Heart Disease Prediction.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Heart Disease Prediction\n",
    "\n",
    "In this machine learning project, I have collected the dataset from Kaggle (https://www.kaggle.com/ronitf/heart-disease-uci) and I will be using Machine Learning to make predictions on whether a person is suffering from Heart Disease or not."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Import libraries\n",
    "\n",
    "Let's first import all the necessary libraries. I'll use `numpy` and `pandas` to start with. For visualization, I will use `pyplot` subpackage of `matplotlib`, use `rcParams` to add styling to the plots and `rainbow` for colors. For implementing Machine Learning models and processing of data, I will use the `sklearn` library."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib import rcParams\n",
    "from matplotlib.cm import rainbow\n",
    "%matplotlib inline\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For processing the data, I'll import a few libraries. To split the available dataset for testing and training, I'll use the `train_test_split` method. To scale the features, I am using `StandardScaler`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Next, I'll import all the Machine Learning algorithms I will be using.\n",
    "1. K Neighbors Classifier\n",
    "2. Support Vector Classifier\n",
    "3. Decision Tree Classifier\n",
    "4. Random Forest Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Import dataset\n",
    "\n",
    "Now that we have all the libraries we will need, I can import the dataset and take a look at it. The dataset is stored in the file `dataset.csv`. I'll use the pandas `read_csv` method to read the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = pd.read_csv('dataset.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The dataset is now loaded into the variable `dataset`. I'll just take a glimpse of the data using the `desribe()` and `info()` methods before I actually start processing and visualizing it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 303 entries, 0 to 302\n",
      "Data columns (total 14 columns):\n",
      "age         303 non-null int64\n",
      "sex         303 non-null int64\n",
      "cp          303 non-null int64\n",
      "trestbps    303 non-null int64\n",
      "chol        303 non-null int64\n",
      "fbs         303 non-null int64\n",
      "restecg     303 non-null int64\n",
      "thalach     303 non-null int64\n",
      "exang       303 non-null int64\n",
      "oldpeak     303 non-null float64\n",
      "slope       303 non-null int64\n",
      "ca          303 non-null int64\n",
      "thal        303 non-null int64\n",
      "target      303 non-null int64\n",
      "dtypes: float64(1), int64(13)\n",
      "memory usage: 33.2 KB\n"
     ]
    }
   ],
   "source": [
    "dataset.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Looks like the dataset has a total of 303 rows and there are no missing values. There are a total of `13 features` along with one target value which we wish to find."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "      <td>303.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>54.366337</td>\n",
       "      <td>0.683168</td>\n",
       "      <td>0.966997</td>\n",
       "      <td>131.623762</td>\n",
       "      <td>246.264026</td>\n",
       "      <td>0.148515</td>\n",
       "      <td>0.528053</td>\n",
       "      <td>149.646865</td>\n",
       "      <td>0.326733</td>\n",
       "      <td>1.039604</td>\n",
       "      <td>1.399340</td>\n",
       "      <td>0.729373</td>\n",
       "      <td>2.313531</td>\n",
       "      <td>0.544554</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>9.082101</td>\n",
       "      <td>0.466011</td>\n",
       "      <td>1.032052</td>\n",
       "      <td>17.538143</td>\n",
       "      <td>51.830751</td>\n",
       "      <td>0.356198</td>\n",
       "      <td>0.525860</td>\n",
       "      <td>22.905161</td>\n",
       "      <td>0.469794</td>\n",
       "      <td>1.161075</td>\n",
       "      <td>0.616226</td>\n",
       "      <td>1.022606</td>\n",
       "      <td>0.612277</td>\n",
       "      <td>0.498835</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>29.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>94.000000</td>\n",
       "      <td>126.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>71.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>47.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>120.000000</td>\n",
       "      <td>211.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>133.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>55.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>130.000000</td>\n",
       "      <td>240.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>153.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>61.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>140.000000</td>\n",
       "      <td>274.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>166.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.600000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>77.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>200.000000</td>\n",
       "      <td>564.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>202.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>6.200000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              age         sex          cp    trestbps        chol         fbs  \\\n",
       "count  303.000000  303.000000  303.000000  303.000000  303.000000  303.000000   \n",
       "mean    54.366337    0.683168    0.966997  131.623762  246.264026    0.148515   \n",
       "std      9.082101    0.466011    1.032052   17.538143   51.830751    0.356198   \n",
       "min     29.000000    0.000000    0.000000   94.000000  126.000000    0.000000   \n",
       "25%     47.500000    0.000000    0.000000  120.000000  211.000000    0.000000   \n",
       "50%     55.000000    1.000000    1.000000  130.000000  240.000000    0.000000   \n",
       "75%     61.000000    1.000000    2.000000  140.000000  274.500000    0.000000   \n",
       "max     77.000000    1.000000    3.000000  200.000000  564.000000    1.000000   \n",
       "\n",
       "          restecg     thalach       exang     oldpeak       slope          ca  \\\n",
       "count  303.000000  303.000000  303.000000  303.000000  303.000000  303.000000   \n",
       "mean     0.528053  149.646865    0.326733    1.039604    1.399340    0.729373   \n",
       "std      0.525860   22.905161    0.469794    1.161075    0.616226    1.022606   \n",
       "min      0.000000   71.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "25%      0.000000  133.500000    0.000000    0.000000    1.000000    0.000000   \n",
       "50%      1.000000  153.000000    0.000000    0.800000    1.000000    0.000000   \n",
       "75%      1.000000  166.000000    1.000000    1.600000    2.000000    1.000000   \n",
       "max      2.000000  202.000000    1.000000    6.200000    2.000000    4.000000   \n",
       "\n",
       "             thal      target  \n",
       "count  303.000000  303.000000  \n",
       "mean     2.313531    0.544554  \n",
       "std      0.612277    0.498835  \n",
       "min      0.000000    0.000000  \n",
       "25%      2.000000    0.000000  \n",
       "50%      2.000000    1.000000  \n",
       "75%      3.000000    1.000000  \n",
       "max      3.000000    1.000000  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The scale of each feature column is different and quite varied as well. While the maximum for `age` reaches 77, the maximum of `chol` (serum cholestoral) is 564."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Understanding the data\n",
    "\n",
    "Now, we can use visualizations to better understand our data and then look at any processing we might want to do."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.colorbar.Colorbar at 0x1a15fc91d0>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x1008 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "rcParams['figure.figsize'] = 20, 14\n",
    "plt.matshow(dataset.corr())\n",
    "plt.yticks(np.arange(dataset.shape[1]), dataset.columns)\n",
    "plt.xticks(np.arange(dataset.shape[1]), dataset.columns)\n",
    "plt.colorbar()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Taking a look at the correlation matrix above, it's easy to see that a few features have negative correlation with the target value while some have positive.\n",
    "Next, I'll take a look at the histograms for each variable."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[<matplotlib.axes._subplots.AxesSubplot object at 0x1a15d3edd8>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a16d85940>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a16d0dba8>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a16d37e10>],\n",
       "       [<matplotlib.axes._subplots.AxesSubplot object at 0x1a175430b8>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a16dd3320>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a16dfc588>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a1789b828>],\n",
