bt/5c5xdBd955pwAgbrnlFlFRUVG//fjx4yI2NlYAEBs2bGjWe0tEl8YiiMjP1BUrLfnnjiJo165dAoAYNGhQfaFxvldeeUUAEPPmzavf9tBDDwkA4s0332xw7LPPPisAiFdeeaV+2zXXXCMAiFWrVjV67qqqqvqCKicnRwjRsAg6ceJEo8fMnz9fTJs2TTgcjkb7/vnPfwoAYu7cuY1iffnllxsdv3PnzkZF0OnTp4VarRaRkZGisrKy0WNWrVolAIirr7660T4icg37BBH5qbi4OIjaL0IX/BcXF+e282/atAkAMHbsWKhUjT+KJk+eDAAN5iiaNWsWAOCzzz5rcOxnn30GlUqFO+64AwAgyzK2bdsGAJgwYUKj5zaZTBgzZgxkWcb27dsb7DMajYiPj2/0mMWLF2PNmjVQq9X124qLi7Fx40bs3LkTAGC1Wuv3/fDDDwCAqVOnNnquyy+/HFFRUQ22bd26FbIsY8SIETCbzY0ec80110ClUmH79u2QZbnRfiJqOY23AyAi/5SdnQ0AeOONN/DGG29c8jgAGDZsGPr164edO3ciJycHnTt3xp49e3DixAlcddVViI6OBlBbnFRXVwMAQkNDmxVHneDg4Asee/DgQbz99tvYs2cP0tLSUFZWBgCQJAkAIISoPzYrKwsAEBsb2+RzxcXF4cyZM43iWLt2bf3zNaW6uholJSWIiIi48IsiomZhEUREXlHXmjF8+HD06tXrgsf9tiC488478Yc//AH//ve/8fjjj2PlypUA/tdKdP5z6/V6TJ8+/aJx/LbVp6lWKaB29NmTTz4JABgwYAAmT56M/v37Y/jw4UhLS8P8+fMbHG+32wEATqezyec7v2A6P+Z+/fphyJAhF435YkUSETUfiyAi8oq620ETJ07ECy+80OzHzZw5E3/84x+xatUqPPbYY/j8889hNptxww031B8TFhYGrVYLu92OpUuXQq/XtyrW9PR0PP300wgKCsJ///tfJCUlNdh/6NChRo/p3LkzTp48iezsbPTp06fR/pycnAY/170fQ4YMwSeffNKqeImoedgniIi8YsyYMQCAdevWNdla8tVXX2HAgAG4//77G2zv3Lkzxo0bh5SUFHz55Zc4ffo0brzxxgb9aHQ6HZKSkuB0OrF+/fpGzy2EQHJyMq644gqkpKRcMtbdu3fD6XRi3LhxjQogAPj+++8BNGz1GTduHIDaeYJ+a+/evTh9+nSDbaNHjwZQ2zeo7lbebx/Tp08fTJ8+vVErEhG5hkUQEXnF2LFjMWTIEPzyyy9YsGABbDZb/b60tDQ8+OCDOHz4cJO3yu68804IIfDoo48CaHgrrE7dvgceeAD79u2r3+50OvHss89i48aNOHnyJAYPHnzJWOv63+zatQsFBQX12+12O5599lmsW7cOAGCxWOr3PfDAA1CpVFi4cCH27t1bv72oqAj33ntv/c91t7a6d++OqVOnIicnB3PnzkVFRUX9MQUFBZgzZw5SU1PRpUsX3g4jUopXxqQRkde4e7JElUolIiMjL/jvrrvuqn9MamqqiImJEQBEdHS0mDJlipgwYYLQarUCgLjxxhubHJJeUVFRP4dRdHR0k0PshRDiiSeeqJ+scMSIEeKGG26on5zRZDKJHTt21B9bN0Q+Jiam0fM4HA4xZMiQ+kkRp0yZIq677jrRsWPH+skTAYikpKQGj/vrX/9af/7k5GQxbdo0ERQUJDp16iRMJpMAIE6fPl1/fH5+vujXr58AIMLCwsQ111wjJk2aVP9aL7/88iaHzxORa1gEEfkZdxdBl/o3derUBo8rKCgQCxYsEL169RJ6vV6Eh4eLpKQksXz5cmG32y94vpkzZwoAYsGCBReNa+3ateLqq68WISEhQq/Xi/j4eDF37txGcwFdrAgSQoiSkhLx2GOPifj4eGEwGERMTIy48sorxTvvvCNsNpsIDg4WarVa5OXlNXjcypUrxYgRI4TJZBJBQUHilltuEenp6SIkJEQAaDApohC1Bd5f//pXMXDgQGE0GkVwcLAYNmyY+Mc//iGqq6sv+lqJqGUkIXhzmYhIaSdPnoQkSYiLi2swtxAAlJSUIDw8HB07dkReXp6XIiQi9gkiInKD5cuXo0ePHvjjH//YYLvD4cBjjz0GIUSDEW1E5HlsCSIicoOMjAwMHToUpaWl6NWrFwYMGACbzYaff/4ZeXl56N+/P3bs2HHRyRmJyL1YBBERuUlWVhZef/11fPfdd8jJyYEkSejevTtuvvlmPProozCZTN4OkcivsQgiIiIiv8Q+QUREROSXWAQRERGRX2IRRERERH6JRRARERH5JRZBRERE5JdYBBEREZFfYhFEREREfolFEBEREfklFkFERETkl/4fdmmq2SpzCUgAAAAASUVORK5CYII=\n",
            "text/plain": "<Figure size 640x480 with 1 Axes>"
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:52.536106Z",
          "start_time": "2023-01-16T08:22:52.508354Z"
        },
        "trusted": false
      },
      "id": "98e892ba",
      "cell_type": "code",
      "source": "k=3\nn = df.shape[0]\nleverage_cutoff = 3 * ((k+1)/n)\nleverage_cutoff",
      "execution_count": 158,
      "outputs": [
        {
          "data": {
            "text/plain": "0.24"
          },
          "execution_count": 158,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:52.586359Z",
          "start_time": "2023-01-16T08:22:52.539540Z"
        },
        "trusted": false
      },
      "id": "7c079e1c",
      "cell_type": "code",
      "source": "df[df.index.isin([49])]",
      "execution_count": 159,
      "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>RS</th>\n      <th>Ad</th>\n      <th>MS</th>\n      <th>P</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>49</th>\n      <td>0.0</td>\n      <td>116983.8</td>\n      <td>45173.06</td>\n      <td>14681.4</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "     RS        Ad        MS        P\n49  0.0  116983.8  45173.06  14681.4"
          },
          "execution_count": 159,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:52.640943Z",
          "start_time": "2023-01-16T08:22:52.594632Z"
        },
        "trusted": false
      },
      "id": "e30a8dab",
      "cell_type": "code",
      "source": "#there's a too much difference in RS values\ndf.head()",
      "execution_count": 160,
