{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7ctVNsZvi8OE"
      },
      "source": [
        "# 🛡️ SentinelNet — AI-Powered Network Intrusion Detection System (NIDS)\n",
        "\n",
        "**Dataset:** NSL-KDD  \n",
        "**Goal:** Classify network traffic as Normal / DoS / Probe / R2L / U2R using machine learning\n",
        "\n",
        "---\n",
        "\n",
        "## Project Modules\n",
        "| Week | Module |\n",
        "|------|--------|\n",
        "| 1 | Dataset Acquisition & Exploration |\n",
        "| 2 | Data Cleaning & Preprocessing |\n",
        "| 3 | Feature Engineering & Selection |\n",
        "| 4 | Supervised Model Training |\n",
        "| 5 | Anomaly Detection (Unsupervised) |\n",
        "| 6 | Model Evaluation & Fine-Tuning |\n",
        "| 7 | Alert Generation & Logging |\n",
        "| 8 | Documentation & Summary |"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "E5lqsSr3i8OI"
      },
      "source": [
        "---\n",
        "## 📦 Install Dependencies"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "sh1Jsy_9i8OK"
      },
      "outputs": [],
      "source": [
        "# Install required packages (run once)\n",
        "!pip install xgboost imbalanced-learn --quiet"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Rip8w4_Vi8OL"
      },
      "source": [
        "---\n",
        "## 🔧 Global Imports & Configuration"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "JrzAutU4i8OM",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "e28d3e59-b702-45b8-f20c-4e5f68642a55"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "XGBoost available.\n",
            "✅ All libraries imported and directories created.\n"
          ]
        }
      ],
      "source": [
        "import os\n",
        "import json\n",
        "import joblib\n",
        "import warnings\n",
        "import requests\n",
        "from datetime import datetime\n",
        "\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "\n",
        "from sklearn.preprocessing import (\n",
        "    LabelEncoder, StandardScaler, RobustScaler,\n",
        "    OneHotEncoder, label_binarize\n",
        ")\n",
        "from sklearn.model_selection import (\n",
        "    train_test_split, GridSearchCV,\n",
        "    StratifiedKFold, cross_val_score\n",
        ")\n",
        "from sklearn.ensemble import (\n",
        "    RandomForestClassifier, GradientBoostingClassifier, IsolationForest\n",
        ")\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from sklearn.neighbors import LocalOutlierFactor\n",
        "from sklearn.svm import OneClassSVM\n",
        "from sklearn.decomposition import PCA\n",
        "from sklearn.manifold import TSNE\n",
        "from sklearn.metrics import (\n",
        "    classification_report, confusion_matrix,\n",
        "    accuracy_score, f1_score,\n",
        "    precision_score, recall_score,\n",
        "    roc_curve, auc\n",
        ")\n",
        "from imblearn.over_sampling import SMOTE\n",
        "\n",
        "try:\n",
        "    from xgboost import XGBClassifier\n",
        "    XGBOOST_AVAILABLE = True\n",
        "    print('XGBoost available.')\n",
        "except ImportError:\n",
        "    XGBOOST_AVAILABLE = False\n",
        "    print('XGBoost not installed — will skip.')\n",
        "\n",
        "warnings.filterwarnings('ignore')\n",
        "plt.style.use('ggplot')\n",
        "sns.set_palette('husl')\n",
        "\n",
        "# ── Reproducibility ──────────────────────────────────────────────────────────\n",
        "RANDOM_STATE = 42\n",
        "np.random.seed(RANDOM_STATE)\n",
        "\n",
        "# ── Directories ──────────────────────────────────────────────────────────────\n",
        "DATA_DIR    = 'data'\n",
        "MODELS_DIR  = 'models'\n",
        "ALERTS_DIR  = 'alerts'\n",
        "PROC_DIR    = os.path.join(DATA_DIR, 'processed')\n",
        "\n",
        "for d in [DATA_DIR, MODELS_DIR, ALERTS_DIR, PROC_DIR]:\n",
        "    os.makedirs(d, exist_ok=True)\n",
        "\n",
        "print('✅ All libraries imported and directories created.')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rC3swRnSi8OM"
      },
      "source": [
        "---\n",
        "## 📋 NSL-KDD Column Schema & Attack Mapping"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "62mlko4gi8ON",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "517f0699-f8fb-4aaf-954d-1690efada188"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "✅ Schema and mappings defined.\n"
          ]
        }
      ],
      "source": [
        "# ── Column names for the NSL-KDD dataset ─────────────────────────────────────\n",
        "COLUMNS = [\n",
        "    'duration', 'protocol_type', 'service', 'flag', 'src_bytes', 'dst_bytes',\n",
        "    'land', 'wrong_fragment', 'urgent', 'hot', 'num_failed_logins',\n",
        "    'logged_in', 'num_compromised', 'root_shell', 'su_attempted', 'num_root',\n",
        "    'num_file_creations', 'num_shells', 'num_access_files', 'num_outbound_cmds',\n",
        "    'is_host_login', 'is_guest_login', 'count', 'srv_count', 'serror_rate',\n",
        "    'srv_serror_rate', 'rerror_rate', 'srv_rerror_rate', 'same_srv_rate',\n",
        "    'diff_srv_rate', 'srv_diff_host_rate', 'dst_host_count', 'dst_host_srv_count',\n",
        "    'dst_host_same_srv_rate', 'dst_host_diff_srv_rate', 'dst_host_same_src_port_rate',\n",
        "    'dst_host_srv_diff_host_rate', 'dst_host_serror_rate', 'dst_host_srv_serror_rate',\n",
        "    'dst_host_rerror_rate', 'dst_host_srv_rerror_rate', 'label', 'difficulty_level'\n",
        "]\n",
        "\n",
        "# ── Attack → category mapping ─────────────────────────────────────────────────\n",
        "ATTACK_MAPPING = {\n",
        "    'normal'          : 'normal',\n",
        "    # DoS\n",
        "    'back'            : 'DoS', 'land'       : 'DoS', 'neptune'  : 'DoS',\n",
        "    'pod'             : 'DoS', 'smurf'      : 'DoS', 'teardrop' : 'DoS',\n",
        "    'mailbomb'        : 'DoS', 'apache2'    : 'DoS', 'processtable': 'DoS', 'udpstorm': 'DoS',\n",
        "    # Probe\n",
        "    'satan'           : 'Probe', 'ipsweep'  : 'Probe', 'nmap'     : 'Probe',\n",
        "    'portsweep'       : 'Probe', 'mscan'    : 'Probe', 'saint'    : 'Probe',\n",
        "    # R2L\n",
        "    'guess_passwd'    : 'R2L', 'ftp_write'  : 'R2L', 'imap'      : 'R2L',\n",
        "    'phf'             : 'R2L', 'multihop'   : 'R2L', 'warezmaster': 'R2L',\n",
        "    'warezclient'     : 'R2L', 'spy'        : 'R2L', 'xlock'     : 'R2L',\n",
        "    'xsnoop'          : 'R2L', 'snmpguess'  : 'R2L', 'snmpgetattack': 'R2L',\n",
        "    'httptunnel'      : 'R2L', 'sendmail'   : 'R2L', 'named'     : 'R2L',\n",
        "    # U2R\n",
        "    'buffer_overflow' : 'U2R', 'loadmodule' : 'U2R', 'perl'      : 'U2R',\n",
        "    'rootkit'         : 'U2R', 'ps'         : 'U2R', 'xterm'     : 'U2R', 'sqlattack': 'U2R'\n",
        "}\n",
        "\n",
        "# ── Severity levels for alert generation ─────────────────────────────────────\n",
        "SEVERITY_MAP = {\n",
        "    'normal': 'None',\n",
        "    'DoS'   : 'Critical',\n",
        "    'Probe' : 'Medium',\n",
        "    'R2L'   : 'High',\n",
        "    'U2R'   : 'Critical',\n",
        "}\n",
        "SEVERITY_COLOR = {\n",
        "    'None'    : '#4CAF50',\n",
        "    'Medium'  : '#FF9800',\n",
        "    'High'    : '#F44336',\n",
        "    'Critical': '#9C27B0',\n",
        "}\n",
        "\n",
        "print('✅ Schema and mappings defined.')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nMBiXy_Ci8OO"
      },
      "source": [
        "---\n",
        "# 📅 Week 1 — Dataset Acquisition & Exploration"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "i-86VAt9i8OO",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "cbc41910-ab6b-459f-92d5-71deba868a55"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading NSL-KDD dataset...\n",
            "  ⬇ Downloading KDDTrain+.txt...\n",
            "  ✅ Saved → data/KDDTrain+.txt\n",
            "  ⬇ Downloading KDDTest+.txt...\n",
            "  ✅ Saved → data/KDDTest+.txt\n",
            "Done.\n"
          ]
        }
      ],
      "source": [
        "# ── Download NSL-KDD dataset ──────────────────────────────────────────────────\n",
        "URLS = {\n",
        "    'KDDTrain+.txt': 'https://raw.githubusercontent.com/defcom17/NSL_KDD/master/KDDTrain+.txt',\n",
        "    'KDDTest+.txt' : 'https://raw.githubusercontent.com/defcom17/NSL_KDD/master/KDDTest+.txt'\n",
        "}\n",
        "\n",
        "def download_file(url, filename):\n",
        "    path = os.path.join(DATA_DIR, filename)\n",
        "    if os.path.exists(path):\n",
        "        print(f'  ✔ Already exists: {filename}')\n",
        "        return\n",
        "    print(f'  ⬇ Downloading {filename}...')\n",
        "    try:\n",
        "        r = requests.get(url, stream=True)\n",
        "        r.raise_for_status()\n",
        "        with open(path, 'wb') as f:\n",
        "            for chunk in r.iter_content(chunk_size=8192):\n",
        "                f.write(chunk)\n",
        "        print(f'  ✅ Saved → {path}')\n",
        "    except Exception as e:\n",
        "        print(f'  ❌ Failed: {e}')\n",
        "\n",
        "print('Downloading NSL-KDD dataset...')\n",
        "for fname, url in URLS.items():\n",
        "    download_file(url, fname)\n",
        "print('Done.')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "5kJtQiG5i8OP",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 290
        },
        "outputId": "985558bb-5630-44dd-9cad-36a33247b54c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Train shape : (125973, 43)\n",
            "Test  shape : (22544, 43)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   duration protocol_type   service flag  src_bytes  dst_bytes  land  \\\n",
              "0         0           tcp  ftp_data   SF        491          0     0   \n",
              "1         0           udp     other   SF        146          0     0   \n",
              "2         0           tcp   private   S0          0          0     0   \n",
              "3         0           tcp      http   SF        232       8153     0   \n",
              "4         0           tcp      http   SF        199        420     0   \n",
              "\n",
              "   wrong_fragment  urgent  hot  ...  dst_host_same_srv_rate  \\\n",
              "0               0       0    0  ...                    0.17   \n",
              "1               0       0    0  ...                    0.00   \n",
              "2               0       0    0  ...                    0.10   \n",
              "3               0       0    0  ...                    1.00   \n",
              "4               0       0    0  ...                    1.00   \n",
              "\n",
              "   dst_host_diff_srv_rate  dst_host_same_src_port_rate  \\\n",
              "0                    0.03                         0.17   \n",
              "1                    0.60                         0.88   \n",
              "2                    0.05                         0.00   \n",
              "3                    0.00                         0.03   \n",
              "4                    0.00                         0.00   \n",
              "\n",
              "   dst_host_srv_diff_host_rate  dst_host_serror_rate  \\\n",
              "0                         0.00                  0.00   \n",
              "1                         0.00                  0.00   \n",
              "2                         0.00                  1.00   \n",
              "3                         0.04                  0.03   \n",
              "4                         0.00                  0.00   \n",
              "\n",
              "   dst_host_srv_serror_rate  dst_host_rerror_rate  dst_host_srv_rerror_rate  \\\n",
              "0                      0.00                  0.05                      0.00   \n",
              "1                      0.00                  0.00                      0.00   \n",
              "2                      1.00                  0.00                      0.00   \n",
              "3                      0.01                  0.00                      0.01   \n",
              "4                      0.00                  0.00                      0.00   \n",
              "\n",
              "     label  difficulty_level  \n",
              "0   normal                20  \n",
              "1   normal                15  \n",
              "2  neptune                19  \n",
              "3   normal                21  \n",
              "4   normal                21  \n",
              "\n",
              "[5 rows x 43 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-406fd153-5862-4330-b984-2cfb16055a2a\" class=\"colab-df-container\">\n",
              "    <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>duration</th>\n",
              "      <th>protocol_type</th>\n",
              "      <th>service</th>\n",
              "      <th>flag</th>\n",
              "      <th>src_bytes</th>\n",
              "      <th>dst_bytes</th>\n",
              "      <th>land</th>\n",
              "      <th>wrong_fragment</th>\n",
              "      <th>urgent</th>\n",
              "      <th>hot</th>\n",
              "      <th>...</th>\n",
              "      <th>dst_host_same_srv_rate</th>\n",
              "      <th>dst_host_diff_srv_rate</th>\n",
              "      <th>dst_host_same_src_port_rate</th>\n",
              "      <th>dst_host_srv_diff_host_rate</th>\n",
              "      <th>dst_host_serror_rate</th>\n",
              "      <th>dst_host_srv_serror_rate</th>\n",
              "      <th>dst_host_rerror_rate</th>\n",
              "      <th>dst_host_srv_rerror_rate</th>\n",
              "      <th>label</th>\n",
              "      <th>difficulty_level</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>tcp</td>\n",
              "      <td>ftp_data</td>\n",
              "      <td>SF</td>\n",
              "      <td>491</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.17</td>\n",
              "      <td>0.03</td>\n",
              "      <td>0.17</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.00</td>\n",
              "      <td>normal</td>\n",
              "      <td>20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0</td>\n",
              "      <td>udp</td>\n",
              "      <td>other</td>\n",
              "      <td>SF</td>\n",
              "      <td>146</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.60</td>\n",
              "      <td>0.88</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>normal</td>\n",
              "      <td>15</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0</td>\n",
              "      <td>tcp</td>\n",
              "      <td>private</td>\n",
              "      <td>S0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.10</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>1.00</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>neptune</td>\n",
              "      <td>19</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0</td>\n",
              "      <td>tcp</td>\n",
              "      <td>http</td>\n",
              "      <td>SF</td>\n",
              "      <td>232</td>\n",
              "      <td>8153</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.03</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.03</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>normal</td>\n",
              "      <td>21</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>tcp</td>\n",
              "      <td>http</td>\n",
              "      <td>SF</td>\n",
              "      <td>199</td>\n",
              "      <td>420</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>1.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>normal</td>\n",
              "      <td>21</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 43 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-406fd153-5862-4330-b984-2cfb16055a2a')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-406fd153-5862-4330-b984-2cfb16055a2a button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-406fd153-5862-4330-b984-2cfb16055a2a');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df_train_raw"
            }
          },
          "metadata": {},
          "execution_count": 5
        }
      ],
      "source": [
        "# ── Load raw data ─────────────────────────────────────────────────────────────\n",
        "TRAIN_PATH = os.path.join(DATA_DIR, 'KDDTrain+.txt')\n",
        "TEST_PATH  = os.path.join(DATA_DIR, 'KDDTest+.txt')\n",
        "\n",
        "df_train_raw = pd.read_csv(TRAIN_PATH, header=None, names=COLUMNS)\n",
        "df_test_raw  = pd.read_csv(TEST_PATH,  header=None, names=COLUMNS)\n",
        "\n",
        "print(f'Train shape : {df_train_raw.shape}')\n",
        "print(f'Test  shape : {df_test_raw.shape}')\n",
        "df_train_raw.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "xynVHyt4i8OP",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "8a0e481e-5857-4a34-ff1a-094f25acf7a8"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "--- Dataset Info ---\n",
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 125973 entries, 0 to 125972\n",
            "Data columns (total 43 columns):\n",
            " #   Column                       Non-Null Count   Dtype  \n",
            "---  ------                       --------------   -----  \n",
            " 0   duration                     125973 non-null  int64  \n",
            " 1   protocol_type                125973 non-null  object \n",
            " 2   service                      125973 non-null  object \n",
            " 3   flag                         125973 non-null  object \n",
            " 4   src_bytes                    125973 non-null  int64  \n",
            " 5   dst_bytes                    125973 non-null  int64  \n",
            " 6   land                         125973 non-null  int64  \n",
            " 7   wrong_fragment               125973 non-null  int64  \n",
            " 8   urgent                       125973 non-null  int64  \n",
            " 9   hot                          125973 non-null  int64  \n",
            " 10  num_failed_logins            125973 non-null  int64  \n",
            " 11  logged_in                    125973 non-null  int64  \n",
            " 12  num_compromised              125973 non-null  int64  \n",
            " 13  root_shell                   125973 non-null  int64  \n",
            " 14  su_attempted                 125973 non-null  int64  \n",
            " 15  num_root                     125973 non-null  int64  \n",
            " 16  num_file_creations           125973 non-null  int64  \n",
            " 17  num_shells                   125973 non-null  int64  \n",
            " 18  num_access_files             125973 non-null  int64  \n",
            " 19  num_outbound_cmds            125973 non-null  int64  \n",
            " 20  is_host_login                125973 non-null  int64  \n",
            " 21  is_guest_login               125973 non-null  int64  \n",
            " 22  count                        125973 non-null  int64  \n",
            " 23  srv_count                    125973 non-null  int64  \n",
            " 24  serror_rate                  125973 non-null  float64\n",
            " 25  srv_serror_rate              125973 non-null  float64\n",
            " 26  rerror_rate                  125973 non-null  float64\n",
            " 27  srv_rerror_rate              125973 non-null  float64\n",
            " 28  same_srv_rate                125973 non-null  float64\n",
            " 29  diff_srv_rate                125973 non-null  float64\n",
            " 30  srv_diff_host_rate           125973 non-null  float64\n",
            " 31  dst_host_count               125973 non-null  int64  \n",
            " 32  dst_host_srv_count           125973 non-null  int64  \n",
            " 33  dst_host_same_srv_rate       125973 non-null  float64\n",
            " 34  dst_host_diff_srv_rate       125973 non-null  float64\n",
            " 35  dst_host_same_src_port_rate  125973 non-null  float64\n",
            " 36  dst_host_srv_diff_host_rate  125973 non-null  float64\n",
            " 37  dst_host_serror_rate         125973 non-null  float64\n",
            " 38  dst_host_srv_serror_rate     125973 non-null  float64\n",
            " 39  dst_host_rerror_rate         125973 non-null  float64\n",
            " 40  dst_host_srv_rerror_rate     125973 non-null  float64\n",
            " 41  label                        125973 non-null  object \n",
            " 42  difficulty_level             125973 non-null  int64  \n",
            "dtypes: float64(15), int64(24), object(4)\n",
            "memory usage: 41.3+ MB\n",
            "\n",
            "--- Descriptive Statistics ---\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "           duration     src_bytes     dst_bytes           land  \\\n",
              "count  125973.00000  1.259730e+05  1.259730e+05  125973.000000   \n",
              "mean      287.14465  4.556674e+04  1.977911e+04       0.000198   \n",
              "std      2604.51531  5.870331e+06  4.021269e+06       0.014086   \n",
              "min         0.00000  0.000000e+00  0.000000e+00       0.000000   \n",
              "25%         0.00000  0.000000e+00  0.000000e+00       0.000000   \n",
              "50%         0.00000  4.400000e+01  0.000000e+00       0.000000   \n",
              "75%         0.00000  2.760000e+02  5.160000e+02       0.000000   \n",
              "max     42908.00000  1.379964e+09  1.309937e+09       1.000000   \n",
              "\n",
              "       wrong_fragment         urgent            hot  num_failed_logins  \\\n",
              "count   125973.000000  125973.000000  125973.000000      125973.000000   \n",
              "mean         0.022687       0.000111       0.204409           0.001222   \n",
              "std          0.253530       0.014366       2.149968           0.045239   \n",
              "min          0.000000       0.000000       0.000000           0.000000   \n",
              "25%          0.000000       0.000000       0.000000           0.000000   \n",
              "50%          0.000000       0.000000       0.000000           0.000000   \n",
              "75%          0.000000       0.000000       0.000000           0.000000   \n",
              "max          3.000000       3.000000      77.000000           5.000000   \n",
              "\n",
              "           logged_in  num_compromised  ...  dst_host_srv_count  \\\n",
              "count  125973.000000    125973.000000  ...       125973.000000   \n",
              "mean        0.395736         0.279250  ...          115.653005   \n",
              "std         0.489010        23.942042  ...          110.702741   \n",
              "min         0.000000         0.000000  ...            0.000000   \n",
              "25%         0.000000         0.000000  ...           10.000000   \n",
              "50%         0.000000         0.000000  ...           63.000000   \n",
              "75%         1.000000         0.000000  ...          255.000000   \n",
              "max         1.000000      7479.000000  ...          255.000000   \n",
              "\n",
              "       dst_host_same_srv_rate  dst_host_diff_srv_rate  \\\n",
              "count           125973.000000           125973.000000   \n",
              "mean                 0.521242                0.082951   \n",
              "std                  0.448949                0.188922   \n",
              "min                  0.000000                0.000000   \n",
              "25%                  0.050000                0.000000   \n",
              "50%                  0.510000                0.020000   \n",
              "75%                  1.000000                0.070000   \n",
              "max                  1.000000                1.000000   \n",
              "\n",
              "       dst_host_same_src_port_rate  dst_host_srv_diff_host_rate  \\\n",
              "count                125973.000000                125973.000000   \n",
              "mean                      0.148379                     0.032542   \n",
              "std                       0.308997                     0.112564   \n",
              "min                       0.000000                     0.000000   \n",
              "25%                       0.000000                     0.000000   \n",
              "50%                       0.000000                     0.000000   \n",
              "75%                       0.060000                     0.020000   \n",
              "max                       1.000000                     1.000000   \n",
              "\n",
              "       dst_host_serror_rate  dst_host_srv_serror_rate  dst_host_rerror_rate  \\\n",
              "count         125973.000000             125973.000000         125973.000000   \n",
              "mean               0.284452                  0.278485              0.118832   \n",
              "std                0.444784                  0.445669              0.306557   \n",
              "min                0.000000                  0.000000              0.000000   \n",
              "25%                0.000000                  0.000000              0.000000   \n",
              "50%                0.000000                  0.000000              0.000000   \n",
              "75%                1.000000                  1.000000              0.000000   \n",
              "max                1.000000                  1.000000              1.000000   \n",
              "\n",
              "       dst_host_srv_rerror_rate  difficulty_level  \n",
              "count             125973.000000     125973.000000  \n",
              "mean                   0.120240         19.504060  \n",
              "std                    0.319459          2.291503  \n",
              "min                    0.000000          0.000000  \n",
              "25%                    0.000000         18.000000  \n",
              "50%                    0.000000         20.000000  \n",
              "75%                    0.000000         21.000000  \n",
              "max                    1.000000         21.000000  \n",
              "\n",
              "[8 rows x 39 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-bfe917d0-6e1f-4487-97b9-6d3fb1b7c823\" class=\"colab-df-container\">\n",
              "    <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>duration</th>\n",
              "      <th>src_bytes</th>\n",
              "      <th>dst_bytes</th>\n",
              "      <th>land</th>\n",
              "      <th>wrong_fragment</th>\n",
              "      <th>urgent</th>\n",
              "      <th>hot</th>\n",
              "      <th>num_failed_logins</th>\n",
              "      <th>logged_in</th>\n",
              "      <th>num_compromised</th>\n",
              "      <th>...</th>\n",
              "      <th>dst_host_srv_count</th>\n",
              "      <th>dst_host_same_srv_rate</th>\n",
              "      <th>dst_host_diff_srv_rate</th>\n",
              "      <th>dst_host_same_src_port_rate</th>\n",
              "      <th>dst_host_srv_diff_host_rate</th>\n",
              "      <th>dst_host_serror_rate</th>\n",
              "      <th>dst_host_srv_serror_rate</th>\n",
              "      <th>dst_host_rerror_rate</th>\n",
              "      <th>dst_host_srv_rerror_rate</th>\n",
              "      <th>difficulty_level</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>125973.00000</td>\n",
              "      <td>1.259730e+05</td>\n",
              "      <td>1.259730e+05</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "      <td>125973.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>287.14465</td>\n",
              "      <td>4.556674e+04</td>\n",
              "      <td>1.977911e+04</td>\n",
              "      <td>0.000198</td>\n",
              "      <td>0.022687</td>\n",
              "      <td>0.000111</td>\n",
              "      <td>0.204409</td>\n",
              "      <td>0.001222</td>\n",
              "      <td>0.395736</td>\n",
              "      <td>0.279250</td>\n",
              "      <td>...</td>\n",
              "      <td>115.653005</td>\n",
              "      <td>0.521242</td>\n",
              "      <td>0.082951</td>\n",
              "      <td>0.148379</td>\n",
              "      <td>0.032542</td>\n",
              "      <td>0.284452</td>\n",
              "      <td>0.278485</td>\n",
              "      <td>0.118832</td>\n",
              "      <td>0.120240</td>\n",
              "      <td>19.504060</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>2604.51531</td>\n",
              "      <td>5.870331e+06</td>\n",
              "      <td>4.021269e+06</td>\n",
              "      <td>0.014086</td>\n",
              "      <td>0.253530</td>\n",
              "      <td>0.014366</td>\n",
              "      <td>2.149968</td>\n",
              "      <td>0.045239</td>\n",
              "      <td>0.489010</td>\n",
              "      <td>23.942042</td>\n",
              "      <td>...</td>\n",
              "      <td>110.702741</td>\n",
              "      <td>0.448949</td>\n",
              "      <td>0.188922</td>\n",
              "      <td>0.308997</td>\n",
              "      <td>0.112564</td>\n",
              "      <td>0.444784</td>\n",
              "      <td>0.445669</td>\n",
              "      <td>0.306557</td>\n",
              "      <td>0.319459</td>\n",
              "      <td>2.291503</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>0.00000</td>\n",
              "      <td>0.000000e+00</td>\n",
              "      <td>0.000000e+00</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",
              "      <td>0.000000</td>\n",
              "      <td>...</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",
              "      <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>0.00000</td>\n",
              "      <td>0.000000e+00</td>\n",
              "      <td>0.000000e+00</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",
              "      <td>0.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>10.000000</td>\n",
              "      <td>0.050000</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",
              "      <td>0.000000</td>\n",
              "      <td>18.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>0.00000</td>\n",
              "      <td>4.400000e+01</td>\n",
              "      <td>0.000000e+00</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",
              "      <td>0.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>63.000000</td>\n",
              "      <td>0.510000</td>\n",
              "      <td>0.020000</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",
              "      <td>20.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>0.00000</td>\n",
              "      <td>2.760000e+02</td>\n",
              "      <td>5.160000e+02</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>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>255.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.070000</td>\n",
              "      <td>0.060000</td>\n",
              "      <td>0.020000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>21.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>42908.00000</td>\n",
              "      <td>1.379964e+09</td>\n",
              "      <td>1.309937e+09</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>77.000000</td>\n",
              "      <td>5.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>7479.000000</td>\n",
              "      <td>...</td>\n",
              "      <td>255.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>21.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>8 rows × 39 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-bfe917d0-6e1f-4487-97b9-6d3fb1b7c823')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-bfe917d0-6e1f-4487-97b9-6d3fb1b7c823 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-bfe917d0-6e1f-4487-97b9-6d3fb1b7c823');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe"
            }
          },
          "metadata": {},
          "execution_count": 6
        }
      ],
      "source": [
        "# ── Basic statistics ──────────────────────────────────────────────────────────\n",
        "print('\\n--- Dataset Info ---')\n",
        "df_train_raw.info()\n",
        "print('\\n--- Descriptive Statistics ---')\n",
        "df_train_raw.describe()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "CcOCVQo2i8OQ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "9ff46590-3556-4851-ab6e-403a755d8135"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Unique attack labels in training set: 23\n",
            "label\n",
            "normal             67343\n",
            "neptune            41214\n",
            "satan               3633\n",
            "ipsweep             3599\n",