       "       [<matplotlib.axes._subplots.AxesSubplot object at 0x1a1789b860>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a178edcc0>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a17916f28>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a1794b1d0>],\n",
       "       [<matplotlib.axes._subplots.AxesSubplot object at 0x1a17972438>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a1799b6a0>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a179c7908>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1a179f1b70>]],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABIcAAAMoCAYAAABVnIAuAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvOIA7rQAAIABJREFUeJzs3Xu4ZFV95//3R/BCEEVEThCIrRHvrag9qMOMOZFgEB3B36gjQxSUTGtGMvpLTyImeaIxMeKMaBQzOigG/IVwGZTAqHEkyAnjjGJECRfRgNpKA4LKRVoTTOP398feR8vDOd3Vp267Tr1fz1NP1d61d9VnV+1atWvVWmunqpAkSZIkSdJsus+kA0iSJEmSJGlyrBySJEmSJEmaYVYOSZIkSZIkzTArhyRJkiRJkmaYlUOSJEmSJEkzzMohSZIkSZKkGWblkCRJkjRiSY5L8plVrvvmJH8x7EySJC2yckiSJEmSJGmGWTkkSZIkSZI0w6wcUl+SnJjka0nuSvLlJC9q5++S5OQk303yjSQnJKkku7b3PzjJaUluTnJjkj9Osstkt0bSWpbkgCQfTfKdJN9L8t4kv5jk0+30d5OcmWTPSWeVtDYtVw713PeOJLe3x03P65n/8CQXJrktyfVJ/sNk0kuaRSscPx2X5P8kOSXJnUm+kuTQSWfVaFg5pH59DfjXwIOBPwT+Ism+wH8AngccBDwNOGrJemcA24BHA08Fngv8+pgyS5oxbeXzx4BvAuuA/YCzgQBvAx4OPB44AHjzREJKWtO2Uw4BPAP4KrA38F+A05Kkve8sYAtNOfVi4E/8ESZpHPoot75OU269Cfhokr0mEFMjlqqadAZNoSRX0BQOrwPOqar/3s7/FeAi4L7AQ4FvAXtW1T+29x8NbKyqX55IcElrWpJnARcC+1bVtu0sdxTwpqp66tjCSZoJK5VDSY4Dfr+qHt1O/xzwA2BfmuOmzTTHTHe197+tfYzjkrwZeHRV/doYN0XSjNhBufUnwH7VVhwk+TxwSlX9f5PIqtHZddIBNB2SvAL4LZqaZIAH0tQePxy4oWfR3tuPoDnYufmnf4pxnyXLSNIwHQB8c2nFUJJ9gPfQtIDcg6Ysun388STNgGXLoda3F29U1Q/b46MH0vyhdttixVDrm8CGUQaVpNb2yq0b62dblHyT5jeg1hi7lWmHkjwC+ABwAvDQqtoTuJqmm8bNwP49ix/Qc/sG4G5g76ras708qKqeOKbokmbPDcAvLI571uNtQAFPrqoHAb9GU4ZJ0rCtVA5tz03AXkn26Jn3C8CNQ00mScvbXrm1X0/3V2jKppvGE0vjZOWQ+rE7zY+q7wAkeSXwpPa+c4HXJdmvHdz1DYsrVdXNwKeAk5M8KMl92kFhf2m88SXNkM/TVFqflGT3JA9IcghNa6GtwB1J9gN+e5IhJa1pK5VDK6qqG4D/C7ytXf7JwPHAmaOPK0nbLbf2Af5TkvsmeQnN2I2fmFRQjY6VQ9qhqvoycDLwWeAWYD3wf9q7P0BTAXQl8CWagmIbcE97/yuA+wFfpunCcR5N33pJGrqqugf4NzSD4H+LZnDXf0czkP7TgDuBjwMfnVRGSWvbdsqhHTmapvv+TcD5NOOiXTSimJL0Ezsoty4DDgS+C7wVeHFVfW8SOTVaDkitoWpPyfr+qnrEpLNIkiRJklanHZD616vqX006i0bPlkMaSJLdkhyRZNe2q8abaP7tkiRJkiRJU8DKIQ0qNN01bqfpVnYt8AcTTSRJkiRpRUk+lOTWJFf3zHtzkhuTXNFejui5741Jrk/y1SS/OpnUkkbJbmWSJEmSNEOSPJvmRA0frqontfPeDGytqncsWfYJwFnAwTSnMP8b4DHtODWS1ghbDkmSJEnSDKmqS4Hb+lz8SODsqrq7qr4BXE9TUSRpDbFySJIkSZIEcEKSK9tuZw9p5+0H3NCzzJZ2nqQ1ZNdJBwDYe++9a926data9wc/+AG77777cAONiFlHw6zDdfnll3+3qh426RxdsTPl0zS8v/1aS9sCbk/X9bs9lk8/a5Djp0ma5v3X7JPT9fxrpHx6H/BHQLXXJwOvohljdKl7jU2SZCOwEWC33XZ7+gEHHNDXk/74xz/mPveZfJuFruSA7mTpSg7oTpau5ID+s/zDP/xDf+VTVU388vSnP71W65JLLln1uuNm1tEw63ABX6gOlAtduexM+TQN72+/1tK2VLk9Xdfv9lg+rb586pJp3n/NPjldzz+N5ROwDrh6R/cBbwTe2HPf/wKetb3Hnsbjp67kqOpOlq7kqOpOlq7kqBr+8VM3qrwkSZIkSROTZN+eyRcBi2cyuxB4WZL7J3kkcCDw+XHnkzRanehWJkmSJEkajyRnAfPA3km2AG8C5pMcRNNlbDPwaoCquibJucCXgW3Aa8szlUlrjpVDkiRJkjRDquroZWaftp3l3wq8dXSJJE2a3cokSZIkSZJmmJVDkiRJkiRJM8xuZeq0dSd+fIfLbFq/jeP6WA5g80nPHzSStKKrbryz732xH+6vkmZJP9/5O8tyVOq+YR8/gZ99aTVsOSRJkiRJkjTDrBySJEmSJEmaYVYOSZIkSZIkzbCBKoeS7JnkvCRfSXJtkmcl2SvJRUmua68fMqywkiRJkiRJGq5BWw69G/hkVT0OeApwLXAicHFVHQhc3E5LkiTNlCQfSnJrkqt75i37J1oa70lyfZIrkzxtcsklSdKsWXXlUJIHAc8GTgOoqh9V1R3AkcAZ7WJnAEcNGlKSJGkKnQ4cvmTeSn+iPQ84sL1sBN43poySJEkDncr+UcB3gD9P8hTgcuB1wFxV3QxQVTcn2We5lZNspDn4YW5ujoWFhVWF2Lp166rXHbe1nvWqG+8ceo5N63e8zNxuzens+zHp13+a9gFJ0mCq6tIk65bMPhKYb2+fASwAb2jnf7iqCvhc23V/38VjKkmSpFEapHJoV+BpwG9W1WVJ3s1OdCGrqlOBUwE2bNhQ8/PzqwqxsLDAatcdt7We9bgTPz6aMDuwaf02Tr6qv1158zHzow2zA9O0D0iSRmKlP9H2A27oWW5LO8/KIUmSNHKDVA5tAbZU1WXt9Hk0lUO3LP7TlWRf4NZBQ0qSJK1xWWZe3WuhIbW8nqSVWtH22wp4Zwz79ZnmFsDTnB2mP78kdd2qK4eq6ttJbkjy2Kr6KnAo8OX2cixwUnt9wVCSSpIkTb+V/kTbAhzQs9z+wE1LVx5Wy+tJWqkV7ShaIA+7xfA0twCe5uww/fklqesGPVvZbwJnJrkSOAj4E5pKocOSXAcc1k5LkiQJLqT58wx+9k+0C4FXtGcteyZwp+MNSZKkcRmkWxlVdQWwYZm7Dh3kcSVJkqZdkrNoBp/eO8kW4E00f5qdm+R44FvAS9rFPwEcAVwP/BB45dgDS5KkmTVQ5ZAkSZKWV1VHr3DXvf5Ea89S9trRJpIkSVreoN3KJEmSJEmSNMWsHJIkSZKkGZHkQ0luTXJ1z7z/muQrSa5Mcn6SPdv565L8Y5Ir2sv7J5dc0ihZOSRJkiRJs+N04PAl8y4CnlRVTwb+AXhjz31fq6qD2strxpRR0phZOSRJkiRJM6KqLgVuWzLvU1W1rZ38HLD/2INJmigrhyRNrRWaRb85yY09zZ+P6LnvjUmuT/LVJL86mdSSJEmd9irgr3umH5nkS0n+Nsm/nlQoSaPl2cokTbPTgfcCH14y/11V9Y7eGUmeALwMeCLwcOBvkjymqu4ZR1BJkqSuS/J7wDbgzHbWzcAvVNX3kjwd+KskT6yq7y+z7kZgI8Dc3BwLCwt9PefcbrBp/bYdL7gT+n3uXlu3bl3VeqPQlSxdyQHdydKVHDD8LFYOSZpaVXVpknV9Ln4kcHZV3Q18I8n1wMHAZ0cUT5IkaWokORZ4AXBoVRVAe9x0d3v78iRfAx4DfGHp+lV1KnAqwIYNG2p+fr6v5z3lzAs4+arh/izdfEx/z91rYWGBfjOPWleydCUHdCdLV3LA8LNYOSRpLTohyStoDlw2VdXtwH40fegXbWnn3UtX/vma5L8SXfpXZBjcnm5ba9sjSdMmyeHAG4Bfqqof9sx/GHBbVd2T5FHAgcDXJxRT0ghZOSRprXkf8EdAtdcn0/SdzzLL1nIP0JV/vlbzr9ewdOlfkWFwe7ptrW2PJHVZkrOAeWDvJFuAN9Gcnez+wEVJAD7Xnpns2cBbkmwD7gFeU1W3LfvAkqaalUOS1pSqumXxdpIPAB9rJ7cAB/Qsuj9w0xijSZIkTVxVHb3M7NNWWPYjwEdGm0hSF3i2MklrSpJ9eyZfBCyeyexC4GVJ7p/kkTTNoj8/7nySJEmS1DW2HJI0tVZoFj2f5CCaLmObgVcDVNU1Sc4FvkxzFo7XeqYySZIkSbJySNIU25lm0e3ybwXeOrpEkiRJkjR9BqocSrIZuItmcLJtVbUhyV7AOcA6mn/tX9qeKUiSJEmSJEkdM4wxh365qg6qqg3t9InAxVV1IHBxOy1JkiRJkqQOGsWA1EcCZ7S3zwCOGsFzSJIkSZIkaQgGrRwq4FNJLk+ysZ03V1U3A7TX+wz4HJIkSZIkSRqRQQekPqSqbkqyD3BRkq/0u2JbmbQRYG5ujoWFhVUF2Lp166rXHbe1nnXT+m2jCbMDc7v1/9yTfv2naR+QJEmSJM2GgSqHquqm9vrWJOcDBwO3JNm3qm5Osi9w6wrrngqcCrBhw4aan59fVYaFhQVWu+64rfWsx5348dGE2YFN67dx8lX97cqbj5kfbZgdmKZ9QJIkSZI0G1bdrSzJ7kn2WLwNPBe4GrgQOLZd7FjggkFDSpIkrRVJ/t8k1yS5OslZSR6Q5JFJLktyXZJzktxv0jklSdLsGGTMoTngM0n+Hvg88PGq+iRwEnBYkuuAw9ppSZKkmZdkP+A/ARuq6knALsDLgLcD72rP9no7cPzkUkqSpFmz6m5lVfV14CnLzP8ecOggoSRJktawXYHdkvwz8HPAzcBzgH/f3n8G8GbgfRNJJ0mSZs6gA1JLkiSpT1V1Y5J3AN8C/hH4FHA5cEdVLZ5dYQuw33LrD+uEHpO00skZRnFii2G/PtN8Yolpzg7Tn1+Sus7KIUmSpDFJ8hDgSOCRwB3A/wCet8yitdz6wzqhxyStdHKGUZzYYtgnopjmE0tMc3aY/vyS1HWDjDkkSZKknfMrwDeq6jtV9c/AR4F/CeyZZPFPu/2BmyYVUJIkzR4rhyRJksbnW8Azk/xcktCM0/hl4BLgxe0ynu1VkiSNlZVDkiRJY1JVlwHnAV8ErqI5FjsVeAPwW0muBx4KnDaxkJIkaeZYOSRJkjRGVfWmqnpcVT2pql5eVXdX1der6uCqenRVvaSq7p50TklrV5IPJbk1ydU98/ZKclGS69rrh7Tzk+Q9Sa5PcmWSp00uuaRRsXJIkiRJkmbL6cDhS+adCFxcVQcCF7fT0Ayaf2B72Qi8b0wZJY2RlUOSJEmSNEOq6lLgtiWzjwTOaG+fARzVM//D1fgczQD6+44nqaRxsXJIkiRJkjRXVTcDtNf7tPP3A27oWW5LO0/SGrLrjheRJEmSJM2oLDOv7rVQspGm2xlzc3MsLCz09eBzu8Gm9dsGyXcv/T53r61bt65qvVHoSpau5IDuZOlKDhh+FiuHJEmStFPWnfjxVa+7af02jhtgfUkjc0uSfavq5rbb2K3t/C3AAT3L7Q/ctHTlqjqV5uyLbNiwoebn5/t60lPOvICTrxruz9LNx/T33L0WFhboN/OodSVLV3JAd7J0JQcMP4uVQ5opgxzMrmTzSc8f+mNKkiRJY3YhcCxwUnt9Qc/8E5KcDTwDuHOx+5mktcPKIUmSJEmaIUnOAuaBvZNsAd5EUyl0bpLjgW8BL2kX/wRwBHA98EPglWMPLGnkrBySJEmSpBlSVUevcNehyyxbwGtHm0jSpHm2MkmSJEmSpBk2cOVQkl2SfCnJx9rpRya5LMl1Sc5Jcr/BY0qSJEmSJGkUhtGt7HXAtcCD2um3A++qqrOTvB84HnjfEJ5HkiRJ6tuwT0Sxaf025of6iJIkdcNALYeS7A88H/hgOx3gOcB57SJnAEcN8hySJEmSJEkanUFbDv0p8DvAHu30Q4E7qmpbO70F2G+5FZNsBDYCzM3NsbCwsKoAW7duXfW647bWs25av23HC43A3G6Te25gp16nadoHJEmSJEmzYdWVQ0leANxaVZcnmV+cvcyitdz6VXUqcCrAhg0ban5+frnFdmhhYYHVrjtuaz3rcUNuut2vTeu3cfJVkzvx3uZj5vtedpr2AUmSJEnSbBjkF/UhwAuTHAE8gGbMoT8F9kyya9t6aH/gpsFjSpIkSZIkaRRWPeZQVb2xqvavqnXAy4BPV9UxwCXAi9vFjgUuGDilJEmSJEmSRmIUfXHeAJyd5I+BLwGnjeA5JEmSJEnSFFntWSQ3rd+24jAmm096/iCR1BpK5VBVLQAL7e2vAwcP43H1U8M+FasfIEmSJEmSBAOeyl6SJi3Jh5LcmuTqnnl7JbkoyXXt9UPa+UnyniTXJ7kyydMml1ySJEmSumFyp3jSRO2oJdL2mu1JHXM68F7gwz3zTgQurqqTkpzYTr8BeB5wYHt5BvC+9lqSxibJnsAHgSfRnNX1VcBXgXOAdcBm4KVVdfuEIkqSpBljyyFJU62qLgVuWzL7SOCM9vYZwFE98z9cjc/RnF1x3/EklaSfeDfwyap6HPAU4Fp+Wql9IHBxOy1JkjQWVg5JWovmqupmgPZ6n3b+fsANPcttaedJ0lgkeRDwbNoTdlTVj6rqDlau1JYkSRo5u5VJmiVZZl7da6FkI7ARYG5ujoWFhb4efG63pkvmsPT7vKOwdevWiT7/sLk93bbWtmcHHgV8B/jzJE8BLgdex5JK7ST7LLfyasunYRukrBt2WTlOc7tNtmwexLR/zqY9vyR1nZVDktaiW5Ls2/7A2he4tZ2/BTigZ7n9gZuWrlxVpwKnAmzYsKHm5+f7etJTzryAk68aXrG6+Zj+nncUFhYW6He7p4Hb021rbXt2YFfgacBvVtVlSd7NTnQhW235NGyDjEu4af22oZaV47Rp/TZeOqX76rR/zqY9vyR1nd3KJK1FFwLHtrePBS7omf+K9qxlzwTuXPynXpLGZAuwpaoua6fPo6ksumVxDLQlldqSJEkjZ+WQpKmW5Czgs8Bjk2xJcjxwEnBYkuuAw9ppgE8AXweuBz4A/McJRJY0w6rq28ANSR7bzjoU+DIrV2pL0tgkeWySK3ou30/y+iRvTnJjz/wjJp1V0nBNZ5teSWpV1dEr3HXoMssW8NrRJpKkHfpN4Mwk96OpsH4lzR9257YV3N8CXjLBfJJmVFV9FTgIIMkuwI3A+TTl1Luq6h0TjCdphKwckiRJGqOqugLYsMxd96rUlqQJOhT4WlV9M1nunB6S1hIrhyRJkiRJS70MOKtn+oQkrwC+AGyqqtt7F+7K2V5hdWcV7NIZ8bqSZRQ5Vvteb28/Gedr1ZX3BoafxcqhEVi3whk8Nq3fNtDZPSRJkiRp1Npury8E3tjOeh/wR0C11ycDr+pdpytne4XVnfG1S2fE60qWUeRY7e/h7Z3pcpxn+O3KewPDz+KA1JIkSZKkXs8DvlhVtwBU1S1VdU9V/ZjmpB4HTzSdpKGzckiSJEmS1OtoerqUJdm3574XAVePPZGkkVp1+70kDwAuBe7fPs55VfWmJI8Ezgb2Ar4IvLyqfjSMsJIkSZKk0Unyc8BhwKt7Zv+XJAfRdCvbvOQ+SWvAIJ077waeU1Vbk9wX+EySvwZ+i+Y0h2cneT9wPE0fVUmSJElSh1XVD4GHLpn38gnFkTQmq+5WVo2t7eR920sBzwHOa+efARw1UEJJkiRJkiSNzEBjDiXZJckVwK3ARcDXgDuqavEcc1uA/QaLKEmSJEmSpFEZ6JyBVXUPcFCSPYHzgccvt9hy6ybZCGwEmJubY2FhYVUZtm7duup1R2XT+m3Lzp/bbeX7usas/duZ/a+L+6skSZIkabYNVDm0qKruSLIAPBPYM8mubeuh/YGbVljnVOBUgA0bNtT8/PyqnnthYYHVrjsqx5348WXnb1q/jZOvGspLPnJm7d/mY+b7XraL+6skSZIkabatultZkoe1LYZIshvwK8C1wCXAi9vFjgUuGDSkJEmSJEmSRmOQ5hb7Amck2YWmkuncqvpYki8DZyf5Y+BLwGlDyClJkiRJkqQRWHXlUFVdCTx1mflfBw4eJJQkSZIkSZLGY6CzlUmSJEmSJGm6WTkkSZIkSZI0w6wckiRJkiRJmmFWDkmSJEmSJM0wK4ckSZIkSZJmmJVDkiRJkiRJM8zKIUmSpDFLskuSLyX5WDv9yCSXJbkuyTlJ7jfpjJIkaXZYOSRJkjR+rwOu7Zl+O/CuqjoQuB04fiKpJEnSTLJySJIkaYyS7A88H/hgOx3gOcB57SJnAEdNJp0kSZpFu046gCRJ0oz5U+B3gD3a6YcCd1TVtnZ6C7Dfcism2QhsBJibm2NhYWG0SVewaf22HS+0grndBlt/kuZ2Y2Kv+aC2bt06tdlh+vNLUtdZOSRJM2TdiR/va7lN67dxXJ/Lbj7p+YNEkmZKkhcAt1bV5UnmF2cvs2gtt35VnQqcCrBhw4aan59fbrGR67d8WM6m9ds4+arpPATdtH4bL53Qaz6ohYUFJrW/DMO0558mSTYDdwH3ANuqakOSvYBzgHXAZuClVXX7pDJKGj67lUmSJI3PIcAL2x9fZ9N0J/tTYM8kizUm+wM3TSaeJAHwy1V1UFVtaKdPBC5ux0W7uJ2WtIZYOSRJkjQmVfXGqtq/qtYBLwM+XVXHAJcAL24XOxa4YEIRJWk5R9KMhwaOiyatSdPZpleSJGlteQNwdpI/Br4EnDbhPJJmVwGfSlLAf2+7s85V1c0AVXVzkn2WrrTaMdFGMQ7ZasanGve4VlfdeOeK983tBqecufP/Eazf78GDRLqXUbwmq32vt7efjPN969L4Z8POYuWQJEnSBFTVArDQ3v46cPAk80hS65CquqmtALooyVf6WWm1Y6KdcuYFQx+HbPMx/T13r3GPa7W9sdtWOzbbarZ7e0bxmqx2zLrtvSbD3u7t6dL4Z8POsupuZUkOSHJJkmuTXJPkde38vZJclOS69vohQ0srSZIkSRqZqrqpvb4VOJ+m4vqWJPsCtNe3Ti6hpFEYpIp2G7Cpqr6YZA/g8iQXAcfRDFZ2UpITaQYre8PgUSVJkqTJ6vesj/3yjI/qkiS7A/epqrva288F3gJcSDMe2kk4Lpq0Jq26cqjtc7rY7/SuJNcC+9EMVjbfLnYGTXNpK4ckSZIkqdvmgPOTQPNb8S+r6pNJ/g44N8nxwLeAl0wwo6QRGErnziTrgKcCl9HHYGXtOqsasGypLg0ItWilgbJGMdjaqJi1fzuz/3Vxf5UkSZLgJ+OfPWWZ+d8DDh1/IknjMnDlUJIHAh8BXl9V329rmXdotQOWLdWlAaEWrTTI1moHFpsEs/ZvZwZA6+L+ulYl2QzcBdwDbKuqDUn2As4B1gGbgZdW1e2TyihJkiRJXbDqAakBktyXpmLozKr6aDvbwcokdcUvV9VBVbWhnT6RZky0A4GL22lJkiRJmmmDnK0swGnAtVX1zp67FgcrAwcrk9QtR9KMhUZ7fdQEs0iSJElSJwzScugQ4OXAc5Jc0V6OoBnB/rAk1wGHtdOSNG4FfCrJ5e0YZ7BkTDRg2THRJEmSJGmWDHK2ss8AKw0w5GBlkibtkKq6qR0U/6IkX+l3xdUOmD/swdFHMXh5v/l2ZlumYZD1tTYYvNsjSZKkYZqOEYclaSdV1U3t9a1JzgcOph0TrT2T4opjoq12wPxTzrxgqIOj78xg5/1aacD8pXZmoPdR5By2tTYYvNsjSZKkYRpoQGpJ6qIkuyfZY/E28FzgahwTTZIkSZLuxZZDktaiOeD8Ztx8dgX+sqo+meTvgHOTHA98C3jJBDNKkiRJUidYOSRpzamqrwNPWWb+93BMNEmSJEn6GXYrkyRJkiRJmmFWDkmSJEmSJM0wK4ckSZIkSZJmmJVDkiRJkiRJM8wBqaUBrTvx430vu2n9No7rY/nNJz1/kEiSJEmSJPXNyiFJ0pp31Y139lUxuzOsxJUkSdJaYbcySZKkMUlyQJJLklyb5Jokr2vn75XkoiTXtdcPmXRWSZI0O6wckiRJGp9twKaqejzwTOC1SZ4AnAhcXFUHAhe305IkSWNh5ZAkSdKYVNXNVfXF9vZdwLXAfsCRwBntYmcAR00moaRZtZ2WjW9OcmOSK9rLEZPOKmn4HHNIkiRpApKsA54KXAbMVdXN0FQgJdlnhXU2AhsB5ubmWFhYGEvWpTat37bqded2G2z9SRpF9nG9h1u3bp3Y/jIM055/Siy2bPxikj2Ay5Nc1N73rqp6xwSzSRqxgSqHknwIeAFwa1U9qZ23F3AOsA7YDLy0qm4fLKYkSdLakeSBwEeA11fV95P0tV5VnQqcCrBhw4aan58fWcbtGWSA903rt3HyVdP5/+Qosm8+Zn6oj7eShYUFJrW/DMO0558GbQX1YiX1XUkWWzZKmgGDfrudDrwX+HDPvMU+8yclObGdfsOAzzMyO3MackmSpEEluS9NxdCZVfXRdvYtSfZtWw3tC9w6uYSSZt2Slo2HACckeQXwBZrWRff683+1LRu70iJv3K3TtrfNq31Nhp1/FK/Jat/r7b0m43zfutSKcdhZBqocqqpL24Kj15HAfHv7DGCBDlcOSZIkjUuaJkKnAddW1Tt77roQOBY4qb2+YALxJGm5lo3vA/4IqPb6ZOBVS9dbbcvGU868oBMt8sbdOm17LTBX20px2C0RR/GarLbl6fZek3G1wIRutWIcdpZRtOntq8+8JEnSDDoEeDlwVZIr2nm/S1MpdG6S44FvAS+ZUD5JM2y5lo1VdUvP/R8APjaheNLUGkWPpdMP332ojzexDt/DGlBx0KZU4xwQcZoGYDTraPSbtStNFSVJw1VVnwFWGmDo0HFmkaReK7VsXOzy2k6+CLh6EvkkjdYoKof66jM/rAEVB21KNciAijtrmgZgNOvlv008AAAgAElEQVRo9Jt1nE0jJUmSJFZu2Xh0koNoupVtBl49mXiSRmkUv6jtMy9JkiRJU2Q7LRs/Me4sksbvPoOsnOQs4LPAY5NsafvJnwQcluQ64LB2WpIkSZIkSR006NnKjl7hLvvMS5IkSZIkTYGBWg5JkiRJkiRpuk3HKL6SJM2Afk9zumn9tr5OqLD5pOcPGklrxChOoStJktYOWw5JkiRJkiTNMCuHJEmSJEmSZpiVQ5IkSZIkSTPMyiFJkiRJkqQZZuWQJEmSJEnSDLNySJIkSZIkaYZZOSRJkiRJkjTDrBySJEmSJEmaYVYOSZIkSZIkzbBdJx1A0r2tO/HjQ3/MzSc9f+iPKUmSJEmaflYOSZIkSWvIcn8ybVq/jeMG+PPJP5kkaW2zW5kkSZIkSdIMs+WQJEnq2yi6vZ5++O5Df0xpWoziMyVJ0s4aWcuhJIcn+WqS65OcOKrnkaSdZfkkqassnyR1leWTtLaNpOVQkl2APwMOA7YAf5fkwqr68qCPvfTflUH7T0uaLaMsnyRpEJZPkrrK8kla+0bVrexg4Pqq+jpAkrOBIwELD0mTZvkkqassn6QBeLbXkbJ8kta4VNXwHzR5MXB4Vf16O/1y4BlVdULPMhuBje3kY4GvrvLp9ga+O0DccTLraJh1uB5RVQ+bdIhRGXH5NA3vb7/W0raA29N1/W6P5dPwjp8maZr3X7NPTtfzWz5N//FTV3JAd7J0JQd0J0tXcsCQj59G1XIoy8z7mVqoqjoVOHXgJ0q+UFUbBn2ccTDraJhVO2lk5dNaen/X0raA29N1a217BjC246dJmub32+yTM+3514A1f/zUlRzQnSxdyQHdydKVHDD8LKMakHoLcEDP9P7ATSN6LknaGZZPkrrK8klSV1k+SWvcqCqH/g44MMkjk9wPeBlw4YieS5J2huWTpK6yfJLUVZZP0ho3km5lVbUtyQnA/wJ2AT5UVdeM4rmYrqbVZh0Ns6pvIy6f1tL7u5a2Bdyerltr27MqYz5+mqRpfr/NPjnTnn+qzcjxU1dyQHeydCUHdCdLV3LAkLOMZEBqSZIkSZIkTYdRdSuTJEmSJEnSFLBySJIkSZIkaYZNTeVQkgck+XySv09yTZI/bOc/MsllSa5Lck47QFonJNklyZeSfKyd7nLWzUmuSnJFki+08/ZKclGb96IkD5l0ToAkeyY5L8lXklyb5FldzJrkse3ruXj5fpLXdzGrBpPk8CRfTXJ9khMnnWcQST6U5NYkV086yzAkOSDJJW1ZcU2S10060yBW+i6cZku/KzXdVvrMrfTdl8Z72vLzyiRPm2D2nTrWTHL/dvr69v51k8q+qN9jz45m7/tYtEv7jfq3o+Olce2XfeQ4Lsl3eo7hf31EObZ7zDWu/byPHPNJ7ux5Pf5gFDna59rhcds4Xpc+c4zldVnpu2nJMkP57ExN5RBwN/CcqnoKcBBweJJnAm8H3lVVBwK3A8dPMONSrwOu7ZnuclaAX66qg6pqQzt9InBxm/fidroL3g18sqoeBzyF5jXuXNaq+mr7eh4EPB34IXA+Hcyq1UuyC/BnwPOAJwBHJ3nCZFMN5HTg8EmHGKJtwKaqejzwTOC1U/7+rPRdOM2Wfldquq30mVvpu+95wIHtZSPwvvFH/omdPdY8Hri9qh4NvKtdbtL6PfbsYnbo/1i0S/uN+tDn8dLI98udOG47Z/E4vqo+OOwcrdPZ/jHXuPbzHeUA+N89r8dbRpQD+jtuG8fr0u/x4zhel36O/Yby2ZmayqFqbG0n79teCngOcF47/wzgqAnEu5ck+wPPBz7YToeOZt2OI2lyQkfyJnkQ8GzgNICq+lFV3UEHsy5xKPC1qvom3c+qnXMwcH1Vfb2qfgScTfMeT6WquhS4bdI5hqWqbq6qL7a376L50bTfZFOt3na+C6fS0u9KTb/tfOZW+u47Evhwu29/Dtgzyb5jjg2s6lizd5vOAw5tj/cmYiePPTuVfTs6v9+ob/0cL41jv+zMcVsfx1xj2c+7dOzX53HbyF+XLh0/9nnsN5TPztRUDsFPmspeAdwKXAR8Dbijqra1i2yhOwf9fwr8DvDjdvqhdDcrNDvYp5JcnmRjO2+uqm6G5gMC7DOxdD/1KOA7wJ+naTb9wSS7082svV4GnNXe7npW7Zz9gBt6prv22VarbWL7VOCyySYZzNLvwqqa5u1Z+l2pNWTJZ26l775OlaE7eaz5k+zt/XfSHO9Nys4ce3YtO+zcsWin9hv1pZ/3bBz7Zb/7zr9tuyydl+SAIWfoV5f282e13Zr+OskTx/GE2zluG+vrsoPjx7G8Ln0c+w3lszNVlUNVdU/bRWd/mlrfxy+32HhT3VuSFwC3VtXlvbOXWXTiWXscUlVPo2mm99okz550oBXsCjwNeF9VPRX4AR3vlpWmf/8Lgf8x6Swaia5/tgUkeSDwEeD1VfX9SecZxNLvwiRPmnSm1Vjhu1JrxE585jpVhu7ksWZnsq/i2LMz2XvszLFoF/Nr+/p5z8bxvvbzHP8TWFdVTwb+hp+2yBi3ruznXwQe0XZrOgX4q1E/4Q6+Q8b2uuwgx9helz6O/YbymkxV5dCithvRAk3/vz2T7NretT9w06Ry9TgEeGGSzTRNFZ9D829OF7MCUFU3tde30oyLczBwy2ITvfb61skl/IktwJae2tLzaCqLuph10fOAL1bVLe10l7Nq520Bev9R6tRnW5DkvjRf7GdW1UcnnWdYer4Lp3WMqHt9Vyb5i8lG0jCs8Jlb6buvk2Von8eaP8ne3v9gJtc1Y2ePPbuUHdjpY9FO7jfarn7es3HslzvMUVXfq6q728kP0IwdOgmd2M+r6vuL3Zqq6hPAfZPsParn6+O4bSyvy45yjPt1aZ9npWO/oXx2pqZyKMnDkuzZ3t4N+BWavn+XAC9uFzsWuGAyCX+qqt5YVftX1Tqa7kSfrqpj6GBWgCS7J9lj8TbwXOBq4EKanNCRvFX1beCGJI9tZx0KfJkOZu1xND/tUgbdzqqd93fAgWnOCHM/ms/8hRPOpFbb3/o04Nqqeuek8wxqhe/Cr0w21eqs8F35axOOpQFt5zO30nffhcAr0ngmcOdiN6JxW8WxZu82vZhmH55I65VVHHt2Jjus6li0M/uN+tbP8dI49ssd5lgyfs0LmdxJEzqxnyf5+cXxa5IcTFOH8L0RPVc/x20jf136yTGu16XPY7/hfHaqaiouwJOBLwFX0nxZ/EE7/1HA54Hrabrt3H/SWZfkngc+1uWsba6/by/XAL/Xzn8ozZkhrmuv95p01jbXQcAX2n3hr4CHdDjrz9EUEg/umdfJrF4Gep+PAP6BZmyK35t0ngG35SzgZuCfaf6FOH7SmQbcnn9F06z2SuCK9nLEpHMNsD3LfhdO+6X3u9LLdF9W+syt9N1H0xT+z9ry8ypgwwSz79SxJvCAdvr69v5HTfr1b3Pt8Niza9l39li0S/uNl516n+91vAS8BXhhe3ss+2UfOd7W7od/T1PB+rgR5bjXMRfwGuA17f1j2c/7yHFCz+vxOeBfjnAfWek7ZKyvS585xvK6sPJ309A/O2kfTJIkSZIkSTNoarqVSZIkSZIkafisHJIkSZIkSZphVg5JkiRJkiTNMCuHJEmSJEmSZpiVQ5IkSZIkSTPMyiFJkiRJkqQZZuWQJEmSJEnSDLNySJIkSZIkaYZZOSRJkiRJkjTDrBySJEmSJEmaYVYOSZIkSZIkzTArhyRJkiRJkmaYlUOSJEmSJEkzzMohSZIkSZKkGWblkCRp6iV5bJIvJbkryW1J/njSmSTNhiSnb6/MSVJJHj3iDOva59l1lM8jSVq7rBySJK0FvwMsVNUewIWTDiNJkjRtrGiebVYOSZLWgkcA10w6hCRJ0qRZuaPVsHJIACR5eJKPJPlOkm8k+U/t/E8kOblnuXOSfKi9/YtJPp3ke0m+m+TMJHv2LLs5yX9OcmWSO9t1H9Bz/+8kuTnJTUl+fRzNriWtPUk+Dfwy8N4kW4H7AXsnuajtZva3SR7RLpsk70pya1suXZnkSZPML2k6JHl8koUkdyS5JskLV1jut3uOb1615L7Tk7x/ufKpvf9x7X23Jflqkpf23Pf8tvvs95PckOTN28n6b9vjMMs3aUa0n/k3JLkS+EGSX1ju91277MFJvtCWJ7ckeWd716Xt9R1JtiZ5Vrv8q5Jcm+T2JP9rSbn1xJ5y65Ykv9vO3y3JGe0617a//baM6eXQKlg5JJLcB/ifwN8D+wGHAq9P8qvAq4CXJ3lOkmOAfwG8bnFV4G3Aw4HHAwcAb17y8C8FDgceCTwZOK59zsOB3wJ+BXg08Euj2TpJa11VPQf438AJVfVA4EfAMcAfAXsDVwBntos/F3g28BhgT+DfAd8bd2ZJ0yXJfWmOlT4F7AP8JnBmkscuWe5w4D8DhwEH0hznLLVs+ZRkd+Ai4C/b5zga+G9Jntiu9wPgFTRl1/OB30hy1DJZXwm8HfiVqrp69VstaQodTVM+7AWcz/K/7wDeDby7qh4E/CJwbjv/2e31nlX1wKr6bFvO/C7w/wAPoznmOgsgyR7A3wCfpPlN+Gjg4vYx3gSsAx5FUyb+2gi2V0Nk5ZCgqfB5WFW9pap+VFVfBz4AvKyqvg28BjiDphB5RVXdBVBV11fVRVV1d1V9B3gn967keU9V3VRVt9EcVB3Uzn8p8OdVdU1V/RD4w5FvpaRZ8vGqurSq7gZ+D3hWkgOAfwb2AB4HpKquraqbJxlU0lR4JvBA4KT2WOnTwMdofoj1Wjy+ubqqfsC9/zSDlcunFwCbq+rPq2pbVX0R+AjwYoCqWqiqq6rqx1V1Jc2Ps6XHXa8HfhuYr6rrh7HhkqbKe6rqBuBJrPD7rl3un4FHJ9m7qrZW1ee285ivBt7WHjNtA/4EOKhtPfQC4NtVdXJV/VNV3VVVl7XrvRT4k6q6vaq2AO8ZwfZqiKwcEjRjdTy8bSZ9R5I7aGqH59r7PwbsAny1qj6zuFKSfZKcneTGJN8H/oLmX7Be3+65/UOaAytoapZv6Lmv97YkDeonZUpVbQVuAx7e/qB7L/BnwC1JTk3yoAlllDQ9Hg7cUFU/7pn3TZp/5O+13JJlllq2fKI5HnvGkuOxY4CfB0jyjCSXtF1E7qT5827pcddvA3/W/hCTNHsWy5cd/b47nqYV9VeS/F2SF2znMR8BvLvncW6j6UGyH03Pka+tsJ6/96aMlUOC5oP6jaras+eyR1Ud0d7/VuBaYN8kvf+QvQ0o4Mltk8Rfoyko+nEzsH/P9AGDbYIk/YyflClJHkjTvPomgKp6T1U9HXgizYHRb08koaRpchNwQNsVf9EvADcuWe5mfvaY5heWeayVyqcbgL9dcjz2wKr6jXbxv6Q5G+MBVfVg4P3c+7jrucDvJ/m3O7d5ktaIaq+3+/uuqq6rqqNpurC+HTiv7dpayzzmDcCrlzzWblX1f9v7fnGFLP7emzJWDgng88D32wHMdkuyS5InJfkXSZ4NvJKmj/srgFOSLP5LtgewlWbAsv3YuR9Y5wKvbAd3/DngD4a3OZLEEUn+VZL70YztcVlV3dCWa89oxw/5AfBPwD0TTSppGlxGU2b8TpL7JpkH/g1w9pLlzgWOS/KE9vjmTcs81rLlE01L7cckeXn7HPdty6zHt+vtAdxWVf+U5GDg3y/z2NfQjPX4Z1lhwGxJM2HF33cASX4tycPa1pB3tOvcA3wH+DHNOEGL3g+8cXH8syQPTvKS9r6PAT+f5PVJ7p9kjyTPaO87t13vIe1vxRNGusUamJVDoqruoTnAOQj4BvBd4IPAvsCHaQZ5vbHtUnYa8OdJQjNO0NOAO4GPAx/dief8a5p+p5cA1wOfbe+6exjbJGnm/SXNj7LbgKfTdM0AeBBNn/vbabp7fA94xyQCSpoeVfUj4IXA82iOk/4bzTiMX1my3F8Dfwp8mub45tPLPNyy5VM7puNzacYEuYmma/7bgfu36/1H4C1J7qL5U+1cllFVf08zDsgHkjxvdVssaZpt5/fdg9tFDgeuSXOW13fTjDX7T+1YsG8F/k/bjeyZVXU+TVl0djuUyNU0ZeFiuXVY+1zfBq6jOYMswFuALe3z/w1wHv7W67RULddyTBqv9l+xq4H7twOdSZIkrSlJTge2VNXvTzqLJI1Tkt+gqYTyLNUdZcshTUySFyW5X5KH0NRG/08rhiRJkiRpuiXZN8khSe6T5LHAJuD8SefSyqwc0iS9mqZf69do+rj+xvYXlyRJkiRNgfsB/x24i6aL7QU0XXLVUXYrkyRJkiRJmmG2HJIkSZIkSZphVg5JkiRJkiTNsF0nHQBg7733rnXr1vW17A9+8AN233330QYakBmHZxpyTkNG6D/n5Zdf/t2qetgYIk0Fy6fxm4aMMB05pyEjWD6t1rSVT13I0JUcZuhWjmFksHz6WdNWPg3TWtqetbQtMLvb03f5VFUTvzz96U+vfl