      "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>RS</th>\n      <th>Ad</th>\n      <th>MS</th>\n      <th>P</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>165349.20</td>\n      <td>136897.80</td>\n      <td>471784.10</td>\n      <td>192261.83</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>162597.70</td>\n      <td>151377.59</td>\n      <td>443898.53</td>\n      <td>191792.06</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>153441.51</td>\n      <td>101145.55</td>\n      <td>407934.54</td>\n      <td>191050.39</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>144372.41</td>\n      <td>118671.85</td>\n      <td>383199.62</td>\n      <td>182901.99</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>142107.34</td>\n      <td>91391.77</td>\n      <td>366168.42</td>\n      <td>166187.94</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "          RS         Ad         MS          P\n0  165349.20  136897.80  471784.10  192261.83\n1  162597.70  151377.59  443898.53  191792.06\n2  153441.51  101145.55  407934.54  191050.39\n3  144372.41  118671.85  383199.62  182901.99\n4  142107.34   91391.77  366168.42  166187.94"
          },
          "execution_count": 160,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {},
      "id": "a1c69231",
      "cell_type": "markdown",
      "source": "# Improving the model"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:52.689996Z",
          "start_time": "2023-01-16T08:22:52.646498Z"
        },
        "trusted": false
      },
      "id": "8e3f39f3",
      "cell_type": "code",
      "source": "#Load the data\ndf_new = pd.read_csv('50_Startups.csv')\ndf_new.head()",
      "execution_count": 161,
      "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>R&amp;D Spend</th>\n      <th>Administration</th>\n      <th>Marketing Spend</th>\n      <th>State</th>\n      <th>Profit</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>165349.20</td>\n      <td>136897.80</td>\n      <td>471784.10</td>\n      <td>New York</td>\n      <td>192261.83</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>162597.70</td>\n      <td>151377.59</td>\n      <td>443898.53</td>\n      <td>California</td>\n      <td>191792.06</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>153441.51</td>\n      <td>101145.55</td>\n      <td>407934.54</td>\n      <td>Florida</td>\n      <td>191050.39</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>144372.41</td>\n      <td>118671.85</td>\n      <td>383199.62</td>\n      <td>New York</td>\n      <td>182901.99</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>142107.34</td>\n      <td>91391.77</td>\n      <td>366168.42</td>\n      <td>Florida</td>\n      <td>166187.94</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "   R&D Spend  Administration  Marketing Spend       State     Profit\n0  165349.20       136897.80        471784.10    New York  192261.83\n1  162597.70       151377.59        443898.53  California  191792.06\n2  153441.51       101145.55        407934.54     Florida  191050.39\n3  144372.41       118671.85        383199.62    New York  182901.99\n4  142107.34        91391.77        366168.42     Florida  166187.94"
          },
          "execution_count": 161,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:52.718880Z",
          "start_time": "2023-01-16T08:22:52.689996Z"
        },
        "trusted": false
      },
      "id": "6eacbf59",
      "cell_type": "code",
      "source": "#Discard the data points which are influencers and reasign the row number (reset_index())\n#df_new1=df_new.drop(df_new[[49]],axis=0).reset_index()\ndf_new1=df_new.drop(df_new.index[[49]],axis=0).reset_index()",
      "execution_count": 162,
      "outputs": []
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:22:52.737341Z",
          "start_time": "2023-01-16T08:22:52.718880Z"
        },
        "trusted": false
      },
      "id": "1204c01c",
      "cell_type": "code",
      "source": "df_new1=df_new1.drop(['index'],axis=1)\n",
      "execution_count": 163,
      "outputs": []