            "portsweep           2931\n",
            "smurf               2646\n",
            "nmap                1493\n",
            "back                 956\n",
            "teardrop             892\n",
            "warezclient          890\n",
            "pod                  201\n",
            "guess_passwd          53\n",
            "buffer_overflow       30\n",
            "warezmaster           20\n",
            "land                  18\n",
            "imap                  11\n",
            "rootkit               10\n",
            "loadmodule             9\n",
            "ftp_write              8\n",
            "multihop               7\n",
            "phf                    4\n",
            "perl                   3\n",
            "spy                    2\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "# ── Attack type distribution ──────────────────────────────────────────────────\n",
        "print('Unique attack labels in training set:', df_train_raw['label'].nunique())\n",
        "print(df_train_raw['label'].value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "gtWu1x7Wi8OQ",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 366
        },
        "outputId": "fa7c1de5-0815-4f15-cafb-81fc4ff179c8"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1300x500 with 2 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABQkAAAHvCAYAAAD3rFl5AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAsJFJREFUeJzs3XlcVdX+//H3YQYBQYGAFHDGEbWcB9ScM8dSS1Mj9ZaadctKzdIsNfPmzUpTc67UyJynBq9DTuWQOc/iEKiQgokiIPv3hz/21xOgRwMRz+v5ePC4nr3XXvuzP+d0WXzO2mtbDMMwBAAAAAAAAMBuOeR3AAAAAAAAAADyF0VCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsHEVCAACQ72bNmiWLxaJ169bldyiAlREjRshisSgmJia/Q7mlRo0aKSwsLL/DAAAABRhFQgAA7MDq1atlsVg0bNiwLPu2bt0qi8UiV1dXXblyJcv+li1bysHBQQkJCfci1Ls2ZcoUdevWTeHh4XJ0dJTFYsnvkKysW7dOFovF/HF0dJSvr68qVaqknj17avXq1TIM4x+dY9euXRoxYsR9WdCaNWuWPv744zs6JiwszCpnf//56quv8ibY+9THH3+sWbNm5XcYAADgAeWU3wEAAIC8V79+fTk5OWU7U2/t2rVycnJSamqqNm/erKZNm5r70tPTtXHjRlWqVEl+fn73MOI7N2bMGP3555+qVq2akpOTdebMmfwOKVtPP/20WrduLcMw9Ndff+nQoUNavHix5syZo6ZNm+rbb7+Vj4/PXfW9a9cuvfvuu/flrLJZs2YpJiZGr7zyyh0dV6xYMY0ZMybbffXq1cuFyAqOjz/+WGFhYerVq1eWfT/88MM/LjIDAAD7RpEQAAA74OnpqRo1amjbtm26cuWKPDw8zH3r1q1Ts2bN9Ntvv2ndunVWRcJt27YpOTlZjRo1yoeo78y6desUEhIiBwcHtWnT5r4tElavXl3du3e32jZ+/Hi98cYbGj9+vJ5++mmtWrUqn6K7/xQuXDhLvgq6tLQ0Xb9+XW5ubrnWp4uLS671BQAA7BO3GwMAYCcaN26s1NRUbdq0ydyWnp6uTZs2KTIyUpGRkVq7dq3VMZkzDxs3bmxui4uL04svvqiQkBC5uLgoODhYffv21fnz57OcMykpSW+++aZKly4tV1dX+fv76+mnn9bx48dtinnUqFGyWCx66aWXlJGRccu2YWFhcnAomEMbR0dHffTRR6pfv75Wr16tjRs3mvtiY2P12muvqWrVqvL19ZWbm5sqVKigsWPH6vr162a7ESNG6LnnnpN04/3KvCU3c9bZX3/9pWHDhqlWrVry8/OTq6urSpcurcGDB2e5zTwjI0Mff/yxqlSpIi8vL3l7e6tcuXJ6/vnnlZaWZtV2+/bt6tChg9lnuXLlNGrUKKWnp5ttwsLCtH79ep08edLqduHcWoPyt99+k5ubm5o1a2Y1m+769etq2LChPDw8tHfvXklSTEyMLBaLRowYoXnz5qlKlSpyc3NTSEiIRowYYRX3rcTExOjZZ5/VQw89JFdXV5UqVUpDhw7NksvMNQ337dunV199VcWKFZObm5u2bt0qSfrmm2/Utm1bhYSEyNXVVX5+fmrfvr12795t1Y/FYtHJkye1fv16qxxm3lqe0+zRDRs2qFmzZipcuLDc3d1VvXp1TZ8+PUu7zONjY2P19NNPy9fXVx4eHmrRooUOHz5sU04AAEDBxkxCAADsROPGjTV69Ghz5qD0fzMFIyMj5e3trZdfflnJyckqVKiQpP9bRy8yMlKSdOrUKdWpU0epqal6/vnnVapUKR09elSff/651q5dq+3bt6tw4cKSbhQI69atq1OnTikqKkoVK1ZUXFycJk2apFq1amn79u0KDQ3NNtbr169rwIABmjx5ssaMGaPBgwffgwzlv+eff14bN27UihUrVL9+fUnS7t27tXDhQnXo0EGlSpVSWlqaVq9ercGDB+v48eOaMmWKJKljx46Ki4vT1KlTNXToUJUvX16SVKpUKUnSH3/8oWnTpqlTp0565pln5OTkpPXr1+vDDz/Ub7/9pu+//96MY9SoUXrnnXf0xBNP6IUXXpCjo6NOnDihpUuX6tq1a3J2dpYkrVixQh07dlTp0qX12muvqUiRItqyZYveeecd7dq1S99++62kG7fJDhkyRAkJCfrvf/9rniczxlu5fv16juthFi1aVBaLRdWqVdOHH36ol19+WR988IGGDBkiSXr33Xf1888/a/LkyapUqZLVsUuXLtXx48fVv39/BQYGaunSpXr33Xd18uRJzZw585YxnTx5UjVr1lRSUpL69eunMmXKaN26dRozZow2bdqkNWvWyMnJepjdrVs3ubu767XXXpPFYlFQUJAk6bPPPlPRokXVt29fBQYG6tixY5o6darq1aunnTt3qkyZMpKkL7/8Uv/+97/l5+ent956y+zX398/xziXLVumDh06KDAwUK+99pq8vLw0f/589e7dW8ePH9eoUaOs2icnJ6thw4aqXbu2Ro8erRMnTmjChAlq166d9u7dK0dHx1vmBQAAFHAGAACwC1euXDFcXFyMOnXqmNtGjx5teHp6Gmlpacb+/fsNScb3339vGIZhpKWlGYUKFTIiIiLM9m3btjX8/f2N06dPW/W9bds2w9HR0Rg+fLi5beDAgYabm5uxa9cuq7YxMTGGl5eX0bNnT3PbzJkzDUnG2rVrjStXrhjt27c3nJ2djdmzZ9/VtT7++OPG/TbMWbt2rSHJGDduXI5tduzYYUgyOnbsaG67cuWKkZGRkaVt9+7dDQcHByM2NtbcdnMe/+7atWtGampqlu3Dhg0zJBm//PKLua1atWpG+fLlb3k9V69eNR566CGjQYMGRlpamtW+8ePHZ4kjMjLSCA0NvWWffxcaGmpIyvEnPj7eqn3btm0NJycnY8uWLcbatWsNBwcHo1OnTlZtTpw4YUgyHBwcjB07dpjbMzIyjPbt2xuSjC1btpjbhw8fbkgyTpw4YW575plnDEnGihUrrPoeNGiQIcmYNm1aluMjIyOz5MkwDOPy5ctZtu3fv99wcXExXnzxxSz5iIyMzDZXf89venq6ERISYhQuXNj4448/zO3Xrl0z6tatazg4OBiHDx+2Ol6SMXbsWKt+P/zwQ0OSsXr16mzPCwAAHhwF854cAABwx9zd3c0ZfMnJyZJuzBSsW7eunJycVL58eQUEBJi3gGbOMsy81TgpKUnLly9X27Zt5ebmpoSEBPMnLCxMpUuX1g8//CBJMgxDX3/9tRo2bKiHH37Yqm2hQoVUu3Zts+3NLly4oGbNmumnn37SsmXL1KNHj3uTnPuEt7e3JOnSpUvmNnd3d/NJzampqbpw4YISEhLUokULZWRkaPv27Tb17eLiYs4ATE9P18WLF5WQkGCuQfnLL7+YbQsXLqw//vjD6rbnv/vxxx917tw5Pffcc0pMTLR6j1u3bi1J2b7HdyosLEw//vhjtj+Zs1YzzZw5U4GBgXr66afVvXt3FS9eXNOmTcu232bNmql69erma4vFojfeeEOStGjRohzjycjI0NKlS1WtWjXzOjMNGTJEDg4O2R7/yiuvZJldKMmctWsYhi5duqSEhAT5+/urXLlyVu/JndqxY4c5izc4ONjc7uLiojfeeEMZGRlasmSJ1TEODg4aOHCg1bYmTZpIko4cOXLXsQAAgIKB240BALAjjRs31s8//6yNGzfqscce06ZNmzR06FBzf8OGDc11CTOLhZkPLTl06JAyMjI0ffr0bNc0k6SSJUtKkuLj4/Xnn3/qhx9+yPF2yOzWD+zVq5cuX76sDRs2mLfb3ivx8fFWa/zdqcw13/6JzOJgZrFQulHQ++CDDzRnzhwdPXo0yxNsL168aHP/kyZN0uTJk7Vv374sazze3M/o0aPVvn17NWjQQMHBwWrUqJEef/xxPfnkk+YDMg4cOCBJioqKyvF8586dszm2nBQqVMjqYTq3UqRIEc2cOdO8nX7jxo05Pik6u1udK1SoIEm3XDMzPj5ely9fVsWKFbM9f1BQULbHly1bNtv+fvvtN7399ttat26dWbzPVKJEiRzjuJ0TJ05IUrZxZm77e5zBwcFZHqZStGhRSdKff/5517EAAICCgSIhAAB2pHHjxho5cqTWrVsnb29vcz3CTJGRkfr3v/+ty5cva926dXJwcFDDhg0lySxOde/eXT179sy2/8wiWWbbpk2b6s0337Q5vi5dumjmzJl67733tHjx4n9cdLsTNWrU0MmTJ+/6+JkzZ5oPCblbmQ+rKFeunLnt1Vdf1aeffqouXbrorbfeUkBAgJydnbVz5069+eabt32gS6bx48frtddeU/PmzTVw4EAFBwfLxcVFf/zxh3r16mXVT506dXTs2DF9//33Wrt2rdauXau5c+fq/fff18aNG1WkSBHzPR43bpyqVq2a7TlvnsF2ryxdutT8965du1SvXr17HkN2bn6ieKZTp06pYcOG8vb21ttvv61y5cqpUKFCslgseuWVV3T58uV7GuOt1hz8e3EaAAA8eCgSAgBgR+rUqSM3NzetXbtW3t7ecnd3V40aNcz9kZGRSk9P17p167Rp0ybzibqSVLp0aVksFqWmpt52Zpe/v798fHx06dIlm2eBSTce7vDYY4/p2WefVZs2bbRs2bJsiyt54euvv9bVq1fv+vjsZmzdqcwZmo8//ri57csvv1TDhg01f/58q7ZHjx7NcnzmbcnZ+fLLLxUWFqZVq1ZZzeJcvXp1tu09PT3VqVMnderUSdKNWYj9+/fX9OnT9frrr5sP1LB1pt+tYsstS5cu1aeffqrnnntOR48e1aBBg9SwYUNVrlw5S9vMmZA3279/v6T/mxGbHX9/f3l5eWnfvn1Z9l28eFFxcXE5Fk3/btGiRbp8+bKWLl1q9QRx6cbMPVdXV6ttd5LDzGvILk5brhMAANgfioQAANgRV1dX1alTRz///LMcHR1Vp04d8/ZRSapUqZKKFi2qcePGKTk52bzVWLpx22Hr1q21cOFCbd26VbVr17bq2zAMcz01BwcHdevWTRMnTtSCBQv05JNPZonl/PnzCggIyLK9a9eucnJy0jPPPKNWrVppxYoV8vT0zL0k5CA/Z5xdv35db775pjZu3KjWrVtbxeLo6JhlFldycrLVU4IzZebpwoULWfY5OjrKYrFY9ZV5K/PfJSQkyM/Pz2pb5vp9mX23aNFCAQEB+uCDD9SlSxcVKVLEqv3Vq1eVnp4uLy8vM7aLFy/KMIw8KRj+8ccfioqKUvny5fXZZ5/pzz//VEREhLp27art27dnmZX6448/aufOneZ1GYahDz/8UJLUvn37HM/j4OCgJ554QnPnztXq1avVsmVLc98HH3ygjIwMdejQwaaYM2fu/f39/eKLL3T27NksT//29PTM9r3NTvXq1RUSEqKZM2fqjTfeUGBgoCQpLS1N48aNk8ViUbt27WzqCwAA2AeKhAAA2JnGjRtr7dq12rx5s959912rfRaLRQ0aNNDixYvNtjf7/PPPVb9+fTVs2FA9evRQtWrVlJGRoePHj2vJkiXq0aOHRowYIUkaNWqUNm3apM6dO6tz586qXbu2XFxcdPLkSa1cuVKPPPKIZs2alW2MTz75pJydndW5c2e1aNFCq1atslqnLzvLli3T77//Lun/Ztm9//77kiQfHx8NGDDgTtKUZ3bu3KmvvvpKkvTXX3/p0KFDWrx4sU6ePKnmzZtr7ty5Vu2ffPJJTZkyRV26dFHTpk117tw5zZgxw1wr7mY1atSQg4ODRo0apYsXL6pQoUIqUaKEatWqpSeffFJDhgxRq1at1LFjR126dElz5841H2Zys/Lly6t27dqqVauWgoODFRcXp6lTp8rFxUVdu3aVdGMG4Zw5c9S+fXuVK1dOUVFRKl26tBITE3Xw4EEtXLhQixYtMgvNtWvX1vLlyzVgwADVrVtXjo6OatKkSbaF4pslJSWZ+fq7ypUrKyIiQhkZGerWrZuSk5P1zTffyMPDQx4eHpo+fbo6duyoV155RVOmTLE6NiIiQk2aNFH//v0VFBSkJUuW6KefftKzzz6rOnXq3DKm0aNH68cff1T79u3Vr18/lS5dWhs2bNA333yjhg0b5ng7/t+1atVKHh4eevbZZzVgwAD5+vpq06ZNWrlypUqVKqX09HSr9rVr19b06dP19ttvq3z58mbBMvPhJzdzdHTUZ599pg4dOqhGjRrq27evvLy89M0332jr1q0aOnSoORsUAABAkpQvz1QGAAD55ueffzYkGZKMdevWZdn/3//+15BkODo6GomJiVn2x8fHG4MGDTLKlCljuLq6GoULFzYqVapkDBw40Ni3b59V2+TkZGPkyJFGpUqVDDc3N8PT09MIDw83evfubWzdutVsN3PmTEOSsXbtWqvjly9fbri6uhq1atXKNpab9ezZ07yuv/+EhobanqA8snbtWquYHBwcDG9vb6NChQpGjx49jFWrVmV7XHJysjFo0CAjJCTEcHV1NUqXLm2MGTPG+OmnnwxJxsyZM63az5o1yyhfvrzh7OxsSDJ69uxpGIZhpKenG6NHjzZKlSpluLi4GCEhIcbrr79u7N+/35BkDB8+3OxjzJgxRoMGDQx/f3/DxcXFKFasmPHkk08aO3bsyBLfnj17jG7duhnBwcGGs7OzERAQYNSpU8cYOXKk8eeff1pdR1RUlBEQEGA4ODhk+37/XWhoaI7vqSTjrbfeMgzDMN59911DkjFp0qQsffTr18+QZCxYsMAwDMM4ceKEeb1z5841KleubF7j22+/baSmplodP3z4cEOSceLECavtx48fN7p37274+/sbzs7ORokSJYwhQ4YYycnJNh2faf369Ua9evUMT09Po3Dhwkbr1q2NPXv2GJGRkVk+t+fOnTM6duxo+Pr6GhaLxarf7NobhmGsW7fOaNq0qeHl5WW4uroaVatWNaZNm5alXU7H35wvAADwYLMYBqsQAwAAwD7ExMSoRIkSGj58uDnrFQAAAJLD7ZsAAAAAAAAAeJBRJAQAAAAAAADsHEVCAAAAAAAAwM6xJiEAAAAAAABg55hJCAAAAAAAANg5ioQAAAAAAACAnaNICAAAAAAAANg5ioQAAAAAAACAnaNICAAAAAAAANg5ioQAAAAAAACAnaNICAAAAAAAANg5ioQAAAAAAACAnaNICAAAAAAAANg5ioQAAAAAAACAnaNICAAAAAAAANg5ioQAAAAAAACAnaNICAAAAAAAANg5ioQAAAAAAACAnaNICAAAAAAAANg5ioQAAAAAAACAnaNICAAAAAAAANg5ioQAAAAAAACAnaNICAAAAAAAANg5ioQAbmnevHmqVq2avLy8ZLFY9Morr5j7fvjhB9WtW1c+Pj6yWCxq3769JKlRo0ayWCz5E/A/NGLECFksFq1bty6/Q8kzYWFhCgsLy+8wcBsF+b8jAABw/5k1a5YsFotmzZqV36EAuE9RJATuYxaL5Y5+cvsX/pYtW9StWzf99ddfevHFFzV8+HC1bNlSkhQTE6N27drpxIkTioqK0vDhw9W1a9dcPf/NvvjiC1ksFnXu3Pm2bUePHi2LxaKXX345z+LB3cksfN384+XlpUceeUSjR4/W1atX8+zcMTExslgs6tWrV56dAwCAgiC/x5i2OnDggIYPH6527dopJCTEjCc9Pf2Wx124cEGvvPKKwsLC5OrqquDgYEVFRenMmTN3Hcvp06fl6Ogoi8WioUOH5tjudl849+rVSxaLRTExMXcdS35Zt27dHX92CuJ1AvbMKb8DAJCz4cOHZ9n28ccfKykpSS+//LJ8fHys9lWtWjVXz79ixQoZhqE5c+aobt26Vvt++uknpaSk6KOPPtIzzzxjtW/OnDm6cuVKrsby9NNP69VXX9WSJUuUkJAgPz+/bNsZhqHp06dLkvr27ZurMSD39OzZU2FhYTIMQ2fOnNHChQv11ltvacmSJdq4caOcnZ3zO0QAAB5Y+T3GtNX333+vkSNHytHRUWXKlJGbm5tSUlJuecyff/6punXr6vDhw2rSpIm6du2qgwcPaubMmVqxYoW2bNmikiVL3nEs06ZNU0ZGhiwWi2bOnKmRI0fKycm+/pwOCwvL8tlJTEzUhAkTVLhwYas7jjL9/bME4P5mX/+vBhQwI0aMyLJt1qxZSkpKMr8dzUuxsbGSpODg4DvaFxISkuuxeHp66umnn9YXX3yhOXPm6NVXX8223f/+9z8dP35cdevWVcWKFXM9DuSOXr16qVGjRubr999/X9WqVdOvv/6quXPnqmfPnvkXHAAAD7j8HmPaqlWrVqpTp46qVKkid3d3hYWF6eTJk7c8ZujQoTp8+LBeffVVffTRR+b2Tz75RC+//LL69eun1atX31Ec169f14wZM+Tt7a3u3btr0qRJWrp0qTp27HhX11VQhYWFZfnsxMTEaMKECfLx8cn2cwWgYOF2Y+ABkXkbZ2pqqkaOHKly5crJ1dXVvLUyKSlJ48aNU5MmTVSsWDG5uLjI399fbdu21ZYtW6z6ylyvZObMmZKkEiVKWN1uYrFYzG8RGzdubO7LvK3iVmup/fDDD3riiScUEBAgV1dXFS9eXO3atdNPP/1022vMnBk4bdq0HNt88cUXVm0l6ciRI+rRo4cefvhhubi4KDg4WD169NCRI0due07p9repZne9mbdjjBgxQtu3b1fLli1VuHBh+fr6qlOnTjp9+rQk6fjx4+ratav8/f3l7u6uxo0b6/fff8/2PFeuXNGYMWNUtWpVFSpUSJ6enqpTp47mzZtn03X8XVJSkgYMGKCHH35Ybm5uqlChgj755BMZhmG2OXjwoCwWixo3bpxjP5UrV5azs7Pi4uLuKg5JCgoKMgfav/76qyTrHP766696/PHHVaRIEatbV65du6YPPvhAlStXloeHh7y9vdWgQQNFR0db9T9ixAiVKFFCkjR79uwcb6HKyMjQ5MmTVaNGDXl6eqpQoUKqUaOGPv/8c2VkZGQb+8GDBxUVFWXe0hQQEKAGDRro888/z9J2zZo1atmypYoUKSJXV1eVLVtWgwcPVlJS0l3nDgCAvBYdHa2GDRuqcOHCcnd3V+XKlTVmzBhdu3YtS9vMtY9tGWfcTrly5VSrVi25u7vb1P7y5cv68ssvVahQoSwFqwEDBig0NFTff/+9jh8/bnMMkrRq1SqdOXNGXbp00Ysvvijp/8acNwsLC9O7774ryXqMnDlOtFgsmj17tiTr8fXNRdkdO3bo5ZdfVkREhIoUKSI3NzeVKVNGr732mi5evJhjjN98840ee+wx85iwsDA9/fTT2r59+22v7+LFi2rYsKEcHBw0ZswYm/OSk7sZP9487tuyZYuaNm2qwoULy8vLSy1atMjxOtLT0zVp0iTVrl1b3t7e8vDwULVq1fTZZ59lO3ZbunSpHnvsMQUFBZm3okdGRmrSpEn/+LqBBwEzCYEHTKdOnbRt2za1atVK7du3V0BAgKQba7q89dZbatiwoR5//HH5+vrq1KlTWrp0qVatWqVly5aZ6w1WrVpVw4cP1+LFi/X7779b3XaSuW/dunVav369eduopNt+6zx8+HCNHDlSnp6eat++vYoXL67Y2Fht3rxZX331lZo2bXrL4x999FFVrVpVu3bt0qZNm1SvXj2r/X/++acWL16swoULm2sXbtu2TU2bNtVff/2ltm3bqkKFCjp48KC++uorLVmyRD/99JNq1Khxh1m23bZt2zR27FhFRkaqT58+2rNnjxYuXKi9e/dqyZIlql+/vsLDw9WjRw+dPHlSCxcuVLNmzXT8+HF5enqa/SQmJqpJkyb67bffVL16dUVFRSkjI0Pff/+9nnnmGe3bt0/vv/++zXGlpqaqadOmSkxMVNeuXZWamqrvvvtOL7/8sg4dOqSJEydKksLDw9W4cWOtXbtWhw8fVtmyZa362bx5s/bu3atOnTopKCjoH+Uq84+Gvxdct2zZojFjxqh+/fqKiopSQkKCXFxclJqaqhYtWmj9+vUKDw9X//79deXKFS1YsEBdunTRrl27NHr0aEk3CrmZt8NERESYD9mRrG+hevbZZzV37lwVL15cvXv3lsVi0aJFi9SvXz9t3LhRX3/9tVVsK1as0FNPPaVr166pZcuWevrpp5WYmKjff/9dH374ofmHhCRNmTJFL774ogoVKqSnnnpKAQEBWrduncaOHatly5Zp06ZN3JIDALjvDB06VGPGjJGfn5+eeeYZeXp6atWqVRo6dKi+//57/fDDD3JxcbE6xtZxRm7bunWrrl69qubNm8vLy8tqn4ODg1q0aKGpU6dq7dq1d3TL8dSpUyXduBOiUqVKeuSRR/TDDz/o5MmTCg0NNdu98sorWrx4cZYxcqacxtc3//7/4osvtGjRIkVGRqpp06bKyMjQjh07NH78eK1atUq//PKL1bUZhqHnnntOs2fPlp+fnzp27Ch/f3+dOXNGa9euVbly5fToo4/meG2nTp1Sy5YtdfToUc2ZM0fdu3e3OS85+Sfjx19++UVjxoxR06ZN1b9/fx09elQLFy7Uhg0b9MMPP6hBgwZm27S0ND3xxBP6/vvvVa5cOT3zzDNyc3PT2rVr9dJLL+mXX37Rl19+abafOnWq/vWvfykwMFBPPPGE/Pz8dP78ee3evVszZ85Uv379/vG1AwWeAaBACQ0NNSQZJ06csNoeGRlpSDIqV65sxMfHZzkuMTEx2+2nT582goKCjPDw8Cz7evbsme25DMMwhg8fbkgy1q5dm2VfZiw3+/777w1JRokSJYwzZ85kG4ctJk2aZEgyevbsmWXf+PHjDUlG//79DcMwjIyMDCM8PNyQZHz11VdWbefPn29IMsqVK2dcv379ltd14sSJHM+Z0/WuXbvWkJTtuaOiogxJhq+vr/H+++9b7Rs5cqQhyfj444+ttme+F2PHjrXafvXqVaNFixaGxWIxfvvtt2zj+7vMz1C9evWMlJQUc/uff/5plCxZ0pBkrF+/3tz+7bffGpKM1157LUtfmXH98MMPNp07M1d//9zExsYaAQEBhiRjzpw5hmFY53Dy5MlZ+ho9erQhyWjVqpWRlpZmbj937px5jZs2bTK33+59nDt3riHJqFatmvHXX3+Z2y9fvmw88sgjhiTj66+/NrfHx8cb3t7ehrOzs7Fu3bos/d38mY6JiTFcXFwMLy8v48CBA1btXnzxRUOS0adPn2xzBQDAvZDdGHPz5s2GJKN48eJGXFycuT0tLc1o06aNIckYNWpUtv3YOs64mxhv/r1/s88++8yQZAwYMCDb/ePGjTMkGW+88YbN5zxz5ozh6OholC1b1tz26aefGpKMYcOGZWl/qzGyYdx6fG0YN8YM6enpWbZPmzbNkGR88MEHVtunTJliSDJq1KhhJCYmWu1LT083YmNjzdczZ840JBkzZ840DMMwdu3aZQQFBRne3t7Gjz/+mG08t5M5vgoNDbXafqfjx5vHfZ9++qlV+8WLFxuSjNKlS2c7bh8wYIBVztLT083x9uLFi83t1atXN1xcXIxz585liSm7v5MAe8RfH0ABc7si4c2/CG310ksvGZKMkydPWm3PzSJh5kBy4cKFdxzfzZKSkoxChQoZHh4eRlJSktW+ChUqGJKM33//3TAMw9i4caMhyahTp062fdWvXz/LQDW3i4T169fP0n79+vWGJCMsLCzLIDAmJsaQZPTq1cvclpCQYDg6OhqPPvpotufftWuXIcl4/fXXs93/d5mfoQ0bNmTZlzl4vPn8aWlpRlBQkFG0aFGrwf7FixcNd3d3o1SpUkZGRoZN587MVc+ePY3hw4cb77zzjhEVFWX4+PgYkoyaNWsaqamphmH8Xw6rVq2abV+lS5c2LBZLlqKbYfzfQPq5554zt93ufWzatKkhyfj++++z7Pvpp58MSUbjxo3Nbf/5z38MScbAgQNve93vv/++IckYMmRIln0XLlwwvLy8DDc3N6v8UiQEANxL2Y0xe/fubUgypkyZkqX9oUOHDAcHB6NEiRLZ9mPrOONuYsypSDhq1ChDkvHWW29lu3/q1KmGJKNv3742nzPzC9zRo0eb2/7880/DxcXFCA4OzjKW+6dFwpxkZGQY3t7eVmMRwzCMSpUqGZKMnTt33raPm4uEP/zwg+Hl5WUEBwcbu3btuqNYbpZTkfBOx4+Z476/FwIzZY6LMr+YvX79ulGkSBEjMDAw28/DxYsXDYvFYjz11FPmturVqxseHh7GhQsX7vp6gQcdtxsDD5iaNWvmuG/Tpk2aMGGCtmzZovPnzys1NdVq/x9//JEnDx2Rbtz+YbFYzFua75a3t7e6dOmiGTNm6OuvvzZv59y8ebP279+vmjVrqkqVKpKknTt3SpKaNGmSbV9NmjTRxo0b9dtvv6lhw4b/KK6cZHd7R+bDXqpWrSpHR0erfQ8//LAk6cyZM+a2bdu26fr16+Y6LX+XlpYm6cYt5bZycnLK8sRqSebDRH777Tertn369NHIkSP13XffmU+z/vLLL3X16lX17ds3xzUoc5K5Ho8kFSpUSGXKlFGnTp306quvZnmycXaf6b/++ktHjx7Vww8/rPDw8Cz7M9/zm6/jdnbu3CkHBwerB6pkioyMlKOjo1V/W7dulXRjUXVb+r45rpv5+vqqWrVq2rBhgw4ePKiIiAibYwYAIC/d6vdX2bJlVaxYMZ04cUJJSUkqXLiwue9Oxhn3s4yMDE2fPl0ODg7q0aOHub1IkSJ64okn9N1332nFihVq27Ztrp0zLS1NU6ZM0fz587V//34lJSVZra33xx9/mP9OTk7W3r179dBDD6latWo2n2PBggX64YcfVKZMGa1atSpPxv93O35s0KCBHByyPjqhUaNGWr9+vX777TdFRkbq8OHDunDhgsqUKZPjkjvu7u5W4+Nu3brptddeU4UKFdS1a1dFRkaqXr168vf3z6WrBgo+ioTAAyYwMDDb7YsWLdKTTz4pNzc3NWvWTKVKlVKhQoXk4OBgri+Y3eLTuSUxMVG+vr42Lzx9K3369NGMGTM0bdo0s0iY+TCTmx9YkvkwiJzWysvcnpiY+I9jysnNA+ZMTk5Ot92XWfiTbqy1KN0oFm7bti3Hc12+fNnmuPz8/LIUKKX/+/z8/UEaffv21ahRozRlyhRzkDd16lS5uLjoueees/m8mdauXZttMS472X2m8+K9TUpKUpEiRbKsqyTdeF8y163JlNl3ZmH3dn3ndrwAAOQ1W35/nTp1SomJiVbjmjsdZ+SWzBhy6j9zu61rAH///fc6efKkWrRokeX3fa9evfTdd99p6tSpuVok7NKlixYtWqSSJUuqXbt2CgwMlKurqyTp448/thqv38lY5GZbtmxRWlqaatWqpeLFi+da7H93N+PHhx56KNvtf//sZI6Pjxw5Yj4sJjs3j49fffVV+fn5adKkSfrkk0/08ccfy2KxKDIyUuPGjbvl2o2AvaBICDxgcprR9fbbb8vFxUXbt29X+fLlrfb961//0vr16/M0Lh8fH/3555+6evXqPy4U1q5dW1WqVNHOnTu1c+dOlSlTRtHR0fL29lbXrl3NdpkDxbNnz2bbT+bT1LIr1t0s89vM9PT0bPfndWEnM75///vfGj9+fK70mZCQoOvXr2cZwGfm6u85efjhh9W2bVstWrRIBw8e1IULF7R371516dIlz799ze4znVvv7d/7vHDhgtLS0rLMZkxPT1dCQoK8vb3NbZl/YPzxxx+qXLnybfvOjLdixYq5Ei8AAHnt5t9fpUqVyrI/p99fdzrOyC3lypWTJB0+fDjb/UeOHJGkLA/SyEnmA0u+//77HMfYq1ev1unTp3Ol2LZ9+3YtWrRITZs21apVq8wvj6Ubsxo//PBDq/Y3j0XuxOjRo7Vy5UrNnDlThmGYsyVz292MH8+dO5ft9r9/djL/t0OHDlq4cKHNMfXo0UM9evRQYmKiNm/erEWLFmnGjBlq0aKFDh48yKxC2L3c/38CAPelo0ePqkKFClkKhBkZGdq4cWOen7927doyDEOrV6/Olf769Okj6cYMwrlz5yo5OVnPPPOMChUqZLbJvO1i3bp12faxdu1aSVL16tVveS5fX19J0unTp7Psu3TpUo4D0dxSs2ZNOTg46Oeff861PtPT07V58+Ys2zNzld0tK5lPfJsyZYo5aP7Xv/6VazHdCS8vL5UqVUp//PGHOeC/WXbvbeYfKtevX8+2z2rVqikjI0MbNmzIsm/Dhg26fv26VX+1a9eWJK1ateq28d7qs5iYmKhdu3bJzc0ty3+fAADkp1v9/jp69KjOnDmjEiVKZJmZdzfjjNxQu3Ztubu7a9OmTfrrr7+s9mVkZOiHH36QJDVu3Pi2fZ09e1bLly+Xt7e3nn/++Wx/6tWrp+vXr2vGjBnmcbcbb9xq/9GjRyVJbdu2tSoQStKvv/6qq1evWm0rVKiQKlWqpHPnzt3RLdyurq5asGCBnnrqKc2aNUvdu3fP8cvwf+pOx48bN260ur06098/O+Hh4fLx8dHWrVut7sCxlY+Pj1q3bq0vvvhCvXr10oULF7IdAwL2hiIhYCfCwsJ05MgRxcbGmtsMw9CIESO0f//+PD//Sy+9JEl67bXXsv22806/Ae3evbvc3d01d+5cTZo0SdL/FQ4z1atXT+XKldPGjRu1YMECq30LFizQzz//rLJly6p+/fq3PJeXl5fCw8O1adMmq1xdv35dr776apYBW24LCAhQt27dtH37dr333nvZDiqPHTumEydO3FG/Q4YMsbpl5cKFC+aaLtndAvLYY4+pbNmymj17tqKjo1WuXDmbBtl5JSoqSoZh6PXXX7fKSUJCgt577z2zTSZfX19ZLBadOnUqx/6kG3m5cuWKuf3KlSsaPHiwJOn55583t/fs2VPe3t76/PPPsx1U3ryuZPfu3eXs7KxPP/3U/AMg09tvv61Lly6pe/fu5u1EAADcDzJ/N77//vuKj483t1+/fl2DBg1SRkaG1e/Gm93pOCM3eHp66tlnn1VycnKWdZw/++wzxcTEqEWLFipZsuRt+5oxY4bS09PVrVs3TZs2LdufWbNmyWKxaPr06WZhq2jRopKU43jjVvvDwsIkZS3Knj9/Xv3798+2v4EDB0q6UXj7+23WGRkZ5mzPv3N2dta8efPUvXt3zZs3T126dLmrYtvt3On48ciRI+bYPtOSJUu0fv16lS5dWg0aNJB0YymYl156SXFxcRo4cGC24/G4uDirsfvatWtlGEaWdpnLyXh4eNzVNQIPEm43BuzEv//9b73wwguqVq2aOnXqJGdnZ7Po9cQTT2jZsmV5ev7mzZtr2LBhev/991W+fHm1b99exYsX17lz57Rx40bVrl1bs2bNsrk/Hx8fPfXUU5ozZ452796tRx55JMuMQIvFotmzZ6tZs2bq0qWL2rVrp/DwcB06dEiLFy+Wl5eX5syZY9PtFa+//rr5jfFTTz0lNzc3rV27VmlpaYqIiNDvv/9+pym5I5999pmOHDmid955R19++aXq16+vhx56SLGxsTpw4IC2bdumefPmqUSJEjb1FxQUpGvXrqlSpUpq27at0tLStGDBAsXFxalfv37ZPsjFYrHohRde0KuvvirJev3H/DBo0CCtWrVKS5YsUUREhFq3bq0rV67o22+/1fnz5/XGG29YFYA9PT1Vq1Yt/fzzz+rWrZvKli0rR0dHtW3bVlWqVNEzzzyjJUuWKDo6WhUrVlT79u1lsVi0ePFinThxQl26dFG3bt3M/vz8/DR37lw9+eSTaty4sVq1aqUqVaro0qVL2r17t06fPm0WbsPCwvTxxx+rf//+ql69ujp37ix/f3+tX79eW7ZsUXh4uMaOHXvPcwgAwK3UrVtXb7zxhj788ENVqlRJTz75pAoVKqRVq1Zp7969ql+/vl5//fUsx93NOCM7CQkJGjRokNVr6caXdpm3/w4ePNjqIWajR4/WunXrNH78eO3atUs1a9bUgQMHtGTJEgUEBGjixIm3Pa9hGOZ61717986xXenSpRUZGal169Zp1apVevzxx9W4cWM5ODhoyJAh2rt3r3lHyrBhwyTdKJqNGzdOffr0UadOneTl5SUfHx8NGDBANWrUUL169bRw4ULVrVtX9evX17lz57Rq1SqVK1fOfPjdzXr37q2ff/5ZX375pcqUKaN27drJ399fsbGx+t///qeoqKhsH3wn3ZjVOHv2bLm5uWnatGnq2LGjFixYkKtfWt7p+LFly5Z67bXXtGrVKkVEROjo0aNauHCh3NzcNGPGDKtx+9tvv63ff/9dkydP1rJly9SkSRM9/PDDOn/+vI4cOaJNmzZp1KhRqlChgqQbtyZ7enqqdu3aCgsLk2EY+vnnn7Vt2zY98sgjatq0aa5dN1Bg5eOTlQHchdDQUEOSceLECavtkZGRxu3+k545c6YRERFheHh4GEWLFjXat29v7N692xg+fLghyVi7dq1V+549e2Z7LsMwcjzmdrGsWLHCaNGiheHr62u4uLgYxYoVM9q3b2+sWbPmlrFnZ+PGjYYkQ5IxZcqUHNsdPHjQ6N69uxEYGGg4OTkZgYGBRrdu3YyDBw/e0XVNmzbNqFChguHi4mI89NBDRt++fY2EhIRsr3ft2rWGJGP48OFZ+jlx4oQhyejZs2e28UoyIiMjs2y/du2a8emnnxp16tQxvL29DRcXF6N48eJGkyZNjP/+979GQkJCjjm4WWhoqBEaGmokJiYa/fr1M4KDgw0XFxcjPDzcmDBhgpGRkZHjsRcuXDAcHBwMNzc3m893s8xcZZffv7tVDjNdvXrVGDVqlFGxYkXDzc3N8PT0NOrVq2fMnTs32/ZHjhwx2rRpYxQpUsSwWCyGJGPmzJnm/uvXrxsTJ040HnnkEcPd3d1wd3c3qlevbnz22WfG9evXs+1z7969xrPPPmsEBwcbzs7ORkBAgNGwYcNsP5Pff/+90axZM8PHx8dwcXExSpUqZbz++uvGxYsXs7S15b9pAAByS05jTMMwjHnz5hn16tUzPD09DVdXV6NChQrG+++/b1y9ejXbfu52nPF3mWOmW/1kN6b4888/jYEDBxohISGGs7OzERgYaDz33HPG6dOnbTrvDz/8YEgyqlWrdtu2X3/9tSHJaNu2rbntyy+/NCIiIgw3Nzczzpt99NFHRnh4uOHi4mJIMkJDQ61if/HFF43Q0FDD1dXVKFmypDFkyBAjOTnZzG12vvrqK6Nhw4aGt7e34erqaoSFhRnPPPOMsWPHDrPNzJkzs4x9DMMwMjIyjAEDBhiSjObNmxtXrly5fZL+v8z3KKe4DMO28ePN477Nmzcbjz32mOHl5WV4enoazZo1M3799ddsj8vIyDDmzJljNGnSxPD19TWcnZ2N4OBgo169esaoUaOMU6dOmW0///xzo3379kaJEiUMd3d3w9fX16hataoxduxY49KlSzZfM/AgsxhGNvNtAQDIxrp169S4cWN1795dX375ZX6HAwAA7jOZt8zGxMTkaxy4f9gyfsxsM3z48BxnPgLIe6xJCACwWeZT9QYMGJDPkQAAAKAgYPwIFBysSQgAuKU9e/Zo+fLl2rFjh1atWqU2bdqoVq1a+R0WAAAA7lOMH4GCiSIhAOCWduzYoaFDh8rb21tPPfVUlifOAQAAADdj/AgUTKxJCAAAAAAAANg51iQEAAAAAAAA7BxFQgAAAAAAAMDOUSQEAAAAAAAA7BxFQgAAAAAAAMDO8XTj+8DFixeVnp6e32HYDX9/f8XHx+d3GIDN+MyiIOHzem85OTnJ19c3v8PAbTDWsx3/H2I7cmU7cmU7cmU7cmU7cmW77HJ1L8d7FAnvA+np6UpLS8vvMOyCxWKRdCPnPNgbBQGfWRQkfF6B7DHWsw3/H2I7cmU7cmU7cmU7cmU7cmW7+yFX3G4MAAAAAAAA2DmKhAAAAAAAAICdo0gIAAAAAAAA2DmKhAAAAAAAAICdo0gIAAAAAAAA2DmKhAAAAAAAAICdo0gIAAAAAAAA2DmKhAAAAAAAAICdo0gIAAAAAAAA2DmKhAAAAAAAAICdo0gIAAAAAAAA2DmKhAAAAAAAAICdo0gIAAAAAAAA2DmKhAAAAAAAAICdc8rvAAAAAIAHmf/CD6S44/kdRoERlN8BFCDkynbkynbkynbkynYPaq5i+07M7xByFUXCB1zP3i/q3J8X8zuM+4qTk5PS09PzO4z7ykNFfTV72uf5HQYAAAAAAMgnFAkfcOf+vKigNm/mdxi4z8UtH5vfIQAAAAAAgHzEmoQAAAAAAACAnaNICAAAAAAAANi5++p24/3792vp0qU6ceKELl68qEGDBqlmzZrmfsMwFB0drTVr1ig5OVnh4eHq3bu3goL+bwnMy5cva8aMGdqxY4csFotq1aql5557Tm5ubmabkydPavr06Tp27Ji8vb3VsmVLtWvXziqWLVu26JtvvlF8fLwCAwPVrVs3Va9e/Y5iAQAAAAAAAAqC+2om4bVr1xQWFqbnn38+2/1LlizRqlWr1KdPH40ePVqurq4aNWqUUlNTzTaffPKJTp8+rWHDhmnw4ME6cOCApkyZYu6/cuWK3n//ffn5+emDDz5Q9+7d9e233+qnn34y2xw6dEgTJkxQkyZNNHbsWNWoUUPjxo3TqVOn7igWAAAAAAAAoCC4r4qE1apVU9euXa1mD2YyDEMrV65Ux44dVaNGDYWGhmrAgAG6ePGitm3bJkk6c+aMdu3apRdeeEFlypRReHi4oqKitHnzZl24cEGStHHjRqWnp6tfv34qXry46tWrp1atWmn58uXmuVauXKmqVauqbdu2KlasmLp27aqSJUtq9erVNscCAAAAAAAAFBT3VZHwVs6fP6/ExERVqVLF3Obh4aHSpUvr8OHDkqTDhw+rUKFCKlWqlNmmcuXKslgsOnr0qNmmfPnycnL6vzutIyIiFBsbq8uXL5ttKleubHX+iIgIHTlyxOZYAAAA8GDp37+/VqxYkd9hAAAA5In7ak3CW0lMTJQkFS5c2Gp74cKFzX2JiYny9va22u/o6ChPT0+rNgEBAVZtfHx8zH2ZbW93ntvFkp20tDSlpaWZry0Wi9zd3c1/A/mJz+D9KfN94f1BQcDnFQAAACi4CkyR8EGwaNEiLViwwHxdokQJjR07Vv7+/nl2zptnTAI5cXJy4qE797nAwMD8DgGwGZ9X5Jf09HTGPgAAAHepwIyiMmf7JSUlydfX19yelJSksLAws82lS5esjrt+/bouX75sHu/j45Nltl/m65vbJCUlWbVJSkqy2n+7WLLToUMHtWnTxnydOdMiPj5e6enpOR73T+RVv3iwpKenKy4uLr/DQDYsFosCAwN19uxZGYaR3+EAt8Tn9d5zcnLK0y8b89qIESMUEhIiFxcXrVmzRk5OTmrWrJk6d+4sSUpISNCMGTO0Z88eOTg4KCIiQlFRUeZYLDo6Wtu2bVPLli21cOFCJSQk6JtvvlHnzp3Vp08f7dixQ3v37pW/v79efPFFeXt7a/LkyTp27Ji5pnRmUfvs2bOaM2eOjhw5opSUFBUrVkxPP/201fIyAAAAD7ICsyZhQECAfHx8tGfPHnPblStXdPToUZUtW1aSVLZsWSUnJ+v48eNmm71798owDJUuXdpsc+DAAavi2e7duxUcHCxPT0+zzc3nyWxTpkwZm2PJjrOzszw8PMyfzFuNpRsPQ8mLH8BWefUZ5Cd3/jvO7xj44cfWHz6v9z7fBd369evl6uqq0aNHq3v37vruu++0e/duZWRk6MMPP9Tly5f17rvvatiwYTp//rw+/vhjq+PPnj2rX375RYMGDdKHH35obv/uu+/UsGFDffjhhwoODtaECRM0depUtW/fXmPGjJFhGJoxY4bZPiUlRdWqVdPbb7+tDz/8UBERERo7dqwSEhLuVSoAAADy1X1VJExJSVFMTIxiYmIk3XhASExMjBISEmSxWNS6dWstXLhQ27dv16lTp/TZZ5/J19dXNWrUkCQVK1ZMVatW1ZQpU3T06FEdPHhQM2bMUN26dVWkSBFJUv369eXk5KTJkyfr9OnT2rx5s1atWmU1w69169b6/ffftWzZMv3xxx+Kjo7WsWPH1LJlS0myKRYAAADcXmhoqJ566ikFBQUpMjJSJUuW1J49e7R3716dOnVKAwcOVMmSJVWmTBkNGDBA+/fvNx9IJ92YDT9gwACVKFFCoaGh5vZGjRqpbt26Cg4OVrt27RQfH6/69euratWqKlasmFq3bq19+/aZ7cPCwtSsWTOFhIQoKChIXbt2VWBgoLZv327ztaSlpenKlSvmz9WrV3MnSQAA4L5ksVhy9Se7Pu+l++p242PHjundd981X8+ZM0eSFBkZqf79+6tdu3a6du2apkyZoitXrig8PFxDhw6Vi4uLeczAgQM1ffp0jRw5UhaLRbVq1VJUVJS538PDQ8OGDdP06dM1ePBgeXl5qVOnTmratKnZply5cho4cKDmz5+vefPmKSgoSK+//rpCQkLMNrbEAgAAgFu7eXwlSb6+vkpKStKZM2dUtGhR+fn5mfuKFSumQoUK6Y8//jDvEvH398/y4DpJVgXDzNuTbz5X4cKFzaKeh4eHUlJSFB0drd9++00XL17U9evXlZqaekczCXNafxoAADyY8mJt//xc3/u+KhJWrFhR0dHROe63WCzq0qWLunTpkmMbT09Pvfzyy7c8T2hoqEaOHHnLNnXq1FGdOnX+USwAAAC4teweNHInt1K7urpmu93R0fGW58r8Zj7zXHPmzNGePXv07LPPKjAwUC4uLvroo4/uaH3nnNafBgAAD6bcXNs/p/W97+Ua1PdVkRAAAACQbswa/PPPP5WQkGDOJjxz5oySk5NVrFixXD/foUOHFBkZqZo1a0q6sQxOfHz8HfXh7OwsZ2fnXI8NAADcn/Jijej8XHuaIiEAAADuO5UrV1ZISIg+/fRT9ezZUxkZGZo2bZoqVKigUqVK5fr5goKC9Ouvv+rRRx+VJH3zzTcPzMNhAAAAbEGREAAAAPcdi8WiN954QzNmzNDw4cPl4OCgiIgIq7Wmc1OPHj30+eefa9iwYfLy8lK7du148AgAALArFoOvSPNdfHy80tLS8qTvlh26KqjNm3nSNx4cccvHavWi+fkdBrJhsVgUFBSkuLg4ZrTgvsfn9d5zdna+Z2vU4B+Y8poUdzy/owAAALkstu/EXOsrp7H0vRzvOdyTswAAAAAAAAC4b1EkBAAAAAAAAOwcRUIAAAAAAADAzlEkBAAAAAAAAOwcRUIAAAAAAADAzlEkBAAAAAAAAOwcRUIAAAAAAADAzjnldwAAAADAgyy+42ClpaXldxj3PYvFoqCgIMXFxckwjPwO575GrmxHrmxHrmxHrmxHrgoWZhICAAAAAAAAdo4iIQAAAAAAAGDnKBICAAAAAAAAdo4iIQAAAAAAAGDnKBICAAAAAAAAdo4iIQAAAAAAAGDnnPI7AAAAAOBB5r/wAynueH6HUWAE5XcABQi5sh25st3tchXbd+I9iQPAvcdMQgAAAAAAAMDOUSQEAAAAAAAA7BxFQgAAAAAAAMDOUSQEAAAAAAAA7BxFQgAAAAAAAMDOUSQEAAAAAAAA7BxFQgAAAAAAAMDOUSQEAAAAAAAA7BxFQgAAABRIEydO1IcffpjfYQAAADwQKBICAAAAAAAAds4pvwMAAADAg2fEiBEKCQmRi4uL1qxZIycnJzVr1kydO3eWJCUnJ+vLL7/Utm3blJ6erpIlS6pnz54KCwuTJEVHR2vbtm1q3ry5Fi5cqL/++kvVq1fXCy+8IA8PD0VHR2v9+vWSZPY5fPhwSdK7776rmTNnqlChQpKkmJgYvfHGG/rss88UEBCgdevWadasWXrllVc0e/ZsJSQkKDw8XP369ZOvr695DWvWrNHy5ct1/vx5+fv7q1WrVmrRosW9SiEAAMA9RZEQAAAAeWL9+vVq06aNRo8ercOHD2vSpEkKDw9XlSpVNH78eLm4uGjo0KHy8PDQjz/+qPfee08TJkyQp6enJOns2bPasmWL3nzzTV25ckWTJ0/WtGnTNHDgQLVt21Z//PGHrl69qn79+kmSPD09dejQIZtiu3btmpYtW6YBAwbIYrHo008/1ZdffqmBAwdKkn7++WdFR0crKipKJUqU0IkTJzRlyhS5urqqUaNGeZIvAACA/ESREAAAAHkiNDRUTz31lCQpKChIq1ev1p49e+Ti4qKjR49q2rRpcnZ2liT16NFD27Zt09atW9W0aVNJUlpamgYMGKAiRYpIkqKiojRmzBj16NFDPj4+cnFxUVpamnx8fO44tuvXr6tPnz4KDAyUJLVs2VILFiww90dHR+vZZ59VrVq1JEkBAQE6c+aMfvrppxyLhGlpaUpLSzNfWywWubu733FsAHA/s1gs+R1CvsvMAbm4PXJlu/shVxQJAQAAkCdCQkKsXvv6+iopKUkxMTFKSUlRVFSU1f7U1FSdPXvWfO3n52cWCCWpbNmyMgxDsbGxd1UYvJmrq6tZIMyM7dKlS5KklJQUnTt3TpMnT9aUKVPMNhkZGfLw8Mixz0WLFlkVGkuUKKGxY8f+ozgB4H4TFBSU3yHcN27+PYJbI1e2y89cUSQEAABAnnByyjrUNAxDKSkp8vX11YgRI7Lsv1URzhaZ374bhmFuS09Pz9LO0dEx29ikG0VCSfrXv/6lMmXKWLVxcMj5uX8dOnRQmzZtssQCAA+SuLi4/A4h31ksFgUGBurs2bNWv2+QFbmyXU65cnJykr+//z2JgSIhAAAA7qmSJUsqMTFRDg4OCggIyLFdQkKCLly4YM4mPHz4sCwWi4KDgyXdGDRnZGRYHePt7S1JSkxMNNc2jImJuaP4fHx85Ovrq3PnzqlBgwY2H+fs7GzePg0ADyoKPf/HMAzyYSNyZbv8zFXOX4UCAAAAeaBy5coqW7asxo0bp99//13nz5/XoUOHNG/ePB07dsxs5+zsrIkTJyomJkYHDhzQzJkzVadOHfNWY39/f506dUqxsbG6dOmS0tPTFRgYqKJFiyo6OlpxcXHauXOnli9ffscxdu7cWYsXL9bKlSsVGxurU6dOae3atXfVFwAAQEHATEIAAADcUxaLRUOGDNG8efM0adIkXbp0ST4+PipfvrwKFy5stgsMDFStWrU0ZswYXb58WY888oh69+5t7m/atKn279+vwYMHKyUlRcOHD1fFihX18ssva9q0aRo0aJBKly6trl27avz48XcU42OPPSZXV1ctXbpUX331lVxdXRUSEqLHH3881/IAAABwP7EYzPfMd/Hx8VZPwstNLTt0VVCbN/Okbzw44paP1epF8/M7DGTDYrEoKChIcXFxTM/HfY/P673n7Ox8z9aoudeio6O1bds2jRs3Lr9D+eemvCbFHc/vKAAgV8T2nZjfIeQ7xjy2I1e2yylX93K8x+3GAAAAAAAAgJ2jSAgAAAAAAADYOdYkBAAAwH2nc+fO6ty5c36HAQAAYDeYSQgAAAAAAADYOYqEAAAAAAAAgJ2jSAgAAAAAAADYOYqEAAAAAAAAgJ3jwSUAAABAHorvOFhpaWn5HcZ9z2KxKCgoSHFxcTIMI7/Dua+RK9uRK9uRKwDMJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM455XcAAAAAwIPMf+EHUtzxe3Ku2L4T78l5AADAg4eZhAAAAAAAAICdo0gIAAAAAAAA2DmKhAAAAAAAAICdo0gIAAAAAAAA2LkC9eCSjIwMRUdH6+eff1ZiYqKKFCmiyMhIderUSRaLRZJkGIaio6O1Zs0aJScnKzw8XL1791ZQUJDZz+XLlzVjxgzt2LFDFotFtWrV0nPPPSc3NzezzcmTJzV9+nQdO3ZM3t7eatmypdq1a2cVz5YtW/TNN98oPj5egYGB6tatm6pXr35vkgEAAAAAAADkkgI1k3Dx4sX68ccf9fzzz+u///2vunXrpqVLl2rVqlVmmyVLlmjVqlXq06ePRo8eLVdXV40aNUqpqalmm08++USnT5/WsGHDNHjwYB04cEBTpkwx91+5ckXvv/++/Pz89MEHH6h79+769ttv9dNPP5ltDh06pAkTJqhJkyYaO3asatSooXHjxunUqVP3JhkAAAAAAABALilQRcLDhw/r0UcfVfXq1RUQEKDatWurSpUqOnr0qKQbswhXrlypjh07qkaNGgoNDdWAAQN08eJFbdu2TZJ05swZ7dq1Sy+88ILKlCmj8PBwRUVFafPmzbpw4YIkaePGjUpPT1e/fv1UvHhx1atXT61atdLy5cvNWFauXKmqVauqbdu2KlasmLp27aqSJUtq9erV9z4xAAAAAAAAwD9QoIqEZcuW1d69exUbGytJiomJ0aFDh1StWjVJ0vnz55WYmKgqVaqYx3h4eKh06dI6fPiwpBuFxkKFCqlUqVJmm8qVK8tisZjFxsOHD6t8+fJycvq/u7EjIiIUGxury5cvm20qV65sFV9ERISOHDmSB1cOAAAAAAAA5J0CtSZh+/btdfXqVf373/+Wg4ODMjIy1LVrVzVo0ECSlJiYKEkqXLiw1XGFCxc29yUmJsrb29tqv6Ojozw9Pa3aBAQEWLXx8fEx92W2vdV5spOWlqa0tDTztcVikbu7u/lvID/xGbw/Zb4vvD8oCPi84n7VuXNnDRo0SDVr1szvUAAAAO5bBapIuGXLFm3cuFEDBw5U8eLFFRMTo1mzZsnX11eNGjXK7/Bua9GiRVqwYIH5ukSJEho7dqz8/f3z7Jw3z4YEcuLk5GT1cB/cfwIDA/M7BMBmfF4BAACAgqdAVZC++uortWvXTvXq1ZMkhYSEKD4+XosXL1ajRo3M2X5JSUny9fU1j0tKSlJYWJikGzMCL126ZNXv9evXdfnyZfN4Hx+fLDMCM1/f3CYpKcmqTVJSkrk/Ox06dFCbNm3M15kzLeLj45Wenn67y78redUvHizp6emKi4vL7zCQDYvFosDAQJ09e1aGYeR3OMAt8Xm995ycnPL0y8b7ydatW/Xtt9/q7NmzcnV1VYkSJfT666/rzJkzmjdvnmJiYpSenq6wsDD17NlTJUuWlCT1799fkvSf//xHkuTv76+JEyfq7NmzmjNnjo4cOaKUlBQVK1ZMTz/9tNWyNf3799djjz2ms2fPauvWrSpUqJA6deqkpk2b3vsEAAAA5LECVSS8du2aHBysl1F0cHAw/xAJCAiQj4+P9uzZYxYFr1y5oqNHj6p58+aSbqxrmJycrOPHj5uDx71798owDJUuXdpsM2/ePKWnp5sz8Xbv3q3g4GB5enqabfbs2aPHH3/cjGX37t0qU6ZMjvE7OzvL2dk52338MYX8xmfw/mYYBu8RCgw+r8htFy9e1IQJE9StWzfVrFlTKSkpOnDggCQpJSVFkZGRioqKkmEYWr58ucaMGaNPPvlE7u7uGjNmjHr37q1+/fqpatWq5lgyJSVF1apVU9euXeXs7Kz169dr7NixmjBhgvz8/MxzL1++XF26dFHHjh21detWffHFF6pQoYKCg4PzJRcAAAB5pUAVCR955BEtXLhQfn5+KlasmGJiYrR8+XI1btxY0o0ZDK1bt9bChQsVFBSkgIAAzZ8/X76+vqpRo4YkqVixYqpataqmTJmiPn36KD09XTNmzFDdunVVpEgRSVL9+vX17bffavLkyWrXrp1Onz6tVatWqWfPnmYsrVu31ogRI7Rs2TJVr15dmzZt0rFjx9S3b997nxgAAIAH2MWLF3X9+nXVqlXLnDkZEhIiSapUqZJV2759++q5557T/v379cgjj5hrUXt4eFjd8REWFmZ+qSxJXbt21bZt27R9+3a1bNnS3F6tWjW1aNFCktSuXTutWLFCe/fuzbZIeKv1p++VgrwmKOua2o5c2Y5c2Y5c2Y5c2Y5c2e5+yFWBKhJGRUXpm2++0bRp05SUlKQiRYqoWbNmevLJJ8027dq107Vr1zRlyhRduXJF4eHhGjp0qFxcXMw2AwcO1PTp0zVy5EhZLBbVqlVLUVFR5n4PDw8NGzZM06dP1+DBg+Xl5ZXl1pJy5cpp4MCBmj9/vubNm6egoCC9/vrr5oAVAAAAuSMsLEyVK1fWoEGDFBERoSpVqqh27drmw+Tmz5+v/fv3KykpSRkZGUpNTVVCQsIt+0xJSVF0dLR+++03swiZ3XGhoaHmvy0WS7ZL12TKaf3pe+lBWGOYdU1tR65sR65sR65sR65sR65sl5+5KlBFQnd3d/Xq1Uu9evXKsY3FYlGXLl3UpUuXHNt4enrq5ZdfvuW5QkNDNXLkyFu2qVOnjurUqXPLNgAAAPhnHBwcNGzYMB06dEi7d+/W6tWrNX/+fI0ePVpffPGFLl++rF69esnf31/Ozs566623brsu85w5c7Rnzx49++yzCgwMlIuLiz766KMsxzk6OmY5NiMjI9s+c1p/+l4qyGsMs66p7ciV7ciV7ciV7ciV7ciV7XLK1b1cg7pAFQkBAABgnywWi8LDwxUeHq4nn3xS/fr106+//qpDhw6pd+/eql69uiQpISFBf/31l9Wxjo6OWQp7hw4dUmRkpGrWrCnpxszC+Pj4fxTjrdafvlcehD/AWNfUduTKduTKduTKduTKduTKdvmZK4qEAAAAuK8dOXJEe/bsUUREhAoXLqwjR47o0qVLevjhhxUUFKQNGzaoZMmSunr1qr766iurZWakGw+327t3r8LDw+Xk5CRPT08FBQXp119/1aOPPipJ+uabb/jjBQAA2DWKhAAAALivubu768CBA1q5cqWuXr0qPz8/9ejRQ9WqVZOPj4+mTp2qN998U35+fnr66af15ZdfWh3/7LPPas6cOVqzZo2KFCmiiRMnqkePHvr88881bNgweXl5qV27drp69Wo+XSEAAED+o0gIAACA+1qxYsX01ltvZbuvRIkSGjNmjNW22rVrW71+9NFHzRmDmQICAjR8+HCrbTc/1ViSJk6cmOV848aNszluAACAgsQhvwMAAAAAAAAAkL8oEgIAAAAAAAB2jiIhAAAAAAAAYOcoEgIAAAAAAAB2jiIhAAAAAAAAYOcoEgIAAAAAAAB2jiIhAAAAAAAAYOec8jsAAAAA4EEW33Gw0tLS8jsMAACAW2ImIQAAAAAAAGDnKBICAAAAAAAAdo4iIQAAAAAAAGDnKBICAAAAAAAAdo4iIQAAAAAAAGDnKBICAAAAAAAAds4pvwMAAAAAHmT+Cz+Q4o7n+Xli+07M83MAAIAHFzMJAQAAAAAAADtHkRAAAAAAAACwcxQJAQAAAAAAADtHkRAAAAAAAACwcxQJAQAAAAAAADtHkRAAAAAAAACwcxQJAQAAAAAAADtHkRAAAAB5YsSIEZo1a1Z+hwEAAAAbOOV3AAAAAHgwDRo0SI6OjvkdBgAAAGxAkRAAAAB5wtPTM79DAAAAgI0oEgIAACBPjBgxQmFhYerVq5f69++vxo0b68yZM9qxY4c8PDzUoUMHtWzZUpJkGIa+/fZbrV27VklJSfLy8lKtWrUUFRWl1atX68cff9RHH30kSfr111/1n//8R71791bz5s0lSe+9957KlCmjrl27SpK2bdumBQsW6MyZM/L19VVkZKQ6duxozmxMTk7Wl19+qW3btik9PV0lS5ZUz549FRYWJkmKjo7Wtm3b1Lx5cy1cuFB//fWXqlevrhdeeEEeHh73OJMAAAB5jzUJAQAAcE8sW7ZMYWFhGjt2rNq3b69Zs2Zp9+7dkqRffvlFK1asUN++ffXJJ5/o9ddfV0hIiCSpQoUKOnPmjC5duiRJ2r9/v7y8vLR//35JUnp6ug4fPqwKFSpIkg4cOKDPPvtMrVq10vjx49W3b1+tW7dOCxcuNGMZP368kpKSNHToUH3wwQcqUaKE3nvvPV2+fNlsc/bsWW3ZskVvvvmmhg4dqpiYGE2bNu2e5AoAAOBeYyYhAAAA7oly5cqpffv2kqTg4GAdOnRIK1asUJUqVZSQkCAfHx9VrlxZTk5O8vPzU+nSpSVJxYsXl6enp/bv36/atWtr//79euKJJ7Ry5UpJ0tGjR5Wenq5y5cpJkhYsWKD27durUaNGkqSHHnpIXbp00ddff62nnnpKBw8e1NGjRzVt2jQ5OztLknr06KFt27Zp69atatq0qSQpLS1NAwYMUJEiRSRJUVFRGjNmjHr06CEfH58s15eWlqa0tDTztcVikbu7e67nMScWi+WenSsvZMZf0K/jXiBXtiNXtiNXtiNXtiNXtrsfckWREAAAAPdE2bJls7xesWKFJKl27dpasWKFXnrpJUVERKh69ep65JFH5OjoKIvFovLly2vfvn2qXLmyzpw5o+bNm2vJkiX6448/tH//fpUuXVqurq6SpJiYGB08eNBq5mBGRobS0tJ07do1xcTEKCUlRVFRUVbxpKam6uzZs+ZrPz8/s0CYGa9hGIqNjc22SLho0SItWLDAfF2iRAmNHTv27hN2h4KCgu7ZufJSYGBgfodQYJAr25Er25Er25Er25Er2+VnrigSAgAAIN/5+flpwoQJ2r17t3bv3q1p06Zp6dKlGjFihJycnFShQgWtWbNGBw4cUIkSJeTh4WEWDg8cOKDy5cubfaWkpKhz586qVatWlvM4OzsrJSVFvr6+GjFiRJb9/2S9wQ4dOqhNmzbm63s9EyAuLu6eni+3WSwWBQYG6uzZszIMI7/Dua+RK9uRK9uRK9uRK9uRK9vllCsnJyf5+/vfkxgoEgIAAOCeOHLkiNXrw4cPq1ixYuZrFxcXPfroo3r00UfVsmVLvfLKKzp16pRKliypChUqaPbs2dq6dau59mDFihW1Z88eHTx40Ko4V7JkScXGxub4TXzJkiWVmJgoBwcHBQQE5BhvQkKCLly4YM4mPHz4sCwWi4KDg7Nt7+zsbN6+nB8elD++DMN4YK4lr5Er25Er25Er25Er25Er2+VnrnhwCQAAAO6JgwcPasmSJYqNjdXq1au1detWtWrVSpK0bt06/e9//9OpU6d07tw5bdiwQS4uLuY356GhoSpUqJA2btyoihUrSrpRJMx8OnHmeoSS1KlTJ23YsEHffvutTp8+rTNnzmjTpk2aP3++JKly5coqW7asxo0bp99//13nz5/XoUOHNG/ePB07dszsx9nZWRMnTlRMTIwOHDigmTNnqk6dOtneagwAAFDQMZMQAAAA98QTTzyhY8eOacGCBXJ3d1ePHj1UtWpVSTdu812yZIlmz56tjIwMhYSE6M0335SXl5ekG7fghIeH67ffflN4eLgkKSQkRO7u7goODpabm5t5nqpVq+rNN9/Ud999pyVLlsjR0VEPP/ywmjRpYvY1ZMgQzZs3T5MmTdKlS5fk4+Oj8uXLq3DhwmY/gYGBqlWrlsaMGaPLly/rkUceUe/eve9RtgAAAO4tioQAAADIE39f88/d3V2vvvpqtm1r1qypmjVr3rK/N954w+q1g4ODZs6cmW3bqlWrmgXI7Li7uysqKirLw0v+rnnz5mrevPkt2wAAADwIuN0YAAAAAAAAsHMUCQEAAAAAAAA7x+3GAAAAyHMTJ07M7xDuSOfOndW5c+f8DgMAAOCeYSYhAAAAAAAAYOcoEgIAAAAAAAB2jiIhAAAAAAAAYOcoEgIAAAAAAAB2jgeXAAAAAHkovuNgpaWl5XcYAAAAt8RMQgAAAAAAAMDOUSQEAAAAAAAA7BxFQgAAAAAAAMDOUSQEAAAAAAAA7BxFQgAAAAAAAMDOUSQEAAAAAAAA7JxTfgcAAAAAPMj8F34gxR3P1T5j+07M1f4AAACYSQgAAAAAAADYOYqEAAAAAAAAgJ2jSAgAAAAAAADYOYqEAAAAAAAAgJ0rcA8uuXDhgr766ivt2rVL165dU2BgoPr166dSpUpJkgzDUHR0tNasWaPk5GSFh4erd+/eCgoKMvu4fPmyZsyYoR07dshisahWrVp67rnn5ObmZrY5efKkpk+frmPHjsnb21stW7ZUu3btrGLZsmWLvvnmG8XHxyswMFDdunVT9erV700iAAAAAAAAgFxSoGYSXr58WW+//bacnJw0dOhQ/fe//1WPHj1UqFAhs82SJUu0atUq9enTR6NHj5arq6tGjRql1NRUs80nn3yi06dPa9iwYRo8eLAOHDigKVOmmPuvXLmi999/X35+fvrggw/UvXt3ffvtt/rpp5/MNocOHdKECRPUpEkTjR07VjVq1NC4ceN06tSpe5MMAAAAAAAAIJcUqCLhkiVLVLRoUfXr10+lS5dWQECAIiIiFBgYKOnGLMKVK1eqY8eOqlGjhkJDQzVgwABdvHhR27ZtkySdOXNGu3bt0gsvvKAyZcooPDxcUVFR2rx5sy5cuCBJ2rhxo9LT09WvXz8VL15c9erVU6tWrbR8+XIzlpUrV6pq1apq27atihUrpq5du6pkyZJavXr1vU8MAAAAAAAA8A/cdZHw3Xff1Z49e3Lcv3fvXr377rt32322tm/frpIlS2r8+PHq3bu33njjDavZfefPn1diYqKqVKlibvPw8FDp0qV1+PBhSdLhw4dVqFAh8/ZkSapcubIsFouOHj1qtilfvrycnP7vbuyIiAjFxsbq8uXLZpvKlStbxRcREaEjR47k6jUDAAAAAAAAee2u1yTcv3+/HnvssRz3X7p0Sfv377/b7rN1/vx5/fjjj3r88cfVoUMHHTt2TDNnzpSTk5MaNWqkxMRESVLhwoWtjitcuLC5LzExUd7e3lb7HR0d5enpadUmICDAqo2Pj4+5L7Ptrc6TnbS0NKWlpZmvLRaL3N3dzX8D+YnP4P0p833h/UFBwOcVtpo4caKSk5P1xhtv5HcoAAAA+P/y7MElZ8+eNQtguSUjI0OlSpXSM888I0kqUaKETp06pR9//FGNGjXK1XPlhUWLFmnBggXm6xIlSmjs2LHy9/fPs3PePBsSyImTk5PVw31w/8lcVgEoCPi8IicZGRn5HQIAAABycEcVpHXr1mn9+vXm64ULF2rNmjVZ2l25ckUnT55UtWrV/nmEN/H19VWxYsWsthUrVky//PKLpP+b7ZeUlCRfX1+zTVJSksLCwsw2ly5dsurj+vXrunz5snm8j49PlhmBma9vbpOUlGTVJikpydyfnQ4dOqhNmzbm68yZFvHx8UpPT8/xuH8ir/rFgyU9PV1xcXH5HQayYbFYFBgYqLNnz8owjPwOB7glPq/3npOTU55+2ThixAgVL15ckrRhwwY5OTmpWbNm6tKliywWiy5fvqxZs2Zpx44dSktLU4UKFfTcc8+ZXzytW7dOs2bN0oABA/T1118rLi5ODRo0MMeTnTt3liQNHz5c5cqV0+zZs/XLL78oOTlZhQsXVrNmzdShQwfNmTNHsbGxGjx4sCRpxYoVmj17toYOHaqqVatKkl566SW1b9/evNNlzZo1Wr58uc6fPy9/f3+1atVKLVq0MK8tISFBc+bM0e7du2WxWFS+fHn16tXLvJskc7ZjiRIltHr1aqWnp6tevXqKioriS1gAAPBAuqMRTmpqqlWB7erVq1luKbJYLHJ1dVWzZs305JNP5k6U/1+5cuUUGxtrtS02NtYcHAcEBMjHx0d79uwxi4JXrlzR0aNH1bx5c0lS2bJllZycrOPHj6tkyZKSbqyfaBiGSpcubbaZN2+e0tPTzUHg7t27FRwcLE9PT7PNnj179Pjjj5ux7N69W2XKlMkxfmdnZzk7O2e7jz+mkN/4DN7fDMPgPUKBwef1wbJ+/Xo1adJEY8aM0bFjxzR16lT5+fmpadOmmjRpkuLi4vTGG2/I3d1dX3/9tcaMGaPx48ebY6hr165pyZIleuGFF+Tl5SUfHx+lpqbq6tWr6tevnyTJ09NTK1eu1Pbt2/Xvf/9bfn5++vPPP5WQkCBJqlChgv73v/8pIyNDDg4O2r9/v7y8vLRv3z5VrVpVFy5c0Llz51SxYkVJ0s8//6zo6GhFRUWpRIkSOnHihKZMmSJXV1c1atRI6enpGjVqlMqWLauRI0fKwcFBCxcu1OjRo/Wf//zHjH3v3r1ycXHRiBEjFB8fr0mTJsnLy0tPP/10PrwTAAAAeeuOioTNmzc3i239+/fXc889p0cffTRPAsvO448/rrffflsLFy5U3bp1dfToUa1Zs0Z9+/aVdKNA2bp1ay1cuFBBQUEKCAjQ/Pnz5evrqxo1aki6MfOwatWqmjJlivr06aP09HTNmDFDdevWVZEiRSRJ9evX17fffqvJkyerXbt2On36tFatWqWePXuasbRu3VojRozQsmXLVL16dW3atEnHjh0zYwEAAHgQFC1aVD179pTFYlFwcLBOnTqlFStWqGLFitq+fbvee+89lStXTpI0cOBAvfjii9q2bZvq1Kkj6cYdG88//7z5Ba4kubi4KC0tzeoOjISEBAUFBSk8PFwWi8VqhmT58uV19epVnThxQiVLltSBAwfUtm1bbdu2TZK0b98+FSlSxLzVPTo6Ws8++6xq1aol6cYXyWfOnNFPP/2kRo0aafPmzTIMQy+88IL5hXe/fv3Uq1cv7du3TxEREZJuzNR88cUX5erqquLFi6tz58766quv1KVLFzk4ZH3+363Wn85tD+Lan6xrajtyZTtyZTtyZTtyZTtyZbv7IVd3fa/ExIkTczMOm5QuXVqDBg3S3Llz9d133ykgIEA9e/ZUgwYNzDbt2rXTtWvXNGXKFF25ckXh4eEaOnSoXFxczDYDBw7U9OnTNXLkSFksFtWqVUtRUVHmfg8PDw0bNkzTp0/X4MGD5eXlpU6dOqlp06Zmm3LlymngwIGaP3++5s2bp6CgIL3++usKCQm5N8kAAAC4B8qUKWM1WC1btqyWL1+uM2fOyNHR0eouCi8vLwUHB+uPP/4wtzk5OSk0NPS252nUqJHef/99vfLKK4qIiNAjjzxiFusKFSqksLAw7du3T05OTnJyclLTpk0VHR2tlJQU7d+/XxUqVJAkpaSk6Ny5c5o8ebKmTJli9p+RkSEPDw9J0smTJ3X27Fn16NHDKoa0tDSdO3fOfB0aGipXV1era09JSdGff/6Z7W3eOa0/nRce5LWEWdfUduTKduTKduTKduTKduTKdvmZq3+8oMrVq1cVHx+v5OTkbG8tyhyw5ZZHHnlEjzzySI77LRaLunTpoi5duuTYxtPTUy+//PItzxMaGqqRI0fesk2dOnXMb8kBAACQlYuLi03fiJcsWVKfffaZdu3apd27d+u///2vKleurNdee03SjTHl/v375ezsrAoVKsjT01MPP/ywDh48qP379+uJJ56QdKNIKEn/+te/siwDkzn7LyUlRSVLltTAgQOzxOHt7X3X15rT+tN54UFcS5h1TW1HrmxHrmxHrmxHrmxHrmyXU67yeg3qm911kfDSpUuaMWOGfvnll1s+qe6bb76521MAAAAgnx09etTq9ZEjRxQYGKhixYrp+vXrOnLkiHm78V9//aXY2NgsD5r7Oycnp2zHjx4eHqpbt67q1q2r2rVra/To0bp8+bI8PT1VoUIFrV27Vg4ODubDSipWrKiNGzcqLi7O/GLax8dHvr6+OnfunNXdJjcrUaKENm/eLG9vb3N2YXZOnjyp1NRU846UI0eOyM3NTUWLFs22/a3Wn85tD/IfWqxrajtyZTtyZTtyZTtyZTtyZbv8zNVdFwmnTp2qHTt2qFWrVgoPDzcf6AEAAIAHR0JCgmbPnq1mzZrp+PHjWrVqlXr06KGgoCA9+uijmjJlivr27Ss3NzfNnTtXRYoUue2a1f7+/vr9998VGxsrT09PeXh4aPXq1fLx8VGJEiVksVi0detW+fj4mEW8zHUJd+7cqW7dukm6Mbtw/Pjx8vX1VXBwsNl/586dNXPmTHl4eKhq1apKT0/XsWPHlJycrDZt2qhBgwZatmyZxo0bp86dO6to0aKKj4/XL7/8onbt2plFwPT0dH3++efq1KmTzp8/r+joaLVs2TLb9QgBAAAKursuEv7+++96/PHH1b1799yMBwAAAPeRhg0bKjU1VUOGDJGDg4Nat25trtPcr18/zZo1Sx988IHS09NVvnx5DRkyxHw6cE6aNm2q/fv3a/DgwUpJSdHw4cPl5uampUuXKi4uTg4ODipdurR5TunGcjEhISFKSkrSww8/LOlGkdAwDJUvX96q/8cee0yurq5aunSpvvrqK7m6uiokJESPP/64JMnV1VXvvvuuvvrqK/3nP/9RSkqKihQpokqVKlk9aKRSpUoKCgrS8OHDlZaWpnr16umpp57KtdwCAADcT+66SOjq6nrP7okGAABA/nByclKvXr3Up0+fLPs8PT01YMCAHI9t1KiRGjVqlGW7t7e3hg0bZrWtYsWKVg+Jy864ceOynD+npW3q16+v+vXr59iXj4/PLWPP1LlzZ3Xu3Pm27QAAAAq6u75XokGDBvr1119zMxYAAAAAAAAA+eCuZxLWrl1b+/fv16hRo9S0aVMVLVo02/VZSpYs+Y8CBAAAAAAAAJC37rpI+M4775j/3r17d47teLoxAABAwTRixIj8DiHf9O/fP79DAAAAuKfuukj44osv5mYcAAAAAAAAAPLJXRcJs1uEGgAAAAAAAEDBc9cPLgEAAAAAAADwYLjrmYSTJk26bRuLxcJtyQAAAAAAAMB97q6LhPv27cuyLSMjQ4mJicrIyJC3t7dcXV3/UXAAAABAQRffcbDS0tLyOwwAAIBbuusi4cSJE7Pdnp6erp9++kkrVqzQ22+/fdeBAQAAAAAAALg3cn1NQicnJ7Vs2VIRERGaPn16bncPAAAAAAAAIJfl2YNLQkNDdeDAgbzqHgAAAAAAAEAuybMi4e7du1mTEAAAAAAAACgA7npNwgULFmS7PTk5WQcOHNCJEyfUrl27uw4MAAAAAAAAwL1x10XCb7/9NtvthQoV0kMPPaQ+ffroscceu+vAAAAAAAAAANwbd10k/Oabb3IzDgAAAOCB5L/wAynueK70Fdt3Yq70AwAA8Hd5tiYhAAAAAAAAgILhrmcSZtq/f7927typ+Ph4SZK/v7+qV6+uChUq/OPgAAAAAAAAAOS9uy4Spqen6+OPP9a2bdskSR4eHpKkK1euaNmyZapZs6ZefvllOTn94zokAAAAAAAAgDz0jx5csm3bNj3xxBNq06aNfHx8JElJSUlatmyZli1bpgULFqhr1665FSsAAAAAAACAPHDXaxJu3LhRkZGR6t69u1kglKTChQure/fuatiwoX7++efciBEAAAAAAABAHrrrImFiYqJKly6d4/4yZcooMTHxbrsHAAAAAAAAcI/cdZGwSJEi2r9/f4779+/fryJFitxt9wAAAAAAAADukbsuEkZGRmrLli2aOnWqYmNjlZGRoYyMDMXGxuqLL77Qli1b1KhRo1wMFQAAAMg/0dHR6tOnjzp37qxff/01v8MBAADIVXf94JKOHTvq3LlzWrNmjdasWSMHhxv1xoyMDEk3iogdOnTInSgBAACAfHTmzBktWLBAgwYNUtmyZVWoUKH8DgkAACBX3XWR0MHBQf3791ebNm3022+/KT4+XpLk7++vatWqKTQ0NNeCBAAAAPJD5hfg586dkyTVqFFDFoslP0MCAADIE3dUJExNTdWsWbNUvHhxtWrVSpIUGhqapSC4cuVK/fjjj+rVq5ecnO66DgkAAAA7t3XrVn377bc6e/asXF1dVaJECb3++uuaPn26kpOTVbp0aa1atUppaWlq06aNOnTooLlz5+p///ufXF1d1aVLFzVu3FiStG/fPr377ruaOXOmORMwJiZGb7zxhj777DMFBARo3bp1mjVrlgYMGKCvv/5acXFxatCggdavXy9J6tKli6Qbtx4DAAA8SO6ogvfTTz9p/fr1Gj9+/C3bVa9eXV9//bVCQkLUvHnzfxQgAAAA7NPFixc1YcIEdevWTTVr1lRKSooOHDhg7t+3b5+KFi2qd999VwcPHtTkyZN16NAhlS9fXqNHj9bmzZs1depUValSRUWLFrX5vNeuXdOSJUv0wgsvyMvLSz4+PqpYsaImTZqkqVOn5sWlAgAA5Ls7KhJu2bJFtWrV0kMPPXTLdoGBgapdu7Y2bdpEkRAAAAB35eLFi7p+/bpq1aolf39/SVJISIi539PTU88995wcHBwUHByspUuXKjU1VR07dpQkdejQQYsXL9bBgwdVr149m897/fp1Pf/88woLCzO3eXh4SJJ8fHxyPC4tLU1paWnma4vFInd3d5vPa4sH+VbnzGt7kK8xt5Ar25Er25Er25Er25Er290PubqjIuGpU6fUoEEDm9qWK1dOO3bsuKugAAAAgLCwMFWuXFmDBg1SRESEqlSpotq1a8vT01OSVKxYMfPheZJUuHBhFS9e3Hzt4OAgLy8vJSUl3dF5nZyc7mp97UWLFmnBggXm6xIlSmjs2LF33M+tBAUF5Wp/96PAwMD8DqHAIFe2I1e2I1e2I1e2I1e2y89c3VGRMD093eY1Bp2cnKy+SQUAAADuhIODg4YNG6ZDhw5p9+7dWr16tebPn6/Ro0dLkhwdHa3aWyyWLGNVi8UiwzDMf0syX0s3xrd/5+Liclff4nfo0EFt2rSxOndui4uLy/U+7xcWi0WBgYE6e/as1XuErMiV7ciV7ciV7ciV7ciV7XLKlZOTk3lHRV67oyJhkSJFdOrUKZvanjp1SkWKFLmroAAAAADpxoA5PDxc4eHhevLJJ9WvXz/9+uuvd9WXt7e3JCkxMdGcjRgTE5NbocrZ2VnOzs651l927OEPLMMw7OI6cwO5sh25sh25sh25sh25sl1+5srh9k3+T+XKlbVhw4bb3rKRlJSkDRs2qHLlyv8oOAAAANivI0eOaOHChTp27JgSEhL0yy+/6NKlS3r44Yfvqr/AwEAVLVpU0dHRiouL086dO7V8+fJcjhoAAKBguqMiYbt27ZSWlqaRI0fqyJEj2bY5cuSIRo4cqbS0NLVt2zZXggQAAID9cXd314EDBzRmzBi9/PLLmj9/vnr06KFq1ardVX9OTk56+eWXFRsbq0GDBmnJkiXq2rVrLkcNAABQMFmMO5zDuHPnTk2YMEEpKSl66KGHFBISIjc3N6WkpOj06dM6e/asXF1dNXDgQD366KN5FfcDJT4+Ps/Wb2zZoauC2ryZJ33jwRG3fKxWL5qf32EgGxaLRUFBQYqLi2N6Pu57fF7vPWdn53u2Rg3+gSmvSXHHc6Wr2L4Tc6Wf+xH/H2I7cmU7cmU7cmU7cmU7cmW7nHJ1L8d7d7QmoSRVr15d48aN05IlS7Rz505t27bN3Ofr66vHHntM7dq100MPPZSrgQIAAAAAAADIG3dcJJSkgIAA9enTR5J09epVXb16Ve7u7nJ3d8/V4AAAAAAAAADkvbsqEt6M4iAAAAAAAABQsN3Rg0sAAAAAAAAAPHgoEgIAAAAAAAB2jiIhAAAAAAAAYOcoEgIAAAAAAAB27h8/uAQAAABAzuI7DlZaWlp+hwEAAHBLzCQEAAAAAAAA7BxFQgAAAAAAAMDOUSQEAAAAAAAA7BxFQgAAAAAAAMDOUSQEAAAAAAAA7BxFQgAAAAAAAMDOOeV3AAAAAMCDzH/hB1LccZvaxvadmMfRAAAAZI+ZhAAAAAAAAICdo0gIAAAAAAAA2DmKhAAAAAAAAICdo0gIAAAAAAAA2LkC/eCSxYsXa+7cuWrdurV69eolSUpNTdWcOXO0efNmpaWlKSIiQr1795aPj495XEJCgr744gvt27dPbm5uioyM1DPPPCNHR0ezzb59+zRnzhydPn1aRYsWVadOndSoUSOr869evVrLli1TYmKiQkNDFRUVpdKlS9+DKwcAAAAAAAByT4GdSXj06FH9+OOPCg0Ntdo+e/Zs7dixQ6+++qreffddXbx4UR999JG5PyMjQ2PGjFF6erref/999e/fX+vWrdM333xjtjl//rw++OADVaxYUR9++KEef/xxTZ48Wbt27TLbbN68WXPmzNGTTz6psWPHKjQ0VKNGjVJSUlKeXzsAAAAAAACQmwpkkTAlJUWffvqp/vWvf6lQoULm9itXruh///ufevbsqUqVKqlkyZLq16+fDh06pMOHD0uSfv/9d505c0YvvfSSwsLCVK1aNXXp0kXff/+90tPTJUk//PCDAgIC1KNHDxUrVkwtW7ZU7dq1tWLFCvNcy5cv12OPPabGjRurWLFi6tOnj1xcXLR27dp7mwwAAAAAAADgHyqQRcJp06apWrVqqlKlitX248eP6/r166pcubK57eGHH5afn59ZJDx8+LBCQkKsbj+uWrWqrl69qtOnT0uSjhw5YtWHJEVERJh9pKen6/jx41ZtHBwcVLlyZbMNAAAAAAAAUFAUuDUJN23apBMnTmjMmDFZ9iUmJsrJyclqdqEkFS5cWImJiWabmwuEmfsz92X+b+a2m9tcvXpVqampunz5sjIyMrL04+Pjo9jY2BxjT0tLU1pamvnaYrHI3d3d/DeQn/gM3p8y3xfeHxQEfF4BAACAgqtAFQkTEhI0a9YsDRs2TC4uLvkdzh1btGiRFixYYL4uUaKExo4dK39//zw7p5NTgXqLkU+cnJwUFBSU32HgFgIDA/M7BMBmfF4BAACAgqdAVZCOHz+upKQkvfnmm+a2jIwMHThwQKtXr9Zbb72l9PR0JScnW80mTEpKMmf9+fj46OjRo1b9Zj5s5OY2f38ASVJSktzd3eXi4iJvb285ODiYMw8zZTdL8WYdOnRQmzZtzNeZMy3i4+PN9RBzW171iwdLenq64uLi8jsMZMNisSgwMFBnz56VYRj5HQ5wS3xe7z0nJ6c8/bLxfjBixAiFhITIxcVFa9askZOTk5o1a6bOnTtLkjp37qw+ffpox44d2rt3r/z9/fXiiy/K29tbkydP1rFjxxQaGqoBAwaYBeyzZ89qzpw5OnLkiFJSUlSsWDE9/fTTVkvZ9O/fX40bN9aZM2e0Y8cOeXh4qEOHDmrZsmW+5AEAACCvFagiYeXKlfWf//zHatvnn3+u4OBgtWvXTn5+fnJ0dNSePXtUu3ZtSVJsbKwSEhJUtmxZSVLZsmW1cOFCJSUlmbcU7969W+7u7ipWrJgkqUyZMvrtt9+szrN7926zDycnJ5UsWVJ79+5VzZo1Jd0oVu7du/eWA0dnZ2c5Oztnu48/ppDf+Aze3wzD4D1CgcHnFblt/fr1atOmjUaPHq3Dhw9r0qRJCg8PN4t63333nXr06KEePXro66+/1oQJE/TQQw+pffv28vPz0+eff64ZM2Zo6NChkm48BK9atWrq2rWrnJ2dtX79eo0dO1YTJkyQn5+fed5ly5apQ4cO6ty5s37//XfNmjVLwcHBWdbFBgAAeBAUqCKhu7u7QkJCrLa5urrKy8vL3N6kSRPNmTNHnp6e8vDw0IwZM1S2bFmzwBcREaFixYrps88+U7du3ZSYmKj58+erRYsWZgGvefPm+v777/XVV1+pcePG2rt3r7Zs2aLBgweb523Tpo0mTpyokiVLqnTp0lq5cqWuXbumRo0a3ZtkAAAA2InQ0FA99dRTkqSgoCCtXr1ae/bsMYt1jRo1Ut26dSVJ7dq107Bhw9SpUydVrVpVktS6dWtNmjTJ7C8sLExhYWHm665du2rbtm3avn271Re+5cqVU/v27SVJwcHBOnTokFasWJFjkfBW60/byp7X9GRdU9uRK9uRK9uRK9uRK9uRK9vdD7kqUEVCW/Ts2VMWi0UfffSR0tPTFRERod69e5v7HRwcNHjwYE2bNk3Dhg2Tq6urIiMj1aVLF7NNQECABg8erNmzZ2vlypUqWrSoXnjhBXOgKUl169bVpUuXFB0drcTERIWFhWno0KG3vN0YAAAAd+7vXxL7+vpaLQ0TGhpq/jtzLHbzMYULF1ZaWpquXLkiDw8PpaSkKDo6Wr/99psuXryo69evKzU1VQkJCVbnyfyS+ebXK1asyDHOnNafvhOsEcy6pneCXNmOXNmOXNmOXNmOXNkuP3NV4IuEI0aMsHrt4uKi3r17WxUG/87f319Dhgy5Zb8VK1bUhx9+eMs2LVu2ZF0aAACAPJbdg9huvqXd0dHxlsdkfiOfecycOXO0Z88ePfvsswoMDJSLi4v5BfM/kdP603fCntcIZl1T25Er25Er25Er25Er25Er2+WUq3u5BnWBLxICAAAAd+LQoUOKjIw015ZOSUlRfHx8lnZHjhyxen348GFzDevs3Gr9aVvxBxTrmt4JcmU7cmU7cmU7cmU7cmW7/MyVQ76cFQAAAMgnQUFB+vXXXxUTE6OYmBhNmDAh28H4wYMHtWTJEsXGxmr16tXaunWrWrVqlQ8RAwAA5D1mEgIAAMCu9OjRQ59//rmGDRsmLy8vtWvXTlevXs3S7oknntCxY8e0YMECubu7q0ePHlZrVAMAADxIKBICAADgvvX39acl6Y033jD/HR0dbbUvICAgy7aKFStabQsICNDw4cOt2mS3zrS7u7teffXVuwkbAACgwOF2YwAAAAAAAMDOUSQEAAAAAAAA7By3GwMAAAB/M3HixPwOAQAA4J5iJiEAAAAAAABg5ygSAgAAAAAAAHaOIiEAAAAAAABg5ygSAgAAAAAAAHaOB5cAAAAAeSi+42ClpaXldxgAAAC3xExCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsnFN+BwAAAAA8yPwXfiDFHc92X2zfifc4GgAAgOwxkxAAAAAAAACwcxQJAQAAAAAAADtHkRAAAAAAAACwcxQJAQAAAAAAADtHkRAAAAAAAACwcxQJAQAAAAAAADtHkRAAAAAAAACwcxQJAQAAUCCNGDFCs2bNyrP+J06cqA8//DDP+gcAALifUCQEAAAAAAAA7BxFQgAAAAAAAMDOOeV3AAAAAMDdun79uqZPn64NGzbIyclJzZo1U5cuXWSxWLRhwwatXLlSsbGxcnV1VaVKldSrVy8VLlzYPP706dP6+uuvdeDAARmGobCwMPXr10+BgYFZznX06FGNGTNGTzzxhNq3b38PrxIAACDvUSQEAABAgbV+/Xo1adJEY8aM0bFjxzR16lT5+fmpadOmSk9PV5cuXRQcHKykpCTNmTNHkyZN0pAhQyRJFy5c0PDhw1WhQgW98847cnd316FDh5SRkZHlPHv37tV//vMfde/eXU2bNs02lrS0NKWlpZmvLRaL3N3dbxm/xWL5B1f/YMnMBTm5PXJlO3JlO3JlO3JlO3Jlu/shVxQJAQAAUGAVLVpUPXv2lMViUXBwsE6dOqUVK1aoadOmatKkidnuoYce0nPPPachQ4YoJSVFbm5uWr16tTw8PPTKK6/IyenGsDg4ODjLOX799Vd99tlneuGFF1S3bt0cY1m0aJEWLFhgvi5RooTGjh17y/iDgoLu9JIfeNnN4kT2yJXtyJXtyJXtyJXtyJXt8jNXFAkBAABQYJUpU8bqG/eyZctq+fLlysjIUExMjKKjo3Xy5EklJyfLMAxJUkJCgooVK6aTJ08qPDzcLBBm5+jRo9q5c6deffVV1axZ85axdOjQQW3atDFf2zITIC4u7rZt7IXFYlFgYKDOnj1rvlfIHrmyHbmyHbmyHbmyHbmyXU65cnJykr+//z2JgSIhAAAAHjipqakaNWqUIiIiNHDgQHl7eyshIUGjRo1Senq6JMnZ2fm2/Tz00EPy8vLS2rVrVb169VsWFJ2dnW3q82b8wZSVYRjkxUbkynbkynbkynbkynbkynb5mSuebgwAAIAC6+jRo1avjxw5osDAQMXGxuqvv/7SM888o/Lly+vhhx9WUlKSVdvQ0FAdPHjQLBpmx8vLS++8847Onj2r//73v7dsCwAAUJBRJAQAAECBlZCQoNmzZys2NlYbN27UqlWr1Lp1a/n5+cnJyUmrV6/WuXPntH37dn333XdWx7Zs2VJXr17Vxx9/rGPHjikuLk4bNmxQbGysVbvChQtr+PDhio2N1YQJE3T9+vV7eYkAAAD3BEVCAAAAFFgNGzZUamqqhgwZounTp6t169Zq2rSpvL291a9fP23ZskWvvvqqFi9erGeffdbq2MxZgteuXdOIESM0ePBgrVmzRo6OjlnO4+Pjo3feeUenTp3SJ598ku0TkAEAAAoy1iQEAABAgTRixAjz33369Mmyv379+qpfv77VtujoaKvXoaGheuutt7Ltv3///lavfX19NWHChLuMFgAA4P7GTEIAAAAAAADAzlEkBAAAAAAAAOwcRUIAAAAAAADAzlEkBAAAAAAAAOwcRUIAAAAAAADAzlEkBAAAAAAAAOwcRUIAAAAAAADAzjnldwAAAADAgyy+42ClpaXldxgAAAC3xExCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsnFN+BwAAAAA8yPwXfiDFHc+yPbbvxHyIBgAAIHvMJAQAAAAAAADsHEVCAAAAAAAAwM5RJAQAAAAAAADsHEVCAAAAAAAAwM4VqAeXLFq0SL/++qv++OMPubi4qGzZsurevbuCg4PNNqmpqZozZ442b96stLQ0RUREqHfv3vLx8THbJCQk6IsvvtC+ffvk5uamyMhIPfPMM3J0dDTb7Nu3T3PmzNHp06dVtGhRderUSY0a/b/27jwuqnr/4/hrYFhVxAUEBEFEMtwry25dFe0quVSWqVdN1PTm1m3ztpg/xS1TK+teKSspNTUlszLEJUstU6/mGuJOKrIEKmiyCOPw+8MH5zqiNpkKOO/n48Ejzznfc+ZzPhymM5/5fr+nnU08K1eu5OuvvyY3N5fg4GAGDRpEWFjYjU6DiIiIiIiIiIjIdVWpehImJyfTqVMnJk+ezJgxYzh//jyTJk2isLDQaDN37ly2bdvG888/z/jx48nJyeHNN980tlutVqZMmYLFYmHSpEmMGDGCdevWsXjxYqNNVlYWr7/+Oo0bN2batGl06dKFWbNmsXPnTqPNxo0bmTdvHj169GDq1KkEBwczefJkTp8+fVNyISIiIiIiIiIicr1UqiLhq6++Srt27QgKCiIkJIQRI0Zw4sQJUlJSAMjPz+e7774jOjqaJk2aEBoayvDhw9m/fz8HDhwAYNeuXRw/fpynn36akJAQWrZsSa9evVi1ahUWiwWA1atX4+vrS//+/QkMDCQqKorWrVuzfPlyI5aEhAQ6dOhAZGQkgYGBDBkyBFdXV9auXXvzEyMiIiIiIiIiIvInVKoi4aXy8/MBqFq1KgApKSmcP3+epk2bGm3q1q1L7dq1jSLhgQMHqFevns3w4xYtWlBQUEBqaioABw8etDkGQPPmzY1jWCwWUlJSbNo4OTnRtGlTo42IiIiI3HyxsbFMmzatvMMQERERqXQq1ZyEF7NarcyZM4fbbruNevXqAZCbm4vZbKZKlSo2batXr05ubq7R5uICYen20m2l/y1dd3GbgoICioqKOHv2LFartcxxvL29SU9Pv2LMxcXFFBcXG8smkwkPDw/j3yLlSddgxVT6e9HvRyoDXa8CEBMTQ0hICAMGDCjvUERERETkD6i0RcK4uDhSU1OZMGFCeYdity+++IIlS5YYy/Xr12fq1Kn4+PjcsNc0myvtr1huIrPZjL+/f3mHIVfh5+dX3iGI2E3Xq9wMFovlmu5zrnU/ERERkVtdpbxDiouLY/v27YwfP55atWoZ6729vbFYLOTl5dn0Jjx9+rTR68/b25tDhw7ZHK/0YSMXt7n0ASSnT5/Gw8MDV1dXvLy8cHJyMnoelrpcL8WLde/ena5duxrLpT0tsrOzjfkQr7cbdVy5tVgsFjIyMso7DLkMk8mEn58fmZmZlJSUlHc4Ilel6/XmM5vNN/TLxj8qNjaW5ORkkpOTSUxMBGDmzJkUFhYyf/589u7di7u7O82aNSM6OhovLy8Adu7cyeeff05qaipOTk6Eh4czYMAAo+CclZXFyJEjefbZZ1m1ahWHDh1iyJAhtGnThk8++YS1a9fi5ORE+/bty1x7MTExBAUF4ezszA8//EC9evUYN24cycnJfPLJJxw9epSqVavStm1bevfujbOzs81+AN9//z1ms5m//e1v9OrVS71lRURE5JZUqYqEJSUlfPTRR2zZsoWYmBh8fX1ttoeGhuLs7MzPP/9M69atAUhPT+fEiROEh4cDEB4eztKlSzl9+rQxpHj37t14eHgQGBgIQMOGDdmxY4fNsXfv3m0cw2w2ExoaSlJSEnfffTdwYfhzUlISUVFRV4zfxcUFFxeXK56bSHnSNVixlZSU6HcklYauV8c1cOBAMjIyCAoKolevXgA4OzszevRo2rdvT3R0NEVFRSxYsIAZM2Ywbtw4AAoLC+natSvBwcEUFhayePFi3njjDaZNm4aT0/+m0F6wYAH9+/enfv36uLi48PXXX7Nu3TqGDRtG3bp1SUhIYOvWrTRu3NgmrvXr19OxY0cmTpwIwKlTp5gyZQpt27Zl5MiRpKWl8f777+Pi4kLPnj1t9mvfvj1Tpkzh8OHDfPDBB9SuXZsHHnjgsud/tallLkfFRluassB+ypX9lCv7KVf2U67sp1zZryLkqlIVCePi4tiwYQMvvvgiHh4eRk8+T09PXF1d8fT0pH379sybN4+qVavi6enJRx99RHh4uFHga968OYGBgcycOZO+ffuSm5vLokWL6NSpk1HA69ixI6tWrWL+/PlERkaSlJTEpk2bePnll41YunbtSmxsLKGhoYSFhZGYmMi5c+do167dzU6LiIiISIXg6emJ2WzGzc3NGF3x+eefU79+ffr06WO0GzZsGMOGDSM9PZ2AgADjy92Ltw8ePJjjx48bc08DdOnShXvuucdYTkxMpHv37sa6IUOGsGvXrjJx+fv7069fP2P5008/pVatWjz55JOYTCbq1q1LTk4OCxYsoEePHkZhslatWkRHR2MymQgICODYsWMsX778ikXCK00tcyWa6uPyNGWB/ZQr+ylX9lOu7Kdc2U+5sl955qpSFQlXr14NXBj+cbHhw4cbxbnSG7k333wTi8VC8+bNGTx4sNHWycmJl19+mdmzZzNmzBjc3Nxo27at8W03gK+vLy+//DJz584lMTGRWrVqMXToUFq0aGG0+ctf/sKZM2eIj48nNzeXkJAQRo8efdXhxiIiIiKO5ujRoyQlJfHEE0+U2fbrr78SEBBARkYGixcv5tChQ/z2229YrVYATpw4YVMkDA0NNf6dn59PTk4OYWFhxjpnZ2dCQ0PL9GStX7++zXJaWhrh4eE239TfdtttFBYWcurUKWrXrg1cGF1ycZvw8HASEhKwWq02PRxLXWlqmSvRVB+2NGWB/ZQr+ylX9lOu7Kdc2U+5st+VcnUzp5epVEXC+Pj4323j6urK4MGDbQqDl/Lx8eGVV1656nEaN27MtGnTrtomKirqqsOLRURERBxdYWEhd955p01PvlKlX66WPsjtqaeeokaNGpSUlPDCCy+UmVvZ3d39mmK41v3+qKtNLXM5+rB0eZqywH7Klf2UK/spV/ZTruynXNmvPHNV9itQEREREZFrZDabjZ6AcKEX3/Hjx/Hx8cHPz8/mx93dnd9++4309HQeffRRmjZtSmBgIHl5eb/7Op6entSoUcPmgXTnz58nJSXld/etW7cuBw4csLkB379/Px4eHtSsWdNYd+nD7g4ePIifn99lexGKiIiIVHa6wxERERGR68bHx4eDBw+SlZXFmTNn6NSpE2fPnuWdd97h0KFDZGZmsnPnTt59912sVitVqlShWrVqrFmzhszMTJKSkpg7d65dr/Xggw/y5ZdfsmXLFtLS0pg9ezb5+fm/u1+nTp04efIkH330EWlpaWzdupX4+Hi6dOliUwA8ceIEc+fOJT09nQ0bNrBixQo6d+58zbkRERERqcgq1XBjEREREanYunXrRmxsLM8//zxFRUXMnDmTiRMnsmDBAiZPnkxxcTE+Pj40b94ck8mEyWTimWee4eOPP+aFF14gICCAgQMHlpmD+kqvlZubS2xsLE5OTkRGRtKqVavfLRTWrFmTV155hU8++YR//etfVK1alfbt2/PYY4/ZtGvTpg1FRUW88sorODk50blz5ys+tERERESksjOVaFB4ucvOzqa4uPiGHDuqe2/8u750Q44tt46MhKms/GJReYchl2EymfD39ycjI0NzeEiFp+v15nNxcblpE1k7mpiYGEJCQhgwYMCfP9j7L0BG2WHQ6f+I/fPHvoXoPcR+ypX9lCv7KVf2U67sp1zZ70q5upn3expuLCIiIiIiIiIi4uBUJBQREREREREREXFwmpNQREREROQS9syJKCIiInIrUU9CERERERERERERB6cioYiIiIiIiIiIiINTkVBERERERERERMTBqUgoIiIiIiIiIiLi4PTgEhGpUJ4dFM3ZrF/LO4wKxWw2Y7FYyjuMCqWqbx3e/mhueYchImKX7Edfpri4uLzDEBEREbkqFQlFpEI5m/UriXcElHcYUsF13p5e3iGIiIiIiIjcUjTcWERERERERERExMGpSCgiIiIiIiIiIuLgVCQUERERERERERFxcCoSioiIiIiIiIiIODgVCUVERERERERERBycnm4sIiIiInID+Sx9HTJSyqxP/0dsOUQjIiIicnnqSSgiIiIiIiIiIuLgVCQUERERERERERFxcCoSioiIiIiIiIiIODgVCUVERERERERERBycioQiIiIiIiIiIiIOTkVCERERERERERERB6cioYiIiIiIiIiIiINTkVBEREREKrWYmBjmzJljLI8YMYLly5eXX0AiIiIilZC5vAMQEREREbmepkyZgpub23U9ZkxMDCEhIQwYMOC6HldERESkolCRUERERERuGIvFgtl8c285vby8burriYiIiNwKVCQUERERcWDbtm3jP//5Dx999BFOTk4cOXKEF198kYcffpi+ffsCMGvWLIqKihg4cCBxcXHs3buXvLw86tSpQ/fu3bn//vuN48XExBAUFISzszM//PAD9erVY9y4cRw7doz58+ezd+9e3N3dadasGdHR0Xh5eZGVlcXIkSPLxBYREUFMTAwA+/btY9GiRRw6dAgXFxfCwsJ45plnqFq1apn9RowYQefOnenSpQsAeXl5fPLJJ2zduhWLxUJoaCjR0dGEhIQAEB8fz9atW+nWrRuLFy/m7NmztGzZkqeeegoPDw9iY2NJTk4mOTmZxMREAGbOnImvr+/1/FWIiIiIlCsVCUVEREQc2O23305BQQG//PILDRo0IDk5mWrVqpGcnGy0SU5O5uGHH6a4uJjQ0FAeeeQRPDw82L59OzNnzsTPz4+wsDCj/fr16+nYsSMTJ04ELhTpJkyYQPv27YmOjqaoqIgFCxYwY8YMxo0bR+3atfnggw+M/XNzc5k4cSK33347AEeOHGHixIlERkYyYMAAnJ2d2bNnD1ar1a5zfOutt3B1dWX06NF4enryzTffMHHiRN555x2jyPjrr7+yZcsWXnrpJfLy8pgxYwZffvklf//73xk4cCAZGRkEBQXRq1cv4PK9FYuLiykuLjaWTSYTHh4eV4zLZDLZFb+jKM2H8vL7lCv7KVf2U67sp1zZT7myX0XIlYqEIiIiIg7M09OTkJAQ9uzZQ4MGDdizZw9dunRhyZIlFBYWkp+fT2ZmJhEREdSsWZOHHnrI2PfBBx9k165dbNy40aZI6O/vT79+/Yzlzz//nPr169OnTx9j3bBhwxg2bBjp6ekEBATg7e0NQFFREdOnT6dhw4Y8/vjjAHz11VeEhoYyePBgY/+goCC7zm/fvn0cOnSI2bNn4+LiAkD//v3ZunUrmzdv5oEHHgCgpKSEESNGGEW9Nm3akJSUZOTIbDbj5uZmxHk5X3zxBUuWLDGW69evz9SpU6/Y3t/f365zcDR+fn7lHUKloVzZT7myn3JlP+XKfsqV/cozVyoSioiIiDi4iIgIkpOT6datG/v27aNPnz5s2rSJffv2cfbsWWrUqIG/vz9Wq5WlS5eyadMmTp06hcViwWKx4OrqanO8+vXr2ywfPXqUpKQknnjiiTKv/euvvxIQEGAsv/feexQUFDBmzBicnJyACz0J77333ms6tyNHjlBYWMigQYNs1hcVFZGZmWks+/j42PT68/b25vTp03/otbp3707Xrl2N5d/rCZCRkfGHjn+rM5lM+Pn5kZmZSUlJSXmHU6EpV/ZTruynXNlPubKfcmW/K+XKbDbj4+NzU2JQkVBERETEwTVu3Ji1a9dy9OhRnJ2dqVu3Lo0bN2bPnj3k5eUREREBwLJly1ixYgXR0dHUq1cPd3d35syZg8VisTmeu7u7zXJhYSF33nmnTe/CUhf3zPv888/ZtWsXr732mk3B7tIi5B9RWFhIjRo1jLkNL+bp6Wn829nZ2WabyWT6wx9mXFxcjN6K9tCHpcsrKSlRbuykXNlPubKfcmU/5cp+ypX9yjNXKhKKiIhcoyeGDCDjZFZ5h1GBmDCbnbFYzgO6CSzlX8uXTz6cU95hXFWjRo0oKCggISHBKAhGRETw1VdfcfbsWbp16wZcGLp711130aZNGwCsVisZGRnUrVv3qsevX78+//3vf/Hx8SlTjCu1efNmlixZwujRo8sMswkODubnn3+mZ8+ef/jcQkNDyc3NxcnJ6U89aMRsNts9B6KIiIhIZaQioYiIyDXKOJmFS49G5R1GhWN/PyrHkLFkX3mH8LuqVq1KcHAwGzZsMIblRkREMGPGDM6fP28UDv39/dm8eTP79++nSpUqJCQkkJub+7tFwk6dOvHtt9/yzjvv8NBDD1G1alUyMzPZuHEjQ4cO5fjx48TGxvLwww8TFBREbm4ucKEwV7VqVR555BFGjRrF7Nmz+dvf/obZbGbPnj20bt36sg8QuVjTpk0JDw9n+vTp9OvXD39/f3Jycti+fTt33303DRo0sCtHPj4+HDx4kKysLNzd3alataoxHFpERETkVqAioYiIiIgQERHBkSNHaNy4MXChcBgYGMjp06eNOQMfe+wxfv31VyZPnoybmxsdOnSgVatW5OfnX/XYNWvWZOLEiSxYsIDJkydTXFyMj48PzZs3x2QykZKSwrlz51i6dClLly61iSkmJoaAgADGjBnDp59+yujRo3F1dSUsLIz77rvvd8/LZDLxyiuv8Omnn/Luu+9y5swZvL29uf3226levbrd+enWrRuxsbE8//zzFBUVMXPmzD/VM1FERESkojGVaFB4ucvOzqa4uPiGHDuqe2/8u750Q44tt46MhKms/GJReYcBwOCuUSTeEfD7DcWhdd6ezuyEleUdBg882lk9CeV3FS/Zx5qliTfk2C4uLjdtImv5E95/ATJSyqxO/0dsOQRTcZlMJvz9/cnIyNC8Vb9DubKfcmU/5cp+ypX9lCv7XSlXN/N+T2MkREREREREREREHJyKhCIiIiIiIiIiIg5ORUIREREREREREREHpyKhiIiIiIiIiIiIg1ORUERERERERERExMGpSCgiIiIiIiIiIuLgVCQUERERERERERFxcObyDkBERERE5FaW/ejLFBcXl3cYIiIiIlelnoQiIiIiIiIiIiIOTkVCERERERERERERB6cioYiIiIiIiIiIiINTkVBERERERERERMTBqUgoIiIiIiIiIiLi4FQkFBERERERERERcXAqEoqIiIiIiIiIiDg4FQlFREREREREREQcnIqEIiIiIiIiIiIiDk5FQhEREREREREREQenIqGIiIiIiIiIiIiDM5d3AJXdypUr+frrr8nNzSU4OJhBgwYRFhZW3mGJiIiIiIiIiIjYTT0J/4SNGzcyb948evTowdSpUwkODmby5MmcPn26vEMTERERERERERGxm4qEf0JCQgIdOnQgMjKSwMBAhgwZgqurK2vXri3v0EREREREREREROymIuE1slgspKSk0LRpU2Odk5MTTZs25cCBA+UYmYiIiIiIiIiIyB+jOQmv0ZkzZ7BarXh7e9us9/b2Jj09/bL7FBcXU1xcbCybTCY8PDwwm2/cr+H228Kp7ed1w44vtwbv28JxcXEp7zAAaNDodqjnU95hSAXXIL96hbhmb7/tdsy+weUdhlRwlttMN+x6vZH3EHL96Pf0xyhf9lOu7Kdc2U+5sp9yZT/lyn6X5upm5s5UUlJSctNe7RZy6tQphg4dyqRJkwgPDzfWz58/n+TkZF577bUy+8THx7NkyRJj+b777uOZZ565KfGKiIiIyM1VXFxcIb7QEBEREbGHhhtfIy8vL5ycnMjNzbVZn5ubW6Z3Yanu3bszZ84c42fIkCE2PQvlxisoKOCll16ioKCgvEMRsYuuWalMdL2K2CouLuadd97R34Sd9B5iP+XKfsqV/ZQr+ylX9lOu7FcRcqUi4TUym82EhoaSlJRkrLNarSQlJdn0LLyYi4sLnp6eNj/6dvnmKikp4ZdffkEdaKWy0DUrlYmuV5GyfvzxR/1N2EnvIfZTruynXNlPubKfcmU/5cp+FSFXGhT+J3Tt2pXY2FhCQ0MJCwsjMTGRc+fO0a5du/IOTURERERERERExG4qEv4Jf/nLXzhz5gzx8fHk5uYSEhLC6NGjrzjcWEREREREREREpCJSkfBPioqKIioqqrzDEDu5uLjQo0cPDfOWSkPXrFQmul5FbOlv4o9RvuynXNlPubKfcmU/5cp+ypX9KkKu9HRjERERERERERERB6cHl4iIiIiIiIiIiDg4FQlFREREREREREQcnIqEIiIVXM+ePdmyZUt5hyEOIiYmhjlz5pR3GCIiIiIicpPpwSVyy4iJiSEkJIQBAwaUdygiIpXWqFGjcHZ2Lu8wRG4JK1eu5OuvvyY3N5fg4GAGDRpEWFhYeYd13SQnJ7Ns2TJ++eUXcnJyGDVqFHfffbexvaSkhPj4eL799lvy8vJo1KgRgwcPxt/f32hz9uxZPvroI7Zt24bJZOKee+5h4MCBuLu7G22OHj1KXFwchw8fxsvLi6ioKB5++GGbWDZt2sTixYvJzs7Gz8+Pvn37cscdd9z4JNjpiy++YMuWLaSlpeHq6kp4eDj9+vUjICDAaFNUVMS8efPYuHEjxcXFNG/enMGDB+Pt7W20OXHiBB9++CF79uzB3d2dtm3b0qdPH5v37T179jBv3jxSU1OpVasWjz32GO3atbOJpyJfm6tXr2b16tVkZ2cDEBgYSI8ePWjZsiWgPF3Nl19+ycKFC+ncubPxmUj5uiA+Pp4lS5bYrAsICODtt98GlKdLnTp1ivnz57Nz507OnTuHn58fw4cPp0GDBoDe3y82YsQI4/3qYh07dmTw4MGV7tpST0IRERExVK1aFQ8Pj/IOQ6TS27hxI/PmzaNHjx5MnTqV4OBgJk+ezOnTp8s7tOvm3LlzhISE8OSTT152+1dffcWKFSsYMmQIr732Gm5ubkyePJmioiKjzb///W9SU1MZM2YML7/8Mnv37uX99983tufn5zNp0iRq167N66+/Tr9+/fjss89Ys2aN0Wb//v288847tG/fnqlTp9KqVSumT5/OsWPHbtzJ/0HJycl06tSJyZMnM2bMGM6fP8+kSZMoLCw02sydO5dt27bx/PPPM378eHJycnjzzTeN7VarlSlTpmCxWJg0aRIjRoxg3bp1LF682GiTlZXF66+/TuPGjZk2bRpdunRh1qxZ7Ny502hT0a/NmjVr0qdPH15//XWmTJlCkyZNmDZtGqmpqYDydCWHDh3im2++ITg42Ga98vU/QUFBfPDBB8bPhAkTjG3K0/+cPXuW//u//8NsNjN69GhmzJhB//79qVKlitFG7+//M2XKFJvrasyYMQDce++9QOW7tlQklFtCbGwsycnJJCYm0rNnT3r27ElWVhapqam8/vrrREdH079/f8aOHUtmZqaxz7Rp0/jss8948skniY6O5oMPPsBisZTz2citbMSIESxfvtxm3b/+9S/i4+MByMjIYNy4cfTt25fnnnuO3bt327TNysqiZ8+e/Pjjj4wZM4a+ffvywgsvkJycfNPOQW5tFw83Li4uZv78+QwbNow+ffrw9NNP89133wEXvs3s2bMnO3fu5MUXX6Rv376MHz+e06dPs2PHDp577jmio6N55513OHfunM3x4+LiiIuLIzo6mieffJJFixZRUlJSHqcrcsMkJCTQoUMHIiMjCQwMZMiQIbi6urJ27dryDu26admyJb1797bpPViqpKSExMREHn30UVq1akVwcDAjR44kJyeHrVu3AnD8+HF27tzJ0KFDadiwIY0aNWLQoEFs3LiRU6dOAbBhwwYsFgvDhw8nKCiI++67jwcffJCEhATjtRITE2nRogUPPfQQgYGB9O7dm9DQUFauXHlzEmGHV199lXbt2hEUFERISAgjRozgxIkTpKSkABc+LH/33XdER0fTpEkTQkNDGT58OPv37+fAgQMA7Nq1i+PHj/P0008TEhJCy5Yt6dWrF6tWrTLuX1evXo2vry/9+/cnMDCQqKgoWrdubXPvUdGvzbvuuos77rgDf39/AgIC+Pvf/467uzsHDx5Unq6gsLCQ//znPzz11FM2hRzly5aTkxPe3t7Gj5eXF6A8Xeqrr76iVq1aDB8+nLCwMHx9fWnevDl+fn6A3t8v5eXlZXNdbd++nTp16hAREVEpry0VCeWWMHDgQMLDw+nQoYNRwTebzYwbNw6z2czYsWN5/fXXiYyMxGq1GvslJSWRlpZGTEwMzzzzDFu2bOGzzz4rxzMRR2a1WnnjjTcwm81MnjyZIUOGsGDBgsu2nT9/Pl27dmXq1Kk0bNiQqVOn8ttvv93kiOVWN3PmTH788UcGDhzIjBkz+Mc//mEzRATgs88+Y9CgQUyaNImTJ08yY8YMEhMT+ec//8nLL7/M7t27WbFihc0+69evx9nZmSlTpjBgwACWL1/Ot99+ezNPTeSGslgspKSk0LRpU2Odk5MTTZs2NT4U3OqysrLIzc2lWbNmxjpPT0/CwsKMHBw4cIAqVaoYw9cAmjZtislk4tChQ0ab22+/HbP5f7MkNW/enPT0dM6ePWu0uTjXpW0OHjx4w87vz8rPzwcu9N4GSElJ4fz58zbnUbduXWrXrm2Tr3r16tkMUWvRogUFBQVGL7uDBw9eNhelx6hs16bVauXHH3/k3LlzhIeHK09XMHv2bFq2bGnz9wa6ri6VmZnJU089xciRI/n3v//NiRMnAOXpUj/99BOhoaG89dZbDB48mBdffNGmd5/e36/MYrHwww8/EBkZiclkqpTXluYklFuCp6cnZrMZNzc3449r4cKFeHp68uyzzxpvPBfP+wJgNpsZNmwYbm5uBAUF0bNnT+bPn0+vXr1wclINXW6un3/+mfT0dF599VVq1qwJwN///ndee+21Mm07depE69atARgyZAi7du3iu+++KzOHh8i1Sk9PZ9OmTYwZM8a4CaxTp06Zdr1796ZRo0YAtG/fnoULF/Kf//zHaHvPPfewZ88eHnnkEWOfWrVqER0djclkIiAggGPHjrF8+XIeeOCBG39iIjfBmTNnsFqtNjf8AN7e3qSnp5dPUDdZbm4uANWrV7dZX716dWNbbm6u0ZOnlLOzM1WrVrVp4+vra9OmNK+5ublG26u9TkVjtVqZM2cOt912G/Xq1QMunIvZbLbpBQZl83XpNVV63he3uVwuCgoKKCoq4uzZs5Xi2jx27BivvvoqxcXFuLu7M2rUKAIDAzly5IjydIkff/yRX375hSlTppTZpuvqfxo2bMjw4cMJCAggJyeHJUuWMHbsWN58803l6RJZWVl88803dOnShe7du3P48GE+/vhjzGYz7dq10/v7VWzZsoW8vDxjrsDKeG2pSCi3rKNHj9KoUSObbyYuFRwcjJubm7EcHh5OYWEhJ0+exMfH52aEKWJIS0ujVq1aRoEQLlyTl3PxemdnZ0JDQ0lLS7vhMYrjOHLkCE5OTkRERFy13cVzH1WvXh03NzebYqK3tzeHDx+22adhw4aYTCZjOTw8nISEBKxWq76gEZFbXlxcHKmpqTbzoYmtgIAApk+fTn5+Pps3byY2Npbx48eXd1gVzokTJ5gzZw5jxozB1dW1vMOp0EoffAMX7l1Ki4abNm1S7i5htVpp0KABffr0AaB+/focO3aMb775psyDMsTW2rVradGihc3nucpGd+Jyy3JxcSnvEETKMJlMZeZeO3/+fDlFI3Jl9t4wX/zUNZPJdNknI188zYOII/Dy8sLJyalMT4fL9Ra4VZWe56UTpp8+fdrY5u3tzZkzZ2y2nz9/nrNnz9q0uVweL34Nb2/vq75ORRIXF8f27dsZN24ctWrVMtZ7e3tjsVjIy8uzaX9pvi7NRel5/14uPDw8cHV1rTTXptlsxs/Pj9DQUPr06UNISAiJiYnK0yVSUlI4ffo0L730Er1796Z3794kJyezYsUKevfuTfXq1ZWvK6hSpQoBAQFkZmbqurpEjRo1CAwMtFkXGBhoDM/W+/vlZWdns3v3bjp06GCsq4zXloqEcsswm802H0SDg4PZt2/fVR9EcvToUZsnMB08eBB3d3ebmzaR68nLy8vmzTs/P5+srCzgwvwUJ0+eJCcnx9h+pTkkLp6H4/z586SkpFC3bt0bE7Q4pHr16lFSUnJDHopTOhdNqYMHD+Ln56dehHLLMJvNhIaGkpSUZKyzWq0kJSVdsYf4rcbX1xdvb29+/vlnY11+fj6HDh0ychAeHk5eXp7x8A64MF90SUkJYWFhRpu9e/fa3M/t3r2bgIAAYz6/8PBwm9cpbdOwYcMbdn5/VElJCXFxcWzZsoWxY8eWGWIXGhqKs7OzzXmkp6dz4sQJm3wdO3bM5oPi7t278fDwMD7QN2zY8LK5KD1GZb02rVYrxcXFytMlmjZtyhtvvMG0adOMnwYNGnD//fcb/1a+Lq+wsNAoEOq6snXbbbeVGaKanp5ujLTT+/vlrV27lurVq3PHHXcY6yrjtaW7cbll+Pj4cPDgQbKysjhz5gxRUVEUFBTw9ttvc/jwYTIyMvj+++9t3vAsFgvvvfcex48fZ/v27cTHxxMVFaUPqnLDNGnShO+//569e/dy7NgxYmNjjeutadOm+Pv7Exsby5EjR9i7dy+LFi267HFWrVrFli1bSEtLIy4ujry8PCIjI2/mqcgtztfXl7Zt2/Lee++xZcsWsrKy2LNnDxs3bvzTxz5x4gRz584lPT2dDRs2sGLFCjp37nwdohapOLp27cq3337LunXrOH78OLNnz+bcuXO31FCtwsJCjhw5wpEjR4AL81gdOXKEEydOYDKZ6Ny5M0uXLuWnn37i2LFjzJw5kxo1atCqVSvgQs+UFi1a8P7773Po0CH27dvHRx99xF/+8hdjqNb999+P2Wxm1qxZpKamsnHjRlasWEHXrl2NODp37syuXbv4+uuvSUtLIz4+nsOHDxMVFXXTc3IlcXFx/PDDDzzzzDN4eHiQm5tLbm6u8WW1p6cn7du3Z968eSQlJZGSksK7775LeHi48QGvefPmBAYGMnPmTI4cOcLOnTtZtGgRnTp1MkbQdOzYkaysLObPn09aWhqrVq1i06ZNdOnSxYilol+bCxcuJDk5maysLI4dO2Ys//Wvf1WeLuHh4UG9evVsftzc3KhWrRr16tVTvi4yb94847rav38/06dPx8nJifvvv195ukSXLl04ePAgS5cuJTMzkw0bNvDtt9/SqVMnAL2/X4bVamXdunW0bdvWZlRNZby2TCWXjnsTqaTS09OJjY01egfOnDmTgoIC5s+fz759+3ByciIkJIThw4dTp04dYmNjycvLIyQkhFWrVlFcXMx9993HoEGDNFRZbpj8/Hw++OADduzYgaenJ7169WL58uW0atWKnj17kp6ezqxZszh06BA+Pj4MHDiQ1157jVGjRnH33XeTlZXFyJEj+ec//0liYiJHjhzBz8+PQYMG0aRJk/I+PbkFxMTEEBISwoABAygqKuLTTz9l48aN/Pbbb9SuXZvu3bsTGRnJnj17GD9+PB9//LExGfO6deuYM2cOc+bMMY4XHx/P1q1bmT59unH8wMBASkpK2LBhA05OTnTs2JHevXvbzFMocitYuXIly5YtIzc3l5CQEAYOHFghez9cq9L3gUu1bduWESNGUFJSQnx8PGvWrCE/P59GjRrx5JNP2jxI7uzZs8TFxbFt2zZMJhP33HMPgwYNsnmS+tGjR4mLi+Pw4cNUq1aNqKgom4chAWzatIlFixaRnZ2Nv78/ffv2tenNUd569ux52fXDhw83PsAVFRUxb948fvzxRywWC82bN2fw4ME2Q8Wys7OZPXs2e/bswc3NjbZt29K3b1+bD6V79uxh7ty5HD9+nFq1avHYY4+V+ZBYka/N9957j6SkJHJycvD09CQ4OJiHH37YeIiW8nR1F/9/HJSvUm+//TZ79+7lt99+w8vLi0aNGtG7d2/8/PwA5elS27ZtY+HChWRmZuLr60uXLl1sHjCn93dbu3btYvLkybz99ttlHpZa2a4tFQnFYZUWCV988cXyDkXEbqVFwmnTphESElLe4Yj8YZd+eBERERERkYpBYypFREREREREREQcnIqEIiIiIiIiIiIiDk7DjUVERERERERERBycehKKiIiIiIiIiIg4OBUJRUREREREREREHJyKhCIiIiIiIiIiIg5ORUIREREREREREREHpyKhiIiIiIiIiIiIg1ORUERELqtnz57Ex8eXdxgiIiIiIiJyE5jLOwARkYpu3bp1vPvuu8ayi4sLtWvXplmzZjz22GN4e3tfl9dZunQpgYGB3H333dfleCIiIiJyfWVmZrJs2TJ2795NTk4OZrOZevXqce+99/LAAw/g6uparvGtWrUKNzc32rVrV65xiEjlpCKhiIidevbsia+vL8XFxezbt4/Vq1ezY8cO3nzzTdzc3P708b/44gtat26tIqGIiIhIBbR9+3beeustXFxcaNOmDUFBQVgsFvbt28cnn3xCamoqTz31VLnGuHr1aqpVq6YioYhcExUJRUTs1LJlSxo0aABAhw4dqFatGgkJCWzdupX777+/TPvCwkLc3d1vdpgiIiIicp1lZWXx9ttv4+Pjw9ixY6lRo4axLSoqiszMTLZv316OEYqI/HkqEoqIXKMmTZqQkJBAVlYWsbGxbN68menTp/Pxxx+zd+9emjRpwosvvkhhYSHx8fFs2rSJ06dP4+PjQ4cOHejWrRsmkwm40EsRYP369axfvx6Atm3bMmLECAB++eUXPv30U/bv34/VaqVhw4b07t2b8PBwm5jy8vL47LPP2Lp1Kzk5OXh5edGkSRP69++Pl5cXAKdPn2bhwoVs376d/Px8AgIC6NKli75xFhEREbmCr776isLCQoYOHWpTICzl5+dH586dATh//jxffPEF69ev5+TJk9SoUYP77ruPxx9/HBcXF2Ofnj170qNHD+M+sNSIESOIiIgw7gNLp76ZMGEC//3vf/n+++8pKiqiWbNmPPXUU8Y93ogRI8jOzjaODRAREUFMTMx1z4eI3JpUJBQRuUaZmZkAVKtWjYyMDKxWK5MnT6ZRo0Y88cQTuLm5UVJSwrRp09izZw+RkZGEhISwa9cu5s+fz6lTpxgwYAAAI0eO5P333ycsLIwOHToAF242AVJTUxk7diyenp489NBDODs7s2bNGsaPH09MTAwNGzYELvRcHDt2LGlpaURGRlK/fn1+++03fvrpJ06dOoWXlxdFRUXExMSQmZlJVFQUvr6+bN68mXfffZf8/Hzj5lZERERE/mfbtm3UqVOH22677Xfbzpo1i/Xr19O6dWu6du3KwYMH+fLLL0lLS+Nf//rXNcfw8ccfU6VKFR5//HGysrJITEwkLi6O5557DoDo6Gg+/vhj3N3d6d69O8B1mztbRByDioQiInbKz8/nzJkzFBcXs3//fj7//HNcXV258847OXDgAMXFxdx777306dPH2Gfr1q0kJSXRu3dvHn30UeDCkJS33nqLFStWEBUVhZ+fH23atOHDDz/E19eXNm3a2LzuokWLOH/+PBMmTKBOnTrAhV6Gzz77LPPnz2f8+PEALFu2jNTUVEaNGmUzr+Fjjz1GSUkJAGvWrCEtLY2nn36av/71rwD87W9/IyYmhkWLFhEZGYmHh8eNS6KIiIhIJZOfn8+pU6e46667frftkSNHWL9+Pe3bt2fo0KEAdOrUierVq/P111+TlJREkyZNrimOqlWrMmbMGGMkSklJCStWrCA/Px9PT0/uvvtuFi9eTLVq1crcT4qI2MOpvAMQEaksJk6cyODBgxk2bBhvv/027u7ujBo1ipo1axptOnbsaLPPjh07cHJy4sEHH7RZ37VrV0pKSti5c+dVX9NqtbJ7925atWplFAgBY9jKvn37yM/PB+C///0vwcHBl33wSenN5I4dO/D29ua+++4ztpnNZh588EEKCwtJTk62LxkiIiIiDqKgoADAri9Sd+zYAVy417tYt27dAP7UvIUPPPCAcU8HcPvtt2O1Wo0hxiIif5Z6EoqI2OnJJ5/E398fZ2dnqlevTkBAAE5O//uuxdnZ2aZgCJCdnU2NGjXK3FQGBgYa26/mzJkznDt3joCAgDLbAgMDKSkp4eTJk3h6epKZmck999xz1eNlZ2fj7+9vEzdA3bp17YpHRERExNGU3seVFguvJjs7G5PJZEwbU8rb25sqVapw4sSJa46jdu3aNstVqlQBLsxJLSJyPahIKCJip7CwMOPpxpdjNpvLFN9EREREpHLz9PSkRo0apKam2r3PxT3+/iir1XrZ9Ve6zyydVkZE5M/Sp1kRkRvIx8eHnJycMt88p6WlGdtLXe5m0svLCzc3N9LT08tsS0tLw2QyUatWLeDCg05+7+bVx8fHeMjKxUqPf3E8IiIiInLBnXfeya+//sqBAweu2s7Hx4eSkhIyMjJs1ufm5pKXl2fTG7BKlSrGtDGlLBYLOTk51y9wEZE/QEVCEZEbqGXLllitVlauXGmzfvny5ZhMJlq0aGGsc3NzKzNcxMnJiWbNmvHTTz+RlZVlrM/NzWXDhg00atQIT09PAO655x6OHj3Kli1bysRR+g1zy5Ytyc3NZePGjca28+fPs2LFCtzd3YmIiPjT5ywiIiJyq3nooYdwc3Nj1qxZ5ObmltmemZlJYmIiLVu2BCAxMdFme0JCAgB33HGHsc7Pz4+9e/fatFuzZs0VexLaw93dXcOPReSaabixiMgNdOedd9K4cWMWLVpEdnY2wcHB7Nq1i59++onOnTvbzFcTGhrKzz//TEJCAjVq1MDX15eGDRvSu3dvdu/ezdixY+nYsSPOzs6sWbMGi8VCv379jP0feughNm/ezFtvvUVkZCShoaGcPXuWn376iSFDhhASEsIDDzzAN998w7vvvktKSgq+vr5s3ryZ/fv3M2DAAD3ZWEREROQy/Pz8eOaZZ5gxYwbPPfccbdu2JSgoCIvFwv79+9m8eTPt2rWjc+fOtG3bljVr1pCXl0dERASHDh1i/fr1tGrVyubJxu3bt+fDDz/kjTfeoFmzZhw9epRdu3ZRrVq1a46zfv36fPPNN3z++ef4+flRvXr1a36asog4HhUJRURuICcnJ1566SUWL17Mxo0bWbt2Lb6+vvTr1894yl2p6Oho3n//fRYtWkRRURFt27alYcOGBAUFMWHCBBYuXMiXX35JSUkJYWFhPP300zRs2NDY393dnQkTJhAfH8+WLVtYv369cWNYOiTZ1dWVmJgYFixYwPr16ykoKCAgIIDhw4fTrl27m5kaERERkUrlrrvu4o033mDZsmVs3bqV1atX4+LiQr169ejfvz8dOnQAYOjQodSpU4d169axZcsWvL29eeSRR3j88cdtjtehQweysrL47rvv2LVrF40aNWLMmDFMnDjxmmPs0aMHJ06cYNmyZRQUFBAREaEioYjYzVSiWU5FREREREREREQcmuYkFBERERERERERcXAqEoqIiIiIiIiIiDg4FQlFREREREREREQcnIqEIiIiIiIiIiIiDk5FQhEREREREREREQenIqGIiIiIiIiIiIiDU5FQRERERERERETEwalIKCIiIiIiIiIi4uBUJBQREREREREREXFwKhKKiIiIiIiIiIg4OBUJRUREREREREREHJyKhCIiIiIiIiIiIg5ORUIREREREREREREH9/+p+2rshjGGtgAAAABJRU5ErkJggg==\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Protocol vs Attack Category:\n",
            "attack_class     DoS  Probe  R2L  U2R  normal\n",
            "protocol_type                                \n",
            "icmp            2847   4135    0    0    1309\n",
            "tcp            42188   5857  995   49   53600\n",
            "udp              892   1664    0    3   12434\n"
          ]
        }
      ],
      "source": [
        "# ── Protocol distribution ─────────────────────────────────────────────────────\n",
        "fig, axes = plt.subplots(1, 2, figsize=(13, 5))\n",
        "\n",
        "# Protocol counts\n",
        "proto_counts = df_train_raw['protocol_type'].value_counts()\n",
        "axes[0].bar(proto_counts.index, proto_counts.values, color=['steelblue','tomato','seagreen'], edgecolor='black')\n",
        "axes[0].set_title('Traffic Volume by Protocol')\n",
        "axes[0].set_xlabel('Protocol')\n",
        "axes[0].set_ylabel('Count')\n",
        "\n",
        "# Top 10 attack labels\n",
        "top_attacks = df_train_raw['label'].value_counts().head(10)\n",
        "axes[1].barh(top_attacks.index[::-1], top_attacks.values[::-1], color='coral')\n",
        "axes[1].set_title('Top 10 Attack Types')\n",
        "axes[1].set_xlabel('Count')\n",
        "\n",
        "plt.suptitle('Week 1 — Dataset Exploration', fontsize=13)\n",
        "plt.tight_layout()\n",
        "plt.show()\n",
        "\n",
        "print('\\nProtocol vs Attack Category:')\n",
        "df_train_raw['attack_class'] = df_train_raw['label'].map(lambda x: ATTACK_MAPPING.get(x, 'other'))\n",
        "print(pd.crosstab(df_train_raw['protocol_type'], df_train_raw['attack_class']))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "p2Lj1k-Pi8OR"
      },
      "source": [
        "---\n",
        "# 📅 Week 2 — Data Cleaning & Preprocessing"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "h7AU1Usdi8OR",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d8487447-f885-4bd2-c8c2-43670d05badf"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Missing values  (train): 0\n",
            "Duplicate rows  (train): 0\n",
            "Missing values  (test) : 0\n",
            "Duplicate rows  (test) : 0\n"
          ]
        }
      ],
      "source": [
        "# ── Data quality check ────────────────────────────────────────────────────────\n",
        "print('Missing values  (train):', df_train_raw.isnull().sum().sum())\n",
        "print('Duplicate rows  (train):', df_train_raw.duplicated().sum())\n",
        "print('Missing values  (test) :', df_test_raw.isnull().sum().sum())\n",
        "print('Duplicate rows  (test) :', df_test_raw.duplicated().sum())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "X3mXJd5Vi8OR",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "676a511c-5837-4f9c-8e4f-e7a6f8556a83"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Preprocessing training data...\n",
            "Preprocessing test data...\n",
            "\n",
            "Train processed shape : (125973, 60)\n",
            "Test  processed shape : (22544, 60)\n",
            "\n",
            "Class distribution (train):\n",
            "attack_class\n",
            "normal    67343\n",
            "DoS       45927\n",
            "Probe     11656\n",
            "R2L         995\n",
            "U2R          52\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "def preprocess(df, is_train=True, ohe=None, freq_map=None, scaler=None):\n",
        "    \"\"\"\n",
        "    Full preprocessing pipeline:\n",
        "      1. Map labels → attack_class\n",
        "      2. One-hot encode protocol_type & flag\n",
        "      3. Frequency encode service\n",
        "      4. Log-transform skewed columns\n",
        "      5. Engineer new features\n",
        "      6. Drop raw categorical columns\n",
        "      7. RobustScaler on numeric features\n",
        "    Returns (df_out, ohe, freq_map, scaler)\n",
        "    \"\"\"\n",
        "    df = df.copy()\n",
        "\n",
        "    # 1. Attack class mapping\n",
        "    df['attack_class'] = df['label'].map(lambda x: ATTACK_MAPPING.get(x, 'other'))\n",
        "\n",
        "    # 2. One-hot encode protocol_type & flag\n",
        "    cats = ['protocol_type', 'flag']\n",
        "    if is_train:\n",
        "        ohe = OneHotEncoder(sparse_output=False, handle_unknown='ignore')\n",
        "        ohe.fit(df[cats])\n",
        "    enc_df = pd.DataFrame(\n",
        "        ohe.transform(df[cats]),\n",
        "        columns=ohe.get_feature_names_out(cats),\n",
        "        index=df.index\n",
        "    )\n",
        "    df = pd.concat([df, enc_df], axis=1)\n",
        "\n",
        "    # 3. Frequency encode service\n",
        "    if is_train:\n",
        "        freq_map = df['service'].value_counts(normalize=True).to_dict()\n",
        "    df['service_freq'] = df['service'].map(freq_map).fillna(0)\n",
        "\n",
        "    # 4. Log-transform skewed columns\n",
        "    for col in ['src_bytes', 'dst_bytes', 'duration']:\n",
        "        df[f'log_{col}'] = np.log1p(df[col])\n",
        "\n",
        "    # 5. Feature engineering\n",
        "    df['total_bytes']     = df['src_bytes'] + df['dst_bytes']\n",
        "    df['src_bytes_ratio'] = df['src_bytes'] / (df['total_bytes'] + 1e-5)\n",
        "    df['is_error_flag']   = df['flag'].isin(['S0','S1','S2','S3','REJ']).astype(int)\n",
        "\n",