1yySV9LzspZhyeacg5DRmr+s8JfKE6UC505WL5NH7TkLFqOnJOQ8Yqy6fVXqatfOpChqpu5DDDT3UhxzAyWD5Nd/k0TGtpe9bStlTN7vb0Wz7ZrUySJEmSJGmGWTkkSZI0ZEk+lOTWJFf3zHtzkhuTXNFejui5741Jrk/y1SS/OpnUkiRpVlk5JEmSNHynA4cvM/9dVXVQe/kEQJInAC8Dntiu89+S7DK2pJIkaeZZOSRJkjRkVXUpcFufix8JnF1Vd1fVN4DrgYNHFk7SzLN1o6Sldni2siQHAB8Gfh74MXBqVb07yV7AOcA6YDPw0qq6PUmAdwNHAD8EjquqL44mviRJ0lQ5IckrgC8Am6rqdmA/4HM9y2xp591Lko3ARoC5uTkWFhb6etKtW7f2veyodCFDV3KYoVs5upBhAk4H3kvzO6/Xu6rqHb0zlrRufDjwN0keU1X3jCOopPHo51T222gOXr6YZA/g8iQXAccBF1fVSUlOBE4E3gA8DziwvTwDeF97PRRX3Xgnx5348WE9HJtPev7QHkvSbLN8krQD7wP+CKj2+mTgVUCWWbaWe4CqOhU4FWDDhg01Pz/f1xOfcuYFnPyZH+x84hWspnxaWFig37yj1IUcZuhWji5kGLequjTJuj4X/0nrRuAbSRZbN352RPHUEcM+tgWPb7tsh93KqurmxZY/VXUXcC3Nv1lHAme0i50BHNXePhL4cHvWtM8BeybZd+jJJc28JAckuSTJtUmuSfK6dr7NoiV1TlXdUlX3VNWPgQ/w065jW4ADehbdH7hp3PkkiaZ145Vtt7OHtPP2A27oWWbF1o2Splc/LYd+oq1dfipwGTBXVTdDU4GUZJ92sZUKj5sHDStJS6zUshFsFi2pY5Lsu3jsBLwIWBzr40LgL5O8k6ZsOhD4/AQiSpptA7VunOZur8O0lrZnbjfYtH7bUB9zkq/NWnpvYPjb03flUJIHAh8BXl9V32+GFlp+0WXmDa3wGPYOOoqdYxp2umnICNORcxoywvTk3Bntj6zFSuq7kiy2bFyJzaIljUWSs4B5YO8kW4A3AfNJDqI5LtoMvBqgqq5Jci7wZZpK79daaS1p3KrqlsXbST4AfKyd7Kt142q7va61bn1raXtOOfMCTr5qp9qT7NDmY+aH+ng7Yy29NzD87enrnU5yX5qKoTOr6qPt7FsW/wFru43d2s4faeEx7B10FDvnNOx005ARpiPnNGSE6cm5WktaNh7CgIO+StIgquroZWaftp3l3wq8dXSJJGn7bN0ozbZ+zlYWmoOZa6vqnT13XQgcC5zUXl/QM/+EJGfTDER9Z08hI0lDt0zLxok0i7Zl43BMQ0aYjpzTkBGmJ6ckrRVdat3ooMdSN/TTBOcQ4OXAVUmuaOf9Lk2l0LlJjge+Bbykve8TNKexv57mVPavHGpiSeqxXMvGSTWLtmXjcExDRpiOnNOQEaYnpyStFbZulLTUDn/FVNVnWP7fdoBDl1m+gNcOmEuSdmillo02i5YkSZKk/g13dClJGq+VWjYe7aCvkiRJktQfK4ckTa3ttGz8xHbWsVm0JEmSJPW4z6QDSJIkSZIkaXKsHJIkSZIkSZphVg5JkiRJkiTNMCuHJEmSJEmSZpiVQ5IkSZIkSTPMyiFJkiRJkqQZZuWQJEmSJEnSDLNySJIkSZIkaYZZOSRJkiRJkjTDrBySJEmSJEmaYVYOSZIkDVmSDyW5NcnVPfP+a5KvJLkyyflJ9mznr0vyj0muaC/vn1xySZI0i6wckiRJGr7TgcOXzLsIeFJVPRn4B+CNPfd9raoOai+vGVNGSZIkwMohSZKkoauqS4Hblsz7VFVtayc/B+w/9mCSJEnLsHJIkiRp/F4F/HXP9COTfCnJ3yb515MKJWnts9urpOXsOukAkiRJsyTJ7wHbgDPbWTcDv1BV30vydOCvkjyxqr6/zLobgY0Ac3NzLCws9PWcc7vBpvXbdrxgn/p93l5bt25d1XrD1oUcZuhWji5kGLPTgfcCH+6ZdxHwxqraluTtNN1e39De97WqOmi8ESWNm5VDkiRJY5LkWOAFwKFVVQBVdTdwd3v78iRfAx4DfGHp+lV1KnAqwIYNG2p+fr6v5z3lzAs4+arhHfZtPqa/5+21sLBAv3lHqQs5zNCtHF3IME5VdWmSdUvmfapn8nPAi8eZSdLkWTkkSZI0BkkOp/kn/peq6oc98x8G3FZV9yR5FHAg8PUJxZSkVwHn9Ew/MsmXgO8Dv19V/3u5lbrSshFW17pxWNZSSzTfm24b9vZYOSRJkjRkSc4C5oG9k2wB3kTTTeP+wEVJAD7Xnpns2cBbkmwD7gFeU1W3LfvAkjRCg3R77UrLRlhd68ZhWUst0Xxvum3Y22PlkCRJ0pBV1dHLzD5thWU/AnxktIkkafsG7fYqabp5tjJJkiRJmmE93V5fuLTba5Jd2tt2e5XWMCuHJE2tJAf8/+zdf7xldX3f+9c7+COIJIjIyQRIRu8dbTUTiZ6ivbTpsSQGMGHw0WihRAaljkmhadK5t46mj2hjvCVG4o2kJQ6RzpAiQmPIECFGwvWUaytGIQooWkcygYEJY5QgI6np4Of+sdfo5nBmZs+Z/WOtvV/Px+M89t7f/V17vdfe53z3Pp+9vmsl+ViSe5J8Lsm/atqPTXJzki81l89q2pPkvUm2N6dqfclkt0CSJGm8mmmvnwBekGRnkgvpnb3saHrTXvtPWf+jwJ1JPgv8Hk57laaW08okddleYGNV3ZHkaOD2JDcDFwC3VNUlSTYBm+h9G3YGvW+81gAvAy5vLiVJkmaC014lLcc9hyR1VlXtqqo7muuPAvcAJwDrgK1Nt63A2c31dcBV1XMbcEySVWOOLUmSJEmt4p5DkqZCktXAjwCfBOaqahf0CkhJjm+6nQDc37fYzqZt15LHasWpWEdxqs0unMKzCxmhGzm7kBG6k1OSJGlaWRyS1HlJnklvl+dfqKqvN6eIXrbrMm31pIaWnIp1FKf67MIpPLuQEbqRswsZoTs5JUmSppXTyiR1WpKn0isMXV1Vv980P7Rvulhzubtp3wmc1Lf4icCD48oqSZIkSW100OJQkiuT7E5yd1/b25M80BzJ/jNJzuy77y3NmYC+mOQnRhVcktLbRej9wD1V9Rt9d90ArG+urwe29bWf35y17OXAI/umn0mSJEnSrBpk/sMWeqc2vGpJ+3uq6t39DUleCJwDvAj4fuBPkjy/qh4fQlZJWupU4HXAXUk+07S9FbgEuK45Net9wGua+24CzgS2A48Brx9vXEmSJElqn4MWh6rq1uZAr4NYB3ywqr4J/HmS7cApwCdWnFCS9qOqPs7yxxECOG2Z/gVcNNJQkiRJktQxh3Pk1IuTnA98GthYVQ/TO+vPbX199p0J6Ek8G9BkdSEjdCNnFzJCd3JKkiRJksZrpcWhy4F30DvLzzuAS4E3MOCZgMCzAU1aFzJCN3J2ISN0J6ckSZIkabxWdLayqnqoqh6vqm8BV9CbOgaeCUiSJEmSJKlTVlQc2neK6MargX1nMrsBOCfJ05M8F1gD/OnhRZQkSZIkSdKoHHR+VpJrgAXguCQ7gbcBC0lOpjdlbAfwJoCq+lyS64DPA3uBizxTmSRJkiRJUnsNcrayc5dpfv8B+r8TeOfhhJIkSZIkSdJ4rGhamSRJkg4syZVJdie5u6/t2CQ3J/lSc/mspj1J3ptke5I7k7xkcsklSdKssTgkSZI0GluA05e0bQJuqao1wC3NbYAz6B2rcQ2wgd6ZYSVJksbC4pAkSdIIVNWtwNeWNK8DtjbXtwJn97VfVT23AccsOQGIJA2NezZKWsrikCRJ0vjMVdUugOby+Kb9BOD+vn47mzZJGoUtuGejpD4HPSC1JEmSRi7LtNWTOiUb6P1zxtzcHIuLiwM9+NyRsHHt3sPJ9wSDrrffnj17VrTcsLUhhxnalaMNGcatqm5NsnpJ8zp6Z6mG3p6Ni8Cb6duzEbgtyTFJVu0rdEuaDhaHJEmSxuehff9UNdPGdjftO4GT+vqdCDy4dOGq2gxsBpifn6+FhYWBVnrZ1du49K7hfezbcd5g6+23uLjIoHlHqQ05zNCuHG3I0BJP2LMxycH2bLQ4JE0Ri0OSJEnjcwOwHrikudzW135xkg8CLwMe8Vt5SS3RqT0bYWV7Nw7LNO2J5mvTbsPeHotDkiRJI5DkGnpTNI5LshN4G72i0HVJLgTuA17TdL8JOBPYDjwGvH7sgSXNuqnYsxFWtnfjsEzTnmi+Nu027O2xOCRJkjQCVXXufu46bZm+BVw02kSSdEDu2SjNMItDkiRJkjRD3LNR0lIWhyRJkiRphrhno6SlvmvSASRJkiRJkjQ5FockSZIkSZJmmMUhSZ2V5Moku5Pc3df29iQPJPlM83Nm331vSbI9yReT/MRkUkuSJElSu1gcktRlW0LvX58AACAASURBVIDTl2l/T1Wd3PzcBJDkhcA5wIuaZf5jkiPGllSSJEmSWsrikKTOqqpbga8N2H0d8MGq+mZV/Tm9M26cMrJwkiRJktQRFockTaOLk9zZTDt7VtN2AnB/X5+dTZskSZIkzTRPZS9p2lwOvAOo5vJS4A1Alulbyz1Akg3ABoC5uTkWFxcHWvHckbBx7d5DT7wfg673UOzZs2ckjztMXcgI3cjZhYzQnZySJEnTyuKQpKlSVQ/tu57kCuDDzc2dwEl9XU8EHtzPY2wGNgPMz8/XwsLCQOu+7OptXHrX8IbVHecNtt5Dsbi4yKDbMyldyAjdyNmFjNCdnJIkSdPKaWWSpkqSVX03Xw3sO5PZDcA5SZ6e5LnAGuBPx51PkiRJktrGPYckdVaSa4AF4LgkO4G3AQtJTqY3ZWwH8CaAqvpckuuAzwN7gYuq6vFJ5JYkSZKkNrE4JKmzqurcZZrff4D+7wTeObpEkiRJktQ9TiuTJEmSJEmaYRaHJEmSJEmSZpjFIUmSJEmSpBnmMYckSZLGJMkLgGv7mp4H/DJwDPBG4CtN+1ur6qYxx5MkSTPK4pAkSdKYVNUXgZMBkhwBPABcD7weeE9VvXuC8STNOAvY0uw66LSyJFcm2Z3k7r62Y5PcnORLzeWzmvYkeW+S7UnuTPKSUYaXJEnqsNOAL1fVX0w6iCRBr4BdVSdX1cnAS4HH6BWwoVfAPrn5sTAkTZlBjjm0BTh9Sdsm4JaqWgPc0twGOANY0/xsAC4fTkxJkqSpcw5wTd/ti5sv167c98WbJE2QBWxphhx0WllV3Zpk9ZLmdcBCc30rsAi8uWm/qqoKuC3JMUlWVdWuYQWWJEnquiRPA84C3tI0XQ68A6jm8lLgDcsst4HeF3DMzc2xuLg40PrmjoSNa/cedu59Bl1vvz179qxouWFrQw4ztCtHGzK01HIF7POBTwMbq+rhycSSNAorPebQ3L6CT1XtSnJ8034CcH9fv51N25OKQ13+cHMwXXiD6UJG6EbOLmSE7uSUpBlxBnBHVT0EsO8SIMkVwIeXW6iqNgObAebn52thYWGglV129TYuvWt4h5rccd5g6+23uLjIoHlHqQ05zNCuHG3I0DYrKWC35f87GM3/eIOaps/cvjbtNuztGfYBqbNMWy3Xscsfbg6mC28wXcgI3cg5ioyrN9041McD2HL6M1v/XErSDDmXvm/kl+xp/Wrg7mWXkqTxOOQCdlv+v4PR/I83qC78/zIoX5t2G/b2rPSVfmjfh5gkq4DdTftO4KS+ficCDx5OQEmSpGmS5BnAjwNv6mt+V5KT6X2ptmPJfZI0bhawpRmz0uLQDcB64JLmcltf+8VJPgi8DHjE4w1JkiR9R1U9Bjx7SdvrJhRHkp7AArY0mw5aHEpyDb2DTx+XZCfwNnpFoeuSXAjcB7ym6X4TcCawnd5pD18/gsySJEmSpBGwgC3NpkHOVnbufu46bZm+BVx0uKEkSZIkSZI0Ht816QCSJEmSJEmaHItDkiRJkiRJM8zikCRJkiRJ0gyzOCRJkiRJkjTDLA5JkiRJkiTNMItDkiRJkiRJM8zikKROS3Jlkt1J7u5rOzbJzUm+1Fw+q2lPkvcm2Z7kziQvmVxySZIkSWoHi0OSum4LcPqStk3ALVW1BriluQ1wBrCm+dkAXD6mjJIkSZLUWhaHJHVaVd0KfG1J8zpga3N9K3B2X/tV1XMbcEySVeNJKkmSJEntZHFI0jSaq6pdAM3l8U37CcD9ff12Nm2SJEmSNLOeMukAkjRGWaatntQp2UBv2hlzc3MsLi4O9OBzR8LGtXsPJ98TDLreQ7Fnz56RPO4wdSEjdCNnFzJCd3JKkiRNK4tDkqbRQ0lWVdWuZtrY7qZ9J3BSX78TgQeXLlxVm4HNAPPz87WwsDDQSi+7ehuX3jW8YXXHeYOt91AsLi4y6PZMShcyQjdydiEjdCenJEnStHJamaRpdAOwvrm+HtjW135+c9aylwOP7Jt+JkmSJEmzyj2HJHVakmuABeC4JDuBtwGXANcluRC4D3hN0/0m4ExgO/AY8PqxB5YkSZKklrE4JKnTqurc/dx12jJ9C7hotIkk6eCS7AAeBR4H9lbVfJJjgWuB1cAO4LVV9fCkMkqSpNnhtDJJkqTJeEVVnVxV883tTcAtVbUGuKW5LUljlWRHkruSfCbJp5u2Y5PcnORLzeWzJp1T0nBZHJIkSWqHdcDW5vpW4OwJZpE02yxeSzPGaWWSJEnjV8BHkxTwvuYsiXP7DpLfnG3x+KULJdkAbACYm5tjcXFxoJXNHQkb1+4dVnYuu3rbwTstk+FAy6094XsPJ9LA9uzZM/DzZobZyNGGDB2wjt4xHqFXvF4E3jypMJKGz+KQJEnS+J1aVQ82BaCbk3xhkIWaItJmgPn5+VpYWBhoZZddvY1L75rsx76Na/ceMMOO8xbGkmNxcZFBnzczzEaONmRomU4Xr4GJFvumqdjoa9Nuw94ei0OSJEljVlUPNpe7k1wPnAI8lGRV84/XKmD3RENKmlWdL16Pq9i8nGkqNvratNuwt8djDkmSJI1RkqOSHL3vOvBK4G7gBmB90209cOhztyTpMPUXr4EnFK8BLF5L08nikCRJ0njNAR9P8lngT4Ebq+ojwCXAjyf5EvDjzW1JGhuL19LsclqZJEnSGFXVvcCLl2n/KnDa+BNJ0rfNAdcngd7/ih+oqo8k+RRwXZILgfuA10wwo6QRsDgkSZIkSbJ4Lc0wp5VJkiRJkiTNMItDkiRJkiRJM8zikCRJkiRJ0gw7rGMOJdkBPAo8DuytqvkkxwLXAquBHcBrq+rhw4spSZKkabZ6041Df8wdl7xq6I8pSdI0GsaeQ6+oqpOrar65vQm4parWALc0tyVJkiRJktRCo5hWtg7Y2lzfCpw9gnVIkiRJkiRpCA63OFTAR5PcnmRD0zZXVbsAmsvjD3MdkiRJkiRJGpHDOuYQcGpVPZjkeODmJF8YdMGmmLQBYG5ujsXFxYGWmzsSNq7du5Ksyxp0vYdiz549I3ncYepCRuhGzlFkHObv+D5deC4lSZIkSeN3WMWhqnqwudyd5HrgFOChJKuqaleSVcDu/Sy7GdgMMD8/XwsLCwOt87Krt3HpXYdb0/qOHecNtt5Dsbi4yKDbMyldyAjdyDmKjBeM4KCcW04/qvXPpSRJkiRp/FY8rSzJUUmO3ncdeCVwN3ADsL7pth7YdrghJUmSJEmSNBqHswvOHHB9kn2P84Gq+kiSTwHXJbkQuA94zeHHlCRJkiRJ0iisuDhUVfcCL16m/avAaYcTSpIOV5IdwKPA48DeqppPcixwLbAa2AG8tqoenlRGSZIkSWqDUZzKXpLa4hVVdXJVzTe3NwG3VNUa4JbmtiRJkiTNNItDkmbJOmBrc30rcPYEs0iSJElSKwzvtF+S1C4FfDRJAe9rzpA4V1W7AJozKh6/3IJJNgAbAObm5lhcXBxohXNHwsa1e4eRHWDg9R6KPXv2jORxh6kLGaEbObuQEbqTU5IkaVpZHJI0rU6tqgebAtDNSb4w6IJNIWkzwPz8fC0sLAy03GVXb+PSu4Y3rO44b7D1HorFxUUG3Z5J6UJG6EbOLmSE7uQchiQnAVcB3wd8C9hcVb+Z5O3AG4GvNF3fWlU3TSalpFnk+CTNNotDkqZSVT3YXO5Ocj1wCvBQklXNXkOrgN0TDSlpFu0FNlbVHUmOBm5PcnNz33uq6t0TzCZptjk+STPM4pCkqZPkKOC7qurR5vorgV8BbgDWA5c0l9sml1LqptWbbhz6Y245/aihP2ZbNVNb901vfTTJPcAJk00lSY5P0qyzOCRpGs0B1yeB3jj3gar6SJJPAdcluRC4D3jNBDNKmnFJVgM/AnwSOBW4OMn5wKfpfXv/8DLLtOKYaCsxiQzLPT9tOMaVGdqVow0Z2mYl45OkbrM4JGnqVNW9wIuXaf8qcNr4E0nSEyV5JvAh4Beq6utJLgfeQe9g+u8ALgXesHS5thwTbSU2rt07/gx3fWOZHI9z6cef3D6oHZe86nASAe04zlYbMrQlRxsytMlKx6c2Fa8nWeybpmKjr027DXt7LA5JkiSNUZKn0vvH6+qq+n2Aqnqo7/4rgA9PKJ6kGXY441ObitejOKnHoKap2Ohr027D3p7vGtojSZIk6YDSm+/6fuCeqvqNvvZVfd1eDdw97mySZpvjkzTb3HNIkiRpfE4FXgfcleQzTdtbgXOTnExv2sYO4E2TiSdphjk+STPM4pAkSdKYVNXHgSxz103jzqKVGcYZ+zau3csFzeMM4xhG0jA4PkmzzWllkiRJkiRJM8zikCRJkiRJ0gyzOCRJkiRJkjTDLA5JkiRJkiTNMItDkiRJkiRJM8zikCRJkiRJ0gyzOCRJkiRJkjTDLA5JkiRJkiTNsKdMOoAkSZI0q1ZvunHoj7njklcN/TElSdPNPYckSZIkSZJmmMUhSZIkSZKkGWZxSJIkSZIkaYZZHJIkSZIkSZphHpBakiRJmiKDHOR649q9XHAIB8P2INeSNN3cc0iSJEmSJGmGjWzPoSSnA78JHAH8TlVdMqp1SdKhcHyS1FaOT5LayvFJWrlB9ug8VFtOP2qojzeSPYeSHAH8B+AM4IXAuUleOIp1SdKhcHyS1FaOT5LayvFJmn6j2nPoFGB7Vd0LkOSDwDrg8yNanyQNyvFJUls5PkmHYaXfzB/o+Esea+nbHJ+kKTeq4tAJwP19t3cCLxvRuiTpUDg+SWorxye11rCnRFh06RzHJ2nKjao4lGXa6gkdkg3AhubmniRfHPCxjwP+6jCyPUF+bViP9ARDzTgiXcgI3cjZhYy84tcGzvmDo84yYY5P7f997UJG6EbOLmR0fPqOzoxPK/HzLcjQlhxmeMJ7XKufi0N4L3Z8atH4NKLPUIOa+O/0EPnatNiwPz+Nqji0Ezip7/aJwIP9HapqM7D5UB84yaerav7w4o2WGYenCzm7kBG6k3MMHJ/MOBRdyNmFjNCdnGMw1eNTGzK0JYcZ2pWjDRk6YKrHp2Gapu2Zpm0Bt+dgRnUq+08Ba5I8N8nTgHOAG0a0Lkk6FI5PktrK8UlSWzk+SVNuJHsOVdXeJBcDf0zvVIdXVtXnRrEuSToUjk+S2srxSVJbOT5J029U08qoqpuAm0bw0Ie8q+IEmHF4upCzCxmhOzlHzvGp9bqQEbqRswsZoTs5R27Kx6c2ZIB25DDDd7QhRxsytN6Uj0/DNE3bM03bAm7PAaWqDt5LkiRJkiRJU2lUxxySJEmSJElSB7SyOJTk9CRfTLI9yaZl7n96kmub+z+ZZPX4Uw6U818n+XySO5PckmTsp7g8WMa+fj+dpJKM/ejtg2RM8trmufxckg+MO2OT4WCv9w8k+ViSP2te8zMnkPHKJLuT3L2f+5Pkvc023JnkJePO2HWOT+PL2NdvYuNTs/7Wj1GOT9qfQf/ORpzhgK/9mDKc1PwN3NP8nf6rCeX47iR/muSzTY5/N4kcTZYjmjHhwxNa/44kdyX5TJJPTyJDk+OYJL+X5AvN78ffn1SWadeVz1CDGGBbLkjyleb3+zNJ/vkkcg5qmt6jB9iWhSSP9L02vzzujIdikPevob0+VdWqH3oHOPsy8DzgacBngRcu6fMvgN9urp8DXNvSnK8AntFc/7lx5xwkY9PvaOBW4DZgvm0ZgTXAnwHPam4f39LXezPwc831FwI7JpDzR4GXAHfv5/4zgT8CArwc+OS4M3b5x/FpvBmbfhMbnw7huZzoGOX45M/h/G604bUfU4ZVwEua60cD/2NCz0WAZzbXnwp8Enj5hJ6Tfw18APjwhNa/AzhuUr8TfTm2Av+8uf404JhJZ5rGn658hhritlwA/Naksx7CNk3Ne/QA27IwqXFvhdtz0PevYb0+bdxz6BRge1XdW1V/C3wQWLekzzp6AznA7wGnJckYM8IAOavqY1X1WHPzNuDEtmVsvAN4F/A/xxmuMUjGNwL/oaoeBqiq3WPOCIPlLOB7muvfCzw4xny9AFW3Al87QJd1wFXVcxtwTJJV40k3FRyfxpixMcnxCboxRjk+aX8G/TsbqQFe+3Fk2FVVdzTXHwXuAU6YQI6qqj3Nzac2P2M/AGiSE4FXAb8z7nW3SZLvofeP5PsBqupvq+qvJ5tqanXlM9QgWjG2DtM0vUe34T1nmAZ8/xrK69PG4tAJwP19t3fy5I3/dp+q2gs8Ajx7LOmWydBYLme/C+lV88bpoBmT/AhwUlVNZJdiBnsenw88P8l/S3JbktPHlu47Bsn5duBnkuykdyaHfzmeaIfkUH9v9USOT8PThfEJujFGOT5pf3xOl9FMVfkRenvtTGL9RyT5DLAbuLmqJpHj/wH+DfCtCax7nwI+muT2JBsmlOF5wFeA/9RMsfudJEdNKMu068pnqEEMOrb+k2aKz+8lOWk80UZm2t5P/n4zvfePkrxo0mEGdYD3r6G8Pm0sDi1XHV76jcogfUZt4AxJfgaYB359pImWWfUybd/OmOS7gPcAG8eW6MkGeR6fQm/axgJwLvA7SY4Zca6lBsl5LrClqk6kt2vf7zbPcZu04W+nyxyfhqcL4xN0Y4xyfNL++JwukeSZwIeAX6iqr08iQ1U9XlUn09tj85QkPzTO9Sf5SWB3Vd0+zvUu49SqeglwBnBRkh+dQIan0Jt+cnlV/QjwDWAix+aaAV35DDWIQXL+IbC6qn4Y+BO+s0dUV3XltRnEHcAPVtWLgcuAP5hwnoEc5P1rKK9P2z4YQq/K1V9ZPZEn7/7+7T5JnkJvF/lx7zo2SE6S/BjwS8BZVfXNMWXb52AZjwZ+CFhMsoPe/MQbMt6Dvg76em+rqv9VVX8OfJHeP2LjNEjOC4HrAKrqE8B3A8eNJd3gBvq91X45Pg1PF8Yn6MYY5fik/fE57ZPkqfQ+WF9dVb8/6TzN9KVFYNx7G54KnNWMrR8E/nGS/zzmDFTVg83lbuB6elN1xm0nsLNv763fo1cs0vB15TPUIA66LVX11b7PVlcALx1TtlGZmveTqvr6vum9VXUT8NQkbftM9AQDvH8N5fVpY3HoU8CaJM9N8jR6ByO7YUmfG4D1zfWfBv7fao7ENEYHzdlMiXgfvX+8JnGcnANmrKpHquq4qlpdVavpHXfkrKoa5xkjBnm9/4DewXNp/nCfD9w7xowwWM77gNMAkvxdev98fWWsKQ/uBuD85oj2Lwceqapdkw7VIY5PY8rYkvHpoDkbkx6jHJ+0P4P8bsyE5rgl7wfuqarfmGCO5+zbszDJkcCPAV8YZ4aqektVndiMrefQe5/6mXFmSHJUkqP3XQdeCYz9bHZV9ZfA/Ule0DSdBnx+3DlmRFc+Qw1ikM9Z/cd7OYvecWK6bGreo5N8375jWSU5hV5N5KuTTbV/A75/DeX1ecph5ByJqtqb5GLgj+kdCf7Kqvpckl8BPl1VN9B7cn43yXZ61eRzWprz14FnAv+l+f27r6rOalnGiRow4x8Dr0zyeeBx4P+qqrH+AQ+YcyNwRZJfpLcb3wXjfkNLcg29qS3HpXdskbfRO9glVfXb9I41ciawHXgMeP0483Wd49PYM05cF8Yoxyftz/5+N8adY7nXvqreP+YYpwKvA+5K73g/AG9tvjUep1XA1iRH0PuH5LoJH1dtUuaA65v3n6cAH6iqj0woy78Erm7+yb8Xx56R6MpnqEEMuC0/n+QsYC+9bblgYoEHME3v0QNsy08DP5dkL/A3wDktLULus+z7F/ADMNzXJ+1+HiRJkiRJkjRKbZxWJkmSJEmSpDGxOCRJkiRJkjTDLA5JkiRJkiTNMItDkiRJkiRJM8zikCRJkiRJ0gyzOCRJkiRJkjTDLA5JkiRJkiTNMItDkiRJkiRJM8zikCRJkiRJ0gyzOCRJkiRJkjTDLA5JkiRJkiTNMItDkiRJkiRJM8zikCRJkiRJ0gyzOCRJkiRJkjTDLA5JkiRJkiTNMItDkqROS/L2JP950jkkSZK6JsnqJJXkKStcvpL878POpfGzOCRJkiStQJIdSX5sQuvekuRXJ7FuSd02ybFL7WVxSJIkSRqzJEdMOoMkSftYHNJAkrw5yQNJHk3yxSSnJfmuJJuSfDnJV5Ncl+TYpv8/TXJvku9pbp+R5C+TPGeyWyKpy5Ybi5bpc1aSzyX56ySLSf5u3307krwlyeeTPJzkPyX57r77fzLJZ5pl/3uSHx7XtknqliS/C/wA8IdJ9iT5N0n+S/N555EktyZ5UV//LUkuT3JTkm8Ar0jy7CR/mOTrST6V5FeTfLxvmb+T5OYkX2vGvNc27RuA84B/06z7D8e8+ZI6aunYBby2ueu8JPcl+askv9TX/5Qkn2g+G+1K8ltJnjaJ7Boti0M6qCQvAC4G/l5VHQ38BLAD+HngbOAfAd8PPAz8B4Cquhb4BPDeJM8G3g/886r6ytg3QNJUOMBY1N/n+cA1wC8AzwFuovfhp/9DzHnNsv8b8Hzg3zbLvgS4EngT8GzgfcANSZ4+uq2S1FVV9TrgPuCnquqZVfUu4I+ANcDxwB3A1UsW+2fAO4GjgY/T+9z0DeD7gPXNDwBJjgJuBj7QPN65wH9M8qKq2tw89ruadf/UyDZU0lRZOnYB1zV3/QPgBcBpwC/3fbn2OPCLwHHA32/u/xdjDa2xsDikQTwOPB14YZKnVtWOqvoyvX+gfqmqdlbVN4G3Az/ddzCzi4B/DCwCf1hVHx5/dElTZH9jUb9/CtxYVTdX1f8C3g0cCfwffX1+q6rur6qv0fsn7dym/Y3A+6rqk1X1eFVtBb4JvHyUGyVpelTVlVX1aN/nohcn+d6+Ltuq6r9V1beA/wX8E+BtVfVYVX0e2NrX9yeBHVX1n6pqb1XdAXwI+OnxbI2kGfPvqupvquqzwGeBFwNU1e1VdVszDu2g9+XZP5pgTo2IxSEdVFVtp/ct/NuB3Uk+mOT7gR8Erm92Mfxr4B56/7zNNcv9NfBfgB8CLp1EdknT4wBjUb/vB/6ib5lvAfcDJ/T1ub/v+l80y0BvTNu4b0xrxrWT+u6XpP1KckSSS5rp9l/nO3s2HtfXrX/8eQ7wlCVt/dd/EHjZkjHpPHp7GUnSsP1l3/XHgGdCb6/sJB9upsx+Hfi/eeK4pilhcUgDqaoPVNU/oPdBpYBfo/cB5oyqOqbv57ur6gGAJCcDb6A3xeO9k8ouaXrsZyzq92BzHwBJQq/A80Bfn5P6rv9Aswz0xrR3LhnTnlFV1wx7OyRNjeq7/s+AdcCPAd8LrG7as5/+XwH2Aif2tfWPT/cD/3XJmPTMqvq5ZR5Lkg7FoYwflwNfANZU1fcAb+WJ45qmhMUhHVSSFyT5x81xN/4n8Df09hD6beCdSX6w6fecJOua698N/Gd6g8frgROSODdV0oodYCzqdx3wquag+U8FNtKbGvbf+/pclOTE5gD6bwWubdqvAH42ycvSc1SSVyU5eqQbJqnLHgKe11w/mt5481XgGfS+Xd+vqnoc+H3g7UmekeTvAOf3dfkw8Pwkr0vy1Obn7/UdB6R/3ZJ0KA5l/Dga+Dqwpxmnfu4g/dVRFoc0iKcDlwB/RW93w+Pp/UP1m8ANwEeTPArcBrysWebfAzur6vJm3v3PAL+aZM24w0uaGvsbi76tqr5Ib7y5rOn3U/QOuPi3fd0+AHwUuLf5+dVm2U/TO+7Qb9E7wP524IKRbY2kafDvgX/bTPk6lt5U1QeAz9P7XHQwF9Pby+gvgd+lt7f1NwGq6lHglcA59PZw/Et6e0vuO0j+++kdg+2vk/zBsDZI0kzoH7sOdhyz/5PenpGP0vsi7doDd1dXpco9UiVJsyHJDnpnTvyTSWeRpKWS/BrwfVW1/qCdJUkaIvcckiRJkiYgyd9J8sPNVNZTgAuB6yedS5I0e55y8C6SJEmSRuBoelPJvh/YTe/srtsmmkiSNJOcViZJkiRJkjTDnFYmSZIkSZI0wywOSZIkSZIkzbBWHHPouOOOq9WrVw/U9xvf+AZHHXXUaAMdJjMOTxdydiEjDJ7z9ttv/6uqes4YInXCtI1Pg5qmbQG3p+0cn1Zm2sanLmSEbuQ04/A4Pq1MF8entuSA9mRpSw5oT5a25IARjE9VNfGfl770pTWoj33sYwP3nRQzDk8XcnYhY9XgOYFPVwvGhbb8TNv4NKhp2pYqt6ftHJ8cn6q6kbGqGznNODyOT7MzPrUlR1V7srQlR1V7srQlR9XwxyenlUmSJEmSJM0wi0OSJEmSJEkzzOKQJEmSJEnSDLM4JEmSJEmSNMMsDkmSJEmSJM2wVpzKXtITrd5049Afc8vp7TjloqRuc3yS1FaOT1L7rfTvdOPavVywn2V3XPKqw4mkxkH3HEpyUpKPJbknyeeS/Kum/dgkNyf5UnP5rKY9Sd6bZHuSO5O8ZNQbIUmSJEmSpJUZZM+hvcDGqrojydHA7UluBi4AbqmqS5JsAjYBbwbOANY0Py8DLm8uJUmaiLseeGS/3zatlN9SSZIkaVocdM+hqtpVVXc01x8F7gFOANYBW5tuW4Gzm+vrgKuq5zbgmCSrhp5ckiRJkiRJh+2QDkidZDXwI8Angbmq2gW9AhJwfNPtBOD+vsV2Nm2SJEmSJElqmYEPSJ3kmcCHgF+oqq8n2W/XZdpqmcfbAGwAmJubY3FxcaAce/bsGbjvpJhxeLqQcxQZN67dO9THg248l5IkSZKk8RuoOJTkqfQKQ1dX1e83zQ8lWVVVu5ppY7ub9p3ASX2Lnwg8uPQxq2ozsBlgfn6+FhYWBgq8uLjIoH0nxYzD04Wco8g47GOjQO9sG21/LiVJkiRJ4zfI2coCvB+4p6p+o++uG4D1zfX1wLa+9vObs5a9HHhk3/QzSZIkSZIktcsgew6dCrwOuCvJZ5q2twKXANcluRC4D3hNc99NwJnA84YmHgAAIABJREFUduAx4PVDTSxJkiRJkqShOWhxqKo+zvLHEQI4bZn+BVx0mLkkSZIkSZI0Bod0tjJJkiQdXJIrk+xOcndf29uTPJDkM83PmX33vSXJ9iRfTPITk0ktSZJmlcUhSZKk4dsCnL5M+3uq6uTm5yaAJC8EzgFe1CzzH5McMbakkmaOBWxJS1kckiRJGrKquhX42oDd1wEfrKpvVtWf0ztu4ykjCydJFrAlLTHQqewlSZI0FBcnOR/4NLCxqh4GTgBu6+uzs2l7kiQbgA0Ac3NzLC4uDrTSPXv2DNx3UrqQEbqRc1Yzbly7d6iPB914Lleiqm5NsnrA7t8uYAN/nmRfAfsTI4onaQIsDknqrCRXAj8J7K6qH2rafh34KeBvgS8Dr6+qv24+AN0DfLFZ/Laq+tmxh5Y0yy4H3gFUc3kp8AaWP/FHLfcAVbUZ2AwwPz9fCwsLA614cXGRQftOShcyQjdyzmrGCzbdONTHA9hy+lGtfy6HbMUF7K4Xr9uSA9qTpU1F3Lkj97/sOJ+rtrw2MPwsFockddkW4LeAq/rabgbeUlV7k/wa8Bbgzc19X66qk8cbUZJ6quqhfdeTXAF8uLm5Ezipr+uJwINjjCZJcJgF7K4Xr9uSA9qTpU1F3I1r93LpXcuXL3act3AYiQ5NW14bGH4WjzkkqbOWO6ZHVX20qvZ9rXAbvX+yJGnikqzqu/lqYN+BYG8Azkny9CTPBdYAfzrufJJmW1U9VFWPV9W3gCv4zrHPLGBLM8DikKRp9gbgj/puPzfJnyX5r0n+4aRCSZp+Sa6hdzyOFyTZmeRC4F1J7kpyJ/AK4BcBqupzwHXA54GPABdV1eMTii5pRlnAlmab08okTaUkvwTsBa5umnYBP1BVX03yUuAPkryoqr6+zLKdnjM/DNO0LXDgeeorNcnnZ5Kvjwd8HUxVnbtM8/sP0P+dwDtHl0iSvqMpYC8AxyXZCbwNWEhyMr0pYzuAN0GvgJ1kXwF7LxawpalkcUjS1Emynt6Bqk+rqgJozrDxzeb67Um+DDyf3gEXn6Drc+aHYZq2BeCyq7ftd576So1zfvtSk3x9POCrJHWfBWxJSzmtTNJUSXI6vQNQn1VVj/W1PyfJEc3159HbJfreyaSUJEmSpPZwzyFJnbWfXaLfAjwduDkJfOeU9T8K/EqSvcDjwM9W1deWfWBJkiRJmiEWhyR11qHsEl1VHwI+NNpEkiRJktQ9TiuTJEmSJEmaYe45JEmSNOXueuCRoR5MfMclrxraY0mSpMlzzyFJkiRJkqQZZnFIkiRJkiRphlkckiRJkiRJmmEWhyRJkiRJkmaYxSFJkiRJkqQZZnFIkiRJkiRphlkckiRJkiRJmmEWhyRJkoYsyZVJdie5u6/t15N8IcmdSa5PckzTvjrJ3yT5TPPz25NLLkmSZpHFIUmSpOHbApy+pO1m4Ieq6oeB/wG8pe++L1fVyc3Pz44po6QZZPFa0nIsDkmSJA1ZVd0KfG1J20eram9z8zbgxLEHkySL15KWYXFIkiRp/N4A/FHf7ecm+bMk/zXJP5xUKEnTz+K1pOU8ZdIBJEmSZkmSXwL2Alc3TbuAH6iqryZ5KfAHSV5UVV9fZtkNwAaAubk5FhcXB1rn3JGwce3eg3cc0KDrPRR79uwZyeMOWxdyzmrGYf6O79OF53IE3gBc23f7uUn+DPg68G+r6v+bTCxJo3TQ4lCSK4GfBHZX1Q81bW8H3gh8pen21qq6qbnvLcCFwOPAz1fVH48gtyRJUuckWU/vc9VpVVUAVfVN4JvN9duTfBl4PvDppctX1WZgM8D8/HwtLCwMtN7Lrt7GpXcN7zvBHecNtt5Dsbi4yKDbM0ldyDmrGS/YdONQHw9gy+lHtf65HKZJFK/bUoBrSw5oT5Y2FXEP9CXHOJ+rtrw2MPwsg3xK2AL8FnDVkvb3VNW7+xuSvBA4B3gR8P3AnyR5flU9PoSskiRJnZXkdODNwD+qqsf62p8DfK2qHk/yPGANcO+EYkqaUZMqXrelmNmWHNCeLG0q4m5cu3e/X3KM4guL/WnLawPDz3LQYw4tNyf1ANYBH6yqb1bVnwPbgVMOI58kSVLnJLkG+ATwgiQ7k1xI78u2o4Gbl5z150eBO5N8Fvg94GeratDPXpJ02PqK12ctLV4nOaK5bvFammKHs3/xxUnOp1c13lhVDwMn0DuA2T47mzZJGon9TH09lt5c+dXADuC1VfVwkgC/CZwJPAZcUFV3TCK3pOlWVecu0/z+/fT9EPCh0SaSpJ6meL0AHJdkJ/A2emcnezq94jXAbc2ZyX4U+JUke+kdNsTitTSlVlocuhx4B1DN5aX0DlyWZfrWcg/Q9TmpB2LG4elCzjbNxT2QLjyXK7SFJ0993QTcUlWXJNnU3H4zcAa9b7zWAC+jN5a9bKxpJUmSJsjitaTlrKg4VFUP7bue5Argw83NncBJfV1PBB7cz2N0ek7qgZhxeLqQs01zcQ9kWg+oWFW3Jlm9pHkdvW/EALYCi/SKQ+uAq5p59LclOSbJqqraNZ60kiRJktQ+Bz3m0HKSrOq7+Wrg7ub6DcA5SZ6e5Ln0vp3/08OLKEmHbG5fwae5PL5pPwG4v6+fU18lSZIkzbxBTmW/3JzUhSQn05sytgN4E0BVfS7JdcDn6Z0C8SLPVCapRQaa+jrN014HNU3bAgc+/elKTfL5meTr47RXSZKkQ7N6RDNDhumgxaFDmZPa9H8n8M7DCSVJh+mhfdPFmj0ddzftA019neZpr4Oapm0BuOzqbfs9/elKjfO0qUtN8vVx2qskSdL0WdG0MklquRuA9c319cC2vvbz0/Ny