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:37:28.316777Z",
          "start_time": "2023-01-16T08:37:28.300143Z"
        },
        "trusted": false
      },
      "id": "a198c11d",
      "cell_type": "code",
      "source": "#df_new1",
      "execution_count": 165,
      "outputs": []
    },
    {
      "metadata": {},
      "id": "d7248ed9",
      "cell_type": "markdown",
      "source": "# Build Model"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:43:05.989366Z",
          "start_time": "2023-01-16T08:43:05.925768Z"
        },
        "trusted": false
      },
      "id": "78c30437",
      "cell_type": "code",
      "source": "df_new1=df_new1.rename({'R&D Spend':'RS','Administration':'Ad','Marketing Spend':'MS','Profit':'P'},axis=1)\ndf_new1.head()",
      "execution_count": 167,
      "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>RS</th>\n      <th>Ad</th>\n      <th>MS</th>\n      <th>State</th>\n      <th>P</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>165349.20</td>\n      <td>136897.80</td>\n      <td>471784.10</td>\n      <td>New York</td>\n      <td>192261.83</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>162597.70</td>\n      <td>151377.59</td>\n      <td>443898.53</td>\n      <td>California</td>\n      <td>191792.06</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>153441.51</td>\n      <td>101145.55</td>\n      <td>407934.54</td>\n      <td>Florida</td>\n      <td>191050.39</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>144372.41</td>\n      <td>118671.85</td>\n      <td>383199.62</td>\n      <td>New York</td>\n      <td>182901.99</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>142107.34</td>\n      <td>91391.77</td>\n      <td>366168.42</td>\n      <td>Florida</td>\n      <td>166187.94</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "          RS         Ad         MS       State          P\n0  165349.20  136897.80  471784.10    New York  192261.83\n1  162597.70  151377.59  443898.53  California  191792.06\n2  153441.51  101145.55  407934.54     Florida  191050.39\n3  144372.41  118671.85  383199.62    New York  182901.99\n4  142107.34   91391.77  366168.42     Florida  166187.94"
          },
          "execution_count": 167,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:43:26.189361Z",
          "start_time": "2023-01-16T08:43:26.120007Z"
        },
        "trusted": false
      },
      "id": "864117b3",
      "cell_type": "code",
      "source": "model2 = smf.ols('P~MS+RS',data=df_new1).fit()\nmodel2.summary()",
      "execution_count": 169,
      "outputs": [
        {
          "data": {
            "text/html": "<table class=\"simpletable\">\n<caption>OLS Regression Results</caption>\n<tr>\n  <th>Dep. Variable:</th>            <td>P</td>        <th>  R-squared:         </th> <td>   0.961</td>\n</tr>\n<tr>\n  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.959</td>\n</tr>\n<tr>\n  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   568.0</td>\n</tr>\n<tr>\n  <th>Date:</th>             <td>Mon, 16 Jan 2023</td> <th>  Prob (F-statistic):</th> <td>3.74e-33</td>\n</tr>\n<tr>\n  <th>Time:</th>                 <td>14:13:26</td>     <th>  Log-Likelihood:    </th> <td> -506.43</td>\n</tr>\n<tr>\n  <th>No. Observations:</th>      <td>    49</td>      <th>  AIC:               </th> <td>   1019.</td>\n</tr>\n<tr>\n  <th>Df Residuals:</th>          <td>    46</td>      <th>  BIC:               </th> <td>   1025.</td>\n</tr>\n<tr>\n  <th>Df Model:</th>              <td>     2</td>      <th>                     </th>     <td> </td>   \n</tr>\n<tr>\n  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n</tr>\n<tr>\n  <th>Intercept</th> <td> 4.979e+04</td> <td> 2341.584</td> <td>   21.261</td> <td> 0.000</td> <td> 4.51e+04</td> <td> 5.45e+04</td>\n</tr>\n<tr>\n  <th>MS</th>        <td>    0.0274</td> <td>    0.013</td> <td>    2.104</td> <td> 0.041</td> <td>    0.001</td> <td>    0.054</td>\n</tr>\n<tr>\n  <th>RS</th>        <td>    0.7754</td> <td>    0.035</td> <td>   22.136</td> <td> 0.000</td> <td>    0.705</td> <td>    0.846</td>\n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n  <th>Omnibus:</th>       <td> 0.082</td> <th>  Durbin-Watson:     </th> <td>   1.546</td>\n</tr>\n<tr>\n  <th>Prob(Omnibus):</th> <td> 0.960</td> <th>  Jarque-Bera (JB):  </th> <td>   0.273</td>\n</tr>\n<tr>\n  <th>Skew:</th>          <td>-0.051</td> <th>  Prob(JB):          </th> <td>   0.872</td>\n</tr>\n<tr>\n  <th>Kurtosis:</th>      <td> 2.649</td> <th>  Cond. No.          </th> <td>5.52e+05</td>\n</tr>\n</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 5.52e+05. This might indicate that there are<br/>strong multicollinearity or other numerical problems.",
            "text/plain": "<class 'statsmodels.iolib.summary.Summary'>\n\"\"\"\n                            OLS Regression Results                            \n==============================================================================\nDep. Variable:                      P   R-squared:                       0.961\nModel:                            OLS   Adj. R-squared:                  0.959\nMethod:                 Least Squares   F-statistic:                     568.0\nDate:                Mon, 16 Jan 2023   Prob (F-statistic):           3.74e-33\nTime:                        14:13:26   Log-Likelihood:                -506.43\nNo. Observations:                  49   AIC:                             1019.\nDf Residuals:                      46   BIC:                             1025.\nDf Model:                           2                                         \nCovariance Type:            nonrobust                                         \n==============================================================================\n                 coef    std err          t      P>|t|      [0.025      0.975]\n------------------------------------------------------------------------------\nIntercept   4.979e+04   2341.584     21.261      0.000    4.51e+04    5.45e+04\nMS             0.0274      0.013      2.104      0.041       0.001       0.054\nRS             0.7754      0.035     22.136      0.000       0.705       0.846\n==============================================================================\nOmnibus:                        0.082   Durbin-Watson:                   1.546\nProb(Omnibus):                  0.960   Jarque-Bera (JB):                0.273\nSkew:                          -0.051   Prob(JB):                        0.872\nKurtosis:                       2.649   Cond. No.                     5.52e+05\n==============================================================================\n\nNotes:\n[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n[2] The condition number is large, 5.52e+05. This might indicate that there are\nstrong multicollinearity or other numerical problems.\n\"\"\""
          },
          "execution_count": 169,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:45:10.191395Z",
          "start_time": "2023-01-16T08:45:10.167094Z"
        },
        "trusted": false
      },
      "id": "c64253b6",
      "cell_type": "code",
      "source": "model2.rsquared,model2.aic,model2.bic",
      "execution_count": 175,
      "outputs": [
        {
          "data": {
            "text/plain": "(0.9610856807456628, 1018.8564801588338, 1024.5319410531658)"
          },
          "execution_count": 175,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2023-01-16T08:49:43.962494Z",
          "start_time": "2023-01-16T08:49:43.938518Z"
        },
        "trusted": false
      },
      "id": "6706850e",
      "cell_type": "code",
      "source": "(np.argmax(c),np.max(c))",
      "execution_count": 176,
      "outputs": [
        {
          "data": {
            "text/plain": "(49, 0.2880822927543263)"
          },
          "execution_count": 176,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3 (ipykernel)",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.9.13",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "!excelR/assignments/Gists/MLR_50_Startups.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}