        "    # 6. Drop raw categoricals, label, difficulty\n",
        "    drop_cols = ['protocol_type', 'flag', 'service', 'label', 'difficulty_level']\n",
        "    df.drop(columns=drop_cols, inplace=True, errors='ignore')\n",
        "\n",
        "    # 7. Scale numeric features (everything except attack_class)\n",
        "    feature_cols = [c for c in df.columns if c != 'attack_class']\n",
        "    if is_train:\n",
        "        scaler = RobustScaler()\n",
        "        scaler.fit(df[feature_cols])\n",
        "    df[feature_cols] = scaler.transform(df[feature_cols])\n",
        "\n",
        "    return df, ohe, freq_map, scaler\n",
        "\n",
        "\n",
        "print('Preprocessing training data...')\n",
        "df_train_proc, ohe, freq_map, scaler = preprocess(df_train_raw, is_train=True)\n",
        "\n",
        "print('Preprocessing test data...')\n",
        "df_test_proc, _, _, _ = preprocess(df_test_raw, is_train=False,\n",
        "                                    ohe=ohe, freq_map=freq_map, scaler=scaler)\n",
        "\n",
        "print(f'\\nTrain processed shape : {df_train_proc.shape}')\n",
        "print(f'Test  processed shape : {df_test_proc.shape}')\n",
        "print('\\nClass distribution (train):')\n",
        "print(df_train_proc['attack_class'].value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Kvxr6Qs_i8OS",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d4fdb936-3d58-4d7a-9679-c13f69b642ba"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Dropping 7 highly correlated features: ['num_root', 'srv_serror_rate', 'srv_rerror_rate', 'dst_host_serror_rate', 'dst_host_srv_serror_rate', 'dst_host_srv_rerror_rate', 'flag_S0']\n",
            "Features remaining: 52\n"
          ]
        }
      ],
      "source": [
        "# ── Remove highly correlated features ────────────────────────────────────────\n",
        "feature_cols = [c for c in df_train_proc.columns if c != 'attack_class']\n",
        "corr_matrix  = df_train_proc[feature_cols].corr().abs()\n",
        "upper        = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))\n",
        "to_drop_corr = [c for c in upper.columns if any(upper[c] > 0.95)]\n",
        "\n",
        "print(f'Dropping {len(to_drop_corr)} highly correlated features: {to_drop_corr}')\n",
        "df_train_proc.drop(columns=to_drop_corr, inplace=True, errors='ignore')\n",
        "df_test_proc.drop(columns=to_drop_corr,  inplace=True, errors='ignore')\n",
        "\n",
        "feature_cols = [c for c in df_train_proc.columns if c != 'attack_class']\n",
        "print(f'Features remaining: {len(feature_cols)}')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "GL4eLfcUi8OS",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 439
        },
        "outputId": "d71a7b13-6e46-4362-868f-0f83907ef2b9"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x800 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# ── Correlation heatmap (top 20 features) ────────────────────────────────────\n",
        "top20 = feature_cols[:20]\n",
        "plt.figure(figsize=(12, 8))\n",
        "sns.heatmap(df_train_proc[top20].corr(), cmap='coolwarm', center=0, linewidths=0.3)\n",
        "plt.title('Correlation Matrix — Top 20 Features')\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "35xzymkOi8OS"
      },
      "source": [
        "---\n",
        "# 📅 Week 3 — Feature Engineering & Selection"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "z5CaVv4Gi8OS",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "0f330ab4-77bd-489a-c98c-89e2445b12dd"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Class distribution BEFORE SMOTE:\n",
            "attack_class\n",
            "normal    67343\n",
            "DoS       45927\n",
            "Probe     11656\n",
            "R2L         995\n",
            "U2R          52\n",
            "Name: count, dtype: int64\n",
            "\n",
            "Class distribution AFTER SMOTE:\n",
            "attack_class\n",
            "normal    67343\n",
            "DoS       67343\n",
            "R2L       67343\n",
            "Probe     67343\n",
            "U2R       67343\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "# ── Oversample minority classes with SMOTE ────────────────────────────────────\n",
        "X_raw_full = df_train_proc[feature_cols].copy()\n",
        "y_raw_full = df_train_proc['attack_class'].copy()\n",
        "\n",
        "print('Class distribution BEFORE SMOTE:')\n",
        "print(y_raw_full.value_counts())\n",
        "\n",
        "smote = SMOTE(sampling_strategy='auto', k_neighbors=5, random_state=RANDOM_STATE)\n",
        "X_resampled, y_resampled = smote.fit_resample(X_raw_full, y_raw_full)\n",
        "y_resampled = pd.Series(y_resampled, name='attack_class')\n",
        "\n",
        "print('\\nClass distribution AFTER SMOTE:')\n",
        "print(y_resampled.value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "1W_iSTqbi8OT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d7445bd8-be0b-42b2-a609-a7d3609c229f"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Encoded classes: ['DoS', 'Probe', 'R2L', 'U2R', 'normal']\n"
          ]
        }
      ],
      "source": [
        "# ── Encode target for sklearn models ─────────────────────────────────────────\n",
        "le = LabelEncoder()\n",
        "y_encoded = le.fit_transform(y_resampled)\n",
        "print('Encoded classes:', list(le.classes_))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "b1P2OGsHi8OT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ae6d18d4-0b53-43b5-f730-f72ed8b11303"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training lightweight RF for feature importance...\n",
            "\n",
            "Top 25 Features by Importance:\n",
            "service_freq                   0.078412\n",
            "src_bytes                      0.071528\n",
            "total_bytes                    0.061355\n",
            "root_shell                     0.055481\n",
            "log_src_bytes                  0.055055\n",
            "dst_host_srv_count             0.052491\n",
            "src_bytes_ratio                0.045635\n",
            "dst_bytes                      0.044627\n",
            "dst_host_same_src_port_rate    0.044369\n",
            "count                          0.040598\n",
            "logged_in                      0.037820\n",
            "log_dst_bytes                  0.037085\n",
            "serror_rate                    0.037052\n",
            "dst_host_diff_srv_rate         0.036610\n",
            "srv_count                      0.030539\n",
            "diff_srv_rate                  0.028383\n",
            "num_file_creations             0.026379\n",
            "same_srv_rate                  0.021586\n",
            "dst_host_same_srv_rate         0.020908\n",
            "is_error_flag                  0.019345\n",
            "hot                            0.018928\n",
            "dst_host_count                 0.017190\n",
            "duration                       0.013258\n",
            "dst_host_rerror_rate           0.012880\n",
            "is_guest_login                 0.011298\n"
          ]
        }
      ],
      "source": [
        "# ── Feature importance via Random Forest ─────────────────────────────────────\n",
        "print('Training lightweight RF for feature importance...')\n",
        "rf_imp = RandomForestClassifier(\n",
        "    n_estimators=100, max_depth=10,\n",
        "    random_state=RANDOM_STATE, n_jobs=-1\n",
        ")\n",
        "rf_imp.fit(X_resampled, y_encoded)\n",
        "\n",
        "importance = pd.Series(\n",
        "    rf_imp.feature_importances_,\n",
        "    index=X_resampled.columns\n",
        ").sort_values(ascending=False)\n",
        "\n",
        "print('\\nTop 25 Features by Importance:')\n",
        "print(importance.head(25).to_string())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "r85B1CbEi8OT",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 310
        },
        "outputId": "ec30e1f5-f65a-4c3c-dbc0-4d7f10c2542d"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1600x600 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Features kept  (>= 0.001): 37\n",
            "Features dropped (< 0.001): 15\n",
            "Dropped: ['flag_REJ', 'flag_RSTR', 'num_access_files', 'num_shells', 'flag_SH', 'urgent', 'su_attempted', 'flag_S3', 'flag_S1', 'land', 'flag_S2', 'flag_RSTOS0', 'flag_OTH', 'is_host_login', 'num_outbound_cmds']\n"
          ]
        }
      ],
      "source": [
        "# ── Feature importance bar chart ─────────────────────────────────────────────\n",
        "fig, axes = plt.subplots(1, 2, figsize=(16, 6))\n",
        "\n",
        "# Bar chart — top 25\n",
        "sns.barplot(\n",
        "    x=importance.head(25).values,\n",
        "    y=importance.head(25).index,\n",
        "    palette='viridis', ax=axes[0]\n",
        ")\n",
        "axes[0].set_title('Top 25 Feature Importances — Random Forest')\n",
        "axes[0].set_xlabel('Importance Score')\n",
        "\n",
        "# Threshold cutoff plot\n",
        "threshold = 0.001\n",
        "axes[1].plot(range(len(importance)), importance.values, color='steelblue')\n",
        "axes[1].axhline(y=threshold, color='red', linestyle='--', label=f'Threshold = {threshold}')\n",
        "axes[1].fill_between(\n",
        "    range(len(importance)), importance.values, threshold,\n",
        "    where=importance.values < threshold, color='red', alpha=0.3, label='Low importance'\n",
        ")\n",
        "axes[1].set_title('Feature Importance — Threshold Cutoff')\n",
        "axes[1].set_xlabel('Feature Index (sorted)')\n",
        "axes[1].set_ylabel('Importance Score')\n",
        "axes[1].legend()\n",
        "\n",
        "plt.suptitle('Week 3 — Feature Engineering & Selection', fontsize=13)\n",
        "plt.tight_layout()\n",
        "plt.show()\n",
        "\n",
        "# Select features above threshold\n",
        "selected_features = importance[importance >= threshold].index.tolist()\n",
        "low_importance    = importance[importance < threshold].index.tolist()\n",
        "print(f'Features kept  (>= {threshold}): {len(selected_features)}')\n",
        "print(f'Features dropped (< {threshold}): {len(low_importance)}')\n",
        "if low_importance:\n",
        "    print('Dropped:', low_importance)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "yFgO5MH9i8OT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7d1500ff-4b37-45ec-dca1-c80a652b9eec"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Final feature matrix shape: (336715, 37)\n"
          ]
        }
      ],
      "source": [
        "# ── Apply feature selection ───────────────────────────────────────────────────\n",
        "X_selected = X_resampled[selected_features]\n",
        "print(f'Final feature matrix shape: {X_selected.shape}')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "1rtPwPKEi8OU",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 448
        },
        "outputId": "214ed56a-7444-4ac0-ac61-88039db41d77"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Running t-SNE on 3000 samples...\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x700 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA90AAAKyCAYAAADIG729AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzs3Xd4VGX68PHvOdMnZdIrIYUSepGmIFJU5EVRFBXX3v3pWlfdVdddy7q2Vde6rqtrFxsK2JFdEFBUmiJIhxAgvZeZTD3P+0fMLDEBQgkh5P5cF5fOM6fcZ56ZzNznaZpSSiGEEEIIIYQQQohDTu/oAIQQQgghhBBCiKOVJN1CCCGEEEIIIUQ7kaRbCCGEEEIIIYRoJ5J0CyGEEEIIIYQQ7USSbiGEEEIIIYQQop1I0i2EEEIIIYQQQrQTSbqFEEIIIYQQQoh2Ikm3EEIIIYQQQgjRTiTpFkIIIYQQQggh2okk3UIIIYQQQgghRDuRpFsIcchs374dTdO49NJLOzqUPdpTjJdeeimaprF9+/YOievXXn31VTRN49VXX+3oUA5KIBDgnnvuoVevXthsNjRNY86cOR0d1mHV0XXZ0ec/Um3atAmr1cqjjz7a0aGIw8Tj8ZCSksKFF17Y0aEIIboYSbqF2IdDkUi+//77TJ48maSkJCwWC/Hx8fTr148LL7yQ1157rdXzaZrGqFGj9nhMTdPo1q3bHvfd2799JZZjxoxB0zQ+++yzfV5bbm4umqbxww8/7HNb8T9fffUVmqZx7733dnQo7erxxx/n/vvvJy0tjdtuu4177rmHPn36tHn/nTt3YjKZ0DSNu+66a4/b3XvvvWiaxldffdXq80faTZWDNX/+fC644AKys7NxOp04HA569uzJRRddxOeff97R4XUKv/vd74iPj+f6669vVt70Xtn9X0REBAMGDOCOO+6gqqrqsMSXlZVFVlbWAe+/fPlyLrjgAjIzM7HZbERHR9OjRw+mTp3Ko48+itvtbnG+putdsGDBHo972WWXhbfb098vj8fD3//+d0444QQSEhKwWq2kpqYydepU3n//fZRSzbYfP358m767mv41fR833VDa27/dX0On08mdd97JzJkzWb58+QG9rkIIcSDMHR2AEEe7q6++mhdffBGHw8Gpp55KdnY2Sik2bNjAxx9/zFdffcUll1zS6r7Lli3jnXfe4bzzztuvc7pcLm6++eY9Ph8TE7PX/a+66iqWLl3KSy+9xJQpU/a43aJFi9i0aRPDhw9n6NChBAIB1q9fj8vl2q94jwQPPfQQd9xxB+np6R0dCgBnnnkmxx57LKmpqR0dykH55JNPiIyMZP78+Vit1v3e/6WXXsIwDDRN45VXXuH+++/HbO66X111dXVcfPHFzJkzB7vdzsSJEznrrLOwWCzk5eXx2Wef8eabb3Lrrbfy2GOPdXS4R6ylS5fy6aef8te//hWn09nqNmeccQZDhgwBoLi4mI8//phHHnmEWbNmsWzZMuLi4g5jxPvnzTff5JJLLkEpxcSJEznzzDNxOBzk5+fz9ddf88knn3DWWWfRs2fPFvuazWZeeuklJk6c2OK52tpa3nvvPcxmM8FgsNVz//zzz0ydOpW8vDwyMzOZPn068fHx7Nixg08//ZRPPvmEk08+mffeey/8XXTppZcyfvz4ZseZM2cOq1evblYPTX79ePDgwUybNq3VeH79fXfNNddw33338cc//pEvv/yy1X2EEOJQ67q/XIQ4DL7++mtefPFFunXrxrffftuiZToQCOyxZa579+4UFRVx1113cdZZZ+1XwhITE3NQLagzZszg5ptv5pNPPqGkpITk5ORWt3vppZeAxhsLABaLZb9aMY8kqampR1SC63K5OuXNi18rLCwkPj7+gBLuUCjEyy+/THR0NBdeeCH/+Mc/+OijjzjrrLPaIdIjn2EYnHPOOcybN48JEybw5ptvkpaW1mwbn8/HP//5TzZt2tRBUXYOzz33HLquc/HFF+9xm2nTpjXr4fTYY48xatQo1q1bxzPPPMM999xzGCLdfx6Ph9/+9rdomsaXX37JiSee2GKbpUuXkpCQ0Or+p512Gh9++CEVFRXEx8c3e+6tt97C4/Fw5plnMnv27Bb7FhcXc/LJJ1NUVMSdd97Z4iZZZWUl559/PvPmzePcc8/liy++QNf1VnuSbd++ndWrV7eoh9YMGTKkzd95drudGTNm8MILL7B582Z69erVpv2EEOJgSPdyIfbi3nvvJTs7G4DXXnutWZe1toyPXLp0KQDTp09vkXBDY5J68sknt7pvRkYG1113HXl5eTzzzDMHfhEHwOFwcOGFFxIIBPZ4ndXV1cyaNYvIyEh+85vfAHvuil9SUsJtt91Gbm4uERERxMTEkJuby6WXXsq2bdvC2+1r7KmmaS1aQwoLC7n//vsZM2YMKSkpWK1W0tLSOP/881m3bl2br7m17se7d7fcWxdHaBwfescddzB8+HASExOx2WxkZmZy9dVXs2vXrhbnmjBhAgD33Xdfs2M23YTZ22uxcuVKpk+fTlJSUvg81113HUVFRXu9rhdeeIGBAwdit9tJTk7m6quvpqamps2vEUBNTQ133nknubm52O12YmNjOeWUU/jPf/7T6nnz8vLIz89vtavnvnz++efs2rWLGTNmcO211wLw4osvttguKyuL++67D4AJEyY0ez2h8X3TNIwjOzu71VhWrlzJTTfdxODBg4mLi8Nut9OrVy9uvfXWvXYnfvfddznxxBPD+2RlZfGb3/yGFStW7PP6qqqqOOGEE9B1nYceemif27/99tvMmzePnj178vHHH7dIuAFsNhs33XQTTzzxxD6Pt3DhQq6++mr69etHdHQ0DoeDAQMGcN999+H1eltsX1dXx1/+8hcGDBhAdHQ0UVFR9OjRgxkzZrBy5cpm23700UeceOKJpKamYrPZSEtLY9y4cfzjH/9ocdzKykruvPNO+vbti8PhwOVyceKJJ7baCun3+3n66ac55phjiI2Nxel0kpWVxRlnnNHiPbgntbW1zJo1i9GjR7f6d3lPIiMjw72Sli1bFi5v62cCQCnFa6+9xujRo0lMTMRut5ORkcEpp5zCu+++C/xv6El+fn6zz05bhzmtXbuW2tpaBgwY0GrCDTB69Og99ni66qqr8Pl8vPHGGy2ee/HFF8nIyGDy5Mmt7nv33XdTVFTEeeedx4MPPtiiV0pcXBwffPABOTk5zJ8/n7fffnuf19MezjvvPJRSvPzyyx1yfiFE1yMt3ULsxfjx46muruapp55q0X3t193bWtPUSrB58+YDOv+f//xnXnvtNf76179y2WWXHdbujFdddRXPPfcc//73v/nDH/7Q4vk333wTr9fLVVddRWRk5B6P4/F4GDNmDFu3buXkk09m6tSpKKXIz89n7ty5nH322eTk5BxwnIsXL+bhhx9mwoQJTJ8+ncjISDZv3sysWbP46KOP+Oabbxg8ePABHfvmm2+murq6RfnHH3/MqlWrmnVL/fDDD/nnP//JhAkTGD16NFarlZ9//pmXXnqJjz/+mBUrVoS7rje9j1577TXGjRvX7EbCvpLSTz75hOnTp6OU4uyzzyYzM5OVK1fy/PPPM3fuXL7++uvwjaLd/f73v2fevHlMnTqVSZMmsXDhQl588UW2bNmy1/Gbu6uurmbMmDGsW7eOESNGcPPNN1NeXs57773HpEmTeP7557nmmmvC15iVlcWTTz4Zfi1h30Mbdvevf/0LaEzgBwwYwLBhw/jyyy/Jz88nMzMzvN3NN9/MnDlzWLRoEZdcckmL1/Cee+4Jd1W96aabwjHsHsuLL77I7NmzGTduHCeddBKGYbBy5UqeeOIJPv/8c77//nuioqLC2yuluOyyy3jttddISEjgrLPOIjExkV27drFw4UJyc3MZPnz4Hq9tx44dTJ48mS1btvD666+3aWKnptfjtttuIyIiYq/b2my2fR7vkUceYcOGDYwePZpTTz0Vr9fLN998w7333stXX33Ff/7zH0wmU/h6J0+ezNKlSznuuOO48sorMZvN4esdO3Ysw4YNC8d5zTXXkJKSwtSpU0lISKC0tJSffvqJV155heuuuy4cQ35+PuPHj2f79u2MHTuWyZMn43a7+eSTT5g8eTIvvPACV111VXj7Sy+9lLfffpsBAwZw8cUX43A4KCws5Ouvv+aLL77gpJNO2ud1L168GL/fz/HHH7/PbX+taSxy0w2d/flMAPzxj3/koYceIjs7m3PPPReXy0VRURHLly/n/fffZ8aMGWRlZXHPPfe0+OzA/n3vFBYW4na79/le+bWTTz6ZrKwsXnrppWbnXrlyJT/88AP33HMPut6yzaahoYE333wTaPzu2pOIiAhuvfVWfvvb3/Kvf/2LCy64YL/iOxRGjhyJxWJh/vz5bbrhJYQQB00JIfYqLy9PAeqSSy7Z73137dqlXC6XAtTUqVPVW2+9pTZt2qQMw9jn+caMGaOUUupvf/ubAtQtt9zSbDtApaent7qvy+VS99xzT6v/nn/++TbHP3LkSAWohQsXtnhu8ODBClDLly9vcf7dX6uPPvpIAermm29ucQyfz6dqa2vDj1955RUFqFdeeaXVeAA1bty4ZmUlJSXNjtHkxx9/VBEREWry5MnNyvdUn5dccokCVF5eXqvnbvLll18qs9msevbsqcrKysLlu3btUl6vt8X28+bNU7quq//7v/9rVr5w4UIFqHvuuafV87T2WtTV1am4uDil67pavHhxs+0ffvhhBaiTTz651evKyMhQ+fn54fJAIKDGjh2rAPX999/v9ZqbXH311QpQV199dbP38KZNm1R0dLSyWq0tXr/MzEyVmZnZpuPvbteuXcpkMqnevXuHy5555hkFqLvvvrvF9vfcc88e36tK7bt+t2/froLBYIvyl156SQHq4Ycfblb+wgsvKECNGDFCVVdXN3suGAyqwsLC8ONf1+WPP/6oUlNTVXR0tJo/f36r8fxaIBBQVqtVAWrz5s1t2mdP52+ydevWVv8W3X333QpQ77zzTrjsp59+UoCaNm1ai+1DoZCqrKwMPz7mmGOU1WpVJSUlLbbd/TOjlFLjxo1Tmqapt99+u1l5VVWVGjx4sLLb7aq4uFgppVR1dbXSNE0NGzas1boqLy9v5epb+sMf/qAANWvWrFafb3qv/Pr1qqurU3379lWAuv/++5VS+/+ZiIuLU+np6crtdrc4769fmwP97BiGoUaMGKEANXjwYPXss8+qVatWKZ/Pt9f9MjMzFaACgYD6y1/+ogC1dOnS8PPXXHON0nVd5efnqxdffLHF36/FixcrQKWlpe0zxk2bNilAWa3WVutSqT3Xw+6a3tuDBw/e43fe559/3uq+Q4YMUbqut/r9IYQQh5p0LxeiHaWnpzN79mx69OjBxx9/zAUXXEDv3r1xuVxMnjyZN998k1AotNdj3HDDDWRlZfHcc88164q9NzU1Ndx3332t/vvnP//Z5vibxmo3jd1usnz5clavXs3QoUP32pq3O4fD0aLMarU2az08EElJSa0eY/DgwUycOJGFCxcSCAQO6hxN1q5dy9lnn43L5eKzzz5rNiYyPT291dbFSZMm0b9/f+bNm3fQ5587dy6VlZXMmDGDsWPHNnvu1ltvJSsri/nz57Njx44W+/75z3+me/fu4cdms5nLLrsMaN5Vdk/8fj9vvvkmkZGRPPTQQ+GWPoBevXpx44034vf7ef311w/08pp5+eWXCYVCzbrTnn/++Vit1vBzh1JmZma4VXd3l19+OdHR0S3qr2nIxwsvvNBi7L3JZNrj/ADz589n7NixaJrG4sWL29QyC41dsP1+P8B+dYnem5ycnGb12OSWW24BaPU929rnWNd1YmNjm5WZzWYsFkuLbXf/zKxevZpFixYxffr0FpNFxsTEhLu5f/DBB0Bj67JSCpvN1mpL66/HH+9J0+djX3M4zJkzh3vvvZd7772Xa6+9ltzcXNavX0+PHj24/vrrD/gzYbFYWn2v7WmM9f7SNI1Zs2Yxfvx4Vq9ezfXXX88xxxxDZGQko0aN4pFHHqG2tnavx7jsssswmUzh4Rxut5uZM2dyyimnNPs7srum4S0ZGRn7jLFpG7/fT0VFxf5cXqtWr169x++8L774otV9UlJSMAyDgoKCgz6/EELsi3QvF+IgVFdXh7sA7u7mm28Od12dMGECmzZt4ptvvmHRokX88MMPfPPNN8ybN4958+bx2muv8cknn+yxO6jNZuPBBx/k/PPP54477uC9997bZ1yZmZmHZGmk8847j1tuuYUPPviAZ555JvzDuumH2O7dPvdk3LhxpKen8/DDD7Nq1SqmTJnCmDFjGDJkSKs/PA/Ep59+yj//+U9WrFhBeXl5i1l1y8vLD3qStKKiIk499VR8Ph+ffvppi8l3lFK89dZbvPrqq6xevZqqqqpmieGBTCT2a6tWrQJodVZhs9nMCSecwPbt2/nhhx9a/DBu7eZI0w/ftiyBtHHjxvBQgdaGOUycOJEHHnjgkCwdZxgG//73v1tMdBUXF8fUqVP54IMP+PTTTzn99NMP+lxNAoEAL7zwAu+88w7r1q2jpqYGwzDCz+/+w9ztdrN27VqSk5MZOnRom88xa9YsvvzyS3r16sXnn3++x+TlcHG73Tz11FPMnj2bTZs2UVdX12wpp92vuV+/fgwZMoS3336b/Px8zjjjDI4//niGDx/e4r19wQUXcOutt9KvXz/OO+88xo0bx5gxY0hMTGy23bfffgs03iRsbRKssrIyANavXw9AdHQ0U6dO5eOPP2bIkCFMnz6dsWPHMmrUqD3OQN6apiTv1zcKfm3u3LnMnTsXaLzZkJWVxQUXXMAdd9xBbGwsa9as2e/PxAUXXMAzzzxDv379OPfccxk3bhzHHXfcfk+a+OSTT7YY+jJt2rRw9/Pu3buzcOFC1q9fz/z581mxYgXLli0L//vHP/7BV1991epQFGi8iThlyhTee+89nnrqKd577z3q6ura9De/I1xyySX7vQ59U52Vl5e3Q0RCCNGcJN1CHITq6urwBE67u/TSS5uNF9V1nbFjx4ZbJ5VSzJ8/n0suuYT//Oc/PP/883td4uu8887j73//O++//z7fffcdxx577KG+lFZFRERw/vnn88ILL/Dmm29yww034Ha7eeedd4iIiGjTWLzo6Gi+++477rnnHj766KNw61lCQgLXXXcdd999d6stYm311FNPcfPNNxMbG8vJJ59M9+7dcTqdaJoWHsfr8/kO+PjQmJycdtpp7Ny5k7feeqvVsaC/+93vePLJJ0lNTeWUU04hPT093Cr46quvkp+ff1AxAOFJz/Z0A6GpvLVx6K2NpW6a5KgtrcYHc+79NW/ePPLz88Ov4+4uvfRSPvjgA/71r38d0qR7xowZzJ49m5ycHM444wxSUlLCN8KefPLJZu+hpmvc3+Xlvv32WwKBAKNGjWpTa+Du4uLisFqt+P1+CgoK6NGjx37t/2uBQICJEyeybNkyBgwYwIwZM0hMTAx/Fu+7775m12wymViwYAH3338/s2bNCs/zEBUVxSWXXMJDDz0Untvhd7/7HQkJCfzjH//g6aef5sknn0TTNMaNG8ff/va38A2gpuR3/vz5zJ8/f4+x1tfXh///3Xff5ZFHHmHmzJnh2cPtdjtnn302jz322B5XWthd0+eytcnidvfKK6/sdeKyA/lM/P3vfycnJ4dXXnmFhx9+mIcffhiz2cyUKVN4/PHHW13CqzVPPvlki78pWVlZLcZ89+3bl759+4Yfb9iwgcsvv5xvv/2WW265hTlz5uzxHFdddRUff/wxM2fO5JVXXgmP0d+TlJQUAHbu3LnP+Ju2sVqtbe6hcKg1NDQArffeEEKIQ02SbiEOQlZWVrOWobbSNI1JkybxwAMPcOWVV7JgwYK9Jt2apvHYY48xbtw4brvtNr7++uuDiHr/XH311bzwwgu89NJL3HDDDbzzzjvU1dWFu922Rbdu3fj3v/+NUop169axYMECnnvuOe6//34Mw+Avf/kLQLjLaGvrv7aWzAWDQe69915SUlJYtWpVix+/TS1pByMUCnHeeeexatUq/vrXv4Znat9daWkpTz/9NAMGDGDp0qUtursfqhl6m1rDiouLW32+qXtneyw1djjP3TRh2Lx581rt/gzwxRdfsHPnzv1OXluzYsUKZs+ezUknncTnn3/ebMZlwzB49NFHm23fdANjf7ulPvjgg3z22We88sorKKXCrfltYTabOfbYY1m8eDH//e9/Dzrpnjt3LsuWLePSSy/llVdeafZcUVFRqzcTY2Nj+fvf/87f//53tmzZwqJFi3jhhRd49tlnqa6ubjbb9cUXX8zFF19MdXU1S5cuZfbs2bz88succsopbNiwgcTExPB75amnnuLGG29sU9wOhyPc5Xvnzp0sXryYV199lTfffJPt27ezZMmSfR4jKSkJ4KC7NR/IZ8JkMnHzzTdz8803U1paytdff80777zD+++/z88//8zPP//cpknwDrQnU58+fXjjjTfo2bPnPidQnDJlCunp6TzwwAPs2rWLO++8s8Vs5LsbMWIENpuNwsJC1q9f3yzZ/7Wmmd2PPfbYQ9bjaX811X/T+0EIIdqTjOkWYh+afhAc6jGkQDg5a0vifsIJJ3DGGWfwzTffhMc4Hg7HHHMMw4YN46effmLZsmUt1ubeH5qm0b9/f2644YZwy9buLS1N3T1baylpbQmm8vJyqqurGT16dIuEu76+Ptwd+2A0rVd++eWXc9ddd7W6zbZt2zAMg0mTJrVIuHft2tXqWPwDeV81dWVubW33YDAYTjiOOeaYNh+zrXJzc3E6naxevbrVGyALFy48JOcuLi7mk08+ITo6miuuuKLVf2PGjAmv4d1kX6/n3p7fsmULAKeffnqLpGLZsmXhFrEmERERDBgwgJKSkv3qTm+z2Zg1axbnnHMOr776KhdeeGGrN5j2pOkz99hjj+HxePa67b56dzRdc2trni9atGifsfTs2ZMrrriCRYsWERkZGe6G/WsxMTFMmTKFF198kUsvvZTKykoWL14MEO6x05ZEuTUZGRlccMEF4WXUvv766zYl0oMGDQIaW30PxsF+JpKSkjjrrLN47733mDhxIlu3bmXt2rXh500mU4d+75hMJi6//HJ27dqFpmlceeWVe93e4XBw/vnnA/DAAw/scbuGhobwknYH8j1yqGzcuJH4+PhDNkeCEELsjSTdQuxDbGwsmqa1OjnVvnzxxRd8+OGHrU7kVV9fHx4PfsIJJ7TpeI888ghms5k77rhjv2M5GE3j+G677Ta+++47Bg0axKhRo9q0788//0xJSUmL8qay3cdiDh8+HF3XmTlzZrOkorKykt///vctjpGUlITT6WTlypXNuqAGAgFuuummgx6r9+STT/Lss89y0kkn7XUCuqYlqr7++utmP5Lr6+u56qqrWk2smrpU7s/7atq0acTFxfH222/z3XfftYg1Ly+Pk046qV3GClutVi644ALq6ur405/+1Oy5rVu38vTTT2OxWLjooosO6jwvv/wywWCQCy64gJdeeqnVf01rmP/73/8Oj7ve1+u5t+eb6u/XNzNKS0v57W9/2+rxmlpmr7nmmhZrnRuG0eqa6dA4idbbb7/NhRdeyNtvv82MGTPaPNHfb37zG0455RQ2b97MGWec0eo5/H4/zz33HLfeeutej7Wna962bVurSwTm5eW1evOoqqoKn8/XrIvuwoULW03oSktLgf995ocPH87YsWP58MMP97he8po1a8L7lZWVsWbNmhbbuN1u6uvrMZvNbZo7oWmJvl9/hvbX/n4mfD4f33zzTYvjBAIBKisrgeZ/D+Pj4ykrK2tx02df8vLyePrpp1u8L6Ex0f7rX/8KtO1758Ybb2T27NnMmzevTUs7PvDAAyQnJzNz5kz+9Kc/tfjbV1VVxdlnn82WLVs46aSTWu05dDjk5eVRUlLC+PHj99ibRgghDiXpXi7EPjTN+LpkyZLw7OMmk4nTTz893GKyJxs2bOCWW24hNjaWsWPH0qtXr/Datp9++inV1dWMGjWK66+/vk2x5ObmcvXVV/OPf/xjr9tVV1e3OjFRk0svvXSf60Hv7vzzz+e2224Lt0jtz2Q68+fP5/bbb+e4446jd+/eJCUlsWvXLubOnYuu69x+++3hbVNTU7ngggt44403GDJkCKeeeiq1tbV89tlnnHDCCS1aFXVd58Ybb+Thhx9m4MCBnHHGGfj9fhYuXEhlZSUTJkwItzbtr+LiYm699VY0TWPAgAHhH6q7GzJkCNOmTSMlJYXzzjuPd955hyFDhjBp0iRqamqYP38+drudIUOG8OOPPzbbNzc3l/T0dN555x0sFguZmZlomsZFF13UbA3q3UVGRvLyyy9zzjnnMG7cOM455xy6d+/OypUr+fLLL0lJSeGFF144oOtti4cffpglS5bw7LPPsnz5ciZMmBBek7iuro5nn312jxMztYVSKtyTYm+taj179mTcuHF89dVXfP7555x66qlMmDABXde58847Wbt2bbjXxN133w3AiSeeyN/+9jeuuuoqpk+fTlRUFDExMVx//fWMGDGCMWPG8OGHHzJ69GiOP/54SkpK+Pzzz8nNzSUtLa1FDFdeeSVLlizhjTfeoFevXpxxxhkkJiZSWFjIggULuPzyy/f4GTSZTLz22mvY7XZeeuklzjrrLGbNmrXPbsW6rvP+++9z0UUXMXfuXHJycjjxxBPp27cvJpOJ7du3s2DBAsrKyrjtttv2eqypU6fSs2dPnnjiCdasWcPQoUPZsWMHn3zyCaeeemqLmxOrV6/mrLPOYsSIEfTt25e0tDTKysqYO3cugUCgWaJ+5plnEhkZybHHHhsegrNkyRKWL1/OsGHDms3YPnPmTCZOnMgVV1zB008/zahRo4iJiWHXrl389NNPrF27lm+//ZakpCQKCgoYOnQoAwcOZNCgQWRkZFBbW8snn3xCcXExN954Y5tWQxgwYAC5ubn897//JRQKHVT35v35TDQ0NHD88cfTs2dPhg0bRmZmJl6vl/nz57N+/XpOP/30Zl2yTzzxRJYvX87kyZM54YQTsNlsDB48eK/jqqFxrPlNN93E7bffzpgxYxgwYABRUVGUlpayYMECtm3bRlJSEo8//vg+ry8hIYFp06a1+fVIS0vjyy+/5PTTT+eBBx7gzTffZPLkycTFxbFjxw4+/fRTqqqqOOmkk3j//ffbPLxiX3788ce9fuf9+rkvv/wSgOnTpx+S8wshxD51yEJlQnQymzdvVqeddpqKi4tTmqbtc+3QJmVlZerf//63Ou+881Tfvn1VTEyMMpvNKiEhQY0fP14999xzLdZO/fU63b9WWlqqoqOj97pO977+7Wkt47258sorFaAcDoeqqqpqdZvW1sBet26duuWWW9SwYcNUQkKCslqtKjMzU02fPl198803LY7h9XrVbbfdptLT05XFYlE9evRQDz74oAoEAq2u0x0IBNTjjz+u+vbtq+x2u0pOTlYXXnih2r59e6trM7d1ne62vJa7H8Ptdqu77rpL9ejRQ9lsNtWtWzd13XXXqfLycjVu3DjV2p/bZcuWqYkTJ6ro6Ojw+6qpbva2ZvmyZcvUtGnTVEJCgrJYLCojI0P93//9nyooKGix7d7Wp97XWuGtqaqqUr///e9Vz549ldVqVS6XS5100klq3rx5rW6/P2sNf/nllwpQQ4cO3ee2b731lgLU6aefHi574403wms7N9XR7h5//HHVp0+f8HrXu8dVUVGhrr32WpWZmalsNpvKyclRd955p3K73Xu9hjfffFOdcMIJKjo6WtlsNpWVlaXOP/98tXLlyvA2e6pLwzDU9ddfrwA1adIk5fF49v0i/WLevHnqN7/5jcrKylJ2u13ZbDaVnZ2tfvOb37RYl3hP59+xY4c6//zzVVpamrLb7apfv37qkUceafWztnPnTnXnnXeq0aNHq+TkZGW1WlV6erqaPHmy+uyzz5od9/nnn1fTpk1T2dnZyuFwqNjYWDVkyBD1yCOPtLomcm1trfrrX/+qjjnmGBUREaHsdrvKyspSU6ZMUS+88IKqr69XSjW+9+677z41YcIElZaWpqxWq0pJSVHjxo1TM2fObHXN8T158sknFdAidqXatj707tr6mfD7/eqRRx5RkydPVhkZGcpms6mEhAQ1atQo9fzzz7f4Lqivr1f/93//p9LT05XJZGr171ZrvF6vmj17trr22mvV0KFDVVJSkjKbzSo6Olodc8wx6o9//KMqLS1tsd/u63TvS2vrdP869scff1yNGTNGxcbGKovFopKTk9Wpp56q3n333TbV1f6s072vf7923HHHqcTExH2uXS6EEIeKptQBzAIlhBBCCNFJ1dbW0qNHD0aPHr3H8eji6PTTTz8xePBg/vKXv4R7wgghRHuTpFsIIYQQXc4//vEPfvvb37JixQqGDRvW0eGIw2TatGmsWrWKjRs3ynJhQojDRsZ0CyGEEKLLueaaa6iurt7jkl/i6OPxeBg6dCg333yzJNxCiMNKWrqFEEIIIYQQQoh2IkuGCSGEEEIIIYQQ7USSbiGEEEIIIYQQop1I0i2EEEIIIYQQQrQTSbqFEEIIIYQQQoh2IrOXt0FVVRXBYLCjwzisEhMTKSsr6+gwxEGSeuz8pA47P6nDo4PUY+cnddj5tUcdms1mYmNjD+kxhfg1SbrbIBgMEggEOjqMw0bTNKDxumVy+85L6rHzkzrs/KQOjw5Sj52f1GHnJ3UoOjPpXi6EEEIIIYQQQrQTSbqFEEIIIYQQQoh2Ikm3EEIIIYQQQgjRTiTpFkIIIYQQQggh2olMpCaEEEIIIYQQnUxxcTEej6ejw+iynE4nKSkpbdpWkm4hhBBCCCGE6ESqq6vxer1ERUV1dChdltvtprq6mpiYmH1uK93LhRBCCCGEEKITqaqqwul0dnQYXZrT6aSqqqpN20rSLYQQQgghhBCdiFIqvHa56BiaprV5zXhJuoUQQgghhBBCiHYiSbcQQgghhBBCCNFOJOkWQgghhBBCCCHaiSTdQgghhBBCCCHa1Q033EBSUhJJSUmkpaUxfPhw7rvvPrxeLwA7duzg5ptvZvjw4XTv3p0RI0bwyCOP4Pf7w8f45ptvSEpKoqampqMu44DIkmFCCCGEEEIIIdrdxIkTeeqppwgGg6xevZobbrgBTdP485//zJYtWzAMg7/97W9kZ2ezYcMGfve73+HxeLjvvvs6OvSDIkm3EEIIIYQQQnQxhoLC+hBVngCxTgtpkSb0dp4Q3Wq1kpycDEB6ejrvv/8+ixYtAhoT8okTJ4a3zcrKYsuWLbz66quSdAshhBBCCCGE6DwMBYu21fHttvJw2XE5CYzLiWr3xLvJ+vXrWb58ORkZGXvcpq6ujtjY2MMTUDuSpFsIIYQQQgghupDC+lCzhBvg223l9E5ykh5larfzzp8/n6ysLEKhED6fD13Xeeihh1rddtu2bbz00kvce++97RbP4SJJtxBCCCGEEEJ0IVWewB7L2zPpHjNmDI8++igej4cXXngBs9nM1KlTW2xXVFTEeeedx+mnn85FF13UbvEcLjJ7uRBCCCGEEEJ0IbFOy36VHypOp5OcnBwGDBjAU089xapVq3jrrbeabVNcXMyZZ57JiBEjePzxx9s1nsNFkm4hhBBCCCGE6ELSIk0cl5PQrOy4nARSI9uvlfvXdF3npptu4qGHHqKhoQFobOGeNm0agwcP5umnn0bXj450VbqXCyGEEEIIIUQXomswLieK3knO8OzlqYdh9vJfO/3007nvvvt4+eWXOeuss5g2bRrdunXj3nvvpbz8f2POm2Y8b7J+/XoiIiLCjzVNY8CAAYct7v0lSbcQQgghhBBCdDG6BulRpnYdw70vZrOZK664gueeew673U5eXh55eXkMHjy42XalpaXNHp9++unNHptMJoqKito93gMlSbcQQgjRRfkMnXKvgT+kER9hxuM3CBkGKU4dE6GODk8IIcRR5Jlnnmm1/MYbb+TGG28E4IorrtjrMcaMGdMiAe8MJOkWQgghuqAKn8b6Mh8rdlThDRikuuz4AwYhZRDrtHJS71jirZJ4CyGEEAfr6BiZLoQQQoi20zR21gb5eHUhq3fWsKuqgW+2VFDnDxIyoKohyDfb6wjSOIutruuUeM38VG5Q2GA6aia2EUIIIQ4HaekWQgghupiGkJni2gYSox30TXOR5rLjCQR5b/kueiRHsTyvkpHZcUTYTEzIdrIk38uLS7ZRXOsl1mnlsjFZTO4dBaFgR1+KEEIIccTr1El3ZWUlb775Jj/++CM+n4+UlBSuu+46evToAYBSivfee4///ve/uN1u+vTpw5VXXklqamoHRy6EEEJ0nO8LPHywahe+oGJXlQcF/L+ByZzQO5GAoaj1NibT32wpJyc+k7eX5ePxhzCAknofj365kbiIQeTEmEiwqw69FiGEEOJI12mT7vr6ev70pz/Rv39/7rrrLqKjoykqKmo2dfzcuXP5/PPP+e1vf0tSUhLvvvsuf/3rX3niiSewWq0dGL0QQgjRMYKahc/X7kDXNXZVu/EGDQB2VDTQEKhnYm4iaS47iZE2+qVGsrnMjdNuYVCMk0i7mXk/F9PgD7GjysMPefVcMioNu2508FUJIYQQR65Om3TPnTuX+Ph4rrvuunBZUlJS+P+VUnz22WecddZZjBgxAoDrr7+eq666iuXLlzNmzJjDHrMQQgjR0TxB8PkNGvwhgiGFBijA4w8SYTUTNBQn9E4kym5mTWEdy/IqKahuIBhSxDgtnNIvhTk/FhJlNbG1wU9RXYBsV8ctNyOEEEIc6Tpt0r1ixQoGDx7ME088wbp164iLi2PSpEmcdNJJQONabtXV1QwaNCi8j9PppGfPnmzatKnVpDsQCBAIBMKPNU3D4XCE/7+raLrWrnTNRyOpx85P6rDzOxLrMNam6N8tmuV5VSgUJl3DpGtkxkWwamclfVOjWV9Yw+XHZ/P0f7ZgMemkuRwUVjdQ5QngDRqMzIrFbALQMOn6EXV97eFIrEexf6QOOz+pQ9GZddqku7S0lPnz53Pqqady5plnsnXrVl555RXMZjPjx4+nuroaAJfL1Ww/l8sVfu7XZs+ezaxZs8KPs7OzeeSRR0hMTGyvyziipaSkdHQI4hCQeuz8pA47vyOtDk8baMbjC+LxBymu8XFM9xiqG/z0TIyitM5LfqWHkjofVd4AlW4/SVFWeqdEUecNkhZjZ2RWLEu3VdIrOYYBmclE2jvtz4n9cqTVo9h/Uoedn9Sh6Iw67bekYRj06NGD888/H2hMkHfs2MH8+fMZP378AR3zzDPP5LTTTgs/brqTVlZWRjDYdWZo1TSNlJQUiouLUUomyOmspB47P6nDzu9IrUO3O8igtCjG904iaCg2l9bhCxhsKqtnwcZSjs1OYPGmMlKibFS6/VS6A1R5AvRMiiQx0spnqwsZ2zueiT1d1FWVUdfRF9TOjtR6FG0nddj5tVcdms3mLtvAJg6fTpt0x8bG0q1bt2Zl3bp14/vvvwcgJiYGgJqaGmJjY8Pb1NTUkJWV1eoxLRYLFoul1ee64h9opVSXvO6jjdRj5yd12PkdaXVY7vazbFsZ/pBG39QY/CGDN77fgccfwmLSsFl0fthRxZT+qZhMGltK63FazUwZkELAF2BoRiQTe8XgMhscQZfV7o60ehT7T+qw85M6FLu74YYbqKmp4fXXX+/oUPZK7+gADlRubi6FhYXNygoLC8N3qpKSkoiJiWHNmjXh5z0eD1u2bKF3796HNVYhhBDiSOJyNN5grvUF+WpTCYO6ueifFg2AYShiHRaSomws3lxGN5edU/qncFyPOGIcZnZVuxmWGYvLLDOWCyGEaLsbbriBpKQkkpKSSE9PZ+TIkTz22GNdokdxp23pPvXUU/nTn/7Ehx9+yOjRo9myZQv//e9/ufrqq4HGLihTpkzhww8/JDU1laSkJN555x1iY2PDs5kLIYQQXVFWrIXMuAiK6mqocPv5fE0BZw9Pp0dCBCEFOorshEg2l9Yxb30pmgaD0mMojfNy4cgMYq2GtDQJIYTYbxMnTuSpp57C7/fzn//8hzvuuAOLxcJNN93UbDu/339ULfHcaZPunj17cttttzFz5kw++OADkpKSuOSSSxg7dmx4mzPOOAOfz8cLL7yAx+OhT58+3HXXXUdVBQohhBD7y6ErzhqcSK/UaFbvqiXCZqK82k2PxAjWFdVhteiM7RlPmsvOoPQYXA4LTpNiR3kthhHTpbqUCyHE0UpXIezuXWgNlShnPF5nOobWvktAWq1WkpOTAbjsssv47LPP+OKLL9iyZQs1NTUMHTqUl19+GZvNxooVK1i3bh133303K1aswOFwcNppp3HfffcRGRnZ7Lh/+9vfePnll/H5fJx11lk8+OCD4ZzPMAyeeeYZ3njjDUpLS8nJyeHWW29l6tSp7Xqtu+u0STfAsGHDGDZs2B6f1zSNGTNmMGPGjMMYlRBCCHHks2oGQ5OtqFAkX28pwxc0SIyyc+VxaSQ5db7e4aG4xoNFM6is9VJJY7f0KKsOSNdyIYTozHQVIiL/P6i8JQBoQET2WNyZJ7V74r07h8NBVVUVAEuWLCEqKor3338fALfbzYwZMxg+fDjz5s2jvLycW265hTvvvJNnnnkmfIwlS5Zgt9uZPXs2O3fu5KabbiIuLo677roLgKeeeopZs2bx6KOPkpOTw3fffcd1111HfHw8o0ePPizX2amTbiGEEEIcOB3FiHQ7fZK64wsZuGw6ZkIEAiEGJtnYXmpne4UbAKtJ55R+yVg0SbiFEKKzs7t3hRPuJipvCfaEvngiu7f7+ZVSLF68mIULF3LFFVdQUVGB0+nk73//e7iF+o033sDn8/Hss88SEREBwMMPP8yFF17In/70J5KSkoDG1vMnn3wSp9NJnz59+P3vf899993HHXfcQSAQ4KmnnuL9998PDzHOysri+++/5/XXX5ekWwghhBDtTylFpFkRaYbdW7CdJoOzBiVSVBeLN2iQEmXBZe2aq3kIIcTRRmuo3EN5BbRj0j1//nyysrIIBoMYhsFZZ53F7bffzh133EHfvn2bDQPetGkT/fv3DyfcACNHjsQwDLZu3RpOuvv374/T6QxvM3z4cNxuNwUFBbjdbjweD+ecc06zOAKBAAMHDmy36/w1SbqFEEII0SqLZtA9WqdxsRMlY7mFEOIooRxxaK2Wx7freceMGcOjjz6K1WolJSUFs/l/6ejuifOh4nY39taaOXMmKSkpzZ6z2WyH/Hx7Ikm3EEIIIYQQQnQh3ohuRGSPbdbFXMseizcivV3P63Q6ycnJadO2vXv35t1338Xtdodbu5ctW4au6/To0SO83c8//0xDQwMOhwOAlStXEhERQXp6OrGxsdhsNnbt2nXYupK3RpJuIYQQQgghhOhCDM2EO/Mk7Al90RoqUI54vBHtP3v5/pg+fTqPPvooN9xwA7fffjsVFRXceeednHPOOeGu5dC4vNgtt9zCLbfcws6dO3n00Ue54oor0HWdyMhIrrvuOv785z9jGAajRo2irq6OZcuWERkZyXnnnXdYrkWSbiGEEEIIIYToYgzN1Dhp2mGYOO1AOJ1O3n33Xe6++25OOeWUZkuG7W7s2LFkZ2eHl4tuGife5I477iA+Pp6nn36a/Px8XC4XAwcO5Oabbz5s16IpmRFln8rKyggEAh0dxmGjaRqpqakUFRXJhDmdmNRj5yd12PlJHR4dpB47P6nDzq+96tBisZCYmHjIjne4bNu2jaioqI4Oo8urq6trU3d5/TDEIoQQQgghhBBCdEmSdAshhBBCCCGEEO1Ekm4hhBBCCCGEEKKdSNIthBBCCCGEEEK0E0m6hRBCCCGEEEKIdiJJtxBCCCGEEEII0U4k6RZCCCGEEEIIIdqJJN1CCCGEEEIIIUQ7kaRbCCGEEEIIIYRoJ5J0CyGEEEIIIYQQ7USSbiGEEEIIIYQQ7WratGncfffdLcrfeecdevbsCcAbb7zB1KlT6dWrF7169WL69OmsWrWqxXGSkpJISkoiIyODY489lqeeegql1GG5jgMhSbcQQgghhBBCiA73zTffcOaZZ/Lhhx/y2WefkZ6ezrnnnktRUVGz7S666CLWrFnD0qVLuemmm3jkkUd49dVXOyboNpCkWwghhBBCCCG6GAODQn8h6+rWUegvxMDo6JD45z//yeWXX87AgQPp1asXf//73zEMg8WLFzfbzuFwkJycTEZGBr/5zW/o168fixYt6qCo983c0QEIIYQQQgghhDh8DAy+KfuG5cXLw2UjUkYwJnEM+hHULtvQ0EAwGCQ2NrbV55VSfP/992zZsoWcnJzDHF3bHTmvqBBCCCGEEEKIdlfsL26WcAMsL15Oib+kgyJq3f33309ycjInnHBCs/JXXnmFrKwsunXrxumnn45hGFx55ZUdFOW+SUu3EEIIIYQQQnQh1b7qPZanWlMPbzB78PTTTzNnzhxmz56N3W5v9tz06dO5+eabqamp4dFHH2XEiBGMHDmygyLdN0m6hRBCCCGEEKILibHF7Ff5oRAVFUVtbW2L8pqaGqKjo5uVPffcczz99NPMmjWL/v37t9gnOjo63J38xRdfZNSoUQwbNoxx48a1T/AHSbqXCyGEEEIIIUQXkmJNYUTKiGZlI1JGkGxNbrdz9ujRg59++qlF+U8//dRsPPYzzzzDE088wTvvvMOQIUP2edzIyEiuvvpq7r333iN22TBp6RZCCCGEEEKILkRHZ0ziGHq6elLtqybGFkOyNbldJ1G79NJLefnll7nrrru44IILsNlszJ8/n9mzZ/Pmm28CjV3KH330UZ5//nkyMjIoKWkcYx4REUFkZOQej33xxRfzxBNP8MknnzB16tR2u4YDJS3dQgghhBBCCNHF6OikWlPpG9WXVGtqu89anpWVxdy5c9m8eTPnnHMOkydP5qOPPuKll15i4sSJALz22mv4/X6uuOIKBg4cGP73j3/8Y6/Hjo2N5ZxzzuFvf/sbhtHxS5/9mrR0CyGEEEIIIYRod0OHDuX999/f4/MrV67c5zHmzJnTavljjz12oGG1O2npFkIIIYQQQggh2okk3UIIIYQQQgghRDuRpFsIIYQQQgghhGgnknQLIYQQQgghhBDtRJJuIYQQQgghhBCinUjSLYQQQgghhBBCtBNJuoUQQgghhBBCiHYiSbcQQgghhBBCCNFOJOkWQgghhBBCCCHaiSTdQgghhBBCCCHEboYNG8YLL7xwSI4lSbcQQgghhBBCCNFOJOkWQgghhBBCCNGp+P3+jg6hzSTpFkIIIYQQQoguRjMMTAUF8PPPmAoL0QyjXc83bdo07rrrLu677z569+5N//79efTRR8PP79q1i4svvpisrCxycnK48sorKS0tDT//6KOPMmHCBN58802GDx9ORkYGAElJSbz22mtccMEFZGZmMmbMGJYvX862bduYNm0aWVlZTJkyhby8vPCx8vLyuPjii+nXrx9ZWVlMmjSJRYsWtdu1S9IthBBCCCGEEF2IZhiEliyhZuZM6j/7jJq33iK0ZEm7J97vvvsuTqeTL774gj//+c88/vjjfPXVVxiGwcUXX0xVVRVz587l/fffJz8/n6uvvrrZ/nl5eXzyySe88sorLFiwIFz+xBNPcO6557JgwQJ69uzJtddey+23386NN97Il19+iVKKO++8M7y92+3mxBNP5IMPPmDBggVMnDiRiy66iF27drXLdZvb5ahCCCGEEEIIIY5IelERdcuWNSvzLFuGq1cvQmlp7Xbefv36cfvttwOQk5PDyy+/zJIlSwBYv349K1asID09HYBnn32WsWPH8sMPPzB06FAAAoEAzz77LAkJCc2O+5vf/IYzzjgDgBtuuIEpU6bwu9/9jokTJwJw9dVXc9NNN4W3HzBgAAMGDAg/vuOOO/jss8+YN28eV1xxxSG/bmnpFkIIIYQQQoguJFRdvV/lh0q/fv2aPU5OTqa8vJzNmzeTnp4eTrgBcnNzcblcbNq0KVzWrVu3Fgn3r4+bmJgIQN++fZuVeb1e6urqAKivr+eee+5hzJgx9OzZk6ysLDZt2iQt3UIIIYQQQgghDp4pJmaP5aF2PK/FYmlRZuxHl3an09lqudn8v7RW07Q9ljWd695772XRokXce++9ZGdnY7fbueKKKwgEAm2OZX9IS7cQQgghhBBCdCFGairOkSOblTlHjsRISemQeHr16kVBQQEFBQXhso0bN1JTU0Nubu4hP9/y5cs577zzOPXUU+nXrx9JSUns3LnzkJ+nibR0CyGEEEIIIUQXonQd09ixjWO4q6sxxcRgpKSg9I5pkx03bhx9+/bl2muv5YEHHiAYDPKHP/yB0aNHM2TIkEN+vuzsbD799FMmTZqEpmk88sgj+9Xivr+kpVsIIYQQQgghuhil642TpvXrRygtrcMSbmjs/v36668TExPD6aefztlnn01mZib/+te/2uV8999/PzExMZx22mlcdNFFjB8/nkGDBrXLuQA0pZRqt6MfJcrKytqtf/+RSNM0UlNTKSoqQt4enZfUY+cnddj5SR0eHaQeOz+pw86vverQYrGEJ97qTLZt20ZUVFRHh9Hl1dXVkZOTs8/tpKVbCCGEEEIIIYRoJ5J0CyGEEEIIIYQQ7USSbiGEEEIIIYQQop1I0i2EEEIIIYQQQrQTSbqFEEIIIYQQQoh2Ikm3EEIIIYQQQgjRTiTpFkIIIYQQQggh2okk3UIIIYQQQgghRDuRpFsIIYQQQgghhGgnknQLIYQQQgghhBDtRJJuIYQQQgghhBDt6oYbbiApKYmkpCTS0tLo168fZ599NjNnzsQwjDYfJxQK8fTTTzN69Gi6d+9O7969mTx5Mm+++WY7Rn9wzB0dgBBCCCGEEEKIo9/EiRN56qmnMAyDsrIyFixYwB//+Ec+/vhj3njjDczmfaenf/vb33j99dd5+OGHGTx4MHV1daxevZrq6ur2v4ADJEm3EEIIIYQQQnQxSoGvRuF1B7BHWrBFa2ha+57TarWSnJwMQGpqKoMGDWLYsGFMnz6dd955hwsvvJBdu3Zx1113sXjxYnRdZ+LEiTz44IMkJSUBMG/ePC677DJOP/308HEHDBjQvoEfJOleLoQQQgghhBBdiFJQvMHN2kWFbFlRxtqvCine4Eapwx/L2LFj6d+/P59++imGYXDxxRdTVVXF3Llzef/998nPz+fqq68Ob5+UlMTXX39NeXn54Q/2AEnSLYQQQgghhBBdiK9GUbCpullZwaZqfDUdkHUDvXr1YufOnSxevJj169fzz3/+k8GDBzNs2DCeffZZli5dyg8//ADA/fffT0VFBQMGDGDcuHHcdttt/Pe//+2QuNtKkm4hhBBCCCGE6EK87sAeyoOHOZJGSik0TWPz5s2kp6eTnp4efi43NxeXy8WmTZvCjxcvXsznn3/O+eefT3l5ORdeeCG33HJLh8TeFpJ0CyGEEEIIIUQXYo+w7KG8Y6b82rRpE927d2/z9rquM3ToUK655hpeffVVnn76ad566y3y8/PbMcoDJ0m3EEIIIYQQQnQhNpdGeu+YZmXpvWOwudp5JrVWLFmyhPXr13PaaafRq1cvCgoKKCgoCD+/ceNGampqyM3N3eMxmp7zeDztHu+BkNnLhRBCCCGEEKIL0TRI6RNBbKoTrzuIPcKMzdX+s5f7/X5KSkqaLRn21FNPMWnSJM4991x0Xadv375ce+21PPDAAwSDQf7whz8wevRohgwZAsDll1/OyJEjGTFiBElJSezYsYMHHniAHj160KtXr/a9gAMkSbcQQgghhBBCdDGaBvYYDXtM613N28OCBQsYOHAgZrOZmJgY+vXrx4MPPsiMGTPQ9cZO2K+//jp33XUXp59+erMlw5pMmDCB2bNn8/TTT1NbW0tSUhLHH388t99+e5vW+e4ImlIdMTF851JWVkYg0PpkA0cjTdNITU2lqKgIeXt0XlKPnZ/UYecndXh0kHrs/KQOO7/2qkOLxUJiYuIhO97hsm3bNqKiojo6jC6vrq6OnJycfW4nY7qFEEIIIYQQQoh2Ikm3EEIIIYQQQgjRTiTpFkIIIYQQQggh2okk3UIIIYQQQgghRDuRpFsIIYQQQgghhGgnknQLIYQQQgghRCeiaZrMxN/BlFJobVzYXJJuIYQQQgghhOhEYmNj8Xg8HR1Gl+bxeIiLi2vTtkfm6uFCCCGEEEIIIVoVExOD1+ulrq6uo0PpspxOJy6Xq03bStIthBBCCCGEEJ1MSkpKR4cg2ki6lwshhBBCCCGEEO1Ekm4hhBBCCCGEEKKdSNIthBBCCCGEEEK0E0m6hRBCCCGEEEKIdiITqQkhhBBCtBNdKUxlZRjV1egxMQSTkpCVdYUQomuRpFsIIYQQoh3ohoH69ltqly0DpUDTiDjuOBg1CqVpHR2eEEKIw0S6lwshhBBCtANTaRme779vTLgBlML97beYS8s6NjAhhBCHlSTdQgghhBCHiKEblIfKKQ4W4wu44dct2kphVFd1THBCCCE6xFHTvXzOnDnMnDmTKVOmcOmllwLg9/t5/fXXWbp0KYFAgMGDB3PllVcSExPTobEK0ZEsFgtKKYLBYEeHIoQQR5UGGlhQsIAtVVsASMTJSUNziFq1tdl2ustFqCMCFEII0SGOipbuLVu2MH/+fDIzM5uVv/baa6xcuZLf/e533HfffVRVVfH44493UJRCHH4BfwDDY6V2J9TnBfCuLqDhvY/wvzcH8+Z8NJnNRwghDpimaYS0UPjX1IbaDeGEG6Bcufk2uhQtPjZc5hwxklBS0uEOVQghRAfq9C3dXq+XZ555hmuuuYYPP/wwXO7xeFiwYAE33XQTAwYMAOC6667jlltuYdOmTfTu3bujQhai3VgtNvxuDU9lgLpKH9vr88lbXY7ZouOvqiEl3Y7dF0/8poWYN24m8oxp0C+7o8MWQogjmqW6mvq8PHSPB71bNwLR0bhxU1C6gZL6EjxOE8emHUtBQwFmk5mQCqGUQqGxy+5FO2M6EYXVmOLjCSUn77OVW9M0DM3AhAnDMA7LNQohhGg/nT7pfumllxg6dCiDBg1qlnRv27aNUCjEwIEDw2Xp6ekkJCRI0i2OOobbQsVOLzvX7cTvDZHQLRKTWWP90mJCQQMVMohNjmDHujJ6DHQR6DkU/8dvYO3TF0ffHgQ1+VEnhBCtsRYXUztrFgGzBY/Hg2azEvmbcylf8SX1K77FpZvIOH0qn3jmsNNXRJQlikEJgyj1lGLVrSQ5kqiJNFMQaWd95Qo8BR4GxA0gNyIX3WjZ4bA8VM6K8hUU1xeTHZPNiMQRROlRhILSIV0IITqrTp10f/PNN+Tl5fHQQw+1eK66uhqz2UxERESzcpfLRXV1davHCwQCBAKB8GNN03A4HOH/7yqarrUrXXNnZvgs5P9UxdpFBShDoZt0ynfWkz0kAXuEBXeND8NQ+L0Glkg7QcNEQLdhDhkonw+UQtOlro9E8lns/KQOOzcd8C79FhUIgNkCGmAo3Cu/p2TJfwGIGjKMmWvfoDbaTDA5lsL6QtZWrCXKEsXairXkuHK4tP+lPP/j89T4a7CYLMzZNofL+l/GuIRxVAYr8Rt+rCYr/pCfj7d9jD/kx2lzUuov5aOdH2Ez28iNySXXmYvZ6NQ/3TqMfBY7P6lD0Zl12r/c5eXlvPrqq9x9991YrdZDcszZs2cza9as8OPs7GweeeQREhMTD8nxO5uUlJSODkG0wcZlRVQWutE0jWDIQDdBwBeiosBNbJqTuipvs6TabFLYjAb05EQcvXuT1C21A6MXbSGfxc5P6rBzCtXXU+52Y3I4AXA6nJiTkqj8cTVmkwmlQVmMRll+MZFGLPUxdmqCtVT7qpnYfSL5dfkEjSArSlZQG6jFb/jRNI2GYAMzN8xE76tT7atmS80WNlRsYEL3Cfxc8zNpEWl0d3RnfdV6viv6Dk3TiLXGcv0x13N6j9Ml6TgI8lns/KQORWfUaZPubdu2UVNTwx/+8IdwmWEYrF+/ni+++II//vGPBINB3G53s9bumpqaPc5efuaZZ3LaaaeFHzd9qZWVlXWpmZ41TSMlJYXi4mKUkpm2jnR+b2PvDMNQ6CYNI9T431AgREySk4IN1QQDIWxOCxabBVeEgS0vj6iLLoC+vSgqKurgKxB7Ip/FjqVpGmsrFD/urMHtD9IvLZqR6Xas+zHvtNRh56YBocQEvOVlOB1OPA0eLO567LYorA02agO1BFQQBehmC7pJx+P14Df8+EI+qn3VRFmiKPeUY9WteAIeglqQoBGkoqGCcm85hmGwpmwN7oCbGm8NDYEGdHRqAjUsLliMjo5ZN1PaUMpb69+iT2QfolV0R780nY58Fju/9qpDs9ncZRvYxOHTaZPugQMH8thjjzUre/7550lLS+OMM84gISEBk8nEmjVrOPbYYwEoLCykvLx8j+O5LRYLFoul1ee64h9opVSXvO7OJirBjjPaijIUZotOwB/CYjORkuOiptxD/xPSsDnNOKIsuFwazlA1HH85gWgnoVAIpI6PePJZ7Bg/VSjumvMzlfX+cNkf/l8uZ/aJavzs7Aepw85JAbZjjyVQVAw+HyhQaERMmEjGlw0Ue4sIeq1EWCMxEmIADYe5cViaL+RDQ6O0oZSpPaaypnwNhjLQ0FAoBiQOoLKhkjJPGVOypvDupnepD9RjMVmItkZT7asmwhxBSIXQNA2ryUpFQwUVgQqiTFEd+bJ0avJZ7PykDkVn1GmTbofDQffu3ZuV2Ww2oqKiwuUTJ07k9ddfJzIyEqfTycsvv0zv3r1lEjVxVLHFhkjv48LqMFO4uRpN08gaFE98twgiY+xotgAhAuEvKC+/LF2zn0mDEK3RdROFDTq+kKLe4yPdZSPG0vl7BpnNZr7ZUtIs4QZ4fel2jssaQqJFPj9dhT8mhogLLyCy3o3ZXY9KTiZoNhMf4SR66VLK3Q1cMPF3zKqYT0TIR0Z0BrH2WOZsmYNZN9PD1YO0iDROyjyJL/O/JKRCDEoYxMiUkczcMJNhScMAOLPnmXyW9xnTek6joqGCHFcO87bPQ0PDoDFZ7xXTSxJuIYTohDpt0t0Wl1xyCZqm8fjjjxMMBhk8eDBXXnllR4clxCGllMLVXceVGkf24DisDhMhixcwSE51UVRUJHeERbvY5THx+boyVu2oosEfYlROPIVVHmYM78bABL1Tv+/MZjMldb4W5aV1ftx+g8TWO0WJo1TQasXRP5Pq3f6eaj16wE9rsHVLZ5uvAKfJQbYrB78RwGF2cNWAKzErHT2kcLurSXYk88dRfySvJo86fx3vbngXm8lGt6huzNk6hz5xfRifMZ715es5JesU/MrPiJQR/FT2E7qmk+BIYHjKcBLNiRhBWXFCCCE6k6Mq6b733nubPbZarVx55ZWSaIsjnqZpWBTYKsoJbt2K5nCgkpPxJie3KXFRSoHZjx4FQQAls3uK9hXUrHywuoDVO2uo9QYw6zof/lDAtCHpPL84jz9OySXNFtj3gQBDN1MXNBFl1dCD3naOvG28Xi/Dusfy5c8lzcqPy4kjI9oEoc7fmi8OklKE6uuxLN7KmH6ZOPr35f38uYxKH01J+XYK135PhGajX9IgUiqs7MjSWBu1luSIZAxlMDJ1JNHWaEo9pZh1M96Al6zoLEJGiIARYE35GjKjMukb1xdv0ItZN+Pz+wgaQXRaLjUmhBDiyHVUJd1CdEZWrxdtxQp8P6+joawMU0I87m+/I2LMGGyjj8M/cGCnbjEURwhNp8YPJg1cNg2LxUIgENjvsclNNlUF+eSnQjR0PP7GBLRbrJPSWi8ltT6Wb6/mtL4xmIw9J96aprHDo/NtXhVfb6nAYdaZMiiVYWkOIvWOT2qPy47iglHdmbVyF/6QwTHdY7h8TBamUMsWcNH1hAD78OEEPvsU+7p8RpXHktb/dHaYDCZXuvAmd4dgiOKV35FXspV0zxAW5pbREGxgfPfxbKzYyDdF31DjqyErOov8unzya/LZVLGJKGsU3aK6UVhfSNAIsqFiA56Ah2k9p2HGjIG0dAshRGciSbcQ7URDxwho6GZQWsvERtM0nJWV+BctpuaTTwgUFaEaGtAsFqLPnEbtnDnEJsRjzc7G96v15oXYH9V+jc/Wl7OmoI6ggtyUaDSlSIt10Cc5guwotV8T6um6TlGNF6U0QGH8smtJrZcxPRKwW+rZVFLPhsQI+se1fgxN09hQDV/8XMy7K3YRH2ElKcrGP7/axm8n5DAi3YGNjk28481Brh+TwqR+SXgDIXrGW7Er/753FF2G0bsXUZyKd+UKLIZikKUHQ/12qr54iWBJCd7MRDB+WdJxVwE9B+WQENWNMncZK0tXUuopxWay0RBsoHdMb0rcJQxJGcLCnQsbe0DpFmr9tYxNH4uhDEyaiYDS2V4doNITINZhoXuMBasmSbgQQhzJJOkWoh0E3To71lRRW9GAPcJC9wFxOBP+191b0zScGzYQqqqm5uOP0TQN5W3sVqsCAQL5OzDFxhIqLcNcVQ2SdIsDpenM21DBwk2VaLpGXpmbem+Q43sn8sPOanxBA62bi6yItie4uq5TVutlRFYsy/IqsegaAUNhKEVmvIM6n4sfdlZzfK949vQ1U9Kgsbaglp921XDW0DQsZp26hiAmk0Z+uYfUaDs9joD5ooxggJ5NcbSScFtsNjZVhvAGDHLibNiMhsMboOhQhq5j9MnF1rdPY8G2bdT897+Y4+MJlpURWellUGQqvaLT8PXJgowsttXlEWWKYkrWFLZUb6HOX0efuD7YdTvugJsNVRtoCDbgC/lIi0zDaXGiazqBUABdszNvYyVrdlWHY+ibGs2UvrGYkR5RQghxpJKkW4hDLWRi0/cl+DyNSUxDfYBN35fQf1wq1kiF2TAwbdhIyYMPEn3KJIJlZViSksBshsAva27X16NHRGCKi0WLcXXk1YhOrsYPPxXWETAUNW4//VKjcFrNfLamCG/A4LttlZzUJ4kLRqQRb2nbGOxgMEhKjJ01hbVM7JNEXrmbaLuF4Vmx2Mw6VW4fHn+QzFg77KG1enuVl6z4CFJi7GwpreengloAou1mBme46JUcSc8YK+oInmW/Kmjhox9LmLlsB3XeEKNz4rnqhGxyo4/cmEX7CP3SU8TYtQujthZ7n1yMqkp8GzehgkGc6emknNifpJhB1PvdbKncAkCiNZEMRwa5sbl8veNrMlwZVDRUEDSCJDmTqGyoJKiCrKtcR5Qlin6BBL7dsYtIPTJ87vVFtQztFk1GlIzzFkKII5Uk3UIcYt7aUDjhbqIUNBTVYtq8hOC2PFRtLZGjj6Nh0yYiRo+mYdUqLKmpBHbuBKWw9uyJf+dObIMH44mM3MOZhNg3iw6+EFS5/SRG20mPdfLR6kK6xzlJirJR5w3w/fZKjs2JIz7F1ObjDkiJ4OstJr7dWk7v5CgibDqFNV42ldSzq7KBW07qTbpTofbQ6zXCaqKwzkefpCie31AWLq/3BqlpCLKt3MOINAcaR24Cu3xnPS8szgs/XrqtAk2DB6bmSot3F6VHRwMQ8vmwZudgSUkFTUNPTqZuxUqi4uIZ1WsUpe5S/CE/df464uxx9I3siyXDwvrK9WS7sjEwcJgdRFojqfHVcEziMShNsaEsn+210C+mX7PJ1Gq9IZCkWwghjliSdAtxiOmmlrOG64EAxq6dmGvrCCmD+uXL0e12rD16YM3sDoaBLy8P++DBOIcPx5KdTdRZZ+LJzARDxup1NQozZV6Fw6qRepDHctlNDEyLprC6gcLqBlJddjQNgoZiZ6WHbrEO6n1Byt1+wNHm4yZag0zul4zFpGEYinpfEH8gyOT+yZw2MIXcBDPK2HPC3DPOxvIddRgGpLrsVLj9mHWNhEgrQUOh6xq6ChyxHWYjIiJYtaO4Rfk3WyvYUROg1xHQNV4cfnpODqbly9F1nbqlSwEwpyRDMAgogoWFZPTvz8W5F1PqLcVqspJsTcaszAyOHkyf6D5UGVW8veltfiz/EYtuaZzhvKGUUncpfaPjCSpoMBqI0BuHHWkaJEbKGnZCCHEkk6RbiEPMFq0Rm+Kkqtjzv7Kgl6iK7dTOno0eEUHkuBMIFJegR0ZQM2cuppQU4q+4AlNmd/wZGXiDv7SUS8Ld5exya8xcsZPVO6uJj7Ry1rAGTsiwox9gi69hGMRHWjh9cBrLt1fSMzGC7WUR5Fc2Tu7kCRjERVhJirTt13GVUoxMNRPtSGN9cT0akB7jINKqkxunw14SbgCbFiQj1snSreUEQwYuu5mQgpJaH5E2M0PTo9o8a7+u65hMJgzDaHU2doVGUb1BUZ2fCKtOZowNh+ngPlt+v5/4Vl6zWKcZh0VaHLuqQFQUzhnnYSrYhW/NWtA0jMhI+OX2kZ6QgKEUEUSQbc9u3OmXt7lSCitWkrVkru17Lds82yj1lvJt0beUucvwhrwsr/ic43qdTV5hNbpZJ8rsZHxuEokO7X8HEkIIccSRpFuIQ0xhkDk4Bleig6piDy6HwlW6Hc9zL6F8PkLl5QR27SJq0slYumfiWbkKW3Y2em5v6mNjf2kREV2RT5l57ft8NpfW47CZKan189KSPBwTchiVemB/rkOhEL0SIpi/sZySGh9zygs4LieBam+Aarcfq0nj1IGp9EmyAW0b093EMAx6R0OuKwKT2YphBDFCoX0m3E2OSY9g1Y4qTuidyNKtFXgaAhzTPZbzR6TTO2bfE6prmsZ2t87GEjeBkCIh0obNDAMTLZhUKLzNykIv/1n/v/W2k6MdnDMkGYdVJ78mRNBQdI82Y9Pa/tkLBAKMyo5lzqpdVDX8b7+Ljs0iJxr8Msl5lxWMiiTUty8RM86l7osvwm9kc2Iipl692rTYl82w0dfelxRbCsuLlmM1WyltKKVXTC96JgXonx7CoQXoG51OnMUky0oKIcQRTpJuIdqBZjGIzbSQ2CMey4+rqfniA1AKZRjoTieG30+wtBRbdg4JN96AGjkSt23/WhrF0aewLsiGwlosFjM7KjyARkKUhq5pVBlW4s1BjAPo/dAnTqOhRzwbi+soLGzg6y3l9E+NpkdSBH1SouibFEGkduBZolKKYGD/166OtQS49vhurC/zcWxOHFF2MznRJqIsRpuSiLWV8PSCTXj8IbyBEEHD4OLjsthU6uHsAbHoRoDagMbiTWXN9iupbWBtmY9vtlSycFMZJk1jUIaLa8Zkku5se4+CQXHw8PRBLNteRU1DgCHdXIzKiMLvl3W8uzqlFKG+fYmOj8coKUGz2aB7dwJ2+34dJ1aL5bLcy1hQvIDert74lZ/Ptn+KoQyyorPAUkt3oztJtiSsyto+FyOEEOKgSdItRDsy19RAfR0hrxdLRgbB4mKM+nosKSlYunWjduFC4u/+Ix5JuAVgNWnERtrYWu4mOdrOOcO6EQJe/TYfs65zUr8kRnSPIsW2f13NlVIck2wi7qQe/HdzJeuLasmMd9I/NZoByU6iTR3XLBupBxiRrEN4UqhQm5YM13QzizaVYDPppCY6GrvmWkysK6ylrsHPwLRo+saA22/gDzW/UaGhsa6ongUbS/EHG5/7bmsFCRFWbjo+da9j0X9tYJxicEIcVqsVr9cLSMItGikgkJQESUkHdZx4PZ7+Mf0p9hazoWoDxyQfQ6IzkcK6QuZunUuMNYZkazJnZJ9BvCn+0AQvhBDikJKkW4h2YnG78c6di3/NWqxpadR/9RXWzEwAjEAAS0YGStPwJyZ2cKTiSJEaqXPm0FQMTJTVeqnxBnn5m+1ogNmks6GklsvH5HBybjxx5v1L7gzDoHskXDEsDrMlGQC/zwd0zn7QHmWi3hdAafDlusau49F2M+cM79Y4M3qNl74xVmLsOpE2M/W+/3UBD6ETCKlwwt1kRX4VNaPSiTbt300NwzB+SbiFaB8ZjgzKA+Vsq9lGn/g+lHnK2FW/ix6uHoRUiHpfPUuKljCt+zTa1H9dCCHEYSWzvQjRDsxeLyxZgu+HH0EpLN3ScU07Az0qCsfQoUSdfDKB8gqck/8fQVPbl2kSRzddhXDarDw6byPeoMF/NpQQNAzMJp16X5A6b4ilW8v5bns1NcEDu2dqGAZ+n++XhLvz8v4yAdwPO6rDZbXeICu2VxEfacNmbvx6s+sGpw5MwWZp/JxpwOBuLkytfPvFR9pwWlquPiDEwTABNq8X80GsOR+lReENeukb35dVJav4YvsXLC9ZzodbPsQT9ODX/Ox078SjPPs+mBBCiMNOWrqFOEQ0pbBVVEBJKf4ffqD+P//B8PvRnU6q359F1MknQSCAtUcOusuFeehQvCkp+54tSnQZXt3Ohz9sxhsI0TMxkkWbyomwmnH7gjTNTRwyFMV1XtaVWjgurev+CTc0Ha/fwPnL66MAp1VHKUWU3UK6y0pTk19WtM6Vx2VQ7g7gtJpIcpr4eqeXKIeFuobGyePMJo1zhnXDbHTOln9xZLIXFOBbsoT67flYsrOxHTsKf1bWfk98pmkaOjqBUICyhjLsJjvql9nKvy/6nhO7n4hFt2DX7DKJuRBCHIG67i82IQ4hs8+HvnIlDT+uxt6vLzVz5oSnLw653diys1EKlNmMKTMTY9gwGiwWSbhFM5WeEOV1Pq4Yk83HqwsZkRXL3NUNhBSYNAgpGJIRw9pdtcQ7rXTlP+Fx5iAJUVZinBaSo21omoZSihinlZRoG5mRzVusI80Gka5fepWoECPTbdw9JZedlQ34gga9kiIZnGQGJX1zxaFhr6ml+u9PEti2FRUM4V25Ev+mjURd91t88XH7dSylFDnROWys3og36CXKGoVVt2I1WTk29VgMZRAwAqxzr6OPsw9m1XX/NgghxJFIupcLcZDMoRChOXOon/sR+P00rF6N4Xaj2e1odjt6VBSGx4NusRB/3bWERo0iaLF0dNjiCBRlUYzpGU9RTQNLtlag6xoXH5tJj8QIeiRF8tvxPQiEQvxcWEtydNeefE9TIY7LiaVnYgS+QAh/0MBpMTG5fzJDUq37XNe81g955R5+KqjF4wvispvQJOEWh5Bavw7fzz9j1LtRXi9GXR3elasgP/+Ajpdly2Jo0lCcFidF7iLSItOYkj2FteVr2Vy9mWXFy/hg6wcsLF9ISD/wruxCCCEOPbkVKsRB0A0D08qVVL3zLprJhB4RgREKEXvuuYRqa1DBEP4tWwgUFmLNziZYXU1IkzGjonXR5hDjeyfwzMKtaMDr3+YzIC2ay0Znsq6olh92VPFtXiVnDe3GgGQb7COxPNplOkPcflI260sa8IcMeiY46BahQO39dfEpM//+dgdrCmowm3TWF9awdGsF952WS4pDEm9x8DRNw6ithd3HcRsGyucD34FNuqcbOsfFHodvoI9P8j6h3FNOta8as8lMQ6ABXdOpaqhizuY5RJmjGBEzApOSOUOEEOJIIEm3EAfBtGMHvrU/4xg2DN1uR3PYcWRmUffll4TKyghWVGAfMoTYiy6i8r33cE09DcuxxxI4iAl1xNFLKUXPGI3hmXFsLXOjAbuqPTy1YAtnDE7n+F4JDMuMZXhWLJHSkgVArDnI6PSmniNGm8azFrtDuP0hTLpOvS9EhM2MAjaUuknJdLRnuKKL0AFTZBR6bCxGVVW43BQbiyU9/YAXltOCGuMSxpHtyqbYU8y6inWYMBFUQeJscVR6KgEo8ZRQ4iwhzZJ28BcjhBDioEn3ciEOkKZpBIuLsefmEiguxrvmJ3xrf6b2k0+w9+tLqK4Oc3w8wcJC/AUFhAoKUHX16B6ZXVbsmREMMiYnlu5xTirdfty+EGZdo2dSJEu3lJEQaaOHq6OjPHR0wOp2Y/X50Nq5F4gPC6vLYfHWaixmM1MGpTG6RzyGUpS7/RhKeqGIQ8MAghrEzJiBbUB/9OhoHEOHEn/lFfjTDi4R1kM6WXoWY1xjGJUyitSIVCLNkVR6KlEocmJyqPPWUReoOzQXI4QQ4qBJS7cQB8FqNlPz/jsECwtRPh8mVxClFIanAVuvXgQKCjCqq1G1NWg2G3pMDCEZzy32ISsyxL2n9mZdiYdASNE91km9P8D1E3qSHaUIHSU9Jaw1Nfi/+ILqb79Ds5iJmjQJffRo/BERh/xcxT4zPxXW8/maImobAvRJi2ZTSR1BQzEyK47M+Ai6xTqQqZ/FoaCUQs/JIVhRgWP4CJzHjUaZzWjZ2fjMh+anVygUoq+tL5O6T+KdDe8A0Du2N31i+7C9ajvxtvhDch4hhBAHT5JuIQ6Q2eMhsHUbwZJiCATQbDZQClNEBN7169HsNjRdx5yaiik+AWuPHlj798OjSwcTsW8JlgDjMqykpqZSVFSEUhoQ5CjJtzEphffjj3EvWAhG4zjqqrdmEqPAdNKJhA7l50TT+aGgjo3F9eyqamBCbgLl7gA/7qymuiFAmsvO11sr+O24HvSJtWEYMq5bHLxASgrm446DklJAoSWn4N3PWcv3RUfnuJjjiB0Uy+bqzVR4KthZs5PxGeNJMCfIPSQhhDhCSNItxAHSa2poyNuGHhVFsKQUGhogwokeFYUlJRn/jp0YHg8Ro0ZhHdAfx5gxNPTqJcuEdWHKFkFZfYiECB3d37WHGejV1fjXrQ8n3E18mzbhHDqUUGLCITtXVcDMVxvK2Vpaz5DuMegmnSWby0mKtmExNyb3dQ1Blm+vpHdSOik2SbrFwVNKEYiPh/j2bXFWhqKPow8pthRq/bVEW6OJ0WP2ey1wIYQQ7UeSbiEOkB4K4d2wkYghQwgUFKI8bgy3B1NiIo4hQzFFRqLZ7CgNQsEgKitTfgR1YWurNGat3Myagmpyk6M5d3g3hhy6vLLzMZmglW62us2GMg5tc35BbYDl2ys5dXAqC9aXMiwzFrc/RFmdH12DuAgrhlKElKLeG4KuvRqb6ISUUrg0Fy6bK/xYCCHEkUOSbiEOkOFpIOLYY/F8/TURY8agaRqmmBgsWZlUvPgSBIPYcnPR4+Kwjh5Ng93e0SGLDrLLa+W+j1dTUN24VFBRTRlrCmp4asZgciKDHRxdxwi6XESMGU31zp3h3h+azYYlKwuVcGjvRhjKIMZpJRg0CIQU9b4g8RFWAiGDkKEIGQpd10iMtJMeZQK6Zp0IIYQQon1I0i3EgUpKJFhWhmPIYFQwiGa1EaqrQ23aDD4fmM2EqqqIPnu6JNxd3Ibi+nDC3aTC7WdDST05kV3zvaGUQjvxROJdMXi+XYpmd2AfNAgGDiBgOrRrC2e6rAzuFo3ZbMJQBhuL6zi5bxI7qhr4cWc1GXFO+qZGMSo7BqcpJCNAhBBCCHFISdItxAHS/X7McXHUfvRReFyqY+hQos+chuF2o7tc2EcMx3/MMR0cqehoJr31pai6+pR6QbMZjh2FY/Rx4PcTtFjapVusyxzg3OHd2Fzq5nunFdBYkV9FpM3EWUO7MTA9il4JTtKdIemWK4QQQohDTpJuIQ5QcNNmPBs3EjV5MsrrRbNaCRQXEyovxzF+HHr3TLwpyah2XntYHPn6pETQKymCzaXucFmqy06/tCgg0HGBHSEChtE4vrsdE96+MYoMl4v0mD4s2FBCQZWXzAQnx+bE0ivOissclBZuIYQQQrQLSbqFOFAWC0ZtLZ4ffkD5fOD3g8WCKeN8fEOHSouZCEu1+rnz//Vh3s8l/LSrmj6p0UwZkEJ3hyTch1OkFmB4sk6/xO74DEWCQyPo97P7GG5d12XJMCGEEEIcUpJ0C3GA9F49MScnEywpAYcDHA5sOdmo3FxJuLsgzWSipMGMJxiiW6QFs9HQ7Pk+LoPBE7rRoLJxaAF8Pl8HRdq1KaVwaH4cJgj6AV1ne61GtTfE1jI3tQ0BeiRFMKKbA4dMqCaEEEKIQ0CSbiEOkC82lpibbsS7YAGBHTux5fbGesIJ+ByOjg5NHGa1IQvz11fx1nf5eIMG/29gKqcOTKW3SxEM/i9x8/l86PiQdPvIoOs6X+V7CYQUr367g61l9Zg0MJt0Ljq2O5cdE4+GtHoLIYQQ4uBI0i3EQfClpWG66CIswSAhsxmftHB3OZqus2KHm8fnbyY9xoFD13lvxU7yK9xM7p/CiO5RuHR/R4cpWlHcoLOmoBarRWdrWT0AIQW6Usz5sZATc+PJjOjgIIUQQgjR6XX1yXOFOGiGUgRNJulS3kUFNBPL8ipxWHSUUhTVeAkZ8N22StYX1/H1ttqODlHsQUm9H5NJo94balauFHgDBnW+0B72FEIIIYRoO0m6hRDiIJiURrTdQnyEjbL6/3Uct5tNBEIGizaV4nQ6OzBCsSdJkVZKqr1kxDrYfZEBTYOMODuZMdaOC04IIYQQRw1JuoUQYj8pTafKr+HVLFhMcFyPOCwmMO+2HveJfZNYnldFpN0svSCOUKkOgzG94rGZdC49LosIqwmTDr2SIrl+Qk+iTTKRmhBCCCEOnozpFkKI/VAf0vm5uIFqn+LHndVEO6wc3zOeu6b0ZfHmCn4urKFXUhSFNQ0U1ni48cSeNDQ07PvA4rAzDIOTsx1sqdHITnQwukc8IWWQE2slUvPLzRIhhBBCHBKSdAshRBtpmsZPhW6K60M8vXArVpOONxDiw1UF/Pm0vlw0Kp1NpbF8tLqQWKeFR6cPYnS6lVBIxgYfqZRS9IhWgAbhmcpl4jshhBBCHDqSdAshRBsFDB2z2cJ7K/OxmnTqfY3dj4P+IF9tLKPeF+C03pGMzepNKBTC6/VKwi2EEEII0cXJmG4hhGgjk6Ywm3XqvAECoebrN1d6/KwtqKHMb8LtduP1ejsoyiNLSDOzy61T4rdgtcka9kIIIYToeqSlWwgh9qA+qJNf5aMhaJAaZSfCqkh32ZiQm8Sna4rD22nAMd1j+M/6Eky7TabW1RU26Lz87U6sZp1gyCDKYWFAWjRZ8Q4Mv5/uLgsW3dj3gQ4jzWLh57IgxTVeUl12+sXrqAPoraDrjfe0ZVy4EEIIISTpFkKIVtQGNN5ZWUiVx483pFFe72fKoDTK6/2MzIrDZjbx0eoCNE1j6uB0Suu8nDYojThzEOlRDkoz8/r3OzHrGt9tq6DSE8AfNBjfO54JfZJJibKxtdqgV5yOiSMj8Q5g5oMfKnhh8Tb8QYXNrHHd+J6c0S8WC4E2HkXDV61TXeRB0zViUh2oZEm8hRBCiK5Mkm4hhGjFxrIGqjx+FBpFNT40XecfX22ld0o0zy/axqjMGP52zmAq6nysyq+iX7qLE3KiCYXampwd3cq8Bj/sqGFgNxe13iD+oMEp/ZOxmXUe+XwDVrOJQd1cXDYmk9zojo620c/lAZ77aivGL/cAfEHF0ws2k5s8lIHxbTuGpxRWfr4dr7vxfRAVa8OiW9Gj2iloIYQQQhzxZEy3EEL8iqZpVNQ3zmDtCylMJo2yeh8V7gBOqwmAlTtreOPbfE7oGctdk3I4taeDKF0S7iZ2s0ZMhJlAyCBoKGxmnRSXnc/WFOMJGAQNgxX5Vbz1/U4KvSaCquO/jnZVecMJd5OQAbuq27bkm0mzsGVlWTjhBqir8rF9TTkm3XQoQxVCCCFEJ9Lxv3KEEOIIo5QiI65x0i+TphEfacesaaTH2Cmr84W3K631UVrnJ+DzdFSoRyyX2WDa4DRcDgtmXaNHYgTrC2sBMOsaSoFhKJbnVZJX6ePzDZX4jI79SkqMsu1X+a+FAlBT2jJBryryoMnXrRBCCNFlya8AIYRoRa84G33TYil1h1hbUENchIXJ/VMIBENogK7BwG4uUpzyZ7Q1SilO7hnFhNwErjg+m4RIKykuO7oGDqsJTdMIhAziIq34gyG2lrvZXt2x62MPSLYx/Zj0ZmXnjexG/0R7m/Y3WQ3i0pwtyhO7R2IgA/2FEEKIrkrGdAshRCusukFclIPYCCsxTgupLjs/7KzGpOskRlrpkxrFmUPSMKmOTRSPZGZCDE3UObZbAnm94imp8/PDjiqqPEG8gRCaBqcNSqXW48MXCFFeHyA3ruO+liK0AFcem87I7DhKar2kRNsZlGLHobWtjkNGiJ4jkqir8FFf6QUNYhKd9BiWRMCob+fohRBCCHGkkqRbCCFaYZgdfLhqA9/lVQKNLdtZ8RGMyo5j8im9SXaaiDZJwt0WPp+PNBuk2zXundqPZdurqWnwkxkfgcMEeaWN3c7jIywdHClEmwMcn26G9MhfSoL7tb8tJsTIMzOoLwui6RCVaCEhPYqiIkm6hRBCiK5Kkm4hhPiVEDpbSj0EQv+bVctQkFfuJmQoLhiZTrTJt5cjiNYopegbA/2GxbOlKsSK7RVsrWp8nXsmRZEVa4UjZPkwALfmoNYXItUJBNt+g0W3hYju1rheu6ZJt3IhhBCiq5OkWwjRKZl9PkzFxSifDxUTQzApiUO1GnKZJ8Tna3cxqV8KK3dUN3tu6uBUku0GAZmo/ICpUJAeLg1X73hK66KIsJlIizJj0Y6MhFszW1i4zcNby7ZSWuvlhN6JTB2USu9oSaCFEEIIsf8k6RZCdDq2mhp8n3xK7cqV6DYr9iFDsQwZTLBPH5Q6+NRb1zR8QUWUFW6b1Js5PxYSMhSnDkzhxN7xBCTjPnhKkWCHBHtTl/IjI+EG+L7Ax58+WktTR4cPVhVQXu/jzlN6Eq1JDwchhBBC7B9JuoUQnYqmaQQWL6Zu/nwAQkCg6HNcVgvmjAwCzpazR++vBIdOdkIE328rI9pu5pYTe6BrGjmxFqJMknAfzTRNY/XOakK/ugeweHM5M4ZnMCShY+ISQgghROcla90IIToVc0MDnu+XtSj3rt+AfohaoHUMpvRL4LiceEwmnbySGhIcEG2W7sVdgdVsalFm0jTMutYB0QghhBCis5OWbiFEp6NFtGzN1mxWVGRkK1u34XiaRn69xuqCOqo8AXomRjA01c647EjGZkejawplGIek67o4simlGJLhIsKm4/b9r7n71IEp9Iy3gfJ2YHRCCCGE6Iwk6RZCdCpBhwPn2LGESkoJVVc3Fpp0Ik86CZ+pZQtlW+TVa/z1s03kV7gB0DS4YFQmFx6TgG4EkVy7azkm2czj5wwhr9xNrNNClM1MSb2Pr7ZWMyQ9mhSbLBUnhBBCiLaTpFsI0akopdBGjiTa6cT3/fdgtuA4fgyBvn0P6HiappFf6WNAuovu8REsyyvHFzCY80MBJ/SMIysSDEwEDYXNpKS1+yin6zpz1tfx+PyNKAVWk8743CQSIiy8tWwnQzJc3DG5N2k2GdsvhBBCiLaRpFsI0ekErVY45hisQ4eCpnEw7Y4bq3UWbSpj/vpSkqNs/L+BaXy3pZwKt596b5BNfsU3W0tx+4P0TY1mVGY0kaYjZ6ZtcWhtrtV4ZuFm/EFFhNWE2x/i0zVF/O6kXsRHWlmRX82agjrScuwdHaoQQgghOgmZSE0I0WmFNI2DmdqsKmTnkXkb2VRSR8hQFNZ4mfn9Dkb1SKBbnJNoh5k5PxZQWufF7QuyYnslCzZVgiZ/Oo9WRdVe3N6W76rqhgA2U2O9V3mklVsIIYQQbSe/HIUQXZJCY3OZm/XFdVR5/HSPc2LSwVBgGIrfjs9hc3Etv+5MvrG4lhoZ0nvUSo6247Q2zg1gMemYfpmwPMZhwf/LOmLd4hwdFZ4QQgghOiHpXi6E6JIKG3Q0XScn3klD0KC8zku3GCeaDr2SIxmcoPPfmtb21NBapOLiaNEnTuOmk3rx1nc78AZDJERGclyPOAylmNgnmQHp0QxJdQDS2i2EEEKItpGkWwjR5RR7df42fwuaBknRdtYW1pDsspNX7iEpykqPRAdKKXKTIliZX4Wx2+RpA7u5iLaC5N1Hp4aARkGVhxN6J+ANGNjMOqV1PryBEN9urWRXlYcMV3fcZkiJ0GRiPSGEEELskyTdQoguRdd1vlhXwebSegJBg3G5SZzUN5k6b4DxvZMY3SOOXlGNiVR6pMY5w7qxbHsVtd4AA9JcDE5zgpKJ1I5Wa8v9vPHdDgDSXA6Kar2EDMV5w7uxq7qB0jof43sn8vPOMk4dlEqfOPkaFaKjNJgayPPkYRgGCY4Ekk3JaCGto8MSQogW5NeCEKJL8SmdNQU12M0mAkGDRRtLsVl0hmfGcUrfBDIjjWbrcmdFa2QPSQA0lBECJOE+mtV7G9dlt5h0NB1CRuObwW8oNMAfMqhuCGDSNRasLyVndAZW7WCm8xNCHIhCVcgra15BoXCYHPhCPhKdiYxKGUUfZx+shrWjQxRCiDBJuoUQXYpNV2TGOymsbiDSbqbBbxAIKXRdIyXChFItEyhlSKLdVfRMdJIUbaXSHcAfNHBaTXgDISJtJnQd4pxWusXayS+twhc08AQMrPLbXojDSpkUczfPpdxTjtlkJs+bx676XUSYI/hq51ecl3se45LHEalFYlImGQYihOhwknQLIboMpen4Q4opA5JYs6safAqrw0yEVefcY9KwHtSK3+JokGYPcNf/68tzC7eSX+mhX1o0x3SPZeH6YrrFODhnWDe2llQBkBhlJ9KqIQP8hTi8KkOVrK9YT2Z0Jmsr1lLsLgYgqIL4DT9ba7Zi0S2U1pbSJ64Pg2IG4UBWHRBCdBxJuoUQRz2FxpaqIEu3luEJBBnSLYZ7TuvD5lIPSkFuipN0h7Rmi0bdYyz8ZmQGuq6h09jl/MJjs0iItLKxoILiai8RNjP/r38SZhluIMRh59AcuKwuFApN0zB++RzqWuNKuP6Qn2JPMVbdyk9lP+EJepiYNLEjQxZCdHGSdAshjnrFDToFtSHS4iOp9fhZsqWMIb4gp/SK/qXboSRO4n/yqnw8Om8jDYHG94VZ10iIsHLrpF6c2CcBX1CRFGnGocv7RoiOEEEEk7ImsbRwKd2julPsLkYphcPswBvwYjPZyIzKZGvVVuqNeir8FdSpOlJI6ejQhRBdlCTdQoijWr7HzHsrCli6tYJoh5nxvZMY1D2en3ZWMjrLRaRZugaL/zGZTOyqrMdpNeML+lGqcTK1en8Ql91EilMDNORGjRAdRynFmNgxJNgSKPeVk+3K5tvCb7Gb7eTG5uK0OFldtpq1ZWsBWFexjrSINNLi0ygwCvApH2n2NOwBu4z3FkIcFpJ0CyGOWiHdyszlO/h8TRFBA0rqfBRU5XPdhJ64HJaODk8cgSxWG9UNASwmjaQoGzUNAawmnYw4JwlRNiDQ0SF2XZpGhVdR4Q4SZTOT7NTQNUmYuird0Olr74vm0JgQP4FJ3SZR1lCGgcHOup18vePr8LbxjniCBHn151f5eNvHlHnK6BvXlxm5M0h1pJJsTsYUMnXg1QghjnaSdAshjko6UF1ciaO2ivgIKyV1jZOkeQIG64tqOW1AElEWhTRyiN01+IJYTRoD0l18u60Cp9WM3aJzbE4csXZNGrg70KriALNWFeINGiRFWRnV3cXY7EjMHZh4a5qG2etFC4UgFELV1EBMDMGoKGlBPUyUUgSDQVK1VFKdqWi6xrbqbTgsDoJGkFh7LMnOZLwhL+9ufJcafw2GMlhdvhq/4eeMHmewXdtOTmQOqZZUlCH1JoQ49CTpFkIcdSx19fgWLqBh/TZ67Kylz6BBfJnSm2UlPgBcDgv9Eu0oJa2WojldBRiS4eLrLWUcmx2HrmkYSjEgzYVdBWSe8g5S2GDmH4s2c1yPOPqlu8gvb6DKB9tqdXq72neddKvupLbYx4b8ImKTHYRsHgBMwSCsXk3998uguBhTfDymtFR8JSVEnnQywT657RpXV6RpGnVGHQ1GAy6zC6tqXK9P0zX8yo8FC8pQDIodxM6anY0TraGREpnCtpptuANuDPW/O2frK9czOXMydUYdG6s34jQ5GZ86nmRTckddohDiKCVJtxDiqKJpGv6l3+DbsoUIs05qpIWt3y1nwokuVpliseg6Y3rEY5FuwqIVSilyXDo3TOjJ9ooGAoZBTryT3ERLq2u4i/anaRol7gBjeyVgNpl4cdE2TCYTG4vrSIqyct/pA+gfe+i6IGiahrm6GrxegpHdWfN9EeuXFqMMRUyyk5GnZxORGkLbsoW6RYvQPQ34d+yAHTtwoNAcDuq/nEdUagoBl+uQxdXVKRRr6tbw+c7PKfIUEWmJZEbvGSQ5kvhqx1dUNFSQEZHBqORRZDuzGZM2huXFywmEAjjMjsapGH4l0hKJgUG9v546fx0/1/3MtuptXNX/KhK0hMN/kUKIo5Yk3UKIo4rZ46Fu82YALJpBRqwDq0kjUJLHeWMHMTQjhuEpZkIhSaBE6yLNigEJJlIjnGgaxNt0QN4vHaUBG4s37STaYUbT4bgeidR5g3SPdTJvXTELN5Ux5PgUAoGDv5FmCgYxvv+e2hUr0HSdmhP/j3VfF9KUsVWXeFg1L5+Jl+Ti/XkdAMrbEN7f+/M6Ik6ZhDc/H1VRAftIuu0NXtS6dRgV5Zi7dSOQm0vQJGOLW1MSLGH29tn8UPYDJt3EmLQxLNy1kPpgPSmOFDyGh+/Lvie/Pp9Le1/KiJgR9IvpR9AIEiDA9obtdI/uzpbqLeFjTuw+kTJPGYYy8AQ9eINetjZs5Zvibzgl9RTs2DvwioUQRxNJuoUQRxRN07AYDZg0hU9zYuznuEhlNqPb7YT8jWO4oy0GkfF2zLlpDBqVisXwS8It9klTBgnh39sykLsjba/yoWvQ4DeYtbKAQEgxOMNFbnIk3WId5JXVY7ZaD0nSrefnU//99wA4R45i2656UDRrJS3fWU9duR+b09FYYPnfpIyazYb65e+LFhGx13PZ3G48L79M3fz/hMviLrkY05lnEtL1g76Wo02Zt4xCdyFBI8i4buNYWbKSCEsE5Q3l2Ew2BiQMoNhTTHlDOXmePAY4B+DEGa67eks91w6+lg2VGyioLyAzKhObyUZDsIEyTxnrK9YTZ4/Di5eGYAM7G3bSy9ErfH6TUuhuD9isBCwyEacQYv9I0i2EOGKYCeKq24bZXYhWsxMiEggkDaHCktrmYwQtFpzHHUfdvHnhMt2kETlkEAHD3x5hCyHaUcgwiHFa+ffXeaBp+IMG32ypwGLSGdY9lrQYB76Ghn0faB80TSNYUBh+3JCfT0T2oF8e/S/zdkRasDlMWAcOxLtxIzgj0KMiMerqcY4Yga+0FMfgwYQSE/d+wnXrmiXcAJVvvUXq4CF4evY46Os52jgtThqCDfSP74/dbKcuUIfdbEfXdAwMfiz7keHJw1lfvp5ybzlahNZsMrssaxYxCTHkOnIxWUzscu/CHXSzumI1a8vXEueIw+1z4zA7sJvsNAT/956yVFbiXbAQ/66dmCIjiRg7lmBurszxIIRoM0m6hRBHjOiGnViKV6Jt+wrsUeCrx1qylsT+51Bmy2rzcYx+/YiOiCCweQvYrFhycwmmpCBTlQvR+fROdPDuykL8IUWU3YRhKIKGYk1BDf93Qg59U6IwjGCzfczBIFp5OZhMmKOj0atrCMbH4TPv+WePUgpTdFT4sVFYQMrESKIS7NRV+MLlgyZ0w5mo0RDZjeizz8a/Zi1kZ2PLyMBwOLBGRWJkZOyztdooK2tZGAwRKisFSbpbSLelc0zSMWi6Rn5tPg3BBoJGkJAKYYQMNDQsugWXzYVSCl3XW/RqclgcWA0ryqvobuqOZtZITEvE7XOzqWoT3eO608PVgx3VOxiVNAoAcyCA5+NPCFaUAxCqraX2s8+IjooikJZ22F8HIUTnJEm3EOKIYDKZsHjL0HYuA3cJFKyAqBSoLcKsm0hJG4EBeJKGUk/kXo9laBpGVhZadjYAAaUk4Raik7L8f/b+O1qu6z7svr/7tOnl9t4LeidAAALYSbCpkLJM2ZQlx1aKpTi24zdZz1rOk8eOs5I3a8VOnqw3TuJETiwX2RJVSEpsEjsAEgSJXi/a7f3e6fWU/f4xICiIBAsI4F4A+6PFJdwzM+fsmTNzzvmdvffvh0NzPIDf1MgUHcI+nYCpUxfxsawxgvYL8+2tZJLc00/jzMygTU4hTBNhmuB5xB7/VfJLLp1VXOvpQd/7Nm4mDYD80f/gti//FrOjOeyiS1VjiKrOAIVCJYO53dqK3t4OQNn7ZNMQtIbG9y+0LLSmjz+y52bix89Xl3yV/3Lov9AWaePE/AnS5TQNwQZydo6+qj5iVow7W+8krIfxPsb+kFJSJ+rY0bqDGquGRCHBaGqU21pvo9Go7B8xP38h4AbwhEfBLaKPnMZoaUSTaiqAoigfTQXdiqIsHnYRdAPmBysBd2oUYu3wzl8iCkn0oV2E61egbfsD0tZHl3RRdXIV5fonPJf1bVEOj0QYSRYoOx75sstn1zTzt3uGWdUaoWtptNK7CZRefx1vYhIjnSZ/6BA4DqHbtpPfdwBndpbaP/435GpqPnBbdiRC6Mtfxjt3Fi+bw2huxq0q01Lrp6mpiYmJCVyZv+g1Hye4+0DLlxF79FFSP/hB5W9Dp+Y3f5NSdzdc7jpvcFGiNAYbSZQSPNj1ILvHdzOeHeczLZ/htubbODx1mAIFljUs+9jHfyklrWYrda11JO0kISNERFTqrLvCpSByzDkJTGFgaRZD6SHKbplwoZNTo09zb9u9hAip+t6KonwoFXQrirIgguVZjNQgIHFinRR89chwA1gRCNVBZgICVZX/lx7YBfBXIaaPExh5jXTPlxb6LSiKcg1IKVnbYOFsbueNs3OUHY917VXsH57np8en6GuIoGkanutiDg3hTU1hBgJokQjs3Qu6jj0yitnQQPn0adyz5+ASQTeAHQnD6spc7ndTs31AtalPrRQIYP7qr9C4aSPu7CxGSwulnp7LD+JvAp7n0R5u58T8CUYyIyyrXkZjqJFbG27FL/20drTSYDVgyE9+eeuTPhqMys1cKSUI2Jfcx8n0MTa0V1M4fgy/GSBiRchrLrONQd6efZu8zGNJi/X16+n0dyLk1fi2KIpyvVNBt6Io11y4OI5v6BVEKQ3CwJg+jt51B8lgF9U9dyFG91YCbSMAuVkwg+C5UEqBW0ZLDhLUbPKeyiCrKDcDS3isbw4xOFfg3EyW//yzAfJlF1MXeFLiSIF54gSZHz1J6cABvHweo6qK8PbtZF96Cb22lvLZs6DrCGPxlOSyLQt7+XIAVJrHj3Y6d5pEPsHtLbdzZPYIJbtElVVFt68bU54/H1yhDueEm+DN8TfxpMfc1uXUtTYxfeRtgg1NiJXLKNUYFM4WOJU4RXekmx+c+QEPdD9Ah6+DsBZWI60URbmImoiiKMo1ZemCUGkSw8mhF+fR7TTm/DH82REQBvP1n0He9v+B6h7QdIi1Qv99MLQThA6FeRAavhNPES6Of/QGFUW5IXiuy3SmQNFxiQVMljdFeWhVMxPJPD67RP611/DyOYzaWhACmc8jbRu9tgazrhY3kSC0bRuir++jN6YsOpqmMW/PI3XJ4bnDdMQ72Na8jfHUODk3d8W3l3NyeNJDFzpDzPIn+kt8Z12ev2wd5Pu5nQB8of8LfHnZl4n5Yui6zoG5Azw19hRHCkdwhPMRW1AU5WaieroVRblmwvYs4dE9iH3fBteGxpUwdwoZrkcf20PEtUk3bmG26Q5q7/AjhnZDrAV2/mmlt7ucg5o+cIoYOsjTL6Cv+iquSmSjKDe8kOHSEfdzcDhJZ3WQXNnhrXNz/M5dPYhCATebRegGTqGA1d6GtB30+npqtn2G3Dv7qP7N38S/ZTO58IcnYlQWJ096TOQneGbwGYpOkf0z++mOdvO5ns8RMAJwhUflV1lVWLpF1IoykBig5JaYLk6zqWETPt3Hnok9hKwQI+kRfmnJL5FxM2RKGVLlFDvHd7K+bj0PdzxMg/bR+UcURbnxqaBbUZRrwqJMcGwXvPlfIDMFugWJc7D0IYTnQX4WwzAIFMZJB7uYrt1CTaAGfe4U4rZ/CemxSqK17AycfRlq+pGpMUyngKuHFvrtKYpylUkpuW9JFboueG1glqjf5J/c0sDa+ZMwksMfCGKXbTS/HyeTrbwoGqUMxH73dygFg+TUfOnrVtpLcyp5ipgvRo2/hrX1azk0e4gnzz7JSGqEO5rvoNVqvWLDusMizD3t9/DW5FsEzSCe9GgMNNIaaeXA9AEQMJAYYF3DOp479xw5O0dPvIeyW2Y6P82rY6+SKWX4jSW/QVREr0ibFEW5fqmgW1GUa8JfmoORt8ApQyAOdr6SoTczCUsehkgT2twAodwMog7S4W7mA93UmqPwyr9DOAUoF0A3kWt/FTsxhgjV4hj+KzaHT1GUxS2ku3x+aZQd/VX4nTLGT5+jeOgwzuwsoa1bcWZmMNva8PI5fF3d+G+9FbetlZzfrzKCX+dcXApOAU1o9FX1sXt8NwW3QNyMM5wd5skzT/L4kseJidgV2Z6Ukv5gP02dTQwVh7ClzURmgoJToCncxBvjb7CtZRvPDz5PY6gRXeg8c+4Z1tavJe6LY3s2M6UZ9iX30RvppclsQpeLJ5+AoijXlgq6FUW5JqRmgPAQVgiyU2CFoPsOSI7C8O5KpvLZAdAt/MU0XodFJtBCon4bVQ/9Jxh5E5EaQdavoGR7yNQo3rLP46iLGEW5qUgp8QmHwOBZZp/4PvboKADFI0eI7LiP8F13Y7c049XWUlrgtipXjqu5BMwAbtElZIbIOTkczyEejaOjY3s2E4UJYsErE3RD5bsWFmFWBlcSXRLl1fFXqQnVMJIeIWAEmMpPIZEI8V7G8gPTB9jWvI3Dc4cpeSXQ4Gj6KAPaAJ3hTnp9vXiuugGkKDcbFXQrinJVCCGwhEN0/gBabhbpi6F1bofkCORmoPsuOPZDqO6G1DBoBtT2weRhhC+CL9pONthKGYOpqlsQ1RsJyAJG4jR4Ds6Sz1KwakFliFWusKKnkSh6BEyNKkuqLMSLlDs+hj0+jm/FCqyODtx0iuxLLxNYvx5n7Rq1324wQ7khtjZvRYwLUuUUjufQFevCr/sxNRMk6Fydm7BSStqMNr7S+RXm5By60Nk/vf/C40W7SGOokUw5Q9kr4+ERtaKYmsnA/ADPDz1PyS3RGGzkn637Z6z2r74q7VQUZfFSQbeiKFeUJjzC2UF8qUH03BgCAYe/j5Qu3PqPkEs/i/BFKsPL65ZW6m9nJiDWBsNvQPtnENPHEX07EEJcuHCWUpLHD1Ur39uYuqhWrrChjOSv3xphOJEnZOo8sKqRu7oj6LgL3TTlF/n8xD7/eUonTpB55hn0mhqiDz6ICKlEaTcaTdNwPIcnBp4gUUpwR+sddEQ7GEgM0F/VT07m6I300hJsuboN8aCGGrbXbqcx1MipxClGMiMYmoHjObRH2+mL9zGcHqY13MptrbdxYv4Et7Xcht/wc2zuGE+ffZrlq5djOOoSXFFuJuoXryjKFWFi48+O4MuOoo++iTbwHGQnQffBpt9EHPo+7PmfyO2/jxeqR9hZRG4OyhnwRc/P8XYrZcL8UbxYB56ag6lcQyWp8792n+P0dCUJV7pg8392D9Ec7WdFrZrGsNgYHe0k/+qvKJ84AVLiTk+TfvZZArffrnq5rwPvDsl+9+bqh+0zKSVFt8hMYYZEKcH3Tn2Prc1bWVe/DlOYdEY72da4jSDBa9L2gBdgtW81q1tXs7J6Jc8OPcvxuePc1X4X1f5qwmaYjkjlpsATp54AQEPj3o57Gc+Mk5VZ4sSvSVsVRVkcVNCtKMqnZsoyoeGfYZRSmJkxOPQdMHyVB3Udzr0Kax+DvX8BxSS0bIDCHHLkLUSstRJsJwahbRPMDiA3f4NUuF8lSFOuqfGMy5mZi+v9elJycjrHilqVfXixcRIJEAItFkMWCohQCKOxkdLwECxfttDNUy5BCMGsnGUkN0LGzpC38/jxs7xqOXV63Qe+RkqJqZsYmoFAIJG8Mf4GESvC48sex4+fkl26Mle1ArJeFkMzCBD48Bs4DiyxltC8vJkz6TP8+NyPOTB9AFM3aQ23ki6l2di4kbcn38bD4+Xhl/mN1b9BtVGt5nUryk1GBd2Kolw2TUCwPEMoNYBIn0NIwH43aBGVIeN2HmbPQN0KWPc4GAE49TOkL4z4zO/iTR5BFJPQcxfEO5DhBlK163FUwK1cYz5DYGhgu7+4XLtoqoOySFgWTqGA3tSI0HQ818XJZdH8gStdsln5lN7t1ZZSMmQP8aNzP+LgzEEm85O0hFu4p+0ejp06xmN9j1GtV3/gOhr9jfTF+0iUEiBBIumL9+HX/YzMj7CxZuOnbmdapnll7BUGU4P4DB+3Nt3KsugyJouTlL0yjf5Golr0wrFA13WklByYPcDhucPsm96HLnRczyXv5JktzrKkesmF9Wu6Rnu4HexP3VRFUa4z123Q/cMf/pC33nqLsbExLMuiv7+fr3zlKzQ3N194Trlc5tvf/ja7d+/Gtm3WrFnD17/+deLx+MI1XFGuc5oQWKKMz05hjb2JPvAMYvIIGH5Y8gD4I5WkaNb5edv52fP/zoEbhiNP4CUr2YYZfRs2/xOybXejCfBch6IWUsGNsiCaQhr3LG/k2cMTF5bVR3wsawqr7+Qi5LW1Ebr1VnK7d19YptfUYKxYjrOA7VIqDMsgKZNM5acYS49haAa9sV4OJQ5xZO4IU4UpAMayY+ya2MWmuk2cyZyhOv7BQXdQBLmr7S5W1a3iVOIU1f5qOiOd5J08m5s2U2PUfKrRUVKTvDj8IsPpYQCKTpGfjfyMidoJBmYHADA1k8/1fI5Gq5GB7ABH545SF67DEx4Fp0Du/E1nS7Pw6T7KbhlDM2iPtAMQs2LU+GrU1ClFuQldt0H3sWPH2LFjBz09Pbiuy3e+8x3+7b/9t/zpn/4pfr8fgL/8y79k3759/PN//s8JBoN861vf4k/+5E/44z/+4wVuvaJcn4J2gmDyOMbkAcT0MZAu1PTD7CnIjMHQbtjw69C5rVL+Kz8L/jh031kpEZYYhPw8CL3yWl8Ud+QdZMsd5EQAhKWSoykLRkiXz66ooT5sMTSfJ+wzWNsaozMiUHMdFh/b5yPw2C9j9fZQOnIEo7kFa+sWinUfPERZubqMcplSMcE5M8GkM8uBqQPUBGvYNbaLuC9O1Ijy1tRbdFZ1Alx0I2swPcjtLbdTckuXHFVSbVVzKnkKQzO4t+NegnqQTDlDQ6iBkBYiJ3KEufwbZGk3zUh65KJliXKC08nThMwQjucgkbw99TbtsXZOzJ1AapKfjfyMgBlgec1y6gP1TBemcaVLspikM9ZJyS0xkhmhPljPg90P0ma2oYZiKMrN57oNuv/gD/7gor+/+c1v8vWvf52zZ8+yfPly8vk8L730Er/zO7/DypWVbMff+MY3+L3f+z0GBgbo7+9fiGYrynXLxME3/ArG+F7E2RfBDFZKf40fhOWfg+E3IT0CY/ugaT0s+wIMvga+CF5mGpmeRNh5MP148W4AXN2HxEAFNMpiUWV67OiLkLUjmBoEdFUybDErxWJw11347rsP13UpqX11zQkhMM6dY+6lZzjSZzIUyPN8Zg/xaD37pveRKqfI2TlkSFJtVTOWGSNsholYETLlDABV/iqEFHREOi75exMIav21aJrG80PPU3bK9FX1YWkWz517jrZwG48vfZw+X9/71uEJj5HSCPvO7kOzNbrCXURFJU+Dozk40sEQBisbVmJLG0c6WMJidnSW2mAtISOE3/QzW5wl6A+ya2oXUTPK6yOvY2gGPtPH/un9/NryX+NHp3/EeG6cqkAVv9L/KyDhzrY7iVkxmnxN6K5KyqgoN6PrNuj+Rfl8HoBwuFIq5OzZs7iuy6pVqy48p6WlhdraWhV0K8pl8OUn0b0SYvJApcxXz10QrIVgdaV3umElRJuhmIDjB6BjG9IXQY7uw8vPASB67sZLj+JoldEoSBBtGylpIdXDrVwTQgj8FNE8m6IWxv2Ar52QHpHzZ0f1tbw+OI4aUL5QjGSSzNNPM1MHb8zsJ9reRyE5R3dNP6OZUVzpkiqlqA/UI5EIIWgNt5J38uhCp+AU2NGxg+Xx5bT6Wi95DzagB6gOVPNnB/+MVDmFX/ezZ3IPn+v5HP3V/QzMDfD909/nn678p4Rk6MLrhBC8k3yH3eO7CQaD5PN53jDfYEfnDpLlJEW3iOM5+E0/o7lRnjzzJBJJQ7CBL/Z9EYHAw+Po7FFeH3udLc1b0NDYm9gLgOu5SCmpCdRwdO4oD3Y9SNSqzPsOiUqw/uroq2TKGZpDzdzecju1Wu212DWKoiwiN0TQ7Xke/+f//B+WLFlCe3tl3kwymcQwDEKh0EXPjcViJJPJD1yPbdvY9nvZLYQQBAKBC/++Wfx8GQ/l+nXF96OmITQDIo2w9nE4+wpMH4NyrlJv2ylVer/NADLSjMzNYm/+bfRQA4zvR0Sbsfsewi0XEEM7wS1DywbyjRuvbDtvIIv7tygopSTZ+TKGqRGps9B8i3vMpCE8wudewXvnh8hsiuiSzdhrvkQucPkXwHktz1hxDNuzafQ3UiNqLuplW9z7UPm41H68NDk1DY5LIWiSSaeISA+kZDQ5RH91P4dnDiM0gaZpCASb6zdTHajmTPoMnvToiHTQ6e/EJ89XvLjER6wLnZOJk8wV59CFTtkt40qXF4Ze4B+v/scMzA9wOnmaufIcYfO9Wu0ZmeGtybcQ51dckiV0qfPy2MucS5+7kG28I9pBe6SdrngXI+kRDN3gr47/FatqV/HO9DuYmsmdHXfy9sTbPNT1EEfnj15oq5SSoBFESkm2lOVM4gyP9jxKzIzx3YHv4snKsXE0O8qPz/2Yx/sex5LWVdsnNyr1O1SuZzdE0P2tb32LkZER/s2/+Tefaj0//OEPeeKJJy783dXVxX/4D/+Bupt0flhjY+NCN0G5Aq7YfrTjkBuCti1w5AlIjVYCbitY+Xf7FjjzIiz7LEJ6EK5Dr+2Elt+pJFQzgxj6+UPOkjsrc7qta1VV9fq2GH+Lw8fmOLd/pvKHJ5kbMlh1ZyvRmsDCNuxD2IdfoPz8fwPpIQDvwIv4nTLRR/8YdPMTr+/k3EmeOPUEu8Z3IYRgU8MmHux6kI1N78+ivBj3ofLJqf34foW5OdxAgOB0graWLnyORtAMkSoladE7WVW7ivHsOGEzzJa2LWxv307MH2MrWz/RdpKFJEWneCF41jUdPHBcByQYhkHUilIbraUp3nThdeV0Gcv/XoCbc3NYlkXZK3N09iiO5+BJj1w5xxvjb7CxcSNlt8xMYYayW0bTNBzPYb44T6qYwmf4mC/Oc1f7Xewc24mhGdQH6qkL1nFX+120RdpoCDYQtsK8Nvoa/oD/ovdhY1O0inRUd3yKT/3mpn6HyvXoug+6v/Wtb7Fv3z7+6I/+iJqamgvL4/E4juOQy+Uu6u1OpVKXzF7+yCOP8PDDD1/4+907aTMzMzfV0DUhBI2NjUxOTqq5jNexq7EfY5FO/OP7EckREKLyn2uD50BiCC/ciIdOWVqI2lWk02WkPB+YkfuANaauSLtuVIv2t+jqHH9rAqfoUcw6FHMOhqkRqjFpXOZHSslcWWdgtshczqY55qe/xiSsux+97qtE0zQiA7tx7PJFy91Dr1Fac4hspPkSr7z0+t6Ze4dkKUlXtIuB+QGeO/ccQSNIo96I4VZOr4t2HyqfiNqPl6ZHo9jVVVSNzrOpvZfd8wPc13EvR71RkqUkt7fezsqaldTpdcS1OPlEnjz5T7ydHDmW1yzn2cFncTwH7fz/trRs4djsMRzH4f7e+wkVQ0xMvFeBQBMafs9PopjAH/CjSY2JzATt0XYcWUmO5kkPV7qUvTISiamZ5Mo5wlYYx3EIm2HS5TSzhVmWVS1jLDfGjpodLFu+jEPThzA1k1sabqHX7EUv6GQKGTJkKBfKF6Y//rxirshEaeJ9y5UPd7V+h4Zh3LQdbMq1c90G3VJK/uIv/oK33nqLP/zDP6S+vv6ix7u7u9F1ncOHD7N582YAxsfHmZ2dveR8btM0Mc0P7u24GU+yUqoEQjeCK7kfHdeD/ByE6yq93O8G3E4RGWnAm80hA7VQu5J800ZVFuUKWWy/Ra/s4ZRdsnM22UQJ1/EQQjB+MkVtR5C0Af/nrXGePjiB43r4TI1/dFsPj66MYXgLE3hLKZG8fzin1AyQn7wG96gzyrODz3Jo5hBhK8yWpi2cTZ7lrYm3+Gz7Z4nK6Pu3v4j2oXJ51H58P8cw8D/8ML5TpwlPjtDRv45Ec5gtAT8xI0adUYdTrnRcSO/yP7ugCBLTY/zasl/j9bHXydt57um4hw31G0gUEuxo38GS4JL3bUOXOve338+zQ89SEiU0TWNF1QqKThFDGJQooQmtMo870ABA2S1TF6xjbd1aDs0cwnZtuqPdbG3eStkt0xHroDPSSaveytroWgQC4QnwKvXD39UebCdoBMnb7wXeXbEuao1a9T36FNTvULkeXbdB97e+9S127tzJv/yX/5JAIHBhnnYwGMSyLILBIHfddRff/va3CYfDBINB/uIv/oL+/n6VRE1RLlPZX4P0PGi7FXH4+2AGKoF3uAFC9dB5B5nGrZSFpU6INzDdJwiG/UwOZHGcyo0VKSWmX2d2KM9AWOMH+8Z499o3X/b4H6+cYU3rOpZEP2TFV5HnecjOjXDoWZxyGceTCCCw9j7y0aaPnTGtLMqcLpzme6e+x3BmGCEEeSfPC0MvcH/n/SSKCUJaiJIsMZIfIW2n6TA6iBNHR2UtVm5MTjAIa1ZjrV2DKSUXfuYeFwLuT03CkvASil6RO1vvBAmN4UZWR1YTCAcuPOeD1Ol1/Grvr+IGXNLZNCeSJzg0e4hVdavYN7UPIQSWbnF7y+20RdsQTYKGQANPnHqCTDmDz/Cxtm4tqXKKXaO70IXO7tHd/Nbq36Lb7L5kk8MizC/1/BJHEkeYzk/THetmaXQpQqo5yYpys7lug+4XXngBgD/8wz+8aPk3vvEN7rjjDgC+9rWvIYTgT/7kT3AchzVr1vD1r3/9GrdUUW4cZeHHXvVlrMPfgbW/AnYBWbsEWdWJW8xg22UVcN8EpHDpXFXD6IkkTroMApq6YxRzNqWcw5Tn8YsdWgXHYzxZZEl04ZIH5RqXY9z9L8gfeRGZn4eOTRysu5WGgqDW/9Hf2azMsmtmF8PZYfbP7Kct2kaqlEJKiSY0Ck6Bh7sexnVcXpt6jbSTJu/mGS2N0mg1sjG+UV1sKze0q33sD4kQW6u2Uqwqogsdy/v45xtTmrTH2pnIT1BVXUVPtIeZ8gz3tN9DyanUB08X0uwb28fjfY9To9fwzeXf5Gz+LBLJcHaYp04/Vbl5JiFRTPDDMz/kd5b9Doa89OV0lVbFbbW3oWkarrtwU2wURVlY123Q/d3vfvcjn2NZFl//+tdVoK0oV1Ay3E913/3oI3uQwQbk6ZehthdHC0K0GSE++VBd5frji2h0r62jXHAQAlIzBVIzeXpvracRl1jAqAy5FJAq2Ph0jZrwwmbrLQud/53soLbza8QMgVUuEDg2QPnYUczVfbidnXia9oGvFUIwkB7gbOrshV6x6dw0vfFeUqUUhmawvn49G6MbGSoOcSJ9goPTB0FU5gsujy+nM9pJvVEPv3jdrUHBK+DTfGjeB29fUZTzPPBTSU4mL9W1/REMadCsN9MQbODV6Vc5OnP0wmNbmrdQrVcDECHCmuAakjLJ7vHd7+tJny3MknbTVGvVH7o9KaUKuBXlJnfdBt2KoiwMD0GqbhOxQgISQ8iu23CzCWR+Htl7r5rHfZOozOMGN18kOzJN0A9Ltzax37F5ZWCG7X11PHN4Ak1AXdjiS7e00Rk3gE831FQIgSzr5OddnLJXKVUWcD7WjZ6SC7O5EhOux9agDT/4Dun5BLbPpGbfboIPPYTYfOsHrkvTNIYyQ5i6yan5U9zScAs7x3dyNnWWKquKzmgnq6tWgwcJO1EJuN/9rDyXNybfoL+mnxOzJ7iz7U5WhVeheRpJmWTX2C6G08OErTDbmrfR5ev6VJ+Roigfjy51bq+/naXxpaTKKap91dSb9e8bkRLTYjSFmi5aJhDU+mvxaxdnJ1cURfkgKuhWFOUTs6VGrmkLvnwKOX0SDB/030cuvmShm6ZcAwKNocPz6OUCNadfolqYyGSWcmI1f300xNlEiVs6q/idu3uxXUlLlZ9ldSFiuvNxp05fUjGhMXxwjoG3p/FcSSjqY+PDHUTbPnqERcCAjpoQQ3NZqgdPkpyZBSBmWpRHR+CZZwivWokdfH8hO8/zaAw2VrKWl98h5ovxcNfDTOenWVK9hDsb76RWVOp9/2I70uU0BbtAsphk38w+3pl5h2+s/gbr4ut45twzzOQqGf7nC/P8+OyP+eW+X6bBaPh0H5SiKB+LLnWazWaazfMVDD7gMCKkYFvjNo7NHWMoPYShGzQGG7m37V5CIqRGdymK8pFU0K0oymUpGHHKSx/D6k0jNZOSpi48bhZeWZCeLdBuTJM7e47zZXMph+9gIpEgoBtsiUzSMfgcZnGOcNctdDdvIitjn2q7wtOZHylwYs/UhWW5dIkDPx1h2+OdCOvSwzeFEJiJBHe3+HnGdvCOzAEQDfqo9orgSeyJcbRCAT4g6JZSsiK+gsGhQe7vvJ/BzCCz+Vke7HiQVZFVmPK9yhdtwTaaQk1M5idxpIPjObSEW0gUE2TtLABH5o9QG6ylIdJAa7SVklNiKDlEzs4xlh+jIaqCbkVZTOpEHb+76nc5mz1LyS3RHGimyWpS5z1FUT4WFXQrinLZXCko6OcDKXXhcdMQJlhBE3KlyoLzuz48dJalje3cUp2maeCvcd0iTWFB+8ggEW8/vjVfZc5ovOzterYgM1d43/Jcqkwh5RK8RJlVo1TCee010kePUr12HV9pbiO/bimZ04fwFzOQq6zTbG9HRi+dXj0qojzS9QjjhXFWV6+mIdBASL7/ZlOtXsuXer7Ez0Z/Rs7NMVOYYUn1Et6ZfgcNjQ0NG9jUtIlDs4fIlrMgoCXUwvqW9ZjCxPqA0mbKx2MVi3D8BM7YKHpdPWLlCsqh0EI3S7lBhGSIVaFV7y1Qpz1FUT4mFXQriqIon4xw6VhRTf5kGqFrSNdDaAJv336+9g82wMQx8k6JJVUQzw8STpVg5i0sK0z1ks8zb7Vc3mYNCETeH5CaAR0zoPP+DGUV3tFjFFs6OLDyLvYPJ9GSsKmngw0PpMk88V0kYLa2Ev3CFyiZ5geu411+6afbf75EkHeJRE4S1kTX0LG0g5Sd4lzhHD84+QPu7bgXv+6nOdzMd45/h4OzBzE1k9W1q4n74rxy+hU86XFX210EjAAhM0RMi2F46lT9cZiOg/uzF7EHB6FcxhkcQgwM4Pvio5Q/YPSCoiiKolwr6kyuKIqifGLhBg0r2I0WepTCqy+jOUWK0k/XzCwNTRqFdJBI9iw+kUYrJCsvSg5hHv8B4VVfJat98qHmwnCp7QhT1xpmZrQyTNswNJZsasAKf3AeY13XscdGeXPN/fzBE4eQ52uZfeetEf7DF+9gq3TAkxg93Tjdl663+0lJKYmJGHFfnOaqZkJGiG8d/RZratcwnBnm0OwhwmYY13Op9lfzV0f/itpgLaPZUWYKM2xt2srA7ACNkUbubr6b5ZHlaFJlNv8w+ugo2V27KB49itA0EAL/qlUEBgdh+fKFbp6iKIpyE1NBt6IoivKJSSkxw8D6JcRXdCLyecJmhOPvpGgP1RMuDSGyw+AUKy9oWAGZCSgk8bWdIlt9y2VtM1jncctn20lMFLGLLtF6P5FGDXmJXm4pJYV7P8f3nj17IeAGsF2PJw9OsP2RR/HyWcri6tTPFkIwmB7k6NxRdKGTLqdBgCtdik6R+mA9U/kpXFyEEOhCZ64wx9tTb7O0ainH54/juR6h7pDKav5RpqcpnzyJZhogQToOpUOHkPfvWOiWKYqiKDc5ddtcURRF+VQcnw+7qgovbLB0ez3zsY2w5behth+sMLTdCvFOKKYQ/hhGeoSAm0JcRqArpcSIONT1GzSv9hFulJcMuKGSdbxgmMxkShc/IGA6U6TognuVAm4AB4fhzDBj2TGm89NIIdHQMISB4znoQkciMTUTT3r4DT8lr4SHh4ZG2SnjSIdTyVNol6ghroDuOLipNLJcxkul8VIpcF28chmZy6uLHUVRFGVBqfOQoiiKcsVIzUUGNCYb70Te/Uew/BHwPOTsAFJW8g5JBNae/0okdfKatKk1ZnHHkrpKlvV3/0Nwe38dllu8qtsWQpC38/TEeyg6RUbTo3h43NJ4CwEjQM7O0RfvozncTLacRUpJQ7CBnmgPZ5NnsQwLQxj4db/KkgzoGHgFE82zLrppo4+P4ybmMdvbEIEACIG0bXw9PdiOjZ5MLWCrFUVRlJudGl6uKIqiXBVT4WXU9j+AJgxw8lBMQVUX5fQMOCXEsR/hv/WfUhRXJ8lV3J3HnD+OTIZ4bM1a5nNlnjs6iSEED69p5o7+WlzXvirbfpfmaaypX8NQYoj+qn6Ozx/Hr/tZWbuS7S3bsYRFT6yHvngfu8d343gOS6uXMpQaImNnaI+2Y2KyJL7kpg+6SwmdY6+NM3U2QyBqsvK2Fmr7Lcx8Fnf/frKvvIq/rx+ZzyN0A2kYhO+5h+zQEJHNmxe6+YqiKMpNTAXdiqIoylUhpWS2aj3hdR34Zw9COYc9fQ6Zn6w8oZzDKM5D4MoG3YFyGd/oMcTwbsgeIBmLU2g+yOObN/DYliVIO8LSBguv8P7yY1fDuvp1lAolvrr0qxyeP4zruUTMCNlclnta7iEswrRVt3FX7V3kZZ650hxtoTbawm1U+6pZVb2KRrPx5g66ywb7nxtmdiSLBOw5lzefPMudX2wjfPB5nHODOKOjFPJ5fF3dCNNEi0ZwUkl8NbW4VVUAaJqGlPLm/iwVRVGUa04F3YqiKMpVI6UkY1QjjDhi4JWLH9QtXCtyRbcXHB0j+/d/Q/bEq8hCkvRv/CZPu3spHfoLmN2HjC/nkd5H8Ar1V3S7H8bSLfoCfWiaxrLIMiYLk+hCp96qx5CV07DneeCBHz8tRgstsRa2VW9DSonneTd9kJhLOMyP5y/KUK/jMntmlsDkJPkDBwhv20Z21y4K6TTScaj+ylcoZdIEb12FWyjAiRPYg4OYDQ0Yy1dgxz95Bn1FURRFuRwq6FYURVGuulJ1P/5YC6TG3lvYdw9FIw5XKKA0NI3cT36MffYUeiGJVlPPm/OHyGhZLMMH+TnKsTJ7pvbw2dbPgndFNvuxua6LiUmb1VZZ8BFv23UvnSDuZqObGkJIhJTI83O5hetg6KAFQ7iJBPkDBwht3IgWiyI0Ha2nB+ftvbj5PKVnn6U8OIih6UjbwZmaxr/tMxTr6hb4nSmKoig3AxV0K4qiKFddSQvBqq9gpc8hyjm8cBP5YOsV7cG1EgnSe/cicNHNAG5dHZP5KVwni2yJIXwRPOkxlZvCkQ6GOgUuSrrrok1PI4tFRH09nmkSnBmlc1mcM+9MgtAQhkEg5qc27qCX6gitX09+/36yr7+O2d5OYMN67PExvFwOw7LInToFqTRGUxOp730PAfgOHybwyCN4q1Z+1P0PRVEURflU1BWHoiiKck2UtCCl+Iqrtn7P78doaKR44ABmXwfa5BRty/s4XhxCaBpeuBkktEZaVcC9SBnFIqXnX6B85jQAwucjtmUL5cEh+pv7qLqniZlJm2itn6Z4AfP1pyhOTmI0NVH9ta+B9HClRBomhdFRQv1L8HI53HPnCCxbTvqll8B18a9ahdXUiL1rJ37HwVu+DMfnW+B3ryiKotyo1FWHoiiKckMo+f3EPv95SsePUxhO4m+tZ73Wy8ySetKWQ0kPEfVFubX+1o8c2q0skNOnLwTcABRLZJ7+MVgWpaeeIlZXR11XN2YqiDM7S37fPrxMBm/PHvxLl+JbuhT/+nXIQIDAmtWkXnmFkN+PLJbwCnlEuYxvxQrcVIrsT3+G1DTsM2fx3boJ/ZFHcHV94d67oiiKcsNSQbeiKIpyQ5BSUt60kfo//jeUT5xAaBqxpcv40ooexvPjADT6G/FJ1aO5GAkhsMfGLl4GlAcGCGy+tfJHqYRZXUV+5078a9Zg9VQylZeGhrAnJiiPjSICfoqDgwSWr8A7e47c5CTh7duRjoN0XczGRvJv7MbN5RE+C69YJPPss9SuXo3b378g711RFEW5samgW1EURblhuEBhxQrEypUA5KXEdKHD11F5wof0cBuAXi7jZbPIcBjHsq56e5X3SCnR6+vh6NH3lnkeelUcr1hCWD4CK1ZQPHoULRJBCLBHRhGmQXDNWsymJlLPPYcslbDPDeIODxO8404yr7yCWVWNm04TuX8HRmMjWjSGFo0hTBMBWLEY3sgIYomqh64oiqJceSroVhRFUW44Px84CSFIe2mKbpEqqwrDu/jUp3ke2okTlF5+GWdiEt/SpXiWiW/jJpzuLhWEXUN6Xx/GocM4c7MASNMk8sUvkn/jTQIrVlA4eABnZpaqX/kyuZ27MJqaMKIR3JkZ9HCY2Gc/SzmZAM/DTSbRwyFwXfInTxLs78e/fBnuzAxuMgGOi7AshN+Pl8mgaTr++XkKVVWI8xnS1b5XFEVRrgQVdCuKcl3SdA3k+frGH0AIQTx3BmNiP5QzePWrSNesxUbN2byZeHi8k3yHvZN7oJggrvt4sP1eWgOt5Kx6pJRoJ0+S+9GTlE8NgITy6Cjhu+8i+9yzhB9/HDsaXei3cdOww2ECv/wlGB1FSIkeDEIggIWAVArvrT34enspnjiJFomAY5PbtRsJFE+cILBxI1ZnB6FNm7BnptFCIdB1vFQKT9coj4xQmpomfNvtZF99FXduDquri+A9d1M8fRqjkMdctgz79BlEKIjZ349dW7vQH4uiKIpynVNBt6Io1xVb2AxkBzg0ewi/7mdd3To6/Z3vGzZclR1Af/EPoZgEQON7xDd/g9mOh1Xv1U1kpDTC7rHdxL0yYc2g2XWZG9tNR80K4tE8aX8HxXf2IQuFi75DxYOHsDasR05Pgwq6ryknEMBsbKL00kuUzp4BTSOwajXB22/DPnIYvbYWd3IKq7WV5He/C56HCAaRxSKlY8fQI2GKhw4RuvNOXF0n8tCDlRX7fJRPncLLZSmMjBJYuxbNssCycLNZrKoqnNFRyseO4WkaAGLfPiKPPYZTX7+An4iiKIpyvdMWugGKoigflxCCg8mDPD/8PFP5KYbTwzx15imGS8MXPU/TNPThXRcC7gsO/i0hJ3HtGqwsuJnCDF1VHRR1SVkTfKZlK1tEkODgLnyTbxPxkiAlGL8wAuLdGzN+/zVv881OCIH9xm5KZ05X9oPrUjiwn/LQEP5Nm3AmJ/GvWI5XKICUCJ8PYRjo1dXYExN42SzO/DzFI4exOjtxJRCOYG3ahN7egQgEkJ5Hfs8eMj/7GfboKKUTJzBbWigePow8P7QcQJbL2MePXxhuriiKoiiXQ/V0K4py3Zj1Znny3JNMF6bx634aQg2EtBCH5w7T2dJ5Yai5rglEbub9ObNKWTQ7B3r8WjddWSABX4Dnjz9HLfCVjoepOvMalLPguYjBnQRmThK961eYn5xECwbx8nkA/GtW44XCyMbGhX0DNyGjUCBz6tT7lhePHCW8aRP2uXNY/f0YDQ0UDx/GTaUwamtxZmcridF8fkQgQHlqGkIhzC/9EgBlz8O/dQvliXHM5mZkLof0+fD192OVyxQOH0GPV+H+QoDtZTLoKuhWFEVRPgUVdCuKcl0o62Uy5QzbW7fz5vibjOXGGEwN0hvvxfbsi3qibMfFa1qDOPvKxStpWEEp0KhqNN9EEsUECI0mfzVtUqCfewXS40gEwheBZQ8TCiYpPXA/pTffRKZS+JcuRe/vx2ttxTHUafJak4aBFgjilkoXLdfjMZxsBl9vL5mXXsaqrsa/di35N97AKxaRhTyR+x+gcOoUUtcxG+rBNC/K+1BubCTyla8g9+/Ht24tRiRK4dAh7KFBzL5+zCX9uNPTF23X6u3FvUTuCEX5RUII5t15xvKV8ndtoTZiIrbArVIUZaGpqwlFURa9gl7g5amX+cm5n+B5Httbt7OqfhXPnn2WnJ1jZfVKXNe96DX5ps2EVozAiR+DW4a6Jdgb/iElqRKp3SyEEHieR1e0m95wI8b0SUiPv/eEUhrGDqB134u3aj2+5csRUuIaBq6a979gHMMguHUrmWd+8t5CXce3fj3FvXuxIlECfX0U3t6LPTGJf80ajNpaNL+fzMsvIw0ds7WV4Ge24oRC71u/HYthdnWR37evskAT0NWFq2uEd+zAe+UVyiMjCMsisGEDsqfnGr1z5UYwVh7jR2d+hCc8glaQPdN7+GzHZ6nXVV4ARbmZqaBbUZRFb/fsbv7rgf+KK110ofM3x/+Gryz/CitqV7ChfgPdge73vSavRSmv+jrhnh3gFiiGOyhKVXf5ZiKlpCvSxf6p/bieh8zNIISGkJIL4yLys0h/DCkl7vnkWaiAe8G5S/qJBvzYZ84gTBOjvx+7sZGQbeMcPEj6J8+A5+JMTePMzeHr6kJ6HsEtW9BaWrDnZtGXLMG+xJx8t7WV4ObN5N96CzwPze8n/MCDlGtrCd9+OwwN40xNIVNpjKkpSq2t1/gTUK5LGuyZ2kM8FEcKyWBqkJpADecK56iP1KtRVopyE1NBt6Ioi5owBS8Nv1T5NwJXuggErwy/wr+45V/QqDeiXSInpONJkv7zF8vqYuem1OZrY0fnDo5O7iRb0020cRVi9jSUc+CPQc89FEbTGF0lHJ9voZurnCeFwO7oQHR2AmBLWbkZks+TfeVVyoODRO6+m/KZs6BpOIkEen8/5soVyHhVJeFaVfySN1A8XUds3Up02TLI5aC6GjcYRBw4SGHvXlJPPw2AZlnoLc3U/F//FzQ1XaN3r1yvbGnj4DBVmOL1sdcRCHRN5+2pt6nbWEe38f4bxIqi3BxU0K0oyqLm4WFolUOVJjQkslJbWdOo8lURdsML3EJlUZOwNLiU/r5ejNRRmB8DI4yULtIM41TdysxP9xK+vxZ61TDixebny/sJIZC5HKXBQcy2NoqnThF58EHKIyOYTU34H30Et7v7QrmvjxqxIAG7qgqqqgAwp6chmSDx/PMXnuOVyzA7h33oMGzYcMXfn3JjsbBojjTzk6GfEDACrKhZQX2oHlOYDCQH6KrvQngqKZ+i3IxU0K0oyqKmORr3ddxHwAiAAA2N2cIst7feTq1Xi1Rd2DecgGbjz47gaiZ5fwvOFahuqbkGXrATu/VB7KNvovn92E6Y+eeOIV0PL5+7Ai1XriYpJaKmBqu9ndK5c+iRCIVjx9DjMUIPPkCxt/fTrT+dQXgesly++AHPw82kP9W6lZuDlJLGUCO6pnNPxz1M5idJl9K40qU+WM+MnKGeehw0EgUPnymImRffXFIU5cakgm5FURY1KSVNgSZydo7B9CCudNnUuIkt9VvUhcoNRsehOn0C/a3/jhzfD/4o/r77yaz+dQr6p8/+m9NilKuXkT+7F8/O48nse9uuq0Plp178ys3NxB97jLm/+AucqSmEYRDavh23r+9Tr1tUxXFOn8LX00PpzJn3lus6Vn//p16/cnPo9HVyV9tdJIoJxjJjHJ8/DsDu8d18Y803WB++jycPTDKTLWJoglu7atjSHkYX6gikKDcyFXQrirKoOcLhtZHXqDVrqaqtQiAQjmA4NUx1tHqhm6dcQZHsObRDf4scfauyID+HOP4koXgHxe5HrshNFicaJfjA/WSffx6KxUrQtm07jpqve11wfT7YtJG6zk68iXFEVRV2Vxf2FVi3U1ODVt9A9NFHyfzkxxSPHceoryf22C/jrVhxBbag3Ax0V2dT4yZ+cu4nnJg/AUDIDLGydiVnU2ep0oZIll1Ax/Eku87M0hC16KtSl+SKciNTv3BFURa1nJdjvjRPwSmAgKAeBAnjuXHWx9dfVINXuX4ZGhiZURjde/EDTgFtdA9G7yPY7ge/9pOQUuL09hJuboZkEkIhnFhMjZq4jri6Tr6pEZoar+h6JeCtX4c2N0e8uwth28h4nFJ1tfp+KJ9InVWHLnQ0TcOv+9neup3XRl/j2NwxziXHWd6yHvJ9jE0F0NAZmivQXx1V3zNFuYGpoFtRlEXNEx6JUoKJ3AQAfsNPR6SDplCTCrhvIALQ/DFY9SVIjcDo25CfqzwYacS9grtaSokdCEAg8O6CK7dy5bomAbum5uKec89DCJX8Svn4qqlmRc0Knjn3DKsbV/PKyCs4nkPMipG3c+yafInbmjWa6WZyKkI0YKqAW1FucCroVhRl0RJCsGdiD5saN/H84PMU3SJFp4hlWPRH1RzLG4EQgoAoEU6dROz+f9Ey42D4kF23IYfeAClxeu7DUxekiqJcJzzPY1PNJr7U/yWKThFTM4mYEZrDzYxnJ8jaOVyRpKOxgJOrp68ugKprqSg3NhV0K4qyaJVFGUc4zBfmeajnIQAKdgG/5ieoBVGZr65vAa9AdHo32uheKCSRffcgszOI408iRvcit3wDJ95NIrxE9UYrinJdCXth7mu5j5H8CIPpQTRN49jsMWzPRgLThWmOzR/n/978x4Q8dXxTlBudCroVRVm0BvODvDzyMkW3iO3aaELjgc4HKnPlpKbKhV0FmqYhhMB1r8AE6g8hhCA69zbamZcgOQJzpxAT+2HFF/HiHchCAseqYj7Uv3gDbgFpmUZHJyzCaniooigXaTPbqIpVkWpN8dzwc5S9MhJJZ7STdDnFeG6UofxJlvuXL3RTFUW5ylTQrSjKouQKl9fGXyNgBsg6WXRdx6f7GMwM8rW+r6kA5woTQmCOjVE6eBA3mcK3fBksXVrJFn0F6bgE8uP4NRdt+jhMHgEzAL13w7nX4OSziFVfwjvwHaT/05cJu1pSIsWxZKXXyvVcglqQ9dXrMaW50E1TFGWRkFISIsS99fcSsAK8OfEmPt2H67kcnz9OwAiQc3NITSI8lTdAUW5kKuhWFGVRKlDANEyivihRX5SIFeHU/CniVpwao+aq98TebOyxKYa//fc4ZYeQTyc8MUFwfh5x111X7AaH6RUJnn4a5gcx4rVw5kXIz4DQoZSB3nvg+FPgi0Lv3eQiPVdku1fanDfHT8d/yrH5YxyfP05doI4dHTsYLAzS5//09aIVRbmx6FKnM9zJX8//NUErSN7Jkyqn6Ih2MJYdI2pEWeJbstDNVBTlKlJBt6Ioi9JgfpBd47uYK8zh4aELnR0dO+iOdauA+wqbLwmm3jhAciZzYVl7TQjt8BEiGzZgR6NXZDuB1CmYPIJR3w+nfgKpMSgkKg/mZ6F1A7RvRUabyLfeRplF2Gss4OD8QVxcYv4YW5u3krNzvDjyImEzzNLQUvX9VBTlfVrMFv7hmn/Inok97Jvex6raVZiayf868r/4fM/naelpIeyGF7qZiqJcJSroVhRl0dENnben3ybqi2LoBqZmUnJKTOWneLD9wYVu3g1FCMGJ6TzRUhkAQxM0+wpE0pP4SpJIZpBMbBWu0IFKVl5TuFjFWaRmULRq+Dg5gIQQiPQYaAZGdRsiOwVCQLAWiknwHHBt5OpfIVW9hqK3OE9PRYq4mssTA09Q9sq40qUp1MSymmXMFGcWunmKoixS44VxJtITIKE+WM+xuWNkyhk86fHG+BtsbtzMqsAqlcRcUW5Qi/OqRlGUm1JZlDmZOYktbA7PHWYgMXDhsaZQExoaMSOmLkquICEEM5kSvrZOeGcfbb480dQJ9HIGs78Pc/+fUCMfo5xL4aGhNa7AHT8IMwMgdKzWdeQ77qWs+T90O1JKCNZh1HbB8B6oWwbnXgHdhEAVeB7ULydfs3JRBtxpmeZ05jSmabJrbFcl2Zys9GhP5CZYXbuaolOkJEsY6tSqKMovKLpFssUsUkiOzh1FFzoeHhJJxIqwd2ovDW0N1Gv1C91URVGuAm2hG6Bcey4aQ2mPfRMljs97zJU1EOqroCwsIQR7Zvewf2Y/OSdHU7gJn+7D0CoBzERugtX1qwmjht9dSZ7n0V0b4h0Ro+7+e4n6y+jYBFatJrYiilaYQez+/2FmRmH6KPqr/x4Tp/Ji6SJH3iYwd+Rjbatcs6xSh3v2JDQshyUPQKgeos3INV+mXN1PWkSu4ru9PFmZ5YmzT/D66OucTZ4lZ+eoCdSgCQ1NaBiaQd7JUxWoYt6ZX+jmKoqyCNX760kWk2xq2ERntBNNaASNID3xHrY0b6El1MJQfgipq7vKinIjUrfjb2BCCKaKGqdmi+iaRm3IIm87TKRz2I5kPmeTKmTorAlSHzZYVu8jaqiDvbIwMjLDcGaYrJvl6PxRUsUUXbEuzqbOoms6q2pW0RZqU1nLr4KltRYTJ4vsSXp87Y5ejHmdQOEMZjIDxQQYfvAcdM+GYgoxeRAR6UTm5wAQ00fRG2/9yLnM0rAQxWSlRJgvBMKE2j6k6yDNEKXqxZlIaCg3RKZUme9eckpYmkVdoI6wGSZdTqMLnf54P2+OvkmtVUtNVQ261Be41YqiLCZVehWf7/s8L4y8wANdD3B87jhCCJbXLMf1XIpekdOp08yV5lhfu556qXq8FeVGooLuG9jhWY8/fXGAqXSJQtmltz7EQ6uaKTkuh8ZSdNaEsF2Pgeks0UAVYxmHWLX6SigLw5MeQSvIK+OvsKN7B2eSZxAINjRsIG7FOZc8R8xavCWkrmfBxCy3n3qdVFsvwXgt1pG/QJSLyPpWhOdC0xrITePpITTdBLsA+s8dK4I1eJ73kdsx0+cg3g5zp5BzZ0EKaFiKbFlOOZdGSw5BdfzqvdHLVHSLF/49lZ1iU+Mm3hzfTa6UoVDO0Vvdz1BqiPUN6zk4eZCuUBfNZvNVbZMQAk3TkZ7Ekypxm6IsdlJKTEyaQk1M56YxNZOaQA2mMCm5Jf78yJ8jpcTQDDY0bOD3V/8+EW/xjfxRFOXyqAjrBlWUBn/39jnGkwU8CWXX48Rklu66NBG/SXdtmO+8NUS+7CGB545M8u8fXUXR0/Fr6gJOufaiWhS/4Wdzy2bGsmP4dT8RK0JPvId3pt5hW9s2qswqNZ/7aigU8JJJIsm3KQVX4t/2TeTRZ6AwDf07kIDnuHjoEG2G+hXIzGzltbqF3bThI0cgaELgnz0GuRmEP4qYHoVII9ItI+OdeNMvI0rpq/9eL0NjoPHCvz3pMT52koeDmwi0NTBXnKVsl3FNjalcAtuzyTt5rkbidSEEmjTxihozQznGT80iNEHrshjxdguhq2O3oixmQggydobj88dpCDXw/ODz1Afr8ek+bm28lTcn3kQieWfqHY4kj7AlumWhm6woyhWigu4b1GzBZSRRQBOCgu2iCYEnJXPZMm3xAG+cmydX9hDnn58ruzx/dJLu2zvxoy7clAUgYWXtSl499CoDiQEKToGgGeRE4gS/t+H32D+xnwCBhW7ldSGqFwlkhpG6QS7UTs75iEN9bS1aOEzrFzZijL4Ek2egaw2y63ZcIwCJczi5FIblR1bfhxvtgKnjYPhwapaQ8zV8ZJv85Vk49QLkZiAYR3ZuBySyphdG9yJCNbjhpivzAVxhzb5m7my7k93juyk7ReqLFuvOFkg6h3gl9RKe56LH4xgrV6KbPur8dVe8DZowSA45TJyeQdc1ho7N4bmS7HyJ1EyBJVvqqF/iU9MvFGURC5kh0uU09aF6Xh97HUc6dMe6MXSDjkgHlm7x1uRbSCmZK84hYkL9phXlBqGC7htU3KfTEPUxnS6hawLXk3gehHwGLdVBZg5NAO91GoZ9BudmcqQKLjUqT5WyQMpOmXQ5TckrIYQga2fxpMebY2+yvXU7plyEdZsXkaCbIjp3ELHv2zA7AHX9RJZ9lmD9Gmb8nZd8ne330/zVhzFe+yMYfQucEiAQp3+K2PH/Jdd+N76j30EfP4o89QJmXR9e7w4KVf3ktI835F/Pz+KZEQxtHjl+ACE9cG3Eyije6DsYn/k9MpFLt3EhCSlYE11Db7QXO58i9uYxMs/+LdFQkHvvv4dXJndSzuXpDDTT1rKMVDlFwB/AktYVa0N2wuWNH5wmXB1A0wTpmSLBmIUVNJgfzzJ23KK2uxFhqJumirJYhQixtHop3z/9fRzPoTXSSnO4mWfPPcub42/SE+/hrva72De1j4ZgAw4OOio/hKLcCFTQfYMK6w6PbWhlZG6AdMklW3Jorw7Q1xBm99lZ7lhSx9/sGUZKCPl0asMW3XVhIpYGqqdbWSCGZlBwCjQEGzA1E096ZMtZJLIytFy5pEh+CP/sYcSr/x4K86AZMH4AkZnA2PxNrM5eyo5zydebiWMwfwacd+cvS8jOoE0fxzd7FjF/BjkzgOaVYG4A3SkTDFRj9D5IOtp/yVH/PjeHL3Ua084g3BL4omCFkdJD6AZeuB6vdgl2qBF3EZ+SpJQECWJYPrz8fvA8ZCZL148P0bx2A9mtK3kxf5SzQ9MgIeaL8UjPI1SJT/+91TSNmeEsngeeKxGiMkYpnyoTqw+QmnZwHQmqR0xRFjcPlseXszO4k9PJ06ysXcnzg88TNIMUnALzxXnemniLL/Z9kZJb4u/O/R33td1HnX7lR88oinJtLd4rHOVT29Cg8x8eXcGp2TwSQcgyODmZpqc2TF9dmLlsmSPjKfJll3jQ5P6VDdT6HDVnVlkwYSNMb7yXAzMHKDgFLM2iJ95DY6iRWqMWLh0z3tRM4aKdegHNZ0AxVVnoOaBbkBhEZqcIl8aY1z94GLiuCYRTBNf+hUc8MP2IieOIQgJNOpXe6VAN5GfAzqGPvUXQF/vAIeY+L4//6N9CchQ3WIUZroPEOTzj/DSB+mU4jsQzo9jB6yNTr6Pr+NetRX/xRdz5eWShQPDcFHv7IBfJgxlGcxzSM6d5c+67PCBXU964EfTL762SUiKlxHE8XNsjXh9k6tx789/9IYOmvjiaJVXcrSiLXLWs5tHeR5krzOFJD9uz0VyNvngf7dF2/EYln8nzQ8/THe7mmaFneLzncQypLtkV5XqmfsE3uPaQR3vIT0nqPHFojkTe5uWTM3gSvrqlnftWNGA7Hi1xP+1hCZ4LQnz0ihXlKsh7eXpiPbjSZTg9TGuklZZwC22RNnRHDbG7FMPJQ2YSAp2V3++7gZfngNDB9GMbkUveUNOkgwxUIaq7ITf93gPBGqQviheqQU8Pgy+C8Gwo5yHcgNawEk9Y6Jlx+KCgO3UOkqMAyHwCO9KIuWQlmq7hei5udh4vM41c+ShFs/q66aktNjdT/c9+m8wPf4ibziBXLmEiNIwMhhBS4o4M42ayDIWK5LxqxBPDGA89iB0KXdb2pJTUdYTRBTiOR3q2QO+GelKzeYQQLNvaRNOyEFL+4k0TRVEWoyXWEn5jxW9wPHmcuC9OS7iF5nAzO8d2kiql2N66neZwM2FfmPHUOAk7QZ2hersV5Xqmgu6bhE+41EZ8vHhyhpLt4jd1nnh7lM+ubuSzSyJIqXq4lYU3V5rj7wb+jpgZoz5Uz3B6mNPJ03REOxBBlVDmUmwjhBVpxNGDWNXdlfncUBli3rgaapaQkcFLvt7BoOR4+Df8A6jqgJE9EG2Ftlux69fiRLrQU8OI6QmEGYBSGunZiL1/jrHxH2Nbl0gEUc5c+KcI1WDqGiJ5Dtwymmsj6pdjL3mAtNV03e3bYmcngX/6TxHJJIRC1KdeJp04jcjnKaaTWMEQd9VtwTw6j1tyMAZOIdauQV7mTc1Is+Azv9zHiTcmKRccQlUWS7Y2YAZ09ICDpwJuRbluSClZ5ltGTWMNb0++TWu4lafOPgVAQ7CBI7NHaAw20tPWw5SYwtKvXH4IRVEWhgq6bxJC6BTLDrf11eJ6ksHZHJqQDM5kKPVGsbTr64JXuTEV3SK2azPpTDJZmLyw3NKs6y4ou5YcqeH17cA59PdoG34TY+oQJIaQ7bciWzaRqF79oUPzpZQUa9fAuRfwdd4OffcDkkLNclLE0Pwt6Bv/Efq5l5DpUXAdGNxZ6Uk/8NdoD/6/H7zecGOlQoLQMP0htOwkYvQtpNARmoYY3oV57lViG/8JmUgv7nWWMMgxTair9D6t9a1lIDmA7ebJ1gZ4ILgB97mXOZfNU28H8E1MEA4Fcfr7L2tbnucR6xBs7ejAdUCzHDzPBmw89dNQlOtSvaznm6u+yZ6ZPTSHmzGFSdEtUnAKeNIjZ+dY17COuBZX50BFuc6poPsmcTbt8eLJWU5MpPGbOvcsr8evSQxNYGhqOLmyOJiayYraFRydPYojHQSC1nArNf6ahW7aopcJthPY+I/wMmNQuxo31kHB1SoXah9jLnzBiGL3P0K5MAUSysEGbFkJgj0JxUAzuu5HH9uPcMuVgTG6D/wxZGYK/O3vW2c+1Ea47x707DRa8hQCWanTHW5AJodBaAh5EmN4F6EWh3R8xZX9UK6RkfIIzw89z+aWLZQa8szPjVH/ygiTU4M0+Wspeza+XJbSCz/F392NbVz+qdelDAZ43sXLdU3HtTU008PzVDJMRbletGgt9IR66I/1k3NyeNJDE5UpOCtqV9Dt71YBt6LcAFTQfRMoegZ/9uopiraLEIKi7fLjgxM8fms7mzsiaCpbubJItAXaaIu00RBsYDY/S1Wgilp/Lc2BZjX94WMo6DGIny/h5cAn/dAcqeP4myt//MJLi0aUYFU3HqISbOs+QEMGapG6/wPX56JTbr6V2NgriISDjLVC/TKYOoqQLlKc79mWHtrwm+jVq3B/MZpc5MqizAtDL9AQaeCtqXfI2RkKxRQdqQKN/jr0kUlymoZlxXHTGUInT+KsXHlFL6JL8xqn9s6QmspR3RKm55ZarJg6rivK9aIz1EmVUUWAwIVlK+tWsiSwhLRMM1YcI6gHafW1onnaArZUUZTLpYLum8BoxmE0UcDQBJ01QXJlFykh6DPoqzZR0YyyWDRoDexo28FPBn9CwAwQNsLc3nI7NVL1dC80KSW5xluJLPssnHsVNAsZqsWJdlCOdX3ga/wUiR77G9j1X0AIRN89kJsDK4TMz4EvgPTF8DQDvOtzTnLKThHzx9g5vpN0yaGnuplD2UGKKzZTP3gAW9PwSR1RtvGt6Cbx99+lqraOYsOVydbu5g32PHWWUr4ynCF/MkFiMs+WX+pE+K7Pz/RqEEJgZHMIn4VnWTjX2c0d5cYWEzG+1PsljiePkygl6I500xvu5XTpNP/76P9mMjeJJjS2t27n0Y5HCcnLS8qoKMrCUUH3TSBoCSxDo+x4pAtldE2gCYj5dDQVcCuLiJSSfqufnqU9lCjhx6/u6i8iReFHrvga/uZbEYlzyHAD5doVFPX3J1ITQhBOnETs/xugsm/FuV2w/LNQSML4AWT9CmTLLbjTZ5ArvnDd9XIDBPQAuq6TLCXRhEXA8JMpp9lTn2HJmtX4X3kDLZvH19+JtB3kxDhybBTR2HCht1sDNMfBNc0Ly4QQGJks6BpOMHjJnvHUZPFCwP2uXKpEerpErE39doQQBFIp5PAwXr5A9tVXEZZJ4NZbIRbDKxbRWltx6uvVEF5lQVVr1Wyr2YYQAs/zKGklvjvwXabyU4StMAg4njjO4fhhNkc3L3RzFUX5hFTQfRNoCQkeWtXMD/dXSve4nqQu4mNVcxi4/i5ylRuf7ukEuXS2bWXhlLQApZp1iNr1Hxqk6AJEfhZZziE0HTwHaefg8Pfgrv8Hb9nnsadPI7NzsOxhctXX53zuiBahO9ZNwAgwVZjmjYk93NtxLwenD5Fd9wUacg6GLbGPnaB0/DjWsmW48/NonocrBNbkJIU338SdmcHq7MLceAuYJuXXXiN98iTCNAlu2IB2yy24HzAXXFwqG/pNXvpRkxLf8DByYoLkk09RHhxEr60l/stfIn/4MMn/+b8IbNyIjcR77TWiX/gCdkfHQjdbuclJKS8cV+ecOc4kzxDxRagN1OIzfMwX5jmePE53pJt6cWVGyyiKcm2ooPsmID2Pzy2voqMmwMBUluqQxfrWME0BFXArinJ5PqpX0JPgCgOteR2M7wMEyErdcGmFmavfgl53K1KICwnbrkdSSlaEV7C+YT3PDT2HjiBkhnmw+0EiXheafpbcq6+glWz8q1fjX7Mad34eoeuY8wnSTzyBLJcBKBw+hJfN4GtsQqbTCNNElkrkdu8mEo3C8uXv236syY8/bFLMvjeUPFrjJ1Zv8rEy6N0gNM9Dn55GZnNo1dWIkydxiwWyL/yUwpEjWD09BJcuIfW9JzAbG/EvW4qbTmP19oDr4h46jOl5yKYmHP8H5yhQlGspYkSo8dcQC8SYyE1wNnUWiWSmOMNkbpLfXfm7BNzAR69IUZRFQQXdNwm/5nJrk8nm5urzF8tqGJ2iKFePJyV2rBN9xaNoAOP7Eb4YcsM/INW8DVdquGg3xKHIkAaf6/gctmcT8UV45twzaGhM6ke5tTDD+l/7FfyOIH/gINkXfkr0kS+gpVK4oyMXAm4Ao6YGU0L67/8OCQRWrcKLxylPTVE6egxr1Spc9+IEaZrf5tbPdTJ4cI7EZIHalhDtq6vAunkCbt1xcF99ldzBgwAE6+qhkKc0OIgzNkbs/h0Iv5/kd/4OpETmcqBrmL29+BoaSH7ve3iZLMaJE2g1NYQe+QJ2VdUCvyvlZheVUR7tf5Q9U3s4O34WT3pYhoUhDA7MHOBg6iCbY5tRuXAV5fqggu6bjJqzpijKtZINdeJpFtbGRgxZwgtUkwr347jX71WioVWOoY538fDtKqq4ve12/vzwnzNXmMP2bEq+ImtW3kJuao7C0y8iNQ0nFCX55gEC1c1UxX9uCoWmYZoWmRdfROZyeED29Z2Et29HWBYidOl53VbcZfldtUhXA83FvYlKhhmuizE4iDc5hb+qGqdYwJmcJPfyy/iXLcMeHyfz8ivEHnrwQp01KT3cuSR6p0vp8BHcZAo9HkfqGm4ygf3OO4h771XnS2VBSSnZHNtM3s1zZO4IAoHruQymB4n6orw9+TZBI8hq/+qFbqqiKB+DCroVRVGUq0JKSc7fRM7f9N7C6zTg1oRHeP4Y2vAucG1k60bydeuwhQVU3mtMj5EsJgkYAfz4sd0yB1sc+o9NEWtuJmUEGHMMRsYzhJ95habHf5UO049uFzGjMYr79uGl0xj1dcjpGaSuUzh8CN+WLfjWrMH+kERzjnu+Z/smmDUkhMB0XbSxcbzRUQr73iHzsxfxr15N+LbbSD/3HNLzkLaNXlWFdF3Ko2Po1dV4xSLSdvByOayGBkpnzqAFAuiNDRc+Ont4GP/5OfeKspCkJ1keXY4pTIYyQ9iejU/3EffFyTgZdk/spq+7j4BUw8wVZbG77KD71KlT9PX1Xcm2KIqiKMqiFE6eRBz+3nuj4U88Q9C1STdvv9AjWq/Xs7ZuLa+NvoZEommClJOhaOnIaA1vz5SILOmnOl5FfW2UYl0jU4/9Ji3jZ+D1F9EjEWSphJPJoldVARK9tpbg7bdTamy8au/NymSQZ88hANHeRukaDa0WQmAkknjTUwifD5qbcUwTc24OpqYQmoZobUXqOrJQgFgMfXQUOT5BefAc9tAweiiE57pE7ryD4qHDpP7+7whu2YIeDGIPDWE2NiJdF6OmBr2xAS1fwJ6cRI9GMdvb8HI5vFQSsjmoskCA0dyMp2mgerqVRaBRb+S31v4Wf3Xsr5jOTxMxI/RU9bB7bDe3NNzCVGmKTqtzoZupKMpHuOyg+1/9q39FY2Mj27dvZ/v27TQ0NFzJdimKcgUJIdB0A09KpHvzzPVUlCtB13W0kTffP/18+A3Mxlsoi0riLelKHul8hGQhyZn0GTQ06qpa6bx9HUNPvoZ53128MJRhaUMrE11d/O2PjzOfL7OuNcY3v/xbLN/3EsnvfAcAp1zG6uoi+LnPXd2Ae2aGwne/i6bp2FNT6MEg4YceorhyxVUfXm2cPUfm6aeQTuWYZHV0EFi2jMzTT+MMDSMCAUKrVlEaHcXz+zEcB7O5ifRPniGwZg3+vl5STz+N1dGJVleLl8ngpFJIx8W3fDlaQwNeKoleU4vR3o5fSopHjmC1tRK67XbcVBrh9+Hl8rjpNKamQUsz1i0bsVXArSwSUkqWBZbxmebPcHTuKMlSkpeHX6bKX0VXrIuCXQBroVupKMpHueyg+7d/+7d5/fXX+f73v8/3vvc9+vv72b59O1u3biUcfn/NVkVRFkbK1nhrOMuZ2TyxoMXq5ghLqwSaUBeVytUlhEAvFhHlMl4ohKtdx3Wj5QeM25byfSW7mvQmfn/17zNSGMEQBm2BNhrj9YyF2nnhyQOYukHrqiX8++cGAPAbOgeGE/zHos2fblpB1a98mdwbb4LnEr7nbrwVV6+UmhACe9duNE+Sfv7ZC8uLJ05Q+0d/SKGt7apt2yiXyb34swsBN1QykGd/8EOc8XG8fJ7wypUkf/ADzJYWjJpqCidOUq6KE1ixAhybxN9+By0apXTiBPm30kTvv5/sa6+hBYM4U1P4V6ygPDpCYP16pGmixaIE77wD4bpowSCYJpq/mcj99yPTKYyWVswtm8lXV1+1960ol0N3dbY3bGciO8FEboLPNH+GZdXL0IVOwBfAEx6avI6Pr4pyE7jsoHvbtm1s27aNdDrN7t272blzJ9/61rf4y7/8S9asWcNtt93GLbfcgvEBdUUVRbk2skWHl08nOTtX5I0zc8zmSqxsjvIPtnayrk7NV1SuHgFoR46Qe/11vHweq60N/913Y1+HAY3runitmxCJ4YuWi7aNlV7uX+gV9Xk+en29led4As3nYzJSi+hbSmtNkOPTOXLlytx2Uxf4fSYnJzOcoYmVJ0+iL1sKjgMrVuDqV6+cmuZ5uMUCub17L1rupVKU39mH1tGB9yHzyD8NkcvhptMXL9M03OnpSkZ3IfAKBYSUyEIBL5kC28admsZ32+0kzpdaM5ubcQp5kJLyxAT+lSvxHAdRU41/y2YYaUWEghjhMI7ngeth1tdTPHyI/Dv7kPk8/v5+PNsm9fSPiYyO4Lv/Acod7VflfSvK5aqSVTzW9Rhn6s9wOnWaneM7KdgFXhx+kR0dO7i7/m40TwXeirJYfeqIOBqNcv/993P//fczOTnJzp072blzJ//pP/0ngsEgmzdv5vbbb2fp0qVXor2KonwCg3NZxtNlfrB/jIhf57a+WoKWwdGJNP0NTYS8/EI3UblBGSMjpJ9//sLf5ZERvJ/8hMCv/irO+UBSCIG0NRAgDG9RZ4vOxZcTXvEFxODOSiK1to3kGjd97DbbrodpCKayJbrr3h0NJnFdcIQk6DcIGZLS6dOElyzFWL4Mp6rqqs4r9jQNq7kZL5dDj0TQ/H7wPEQ4hJPPYVzFRGIyFEKPRi8KvD3XxWioxzlzFqREC/grU2MsCzQN4fPhZrOIYKCSiVx6ICVmUxNaJIpRXQUSjPo6rNWrKS1dimWa5N98E8PzKLz9DkZdHXY0QvrHP0ELBPAKBbxsFv/qVei1teR2v4Goq8MMBrDr6q7a+1eUyxEXcZr9zTx19ilm87MXSi5+7+T3aI+0s8S3ZGEbqCjKJV3RbmjLsvD5fJimCVQuqN5++21eeukluru7+eY3v0lra+uV3KSyCL073HIxX0DfLGzXI1N0CFk6O5Y38tLJaeayZUxdIIFHVtQQ1tUcb+XK884NIpJJ8CQiGMTz+3FmZhDz81BXB67G5Ok8U+fSIKCpO0pddxD0xZl+2xU6qZp1mLWrEVJiC/MTHeNaYz6a4wH2nEuwtq2KxoiPqUwJSeV3+vitHXQffxvWrce8+y7KhnEh4NalRNg2rs/3vm0KIRBCXFaPtJQSfeVKwrfdRm7XLuyZGTB09EIMX2vbh2ZL/7QcyyJ0991knn76whBzT9MIf+lLuH/5bdz5eYRh4FuxAjeZBNdFj8Xwr11Lbv8BQlu3Uh4aAl1HBILI6Rn0eBW5t99GSyWRkQihvn5S33sCvboKEJTPniW4bi25nbtACHDdSu/67CzO5BRmezulM2cAgTcxUfmeKsoikygnmMnP8PNJJjw8zqTOsKxx2VUbnaIoyqfzqYPuQqHAm2++yc6dOzl27BhCCNauXcsv/dIvsWHDBjRN46233uLb3/42f/Znf8a/+3f/7kq0W1mEJILBlMvxySy6Bssaw7RHdZUBdgG1xIM0RP3c0lnFqwMzzGTKAHgSfnxwgtZYgDs7VAYW5fJpQmDIEq5m4p6vXW0mk9ijI9jDI5UnCYHV2YkXi4JhIIRgZrDI+KnkhfWMnkyiWzrVHeYCvIuPz5bnh3t/wuNaU0hjfVsEhOAH74zx69s6mUwVmcuVWdEUYbuYp/z6YaKf+xxlw0B3XbTpacT0NM7sHIVzZzHb2rA2b8aOxQDwz83hHD2Gl0zi6+zEWdKP6/N9onYVqqsJ7bgPN5mgeOw4WjBAYPNmCuNj+NMZ7MjVy9HidHcT+epX8aamEf5K9vKyZRH9/X+OGBpCTk2j+QO4mQy4DnpNLVZfL87oGGZbG/b0NPm9e9F8PkJ33UV5ahICfoRhYJ85g7t/P6XjxzHq67FqatBCQfAkeiBQuaGg65Uec01D+P3IQp7A8uU4Z89iBPxYgLd0KY6ljpHK4hGzYni/kGNCIDCFiVS5WhRl0brsoHvv3r28/vrr7Nu3D9u26enp4Wtf+xqf+cxniEQiFz138+bNZLNZvvWtb33qBiuL18C8zY8OjF/4+9Bokl9a30pXTM0xWij1UT8bO6soOx6vDcwiAEMXxIMmmaLNsck0d/Y0gWMvdFM/lKZpCKhkX1c3cRYFE4dwbgh9ZDcyMYwbacbtupNcpBvn0GHw+9GCQbx8Zb6tMzFB5DNb8Wpq0KTO9ODM+9Y5PZihtrMOT16ftbw/jCE81jeHiPotplNFXjk+TXXQpC0kuEWkqJkdRf/lX8ZpacEoFCg9/wLOkSOUT59G+P1E7ruX/PHjuHPz+B/7ZYxEgvR/++/ne2YBTaP2H/5D9MZG3HIZraEBpyr+sX4vpVQK2d5OZNVq8DxKszN44+P4sxm4ikG3lBI7Hod4/OcXUq6uxj80xMz/+B/IQgGh62jxOPFHH4FymdyB/Xhv78XX1ITZ1ooeCpH4u7+v1O9ubcWZnkE35hHbthHasAE8D6ujHTebxZ2dxerqpHjqFNK20UIhPE0juHEj9sQEIMkfOAiaRuHvv0vkvvvQf+XLeKpmt7JINFvNPND1AD8+82MkEoFgW+s2WsOtSFedHxVlsbrsoPs//sf/SE1NDQ899BC33347zc3NH/r8zs5Otm/ffrmbU66SktQoORA2QePjD0kSQpAuC/K2S8AyyZRdXjw5f/7wXznoexL2DCboXleHVMOdFsyKKonWX8OrAzMk8mVCloHjeaTKLlG/iS4liznEMadnKO/fhzM5idXXh7l6NbaqkLCgTK9IeOw1jONPQnIQgYZW3YlMjRLc9E9IjY9TnpokdM/deNPTOKkUVlcXkXWdcOLv0VyHJU1LOTPVTC733kWiYVbmd7+/NteNIah7rK7T6bqnk6FEASmhLe4jbkm8vubKEVhKOH2a8pnTiFwO4bqQy5HbuRPfxo2Ux8cJzMzgDgy8F3ADgZUrSf7N36A3NeIGAgjDIPL5z2N3dHxku7TqatxEgkIicWGZ8PkgGr0Kn8JH04SgsH8/0nURponR1IS/u5v0M8+iV1Whd3URXr6M+b/6azQhCN56KwiBdF2kXUazLPRIhOLAKYoHD2JPT2O1t+Pv7aU4NIR/+TKiDz2Em80gNJ3wvfcgI1G8t97CGRkhsGE9+X37Acj89KfUfWYrpc7OBfksFOUXCU9wX9N9NAQbGE4PEzACdEY78Wk+3ki8QdgM0xXqIizUeVJRFpPLDrr/9b/+16z4BKVMent76e3tvdzNKVeaEBybtXnlxDSZkkNLVZD7ltVR7//gq11d18k7gkTBJmzpnJor8urJadpqI7x6coaVrTEOj6eJ+A2W1IfIFcsUbJdcyblRr5+vK0tjki+ub+F/7TzHTLYESJY1RVjdHMFdxHW7zVSKzPe+iyyVAHDm5rDGxrAeffSqZnVWPlwgdRotMw7JwfNLPEgOo5sRZOIsZk835fExCoODCJ8PraaGcE8YcfSvkJVnEykcp6tuB0cLvUivcpRo6o/heYv5FtCVETFcVta9O2T5/XO07bFxhCcrpa0MAy0YRDoups9PGUDXcWZn33uNaSI8j/LwMP7aGggEkI5D7sWXCH7113A+qopIRwe+JUsonTxZ+VvXCd99N044vCDTg4Tn4XkSo6oKN53Gv3QpmeefRwsE0GMxCnv3YgQCaJEIcn6e8rlzxB96iMKhQwhdx+zuJrB6FbN/+W0008Rqb0eYJqUzZ4h+7nPY8/OYjQ042SxaVRXlW27BdV2smWkyr72KLJbea4yUePMJUEG3sogEZIAtsS2sjq5GFzoHkwd5afClC4/HfDG+2PNFIkQ+ZC2KolxLlx10f5KAW1l8xjMePz44fuFybyyR50cHJvn1W5vw/dycIA/BSMbj2FSG549OEjA1In6TnvowW/saOTuXp68xRjzo4/FbOzk0lqToQiQUpMEUdFZXsuEqC0xKHloSoyG6lGPjaQKWzqrmCCtqDfgEIxyuNTk8ciHgfld5ZAT/zAxuY+MCtUoR2an3L/QcNK+SM0Bfvhzz3Dns0VFkqYReW4PFyEUjKsyARlXxHdp7V5LN6dS1hwnU3MDd3L/AFjaTpUkAGnwNWLIShEsp0evrEJkMXrGAf9kynNkZtFAIs6Yan2ni1dRgdnReWJcWieDMzqL5fIhA8MJyN5lA5PMf2WPtWBbmjh341q7Fy+fRamuxr3Lm9A/jCoG5bi3O2Bh6Loc9MQ4+H0ZzM06xCED+4EFC69aSefrHePNzpE+dwmxpIfrZh8kePkz5zFk0vx8vn8crlRA+Cz0QxE4lKYyNUhgbBSDy0EM4buWbKaqqkKXyRW3xr1qFZugYu3aTbWnBaG7CNhd33gHl5iClJEiQtJdm70Sl7F9Jlsg5OVJOitPZ06wLr1vgViqK8i5VRPsmNZoqXbi0lQgKtiSdLDKW9eiOvjd37VzSYf9ohpdOzmJ7kvlciXhIMpyYZaalzI/2j9NSFSQaMNjWKzg0mmI0UaAh6ue+5Q2saAwDi7cn9WZiCYetzQbb2+sBcB2HxRxwA8hL9Xq6i7vdNzoZqsObO4VW3QPz54c4Cx1phnDi3dhWCP+jjxKYmkI6LkZzI97R93J6iFANhj+CZWfprR6g0LuMggY3S8CdkimeOvsU88V5AOL+OJ/v+jxxEQfAWLIEze/H7Ooi89zzlbJYLS0U//x/Uv+v/29KgNZQT80/+HWcmRkyr7yK2d0NhoFrvndaN6prkMHgB7Tg/VzDwG1pqfz7ir7byyNWrsSfz2OfOIlIzGM5Dnp9A+7ZswBIx8FsbSO4+VYKA6fQQiF8PT3Mf/d7hO+8AwkYsRheNIrQNEQkgojFMLq6EFNTaKZJYNMm5M+NwHN7e4l/6UuknnoSWSwR3LAezbRIfOtbULbJ+v2EH3yA4MaNFOLvny+vuy7a7Cy4LrK+/qNHGCjKFVBySzieQ8bNMJQdwtItNKFxMnWS3lAvEaF6uxVlMVBnhBuQLTWKriRsCMQlgiqfUUlu5krBSLJEMl9GAPtHUmhtUZqaKsmrDo5nsUyLrO0xky5RHbLIlVwcTzKfs6mP+hmcy/Houhb+52tnqQ5ZOJ5kLlfi2SMTbO2MoqbfLi6uc/3cBNFaWioZht33wgCjugZZr0r5LKRSvI/AxH7c5g3o0SaYHYCWDZT7P0/BV19JnGYYcD6IcwBfyy2Q/jH4IpjShqNPQLgBNzOLL7gHufarFPWFmUN8LQkheGfmnQsBd8SKIKXkrem32NG4o/KkfJ7w7beTefZZrO5upOPgJpPIcpny8DDe4SMkXnwRZ34ePR6j9jd/E9HTQ/r5F/AmKskshWURvOsu7Os08HN9PsRttxG45Rb0iQnKTz2N67mYvT3IdJrgli2IeBzR20ukvZ3S2XPkDh9G2jZSglMu4VuzmsLEBFJKRCBA6OGHcTs6iKxYgdR1nF/osXYMA+P+HdSuXoWXTCKKJeb/23/DmZlBj0SgXCb5N39LcOAURkc7+t13U/b7ATCzOYrPP095aBAAo7aW0MMPU66uvtYfnXKTiVtxIr4IA7MDGJrBWG4MS7OImBGm3WlivhieulGtKAvu+jwbKxcRQlTuuAvBiTmbl0/MkCvZLG+uYkt3FVXm+4OszmofIUtnNG2TzFeG061uizObKfDskQIr2uuZK2vEwwGOjqeJBUyWN8UYnM0wn7OpDftojvk5O5tDSijaHgXbwwPSRQdTt5jP28zlbdrC6mumXB6nro7oI49QeH0nTjJRSYa0bRtlNbxzQZW0AN7yL+PPDuM4ReT6Bgq+BhxXXnJIcr52DaHuLFpuAo58D0J1uOFGkCBzM1iJMxRrb/yhkK5wGUoPUW1E+UyhCXHoNLZwsVa2UmjMExmZI/X97xMIhSgdOYJXKGC2teIVixg1NQjXI/uTn1yY0+3l88z+9/9B7b/6A/xffBT/xATy3ezlsdh1XbJRSokdCOD09BB99BFKBw4g8wV8q1ch+/uRU1OUXnsVzXEonz4FrleZ/27o2OOzBD7/ecxYrJIBvbYWOxAAz8M7Hyh/EEfTcFpbobUV/amncOdmQYAeCFAeHARdx4hGcU6dQs7PY65ajejrxTl65ELADeDMzlLcuQvjc59d5OOJlOud6Znc23kvZ7NnOZE4wY72HdzSeAsTuQl+MvgTllYvZWPNRqpk1UI3VVFuaioaug4UpI+B+RLD8wXiQZOVjUGCwubEvMfxqQy2LVnWFKYhbPLUwXHiQR+NVRF2np1nNF1mW18tfkNQKLu0xkxiukPMlPzqplZeOJEgaBm0VQcwhGQ8kQcEI3M5jk7k+d87B5nJljB0jXeGkjywsgFdKxILWAzN5emuDVETsjB1QUdNEEPXaI0H8BkatucRD5rcLENGb2SGYSB0Hde28a7hHH0pJXZ7O75f/RX8pRKe/3wiKWXB2cKHHel7b8FHlKqxhUWq7S5imdNokwcRTgm9mEJYIRw9gCinr3KLFwdd6jQGG1k26jD25N+QKWcAMA/sIvAVC+PkDLgudrlMYMMGcrt346XSmI2NGL29uKkUbjJ50TqdmRmcs+eQnZ2457OVu3BdB9w/793jgNHZiRDiwhxs2dxM+PY7yO3ahdnSiptMEL7jDgpjY1hd3cjWVpxPWLf8Xdr52t3oBrrfjzM/D1Ji9fTgzM2Rfq6S2M1/9hxadTX+Jf0EWlpwymXsmUo5vPLIML5i8UODfEW5ElqtVu7puIe7Ou5irjDHf97/n8mWs9QH6/nZ0M94bMljPNbxGIarLvsVZaGoX98ilyxrvDaY4D/+9CTO+RG29yyr55fWt/L/PHWM+fO91NVBi69s6cDSTYI+i5dOzLC6rYqBqQy5ssfAVAYENEd9PL6pne6IS7UlWdYQJJkrYJfL+PwWdRE/hZLLZLrEickMedslX3aJBTTaqgKMJQrcubSewdkce4cS5EsO/Q0RVrVEOTKWYjhRwPUkpi54eFUTrWEdNaf7+iWE4FhC8sKxcUYTBTZ0VLGtK05r6Nr23bhCgLpwvWYMTRLMjwEa+UADjrwymeKllLj+GGZuFrKVJGIaAqumh2Kk5YpsY7GTUrK9dhPTP/qzCwG3EIKA4Sf/1l4i8VbMqircXA7/0iWEdI3SqdPo/f1YG2/B0PX3JafUwmEQolJe7DodTv5x/OINP08IxC0biPT1Qj6PbhjYiQThjRuRjY3vGz7+SbelNzcT3HwrxQMHK5+v30/knntI/PVfgxAYTU04U1MwMYERDpF59TUC69ahx+O4ySR6LI5nWR+9MUX5lHSpU+2v5s8O/BnLapcxW6iMhBnNjNIYauTJM0+yrWkbHfr7SwiahQJybAzpumhNTdgLVCpQUW50N+7Z+QYghGAsL/lvr565EHAD7Dw1y/r2KpIF+8Ky+XyZ1wZmuKu/jp1nZulvjPL80UnuWd7AkwfGcDxJxG/geZJv7xnmH32mjUa/pKfGx3gmwv7hNHuH56gN+3hsYytF2yFXdrF0DZCkCja5koMAZjMlTk5l8RsaDZEQdRGLU1NZuuvDdNWFmcuWaK0O0F7tR1cD664rGibSAWG5eJ7HYEbwR08fYz5XublzcCTJ4FwDv7W1ldgHTFtQrn8RZ4bAwW8jz70Omoav4zPk1/w6OaPmiqxfmzmJ7L4Tceo5KCRAN6CmDzvS+pGv1TWJ7pVxhB/vOu7FjcsIWc8ibIYAMDQDDR0rXybUXUfpyC6shgYQAq+xkfg99yCWLcOORBCpFP6VKygcOlxZmaYRufMORH1dJci8jj+XyyGlrAQJ0Sg2QG3tlVt3Ryeit49IRweG5aNw5DDOzAyyWMRsaMCbn68M8zdNwrfdhlFdTWH/fiKffZhCOk1w2zZsTbti7VGUSxFCMFecQyLJ2/kLyz08NDRMzSRtp5GGxNAMPM9DSomZSJB74vu4mcpII2FZRL74ReympoV6K4pyw1JB9yKm6zqJbIFU4eLgRtMEc9kypq5R+rlo3HYlhqHhuB626+EzNbIlF9uV+AyNkuORKtikCg57hjJUBQ1WN4c4OpFhMl0iHvShaxo/PTrJI7d0sKQhzM+OT9FaFSRbdEDA+o446YKN63lE/SaJvI3f0PAknJzMkizY1IYtxLzAkC7l/hg+dc2x6Ak0EoMOp/aOUMrbNPfH6VpfxdvDiQsB97teH5jh/uX1rK1TO/ZGEwz48Q/sRY7uBc+uJLc/8xLBUB2F/z97/x1l15Ufdr7ffeLNqXJOqELOBAiCAWDO3exudlar5ZYlWbZkjeNb9po1896spfHzs72W7bFmjTWWZGukVneru0WymzlnEiABgsipUDlX3RxO3O+PC4JEE0xNEPF8/gHq1A373HPr3vM7+7d/v5Xf/7UC3fdqTqin+6qL0jTO0jhK/61o4SRoJr5VRvNqoJ47m0EIQaw0gjryHFp+DNI9uH23kg93f6iC9OXAM00y67ZgzhxDnl5+094xRGv3KvzRcYyWFsrv7EOEQ8Tuux9WrMQ+3TPbSiRI/tEfEXlzF87UJFpTM2pvD/7g4GX5WpwvqusiJibwFxdRkino7sL9DLPMqqoipTxrNt2NxwjddSdyfBw8j3hrC9bJYcyhIZzJSeR7RSkdB2dqivDKFdT2H8Boa0e/6Sbc5uar7iJI4OKQUhJSQyxai2yPbj+zfUPTBnoTvdS8Glkry0FxkKNzR2kKN7G2YS3pd945E3ADSNum+vLLmF//ej3DLBAInDdB0H0J8zyPhphJOqKRrbwfeDueT0c6hPOBkwNFCLrSIda2xUC2cmS2iKYITE0gBBiaQslySYR0js0WOTFX5OUTi/zGtT2MLdWwPY9TCyXChkZ7KsT4UoWBxhDf29bNI/umMTXBtv4Gbl/VwpMHZtjSmyFbcVgoWcRCOqmwwWSuSthQmMpWWSjW2NrbhanKYEn3ZaA45bP78ZEzx+rk3nl8T+ImP3zwXN/H9T/5oIrTX9hXcyBwuWisDqMtHEZM74PCFLJzE9KIQa0Amgl2kRA1qiJEyMmi+jaKZqLh4QoDR4JamkJVVJASrTZfb9NkV0CAUppFLJ2AeDuycTm+U0RkehFjb4CqoQgNJl7H77oJISSgUFPrKdOe5xG25tDe+R9ouZNQXoCJXehjb5C8/p+Rjw9ddu8xKSWRLdsZqhU49eYzJDv7aCyqFH/2d4iFJYyubuK33IJ18gRqZwdO/OwWENWmJpQv3U+oWkUCTih02b0Gn5a+uIi/sIAIh5FtbfiGgVYuQ7mMTCRQfB9OnkROT+OUy1izs0gpia5ajdnfh9/QUC+g9hG0ahVtbBz3xHGE7WAODmKtWX0mR8sJh2FoCCEEDQ0NFA8eRGtrZem//TdwHEQ4TOz67VQP7Ce8ahX29DSKoWM3NV2xxyRw6fF9n6HEEEOpIY4tHeO+vvsYL46jCIWXJ1+mIdTASxMvsbpxNTe23sjeub3MVWe5ayyHIkB84K3qzs8TrtXwPubvJhAIfHZB0H0Jk1LSHlP5Rzcv4989eRTLrX8q3r6yheXNUe5Z08bTB2fxpGT7QAP3r22jMwYdQwkyMYOTcyVipkbc1PCkpCURYq5QY21HkncnC9iuT2NMZ21HEseTXNvfyNHpAm+P5WiKL1Ks2vy97T1c35+maEsqNYd3J3JMFy0mx3NYts9tq5ppT4Z4azTLQFOUqVwVgJ6GKF3pEIoQl3Ua6NVAURTmRvIfujgyun+BDQ/2E9JVas77GRXrOlP0pk0+aq2+EIJodRJ1/iDCtfAal1NODODLYGb8UtNUPoJaGEPMHoJTL0J+AgAxdwDRshqMOIy+Ao1DxNvWE6vmwPcRhVGU0dfB9zBW3ANLw7iOgyhOoSQ7kJk+xLGnEKEEwneRswcQoQTSsRDpXpStv4eY2YeYP4Sc3gdaCL1/J7pw8Q79EkVViTUtRya7QNURsVYYuhmc7cj5o8jh5yA/jjr+BqGhVqrq5deH1g2FSN/5VRLX70AMj1L94Y/RUQnffDP2yWEqL71E9KabUD7i49P3faz3ioRdQZ+xWq0GY2PIWg3Vcci/9DLIeghs9vUTXrWK/DNPIy0LXdMwW1opPPssfjaL1tJC9M47kJZF8Wc/Q21shMYGYnfdhdvf/6EgWJES9cgRsn/259hjY/WNQtD4j/8QedttH769YWC3tqLOzhHatAnVDIHnUnr5FXBdMEzit95K7dhx9L56wB8IXCiNNPL9Fd9n/9J+ClaBB4ce5MdHf0xUjzJVmsLyLPbO7uXa1mtxhcu+pXe5pmUZhZHjtERaSagJQKK3tAYBdyDwBQiC7ktcUnO5ZVmSnswmRpfKZCImq1vCJFSbP7i+gy+vb8WXkva4TlJzT5+c+LQnNHYubyZXtfnBDX3MFGrMFy1URVCzPQ5PF/mDWwZ4d7LAUwdnyVcdIobKPWvb6MrU0BTBbNHmL14b449u6efAxCKxkMlLxxeZzFUxNAXX93n2yBx/77pe3hrNMtgc4641bTiuR8JUqVpOcKX/MiGUD6eRCUUwENf4V3ev4Ie7xpjO19jal+GrG9poND56PXe0PIa657+D7yIBZXw38dUPkG+48ttBXU6aiwdRHv0niK6t4FZh/hjEmsG1wK5AYQZWbALPhnQfYuRlRGkekIj5I1BZBD2MePO/IgduRi9P4/kODD+HkvgesjgNTUNw6CGEEYXiLKS6Yf4QwspCbgRmD9Rn0pGghRBv/J8osRaYO4YyvQc6rkHaFUQ4DYUJ0MKw8j7k2q9DcQoRTqDWshD9dEG3EIK8n6fiVkjpKUJc3OJ8vu8jImmUwmGo2UTWr6fw2GNo6QRC1yg9+wyp3g8XPrpSaZUK1b97CHd2hlBXF4XnX0BNJpBNzYDEOXQIpVZDWhZCgnPsOJVXXyN+441U9+xBWjXsve+AYeBNTiJ8H8UwKD72GPHf+i2caPSs51OzWdzjx98PuAGkJPejH5PZvBkrlUKzLJiZRQgojY5hvfQiaBp6YyPVd9/FW8qid3aiptNorS0Unn+B2M6dCNdFBaSiXNCOD4Grl5SSwdAg4UyYyeokZafMSGGEmlsjZsTwXR9VqFScCs2xZk5OnmRxxQ3ox9KMzY/Rn+wnFmsgfNONQZeQQOALEATdl4GQtFmdhtXp9648WkgJEdVlefK9WzlnzVRO5WweemeKqu1i6gptyTC3rmzm53smODlf4YaBBqqOx0/emqAzFSKkq5Rtl90jS3zn2m4e2z/NTKHGZLbC88eXsF1J2IThhTICsFwfy/Xw/XoRt+0DDewbz4MQhDWFQ2WL21defmmfVyPf92ntjzP8zjz+B9LGe9c2YkR8rgtpbH5gOUUHMqZE+B8dcCuKgjb1FtJ3UfDQ3RLCLsGhnyC3d1NQg5mfS4GqqigjLyEqc/ULdUIBMwZ2CdwaGDHo3gZHfgm1PEzsRjgV5I5/CXv/GgpToKigh6GaRWRHAYnQw+B7kBuFcBqkR70R93vvK1m/n1ND5CeREiQCEUoiCpPgVMC1EL5TH9PUXkTv9XD8GVh2Sz3ofu3/QEgfGgZRCjOEGwawcbD5+ErVUkj25Pfw+tTruL5LWAtzR+8d9Jl9F/1zSmlsRGtvx5meIrKsFUWzUGJRhGFivbMLbeNGXPX8VJC/pI2M4s7Wq9oL6j3I/VoVI5lCmgaUisilJQQCYVt45TLCdZC1Ks7EBEoohOP5hNavx69U8LJZfEDt7UUuLsLpoFvzPMTSEprrUlla+tAw/EIBCgUM36f0dw8h5+eQ8wsUSkVCGzZijY+jrVhB7J57oVrFPnUKr1Yl/8STGH196B3tOO/sw56aRO/qQt+8GScd9EgOfPEUqdBtdtMT6mHMH8NQDKQqqbk1GsONmKpJza2xf2E/2zu2U4qFKN+zkdasxI92EOvdiB2JXOzdCASuSEHQfYVSVYXpfL19ly9hMltDFfCtrd38fM8k/c0xZgsWmiKYLtTQFYWuTATPl1iOR3cmwlLJIluxqTkej++f5p/cPoTvS1zfJ6SrRHSNiKkSD2l0ZyJs6k4zna9Rsly+saUT33MJ3mKXh0gLXPvlfkb2LVAtOXQuT9G2PIZ/OsA2cGjQ4ZOK0QshoLqEquvongtzh6GWBS1MKPVT5MDdFCPdX/wOBT6WqqqI4iQgQD1d8VozwS7X/59oh4XjYJXqP9tlwEcsnUKGUsBIPbj2nXrgrYXALoCI1oPlZAeMvVEP4CNN9Zl0Va8H+HoUacTr6euLJ+oD8l3QTKQZq/9fynrUhQBf1u+f6oUDP4XqEjSvgvwYYv4wSiRDxHgdbfWDVLR6YCOEYMlbYrI2iUDQF+0jZ+d4eeLlM69B1a3yxKkn+N7y7xHl7BnQC66nh9D69XjH3iHa04IVzlEQFnZmELcapVt61OdNr2x+Pnfm/1IIlEgEWShALge2hXQ9hKogx0ZR0hmUaBRvfh7puKCqSN9HSafxcjmUaBRUFSElwnEQpwMJPZ+n+uhjODPTCEUlPjCAomn47vsXE/XubmhtxXr2OfxcDn9qGlku4y8s4MzO1oP94WGKS4ukvv9bhDs6sA4dRO/uRu/sorp3D45T7y7iZrPYIyNEv/vdj11b/l7BwUDgfJBS0q618w83/EP+6vBfMVeZozHcyLLUMo4uHaU70U3JLYECycZ2Xrbf4saOZTQFAXcg8IUJIqIrVFfapLchyqnFMr5Xr4+biZkcnS7w5fXtKKI+Q60IcDxoToUYXSyjqwojixWePDjDvWvbqFgu2bJF2fZYKlncvbaVpw7OAoJUWKO/KcaphTLvTuQ5OV9mWXOM3sYoTxyY5e9t6yCoonZ5kFISa4P1nc0IFFzP4dfpr+55HmrHJrSR5xCEYM1XAYmcO4wc34UhQVv/u7gyqIp6Mdm2jezYjDj+NJx4FjZ8ByL319O98xPQvxMWjkJxGkIpCCXrs+CTe5E92xGlaagsgVWGeBsy0Q5Fga+FUTo247sOYujOehX0VV9GzOyvB8uqCWsfxNdCkB6AlrVgFZBCQMsapFUCzwEhQCjI3uvrxd0y/eBUoTQHeqQemDtVpPQhP46IC/SJ1xF99yKlZMwa4y+P/SWTpUk86dER6+COnjs+9DpYnsWStUTUvLhBt2uaaLfcTENHjfl3/oyJqQlQVKKFeUID97FUPEU4s+KKD8rU5uYz/7dmZohdfz35hx9GAPbIKOG1a/EsG1mu4KsaWiqJvu1a7JER8H3UTIbI1i2Ud+1Ca2nGnZvHKxaJbNqEIiVCCKxXXsGZmQZA+h4+kthtt1J8+hmQEr2zg9Rv/zauouCMjyFsG69cQqlfBcIZH0fr6cHP5SCVwlcE7uZN6CuWQ7UKS0tnAm7h+wjXxRACZd8+QoODWI2NZx1H1XURp07hDA+jxuOoy5fjBGvBA+eB6qlsSmwiti5G1spyZOkIs6VZVjas5NFTj+L4Dq9NvcZQeohvDH2DqBZFCokIvp8DgS9EEHRfoToikq9sbOfITJGi5RHRVWYLFe67oR/hu+iKoDUZ4vpljew6tUTN8fCl5N51bYwtlWmKmcwWauxYlmHfeI5MVCdfc+hKh7l3bSuuLxlqjrNnPMvIYoUT82UAjs+V6G+K8vZolgc3tkE0+PC+nHieB3ifeLtzMbCJlkbQShOIaBPirT8Hp1yfobz+H8Mb/zfkJ9D8Kq4IrqZfbE77NoxVD8C7P4aDP4eVX4ahu0CPwuirEO+ApuX1mWs9gsxPIJtX1tenbvwtlMVjYBWRzWuQLauxUJHCRDoR/NlZtLY4rP4mvmqirP8tVCuL1EJ4UsFRTGRriEjzGtTsMEKAF29DtKyBU69C4zKItUJ5FlI9kOyE2YP1f1UTCtOgKKdn5TuQtoVYOIbadxe2Ak9MPMGp/Kkz+zpWGGO+Nl+fPf9A3CoQRLRL5L2oKYjiO8wrZRTNpLHtXmqv7cN+4c/Idq2h747v4K1ZU79AcYXye3oIb9xI9Z13kLZDbWyMxj/4A/zFBbTGRrSOjnohv1Ur0dvaMVetwjp5EjWRxFy9GtXQyf7wb2j4nb+PPTKK19qG3tuLH4+R/9nPSH396+RGRs56ztLx40Q3bKD1rrvwyhVETze1RAIFUJtbcLM5kBIlGsUXAq2lBS+fR2gaoZUr8FKpeq/wSAQiEfTFRZRqFRQVWa1iNDdTePIp9Lf3IHWd5A/+Hu769Ujqs9v+7t1UXn/9zHjE3r3Ev/1tnEzmQr70gStUlCirIqt4rvwcY4Ux0qE0jww/QsEuIBCkzBSHFg/x+vTr7Jnbw/1993Nt5lriXH7FKQOBS10QdF+hpO9z80ACgWT3SBZDU/nB9b1saBRIWT/sEkHTTb3cu7aVo7MlXE8yulAgqqukowbz+Rply0VTJF9e20YqojK+WGZ1W5yIrhIyFHaP+mdVtoZ6+zJDU6g5LnzCOsvAlSFuzxJ66/9CndyNiDbWZyu3/DbM7AdATOxGvfa38ReGcZRwkABxCSiZrSQT3Sg3/lPwPUS0CbKjsLQbkt3QvAJUHf/QL0APIVd+GWfwbhypY8c68LUwhnDwpaDm1lsv1X75KM746aJUqkrivvtwBjrrP4c/vKZVC2UwJv4WPBtPNZFCQdn4PUrJ5ahembC1gGbnURZPIOItEGlEHP4FIJGlOWTDEH4ohazNIuJt+KjUZJnRwuhZzxPVohiKwUDDAK7rslhepOSUWNe8jgat4ZJ4Pwp8PEDKCsmurVSe3YWXn0cxEpTLeWaeepi2hgac9vaLPdQvhFatwugoaiJB6p57kLEYjIxQ2fcuolxGmCaVV1/FOnwYNBVUjcR992FsWE/12WdRNBV7bBxjoB9Ujcpbu4nt3Im7MI974gRmXy9ks6ixOK5lnfXcnmVTW7bsrIJnPhC+7joKk5NojU24S0uEVq7AXL+e8ttvE7v7bsS2a3E/MGutLy7iDZ/CnZ5BEWD291N45hmEqqJEwvi2Q/UXvySZTmO3toJtU9y9+6yxSMvCO34Crt36Rb7cgauIKU1ubLqRilthpDBCwX6/L7dAENJCzJZnQcJPj/+U0MoQN6Ru+MTlZIFA4LO5KoLuJ554gl/84hfkcjl6enr4wQ9+wLJlyy72sL5wCc3jyyviPLAqDULiu+5ZaW0CSUfYpSOsYYowzxyeI27U2zrFmmKkQyrNcYNVrW0MNZqYKth9CXQVhPSpegqvRFRs1yCsK3gSFCBqqDRFdbpSJsGn9pVLERD2y2i4hIafhNoSomNjPe04nIZqFib3QnECEp3QuhZv6F68IHXtkmD5ArdlDfpL/wbyUzB4K2L0dYi3IK0CZEeRg7cjd6zCS/ZQTC7Hlh/4ynBdXD5wLE+cfD/gBvA8Ss88Q7SjAzf04SrhEVkmfOinyOk9ACjhNF6iG//wLxHX9FDDpGZ0gNEBsVUIITAMlWj7VvTFI7BwHM/zcXKzoJm4PTfgS0lYDdMZ72SmXC/INZAYYFP7Jl6dehVd0fGlzzVN17A2vZZ2s/2SCLgBXDRk9w6S2aNIL0mtsAiKjhdvQYmlWLLztM7OwhUYdOuVCpWf/Rx3fu7Mtvg11+AXS9QOHCB9zz3geVR37UKEQkjHQWga5TfeILRxA5FbbgbbJn7nneB6uEuLRLZeW08ZVwRS1bBHRhChMNGbbyb/85/B6QBbGAbGpo0456gwbrc0E//eb8D4OOQLaJqKrWqkb7sNq7Hh7DRxKak++yzO1BSx227DPXUKFAUtlUJrbcHP5tDb28F1WPz3/wGlsYHY7XegJhK4v1LMzS+XgzXegfMqJmMMJYbQVZ3Di4fJWlkyoQwVp0JjpJGVDSupulX2zu1l//x+dKGzMbERQxoXe+iBwBXjig+6X3vtNf7yL/+S3/md32FwcJBHH32UP/7jP+Y//sf/SDKZ/OQHuMxJKZGe84m3W9USZjIX58h0AYmgrzHK7csSZEx5+ovfBwmGwpmT1LDq88C6Nn55YBbLTTKVq7K1L4OUPr+/o58mMwi4L0eKotTfN6dP+BQBkeoUSmESjAheogukJDzzJurIywjfRVj5elXqo4+BatQLbyXaYOhOeOevoJZFzB7Ea7/+kglyApBLryV5079CXziEOPksMpxEKjp+qBHf98B1yC37an3ZwcccNyHEmarTH+SXy4hyGX4l6BZCYMzuRS6dfH9jNYuqhfD0KIpfAyV21n2klFiWi2V0Itq7CDdsQMuPQKeCm+ylotfTcYUnuKv7Lk7mThJRI1zXfR1/+u6fkrfyeNKjK94FwKaGTWjy0vkKlFJSbbmGzMosuYkxPD2CWLGZsVW9jFizJPUYrU0GySswGJMjI2cF3ACFhx8h/a1v0vCNb1B8/HH0jg7cuTm0lhZ8y0JoGlJRwDDQNm1CViqIapXCiy9hdnaAIvCKRYSmIRIJhK5jjY2i334biW99C29sHKGpKD09H7uG2kkkYPVqhBA0tbUxMzNDzfc/1BtdKZVwJup97ivDJ0neeCP+9DTlV17BLxSRrgOuS2XfPsyeHpyTw5QqDxO+diulbPasx9N7e3CusGMcuPgSaoIj80e4f+B+Hj7xMLZn4+MT02IcWTpC2S3zvVXfo+JWGC2OoqGxOb75Yg87ELhiXDpnHF+QX/7yl9x6663cfPPNAPzO7/wOe/bs4fnnn+eBBx64uIO7hIQVn/tXZtjel8L1YUV3M/nF+U88uetJCH57Wzu5mo9UVFxfkjIFCc2/4k4Mr3SmX8FcPIiycAwZa8VpWU/VbCK+sAcOPoyKg1qZByOG0ncjYnI38uTz9XW/7Rth9/9dL3IllHqVaqsEqgarvgTSRxoxpGr+OvXZAl8QXyrk0xvIeDai8NdI6SFrJagVkZll+JXcp3ocKSVaSyvw7lnblWgUGf1wkTJd2six3dAwCEvD7/+iuoTafyuOGvvYIF9KScVohKbGc/6+z+jjn278p8xas7wx8wbZWhb/dNbNWLHeRmeiNkFbrO1T7d+FYilhlPdW2MYAAOQmSURBVL4HqDQeJlJt41VtnD0jzyBqNQwjzKha4Nu6QaJpAF9RLvZwfy0C0LJZZKmEyGRwYzH8YvHs23geQkr8qSnyv/gl+D6h1asRpok7P4/R1YUzP4+WTiE6OnBbW9E0Deuhh5FIalNTRNva0Jqa8MsltHQapbkZX1XBdXFaW6G1FfjsFSw+6ntNmmZ93Xe5jNHaSuHhR9BiMczBQbxcDq2xkeqRI+itrdROnADPQ5ZKqOk0sYEBSqOjCNMgum0bXm/vZ39hA4FP0BnqZDA9yLMjz3JDxw0kzSR5K89wfpjh/DBLtSVWN6xGSslkZZLWSGs9fTGYPwkEzosrOuh2XZfh4eGzgmtFUVi7di3Hjh27eAO7RAl8GkP1WaiIoZH/lPcLKT6tEfjg6UsQb18+FCRRe5bQsUeQs4fw9Dhy/hj61B60Tb+JcuJpUAR6LY9wK+Bb4NVg7E2EoiCXTiIGbqnPdHt2vTezEYNkVz34PvFs/d90H1pmNUrbdfjB++OSEbYX4ORzkO5GzB5CqCa+XUK1C7jNq04X1/sUlg2gH+k+a0137LbbcM6RWu4LDSIZiKZQVtwN5UVQDXynit1/B97nfH9IKWlT2hh3xxEI5K9E8LZv48tL80zS930i0V7Gr/M49PZudMNEi6fRIhGKxw9xxHuR65NFnPXr60HkZUTxfeQbb1DYtateEM00id91F3ygajmAkOCVy0hf4oyMgJSUdu0iee+9FF94Ad+20Lu7SNx9N1IItGPHcEdGUR0bpVbDD4WQug6hEHoyibRtvJERzFUr0SwLxXFwTPOsNdyfl2sYRG+6ieITT6CaJpWJCVxdI3bLLYTa27EnJ0HTsA4cBNdFCZl4pRLuxDhGXx/p7duRq1dhJ5PBBevAF0KVKtubtqNIhZAe4sDSAcaKY+iqjq7o3NR5Ew+feJiGcAOL1UUWagusTq+mUTQG78lA4Dy4ooPuQqGA7/ukUqmztqdSKaampj50e8dxzrT6gHrwGT7dV1NcwRVjf9V7+3o17fOV6NMcRyEEielXUJdOwKFHEEi0UAo31Ydi5dGWDiEWDyK0EMy8C1YRYi1QnoNQHIplpPCRiycQbRvqv0dCOAO1HJQX6jPfRhQZTsOJZwhnllExmz9yTIH3XYi/xVDuOGLkJWTfjYjyImRHUMIZZOtarMa1n/q5vUiE0FceIDw1haxWUVpacDMZxDlO1jwEevs6eO5/wxcCRTNBNRDX/0+IygLRsE8t1Py5L85kQhkmChNc23Ytb0y/cWb7moY1ZMzMBfmM+6zHULFtooeOknTn0SoWeAJFUbCOHAUpKc5PUXx5mqhpItes+SKHft6pk5MU3njz9E8CadkUn3iS5G99n8g1W6js2YNSraJ4LuEbb8TNZetp5I6DzOcovfQS4Y0biG67DsdxKI+NEtm3j+LBQ/UlL729uLOzaC0t1BaXSN1zD4WnnsQvl9FaWlATCbwjR7FfeAFicYwt1+B0dX2qsX/ScRRCoPT1kf7a16BcwTpwkNCG9SieT+nd/WjhMObgENU3d6FEIviVCqgqRk8v1TffpPzmm6T0b8GWLcF37xckOLeBFr2F1Q2rOZo/Sm+il6SZpObVaI+18+rEq+iqTskuUXErHF06yvNTz3Nd83V0ap0Xe+hAcAwDl7crOuj+rP7u7/6On/70p2d+7uvr49/+239LU1PTRRzVxdN6Ov0ucHk753GsLNXTv30Hpl6rB9KaWu9/XF1Aj6QgOwJN/VDN1dPEATSzHkjrUWhZXV+H6zsw8hKs+2a9x3N2BOwirPsWjL0BDQMgfdTiFJFoI2guybZLK633UveF/S3WijAyA+EkjL9eT/duX18/vmseoKG9/7M/Znf3J9/Gc+DEUWhZXh8Dsp4NcfBnxFPdYOVJLrujXhPgc6RRJ+0kB7IHeGXiFW7vvh3Hd2iPtdMcbmZdyzrS56io/kX5NMfQLRQovvYa1slhmge6ScdbGF2cxszW8DRQUekkjcyNUP35z0mHQugdHRjt7SjnyCi41BQPH8GNfLhFW8RxyHz9QcrdXVTf2Yfe3UXljTfwS2XSv/mbVHbtwstm8fIF7OMnMHr78LNZtFIRpbOTeHcXQteRtkP69jtQwmH0rk6KL75E/IYb8BYXcZaylJ97nmo0gtbUTGhwEPf5F0h/+UuEVqz41PtwruMoHYfSG29QfvkVAIyeHjJf/Qrl198g//TTSNsmfMP1JO6+Gy2VonbwAG42h9HWSvmNN4lccw3WiRM4R4/ScvvtKKcv9ge+GFfzuc10aZo9U3tQhYqPz6PDj+JKl+ZIM/3JflKhFG/OvImhGsTNOMP5YZJmki1rtlzsoZ/laj6GgcvXFR10JxIJFEUhl8udtT2Xy31o9hvgK1/5Cvfdd9+Zn9+7kjY/P4/rXj0LUYUQtLa2MjMzE6QUXcbOdRwVJLH5t+HE0+BU0dtWQX4WT09hGDFYOAGRDCI/gajm6uttu6+FsdfrAblQoWMdcv5ovZfy1t9FTu+DWBuydT1e32315/ZsmD2ImDty1ph826bmalSmpy/0y3FZ+qL/FkNeCWPmOPqyOxBHfgmzh+uZCYN3UFCbsL+g42RIh8TMYVg4Ca6NYkZAgu9YuPFu/HIJ3n0IL9RK2fx8J1f3tt3LQGKA0WK9jVhLuIXlseXUcjWmc1/8+/DTHkPVcXAeeojS40+A51GWW9m0bRNetcL06CE0zWBb6zYSrx/HUTS8iUkWf/Rj9M4ORChM6KYbcdva8C7hGSBVUahUKmdvVBQ0KSmNj1N66mm0WIzyk0/iHDmKNz+P2tRE9Nqt6J2dgMBZWqQyM41SKuEvLuGVSlTf3Y/W3ExowwZcw8Do6sRbNoj98itYp04h5+ZwJybxCwWUSAQ0jewjj5D8zndY2rUL5XSv7V8dq4QzKegfdxy1sTEKv/gFke5u3KlpKs8+i9nWSnj9eoqPP44Ih4msXk3uhz/EyxdQUylCy5ZRfustzIEBvHIJt1gEwyS7dy+eZaF0dODEg17J59PVfm4jhOC1xdeYzk2zpnUN/3HPfyQTyqApGnEjzsHFg+zs2glATI+hoRHRIhxZOMLCwsJZmaAXyxd1DDVNu2on2AIXzhUddGuaRn9/PwcOHGDr1nrPS9/3OXDgAHfdddeHbq/rOrp+7r7SV+MH9AcrWAcuXx88jpHyCBx/uj7TKMG3LdTKImp2BDqvRcSaYWkYoUdh9QNw8nnIjcLG34TcqfoDFufqQbvvULr132MM3Yc2+jJy6h3Q47jZCfTGbjzXQ+/ejjK7r/58RhQ5eBtVsyl4X31GX9TfoqVGMTL9OHNHUJffj+I7SNXAbV6L5Qm+qFLzhrWI0HREdQk8B2HlQKiIlV/GL2frTyt9RGURabR8rufSPZ21obWsC69DUZQza9Qv9HvwE4/h+Dj28PCZghhzbQayUOCOhhsQkc04u/egP32EckilKqFr5Vqqhw/jDA8T2biRyt/+FH31akIb1lM9XY1bFQKjWETMzeFOTuJVKojubujrO2cbty9cdxd6RzvO5OSZTZEtW3DTabTFRfxSETWVpHL0GEo0gp4aJDQwgF+p4FeqiEgEo7sHZWYata8Pd2GB/M9+DgKcqSmErhHeuROtvx9HEYQ3bqDy3HPIShUvlwPXxeztpbRrF1pTE4qU4HmIAwcQra24DQ2otRr+gQPUDh1CSSSJrF2DHw4jEwlobT3ncfRPnSIUjVJ65Bd4+TxKOIz9zjv4xSKhjRvR2tooPP4E1tGjoOsY3V1UczkS995D+bXXcUemCK9ejZrJkHv44fqYTJPEg1/HbgmW4pxvV+u5jaIoTJQmqPrVM7263/u37JTJhDIoKHREO6g4FZojzZTtMmsa1+A4ziX1ml2txzBwebuig26A++67jz/5kz+hv7+fZcuW8dhjj2FZFjt37rzYQwsELihdOpjZYwgsCMeRzasRdgG1ZxuEM0g9hFRURMtq5OwhxO4/g57rID8GRx+Frq1w5FGkEYO2Dfhbf4/oxPOI6b316uSLJxCFWcSar+POnkBdeRdCV5F+rV7MKpxEzB8h0riWkhGcSF4KfAl2362YdhlvYRhPKIjOTVQznz7d9tehZk/Wi+3FWmHxOKg6JFsh0w+jb52+lUCa56+to5Ty0xeF+zUJIfCKEitXQ4+ZaEkFPuXEsyyV8DUdLZ3GzWZpbu4h++4e/sLdzdau7azu6yW7MItll0lu2gpZHYpFpOfhlcsIw8AfH8daWCA80I84XUnbmZyi9OyzWMePIcwQRn8/xg03YNx/H+5HXGT+orihEKEvf5nQ2Dh+sYDa1IzX2YEPyFgMNRYDywIp8StVots3Un75Zdx8DrO/HzebJXrttdjDp3Dn51BjccKbNiF0HWEYeI6N0d6O+1717zVriJXKlLM5tKYmQmvW1Ge+q1W0hgyKaeDMzEC5jL1rF9GdO3GPn6D62mtgWQjfZ/HZZ4nt3EF1aorw/ffDr1QWVwC5uISs1nCXlhBS4hUKCEWhdvQYybvuAk2lcPgwKApCVXFmZlFME1kuE9q8CSEEekcn5ZFT8N5FIcui+vpr6A88EBSPDpwXvu/TlejipemX2NKxhbAWJm/nUVCoeTUkkq1tW0GC67vMVmbxpc91zdcFAW4gcB5c8UH39u3bKRQK/OQnPyGXy9Hb28u//tf/+pzp5YHAlUoRgujEK4hDD9VnrjuuQRt/GU69gpAeIBCd1yB9rz63qYXqyyvG3kC2rkMsDSPNBPLGf4YfacZvXI7++n+Gyd2IwlR9JnvFPWBXEKdeRHRcC0YYefxphGvhuQ64VQBCjcspd94efIlfIqpaCnvNb2BaS6Co1PT0F15dXpU28vgzyIYBlOZVSD1cX9JQeH8G1G+/jtlCM2oNQikFxKUdegghyB3KcfLJd/EqVRTTpGvHalq3fLqZeqWxEZCIlhbMlhZC4yXmxydJ9Kd46dRzvG2mWHnrRpSqxZLu0/baEaTrYg4OosZilHfvxmhtxR4exisUSH7pS5grV+JOT2MdPAiKgpQ1nLExxMEDGNds/nTr788zNxSCoUHg7E5EXihE/Prr8cfGUHUdEQ7jl0u4uRxCVUFR8LI5yq+8SmTLFrzFRfxqlcjAQH122LYxV69G7enBPl3V3TMMRF8fxvbrMFcsp/Tsc/UU83iM0KrVFB9/HGdqGrW7u96qa+9enMlJnFOnEK6LVyigZTL4hfpsYPHJp9C//nXsdOrMuNV8HgeJ0OrPGVq3FjUWQ0km6xc9FhYIrVmDmskgPRfpevULJZUK0jAIPfggwvfJ//CHuAsLZ79WMzOYto1vGF/cAQlcNaSUDCYHSZtpstUst/fczrNjz1Jza+iqzs6unaT1NF/p/Qpj5TF0RWcgOkBYBjUGAoHz4YoPugHuuuuuc6aTX3WEYKwEJ+arGKpgRXOERvOLnfkJXBpMJ4sceQXfTKAoOkrTILz0/0NEMlArgO/ByMuIDd+F/X+LXHE/fmYA4XvIwTvwqnnccAtu97WEs8cwjjwEdh46r4Gjj4HvIo49Ceu/jeJU0GINKJUlZLITf2pfvUjWaaI0gxAiCLovIZ5U6n2v4YvKKD+Ln+ioVyxfHIbyPJSmkS1rIdqC0bqBnN/OoSMmpeIiAE09cTrXxC/pwNtfsjnxy7fxnXr9D9+yGHtmL+mum+BT1A10W1uJ3XQTpVdfRSSSGEsl2uc9dmzdxqO1F7DLLofHDpJs7+ReuQqpTxG55pp6ADc/j9HehnX4CH6+3uyx+PjjqA2Z+t+2adZnkFUVaVlQrSKr1S/y5fjMtIUFrHf3Yx08QHjLNdQOH8bLZlF0Ha29HVmzAPByOZRwCBGJEFq1iuIzzyDzeUQshjB0Cs8/T/jb3wbfByEQjQ1YExPoySTRHTuwjx0jev12yq+8imfZJL/2Napvv03p8ceJ33YbZl8/slLFLxbx9u+vz15DvdaB7+MvzMMHgm6EoDo+TmLdOpKKQuWtt7H2HwBNQ4nFyPzgB0jHIX77beT+9qcIwwBFQW9vR29pofDf/gypqoTbWqn5Pu7S0pmH1js78Uwz6MEZOG+SIsm1LdeiaApHlo7w3RXfxZMenvQ4lT9FxarQFe6iIVZfonIhvg8CgavFVRF0B+reXfD4T88ep2LVA+3WZIh/eusAXdHgU/VKp/g2+C6uMNGaVqC4NkIz68Gw79a/WF0LhIKQEil97EQPsmkFVs8dSF+iC5/o4R8hjj0OZhySnTBzAHpvguHnwbUh1VOfTa/k8LQw6uIx6NmOHHnlzFhksuu89scNXH7K0V4S67+DsnQcZvZB1zZkuhdhFxAVjZjq0tnSxvFqHM/1mR8t0tgZJXThio1/ZrWFwpmA+z3Sl1TnCp/q/lII/C1bSCxbBqUSWqWC+corLHt+nG+su4PZTAXNCNHefwvMmoT/8Q7MmWM4+w/gFwp4E+P1NlSn+eUyQlJPaTaNerANoKoQDqM0NXEpXXJVpqYoPvMMeB7O4hKhFSswW1uRjotXKqKYBoqmoff341eqSMfBL+TRmhpREol6Gy5Vg6lplL17Kb29B1VAaN16UvfcQ/HVV7FHRlDiMZRMBnOgH72jnfJLL2F0diJME79QQObz2IcOgaKQuOkmym+/jd7UTDV7FMIRRDR61rjdRILw6tWUjh4lnErhV8r4rouWyaCEQ+Qe+jv0gWVE1q+n4fd+D2dmBjWdQm9vp/jCi3jxGACVuTlCQ0O4uRz4PmosjrntOnzHQYyO4s3OoiaTiL4+nHNUgA8EPg1NaqxKr2K4NExfso/Xp19nobrAsvQyOiIdxI168T5FUc58T5coMVudRVM02kJt5LwcJa9EQk/QoDYgvEu3eGMgcCkJgu6rhIPOT98aPhNwA8zka7x8MstvbMgEQdAVzjYyGC2rkKV5PN9FS7aDHgHPqq+tdSogVGQ4A76LH25AxqPYA3dhC5O4M0Po2EP1dd6eBZEMTLwFq78Kvl1/ksYhyI3ixzuwtQRCgBptQJSm649bXUL030y5adPFfTECF52NTq3jOkKKjshPQq2IkulDzB1GOfgzFC1Mz9A9hFfdxN5366mNVsUllL50v7LMiIZQBPJXcvND0U8/ZiklTioFqRQu0PAH/4j8Uy9gPHGQwd4u9B3XMXbUwPd8Iq0RGrZuJdTUhPXKqzgTE2d6WgOYg4OU33qLyLZtJG69jeJzz+HXapiDy4g/+CB2JnMe9/7z88vl99czV6tU9+5Fv/021EwGe2QE13Mx+vsJb9pI8YknUZua0Ds6qR05ihQCt1JBUwTCcbBHRuvr2ycnqLz6GvF77yG0fDnali04p07VZ6xtB3tiEvvECewTJ4jeeitePk9l71605mac6Wlqhw+T+Y3fwKtVibS2Yba14Z6jVVFo/XrMZKqeXdDahtHXjzM3hzu/gBKLkbzjdrx4HCJh3FOn8Gyb0ksv49t2/SJCJIxvGrilEsmvfx3fthGtrXihEP7zz1N9550zz6U1txD+2ldxg7ZigV9Tn9mHp3g8NPwQJ3InkEgmihPs7NpJ3skzUZpgsbpIe7SddDjNYycfw/IsMqEMbak2juWOcSJ7goSR4I6eO7gmeQ2GDJZABAKf5NI9gwmcVwXbZ2yp8qHtJ+ZKaFoztm1fhFEFLgQVj3DuKGp1AVGeQGnfgFwaRa5+AHHokXrP7lgrcvUDyONPIZbdgbPyKxT1JnS3TPzELzDcAhx/sh5gCwWcan22uzRTv2/rBtj6uzgnX8TVEkA9I9KKdqBrBnLD9/EUg0pqORbBl3MASqF21Jb1aKOvoPTfjFg4itjz38G1EAiU7DDNO1LoxnYc2yMcu7S/rsyWGD3XdDGya+zMttaVbUQ6fr22TxKw1q4ltnwthb3TFC2NQsHjvXzP916PWl8fZnMzWksz7vw87swMRlcnRl8vtcNHCK1Zg9vaUi/YFY3h9fXiJBKXXMqy2tEJmgbvtedUFPx8HhGPE925E2lZ+NLHLRRJffc7uIuLiKZmiMWQ5XL9LqEQem8vzvgY7vj4mce2jx7DqVaJr11L/uc/RzNMnJERzJUrCK1dS+3wYYSqYA+fQug6eB5GRzv22DjV/e9iT06hZTJE1q2tXxw43cpLkRJ2v0X2tVdRQiGM3p56wb58DmGaaC0taF1dFA8fJnTHHbinRvB9j9CyAaRtUzt6FHd6GrW/HylAGgZeZyfe6WOjzy9Q3rfvrNfJnZuF8XEYGroARyVwJRJCcDx3nGwtS3usHR8fgeDN6TfZ1LyJ/XP7UXyFXC3HSGUEx3dQhcqWxi3sntvNKxOvcG//vcSMGLPVWaaiU/SqvRd7twKBS96lfRYTOG9SpmCoJcb+yfxZ29d0JC6J3ouB80sIgSZ88H1ihZNw6kWc8hKa0FDe+RtYfg92uBVjy++ClYN4O9KuQMtqnJVfoaKliblZzMUDiFAYWavV08/1SD3gdqpgRCGUwu+7CTczRD7cS2xxDGYPnRmHlAK7YTnFhs1feHGuwOWnEukg2rIeLdOLeP0/1d9jAAKEXUYZfobGth2ooThG4otrYfZJhICINYdSnkMaMaxoJ86vfH06mkr79l5SnUnKcwUijTEi3Rm80OerEO6ZgkhvC9Nvz5/Z1tQdJ9yg8V4pMisaRbnrLlp6erBHRrFOnULRdRpuvx2pa9g33nh2DYULHHDrnodaLOImEriKcs7bWJ0dpL77HYoPP4KsVlFbWxCxGPbsHM7xY0j7/e8ppakRZ3oGRVWJ3nYr/tIS0nGIbd9O8YUXcY8fxy8U0JuaQAjUWIzQ4CD5xx5H7+hEzs+DIrCPnyCybRv26CiIel9utaEBJRbDGRk5HYD7uHNzSNumums39v79hL72NVxdR52eofDKywD4lQqiqalevXx+vt4JIhwmsnIF1WPHiQwM4Bw+TLivD/vESYT0iW5Yj7uwgCyVEOEwoc2bcD9wbGS1cs5j5Z++yBAIfB5lt8xC7f3ifbqiU/EqhLUwlm1hGAb7xvZxS/ctzJXneG36NcpOmT/a9Ef8+OiPOZY7BsAN7Tfw+6t/n0YaL9auBAKXhSDovkqo0uVb13QwlauyWLYRwPK2ODf2p5HyUlrZF/i8Ql4Bc2oXojABLcsIHXkMv5JFNq/GFyr+7H6YfAvZdg3V4gymX0PkJ/GX3YnXuQ2vuEA69xxi7FVEJYuMNiJibTBwC/LUy/Xeyk4FFB15Ol28pGXA93F6bkLLjoJ9+qTQjOH23BgE3IFzctCwln8Zs3jydGut028UKev1BRSNvrUZaoC8SI2ThBAk5t+Gw7+E05+VkdY1VAa/hCPMs27rRELoK9rIrOrA931cPnXHsI8kpSTWorDmljaqRRfdVAgllA+9Hr7vUxkcJBSPo3Z11meMGxuptrdftKKFiqJg7t9P/kc/xh4ZwVy5kvg3v0FtYOBDt5VCIHfsILlyJSwuQjIJ2RzVp59GTaVx5+YAUBMJfM/D3HYt2uAQ7tQk2po1qD091N58EzUWw1EUtIYG7LExEILQhg3YBw6CbeMnEyhNTYiFBbxiEXwfJZXCrVSI3Xgj1cOHkZVKvVe2oqCEQyi6jhqN4i4u4ieTMDsLnZ14C/Nn7UN1dJT49ddj9PUhNQ0RMrFOnMQbHqZ24CBmSzOLf/4XqOEwIhpFSJ/Q+vVIz0fv7UE53V9dCIHqOOipFKqi4Hs+SIlUFECitrQEbcQCvzYpJctTy4lqUWpuvVUYwIamDViuheVZVGSFifIEXxv8GoeXDjNZnCRuxsnWsvxi+Bc0hBrQhIYnPd5deJcXpl/gGx3fCJYqBgIfIwi6ryL9CfjjLy3n5KKFrgqGMgamEgTclzNFCOLWJFphAi+cphrrI3TsF2CXCKXb4KV/j6gsovoe/tIwDNwCqR6wCoAA38fCQA7eQ6H5WjLZdwj5RZR3/wYm3wYpEUYUWtYg13wdWc1D9iQkupCrv8pS83U4H/iOLYfaCF/zD9CKY4DATXRTVX+99NrA1UGxC8ilU7Dyfnj9T3h/NlsgB27BOPSXKMvupGw0XZTxhZwsHH38TMANwMwBQi1rcJIrz3mfL+LEUw35xEL1WeKPugDhKwqV9naUzs4vbByfRWh0lNk//t/xSyUAKm+8gTM+Tub/+2+oJT/cg91XFPzWVrRUClGpoCSTGP19uK6Datv4lTLRHTfhxeMoGzfixmKo8RhSVfGB2oEDqLEY0Vtvo/rKKwhdJ7RiOZWjRwkPDSG9entEPxxGX7YMMT6OSKUIbb+O+I4dVEdGMHwPd2QUNRZD7+6m/OKL+LUa9tgYseuvxxodPTP7rMQ+/NnmZJdwczlctz4zL5aW8Gs1RCKOOzOLomn1WXHHQXouzvQM4Z07KB88iCkUwrfdivvqqzijY3imQWLrtWR/9jP8bBalqZHElx/Aa29HLxSgUIBEor5cIBD4DLrNbv5w4x/y+MjjTJYmWdO4hrWNaxnJj1D1qtTcGploBtd32Tu3F1M1aYu1YSgGBxcPcn379eiqjoGBJjTenn2bb/d+G98Kgu5A4KMEQfdVJql5bGp577AHAfflTAhBZuZFxGv/BZwyilAxV38JW41jJFvqLbxy4xBvhuIMiu/BqRfx1jyI0EL4i2OgGtB9LbXmjaQLRzD2/BmkumH2YP3f3Dh4FnJ6H/TegN+4CtF7E7WmtRRDHR8qGgVQ1RKQXnMRXpHA5Uj4Lv7oaygDOxHX/08wsQu0EPTvQEZbYOQtNLeGtv4HuPLcqclfJLWWA99DT7WiKgJplfAqedzKAnw4brwkXOxg+z3O0aNnAu4z2yYnkcePwzXXnPM++vHjlJ59Fr9SQY3Hid96K96WLYhKBTUWx49GEYk4VKv4zz1H5eBBhKoS37EDxTRx5udRYzFEJoOWSlE7cRItk8FxHCJbrqFyagTpe/iJOKFbbyV87z146TSVp5+mevAgQtPQWprRU2lKTzwBuo5fLGL296Mkk6jJJLSc7r3e2YHR24c9curM+EVzM9Ebb6T89NO48wv1sd11J3Y2C9ksakszQlHrReMUgT0/h1kqgZT4pSLytddQPA9nbAx3chLp+TR+/zdx5ueRCKTjoL77LsUXXkC6LkLTiO7cib9uXdDdKfCpaWgsFhe5ue1mkqEkVadKwS6wPLWc2dIsHYkOXpp4iR2dO7B9m6ZwE5OlSaSUhLUwPj6u7xLVo3jSoyHcQN7JEyGorB8IfJQg6A4ELlMJaxrx+v8JzulUbunBu3+LsfP/hSjP1Vt6ZXrBqUGsBWp5hPQRTSspNG1G8WpIoWCpcZK1MYyX/g3MH0CEU+DZkJ+s36+yAGYcGWkENYQVasLWEkGf7cB5YUdaMWJtyNIcItoIbevrM4kLx1GMGFrfDbinXsGws7h6wwUfnxdOE2vsgoM/ry+taN+Esuw21FAMVUg8GbTL+ShCnPu1Eap6zu364iKFRx+t99gGvGKR/KOPEv/+93E6OnhvVbcQAvfNXVT37AHquRH5J58kuW0b+ddewy0UkLaNNTqC0dePH4uC6yC6uklcdx3e3BwiHK6niHsejI2hKipqIoFXKOAuLlJ9623C69YRXr4ce3ISe3oKgST2wJexjXoxSNcwMO69B3N8HL9QQG1owO/owNY0wt/5DqJYRFlYIP/440jHIdzTTe3AAZRIGMU0cbM5wuvWYS0toUYiRJpbKL30IvbRY5grVhC/+y6Kv3yU4sMPoaTShNetw6tWMJYN1gNuwyDc0Ii/dy9hw8RtyOA0NQXBd+CT+bCtZRsPn3qYglVva9gQaeD6luvRhMZIaYTGcCOWZxHX4qiKymRpEs/32NSyCc/zkFJScSq0RlrZ2LyRpdoSESMIugOBjxIE3YHAZUotToJd/MAWBeJNCLuCmHgLQknIjUGiDdAhqiNX3I8Vaa1XEFeN9+6FPrkbWZlDaCGk7yG08Ol12woYcUi0I/OT2NlpAEKxJsT636SqnjutUZcOodIYopbDjzZTiXbgX4RZysClz8bAWvcbGLNvwuP/AsJpEBpUF+HgI2hf/wvccROpXJyq94ZXg1MvIHy3fhFq7DXE5Fuoq75CavEEpYH7sUTovD+voiiEJifxxsdREgncwUGcjwhWL1XawAB6RwfO5OSZbaEVy2HZsnPe3p+dPRNwv0c6DnJuDj6QQq1VqxQPHviVO/tYc/MkH3wQ+9gxjBUrKb/2Gq6sP57e3o4yNIgdi0FzMwDm+AT2W7uRvsSdnEBVNZTGRjzHAekjHYfyzDReqYjW0EDsjjtY9Lyzipt5pnlmfz44cldVIZVCC4XQu7qxh09i5/Mk7roTZ2YW3/MwBgdRmppw5+aIDw1RePhhlESCyDWb0Ts6qbz2Gl6phF+poiRTlJ57jsSXv4QzMoKRyaAZBqVHf4m7lKWy+y3it96KvmEDdl/vZz1UgatQRsnwnWXfYbY2iyIUms1mDGmQMTIccA5QtIvsm9/HVwa/wuHFw5TsEk2RJtqj7TSEG2iPtxPVowwkBtgzuYctqS0Xe5cCgUtaEHQHApcpP5xBVXTw6/M/SigGkQbEsSdg/HUIp2DozvrabDOJHNiJH+/AU0zCskpsYS9KZR7irUi3ikQBRYeZ/cihuxBjb0C8FeLtkFmGP3cEoYaQUiBL8xjZ41QbN39oXLq0iRx/CGYPIhAIKUksu4VCx46goFrgnMpGE/Fa7nR1/Mr7VcztPORGoe8matrFaXOlFU6BVQLNgPIceE49E6Qyj750kkiyF6vp/J5sKoqCsWsXc//pP+Pl8yAEibvuIvyb36MWjZ7X5/oiWZ2dZH7/H1DbtQt7ZBRzaIjQjpuoxs9d50GEPuLihXn2dqkoKLqOZ1lnb/c93N5eRE8PDhBZtxY5O1tvRdbSgqO/X0k+srhE+dFHKb/yCtK2Ca1ejdbbiwhHcAyD2M23oHW0Uz54EL2zk8iOHRjNzTA9/ZleAzcUwrj/PkIzM8iahWhpRg2FEI4DCPzxMcKuR/nxx8E0UUIhik89TWznTqyjxzD6+7HKZYSo77e0Hdz5OcLtbeR++DdgWYhIBHyfxb/8S1ra2zB6urE/okp8IPBBpjTpNrvrP5z+eO0N9VJtrvLG1Btn1nQ3hZv4yuBXeGHsBR4feRxPeqTNNH9/zd/nrYm3uKnzJpJKMsiACwQ+RhB0BwKXqVKsj/S6b8I7f1Xf4DuIZBdy8u36rFxpHo48Cu2boe9GJCqemUSGkiQO/w2iNF1fu12cQmz8HiTbkbkJqOXg1Euw5ivIplVICfLV/4SQHnqqGzvcXP9yruXPOa5QcQR94o16Kq70keE07vDzhBpXUjGaL9jrE7jMhFL1gPuDhArRRkqpjRflZE7xfWTVrVfqrxYRlUXquSF+vbp6YQp95HnM5o1Y8vx9nYbmF5j/r39aD7gBpKTw+OOYa9bAjTect+f5onmahr9uHUZfHxHXxYnFqOof00KtsxO9rQ3nA4Gt0duLbGs9+3FNk/CWLZSef/79jUJgbtyI84GZciccht7eDz2N5ro4e/dSevpp/GoVXJfK668T9lxi93+JxO231auUA/Ft2/BDIZzPEcR6qorX0fErg6i/X5QVK6g99RSoKkZbG+WXX673qBMC6bq48/Po7e1Ix0ExDdR4nPCKlXhz83D6ooMSCiE0DaOhAfvIUbzxCYwt1+D29ASp5oHPTEdnfWQ9/3LLv2Tv/F6OZ4+zsmElBxYOsLllM6lQipge4/ae22lQGtgwuIGUkgoC7kDgEwRBdyBwmXJ9yA9+jXjzKpTcCEIRYJcQp148fdKmgPRh8Rgy04vs2IrVtJ7E7JuIk8/AwlFI9SD7diCOPo5cfi805ZDl+uw33ddTO/ocSjSDFkpANQv5STQzjSt0/ETHOccVKo4isqcQmon0Pagsoqf7cGs5MJpxULBciOnUxxcIAH7rBtT+nTD8wvsbt/4u1cZ1eO7FSatWT42QOzpHU2YIMfF6vcCbW4PGQagsIQVIRcXIn8JKDJ6355Uz07izsx/a7gwPI2668ZI9ufVtlcqSi2P5GCEF1VQIpcCOx7E/xf1dwyD85S9jHj+BNzeH2taKWLYMVzv7VEVKCevWEQ+FsA4cRJgG5vr1uD09n2qcylIWZ2ICWavVW6sB+D7Vt/eQfPDrVFOpM7f1wmHg87d++yhCCLyFRfT+Pqy33sav1VAiEWonThC76SYq776L2tSIPTuLNrAMpbUFv1rFaGxE6+hA6BrCMMHzcJeWAIlfKuHs3o0+PQ09PXgtLfjBzHfgM5BSMqgNsrxzOcXOIsfzx/HSHjk7x+3dtzOYGKRNabtkP4sCgUtREHQHApepkFfAWDiEW5hCpLpQhI14528g0QmlObCKYMaQ8Q7chuXY7duIzLyF2PPn9ZRdpwaLxxHFGWT3NqRm4Dcsw+/ejjSTyMoCWEV8p4ocvAtx7LHTs9sSeq+nGu//0Jji9iyKW0VYOSgWEUYMGWvDrywhIhkOLvn8cv8UubLLqvY4d6/M0GgGX9oBmNM7ad7xr1GW31MPaJOduC0bKLgXZy23EAL7xHFqR0bQr91Oan0/IjdcT333LOToq8j2zYimISKlEXRNpRDtwZWf/wKBSKVR4nH8YvGs7VpbK84lepLrlBSOvDpNbrpGreJiRjR61zYQiqu0LA+fOTlXpUQfG8cvFVE6OrDS6bNO3J1IBNavqwejH7OvnqrCypUYa9YgpTxrhvuTSEWArqM1NeFMTZ3ZrmYyiJD5Mfc8/zzPw1i9ivIrrxC7bhtaUxOyWkFJplDSaZLLhxBNTcSjUZTubqSuU/ov/wVFCIzeXuyREfxSGWlb6F1deMUiMpendOQISiaD0tdH+PrtqNu24V0iVe0Dlw/f84kSZWN8I6vjqzFUA7x6UB4E3IHAZxME3YHAZciUNcz9fwOF+gmjNrMHxbeQvTcii1Ow7puI0hxEm/B7tlNNLid88gmUhaPIWh5hl8GMglUGuwR6GBBQXcIb24OUPnoohNI8hDt3DGfhFOrA7ShGGKdnJyWz9UPrs8NuDn3sNZh6E1pWw6mXwc0iXAex/Q/ZV87wx48dY6FUT4k8PFNksWTzj25oQ/+IvsOBq8uc3gVdXRd7GGco4Xol3tybh6i1NZDZtAPDGkZQQ3ZtA9VAeeeH4FYxPIfG9d+iNPglSuLz9RKzOjvIfPe7LPzX/3pmHbu5YgXapk1nKnhfSoRQmDySo1b0qFXqM8dWxSU/W6WQlaTbw+gx0Gs1nJ/9nPxLLyEtCzWRIPN7v0tt9eoPPeanPaH3vM/e+tJvaEBfNoD/xBPoXV319l2qQuy22y/KRQ2xfDmRchn/1Eg9Zd73QVXR+/uJ338/3o6bsE+PSwDRW24h/5f/D8k770DNZFBjMbxSCXdpCb2lFVmuENmwAd910dJp/LfehslJtJUrkQMDeB+X4h8InIOUEh0d6QaBdiDw6wqC7kDgMmQUR6FQb2Fj2ksIqwhLJxBaCApTSKuE79ZQEdQya1GK04jh5+tVyK0yIt4KhWnQTxcoal5VT00feRVd0fHDjXg1D01MIqKNyPICXnkJu/8blIxWzrVQUCtOIJwCLJ2op5WvuLfexkyPILUIb0+WzwTcABXb5c2RLA9ubKXz8qkNFbhKSCnRVyxHvLMX6brUpheZebZM823LYektTKWIcvxxRGkW6dn1GfCX/h1RRcUb+ApVEf61n9uTEnHH7bR2d+GOjiHicdQ1q6lmMudxD88f6QlKWQvfO/uDoZi1aOqNYtc89JiCdvQo1uIikcFB1IYGnHyOwt89RLy3F+sCFojzhEBdv570936D2jvv4NcsjIF+XE1DbT/3spkvkmsYmCtWkH/4EYz+fvxarV61vVrFzS6hF4v1quvUP3rl9u00tLfjnzqF9fIraOk0QlPRkkkKjz1WXxPvuiS/+U2qb7yBPT5OaN1a/FOniGzajNi5I1jrHfhYjupwrHyM+do8reFW+sP9GP7FyToKBK4UQdAdCFyGhFvD8KuobgWRPQXShVgz4MHs/vpthArbfp+KGiNamkZqEaRnIfQovpVHyfRCKIVM9+Kn++HwL5HlBQCU6iKycSWObSGv+S6e6+FEWrDEx6ReChUkSCkQ0oeTzwMS0r34g/egVgVhXaXqvD8zla86BBfOA5cqt6WF+De+iXPoEH6xgLF8OeWBZZg9azDn94Jmvh9wnybmDhPJrKCa2fT5nlvTcNesgTVrPu9ufOEUVRJvCFErnj3rnGgM4dRcQlENY2mB3F//kNr+/YRWrkRaFtKyEIqCMjKCOJ0mfqHYoRDazp2Ee3pwJqcQ0SjmiuU48dgFG8MH+YUivlXDW8q+v9GykIUi8ldaxfmKgtXfj9HQgHLwIO6JE0Q2bqL2zl6EroPnocRjeAsLyGoVNRZDb21FmiaVfe+Q2LABJ/X5sjECV66iKPLQyEM8NfoUqlDxfI/bem/jW13fwuTCLr8IBK4kQdAdCFxmTL+CWZ1HzZ1ClGbq1cYBMsugcQhOvYLQI8ihO2HdN/BsgQylcLUoenkRurchrAJ+aQ65+qt4bevxjj2Prn9gZs61UewSfrKJqtmEbX7yFW4n2YM2tRsl1YtcPI5I9yIUHbnum+iFcX7HfYcHb+riqVIP/26XjZRwbV+G9rgG8lJMmg1c7aSUOK0tiLZWNCFwT6+JddUWjEQPpu+9H3ArGggDqScRVhEhxFWz5tGXPh3Lk5SWLJyqSSlvEYkbJJpCJFtMtIjE3X0Av1RCa2xEiUYpv/46QtfRu7rI/fgnJONxat3dF3TcrmHA8uUoK1fi+/7FXeSSSqI1t+Bls2dlEunLBnAjkXO2y3NSKaI7dlCenUM6Du7cPFpLC3pXF+7CArJSwRgaQqgKtf370RobiW6+Bjz3Au5Y4HIihOBI8Qi7Z3ejCAXbt0maSfbO7WVz02bWhC79i4CBwKUqCLoDgcuIEILQ7Nso84dg/Tdgz1/VT/rjrdC1BSbehtv+F/xII74nUeaPEot0YqUGCCU7sYVAq5UQioG6/Q9g7C20gz9FizTB0F34MwfBLtSfS0r8wduxOXfALYRAUZQzayprIoIyeC8i0486fwCZn4Lld6Ds/1tYOIZWWaJBNfjGmm9g7vwqb85q3LOmGSMIuAOXuHMVDSolhzCW341YPA7CwLc8ZNMQ7mKFaq2Cmq7iflTf6SuQFvVZvbOFSs7Fd0APKWhhgRryEULgLyyiRCKYAwP13tiWhbRtpONALoe9ezdqXx9SSvwLXPDrQj/fubjJJJEvfQn5kI83O4t0XeK33w4bP7pdnpQSb/16kg0NqEtZKrt3YU9NoaXTaJk0+tAg9omTlF97DSUcxltcwpmZpXHjBpyGhgu8h4HLgoCqW2W6PE3ZKeNLn7yVpyPeQc7OwdXzkRYInHdB0B0IXEY0PMzSBMqpl6BnG7SugaE7wPdg9HWY2QeNy1CMGBx9HHyXkJHAuOlfUl73PYzsCTyniG6GYdefIqberq8DnzuMLEzAlh/A/DHwXdzBuyglVnxo/bYQgkzpKNroy5CfwO/YTLnjJipqgoreQLXtRpSOHQggM/EUzB2C0iwCUN0qyp6/4IEvbaG34zp6EuKSOOENBD4rR6pkV3yXdKoHeeot/KqF54WozEoKLz5HTMThhsunp/Z5oXlEGt9rriV578PD933Mvl4Kf/3XmEOD9Z7TkXC9UJ3rIl0XISXqc8/hLC6h9fbCqpVX1UULKSXuqpXE2tshu4SIxXEbG3DExzcrk0Cts5NQIkH8jjspPP44SjSKWy6haDru3Fy9En6lgpZOY/T24E9MEA6FcDUNv6mpXgk+EAAUoSCFxHItPFm/oO5Kl/HiOAkzcZFHFwhc3oKgOxC4jJjWPMqhn0Osqd7jWij1KuHleWhcBlt/r95PuzQHVgl0EyqLKPv+BvW6f04xs5ZUdQRl7h0IxcBMIK0iQjMRhUlEfgIbDX/oborxZeecYWkoHUV9/J9DaQYA5djjxNd8Deeaf44j6ym1781+C6sI5bl6j1shQEqEdNELo/S0bA8C7sBlzcZgKbUdf3IKpbxAbXQWe76AW6xQfPIpkhs3nimAdbXzEwmiN96APTFBaNUqrKNHEKEQzuQkwjTRMg3kfvg3KJkMoXIZb2Ya/e678T4h6LzSOKkk/Brrra1kEmVwkKgi0MJhvPkFRCyKX6uiRKMokTDRG27AHhtj6c//AiUcJnzD9dDQiL5zR71VW+Cq53keBavATV038fz487i+i0CwrXUbmghChkDg8wj+ggKBy4hSGIdwGsw4OBWYOQhLx+vB93QZzCR4NlIPI8UHZi8KU5hOlvDsbtRDDyHcCmLmEHLwdph8G1ldqhdVS3ZS7rgFB+2cawhV4aNO7T4TcAP14P/IL4mt/CrZyMBZt5epHhShAh54dn1jpAGkT6p4lKXo4BfwKgUCF47Udey5IpVd+87arsai+NPTMHh1vMeFEGilEhQKEIvjJuJnXbSTUuJGo6R37sSdmkZtaqL29ttobW2E162j+s47eLaNffAg1smTJL/+dZS5ObyWlou4V5cPKSVy7Rq0eAx3fBytsYHya69jdPdQeflljNWrsU4OUzt4EL21FS+Xo/jsc8TvuRtx6hSaaSJtG6W1Fbeh4aqpRxD4sPZYOz899lNuaK9n6qhCxVRNNBmEDIHA5xH8BQUClxGphpBaCIwYwilDYQxiLaCFwS4h549Az/VIzzkrK1wM3Y4+/ir+vp+AW0GoOkQbEEd+gRy6G3HyWWS8lWrj2nrA/RE06dRn0H+VZ6M41Q9tzqXXkbn+HyPe/NN60B1vh5X3ISsLqMPPoqxfHsx2By5rrqoSvm4bld27379QpWkYQ0P4tdrFHdwFpB4+QvHZZ+oVyQ2D6I6d+GvXnPkcEu3thFpaqB48RPGhhwAwB/pRMg0UX3iBUH8/WiqJt7iIrNWQpWJ9vXfgU/NVFX9gAGVwEOm6JFavRszMYHR1AlB68SWMzg6c2TnwPITvI7M5Kk88iasoSFnvD5740pdw+vou8t4ELpah+BB39d3FgYUDFOwC3Ylu+pJ9tIXaztkuNBAIfDpB0B0IXEacZD9Osh/Dr4AjwK4CAsiDUJDxVui9Ef/gI+/fqWk5opbHlxKkjxAKsrKISPdCqgfMKGLZ7bgbv0851H7OGe4zzy9CyIZl9XZk8gPtgRoGqCU/fJJmSxVr4G5MIwbFaZAS6Xn4Y29A4yCKEBe3YnAgcB7INWtIff1B7JERhKqhNjVSm58ndvPNV8X7W89mKTz5BJxeViJtm9IzT5NobcFpagLAiUQwOjspPfY4ofXrqO5+i+rBQyjhMFoqidbcTPXYMQCEoiDMEJy+bwA0x4GZGfAltDR/7Hp33/dBUfB6e1F7exETEwgJemcn1qFDyEoFoevIahUhfbxcDjJpEALXlWSfeZ7UD7pxg7XeV6W4F+f2jttpi7RRsAuEtTDr0+uJy/jFHlogcFkLgu5A4DJSUyKI9b+FOrcHFQcxexBqOWQ4jZ/qxc0MUmrcjHnDSsy5feAU8JJ9+MefgkgDCiA9G6GayOIsNAwge3dgl3NYWvITUwp9Kak2bSBy4z+Fd/4aCtPQsRnvuj+gTPSc9ykZzWjZMciO1iut58cBBb9zK14wyx24Aji6jrF9O6phYI+OIn1J7L77cNPpiz20C0IuLJwJuN/fKPHn588KnJ1aDS8aQY/GMNeto7L/AIqmE7vlVqqHDtVrPigKWkc75nXXUTODnsAAeqFA5eFHcOfnQAjURILoAw98qgrkHmDecSf+m28SWrkCb3EBe2KynkqeTKLG4gjLwt33LnYyw6weZXokS/TgLN2DnbSGg8/oq1EjjdycuRkbGx09mOEOBM6DIOgOBC4zVS1Ftf0WVFUlef8qlOFn8YqLyMZB7K4bsDGxVZNS+820tbWRn50l3jAO2WGU9k0w9irSq9bXcDeuxJ7cj6zm8Lt3fKrnL2oNOP0PEGnbiuLXqMa6KcvwR97e8QX2qm9ivP1/wewhCCWh9wYqHTcG6wYDVww7lULcdhsRx8HXdRyoB5FXQSEwEY2iINEMgRKNY5ctfNtGRM++EKe1tKB4LpXxadxcmdD2mxCGjujpJ2QYODPTqOkMoR03YfX2fmzWzdVCCIHzzjt409OQy+EXChAJ4zz/AsqDX/vETAohBPaePVSPHiGxejXhTZsxenpREnGM3j68bBZvaQmnXKGYKxNOJEn3LueFmRq7yjP8w+1tKNL7hGcJXImklPWAOxAInBdB0B0IXKY8z2PJ7EJd/fdQpIOHXk8h/xW+72N3XouxeBQ32o6+/tuI8hyyeTV2dgpZnEUsu5Wanv7UJ7k1dGrhnvoPn+Iu+VAH5vX/C2ZlGqloVMMtuDJIXQxcWSTg6lffSarREKLxuj7E5C5EeR+yezl261bc9vYztzGljakU8FuSlGdGUBMx3FyO8K23M6e0kPnqjYRkFanrWKc7HQRAAayTw3gTE/WAG/BLJSqvvELm1luppVMfe38tl6Ow7x3wPKQQlF56CaEooChYhw4RWrcOraWF6tw8IdfH9SNkbryeydk8cwsWMxtaaf/oa6qBQCAQ+JSCoDsQuMx5vsRD4+Oi34regL/599ALY7i+hxJrROYnUPQk/sDtVBL9X/iss4WOFemu/xCcTwcCVwRVQGj+bZTs4/huCSlcRGU/htTI6/XsGc1xEM88wuIjP0R2ryOy4w70eAIyCUZq3czMecSqHiJhXOS9ufRIIdDTaaqnA+73qJk0/uICfELQjeOcSf2vjI2R+uY3KD3/AkokjNHZhTs3h1/IE7/xBmQoQhWFXUs1ZMVHMxT0qyBTIxAIBC6EIOgOBK4SNRGhllzx/obGS68Vz6IFw4s1HE/SnQ7RGVeCGa9A4BKmeyWU3AiUplAUICQACdNvEa5M4UR60E+epPDEQ1TMHvREB4uPPIU3N0dk9RChVAc9O+7HjJ5uLRg4i+/7hNauRXnmGfxSvXOECJmE1q3DK52jk8Sv3j+TQW9pxZmdwV1YQPT0oHa0E123DuvIEcpv7gLLwjt+Ei8cRbtuO6fKEssX3N4TpWviGE5vD54WnC4G3ieEYM6dY7oyjaEadEW6iH5EXZdAIFAXfIoGAoFLwlwVfrh7Asutr1IUwJfWt7OiIfiYCgQuVb5igvLBv9H32qaFkb6LoijYo6M4oRaqJQV9YQ53dgYpwSrUQC+TnDmAULuCBJiP4HZ1Erv7LvxcDgARDlOdmCC+ffsnXqbwFIXIPXdTfeZZ7IlxSocPk/7Wt6g++xzVQ4dJ3HkH1QMHUbNZtJUr0XbejFwK87X2FFsrk3iHJgn5HtaKFbiXQOHLWCyG4zhYlnWxh3JVO149zo9O/oiCXUBXdDqiHXx32XdJkrzYQwsELlnB2WwgELjohBC8M1k4E3BD/dT9hWPzDFzXgX5VNF4KBC4/Njp+xzUohx8Bz65vFAoyswwn2oaUEiUSwSWK0RTFHhtGvFdgzgijmSre7Dim6+IGs6nn5BoGxtatVJ5/HmdyEjWRJH7XXbgtLZ8qE8hOpzEe/BqhYglMg2oohDK4DPXwIUqvvIre1YnR3Y1XLpGM6PzDqSNUfrQLPR6n5vs483OEXQ931coLsLfntuQZvH6qwBunJkiFDXYMNXF9VygIvi8CR3H4ycmfsHduL/L0pbKZygyrGlZxc+bmDy1Vy4s8hwuHsTyLZYlldCgdF2PYgcBFF3zDBQKBi05RFOaLZ588fWtLL40RAZ6EoOZaIHDJyqXXkbrlf0E58jCUlpAtq6kNfZmaiICUKMuXYx4fpXp0jFhrO+78IlpbO1URJqEK1KYm/CDg/lh2UxPm179OuFxGmiaOrn+mpTeeEHiJ032WpURZswbl0GHMWBxZqeD7Psn77iP3d3+H0dGBFo1SPXgQoap4b7+NrNYIrViOpShf0B5+NNM0+cWbc/zXl4bPbHt8/wz/9sG1bG4K1pxfaIv+IvsW9hE34hiqgS99ClaBE/kT3NZ0G67rnrntjD/Df3jnP3Aqfwofn4gW4V9s/hesj6y/iHsQCFwcwbdcIBC46DzPY2VrnIlshc2dKX4jvQ+x5z9DaRa57Fb8/h3M6X0Xe5iBwHkjFBUfFUU6l33rPM+XLKY3om9fh+rWcLQInnw/GHJaWoh/6X6cPScxVRsXjWoN9IiOGjMJX3cd9kUc/+XCEwIvFjsvj+Ukk0S+8x3k+BjSslHaWpGJBObEBMKXlJ59Fk4XUdPa2ii/8QaxO+/AGRy84HlHJ/MeP9o1fta2iuPx+skltne2B7PdF5jjOqxtXMv+hf3k7BwqKg3hBlqjrWd9limKwqtTrzKcHz4zI15za/z1kb9maMsQYS8oix+4ugRBdyAQuCSsbA4xnU/x3YaDiIf+ELz6iZSYfAu1OE3qhv83uVpwchW4vAkhOJmXPH9sjrGlCms7kuxYlqbJvPyLiDlSxVGjH+pOIKXEbkwSu3UL5UWHUP9yEtkZtBAonR3YicTFGfBVzolGYEW9uKZH/b2p9w9Qe/WVesAtJVpnJ5GtWxCGgZ/Nog8PY/X3X9hx+lCynA9tL9bqNQMCF1ZCS7AstYyT+ZOUq2WkkLREWuiN9+J573+OqarKyfxJJBJNaGiqhuM7jJfHmXPm6FF6LuJeBAIXXhB0BwKBS0JYlTywthGx680zAfcZ+36MufIBiF68NYWBwPkwVRb8+6ePka3Ug4hjs0WOzxX5Zzt7MIT7Cfe+zKke0WYFSENfGo+gXvn5pHoeYnoaWSqhNDbiNjZ+puJ0UkpkyERNpUHT0Ds7MYeGKDz8CELXqe7ZQ+KuuzAGBrAvYHZGT1LntlUtPHlw9qzt1/ZlqFarF2wcgbqKU+GVyVfojnezPLMcFZW56hy5Wg5C79/OdV1WZFbw5sybqKrKUm0JiWRNwxqeGHmCmztvZsgYumj7EQhcaEHQHQgELhmapiJ+NeAG8B2Qwel54PJ3dL5yJuCu1+iHdyfyDOccVqSD9amBX49m29hPPYV17Fh9g6IQu/U2/HVrP9vyhaYmLNcl+fUHwZfkf/ITUBT09nbcuXlyP/oxTatXYw8OfjE7cg6KU+V713ahqwrPHJ4hHTH57rU9bO2JAUH204XmCAfbtRkpjOD4DopQ0IWO9yvf0VJKtjZv5cDCAV6feR2JpCncxK3dt/GXB3+IEAqrBledtQY8ELiSBUF3IBC4ZFSrVZJdWxF7/8fZRYKW34ObWUWw8DNwuXM9CQhcCY7nIxDoqsA7vT0Q+LWMjb0fcAP4PuUXnife043zGdL3vZYWzBXLsd7eQ7SnG62tDcUw8LJZZK2G73l4k5NwAYNugP6Yx/98Vy/f3dpFWFNoC7t457pAG/jCRUWUVU2reGnipTPbMmaGuBH/0G1bRSu/u/Z3WdW4Csuz8SX85f6fUrRcxgszeKoHQcwduEoEQXcgELik1Fq2Ebr73yHe/h9QnofBO/BXf41FO1i7F7j8DTZH8BFkKzaO6yOBFa1xGhMhgqtKgV+Xn81+aJt0HCgU4TME3b6ioFx/PYm2dvyxUWS1ipPNIiuV+mO6Ln7NwiyVsM5TUbdPPbZajZ5I/f9ekPh00SSMBCkjxW3dt7FQXSBhJDBVk7JdRokr+L/Sz71FaWEsP83TIy+TCqXY3LoeVZFsbtnMcHGRfrPhsi8mGQh8GkHQHQgELik5wtB5L01dNyDcAjWzj0KQfha4QrTHNH77hj5++vY4Y0tV1nUk2diT4tXhJb62Mh6cfAZ+LUo6/aFtQtch+dmL1PmKgtPXi1iYJ3rDDRQeeeTM7xL33kvl0CGinR2wZs3nGnPg8iR9SVOoibHiGK7nYjkWffE+Zkoz0Pjh23uuxy0d9+FIF4TLKxPPkw6nyVpLbGurYse7WRFeEXz2Ba54QdAdCAQuSfMyCWoSgoA7cAXJ2ZK/fWuMrnSEzd1pjs0W+dOXTrG+M8mD6xuRVu1iDzFwOerpIbR8BbWjR+o/KwrRm2/GTSQ+Uz/v93iqir52LWFdR29rw69UUJNJaqOj2AcOENm54zzvQOByYWIS1+KovsrazFocz2EkO8LN3Tfje+duKBdRImxu2spDp35Eb7KXpVqWdxfeZao0xe+s/R3K4TIRIhd4TwKBCysIuq9UqsF40SekK7SGvLPaOAQCgUDg4ogYGoau8cShOQDWdcT5V3evIB7SyFYlyWAVReDX4Oo62p13EF+/Dlku16uXN3y+tF0nGkXt7aX4//wV3tJSPcXc99F7uhGOg16p4ESCQOlqI6XkmoZrUBSFql9lsbbIUPMQ6UgaoQik/+H3XMGdYKY6wXhhgopbor6wRjJTnSZnL1HxKkSU4L0UuLIFQfcVaKSk8t9fP8VLx+dJhnW+u62H+1akCF3p7WgCgUDgEvfGqTw3Lmtk/0Seb17Tia6p/Kdnj+P5kq29aX5rew/9seAiaeCz8zQNOjvr/z9Pj1lraCD1j/+Q0l//EHdsDEIm5oqVZP/2p6QcF3HjDUFa8FUoKqIg4CfHfkLBLuD5Hk2RJv7B2n/A2shaUMCVLgYG8/48Rb9AWNe5sfMG5qvz5GpZNEVDIDBVEzc4Pw1cBYKg+wrjKzp//topXjg2D8Bi2eb/eO44jbE17OzSL/LoAoFA4OolVYODM/Nkojr/25dXI5D8h6ePU7U9bM/npeML6JrK/3xHL8INKjMHLg1eZyfhrVuwGzIY/QMouobR24u/tIjuONhacCp5tcn7eZ4cffJM722A2cos+xb2oTQpnFo6RUOsgYpXYb46z765fVi+Tba2RGO4ke5EN0eWjrCheQOL1UVqsVoQkQSueEEi2xVmtODx0vEFAAabYvz9G/v5wfZ+ALKeiRBBS5rA5UERAk2RKErwMRW4MlRdyTXdaRwPXjm+wOvDS9yxqpWGqIYvwfYkTx+aYTgXzHQHLiGmiXXyJOGVK3FPDZP76x9S/MUv8HM5tJMnL/boAhdBza+RtbNnAu73SCSPn3ocM2TyJ/v+hL1ze/nh4R9yIneCqB4hFUpRsAt0xjtZ3bCaqlNl98xuxspjF2lPAoELJ7iudIUxVIWYqWFoCpt7MxyZKeL5kqcOzdDbGOUb13SxMq1gKOcudhEIXAoi9jyxxQMolUXQDZz2LSxqbRd7WIHA5+L5ksOzRf781REMVaE9FWapZPGVTR08dWiW+aJFdzqC60l8VJTzliQcCPz6XCmJ3347hb/9W8rPPV8vzKZp2KOjICHU1UUtWNt9VUlpKTqjnUyXps8E3qpQiRtxGhsbeXT4UTzp4UsfV7pIT1JxKsxX5slaWcYL47w48SKKULij9w5O5k9yc+bmoP5Q4IoWBN1XmJ44fGtLF4tlm+H5EvMlm+NzJXRVULY9Hts/RWRjO8vSGlKozBQsVCFpiqgoBIF44OJr9GbRh5+A6iJMvg2qgTH9Ls3rvs1ceOBiDy8Q+LXNV32eOTQHEhpjBoqAku2ydzyHrgpWtMZZ15Hkz189xaqWEHesbKYtiGUCF5nmujhjYzjDp85UQtcyGULr16OGw6jT04hly36ttd1SKFRdCKkiuMh0GTGkwbeHvk3WynI8dxxd0dnRuYN0KI2QgpnKDAKB7dlE9Sg1t4bt20gkCkp9PffpzEtf+mRCmQ/19w4ErjRB0H2FcV2XL61p5MBslYrtsWskS8xU2TnUzESuyon5MsfmKxyckbx+coHWZJiVLRGihsLWzihmMAMeuIgURUE78QwsHYcDP3v/F9UsqhEhvPWfUHWCJRKBy5OqKBRrDqoi8HwYXazQmYoQ1VXWLmtEICjVHHRVcHSuyvDiON/f1kVXTEEPPpsDF4mYX8DN5xGhEKgqRk8Pekc7pRdfxDpyBO2dvSS//g2qGzd8+scEstkqLxxZYKxok8jE2THYSH9KDQqzXSZ6tB7+183/KyfLJ1FVlWwlS87OMV4YZyg9xOHFwxzPHWdn505enXqViBZhSS5xV+9d7J3fiyc9DMUgbsTZ3LQ5OO6BK14QdF+BEqrDhhaT/ZM6UkquG2jk2SNz1ByPvoYIe8Zy7B5ZQvqSsK6yd8JDVwV5S7KjN0bCCD74AhdHgzOFGHsTrOLZv6guweRbxCoTVPWuizO4QOBz6k+p3LmmlUfemaLqeLi+ZDpf5fplDRybLXF0psiD13Rycr5EvmoD8PpwlsNhhbuG0qgiCLwDF4Gm4VSrGIODOFNTmIODFJ96ChEOo3d1oWYy1HbvIt7aQrHtk5cBOVNz+FMz/PhElaViFb9cptrczM+LNb63rZvm8AXYp8B5EfEjrA2vZW9xL29NvYWpmrQl2ljVtIq8lSdby3Jw/iDfWv4t+pJ9zJRmeGbsGaJ6lHWN67i562ZWZlbSKTov9q4EAl+4IOi+QkVUj51DjbwxvARA1fFIhDRWtifYPZJlsWRz95pW9o5lWao4dGciHJ0tsXc8zPev66bJC07uAheB9MC1QP2VjyYJqCZSCSrwBy5fnm3x5XWtALw9kkURcN1AA5brUbE9+pqilGvOmYAbQFUEBybzrO9I0BkLsjwCF57X2ICSTKKEwyQffBAvn0drbye8aSPewiKlJ54ARUHoOuGvfY1qIvGRj1Xaf4z5v/kR5YGVjJ8oo4bDhNpbcedmURJxJnIWzWHzAu5d4PPyFZ93598FwPIsRrIjZMtZfrDqB4S1MKYw6Qp1UchNUDm8m29GrqGYNjgqZxgtjHJn650QdAwLXAWCoPsKtjwp+f/cv5IXjy9yMBnC1BWSEZ1CzSFqqrQmTQo1FwH4UjKyUCZfdTgwVeLgVImBTIjulEpIBOusAhdGIdpPumU1wndg4m3wLFB1SPcgu68lb3RAUGglcBnrjrj80Y3tHF/Tyr6JHI+8M8VUrsaKtjg7hprYPbxw5rYDzTGqtgNA0XIhFlx0Clx4vhAYt92Gf/gw7vgE4Y527OGT+PkClddfR4lGASi/uQsllUa/714c/cPvVWm5DD/yOCmrhnJ6/a5XreJbFkJRkDULVQkuLF1uBAJDMc7alrfzHJo/xHf6v4PwBVq+hPfzF+iaG2GiNIHwLO780rdIbLsB1VUv0sgDgQsrCLqvcD0xn2WNEdqSIeaKFntHs9y9ugXXh1zF5dq+BnRNcHK2SFsyRNFy2XVqiZeOzdOeCvGdrZ3c0h8nFKwnDFwAlmXhrfwS6snnEJu+B3NHwExA1xa8jutwgoA7cAXwHZuBGDQMZmhJhLFcj6GmCHHVI2kqvHpykY50mIgmGF8qowhojhpAsPQncHG4oRBs3Ih+zTWoC4uYR49RfuEFlEgEv1JBa23BGRuj+NhjJNIp1J07P1QWzS2VKS/lias6ieHD9HdsYnhyCa9qoYcNQtEwPWmT4H1+eRG+YHPLZh4/9fhZ269pvgbhny6Wdvw4/tISDVqGdDqNj4+xZ4rYughOsJwgcJUIgu4rnPR9FAGbe9O8dmKRVETD0FTeHl6ityFCIqwR1lXuWdfGi8fmmStaVB0P2/Mp1FyePDDL8qYoA8mLvSeBq8W80Yu54fdJVkYR+Pi+S9looyKDWb7AlSWl2lzfrgIq7+VX3jYQoz1p8tTBaRZdH10V3LqihYYwQSwSuOg8z6OSTpG4717cmRmciQlkrYaXyyFtGxGLUnrpZZKDg3gdHWfd10gmSHa0kp2Zo6WwyM2Nk3QM9TAWbaSzJcWWLYOkgpoyl6VlkWXc138f7y68i0SyrnEd/eF+kCCEYCFSY2pLA6ZUaMvpaCem8KtVqFYhHETdgatDEHRfBRojKjPZKp3pMF3pMD96a5x1HSks1+eN4SVqjk9b0uTm5c0MNMX45bszCMB2faYLFiXLo35SGAhcGJZlMafW176iEgQbgauH9FnVoNK+rYtCzSMZVkkZBJV9A5eUUmfn/5+9/4yy9LrvO9/vfuLJqU6dyl1VnRO6kUEkChQDKIkUk6xg2ZKXl0XLHN97HWe0PHrh0ZLWjLxmmWuWZyxpzaU9vrYsW5ZEUxIJBokiRRIgiNAIndCpunI+OT5p3xen0WADDRChu6ur+//B6oU6zwm1n3pO+j177/8m/ZM/wca/+T8JlpbANDGyWdwDB2h+/2l0s/mG+2hLsfMzH+PUv/sD1hggv7rMg4UUH/+x+4gGBwhkaPm2ZWiDXbFd7J3cC/RPzrz6uX2xdZIvL3+J9sx5QFPKjvLJ/Q8RW+mg32L+vxC3Ggndt4GRtMVdkzn+6PlF/EjT7IakYjbfObtOzw8ZTLu4tsmLCzUsQ+GHEamYRTcI2ZlKkE9I4BZCiBsp52hyjgFoJG+Lm00URXTvvZfi/+f/TeMrT4DWmKVB2idO4u7aBQMDV71fbHKUI//sf6C9uIwZj5EcH8YzJWzfKsLXTQHzDZ+vnvlTFqJNnLRNWKng1RY4N9jkwY/+JD1LYoi4fciz/TaQMCPeP5UGxnl+rsrkQJxIR4SRJtTghZqYZdLqBTy6p8jLi7XL1c5//r4JxpIGIHO6hRBCCNGnAe/oUeL1OvWvfpXO0zO4e/eS+uhH8d8kdAOY6Rjp/dOXH0PcujpRk+OrL9JpV4nFE2TTI7QizeKgiTE+KF8txW1FQvdtIm4E3Due4qWFKh85OEy55RGEEWnXYmogQc8PCSON1pqfv2+ChGNyZDzD/ryCSN4VhRBCCHGl0DTRjz1G/uBBaDSI8nn8QkHCtAAg1CFJO0VLl2l5Ddp+E4UibsUJtUQQcXsxtroB4sYZcAJ+8b5RLKXZMZDgU3eNcWQ8y1y5zUK1w0cODRFpGMvHefzwMAdySOAWQgghxJuKgG6pRHfXLjwJ3OKH+ES8b8ejJGI5lOGgNewq7GE8PYGnZVqBuL3IaabbzGg84pfuHsA0TbpBgW9fbHB4NEMyZrFcbbO3lOGxySSTI1mWl9tb3VwhhBBCCLENKS8g4Wb4sdH34/ldbNNBG1AoTG1104S44SR034aiKCKKIkzgg1MxZgdiLNa63DEyyM6siWPIWshCCCGEEOLdC1cWSf/Vs+iJHKtmi2xsgEO7H8Yw3K1umhA3nITu25zWmh0p2JF69Q0wAmTIjxBCCCGEeHcsR7H27a+z8dxTqGMm47kiXqdJ7XCVqV/+51JFT9x2JHQLIYQQQgghrpnQa9OdnwOl0FFIq7wKQG9+DjOMiKSqlLjNyFNeCCGEEEIIcc0oI8HInjv7PdpKXf43uvculJXY6uYJccNJT7cQQgghhBDimokizdAHf4qHzRid8jqRZRJFIUMf+CihrIwjbkMSuoUQQgghhBDXjGEY5OYvok+fxe0EgCZ97104mQG6W904IbaADC8XQgghhBBCXDPx2iqNP/0SLC5jzM1gbazhff97mOdObXXThNgS0tMthBBCCCGEuHY2NvDOzxN12gBE3Q5hvU64ugEHt7htQmwB6ekWQgghhBBCXDMaB/26uds68MFJblGLhNhaErqFEEIIIYQQ14xvx0h96CdAvRY13H2HoDi8ha0SYuvI8HIhhBBCCCHENaOLA3hOgvTP/RK6XkO5MULLIRyS0C1uT9LTLYQQQgghhLhmgliM+OOPEzgxuh0P33JxHn4YP5fd6qYJsSWkp1sIIYQQQghxTYWFArGHHybe6aKHSnimudVNEmLLSOgWQgghhBBCXDNmr0f47W9TO3kStMYqFkn+1E/hFQpb3TQhtoQMLxdCCCGEEG9gAPG1deLnzhGrVre6OWI7eeUVek//AGN1FWN1FT0zQ/eb35TgIW5b0tMthBBCCCGuYEUR5ne+Q+VLXyLc2MTZu5f0T3+c3tGjaK23unniJmYYBuFLL2G0W4SNJkopQBGcPInbbBGlZNkwcfuR0C2EEEIIIa7gnDrNyuc/j+50QWuC9XWi8ib5//l/pj0wsNXNEzcxQymMeJzGK69gOC5Rp4OKucTuvhvDlughbk/yzBdCCCGEEFfwz51DtzuvbQhDuqdOE83Pg4Ru8RZi3R5ePEHywYfw52YxUinMbBZn/wEM297q5gmxJSR0CyGEEEKIywzDAOsqlaa1xnDdG98gsa0Y9TrtY8fonToJKNgsYyQTWNPT2IkEnW53q5soxA0noVsIIYQQQlymtcbaMYk1MkKwvHx5e+qxx9CTk1vYMrEdhIbCe+UVgqVLzx2lQGuSD7bphOHWNk6ILSKhWwghhBBCXKa1JigNUvj7n6X7/DH81VXiBw7g3HUn3WQSpJCaeAu+Ulijo4TVKlGrBUphZLMYuRxBEGx184TYEhK6hRBCCCHEFYLhYewwxAgjYmGIMTKMt3OnVC4XP1KYzWLddRfKtolqNTBNjFwWdddd8vwRty0J3UIIIYQQ4gpaa7zRUYzxcZRS+DIsWLxNoVK4H32crusQzlxExWLEHnqIcHLHVjdNiC0joVsIIYQQQlxVFEVb3QSxDRkKUvt3wu5p1OAwneFh6eUWtzUJ3UIIIYQQQohrIr6+TOcL/xrWzgManSqR+KV/RGf3ga1umhBbxtjqBgghhBBCCCG2P6UU+um/hMXj+GFEGISozRm8L/8BjkxRELcxCd1CCCGEEEKI9yxuW/QunmMjTLLahtWuScPM4i+ewe42t7p5QmwZCd1CCCGEEEKI90736E3tpu2FRFoRRFBp+0RTh1Cp2Fa3TogtI6FbCCGEEOI2pJQCB0IzRCnVvyzEezBbV5wfPURi736IIogi7OIQ/o9/nNDJbHXzhNgyUkhNCCGEEOI2oJQiVCHr3jqVsELFq/DExScwMHhk7BFGYiNoNEPxIUpGSapNi3fM9AP+albxc49/hon3/xhRpDkbG+J77WF+XuZ0i9uYhG4hhBBCiFuYUopVf5Wl7hLPrT/HUnOJTW+TldYKj449yl/M/QXnauf4mT0/w7dnv01IyKd2fYqHiw/jaGermy+2kbH2Jh+Zf54nv3QSwzRQhkHm/e/nzh/fQxAEW908IbbMtgzda2tr/PEf/zHHjx+nWq1SKBR49NFH+fSnP41lvbZLs7OzfOELX+D8+fNkMhk++tGP8olPfGILWy6EEEIIcWMt+Uv89/P/nWwiy1NLT6EMRaADmn6Tlzde5qOTH2W+Oc+xtWPsKuziu4vf5WtzX2PAHeBI6shWN19sI+HqKsWLp9g/nGW16eFaBqMXXmLXj91Bl/RWN0+ILbMtQ/fS0hJaaz772c8yPDzM/Pw8v/d7v0e32+WXfumXAGi32/zmb/4md9xxB7/yK7/C3Nwcv/M7v0MymeRDH/rQFu+BEEIIIcS1V9M1ljvLKBRjiTEyRoYXN1/ENmxW26ugINIRXuhRjBXphT3aQZtXKq/w2PhjjCRGuHvobsbT4yy3l7kzeydRGG31boltIuh2icUchlcuMp5KEXkBRi1GZEgZKXF725ah+8477+TOO++8fHloaIilpSW+/vWvXw7d3/3udwmCgM997nNYlsXExAQXL17kz//8zyV0CyGEEOKWoJQiIEApxZq3xp+c+xP8yAcgZsX4hX2/QK1Xoxt0ySfytMIWQRhQiBcIo5C232azu0kn6HCxfpEdmR2Mp8Ypd8uYymQpXGKY4S3eS7FdmIOD6IEBnFQS3e1h2TYUCuhCfqubJsSW2pah+2ra7TapVOry5TNnznDgwIErhpsfPXqUL33pSzSbzStu+yrf9/F9//JlpRTxePzyz7eLV/f1dtrnW5Ecx+3vRx1DGx83ahMYcbrIvMubkbwObw0363Gs6iozrRk2e5sYyqAbdPGVDwoCAja9Tb6z+h0ODhzkm61v4pgOMTPGhrdByk6x0dng4bGHeWblGQ4WDqLRPL38NI7hcKpyCi/weGb5Gf7He/5HhtTQVu/ue3KzHsNbjZ6cJH7nUTovvQyxODg26Y8+TpBM8l7/8nIMxXZ2S4TulZUVnnjiCf723/7bl7dVq1VKpdIVt8vlcpevu1ro/uIXv8gf/dEfXb48PT3Nb//2bzM4OHh9Gn6TGx6WM9u3AjmO298bjqHfgcXnYeY7sPISJAqw53E48DGQLyM3JXkd3hpuxHHUWtMNuriWi6HefEjuXH2Or5/9Ot+a/xbLrWVcy6UYK3K4eJi19hqr7VUCHdBd7XL48GHuG7+Pr818jaODRyklShTjRdY76xxfP87O7E4qvQpe6GEaJs1uk5bfIm2nOVs7y3dWvsNnj3wW13Kv+/5fb/JavL50GOK9//34e/YA4E5PYw9d2xM2cgzFdnRThe7f//3f50tf+tJb3ubzn/88Y2Njly+Xy2V+67d+iwcffPA9Dxv/1Kc+xcc+9rHLl189k7a+vn5bVVxUSjE8PMzKyoosF7KNyXHc/q52DFOtWZz1l7BXnkcd/2NwMxDLoi98i1DZbOSObnGrxQ+T1+Gt4UYdx0pU4Uz9DM2oyWJzkaybZW92Lxkjw5A7hKX7X9sMw+Dry1/nQu0CF+sXCXRAJ+gQt+K8sP4CO1I7MDFxlMNHJj/CiY0TDCQG+MldP0nbb/PsyrN85cJX+Mzez3ChfoGR5AhNr8lwcpjHJh6j0q1w19BdfGv+W2hPc7ZylifnnuRA4sC2fR7La/H6M8IQ/dRTtJ95pr9Gtxsj/fjjhFpfk7/59TqGlmXdth1s4sa5qUL3xz/+cR577LG3vM3QD50tK5fL/C//y//Cvn37+OxnP3vF7XK5HNVq9Yptr15+tcf79Wzbxrbtq153O75B62v0Jim2lhzH7e/VYxgPGxgv/meskf2oM1+DA5+E3DjUl1DxAma3jFKKKIqwej1YWUF7HsbQEEE2K8+DLSSvw1vD9TyOXdXl6/Nfx3RM/vCVPyQiouW3yLt5fvngL3Nan+ax4mMYGKBgrjFHrVfj0MAh8rE85W6Z2fos8UQc13KJW3EeGH2APzj1B4SELLWW2Jvbi2M6JO0kewp7mKvP8ffv+PscWztGEAXsLezlv73y31hoLVCKl/jZvT/Ll2e+zI70Dk5snGDHxA7iOn5d9v9Gkdfi9WPOz1N/4quE6+v9y8UizSeeIDU8hH+VEabvlhxDsR3dVKE7k8mQyWTe1m1fDdzT09N87nOfw3hdVcS9e/fyB3/wBwRBcHle90svvcTo6OhVh5YLIcTNzmou9YeWKwMGDwIRfPdfw6WZcmrkToof2UHFG6T9p39GsLrS3+44pD/xCfyJia1rvBDiLS13lhlKDfHvT/17DMOg1q0BUOlVuFi/yFprjYO5gwxbwygUeTfPcHqYL579Ii9tvMRgfJAPTn6QXtBjb34vj4w+wpdnvkzVq+JFHn7oc2LzBB+c/CBnK2c5XDxM02vSDbustFd4bOIx/u0L/5aUk0KhWO+s85WZr/Dx6Y+z1FxivbdOJ+oQV9s7dIvrJzp3jrBcJr5vkiiI6J6dxQJ0uQLy3Vvc5rZl/f5yucy//Jf/kmKxyC/90i9Rr9epVqtX9Gw/8sgjWJbF7/7u7zI/P8+TTz7JE088ccXwcSGE2E602S+WFrarcPBjcOKL9N/GL53xr8xgzH2fWGP1cuAG0J5H+6/+CisMb3ibhRBvn2mYtPwWQXTllLZar0akI8p+GYAgCDhSOsI3576JRnNw4CAjyRFeWHuBh0cfZiQ+wnprnXK3jGu5tPzW5fnhnaCD1pql5hKT6UkMZbAvv4+l5hK2YdPwGsSsGBknw0p7hVKyxFNLT/WHsjcu3ug/idgmTK2xYjD8sZ0MDL1CccdFhj5xBDPhYKaSW908IbbcTdXT/Xa99NJLrKyssLKywq/+6q9ecd0f/uEfApBIJPj1X/91vvCFL/Brv/ZrpNNpPvOZz8hyYUKIbauXGidZmMLfOI9ZeAzDjvd7vg0X3BSEPspvEmcZZVnoH6pFEWxsoNptSKe3cA+EEG9mJDbCxeZFDg0c4lT5FADq0n/TuWm+OfNNCm7h8u39wGc8Pc7+wn5e3niZvJPn/WPvx8RkT3IPhViB45XjzNRmiFvx/jJiEcTMGBrN0eJRbNPmG3PfoNat8ej4oxiGQRiGNLwGtmEzlhqj5bVwLZex5Biny6e5L38foZzAE6+jlCKVXkGd+Sq62T85ZHXmcT7+D2i+ybROIW4n2zJ0P/bYYz9y7jfA5OQkv/Ebv3H9GySEEDeAj033wM/grh8ncuMY2QmoL4BhQ7sMaDBd1LF/R/7QRyi/uHz5vlZhAB2XYaFC3KxixDhaOEo+kUcrzfGN4wA8Pvk41XaVT+75JMPm8OWBLbZpEzNjfH/p+9w/cj/zjXmeXH6SbCzLXG0Ox3QYSY6w2l6lpErM1ec4NHCImBljIjXBSHKEzx/7PDknR9pJYxs2eSdPpCO80CPUIR/f+XEW6gvsSu9CaUUxXpS5tOKq4jSw57+Gpo5OuuAkQQeYrZeIrE/1C6sJcRvblqFbCCFuV10zTXf4QQzDoPRj/xPq2/8blC/0q5jf9Ysw+xToANc7j5kqETabKNsm8eMfwLfkLV+Im1nBKFBIFth/535mO7N4oUetVyPv5Nmb3As/lFsG44PM1Ga4s3QnT8w8QaADLMPiv57+r3x696d5ceNFVpor3D1yN3knTzaeJW7G8UKPmdoM8815wiikE3QYSg7xx2f/mE/v+TQpO0WlWyHjZoibcdq6jdIK27A5OnCUSMKTeB3HhERtAQCVGULpEDpVMG1QEbZlEnryvBG3N/kGJoQQ21AURawOvI/Bj/yvmAtPQ9hDn/kG9BpoN4s9aJN74DNQbxBpTaQUsSiiZ5rSUyXEzUxDLIixz96H4RropEaH+orADZC1skxmJml4DUyjvzxYpCMUiqeWn2I8NU7Db/Ddhe+yN7sXC4tSssTf2vW3OJA6wKnWKbJOllCH+KGPbdj8l1P/hcd2PMa3579N0k7yj+/5xxSsAruzu5lMTVK0pKdbXMlSEdlTXyE6/w3U4H7U7HehvQm9BqDBipFZf4Zu9s6tbqoQW0pCtxBCbFNaa+rpvWTbT8DcU6AMdHIIZVlEsTG6//l38codrPGduNPTNP7D/w93/37sRx/B+6HlF8X2ZBo2rdWIXickPeBgZ0KZa3uLeateZd/zuaN4B381/1eEUUhI2C+A5mbY7GxypHgEAEMZ/SJqGqYyU0RhRN7Ic1fmLu4t3cuJzRPUu3UmM5Psye1htj7L/cP38/DYw+yK72LAGLj8OyVwi9dLrx6HE38CzWUo7YDxe2HtFNpOQmEK1s9g6BD7ofvwfX+rmyvElpHQLYQQ25kO0Ht/AsNrosoXIAoJkzuon6jQOb1AsLFJ78ICwcIC1mCJ2n/5L7gvv0jhH/5dwnyOrp2XL9LbUWDz8jfXOP/8OqZtUJpMs+feIdyMIp430ErC960uoRKoUPHw2MPMN+aJiEjbafzQZyI9wWBskKSdJOfmMLRBMVHkcO7w5dd7XMf5e/v/HifrJ9nobDCcGGY6M03Vq2Jog4JdII0UXhRvzWwsoTfPoxs1jMY6zH0HnSoRZQdpz74IfpdkcgBLe/iXlrcU4nYkoVsIIbaZuBmSqp3HCNtw6k9Ryy+iSgfQuz+IWj