4BGPNyRJkiRp1g33a1RJGrP9TH29BLguyYXAfcBrmu430TuN/XZ6p7J//dgDS5IkSVLLWByS1Gn7mfoKcNoyfQu4aLSJJEmSJKlbnFYmSZIkSZI0wywOSZIkSZIkzTCLQ5IkSZIkSTPM4pAkSZIkSdIMszgkSZIkSZI0wywOSZIkSZIkzTCLQ5IkSSOQ5Moku5Pc3dd2bJKbk3ypuXxW054k702yPcmdSV4yueSSpp3jk6SlLA5JkiSNxhbg9CVtm4BbqmoNcEtzG+AMYE3zswG4fEwZJc2mLTg+SepjcUiSJGkEqupW4GtLmtcBW5vrW4Gz+9qvqp7bgGOSrBpPUkmzxvFJ0lJPmXQASZKkGTJXVbsAqmpXkuOb9hOA+/v67WzadvUvnGQDvW/umZubY3FxcbCVHgkb1+49vOR9Bl3vodizZ89IHnfYupBzVjMO83d8ny48l0N0WOOTpG6zOCRJkjR5WaatntRQtRnYDDA/P18LCwsDPfhlV2/j0ruG97Fvx3mDrfdQLC4uMuj2TFIXcs5qxgs23TjUxwPYcvpRrX8ux2Cg8Wmlxeu2FODakgPak6VNRdwDfckxzudqpc9JF4rXFockSZLG56Ekq5pv5VcBu5v2ncBJff1OBB4cezpJs+ywxqeVFq/bUsxsSw5oT5Y2FXE3rt273y85RvGFxf6s9DnpQvHaYw5JkiSNzw3A+ub6emBbX/v5zVmBXg48sm96hySNieOTNMPcc0iSJGkEklwDLADHJdkJvA24BLguyYXAfcBrmu43AWcC24HHgNePPbCkmeH4JGkpi0OSJEkjUFXn7ueu05bpW8BFo00kST2OT5KWclqZJEmSJEnSDLM4JEmSJEmSNMOcViZp6iR5AXBtX9PzgF8GjgHeCHylaX9rVd005niSJEmS1CoWhyRNnar6InAyQJIjgAeA6+kdQPE9VfXuCcaTJEmSpFZxWpmkaXca8OWq+otJB5EkSZKkNrI4JGnanQNc03f74iR3JrkyybMmFUqSJEmS2sJpZZKmVpKnAWcBb2maLgfeAVRzeSnwhmWW2wBsAJibm2NxcXGg9e3Zs2fgvm03TdsCMHckbFy7d6iPOcnnZ5Kvz7CfR5i+3zdJkqSusTgkaZqdAdxRVQ8B7LsESHIF8OHlFqqqzcBmgPn5+VpYWBhoZYuLiwzat+2maVsALrt6G5feNdy3vB3nLQz18Q7FJF+fCzbdOPTH3HL6UVP1+yZJktQ1TiuTNM3OpW9KWZJVffe9Grh77IkkSZIkqWUOWhxqjsuxO8ndfW3HJrk5yZeay2c17Uny3iTbm2N6vGSU4SVpf5I8A/hx4Pf7mt+V5K4kdwKvAH5xIuEkSZIkqUUG2XNoC3D6krZNwC1VtQa4pbkNvSkca5qfDfSO7yFJY1dVj1XVs6vqkb6211XV2qr64ao6q6p2TTKjJEmSJLXBQYtDVXUr8LUlzeuArc31rcDZfe1XVc9twDFLpnFIkiRJkiSpRVZ6dM65fd+4V9WuJMc37ScA9/f129m0Penb+Wk+G5AZh6cLOUeR0bMBSZIkSZLGZdhnK8sybbVcx2k+G5AZh6cLOUeR0bMBSdJ0SvIC4Nq+pucBvwwcA7wR+ErT/taqumnM8SRJ0oxaaXHooSSrmr2GVgG7m/adwEl9/U4EHjycgJIkSdOiqr4InAyQ5AjgAeB64PXAe6rq3ROMJ2nGWcCWZtdKi0M3AOuBS5rLbX3tFyf5IPAy4JFhH/D1rgceGepeFTsuedXQHkuSJOkQnAZ8uar+Illu52tJGi8L2NLsGuRU9tcAnwBekGRnkgvpFYV+PMmX6J0q+pKm+03AvcB24ArgX4wktSRJUvedA1zTd/viJHcmuTLJsyYVSpIa3y5gTzqIpNE76J5DVXXufu46bZm+BVx0uKEkSZKmWZKnAWcBb2maLgfeQe9Yje8ALgXesMxyKzqhx9yRwz3ZwShOcNCVEyd0IeesZvSEHkO3XAH7fODTwMaqeri/c9dPONSWHNCeLG36Oz3Q+9g4n6uVPiddGJ+GfUBqSZIkHdwZwB1V9RDAvkuAJFcAH15uoZWe0OOyq7dx6V3D+9i347zB1nsounASCuhGzlnN6Ak9hmclBeyun3CoLTmgPVna9He6ce3e/b6PjeI9aX9W+px0YXw66LQySZIkDd259H0j35zgY59XA3ePPZEkfceTCthV9XhVfYve4UNOmWg6SUPnnkOSJEljlOQZ9I7Z+Ka+5nclOZnet/I7ltwnSeP2pAJ234mGLGBLU8jikCRJ0hhV1WPAs5e0vW5CcSTpCSxgS7PJ4pAkSZIkCbCALc0qjzkkSZIkSZI0wywOSZIkSZIkzTCLQ5IkSZIkSTPM4pAkSZIkSdIMszgkSZIkSZI0wzxbmaSplGQH8CjwOLC3quaTHAtcC6ymdxrW11bVw5PKKEmSJElt4J5DkqbZK6rq5Kqab25vAm6pqjXALc1tSZIkSZppFockzZJ1wNbm+lbg7AlmkSRJkqRWsDgkaVoV8NEktyfZ0LTNVdUugOby+ImlkyRJkqSW8JhDkqbVqVX1YJLjgZuTfGHQBZti0gaAubk5FhcXB1puz549A/dtu2naFoC5I2Hj2r1DfcxJPj+TfH2G/TzC9P2+SZIkdY3FIUlTqaoebC53J7keOAV4KMmqqtqVZBWwez/LbgY2A8zPz9fCwsJA61xcXGTQvm03TdsCcNnV27j0ruG+5e04b2Goj3coJvn6XLDpxqE/5pbTj5qq3zdJkqSucVqZpKmT5KgkR++7DrwSuBu4AVjfdFsPbJtMQkmSJElqD/cckjSN5oDrk0BvnPtAVX0kyaeA65JcCNwHvGaCGSVJkiSpFSwOSZo6VXUv8OJl2r8KnDb+RJL0REl2AI8CjwN7q2o+ybHAtcBqYAfw2qp6eFIZJc0mxydpNjmtTJIkaTJeUVUnV9V8c3sTcEtVrQFuaW5L0iQ4PkkzxuKQJElSO6wDtjbXtwJnTzCLJPVzfJKmnNPKJEmSxq+AjyYp4H3NWRLnqmoXQHNWxeOXLpRkA7ABYG5ujsXFxYFWNnckbFy7d1jZB17vodizZ89IHnfYupBzVjMO83d8ny48lyMw1vGpLc9xW3JAe7K06e/0QO9j43yuVvqcdGF8sjgkSZI0fqdW1YPNP1g3J/nCIAs1/6RtBpifn6+FhYWBVnbZ1du49K7hfezbcd5g6z0Ui4uLDLo9k9SFnLOa8YJNNw718QC2nH5U65/LERjr+NSW39e25ID2ZGnT3+nGtXv3+z42ivek/Vnpc9KF8clpZZIkSWNWVQ82l7uB64FTgIeSrAJoLndPLqGkWeX4JM0mi0OSJEljlOSoJEfvuw68ErgbuAFY33RbD2ybTEJJs8rxSZpdTiuTJEkarzng+iTQ+yz2gar6SJJPAdcluRC4D3jNBDNKmk2OT9KMsjgkSZI0RlV1L/DiZdq/Cpw2/kSS1OP4JM2uwyoOJdkBPAo8DuytqvkkxwLXAquBHcBrq+rhw4spSZIkSZKkURjGMYdeUVUnV9V8c3sTcEtVrQFuaW5LkiRJkiSphUZxQOp1wNbm+lbg7BGsQ5IkSZIkSUNwuMccKuCjSQp4X1VtBuaqahdAVe1KcvxyCybZAGwAmJubY3FxcaAVzh0JG9fuPczY3zHoeg/Fnj17RvK4w9SFjNCNnKPIOMzf8X268FxKkiRJksbvcItDp9b/3979x1tW1/Uef71jJBFUUHQiQAcLTXIUbeJaWh1FE6HE7lXTSJmkSEuv2pSOeh/+yLphpWZm2hReqYuCP4MEM1JOPuwGCoiOiCTixK8R/AmOv0c/94+9jm6GM3P2nP1r7b1ez8fjPGbvtddZ+73XWvs763z29/vdVTc2BaALknxq0F9sCklbADZs2FALCwsD/d7rzjyHV20d3Tza204a7Hn3xuLiIoO+nmmZhYwwGznHkXHj5vNGuj2ANx+3f+v3pSRJkiRp8oYaVlZVNzb/3gy8GzgGuCnJIQDNvzcPG1KSJEmSJEnjseriUJL9k9x56Tbwi8AngHOBk5vVTgbOGTakJEmSJEmSxmOY8VlrgXcnWdrOW6rqn5N8BHhbklOAa4EnDh9TkiRJkiRJ47Dq4lBVXQM8aJnlXwSOHSaUJEmSJEmSJmMcX2UvSVOV5PAkFya5MskVSZ7TLH9ZkhuSXN78HD/trJIkSZI0baP72i9Jao+dwKaquqyZG+3SJBc0j72mqv58itkkSZIkqVUsDkmaO1W1Hdje3P5qkiuBQ6ebSpIkSZLayWFlkuZaknXAg4GLm0XPSvLxJG9KctDUgkmSJElSS9hzSNLcSnIA8E7guVV1a5I3AK8Aqvn3VcDTl/m9U4FTAdauXcvi4uJAz7djx46B1227eXotAGv3g03rd450m9PcP9M8PqPejzB/59ueJDkc+HvgR4DvAVuq6rVJXgb8FvD5ZtUXVdX500kpqYtsn6RuszgkaS4luQO9wtCZVfUugKq6qe/xvwXes9zvVtUWYAvAhg0bamFhYaDnXFxcZNB1226eXgvA6848h1dtHe1/edtOWhjp9vbGNI/Pxs3njXybbz5u/7k631bgnGiS2sr2Seowi0OS5k6SAKcDV1bVq/uWH9LMRwTwK8AnppFPUnc5J5qktrJ9krrN4pCkefQw4KnA1iSXN8teBDwlydH0hpVtA357OvEk6XZzoj2M3pxoTwMuoffp/ZeX+Z1VDXsd9dDKcQwDnJXhhbOQs6sZHfY6OqtpnyTNNotDkuZOVX0IyDIPjXV8/NYbbhnpkJttp50wsm1JapfVzom22mGvox5aOY5hlbMynHUWcnY1o8NeR6Orcza2JQe0J0ubirh7+pBjkvtqtftkForXFockSZImaJg50SRpnLo8Z2NbckB7srSpiLtp/c7dfsgxyXkgV7tPZqF47VfZS5IkTcie5kTrW8050SRNnO2T1G32HJIkSZoc50ST1Fa2T1KHWRySJEmakGnNiSZJK7F9krrNYWWSJEmSJEkdZs8hSZIkSZImaN0eJijetH7nqiYw9ptuNQx7DkmSJEmSJHWYxSFJkiRJkqQOszgkSZIkSZLUYRaHJEmSJEmSOszikCRJkiRJUodZHJIkSZIkSeowi0OSJEmSJEkdZnFIkiRJkiSpwywOSZIkSZIkdZjFIUmSJEmSpA6zOCRJkiRJktRhYysOJTkuyVVJrk6yeVzPI0l7y/ZJUlvZPklqK9snab6NpTiUZB/g9cBjgaOApyQ5ahzPJUl7w/ZJUlvZPklqK9snaf6tGdN2jwGurqprAJKcBZwIfHJMzydJg7J9ktRWtk+S2mps7dPWG25h4+bzht3MbWw77YSRbk/qgnENKzsUuK7v/vXNMkmaNtsnSW1l+ySprWyfpDk3rp5DWWZZ3WaF5FTg1ObujiRXDbjtg4EvDJHtNvLKUW3pNkaacUxmISPMRs5ZyMgjXjlwznuPO8uUdb19GtRMnNd7YeSvx+MzOrZP39f19mlWzutZyGnGEbF9+r6ZaZ9g1W1Ua87J/7nKLGNom2din0z4mqw1+2TU7dO4ikPXA4f33T8MuLF/haraAmzZ2w0nuaSqNgwXb7zMODqzkHMWMsLs5JyATrdPg5qn1wK+nrabt9czhE63T7OQEWYjpxlHZ1ZyTsDct09tyQHtydKWHNCeLG3JAaPPMq5hZR8BjkxyRJJ9gScD547puSRpb9g+SWor2ydJbWX7JM25sfQcqqqdSZ4FvA/YB3hTVV0xjueSpL1h+ySprWyfJLWV7ZM0/8Y1rIyqOh84fwyb3uuuilNgxtGZhZyzkBFmJ+fYdbx9GtQ8vRbw9bTdvL2eVet4+zQLGWE2cppxdGYl59h1oH1qSw5oT5a25ID2ZGlLDhhxllTVymtJkiRJkiRpLo1rziFJkiRJkiTNgFYWh5Icl+SqJFcn2bzM4z+c5Ozm8YuTrJt8yoFy/l6STyb5eJL3J5n4V1yulLFvvSckqSQTn3l9kIxJntTsyyuSvGXSGZsMKx3veyW5MMlHm2N+/BQyvinJzUk+sZvHk+Qvm9fw8SQPmXTGWTcr7dOgBng9G5N8Psnlzc9vTiPnIObt/B/g9SwkuaXv2Lxk0hkHleTwpn28smnHn7PMOjN1fNpoVtonr59GZxauobx+0pK2tFFtufZpy3nXpuuNtlwvDJhjIvslyR2TfDjJx5osL19mndG8d6qqVT/0Jjj7DHAfYF/gY8BRu6zzO8Abm9tPBs5uac5HAHdqbj9z0jkHydisd2fgg8BFwIa2ZQSOBD4KHNTcv2dLj/cW4JnN7aOAbVPI+fPAQ4BP7Obx44H3AgEeClw86Yyz/DMr7dOIX89G4K+mnXXA1zNX5/8Ar2cBeM+0cw74Wg4BHtLcvjPwn8ucazN1fNr2Myvt04A5vX4a3b6c6jXUgBm9furAT1vaqAFzbGQC1z5tOe8GyLHAhK43aMn1woA5JrJfmtd5QHP7DsDFwEN3WWck75029hw6Bri6qq6pqm8DZwEn7rLOicAZze13AMcmyQQzwgA5q+rCqvp6c/ci4LC2ZWy8AvhT4JuTDNcYJONvAa+vqi8DVNXNE84Ig+Us4C7N7bsCN04wXy9A1QeBL+1hlROBv6+ei4ADkxwymXRzYVbap0EN2kbMhHk7/wd4PTOjqrZX1WXN7a8CVwKH7rLaTB2fFpqV9snrp9GZhWsor5+0pC1tVGuufdpy3rXpeqMt1wsD5piI5nXuaO7eofnZdeLokbx32lgcOhS4ru/+9dz+QHx/naraCdwC3H0i6ZbJ0FguZ79T6FU4J2nFjEkeDBxeVe+ZZLA+g+zH+wL3TfLvSS5KctzE0v3AIDlfBvx6kuvpfZPDsycTba/s7Xmr25qV9mlQg54P/6PptvuOJIdPJtpYzOP5/zNNN+P3JvnJaYcZRNPV+cH0PvnqN4/HZ5JmpX3y+ml0ZuEayusnLWlLGzVL1z5tOu8mfr3RluuFPeSACe2XJPskuRy4Gbigqna7T4Z577SxOLRchWvXytgg64zbwBmS/DqwAfizsSZa5qmXWfb9jEl+CHgNsGliiW5vkP24hl636AXgKcDfJTlwzLl2NUjOpwBvrqrD6HV3/IdmH7dJG947s2xW2qdBDZL1n4B1VfVA4F/5wacSs2iWjs0gLgPuXVUPAl4H/OOU86woyQHAO4HnVtWtuz68zK/M8vGZtFlpn7x+Gp1ZuIby+klL2tJGzdK1T1vOu4lfb7TlemGFHBPbL1X13ao6ml5P2mOSPGDXqMv92t4+T9saXuhV/vqrs4dx++6l318nyRp6XVAn3RVukJwkeRTwYuBxVfWtCWVbslLGOwMPABaTbKM3ZvPcTHZSxUGP9zlV9Z2q+ixwFb0LnUkaJOcpwNsAquo/gDsCB08k3eAGOm+1W7PSPg1qxddTVV/sa7v+FvipCWUbh7k6/6vq1qVuxlV1PnCHJG1rc74vyR3oXWCdWVXvWmaVuTo+UzAr7ZPXT6MzC9dQXj9pSVvaqFm69mnFeTfp6422XC+slGMa12FV9RVgEdi1F+hI3jttLA59BDgyyRFJ9qU3odK5u6xzLnByc/sJwAeqatJV1BVzNl2O/4behc005snZY8aquqWqDq6qdVW1jt64/sdV1SVtydj4R3qTU9K84e4LXDPBjDBYzmuBYwGS3J/exc3nJ5pyZecCT2tm+X8ocEtVbZ92qBkyK+3ToAZpx/rHcD+O3pjrWTVX53+SH1kaT57kGHr/p39xuqmW1+Q8Hbiyql69m9Xm6vhMway0T14/TShnY9rXUF4/aUlb2qhZuvZpxXk3yeuNtlwvDJJjUvslyT2Wenwm2Q94FPCpXVYbzXunJjDr+N7+0OtS+p/0ZpJ/cbPsD+n9xwu9/zTeDlwNfBi4T0tz/itwE3B583Nu2zLusu4i0/m2jZX2Y4BXA58EtgJPbunxPgr4d3rfenA58ItTyPhWYDvwHXoV5FOAZwDP6NuXr29ew9ZpHO9Z/5mV9mmEr+dPgCua8/pC4CemnXkPr2Wuzv8BXs+z+o7NRcDPTjvzHl7Lw+l1b/543/+Jx8/y8Wnjz6y0TwMidE6cAAAadUlEQVTk9PppdPty6tdQA2T0+qkjP21powbIMZFrn7acdwPkmNj1Bi25Xhgwx0T2C/BAet86+XHgE8BLljlnR/LeSbMxSZIkSZIkdVAbh5VJkiRJkiRpQiwOSZIkSZIkdZjFIUmSJEmSpA6zOCRJkiRJktRhFockSZIkSZI6zOKQJEmSJElSh1kckiRJkiRJ6jCLQ5IkSZIkSR1mcUiSJEmSJKnDLA5JkiRJkiR1mMUhSZIkSZKkDrM4JEmSJEmS1GEWhyRJkiRJkjrM4pAkSZIkSVKHWRySJEmSJEnqMItDIsm6JJVkzSp/v5L8+JAZ3pzkj4bZhiQNyjZHkiRJ+gGLQx2VZFuSR007hyQtGVe7lGRjkg+NeruSJEnSvLA4JElqvdX2bJQkSZK0MotDHZTkH4B7Af+UZAfwpOahk5Jcm+QLSV7ct/4xSf4jyVeSbE/yV0n23c22T0jy0SS3Jrkuyct2efzhSf5fs63rkmzse/igJOcl+WqSi5P82EhfuKTW2rVdSvL8ZsjqKUmuBT7QrPfQvjbkY0kW+raxMck1TRvy2SQnJbk/8EbgZ5rtfqXvaQ9OckGz/r8luXfftirJ/2y294Ukf5bkh5rHfrxZ/5bmsbMnsIskSZKksbE41EFV9VTgWuCXq+oA4G3NQw8H7gccC7yk+aMK4LvA84CDgZ9pHv+d3Wz+a8DTgAOBE4BnJnk8QJJ7Ae8FXgfcAzgauLzvd58CvBw4CLga+ONhX6uk2bCHdukXgPsDj0lyKHAe8EfA3YDfB96Z5B5J9gf+EnhsVd0Z+Fng8qq6EngG8B9VdUBVHdj3tCcBr6DXtl0OnLlLrF8BNgAPAU4Ent4sfwXwL/TaqsPotWmSJEnSzLI4pH4vr6pvVNXHgI8BDwKoqkur6qKq2llV24C/ofcH2+1U1WJVba2q71XVx4G39q17EvCvVfXWqvpOVX2xqvqLQ++qqg9X1U56f6QdPZ6XKWmGvKyqvlZV3wB+HTi/qs5v2pgLgEuA45t1vwc8IMl+VbW9qq5YYdvnVdUHq+pbwIvp9S46vO/xV1bVl6rqWuAv6BWwAb4D3Bv40ar6ZlU5n5EkSZJmmsUh9ftc3+2vAwcAJLlvkvck+VySW4H/Te+T9ttJ8t+SXJjk80luofeJ/dK6hwOf2dvnl9Rp1/XdvjfwxGZI2VeaIWIPBw6pqq8Bv0qvzdneDFH9iUG3XVU7gC8BP7qb5/6vvseeDwT4cJIrkjwdSZIkaYZZHOqu2ot13wB8Cjiyqu4CvIjeH0bLeQtwLnB4Vd2V3lwfS+teBziPkKTdWa5d6l92HfAPVXVg38/+VXUaQFW9r6oeDRxCr8362z1sF3oFawCSHEBvqNqNyz1Obz6kG5vn+VxV/VZV/Sjw28BfJ/nxgV+lJEmS1DIWh7rrJuA+A657Z+BWYEfzSfwzV1j3S1X1zSTHAL/W99iZwKOSPCnJmiR3T+LQMUlLVmqX/i/wy0kek2SfJHdMspDksCRrkzyumXvoW8AOevOlLW33sGUm0j++mSR/X3rzCF1cVf29hf4gyUHNULPnAGcDJHliksOadb5Mr/j0XSRJkqQZZXGou/4E+F/NsIwnrLDu79Mr8nyV3ifxe/pmnt8B/jDJV4GX8INJZWnm7Tge2ERv+MblNPMaSRIrtEtN4eZEer0XP0+vJ9Ef0Pu/7IfotS030mtffoEfTJz/AeAK4HNJvtC3ybcAL23W/yl686L1Owe4lF5bdR5werP8p4GLm297PBd4TlV9dtWvWpIkSZqyVO3N6CJJkuZfkqI3lPbqaWeRJEmSxs2eQ5IkSZIkSR1mcUiSJEmSJKnDHFYmSZIkSZLUYUP1HEryvCRXJPlEkrc23xxzRJKLk3w6ydnLfDuMJEmSJEmSWmLVPYeSHAp8CDiqqr6R5G3A+fS+jepdVXVWkjcCH6uqN+xpWwcffHCtW7duVTmWfO1rX2P//fcfahvj0uZs0O58bc4G7c632myXXnrpF6rqHmOINJNG0T4tZx7PnUloczZod755yGb7JEmSNB5rRvD7+yX5DnAnYDvwSHpfew5wBvAyYI/FoXXr1nHJJZcMFWRxcZGFhYWhtjEubc4G7c7X5mzQ7nyrzZbkv0afZnaNon1azjyeO5PQ5mzQ7nzzkM32SZIkaTxWXRyqqhuS/DlwLfAN4F+AS4GvVNXOZrXrgUOX+/0kpwKnAqxdu5bFxcXVRgFgx44dQ29jXNqcDdqdr83ZoN352pxNkiRJktQeqy4OJTkIOBE4AvgK8Hbgscusuuy4taraAmwB2LBhQw37aeY8fCI6LW3O1+Zs0O58bc4mSZIkSWqPYSakfhTw2ar6fFV9B3gX8LPAgUmWik6HATcOmVGSJEmSJEljMkxx6FrgoUnulCTAscAngQuBJzTrnAycM1xESZIkSZIkjcuqi0NVdTHwDuAyYGuzrS3AC4DfS3I1cHfg9BHklCRJkiRJ0hgM9W1lVfVS4KW7LL4GOGaY7UqSJEmSJGkyhv0qe2mstt5wCxs3nzey7W077YSRbUtSz7oRvkfB96kkSZI0acPMOSRJkiRJkqQZZ3FIkiRJkiSpwywOSZIkSZIkdZjFIUmSJEmSpA6zOCRJkiRJktRhFockSZIkSZI6zOKQJEmSJElSh1kckiRJkiRJ6jCLQ5IkSZIkSR1mcUiSJEmSJKnDLA5JkiRJkiR1mMUhSZIkSZKkDrM4JEmSJEmS1GFrph1AkjQ56zaft+I6m9bvZOMA60mSJEmaD/YckiRJkiRJ6jCLQ5IkSZIkSR1mcUiSJEmSJKnDLA5JkiRJkiR1mMUhSZIkSZKkDrM4JEmSJEmS1GEWhyRJkiRJkjrM4pAkSZIkSVKHWRySJEmSJEnqMItDkuZSkgOTvCPJp5JcmeRnktwtyQVJPt38e9C0c0qSJEnStFkckjSvXgv8c1X9BPAg4EpgM/D+qjoSeH9zX5IkSZI6zeKQpLmT5C7AzwOnA1TVt6vqK8CJwBnNamcAj59OQkmSJElqjzXTDiBN0rrN5410e5vW72RhpFvUiNwH+Dzwf5I8CLgUeA6wtqq2A1TV9iT3nGJGSZIkSWoFi0OS5tEa4CHAs6vq4iSvZS+GkCU5FTgVYO3atSwuLo484I4dO8ay3ZVsWr9zxXXW7jfYeuOyp/0yrf02qDbnM5skSZJ2Z6jiUJIDgb8DHgAU8HTgKuBsYB2wDXhSVX15qJSStHeuB66vqoub+++gVxy6KckhTa+hQ4Cbl/vlqtoCbAHYsGFDLSwsjDzg4uIi49juSjYO0Htu0/qdvGrr9D472HbSwm4fm9Z+G1Sb85lNkiRJuzPsnENO+Cqpdarqc8B1Se7XLDoW+CRwLnBys+xk4JwpxJMkSZKkVln1R8N9E75uhN6Er8C3k5wI35+G5QxgEXjBMCElaRWeDZyZZF/gGuA36BXE35bkFOBa4IlTzCdJkiRJrTDMuAEnfJXUWlV1ObBhmYeOnXQWSZIkSWqzYYpDrZrwtc2TWbY5G7Q737Qnxl3J2v32PHnuNLX5uEqSJEmS2mOY4lCrJnxt82SWbc4G7c73ujPPmerEuCvZtH4nT2rpvmvzcZX2ZN0eJs3etH7nQJNq72rbaScME0mSJEmaa6uekNoJXyVJkiRJkmbfsF0ynPBVkiRJkiRphg1VHHLCV0mSJEmSpNm26mFlkiRJkiRJmn0WhyRJkiRJkjrM4pAkSZIkSVKHWRySJEmSJEnqMItDkiRJkiRJHWZxSJIkSZIkqcMsDkmSJEmSJHWYxSFJkiRJkqQOWzPtAJof6zafN/Jtblo/8k1KkiRJkqQ+9hySJEmSJEnqMItDkiRJkiRJHWZxSJIkSZIkqcMsDkmSJEmSJHWYxSFJkiRJkqQOszgkSZIkSZLUYRaHJEmSJEmSOszikCRJkiRJUodZHJIkSZIkSeowi0OSJEmSJEkdZnFIkiRJkiSpwywOSZIkSZIkdZjFIUmSJEmSpA6zOCRJkiRJktRhFockSZIkSZI6zOKQJEmSJElSh1kckiRJkiRJ6rA10w4gSeOSZB/gEuCGqvqlJEcAZwF3Ay4DnlpV355mxj1Zt/m8aUeQJEmS1AH2HJI0z54DXNl3/5XAa6rqSODLwClTSSVJkiRJLWJxSNJcSnIYcALwd839AI8E3tGscgbw+OmkkyRJkqT2GLo4lGSfJB9N8p7m/hFJLk7y6SRnJ9l3+JiStNf+Ang+8L3m/t2Br1TVzub+9cCh0wgmSZIkSW0yijmHloZt3KW5vzRs46wkb6Q3bOMNI3geSRpIkl8Cbq6qS5MsLC1eZtXaze+fCpwKsHbtWhYXF0eecceOHStud9P6nXt8fFzW7je9517JarON4xguZ5DjOi1mkyRJ0u4MVRzqG7bxx8Dv9Q3b+LVmlTOAl2FxSNJkPQx4XJLjgTvSK17/BXBgkjVN76HDgBuX++Wq2gJsAdiwYUMtLCyMPODi4iIrbXfjlCak3rR+J6/a2s7vK1httm0nLYw+zDIGOa7TYjZJkiTtzrDDyhy2Ial1quqFVXVYVa0Dngx8oKpOAi4EntCsdjJwzpQiSpIkSVJrrPqj4bYN22hzl/Q2Z4PR5RvHMJQ2D2+BXr62Htu2n3dT8gLgrCR/BHwUOH3KeSRJkiRp6oYZN9CqYRtt7pLe5mwwunzjGALT5uEt0Mv3pJYe27afd5NSVYvAYnP7GuCYaeaRJEmSpLZZ9bAyh21IkiRJkiTNvqG/yn4ZL6A3OfXV9OYgctiGJEmSJElSS41kvI7DNiRJkiRJkmbTOHoOSZIkSZIkaUZYHJIkSZIkSeowi0OSJEmSJEkdZnFIkiRJkiSpwywOSZIkSZIkddhIvq1Ms2fd5vO+f3vT+p1s7LsvSZIkSZK6w55DkiRJkiRJHWZxSJIkSZIkqcMsDkmSJEmSJHWYxSFJkiRJkqQOszgkSZIkSZLUYRaHJEmSJEmSOszikCRJkiRJUodZHJIkSZIkSeowi0OSJEmSJEkdZnFIkiRJkiSpwywOSZIkSZIkdZjFIUmSJEmSpA5bM+0AkiSN27rN5418m9tOO2Hk25QkSZKmwZ5DkiRJkiRJHWZxSJIkSZIkqcMsDkmSJEmSJHWYcw7NiHHMl6HRcC4TSZIkSdIss+eQJEmSJElSh1kckiRJkiRJ6jCLQ5IkSZIkSR1mcUiSJEmSJKnDLA5JkiRJkiR1mMUhSXMnyeFJLkxyZZIrkjynWX63JBck+XTz70HTzipJkiRJ02ZxSNI82glsqqr7Aw8FfjfJUcBm4P1VdSTw/ua+JEmSJHXaqotDfjIvqa2qantVXdbc/ipwJXAocCJwRrPaGcDjp5NQkiRJktpjmJ5DfjIvqfWSrAMeDFwMrK2q7dArIAH3nF4ySZIkSWqHNav9xeYPq6U/sr6apP+T+YVmtTOAReAFQ6WUpFVIcgDwTuC5VXVrkkF/71TgVIC1a9eyuLg48mw7duxYcbub1u8c+fMOYu1+03vulbQp23LHb5DjOi1mkyRJ0u6kqobfSO+T+Q8CDwCuraoD+x77clXdbmjZLn98/dRZZ501VIYdO3ZwwAEHDLWNcRlFtq033DKiNLe3dj+46Rtj2/xQ2pwNxpdv/aF3HXobqz3vHvGIR1xaVRuGDjBlSe4AvAd4X1W9ull2FbBQVduTHAIsVtX99rSdDRs21CWXXDLyfIuLiywsLOxxnXWbzxv58w5i0/qdvGrrqj87GKs2Zdt22gm3WzbIcZ2WeciWZC7aJ0mSpLYZ+gp7tZ/MV9UWYAv0/vga9oJ1Hi5692TjGP9IbNMfW7tqczYYX75tJy0MvY02vyfGLb2G6HTgyqXCUONc4GTgtObfc6YQT5IkSZJaZahvK2s+mX8ncGZVvatZfFPziTzNvzcPF1GS9trDgKcCj0xyefNzPL2i0KOTfBp4dHNfkiRJkjpt1V0e/GReUltV1YeA3XVjPHaSWSRJkiSp7YYZD7P0yfzWJJc3y15Eryj0tiSnANcCTxwuoiRJkiRJksZlmG8r85N5SZIkSZKkGTfUnEOSJEmSJEmabRaHJEmSJEmSOszikCRJkiRJUodZHJIkSZIkSeowi0OSJEmSJEkdZnFIkiRJkiSpwywOSZIkSZIkddiaaQeQJGkWrdt83u2WbVq/k43LLB/UttNOGCaSJEmStCr2HJIkSZIkSeowi0OSJEmSJEkdZnFIkiRJkiSpwywOSZIkSZIkdZgTUo/BrpOUDjtBqSRJkiRJ0rhYHJKkEVnu26t2x6KxJEmSpLZwWJkkSZIkSVKHWRySJEmSJEnqMItDkiRJkiRJHeacQ5IktcTezFs1iG2nnTDS7UmSJGk+2XNIkiRJkiSpwywOSZIkSZIkdZjFIUmSJEmSpA7r/JxDo57fQZIkSZIkaZbYc0iSJEmSJKnDOt9zSGqjUfRo27R+Jxv7tuO3FkmSJEmSlmPPIUmSJEmSpA6zOCRJkiRJktRhFockSZIkSZI6zDmHJEmaU/3zl+06D9lqOX+ZJEnS/LHnkCRJkiRJUoeNredQkuOA1wL7AH9XVaeN67kkaW/YPkmrN4pvU9zVm4/bf+TblCRJ0uDG0nMoyT7A64HHAkcBT0ly1DieS5L2hu2TJEmSJN3WuHoOHQNcXVXXACQ5CzgR+OSwG97dJ5ajmktB0twbW/skSZIkSbNoXHMOHQpc13f/+maZJE2b7ZMkSZIk9UlVjX6jyROBx1TVbzb3nwocU1XP7lvnVODU5u79gKuGfNqDgS8MuY1xaXM2aHe+NmeDdudbbbZ7V9U9Rh2mLabUPi1nHs+dSWhzNmh3vnnINtftkyRJ0rSMa1jZ9cDhffcPA27sX6GqtgBbRvWESS6pqg2j2t4otTkbtDtfm7NBu/O1OduUTbx9Wk6bj4/ZVq/N+cwmSZKk3RnXsLKPAEcmOSLJvsCTgXPH9FyStDdsnyRJkiSpz1h6DlXVziTPAt5H76ui31RVV4zjuSRpb9g+SZIkSdJtjWtYGVV1PnD+uLa/jLEOARlSm7NBu/O1ORu0O1+bs03VFNqn5bT5+Jht9dqcz2ySJEla1lgmpJYkSZIkSdJsGNecQ5IkSZIkSZoBM1ccSnK/JJf3/dya5LlJXpbkhr7lx08w05uS3JzkE33L7pbkgiSfbv49qFmeJH+Z5OokH0/ykClk+7Mkn2qe/91JDmyWr0vyjb59+MZxZttDvt0eyyQvbPbdVUkeM4VsZ/fl2pbk8mb5NPbd4UkuTHJlkiuSPKdZ3opzr+vmpV1oHpvq+67vsd9PUkkObu5Pfb81y5/d7Jsrkvxp3/Jpt1dHJ7moaZMuSXJMs3zS+822SpIkqeVmrjhUVVdV1dFVdTTwU8DXgXc3D79m6bFmTpFJeTNw3C7LNgPvr6ojgfc39wEeCxzZ/JwKvGEK2S4AHlBVDwT+E3hh32Of6duHzxhztt3lg2WOZZKj6H2z1E82v/PXSfaZZLaq+tW+8++dwLv6Hp70vtsJbKqq+wMPBX632UdtOfe67s3MQbvQhvddk+Nw4NHAtX2Lp77fkjwCOBF4YFX9JPDnzfI27Lc/BV7etFcvae7D5PebbZUkSVLLzVxxaBfH0vuD/L+mGaKqPgh8aZfFJwJnNLfPAB7ft/zvq+ci4MAkh0wyW1X9S1XtbO5eBBw2rudfyW723e6cCJxVVd+qqs8CVwPHTCNbkgBPAt46rudfSVVtr6rLmttfBa4EDqUl517XzVG70Jb33WuA5wP9E+VNfb8BzwROq6pvNevc3Jdt2vutgLs0t+8K3NiXbZL7zbZKkiSp5Wa9OPRkbvvH+bOaLuhvWuqePkVrq2o79C6MgXs2yw8Frutb7/pm2bQ8HXhv3/0jknw0yb8l+blphWL5Y9mmffdzwE1V9em+ZVPbd0nWAQ8GLmZ2zr0umpVj098uTD1bkscBN1TVx3Z5aOrZgPsCP5fk4ua9/9MtyvZc4M+SXEevR9NSL9GpZbOtkiRJaqeZLQ4l2Rd4HPD2ZtEbgB8Djga2A6+aUrSVZJllU/nKuCQvptfd/8xm0XbgXlX1YOD3gLckucvufn+MdncsW7PvgKdw28Lk1PZdkgPoDXF7blXduqdVl1nm1xW2Q2uOzTLtwlSzJbkT8GJ6w6Ju9/Ayyya939YAB9EbLvUHwNuanoVtyPZM4HlVdTjwPOD0ZvlUstlWSZIktdfMFofozUlwWVXdBFBVN1XVd6vqe8DfMsbu+wO6aakbfPPv0lCD64HD+9Y7jB909Z+YJCcDvwScVFUF0Ax/+GJz+1LgM/Q+FZ+oPRzLtuy7NcB/B85eWjatfZfkDvT+2DqzqpbmP2r1uddxrT42y7ULLcj2Y8ARwMeSbGue/7IkP9KCbDQZ3tUMgfow8D3g4JZkO5kfzIv2dqbYltpWSZIktdssF4du03Njl/kIfgW43TfdTNi59C7Maf49p2/505pvY3kocMtSt/pJSXIc8ALgcVX19b7l91iaMDXJfehNBnrNJLM1z727Y3ku8OQkP5zkiCbfhyedD3gU8Kmqun5pwTT2XdM74XTgyqp6dd9DrT331N5js7t2gSm/76pqa1Xds6rWVdU6eoWDh1TV52jBfgP+EXgkQJL7AvsCX6Ad7dWNwC80tx8JLA2Dneh+s62SJElqvzXTDrAazTCDRwO/3bf4T5McTa/r+bZdHht3nrcCC8DBSa4HXgqcRm94wSn0vl3nic3q5wPH05uc9OvAb0wh2wuBHwYu6F2zc1Hz7Vo/D/xhkp3Ad4FnVNWgk0WPMt/Ccseyqq5I8jbgk/SGvfxuVX13ktmq6nRuP9cVTGHfAQ8DngpsTXJ5s+xFtOTc67p5aRda9L5bThv225uAN6X3FfLfBk5uel1Nfb8BvwW8tunt+E163/wFk28LbKskSZJaLj8YOSBJkiRJkqSumeVhZZIkSZIkSRqSxSFJkiRJkqQOszgkSZIkSZLUYRaHJEmSJEmSOszikCRJkiRJUodZHJIkSZIkSeowi0OSJEmSJEkdZnFIkiRJkiSpw/4/XQQSqu3g8jAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1440x1008 with 16 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "dataset.hist()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Taking a look at the histograms above, I can see that each feature has a different range of distribution. Thus, using scaling before our predictions should be of great use. Also, the categorical features do stand out."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It's always a good practice to work with a dataset where the target classes are of approximately equal size. Thus, let's check for the same."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Count of each Target Class')"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "rcParams['figure.figsize'] = 8,6\n",
    "plt.bar(dataset['target'].unique(), dataset['target'].value_counts(), color = ['red', 'green'])\n",
    "plt.xticks([0, 1])\n",
    "plt.xlabel('Target Classes')\n",
    "plt.ylabel('Count')\n",
    "plt.title('Count of each Target Class')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The two classes are not exactly 50% each but the ratio is good enough to continue without dropping/increasing our data."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Data Processing\n",
    "\n",
    "After exploring the dataset, I observed that I need to convert some categorical variables into dummy variables and scale all the values before training the Machine Learning models.\n",
    "First, I'll use the `get_dummies` method to create dummy columns for categorical variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = pd.get_dummies(dataset, columns = ['sex', 'cp', 'fbs', 'restecg', 'exang', 'slope', 'ca', 'thal'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now, I will use the `StandardScaler` from `sklearn` to scale my dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "standardScaler = StandardScaler()\n",
    "columns_to_scale = ['age', 'trestbps', 'chol', 'thalach', 'oldpeak']\n",
    "dataset[columns_to_scale] = standardScaler.fit_transform(dataset[columns_to_scale])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The data is not ready for our Machine Learning application."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Machine Learning\n",
    "\n",
    "I'll now import `train_test_split` to split our dataset into training and testing datasets. Then, I'll import all Machine Learning models I'll be using to train and test the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = dataset['target']\n",
    "X = dataset.drop(['target'], axis = 1)\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.33, random_state = 0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### K Neighbors Classifier\n",
    "\n",
    "The classification score varies based on different values of neighbors that we choose. Thus, I'll plot a score graph for different values of K (neighbors) and check when do I achieve the best score."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "knn_scores = []\n",
    "for k in range(1,21):\n",
    "    knn_classifier = KNeighborsClassifier(n_neighbors = k)\n",
    "    knn_classifier.fit(X_train, y_train)\n",
    "    knn_scores.append(knn_classifier.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "I have the scores for different neighbor values in the array `knn_scores`. I'll now plot it and see for which value of K did I get the best scores."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'K Neighbors Classifier scores for different K values')"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot([k for k in range(1, 21)], knn_scores, color = 'red')\n",
    "for i in range(1,21):\n",
    "    plt.text(i, knn_scores[i-1], (i, knn_scores[i-1]))\n",
    "plt.xticks([i for i in range(1, 21)])\n",
    "plt.xlabel('Number of Neighbors (K)')\n",
    "plt.ylabel('Scores')\n",
    "plt.title('K Neighbors Classifier scores for different K values')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From the plot above, it is clear that the maximum score achieved was `0.87` for the 8 neighbors."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The score for K Neighbors Classifier is 87.0% with 8 nieghbors.\n"
     ]
    }
   ],
   "source": [
    "print(\"The score for K Neighbors Classifier is {}% with {} nieghbors.\".format(knn_scores[7]*100, 8))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Support Vector Classifier\n",
    "\n",
    "There are several kernels for Support Vector Classifier. I'll test some of them and check which has the best score."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "svc_scores = []\n",
    "kernels = ['linear', 'poly', 'rbf', 'sigmoid']\n",
    "for i in range(len(kernels)):\n",
    "    svc_classifier = SVC(kernel = kernels[i])\n",
    "    svc_classifier.fit(X_train, y_train)\n",
    "    svc_scores.append(svc_classifier.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "I'll now plot a bar plot of scores for each kernel and see which performed the best."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Support Vector Classifier scores for different kernels')"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "colors = rainbow(np.linspace(0, 1, len(kernels)))\n",
    "plt.bar(kernels, svc_scores, color = colors)\n",
    "for i in range(len(kernels)):\n",
    "    plt.text(i, svc_scores[i], svc_scores[i])\n",
    "plt.xlabel('Kernels')\n",
    "plt.ylabel('Scores')\n",
    "plt.title('Support Vector Classifier scores for different kernels')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `linear` kernel performed the best, being slightly better than `rbf` kernel."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The score for Support Vector Classifier is 83.0% with linear kernel.\n"
     ]
    }
   ],
   "source": [
    "print(\"The score for Support Vector Classifier is {}% with {} kernel.\".format(svc_scores[0]*100, 'linear'))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Decision Tree Classifier\n",
    "\n",
    "Here, I'll use the Decision Tree Classifier to model the problem at hand. I'll vary between a set of `max_features` and see which returns the best accuracy."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "dt_scores = []\n",
    "for i in range(1, len(X.columns) + 1):\n",
    "    dt_classifier = DecisionTreeClassifier(max_features = i, random_state = 0)\n",
    "    dt_classifier.fit(X_train, y_train)\n",
    "    dt_scores.append(dt_classifier.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "I selected the maximum number of features from 1 to 30 for split. Now, let's see the scores for each of those cases."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Decision Tree Classifier scores for different number of maximum features')"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot([i for i in range(1, len(X.columns) + 1)], dt_scores, color = 'green')\n",
    "for i in range(1, len(X.columns) + 1):\n",
    "    plt.text(i, dt_scores[i-1], (i, dt_scores[i-1]))\n",
    "plt.xticks([i for i in range(1, len(X.columns) + 1)])\n",
    "plt.xlabel('Max features')\n",
    "plt.ylabel('Scores')\n",
    "plt.title('Decision Tree Classifier scores for different number of maximum features')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The model achieved the best accuracy at three values of maximum features, `2`, `4` and `18`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The score for Decision Tree Classifier is 79.0% with [2, 4, 18] maximum features.\n"
     ]
    }
   ],
   "source": [
    "print(\"The score for Decision Tree Classifier is {}% with {} maximum features.\".format(dt_scores[17]*100, [2,4,18]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Random Forest Classifier\n",
    "\n",
    "Now, I'll use the ensemble method, Random Forest Classifier, to create the model and vary the number of estimators to see their effect."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "rf_scores = []\n",
    "estimators = [10, 100, 200, 500, 1000]\n",
    "for i in estimators:\n",
    "    rf_classifier = RandomForestClassifier(n_estimators = i, random_state = 0)\n",
    "    rf_classifier.fit(X_train, y_train)\n",
    "    rf_scores.append(rf_classifier.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The model is trained and the scores are recorded. Let's plot a bar plot to compare the scores."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Random Forest Classifier scores for different number of estimators')"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "colors = rainbow(np.linspace(0, 1, len(estimators)))\n",
    "plt.bar([i for i in range(len(estimators))], rf_scores, color = colors, width = 0.8)\n",
    "for i in range(len(estimators)):\n",
    "    plt.text(i, rf_scores[i], rf_scores[i])\n",
    "plt.xticks(ticks = [i for i in range(len(estimators))], labels = [str(estimator) for estimator in estimators])\n",
    "plt.xlabel('Number of estimators')\n",
    "plt.ylabel('Scores')\n",
    "plt.title('Random Forest Classifier scores for different number of estimators')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The maximum score is achieved when the total estimators are 100 or 500."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The score for Random Forest Classifier is 84.0% with [100, 500] estimators.\n"
     ]
    }
   ],
   "source": [
    "print(\"The score for Random Forest Classifier is {}% with {} estimators.\".format(rf_scores[1]*100, [100, 500]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Conclusion\n",
    "\n",
    "In this project, I used Machine Learning to predict whether a person is suffering from a heart disease. After importing the data, I analysed it using plots. Then, I did generated dummy variables for categorical features and scaled other features. \n",
    "I then applied four Machine Learning algorithms, `K Neighbors Classifier`, `Support Vector Classifier`, `Decision Tree Classifier` and `Random Forest Classifier`. I varied parameters across each model to improve their scores.\n",
    "In the end, `K Neighbors Classifier` achieved the highest score of `87%` with `8 nearest neighbors`."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}