9DlD5A8799lWBuFm2mCDc2CdY3KH7ucxiJOMG5k4THnsZJnsfZ80EapfuItucKkrclpRQrZ9qcfXYN2zVIZhwWTlfo1H3smMnI7gyT96VByRzKW5qGewbu4VvL3+IDEx/gmZVnAHho7CFGE6P4vs8/vusfE4YhtrIZjg3j4l5xki2lU9yfvp/L2TqCvJXfgp0R21nUbEAU0Vt+BWf4KPrid4isJNV6nSAEc+xh/MjkDXMkhLiNSOgWQohtpNg+h/Xs70HgodZOQrIIjUWoL6DOfBV2PYZ+8b+TOrSfyoULKKv/BVt3u0TtNrED++i++AMiL4R4AKefIJGeoBkf3eI9E2+XYRisXWygtSZdiLOx0AQNldU2Ow4XOPvsKoNTSRKlrW6puN6yKsvHxz/Oor/IA6UH8EKPvJ1nIjaBidkfnm5DRMRsd5bZxixJK8nuzG7yxpXh2sNjvjvPZneTnJNjR2IHMWJbtGdiuwhjg6jsDvTmBfxWBQamsO/4WfzyAjo5DJOPcDF1DwUpwCducxK6hRDiJpfQbeLlExjtTYzWClTmID8J9UVQClCAhqADykQ5BmZ0absCDJPYgUMEtTqGbWOm09jDCWj3hyAbzWW4zqE7HWzgbpxCo/Fz0zRj40Qy1PBdiaKIzGDs0s/68hJSiYyD3w3QQKvqkyjZW9dIccMYkcGEOYGy+q8nrftF16JLvYpKKV6ovcB3Fr5z+T7PrT7Hz+75WQpGf93vSEU8X34eT3lEOmKpvMTxzeN8bMfHcLRz43dKbBteZhKjeA/W4EGspMO6TqPCFL2DP8UrFY8nyykeMcYo/OiHEuKWJqFbCCFuUq4K4Mw3SB//Y7jwLVQiD6EHmTF0vNAP3MqAoAeWC8oEZWLSxtp1gMT72nh1n/jgMGG3i+G6BH6Lwi//AmZw6vLv0W7quu5HvnUe67n/L0ZpL8prYtdmiE28j7XEvvf82GYQYKyuoj0PNTSEn0hcgxa/fQoTAM2Nm0OttWZsf5bZl5Ioo39ixVCK0T05ls9XAIinJXDfbt6sNkOLFk8vP33Ftl7Y40ztDA8WHkRrzXq0zonaCb4x+w2CKODw4GEeG32Mxe4i0+70jWi+2KbamUHSd/0NdHMFy+zgEOdrF2z+4zcNLrRc/s7DYxwetIFgq5sqxJaS0C2EEDcZy1AUmmcwl56FtVOok18Ew4KwC4YNnSpq9E4o7IbGMmTHoLECuQm06cD0fZjpAubugwSnFwg9Te7HP4S9exrL3wUXvw5ePySqwjS99OT12xcF1tmvYubGUE/+m/4JAsAcv5eBD/4Gm+67/912p0Pvz/4Mb34BrcCIx0l94pP4oyPXqvlvLjKoLvZYPr8JwOjuLNkxpz+POlK0KxG9VkAsaePnA5RSoA1Q0TUpXGelfR75+Z1Ulrq0qh7Ncpe1uRoRmp1HiqSHzBt6IkDcvPzIxwu9N2yve/X+8xJ4ufwyX5758uXrXlp/iZgRY2LXxA1rp9iekqszcP4Z9Mk/IWiskZ/cxyfe93ew9+wmlYxzRymGhVQtF0JCtxBC3ERywRqx5WdQS8egWwU0RCFEEZguJLL9Xu3qPDq3AzWwB5IDRJlxdHEfQbxANzlCjzjss8jW2yjXJkjYeFGErfPEUlnM1ipRvEA3twdPXb95m3bUxnBiqBf/cz9wGwagYOVl7MVnSE0P0FTvrKddKYVbLuP99V/T/vo3UI6DNTxMhKL9l39J/G/+AoFpXp8duqS66DHz4ublyxde2GCnKpIbdVg+1WJ5pnaprRD2DDr1Ho1Kj0TGZnAqiZl8770+RtJnYI9JMUrRXIszMJkkkbZJD9toQ3qVRF/GyDCaGmWpuXTF9unMNFEUoU3Nuco5Hhp9CI3GUAbdoMvxjeP88v5f3qJWi+0gHnWIXvo+5pn/Bs1NUIrw3Iskot/l0/f+CvXi+wmVBG4hQEK3EELcFExC0o2zxOa/i2qtQa8G6P7wcaUgUQTL6fdoxwvoifdBr0lYOkytcAQv+qHhpa92pKqIKHspUF8qYuMrBz93AHIHbsh++YYLiQJ0ypfmnwN2HJIl1OZZkhvnSOx9nHLhLoKoXyTMMAyCoB8alVKYvR7acQgBq91GnT5N81vfItzYRLfb6CDAm5nB2bObYH0N1WpBJnPd9klhsnx+E6UUOlJEYYRhKZZfqYOfo7LSpTCcplFtMzCSYmO2wdnnVnm1QHz+VIJ7fnoc5VybYKyNkOQwpEZerUwtgVu8RmnFhyY+xNfnv85KcwXLsLh76G52Jnb232K0YlduF//u+L/D1z4aTcbJ8IHJD5CzclJwWryp+PIpvI1T/TojaMAAJ0XUbGFZNcLrfPJTiO1EQrcQ15hh9L9ZR1KpU7xNSinSi9/DWX0ONfMtKB3sh20dweoJOPDTsPQ81BbBzRDtfRx/5RXC3R+mlr0Dwpt3ne1Am4RDRzFyO6A809+neAFaa6Aj1IkvoWqzDNz5i3SYpvHN7+HVasSOHsHYs4fOM8/QnZnBLBRIPPQw0dIitDugFNbAAN3jxzHTabRto5stzKFhdDx+3fcr8hWVxS6BF5LIuFiOifYDVi/UWXilQroYY9edJWqrHVZnGozuztNqdKmtd6istaks9ihMX9svpLLeungzeZXnZ6Z+hlpQwzZsMipz+fkSEXG+dp6QkHbQvnyfQqxAkuTlgmxC/LBUVMVY+j5Yl95vNfQr+PkYrgNOciubJ8RNR0K3ENeIgUlzPWRttobSisHJNKkhg0jLvEpxdSYh8c4KllfFqM2hw6jfC9xrQnMVCtMweickh2DHQ2A6hIkiXqOC9lqohR9gFu8ivMlP8GwmdjH0/l9Dfet/hagHXhsmH4bKBdT+n4DF5+Ab/xJn6EHimT2sf+8lOi+8QOqhh+iVN9FBQNTtEj73LL2Tp/AXFwnrdXJ/42fonT1LuLEBtg2WRfIDj+Hb17eIWLcWEYvbdBs+kYZeu00y57Lr7kFyw3EGxtN4vZAzT63iJCyqKy3KS012HCpg2x6+H+J1AkB6gcSNY0bm5WrlrwZuX/ls+BssNZeYzk2Dhm7YxcBgtbV6ec63EK9nt1ZYcAZpHniIHcMZ7Jf/DMpLKNPEHB5H569frRAhtiMJ3UJcA15dUV/xWJ9toFT/hO+zfz7H4fePkt9ho0xolQMCLyKRtXHS/d7NXk2hQ4jnTELeWOhG3Lpc3SV29k9h5QRm1MGozaL2/SR6x0OoY78Pez4EWoMVg6FDRDN/Tc/vojsLrz2I5b42ZPsmprVmdfAhBj7xO1jLz6Nq8/DKEzC4F079KSgDbcRRyy9g1I6Tu/8xWicWaXztayQff5zu2iru6CjNv/wm+D6R1hAGbP67f0/hl3+JYG0dlUoSe/RRuhPXt/CTUoryYotWvceue0qsztQIfU1hPAVoNmabnHtunWwpztpsAzdpUdyRplnuUl5uURhJsjZbv7Tkl/RMi62zEW3w5YtfxrAMUk6KcXec9e46A8YAeTfPQGyASN3cJ/TE1lBK8WfrJV4p76fn5NG9D/Lh993BnmieYjaJ0k3CV+fTCCEACd1CvCdKKbplxcbFNse/s4QONYEfYbsmpR0pzjy9xpHUGEsXyjTK3Uv3gb33jbA+02D2RJleKyA7FOPoj08QGwxliOhtwt08BSsnAIgMFyMM0Be+TTT1MMZdv4haO4UeOoyafIhq4SiOkeoH1csU0fj7CMPtMZJCa01bx0j4PSwNqjYHpX394eZaQzxH1PaIGnXUmI1x1/0YQ5sYqRSsrWIAQb2Onc8RVaqY+QJGvEuwsooqFHDe/yjd4eEbsi9hqOm1fBobPUzbIAoiZl/eZOwzO3nqTy4QT9mEXoRpGwS9iGa5S7flE4Wa/Q+NkCq4xNImMvdabJXIiPjG7DeodqtgwnR2mv9w8j9gGzbtoE0xXuSf3P1PMJVJIM9T8TpzTc0fPr/K1NAgX35+FnTEF5XNodG7+cV7h/j43P9Gd++n5byiED9ETkMJ8W5pg40LHs0Nj5ULdUI/wu+FGIbC74UoU5EdjFFb72JbNm7SwjAV+aEUm/Md5k5U8Lshhq2orXY59o05GotAJC/LW51SCqM6e/lyhIHOT0O3RohFr1HGP/ILNO7+VTjwU3Qjk1bpHvShT6Fy46jiLvSdv0gzs2cL9+KdU2EPf/E4XmoU/cA/ACcFZgydHkGHPpERx596jIvqXl56OWQucyebY/dh3/1Qf/i4YaCKg1gjI+jAh0QC9567MX7uZ/FuUODWWjMwlsRyDQzTYO1ig8pKi8GJJH43xO+GtGse6QEXw1CEQUQYaJy4xejeHJsLDZyEQeBvj5Ml4tbUCBustdYAGEwO8sVzX2Q0OcpEeoKJ9ARhFPLC+guYhkyBEG+0WOuxe3SA75zbZMdgjtGBHKGyWe9onjhdJXrkn9HS17+2hhDbifR0C/EuNVZ9uvWAZCbO4pkqsaRF6EVEocZyFfnhJMvnaiycqYLWjO7LMjyV5/yza9iuTWWljWEpEhmHZqVLq9YjP5Qk34wxvC9Ot67pNgOcuEks21/fV9watNbo1NAV23wziTFyL9GuD+HvTdC1C+gQspeuD5RNfeBOzMG7+8uybJMe7h/mx4vYiTzhwjF6uXGcyUdRjVV0dZEonibEYTnxKMsvLTP48D1sNhMce7JBfniMnYcPkP+ZFO3TL0M8hjlYxEin0QcO9Ieb30CJgmLP/YPMH6/RqvXIDsbREbRrHsUdKaqrHTaXmkwdGWDuZJlYyiI9ECNdiLF8rsbEgQHcpIW+RmvXGobRf07JKBnxNrmGS9yK0wk6FONFElaCcrdM2kljmzbdoEvDa8icbnFVpaTJnkzA/bsXsFeeI7JjbB65n69sZgmxaSZ2QKez1c0U4qYioVuId8EwDLq1HmuzDYojkMg42K5JPO3gdQIKo0kqy23CIMJyTIJewOpMg2Q2RqcZkCok0Gi07n9RjyUttNZ43ZDKcgtDKeZfKV/+faWpDOP7s/RaIZZrYCUiqY6+zXnFg7iLz6JbG5e2KKJ9P0E9Nt4PT1pf9QvvzV407a14ODh3/CzWyS8SVRfoNjex7/sHBEtnCc5+i+Dwh1k7VSB7aJiVskt1s0u3Dd5ij431TQ4/+D7GhkeIFi9iDhYx9x/AT72zNb6vBY0mNWxwcGiA6TuLnPruMvWNHktnffa/b5hzz67hdULsmMl9H5vCsg2WztWorXUY3JFm+XyFTjPJyL4EnUaA5SjspEK/0yrR2qC5HlBZauImLApjCaxk/zFs20Gh8ANPwrh4gzhxHhp7iKcWn6LSrZCL5VhqLRHqkF7QYzI7yZ2Dd9Ltdre6qeImkwo2ubf2Aw6ZTVbWv8dCs0c7MChUZvnkoV9Ajd1NRwK3EG8goVuId0FrjTIMgiCkst5m4mCe6kqHtdk6AFNHi1w4to4bt4inLHxbEQQh9Y0ulmOQyNgk0g7dlk8YRNgxm7E9OVr1HpnBNAtnqzgxGx1FxFIOteUeUbfGK8+uYBgGu+4eZPKuDJjbr7fzVuBGHdzaOYz2JmFikG5uN75yr7iNYSisqEeg3Kv2xHasLPquv4tTuwB+hyg9TjsxessHpKY7gn3XZ7F7ZbQVp25lIHkPKv8QQWUdI+ZgDw9Tf76M3wmJIo0yFDrUVNZ9mu442X17yA7GSBYMiLbuNaBVRKwIRz4yTGXJo9cKUBYcfmyMhdMV6htdmuUeiYzD3IlNvE5Ithhj4uAAF1/epNP0qK43ARiazjB6IAXG2wveSinWz3eZP/XaybmVC3X2PzBKq+JTXipjuwZu0qYwFsfJSb0I8RqtNYeTh8ntyvGFk1/g7tLdxM04L6y/QMJO8NDoQ9xfuF/W6BZvkFx/AbX6AvaFb2NrBzdZYjNw0ISUnLOoyfeDlsKwQryehG4h3gWtNdlSjMZml9H78gR+RHHcIF1wiUJNp+HR6wQopbBcg9SAQxT054KGUcjGYoOpo0UCLyQKNbZrUtto46ZMkpkY3WZIZiBGtxWwfL5GFEWkB+LYjonXDTn7zCqJrE1prytfpG8wW/eIn/oj9OY5NP3CGImRO2jt+RTBpSWgkr1l7IvfRlcXIL+DYPL9tNw3zjnuGkm6+Tte23CbHEofC98t9S9oDbaPHhnB3THJRLHH+mwL6M+HVkrhJmw6DQ/fiygvt4g0nPvBOnvuKZEoWKRK1pZOvzATEYN7bKKeg98xeOHr8zQ2u7gJm14zYH2+zq47S6xerBP0QlYv1lBKEfmvHfDVmTqZwTip0tsbzht5isUzlSu2+e2I+ZNVFs9UyBbjzJ7YxLJMkjmHox8eJz9pom+XJ5l4W0zDpObV+NrM19iZ28kv7PsFLMNiJDZCUifl+SKu4Do2auVFtLZQXo+Ev8G0nmMiOQyxDIZZZsMI2Yazn4S47iR0C/EuuXnNHY+No7TCDmB1rU51rU2j3CWedth3/xBeN8SyDOyEiWHByN4MQRhQXm5S32yRzLhMHCpw4flVLEcxsitHY7NHY6PL6oU6bsKmMJLg3HPr+L1VhndmWXiljNawcr5Oac8QIJ9uN1KsOY/ePHflxuWXiY3dTy81QSysY5z4E3SzX6SIlRNYlTli9/0qXePGD4XeTnzfI1kysNwMXidi8VQ/VHZbHkoplAHZUoK12Tq9TsDcyTIjezJYZgYiRURELGtgxqIbfjJKa41yNLoV0ar2iCKNaRn4vRC/F9GqeWzMN7Ecg5G9OeJpB62vPFHQqvRID8XfVtt1CFH42u3CHlRXurgJl+JYinPPrhEGGqKQZqXH6e+tcO/AOFZKQpToi8yIb178Jgk7wdnqWZrrTU6XT3OwcJAH9j4gJ3TFG2gdEbYCvJNP44wehPPfwognsJpLYJno4p5tWW9EiBtBQrcQ71IURQztTHL6OxvMHt8kCjSWazK+L0+75lHf7OK1A7xuAAqK42lWzvUL0+w8MoSbtHASCiuhuXN4BB0oNme7nP7+Mm7CprbWnxPVKLvsPFpk7nR/eTHTNgj9CDdpo4z+ikvixlG9xhu22ekBYtXTpM5+CZSJjrmE7iT+5qUK5b0Gdn2ebu7ADW7tdqRxs5q9D+cpjiY58+waueEEjmuxudhgZHeW1dkAZSiGprOU59s8/9UFEimHyTsGiKVtMiUXJ2EQy/Uf70ZSliKVd6mtdQi8kFjSptvyMUxFMucysitLZblNfb1LbihOcTTNxlL/OfVqbYe3w4xBthinttFBYZLIWLhxh4GxJCvnakSRBkU//CuF1w1plgNyKVkdQfSd7ZzlT879CXcP3c1dpbs4XT5N2knz4NiD7HB33DYjb8TbZ1YreO04NCsEzQLWng8RLT6PKu6ByfsJ8zu3uolC3LQkdAvxboUGm3M9Tj+1QhRGZIpxOnWPykp/jvfMixuXe7qcuMXaTJ1cKU6mEOfiyxs0Kz0SOYvcUJyddw+iI023FRAFGqXAMPvDTFtVDydh43dDlAI0xFM2EwdyRFs4n/V2FaaGsJTqD4tWBm4ihdlZh+9/E1prgELld8LYvQTJArp1ac6tFAF+Z8yQwm6ThyYnqa526TZC4lmLpbNVAAYn0qxeqLM60yD0IuqbXU58e4m9DwwR+ZoIn3QxzuDOGJG+9DoJTJplHyJNIm9juP3h64ZhEEXvoHc8MOk1Xy1qeGXVcDetKE2nMExFFEDL98gNJYjCiLF9ORZOV3Di/Y/epXMV9tw3RCxhY5gGmSEXpSIi3wANhvPmbdJETN6ZZ/WsTX3NY+F0BTduYxiK0lSaiy9vYpgKw1TYjoFGY9nyJBSvqfaqADy3+hw5J8fh4mG6QReFQml5rogrKaVwzz9F99wFYsVpooXTeEph7Lqf6PDjWGaDemqPnKwR4k1I6BbiXfKasDHfwDQVSvV7n7OlOMpQ5EoJsoNxmpUeTsykstQCYG22QXRRE09bdJs+xfEk8USMs98vY6BJF+LEMw5RqEkVXNq1fjESw4TSVJrhXRkKYwlK00lihX7uEzdWJz5Kev9PYa6fxApamE4cmitQ2AndKvgdqM+hClPYuZ14rTLEMvjpHVvd9G0psj0y4waZ0CI6G5LIOAR+xMBokpkXNwmD6LXRHgZ43RCj6TO6O8P8KxX8TsTgVBwMeOXJVXrtAADTMtj/4Aj1jTa19Q6ZYpyBiXg/iGsTv6MxbfWG4NutwNlnVgi8/kmwsb15Srvj6EtzyjURO47myA7GqK52KYZpdKgJggivHYLWdOoepq1wXIuV8zXu/+lpKmtNNi92CAPNysUqaChNphnZlwbr6ifXzFhEfiTBwsk6ylS06j3qmx12OSX23j/ExZc2SGQd7JhJthQnWbCB4DoeLbGdxI04+wr7OF0+TdWr8sLaC7iGy+Shya1umrgJFfxlWH+W7kvPEk7uxt31OMpx8XoOlp+nsecDeFrWdRfizUjoFuJd6tQDwiAiP5ok9CICP6LXDjFMhdaaZtXD74UEvf628NIcz8pCg1ypiO2YxFMO5aU2oR/Rrnv4vibohfTaAU7CIplzcRMWlm1y5INjJAY14F5ak3er/wK3p0hDd/AI6cXvY1Qvwvi9UL0IrXUo7gE3A/M/ADsOdgw1eif+jkfoGsmtbvr2ZkaMHIgzvCtFczOgttpG0R8REvr9/0dhv9fZMBUnn1wmV0owf6pMZd0lN5C4HLgBkjmXl/9yCcPpv5DqG102F5vsvnuIc8+t0mn6WLbBjkMFsuM2oCEwLwfuKIDAi5g5tklmYALPC4kCTSLv4KQicjtsClMuUc/kwtMV3LiFZZkM78oShZq5k2UUYDkKQ0EUQLsaMH+6TCLf/30rM3VM22Bo39XneSulqCy3aFa6dOpev7CfoZh5YZ33//xeRvdl+38nU1GaSmHEQnnfEJeNxEa4f/B+SvESJ8snKcaKfGTyI+x19xKFMm9JXMlsr2GUf0DigQfpPPVd/JlXALAOPYL+zF14WiKFEG9FXiFCvEuGqUjkXCrLbQDCMKI4lqIwkiTwInbfM8jMsXU2yj3cpMWOPTk2FhqX1+Ye25en2woIA83s8TLj+/KcfnKZXXeVaNW6tKo98kMJxg7kWT5bYexQ6g2Fl8TWiNfPYy4+gxo9Csf+IzRWIOiA14JkEUoH0cX9tHb9NF1tX3XJMPHOaa3BDkiPKNKDWbx2SLvuXert1sTTNtnBGFGkaVV6dOo+Y/uzRISUF/qjTWJJh3jCwU04LJSrZEpuvwR9pGiVA5bP1LFjFrGEQ6vR5cILGxxMD+NmodcMCbywX7RstY0GRnflePEbC1iuQlmgFOy5b4hkSRFFEcrRTN81yLGvz9JrB2wutkjnXUZ2Z1k+V2P/g6NsLnUgUqzO1mlVPdy4hRnr7/P6XJOh3Ukw3tjbrbXGdizCKMKJWwRev1feck3arR7FqTjxnIGTNDHdG19cTtzcSlaJB0oPkLSS7M/tZyI1wc7ETgnc4g1c3YUwQBWnSEencD/2QfxmiOma2Pd9iA1L4oQQP4q8SoR4l9Ili+amYvroIJXlJpZjMX9qk4VXKoRBxJEPjHPox8ZYvVAnijT19TbKUHjtgGwpjh94WMqkUuvw6hThKNCcfWaV3HCcwmiSdsNn7WKdylqbKAAZuLV1bKXJNs+h2usYaFRtHoq7ob4I2XForPbnAdSX0fd/lu7ow7QjC5ngdu1prcH0mbo3S6oQZ/V8nVjKJjsYp7zSot3wGNmdJwpCMsU41bUG6WIcr2tTXelw/tkNdhwYwO9pQl+hI02j3MGNWyhlsHK2CUozMJokV4rRqvq4WRvLNVBK0ah00PSHqAe+ptP0sX2DeM5Ca7h4fJNDjw31g7I2mTteRqNpNzzyI0lalS6l6QwTP10g8jXPPjFDbiiBaRrYtkmz4pEbiaGJsGyjf1LgTRTGE8QSFt12gBPv33DHoQJuwkDZAbE8gPRwizfSWjNijTA6NHrpxBNyYka8gVKK9MrTsHQMPfUoRugTm3+CmBVDT3+S7qgUCBXi7ZDQLcS7ZYVYrkltrUvga84+s0QY6n4BJFMx+/ImE4fyWI7B0rkqgReitWb6rgHG9qeob3Txu5rAS7Ax1wD6w8+jKKJT91F0CIKQbDFGcSyFk1ES37aIZULh/H+HZ/5vaJcxRu+C6R+DMAArBtU5SA1BahiigLCwn5pd2upm3/KUHTG4z2JgR4mN2Q6nv79CcTxFrxmweLpCPOOwMltj6nCRsX1Zzjy9zvKFGmiIwogojGhu9ui0PHKlBEopWtUugxNp2jWPdt0nkXGJp2wArIRmdE+Ojdl+r7kdMwn8/uoEfi8koWy01njtgMjXGC6EPU237RN4IUE3pKs9nIRFFGkcx+DZv5jDtEzKi21231vi/LE10oUYXjvCTsDYvhz6LZYFNJMB931sktnjFbx2QGoghu0q0iUHWU5QvB1aa3mqiDcVC+uohWfATaG1Qk9/ALX7IxDL4hf2ULXks06It0NCtxDvgZM0ME2FaRn9NXGhX6VagWkbdOo+kdK871M7adf7w8yTgwaakHzKhtAgkXVZvVinstJm3/uGWT5f7fd4xU0KI1k6TZ+D7x9GSwGkLZOvnkA99/9A0IN4vl8sbfU43PGzMPPtfvBOFtGmQzj+ANX07q1u8m3FiAcM7omhKdKp+Syc7pDIOFiOge+FVFZbTBkDtBs9ssU4UaCprLYZ35+nutoBo3+ibGxvnk7T5+R3l9CRxnJM1mcbFCd2A/354sN7EkTeKPVyD9sxMG2T8nKLVN693EuYzDmYbv8kmeUo3Fh/jIrhKCzboLHZJT+cpLzcxklY/WUFgcVXKuy6q4RlG/0TdHcXSAwqgk5/aUA7yVWnmMQHYe/DA3TqIUpp4jnrqsPRhRDincq0ZjGcGFRm0KaJzk4RnfsLdOkgraH3bXXzhNg2JHQL8R5kSg711S4J5eAkLXSoMU2F5ZooAwbGUwzuimMlAtyCCegre63MiPSo4sFPT7E606Rd63H0Q+MkczamaxB4AfGcSSSBe8uYKsJcO4EybYhloFPtl673Wv3iafd/tt/TXbmIv+8TtMcewsfe6mbfdpQZMnwgztoZk4GJRL+wWtSfY43ShEFAIuXQrnl0mh5BENF8cZ299w6RH0ly8eUNlAHzJ8tEl06gBb0Qw1Asn6+xZyRHFEVEKmRgKsHGSoNWPSQzkGBkZwbP679Gbddk6sjA5de5NkKm7ypR3WhhVBRBEDK0M4MyIIw08ZRNt+ER+BGdlk99rc3hx8ZpVNrEsyZLx+usXqwTSzrkSklSBZf0oI0VU4RBSKT7I2iUHZIYgP5ZPwncQoj3rtidwfjav4DyWQCUMlH7P040cpQoPULPSMgyKkK8TRK6hXgPlB0yfkeGbj1CGaOcf34NwzIwTEVuOE5+3MVKvPUXYK01ViZg4s4EkZ9CGRpthECImUAC9xYbaJ5GBR1oLIPl9udv1+b6Q8u9Brz8X2FgL9Hdf4fG6KN4gXwB2SpaaxI5E2X2T2+pS3OhLcukXQmIp126zSqZgTjdjo/fDcgOxqmuteg2PWIJG7936fV6acSKk7AuLfX12rrFdiri8GPDdOoBhqGIZS16jZAwiIhnLTCvfM2P7MwSfniYxnpAtxlg2QbVtQ6aiFTBRusEnbrH2P4C7VqPE99bIpV3SeZcgp6mMJyittbj7DNrjO7KMfOch2kbDE6myQ652EmFYWk61bBfUC5rvekyY0II8XYYSmGtvgjNJTCs/hILOoQzT8Dex2mV7pcaAEK8AxK6hXiPlB0SH4CpgRRDu1PU1rrYjkFq0MXNRG/7JHCkI7Aimbd9E4mZBuaJL8Lqy5AZgdUT/eAdBjB6N9SXIT1MVF+C9jq+5JwtlxywGJxMsz7bAPrDxkem85z46yW8bsjwdIbAj9hxqEAsbbEyVyGRdNlxcIDaZofpI0VmXlwnCjVu0iIMNIM7UmheN6zbCokX+kFcE+Bk4K16mc24JjthkDdiKKUY3OsQ9hSGNlk+28C0TJbP1YilbFo1j+Zmj+UzdZIDLrW1LqZpUBhJMXeyAhp6bZ+ZFzc58PAwQ1NpZk+W6XV7AMRSNvveN4QRkxN2Qoh3Lh1sEt94uf95977/Abp16DXg4l9DbRGUQUcltrqZQmwrErqFuEY0EbECxArOpS1SMXi7S7cvQm6yP6zczcDhz0B1ASK/v2D36S/1C+cVpvASJTnrfzMwIibuSFOaTOH3QpIZl9mXarhJB9MKwFA0ql16HZ8HPjVFsmiRyParjteXQy48v87gZIaN+Qbdls/e+4cY3JVAa/+aNC+KXgvvygZlaHo9D9U1iKdtzj6zhlL9NcA35hscfHSUynIL01aksv11xOobHaJQY1qK2Zc2UUB+KM76ok9xPA2hwdyLNYo7EqSGbDAkfAsh3p50VCd5+o9Q5fP9z72VF/uh23Jh/0/B4ov4A/u2uplCbDsSuoUQ4ioMw8Bcfhae/D8g9PrD60oHYc9HIfLQ1XnY/eH+Gt2tDcL8rq1usrhEE+FkwMEgaGrOPrNGs9LtXzlTZ/rIIN2ORxRGJAb6vdMKyO0w2GUU2VxoMTiVIplxyI26aPPaBO6riaKI0b0ZKgs9Fk5XCcMI0zRAgWEpyost9tw7RGOzS7vhEwURUdQfOm/aJl43YG22QbYUpziapbrUZvbEJrGkzfljmp13Fpk4nMVOyzrdQoi3ppQiOfsN1Pf/T7jvV2DmO+DV+8UxogBO/hn6p/53yubQVjdViG1HQrcQQlxFoTODevLfQNDtf9kIvX7F8j0fRi88C+UL/YJqo3ehd36Q0HC3usnidZRSbC40iKft10I3sHCmzH0/MYVhXxlCNRHZCYP0UIYoVFgxbsiqAXZKM7ovxcr5Bo3N/hDxKIpI52O0Gx4Lp8rUN7vc8dg49fU2aMiPJMgMxMmPJFm+tCRhc7PbL7qWsKlvdDEtxfHvLGEYiuF9Sdzsdd8VIcQ2lo6qqHPf6C+XkB6GzTP9zz4UGCbkptCNVchsdUuF2H6MrW6AEELcjMz6PHQqoAww7Ev/t6C+hG5toLtVtGGjF58HQ9G2B7a6yeJ1lFJ4nZBE1qYwksSNW8QSNqmMS2rAxXDfuPxWvxJ4hBkL33J97GstUB7TdxfIDcdIZGzyQ0nadY/sYJyNxSa9TsjC6QoHHx5l192DxJIOG4tNTn9/Gds1SRViBL7GtAzaNQ/DUEShRgfQa4UsHK9DKOfZhRBvzgq7/elTsVx/Q+hdukb3g3in3B9yLoR4xyR0CyHEVWjTRWdGAdUfWmdYYJjo7BjYsf7a3JEPmTGiWJ4wemOAA0gEFTLrz5JZ+z7J7hLqqrcS10MUReRHE2BEpAcdBidTFMYSTBzOkxxSN91w6/SIwYFHhhicSpLMOYzvLxB4IW7SJpl1WJutA1AYTRJFEW7cIjMQo9cO8DoBA+NJnJiFYfWfZaZloNFEkWZjrsXF56poTz72hRBX51lpGL0HSgegtgy7Ptj//FNG/9/0j6FjMmRGiHdDTnsLIcTrKKWInAzGA38fvfA8zD0F7XXUvp8iVDH89BRWcgSFJjBiBKkdV32cZG8V9+JfYvbqEPTQ8VewJh6hlpL53zdKqmQxcaDA0tkqKM3AUJLJI7kb2ov9dikF6ZLNgZEhupWI73/xwqVijBrfD7BjBvGsw8xL69TXO/hehN8LyRRjVJbbGKYiMxjD74Z43QDfC9n7wDCNzTZu0mHmhU1ygwlyUxaoq58kEkLcvjoqTqqwE4WCsNc/2XzHz/WnUhkWuGlaqemtbqYQ25KEbiGE+CFKKdLVU0Szf43urKOaK3Dok+iBPQT5XQTdOtb8D1B+C23FYPQ+utk3hmilFLHyaYxzX4fWen8b4IQ+zh1TeNq8wXt2m1IRg7tdBnaMoCPdH6Cgb77AHfUMlk41KC+1MG2TyUNFhnZmmD9VuXybdDFGImcDisCLCP0Iw1R0mwH54QS19S7ZUoKR3Vm67QC0Zu74BmP78hTHUzgJk82lNqadJLvDvKKSuhBChFrh53fjLL8EE/eD34H106AjdGqI4NDP0CK+1c0UYluS0C3ENWSaJkopgkCW6Nmu4mEdZ+VZjLWX0H4Hhg6i/S5BapRmYgfx5SeIhu/A8Ltoy0WnRwgNh9cvsG4YBkblwuXAfdnZrxHb99N4dunG7dRtrj9Pu1+hPLq5RpQDYGBw/liF8mKH+nqHKNIsn6tx/8d2kh9OUllqkS0lSA/Eqa10GNqZYX2+gWFemqygNQPjaY5/ewHHNTl/bJ142iEzGMOO2aycr9Fp+Fx8aZNUwWV9rs4dHxglOby1+y2EuPlsJnYzcPRvYZXPwsQDMHQYnBSdwaPUzcJWN0+IbUtCtxDXgKEMOhsG7bqP3wtwXIvMiIsVu7RWtyHL9WwXicopzOe+gAq6oEx0bQ6968OE3RaumoWFZwnhtcHJGzPE8ztpuSNXPE4URf05cK9n2kTRzdfTKraO19LU17v99bcvnRXQGpbPV5k4lCVbKrJ0pk55ZQM3brFwusK++4dp1XvoEGJJi8ZGB8s2CMP+/f1eiGWZVMptALIlhe2a9Fo+iYzNwqkKB0YGiLT0dgshrrRpj8LQKJZlEUWRjIoR4hqQ0C3Ee6SUojwTUltr0tjo4vVCYikLv5umutHG8zwGJ1IM7kygLPnguplZpok19z3o1vrLhCkDFfYwZr+Hse/j6G71KvfSGJ0qvC50a60Jho5inf1a//EALJdo+AieK5XOxWvUpUrjUajfsD3owNnnli/NSYcdBwqM7MqxdK5KGIUEPc3IdJZ2o4cTtzEtAwxIF1y01liuQSzp0G17hGGEEzMJA00QhuhQSTlVIcSbklF7Qlw7ErqFeI+0Z9KudYgCzczxDYJeRK4U5/xz6xx8dBS/G7J4porvRYzfkZQe75tYqreMrsyi0sNQW+gvkRJ4KNMiTA4RWQ3eMBNbmYSJq4foZv4QqSN/C/PityAKCZNDBId/Dg/neu+K2EasBJQm01SXO0SX3h9M2yCZtdlcbLF2sV+1HA1zJ8vse2CIqaMDpAsuUaD787uD/pxuw1Tc89EpFk6XsWMGA2MpRnZmOfaX8zgxE60hnrYpjqfAjN4wLUIIIYQQ156EbiHei8hg6USLbidg+VwNIkhlHcJAo5Ri+VyNwR1J2q0u67N1RvemUY4MLb5ZGa1VyO2AtRNQ2AmhD8pA7/8pmnYRZeZITT8KM9/tl5o2Hdj943Td0lXDi69satM/SWz0Pgy/g58YpKf6RWhM0yQM5bkgQOuIiSMZbMdi9kSZeMomOxTHdAwaS21s1yTwXxslszJTZ/ddRQo7bbSOiHomtSWPtdk6gRfhpk3u/+QODFvTa0Qsn6sxeajAyoUayazN8O40pV1J9E1YUE4IIYS4FUnoFuI9qMyEHPuLeUb3ZAm8kDCIcBIWvXaA3wtpVXpkijF0qDD6RYfFTUyZDgRdmHoUVl7ur8s9eJBg7N5Lc9oMGjs+SHZgF/b6yxD0CNwUho6I3mScbqSh7Qzyaud2oTODvfAUqrmCLh2iOfwQLTN943ZS3JzMkOFDMUo7x2lVPZSpSA+41NbbZEtxvE5IGEYoIDsQp7Q7jdb9oZ+GG1LYaVHcOUroa5Sl0fSviw8oJlN5vHbIvocGMV2FGYskcAshhBA3kIRuId4ly7CZP7VCGESsztTZeWcJrxNSX++SzLsoA/IjSZbPVskNJxjdm8NwImR0+c0pFrXRJ/57P8h4DUgNQaKAnnyYVmbf5dsle+tYT34eXT4PgKlM8g/8fTYmP/Yjpw4UunPYX/1nUJu/3DGeuutv49/9/8KTDCTQGPGQdNy8dMln/ECeM41Vhnel8Tohlm2w/5ESVvLKuZZaa0ICsK4cdKG1xnBCYg68Wv5P3oOEEEKIG0tCtxDvko5AmYoojPC70Kp0GduXZ+bFdQIvZProIE7ColnpMLYvz/CeBFoqBd+0rOYiYa+NiroYQQ8Vy6OVSejk6OJevp27/AMonwfThewYymvD8/+B9OgD1K3iW/4Oe/lZqM1fufGl/0p61+NspvZej90S21yqZHDwkREaG10M0yBTcrCTWoKzEEIIsY1I6BbiXYpUwOCOFHMnN/G7IfOnyux93xB77xui2w7YWGwShZpcKUF2yAWpXH5zu7S8V2DEwI2hUOggQpuJ126iFKq5gho6hGFZqLWTYKfQw4eI1c7j5Vy6bzVU/NUq5j8s9DC8+rXeG3GL0FrjZsHNvnriRwK3EEIIsd3IYiFCvEtaawanE9zx/nGm7igyti9PMueSHoixPtcg9CNMU2E7BulBe6ubK34ELzWGSpX6FzToSIOTws9OXb6N1ho9dAgjaKNOfwXWz8LSMdS5b6C6NWLnvoKp3jwR6eK+N27MTeHld13jvRHXU9Qz6JQ1YcdAKSnUIIQQQoi3Jj3dQrwHZiJg6r40Q9UUSoNhKVZnGhx8ZIRex8e0DQZ3JMGWtS5vZjEzIh724PAnUSsvoTfOQ24H/tj76Lyu5zpKj0J9sV+9HMBJQm4S5r6PVjauV6ZtX30JsdrgfeQe+SfwzP8NvQYU96Ef/afUVP5676K4RupLITMvrhKFGqVgx8ECA9MuWtbeEkIIIcSbkNAtxHsUEeDm+j8rpRiYiFNeamMnFIWxOLG8DAe9WSmg2DyFef7r/Wrlw0fQ4/cRDXyYnjNAxym+YSmwEIvITmOM3Al+B5RC1xYhuwNlu1f7NZf1sNnY94tkdzyK0a3Qy0zRIHXd9k9cW2HH4MILq/1REPQLks2dLJMZHMVKyYtcCCGEEFcnoVuIa0hrTSwPY4Xk5cs/qqK1uHEMw7jimOS8Jczv/xvUxhlAQa+FWj6GSo0QSxRxdn+YRnoPPRW7/Bjt+CjO8B3opeehPEM/lSvIT4Gdp+cUrrpm96vCMKTsjIEzdj13VVwHnWZwOXADhD3oNHyWXmmRG3XIDttoJbUbhBBCCHElCd1CXAcStG8uTtQhtnkCY+MVdLJIMHQXkRXHnf0r1OyTUNwL43fDyklIDKKmH8VYeA5j4WmS4dO404/RSO9Ba40fKXpHfomYm0XFshD5MPkwvdwuuqV7CLXM8b1VuTHz8s9+G9bnGkSRZrDaY3Wmyq57iwxMO/L6F0IIIcQVJHQLIW5pptIkZr6OXny+3wG9fgZ76RjWjvuhsQSxbL+X+oU/gHihf6fjX0Rlx+C5/wfnwc/B8T8kdt8/pGNmAKg7Q7SO/irxgxW05eDhEGBJ2LrF2SkY2Zlh+VyDxmanH7gnUhiWIpmNUZ5rE0vYJIoGGNLjLYQQQog+Cd1CiFua29tAL71wxTazV8dYPwlWEsbvhZlvwdh9sOfDcPF7UL0IE/fD3b+MqlzELu0haK/TSWcuP0YYRTTN7A8NJZfAfctTmuEDKVK5BMu5On4vxHYN6us9quttLMugXu4yvCfN2KEUmn7wXj5fZelchzDQFMYSpIYVUSShXAghhLhdSOgWQtzSVOiBvjLgaKVQUYCe/S7qzl+EWK6/hvb3/g/IjsHUI/0K4xMPwMZZjPUzxHPTNNFEyPDx25qKMGIayzW4eHyDffePsHx+lcCPcOMWQRCiI83gjiR2Gtrrimf/7Azdjte/u4J7f3KK3KSs2CmEEELcLuRTXwhxS/PjJVS6dMW2UNlEo3dDu4q24pDfAQO74b6/11/K65WvwORDsHIcdjwIjWWM839BwVvAVpGszXybS+Qs7Jhi731DeJ2AMNDYjonlGESRpln1CDyNZVnMn6gQ+K+d9NEazjy9iorknLcQQghxu5BPfSHELSdj+Rh+m4aRwdM29sG/gX32y+jyLLgp2P1B6gOHyT3+G6jn/yPMfx+iEAwLHvlH8PTvgZ2EbgW61X5PuWFiP/1/kXcz9MYfpjt8Hz0jsdW7ettTSmEYBlEUXTGnXoUmfk9jxRQY4bX9pUbI2KE0nUrE5myHeMpGvVZjDa01bsLCMAya5e4b7t5pekQBKOfaNksIIYQQNycJ3UKIW0aKFqnl76GO/SeoLxGfej+9O3+ZcmwS646/g+3XiMwYPRXr91bXV9Crx1FRP1QT9PoF1Q5/GtplmHjfpd7uB+Ds1yEzjpEewS2fxgD8sceIpHjalom6Jmvn22wsNMkOxhndl8ZMhrQ2NBdfXMXrBDhxi+k7B0gWjWta6E5ZEcmSotsw2XlXkQvH1vG6IU7cYu+9w9hJ8DyPkT1ZautrV9x3eDqDGYuQad1CCCHE7UFCtxDilmAqTWrlGdRX/icI+/Nneem/4jZXiX/4X9PRLoGVe+32pomuzvV7tIMeSodgOVCbh+wEJAdh5q/BUBDLw5Gfg81zqLPfwDQMGDhDuriXmjOyNTt8m1ORzZkn1whDTSxhU13vsHqhxtHHJzj3g0WiS+tpe52Asz9Y4/AHRjBj1/YEidaa3GiCueNVxvbl0YBpKSIV0a6EuFkY3puiXQ2YeXkNrWFwIsXO+4pE0TXufRdCCCHETUtCtxDilpAyurB87LXA/aqFZ0jWztHJHLpicxAE6MJutDIx4nnwOyi/DUN70alhVH0JUiWYfD/YDvSasPIy1OYAhWE62DPfxNj/t6S3+wZTKBorAbGEjd/TNDa7mJbB2N4Baqvdy4H7VVGo6dQDUrE3ljFRSqFUv5q4Uuod94ZHYUimFEPR70k3TNiYrxFLGrhZF8MNefCTO9lxJIsONbGCQaSD97T/QgghhNheJHQLIW4NWnP12pAazKu/1XVHHyQ28hTR8gsoJ43hZuDuvwMv/zdobcLBj/fne68eB7/bL7aWGYbZJ1FoWDuJs6dB10hdzz0Tr9OpaqIAdKS48MIafi/EjVuUl1rc8xOTV72PaV2a+90zaFU8Qi/CTTnU1jsoDaZl4Xs+sbRNpmSj7Lc59ttQ1DbbV6wY58RsnJhzueCe5Vg42f6c80jLmHIhhBDidiOhWwhxS2hrl/joXRDPQaf62hW7PkQjteuqy2g37AGCR36dRPkk+C3CzDjW8jMY9UWIArjwLeiUIYr6BdiWX4DdH4bMGOgIZVhEhlTDupFMw2TtXAMnZvPytxYJgwg7ZuJ1A+yYSa/tM7Irx+ZSA6/TH8KdHYzjuBYzT9dYOlMjlXcZ3p3j2NdmGNqVJfI1qxdruHGLRN4ilY+x+4ECUQDNsg9AqmBjuG8MzHYCiuMpNuabWLZBIhmnvNRi9sVNipUUI/vSN/TvI4QQQoibj4RuIcQtwdcmrfxhkh/+TdTZr0FtEb3z/fT2fJyefvO3uo6K0xm45/LlwWIDwzAgNQZLxyCWAWWAMvvBff10f763YWPsfD8h5ps+trj2/I5i4UyVsT05TFuRzMVwYibQHxq+erEBaJLZGKM74xgOpAoxTn1nmfq6R6vWo1Xr4cRt9j84SuhHHP/2ItnBGPmRFFGoiQJFa1Vz/sU1wrAf3C3bYP/Dw9ip1635riPGD2VI5VyamyFnf7BCZjCGaRtsLrZxYxajV+98F0IIIcRtQkK3EOKW0bALtEY+QGr8YZQyaIQO0TssEd1JTZG69++hzn0TMqOgFIQ+dCqQHYWhw5AZRxcmCbRBsnySeuGO67RH4vV6LZ9Y3CTwIoZ2Zli72Lg0h1vRqnbJjyS5+NIGI7uz9Hyf3feUWL/YprrcxTAMYgmH3FCcVrVHda1zKbD3h4Sf+t4SbsImDCJqq23iaYcgDFEmBH7E0pka0/dmr3hORZ5BY93Hsg16rS6F0SQoxdzxMlEIG3NN8sNpzIyC0ABTo2WIuRBCCHFbudoESCGE2LYiDfXAoeZb7zhwA7TMLGF2Ep2fQu/+EIQBVGfBdMCKweA+OPMVWDmBai5jzH0PS95Jb5hYyqbXDUhkHNyEzcS+fL/nOmYydaTI+mydKIzo1H1aGwFzL1ZplXt06j7V1Q6hH2GYBrZrsTHXQEeaoZ0Z5k+WQSmiUKMMRavqoQzoNl4retaqeuhIXb4cdg1Of2eNC8fWWTxTpbzYZGAsTXW5jRu3iSVt/F7I6aeWWT/X4/g3Vzn/dIVeTV2e7y2EEEKIW598VRRCiB+igY30QcLRu9DKInrfP0Af+jSM3QNDh+Cp/6u/hrebRK2fxgg9rjphXFxzSimiACb2FWg3PCrLLUpTaabuKDJ1ZIClM1WalR4oRRhGdJo+XifE70b4vRC/FxL0Qjp1D6XAcgzWZuvkh5Mosx+ElQHpgouONFGg8brh5YCcG4qDeu1ETm2lS6/TD+Wdps+eB4boNjy6LZ9u20cDsaRNdb1N0NMEXkhtrcPpJ1cI2hK6hRBCiNuFhG4hhHgdrTWbg++jPfUhPDuLLuxEr53ur9ttOui9j6MxYekYavgQQSQB6kbolDUnvrXEzMvrOK5JfjhJu+EReBGbiy2iUBOG/RMgbsIilrKprbdZPldl4sAAxfEUEZriRJpu22doOoNpG1TX2uSGEmSKMXJDCbxegOUYxNM2bsJCa008bTO0M3V5STGlFO2Gf0X7dAidlt8P3c2A+nqHbrN/m9CLSGUTuHGbKNQ0N1+3tJ0QQgghblkyp1sIIa4i0opGaiekdmKWHqAweBCjfB7sOLq+jF58FvZ8hDA1utVNvS2oyGTmhTUiHRGL2yyerjC6J0evGzI4kaK62mbnXUXadR+loDSdJjMQZ+54GaUU555bI5V3GdmTRylN6EfkhxO4KYvaWpvd9w6yNtugvNwEA4Z2ZsgOxRk9kMUwI2JZC4zwcnu01mQH46zPNgCwXZP1+SahH5HMuTTLPQBa1R4HHh6ltt7h3HNr7Lm3RK/Z740XQgghxO1BQrcQQvwIIQbtxBjW8T8Hw8LIDMHo/USNNYLYwFY377YQ9DTdVr/X2HAMknmX5746x6FHRzn77Br5kTi5XIKBiRS1lQ5eJ+D4Xy/SbfikCzFG9+Xw2gFBJ+D883VG92QZ2Z0FMySeLmHGI0YPJuiUS3i9sD/MvGSDFQAKCN/QpvSgxdBUhtXZen+D1qzO1CmMJRmayhCFGts1sRx1ue3V1TaYEEvYgBRUE0IIIW4HErqFEOJt6MSGSe//STjzdaLKfL+w2r6P0omVZEr3DWC64CQsvHaA7SpMq99T7PcC2rX+UmCrFxpkS3HaNY/po0WUAq2hXu6y74FhNucb1DY6DE2nsWIGG4t1pu7JEGmfKILWpubsM6to3Z+LPdBIMbw3TaTeZCi4GTF2R4rSzhShHxF2FeWlFpvzTXqdANMy2H1PiU7DI5aw+kPWMw6lqRSdZg83b9/Av6AQQgghtoqEbiGEeBsiDfXS/cTyuzG7NcJYlq5duDzHV1xnRsT00QE2L7Zp1X2iULP3gSG6TY+pIwPMnyoT+P2e40TO6fcoo7BdAyduUV5uUdqZYXh3lm7bY/VinUTOJgqyYAKhycWX+4G7tCNL0NXMvlxl+UyDqTsHyE2Y6Kv0TGsdYSX6H6ZGTrHvoWHO/mCNXtunMJKk0/SorLTJjyTIFOOM7smyOldlsigjJIQQQojbhYRuIYR4m7TWdKw8pPKvbtjaBt1m3LjJ5koLrxVgGAa1tS7Du7IEXsjk4QGSWQfTMaistJk/WSaRcXDiFpXlNqmcy8yLGwS9kMk7irhJg0TGQZkaDYSexusEZIsJuvWAk08tgwbLMthYqHPPT06SmzTfsn2Rjogin+JkHKWT1De6+F5Er+MTS1gUx1OceXaV4akMqQGbqw1ZF0IIIcStR6qXCyGE2BbKSx20jrATBmYMCuNxOo0ek3cUSBUcOm2f8nKTdD6GMhRaQ+BHWDEDyzWIggjPC1g6WyYzkGB8f+5y77UZU8RTNm7CZm22cXnKgGEqIg2zx8so/dahG8COmdQ3O9TKLbQR4iYVyayLHTOob7bJFeO0aj1am/6PfCwhhBBC3Bqkp1sIIcRNTymF331dz7ChMWOQGbZpVBSNjQ6tukd5sc3uu0ukB2K0Gz26rYCl8xUKwymcnolSisk7Clip8LXBCipk6kiRymIHvxuiAMs2MS7NHQ+DCB3RH4r+FtIlh1jSotvqr9+tIxgYT4EJiYxLs9ojOxin0wjIjMbQWssUBSGEEOIWJ6FbCCHETU9rTXYozurF+hXbM8U4ZkwzMJaiutKl1fAwbYMwiPC9ABQsn68STzlgRjgJg2wpjp3SRFeEXYO1i3WchM3+B4dZuVBHa0237VPf6DK6N4uyoh85o8BwIvY9XKKx5uF1QpL5GJ2Kz4nvLdFr94N4faODaSpSeZfqWgvLMcmPxLCSEr6FEEKIW5GEbiGEENtCqmgyeajAwitVwiAiW4wzeTSPYSoWz2xiOBE7jw4QRZqN+SbllSZ77isxvi9Pt+UBmnjKZsehPJG+stfcq2s2l5qM7Spw8eVN2jWPZqVLppTgyGPjFMZjaP325mAbTkR23AIsDEPhNazLgRvAdg2UMjjx18uYTn/b8jmDg48OYyVlGTEhhBDiViOhWwghxLagVcTATpf8+Ag67A8t10RobWBYCq8a4nVaANhxg1TBZWhPipGDCbqNCB1q3LQJxhvDcxhEJNIOqzMNVmfrWJZBaiCG7Rh0Wh6dhoGd/tFzut/QZq1J5hzyQwl6zRCNZnhnloUzZZJZh/4a4P3fv7nQZnh/XIabCyGEELcYKaQmhBBi29Bao+wQIxZdLoIWRRHDu7JvuO3o3ixYPpEOcVIaN8tVAzdALG0RT7s0yl2gX0DNtg0sxyDoRvQamqhto5R6x22OJW1q6x0qqy2qq21a1R5+J8Ry+h/Brz5mrx28q8e/WRiGgWHI1wohhBDi9aSnWwghxLaXHDTY98AQKxfqhKFmaDpNZtiGq6ytfTXKDhnbl2FzsU285hFPOViOQbcZcGF5ncALSQ/EuP+Tk7j5d9YTXV5uM76/wNpMnWatB0ozNJ3F74V0Wz5+L8SNW+TuShBF2294uVKKTlmzcr6K34soTaXIjjhgbL99EUIIIa4HOSUthBDiFqBJDCp2P5hn3yMFMiMmqHcW+sxkyKFHSwxOp4iiCDdpU11tYzkmYaSpb3Q598w6Knr7w8yVUtTX28yd2iSRc5g8PIDXjUhkbGJJm3bDI4wi8iNJahsdeBvLkt1sOhXN6SdXaNU8EkmH5qZPfdnf1r32QgghxLUkPd1CCCFuGe+1p9jNw5EPjrB6rs3mfJNExqFd712+vtPwCXoaM/72Hk9rTX4khaEUzXKPynIbraFT89hxR4EjHxgnCkKa9S69VkBrLcRJKpyUujx8/mZmGAab803S+TgKg/PHyugwIlWIcSQ1ip0NfvSDCCGEELc46ekWQgghLtFao9yA1ICDBtpNj1cHk8eSFvGMheW8sx7c8X05pu8oEvQiOg0fHWn2PjBMp+HhtQPmT1XxmhoDg7M/WOP4t5a5+HwNHWyPXu8wiEhm48wer1Bf71Bb77Ix3+T0k6uYykJFJto3MJR85RBCCHF7kp5uIYQQ4nXSwyY77xygvtGlttYmkXHIDLpMHR1Am29v6bBXJTIuuZE4I60ssbSNaRqsztQojKZobHZo1XrU1jr43ZBDPzZKebVBealFZiBGftK+Tnt4bURRRGkqzcLxOvX1NkopokjTqXssnKqw++4SF06sEnRD8iNJxg9mMNybvwdfCCGEuJYkdAshhLglKUx6jX7Ac9MGmh8dlpUy8FuawAtJFE0e/oUpmhseYRiSyFpYyXe+nFevE7B8vkZ9o0unabN0roppGiydrZIfTjA0lWX25U3smEltvYMTs/C6AeXlFsWdA4ThOwv5N1o8r7Ad83LgBvoroWlo1T061QDTgc3FJoEfsuv+PCiNDkz8JjgxExX3t2UROSGEEOLtkNAthBDilhP1DC48v0ljs78EWLYYZ+ruPIZzZbBTSuG3FL12QCzhsDpTp1n2sB0LHWmGd2ZIlhQoE3h362cbCgwLhqeznPju0mvbzf4a4KWpDLGURRBERIHGivWHYSez7rYIopqI3GiCeNqhVeuB6mfuHYcHaGx2CLwI89LyaLW1DkEnT6usOfXX89TWO8RSFgceHqW0O4Y2ZQ64EEKIW4+EbiGEELcUpRQr55qXAzdAbaPD+ozL8P44Wr8anhXlix6zxzfRGnLFJO2ah+9FrM+XAZh9eZM7fnyUwd0u+l2GbjtmMbonS3mhg5uw0BEoA9L5GM1qlzCMSBVcamsdcsNxystNQJHKxvFbCjvJD7X55mMYBqki7L53kEa5RxhExJI28YzD0tkypv3aXG5lKCLP5IWvzVJeaqEj6DR9XvzGPPcnpslMbOGOCCGEENfJtg/dvu/zL/7Fv2B2dpZ/9a/+FVNTU5evm52d5Qtf+ALnz58nk8nw0Y9+lE984hNb11ghhBDXnY4MKivtN2wvL7UY3peES8PM/SZcfHkTANM2aNc9lGGwPlu7XGY0CCLmTpTJjY5gJd59m3LjDk7MZvl8Da0VhlL4Xkg86ZAdjBOGPnvuKwGKKNSYtuLcsRWUodj/4DBu7t3/7uvGs6gsdum2fZLZGMUdKZI5l83FBm7KJJ6x8L2IePq1rxrD0xkamz1q6x30pU78KNC06z7lxRYD03n8wNuiHRJCCCGuj20fuv/Tf/pPFAoFZmdnr9jebrf5zd/8Te644w5+5Vd+hbm5OX7nd36HZDLJhz70oS1qrRBCiOvNMDTxlI3XuXKocjxtowx9Oez1Wq/NlY6CiHgmRq8ZEEUaw1CXHkuhlMJrh1iJd1d9Owwjwp7CzSru/clJnv/qPI1KF8s22HFwgFaly557h3DSsHCyjmErNGC5Jn43ZP5UhT0PFm6aJcSUUnQrcObJFeqVLpl8nJfPL2G7JvnRJBMH8vi+hx1XvO9TU2wuNuk2fQbGk+TH4qyf7WK7FhCiFPheSBhEGKaBMmRtbyGEELeebR26jx07xksvvcQ//af/lGPHjl1x3Xe/+12CIOBzn/sclmUxMTHBxYsX+fM//3MJ3UIIcQuLdMTYvhyNcpco7A/LNkzF6J5sf450aOJ3NW7CxDD6xb+0BjumQFso9VrwS+VcDAvclAXvMPQGbUVrM2TlxAKdZofaZpvxvQVK0ymGd2fQkWb5bI1W3QOl0DoiXYizulqlXeuRLSbIDDi0Gx46VHCTrCAW9gxWz9dZuVhnbG+e88+vA1w6OREwe2KDQ4+MYiXAjEWM5ZMYhkEYhnjtkI3FJoXRJIunKwDYMZPCaIJMKUYQ+Fu5a0IIIcR1sW1Dd7Va5fd+7/f45//8n+M4zhuuP3PmDAcOHMCyXtvFo0eP8qUvfYlms0kqlXrDfXzfx/df+8BXShGPxy//fLt4dV9vp32+Fclx3P7kGL578YLi0I+N0NzwQEGq6OAkobEaMfPCCn4vxI3bjO4eYHmmTOhHVFZb7DpaIpGxmT9dwXYMzJhi6ugAVlzTLw/29rQ3NGd+sEpzwyPwNKYNEwfz1Na6bMy3cJKKVjmg0/BAX1ofXJnMn6xSWWmSKsQwDEXgaQojSQxbo/XWPg+UUvQa0Fz1MZTJvvuH8bo/NFog1Pi9iPpGj4XTVZq1DtNHi2THLKIowjAM1i+0qW90SOVcjn5ogsZml2TW6Q9NH7DQOropn+/yWtz+5Bhuf3IMxXa2LUO31pp/+2//LR/+8IfZtWsXa2trb7hNtVqlVCpdsS2Xy12+7mqh+4tf/CJ/9Ed/dPny9PQ0v/3bv83g4OC13YFtYnh4eKubIK4BOY7bnxzD92D3az/W1jucPjmLbbnYlz79ygttjjw6hd8LiactbMcilfcYns5huxaJjEN6IPYjv+T12j5eNySWstGRZv65OQaGMqiohVIKJ24R+Yp42iEKWrhOjGq3Tuj3P9PiKZcX/3IeANsx2Zhr0ar67DiQZ89do+RK72FC+TWyfKHG0ol1zj23htfpDwk//OgoiZSD1w0xDAOlFKZtEU/GiHzF6rk2o9M7yAzEWZ+rs/TKCvX1HqGvaZS7/Yrn1R5TRwYYKKVJ5tyt3s23JK/F7U+O4fYnx1BsRzdV6P793/99vvSlL73lbT7/+c/z4osv0ul0+NSnPnVNf/+nPvUpPvaxj12+/OqXrPX1dYLg9lnGRCnF8PAwKysrN3XFXPHW5Dhuf3IM3x2lFJGvMEzQKkJh0NoIqSx1WZ+vE0tYGD80QKrZbJIeMqmtdjn37NrltaYLI0km78zRWqle+Qu0QWsjoLHZI5awcOMOF15co9cJSOVcpu4oEkYhZ59ZpdcMAANlaA6/f4x6ucnu+4psLDaIogjLNRjfl6ex2SXwIty4hWGBEzMIvIB41qYXNVlert2wv99VhRYb8x3mT5WxHROvE2AYio2FJsO7slx8aQMn69Cp99h59yCoiDAKMQzF2kKVykadE99axombhGFIeiCG1wqIQiiMJpg5ucorzy6y/+EhrMTN91yX1+L2J8dw+7tex9CyrNu2g03cODdV6P74xz/OY4899pa3GRoa4vjx45w5c4a/+Tf/5hXX/dqv/RqPPPII//Af/kNyuRzVavWK61+9/GqP9+vZto1t21e97nZ8g9Za35b7fauR47j9yTF8+6KuweKpOpXVNm7MYnRfnigIOffcGoXhFO26R6fukRtOYF4K3pat0L7BhRdeC9wA5eUWhbEkmWGbXjNCAW7aYOWVFotnq/3f50O36TO6L0evE9Cs9lg8U6W+1kNrsByTwNOEvqa62saOG2SHXIZ2JxmayLJ4rkplpUV+KIlpGVi2QafhY7tGf1mxoksYbe1JX+0bXHh2g24jpLLcJtKabDFOp+FR3+wyfiBPYTRBs9Ij9CNsx+TMD1bxvf7Q807DY2xvnvpGl3Qxzp57hnjpr+ZRKOyYSafeZXR/jma5x+qFJuN3pG7a9cnltbj9yTHc/uQYiu3opgrdmUyGTCbzI2/3d//u3+Xnf/7nL1+uVCr81m/9Fv/oH/0j9uzZA8DevXv5gz/4A4IguDyv+6WXXmJ0dPSqQ8uFEEJsbwYG546VKc+36TR8ohA2F7oMTaXZmG3huA7ZYoLaeptOzSeWtsiPJIilbJrrIa1NH8sxsFzQQBRAfc1j5XyDZqUDQHYggWEqnLhJPOXSrQfUy13iSQdjWNFteYRhhL5UAV3ZgFYYcZPAjyhNZ7hwbJPCaJLI74fXdL4/fzsz4NLrhFi2gWmaDO/JkB2x0IRvud/XW33Fo77ZwY25WI5Jr+PTrPSIJS0s26C+2aHd7C8BZjs2r/xglVjSRhkKJ2YS+CHrc3UGRlM0q11WZ2qkC3GUAssxaDc91mYbZIoOjc0eSqW3dH+FEEKIa+3drX+yxYrFIjt27Lj8b2RkBOjP8RgYGADgkUcewbIsfvd3f5f5+XmefPJJnnjiiSuGjwshhLh1eC1Neb5NbaNLGPSXBgv9iG4rIAwjZo6tk8g4jO8tkB9JMrF/gMHxDHMvNlg4VaGx2WXlfJ12JSToQrvqEXRCLr60SascgIbycrtfSTwymTteodP02XmkxMwLG5x5Zo1m2See7BcGK4wmyBQTJPMuTsIkkXVZOVcl9DREitNPrtJtBVRW2zz/tTkyxQSJjIMdMylNpdl51wDa2NrArZSiUen1/76dgOkjA1iOQeCHuAmbkT05FJAbTBJL2aTyLpGvifwIvxuC7leOD33N0M4se+4ZwrRMUP3tpmMSS9gYSmE5Jvnh+E3byy2EEEK8WzdVT/e1lEgk+PVf/3W+8IUv8Gu/9muk02k+85nPyHJhQghxizJMk3bdw3ZMQl/TrHSxXZPhnVlypRSVpQarF+ooAyaPFKlvdqivdzj33DqmYzB9pMj5Y+vUN7sksy7JfKzfoxu36TQ93ISJ7Zosn6+RzDsMjqfJDSU5//walmNcCuUtTMvg6OOj+L7P+sUWQS8kNxwnnrEpL7XYmG/htQPqGx3G9uUAiCLN+WNrZAdj2AmLdr2HViHvpGL69aC1Jp50qK30CIOIZMZl991DmLZiYDSJVoqzT6/QaXnkSgkyeZOh6TSbS02UgmathzIUqbE45cUmS2drZAfj6FBjxS16TZ9Oyyc/nCQ/lCI/4aD11p5oEEIIIa61WyJ0l0ol/vAP//AN2ycnJ/mN3/iNLWiREEKIG82KQ2kyw/pck06jh2UZhF6EEzNxYib5kSTKgNJklnQ+xsnvLlHakaHXCVBdOPf8GvvuH6Zd98gOxmnV+8t7Ncs9EjmHMNAYVkS6EMN2TWZe2mD5XB0nblGazLAyU8V2LTp1j/pKj4mDecb25lg61WLpQhm1rFibrWPZJpZjogxFda1NZiCOm7TwOwHdZkCr7jF5eIB41oItHFqulIHfUOjQJ1OMsbnUotcNWLlQZefdg7RbPRZfqWHHTMLQolnpB+xddw0SeCG19S7xpEUqF6MwEmdzsUNxLEW2FCeRcVg4U6FT9xmaStPrBrzwjXke+hs7iRW2bJeFEEKI6+KWCN1CCCFEpAMmjxRw4w5rF+soU5HK9cO17VocemwUxzVZOFWmXfdQCgwLDEuhgNCLWDlfpbrWZeddRTYWmgxNZahvdlAoTKv/rzSV5qW/WsCyDSzHoLbRJpayyQzEqay2Mf7/7d15kOR1ff/x5/fs+5qjZ3Zmdmd39uRYFhAQkfzEKEc0BkNZOTQqGiBxIVVU/kBKtKKJJFVWQlIVg1IBQygDBg0GY4T80Mjvp6ICosByLXvP7txHd0/f3+v3Ry+Dy6HkJ8Pszrwef9Hf7pl597zZ6X715zIN5ifr7H+yyrY3D5DMueSLSSrTTQzDIJF2iCUdDAPG95RJZhxOfusA8xM1mjWP4nCG9ad3geUt2+8y8k0OP7XA+J4KpckGm97Ux/pTe2g1AmIJm2atjRO3icKI+cmjx6LFLLLdCX72vw8TS1kUN2RId8UJ2gFTB2qMPV8iCmHiQIXT37EWTGjVfOYnarQmfAwbpvYvsL4noynmIiKyoih0i4jIipHqNUnN2MSnbWbHa8weruF7AZgGtfkWT++a64x69ydpVD0qs03WndTF4WfnsR2TMIKetSnK03XKUw2cmMXIjh6yPXGSBYdcMc7zP5rpzPo2wLINTMNg9sjC4g7dw6d2k0g7BK0Uo7tKWK6JaRqMnN5Lq+5TK7WYPFBm/Wk9tOo+7VZIxjEYOilPIuOQ7rHBWb7ADTB/uMX06AKmYZLKxNnz8CR9G3LEMw57DlRYM5LDn23RKHudI9rCCAyDyf0LhERMHlzAHqsxdHKedDbJzOEyC3NNoqNZ+rH/OsjJ5w+w99FpwjAkAtyjIV5ERGSlOSE3UhMREXlFZkjf5hR2wiLwo07gBrae3cfY8yVs28Br+WDB8CndTB1coNXw2HxWH1ve3M/GM3uIJSwW5pvEkjbtRoDvhwyekqEwbGMlA/L9cTKF2OIU8a7BFNnuOIm0w4btPZ2p1RMtnnlonMO7SxzZXaJWajM7XqW4Po0dM7Fsk0NPzZAtxmnW2hx4YpqxPXOEkQ/O8h4RZlkWUweqVGfa1Mtt5ic6u8Ef2V2iPFUn35NkfryGaYLvBbgxG0IwTIPQD4knbeJJG8sySaZiWLZBvdzCdi2gs4Ga1w5p1X2yvXEMo7NuPZaw6V2vUW4REVl5NNItIiIriuEGnPr2PrrXpJk9UgNg5sgCiYxLrdwilrLx2x7NJpzyvwZJ51zchM3kgTL7nyiz9uQCmAbV+SY9azNseUs3OD5GZBK2DbqH00zuq9C/MY/fCmkstCmuzzI7WmH/rlmGT+7m4NOzpPJxGpU2URhRnmpw+jvX4iRMCmtSJDIO5akmkwcqWLZBrDsGBqQKLrC8oTPyTLxGAJFBY8HDb/tgGEenlftEQSdshyFse+sAfsMjDCFfTGKY8MwPxzsbyx2dDRAREYYRBpDIOPheiGmA5ZgMb+/myLPz2LHOju3JvAUs74cOIiIirzeFbhERWXGMmM/A9gTJvMP0wSrpbpdYwuaZH4yT6Y7RqAS0qj6pXIxmpU1pqk4YRHQNpgiDEDdl0N+dZWBLFisR0piDA0/O0Cy3sSyb4e1Fdv2fI/jtEMsymB5dYOs5/fQMtgjDiHjCoTRdx1yceg2V2QZbzy1iZ32iKCJZSOEHHguzTZJZh7Und2EnI6JlnmFdnW+TKyaolTxKUw0sxyJoB/SNZHn+kSmGT+umuyvNoadmceIm284bYO+jUzz1/XGK69JsOauffbumqMw0SWYcgiBicGuBfT+dJgwjAi9k+E1F6uUWpekame4EvcNp2o02hhsu+/MXERF5vSl0i4jIymSG5Ict4tkslekmbsLm3PduYHxPhfJUk0JfCtM2ePahccIwIpF2MS0DvxWjMJQm1xUj1WPj1yOe+9EEYRDRqoU0qjWisDOQG/ohgQdRCPsfn2HjWb1EQUS74cMUtNsBpmkAEW7cxvM9rKOh0k6FjJydJ/TBdCCKjpPAaUBpusbms4vk+5J4rQADg7E988RSNl39SQ7tmsNrBYyc2cvj3z5EuxEQi9vMHqlRKx3mzEvWEUUh3RvjtCsRsaRFpjtOrdQmiiICPyCeidGoeNQqbfpGMgydkiOKNLVcRERWHoVuERFZwSLiBYgX4gB4VYN4xsZ0kjz3wwnWbMwT+hGGaZDIOJQmG5Sm6iRzMfaNVtiaKtJu+IRBhGEYtOoebsyi3Qzw2yGlqQYAlmXSWGhj2xYtz2Ngc4G5IzVMy8S0DNadXKBaamDHcvz89PGIEMPm+AjbRyXzFm7CojJbI9PtUplpM3NogVQuzsbTexl7fp5qqUlhTQrTNGhUPQwM7Di4toXvBzTrHoPbU4SRj5szyBHHcmyyvUnmRhdo1iMq0w26BpPkehP0b0121rOLiIisQNpITUREVo3avIfvhVRmGtixzkug7Zrk+xJEEdiOQeCFtOoe5ekmR54t48YcAKIownYsGrU2vesyLMw1gaMj3mFIpjvBwlwTyzEpT9XYeGYv60/rYsOOHuamqsRTLvGMtVxP/bUzQza/uZdsMUGrFlCZrtMzlMZxLQ48OUM87TK4pUAi42A5xuJGaJ2v7RzBZsdMMDofLkRRhJOAVq3N4WdnqVc9Rp+bpzzVoNCXYv2ZeQVuERFZ0TTSLSIiq4ZhQqPWJpawWbutC9M2SeZi1Ept/HZALGkzdFIXC3ONzvFe820SWZt42qFZ9YhnbJo1j3jSon9jnkNPz2KYBsmsS/dgiuaChxXvhHYnYRHP2ASeweCWAoU1CYLw+A+XpmliJqEwEOfw0/M4MZOpQwsszDbYsKOHdsvn0FNzJDIOxXUZ1mzMMn2ouvj13QNpCv1xwjBYvNaqRux/cpaugSS9Q1kGN+dxEzZeO2B6X4NE1iUyQtIF5+i69uNo6F9ERORXpNAtIiKrRqbHxX86wHEtUlmXZDqObZnMHqlSK7VJd8VJpBxa9TYAuWISXJ8t5/YyN9pgYa5zDnc6H6daaZPpHqDd8GlWPaYOLbDt3H7aLY/+TTlmD1fxA590JkXg++T6Y0RR8EsqBMMwME2zc371Gxg+DUxqMwHTh8pYtkmhN83MaI0wjIjFHQY25Zncv4BlG+SKCVpVj92PTHDWuzfQv7HO3FiNfF+S4oYUdubY5xn6EcW1Wdy4zcP/cQDTNGg3fNaf1kO6y2HX98bY9KYiBx6f4eTz+3Eyb9jTFhERWXIK3SIisuKZhoVh2DjpkJPe2sfU/iqtmk95pkZ5tk7XYILBbTlqZY99P5tmaFsBwzQYOilHFPlY8Yjiljj9ZpIgCICA4XiOPY9O06r71MstugdTjO2dZ36izvYLBjn1wj6aFZ9sNoNvNYmMXzzKbVk27ZLJ3GgNPwiJp21yAy5m7JcH9dfDwoTP849OAZDrTbHn0SlSuRgL800gwknY1Eotcn0JWg2PXH8CN2nSarUY3JFg+E0ZwiCkVYtoL0AsbREZndoTuRi2W2P/E9O4MYtW3ceJ20wfXKDQ14cRQWWyge1ajO2usOHsnM7rFhGRFUOhW0REVjSvYnPk6TKTBypkuxOs39HN0PY0hmEw8Wwd0zGxDIvJfTXaTY8tZ6+hd20aN2lSq7TxpnxSeZdEwTgauDvsdMjJF/QxtbtBtdyiOtekWQ8p9CeZHVugf1uCZLdJ75os4+M1+AWD1u0Fi8NPljjyXIl0IYbXDoiCkP5NOYbflANzaaelG1gc2T23eNvEYGp0gQ3be0ikHWaOVElkHLoH01gxSOYcLLezXtuyTaIoot0MGHumytTBCkQQi7sMn9qFFYN4NiCZcWkseDSrHi9sUt4ywfdCCv1pwgDyXUkMy4DQZLnPKxcREXm9KHSLiMjK5bns+u5hJvZW8Nsh43vLHHhyhvN/ZzOZNdA9lKC1ELL3pzP4rYDAD/GaAVEUksp1jhCrV9qMPj3H8KnddK13j5nybVgRC6XOjucAbrKzOZvfDogCMF7Dvml+w2TXf48zuXeBZs1j5nCV/pEsXsunVvKoTfuk+pbkt7MoiiDwXgy5hgX9I3kaCx6xhM3Jbx0gnnYwbSjP1BYf58QtMj0uEFCZ8JjYUyH0Ilr1gJlqnVq5Ta43RqY7TraQwmt3PrQwzM4xa2EEjmuSKyZIpl1mx6vEEjalIy1yQ7bWdouIyIqg0C0iIitWdcZj7PkyYRARBJ1Q2Wr4zB6uEhpxckUX3w9pVNq0Gj7ZrjhzY3XmJxuMnN6D3w4wHYNCf4bRZ+bJD/RjOC8GwSAI6BpKLYbuF3StSWHFXttRYNXpFq2aj99+cRR9Yn+F9du7adU9orBzzvdSMsyQ3uEMh5+dByAyIlpVj9kjVUzHYHT3PNmeBOe8Zx2V2QTzE3WSWZeutUnMWIBpmswcrDA/VieWcChNNzBNg9JEneJwmvE9ZTLnJNl0RpFnfziBaRlgRvQMpUnkY4z9pMxzoxPE0y7R0bXsmWIXhvPGTK0XERFZSgrdIiKyYkVhhGkY+P5LNvYKYW68Rn5NDACv1dm5vFZpE/ghRgimZTI3VqF3OENlqoHlGvjtCMc59mfk+h0Gt+QZ39sJ9/m+JIMnZwnD8NjjtF5F4EcYJrhxG99rHy0cTNMglY+RKFjA0k0vNw2L0IPihhSBFzJ5oIIRGvheQNdgqvPBg23gxk3q1c4IdGFdniiKiI7OE498E78dEQFh2PmAIAwjHNci8CNKk00q0w3CKOC0tw/SbnU2s2vWfVpVj8n9ZaIQqqUmud4EB5+eY91pBWL5JXvaIiIibxiFbhERWbGyxRhdQykm9lYWh50txyJdcAkiD8MOyfUkwKRzBnfFAzq7ltcrLcIwoln1MGzo7U/hJk0iXjL6aob0bU3Qsz4FYYSdgDB67euR090xnLhJqsvF9wK8VkC2J0EyF2PopDx2InhNI+b/P7yqyejTc1TnWiRzLutOKdC3JU19JmBusnMMmB1/YY58ROi/EKiPfX5+KySRsUjn40RBhGWaGCYMbikwP1bDb4XUS21S+TiVmRaT+0oU12eJpxwW5pqdcfzOzHzajQDbNQkDrekWEZGVQaFbRERWrMhpcebFa9n9o2lGn50j3RVj81l9zE8vMHJmN2EYkh9wOeX8Acb3lGnW2uSLSXLFBJXpBvVym/4NOeyEycDm7OJu3C/7OVGE6XbuC/+HATmeh23n9XHwyXkSaYd0V5y127pI9dhEdmvJAnfkWTz3owm8Zqfuhdkmzz40ySkX9JMsmNiOif9z67xNyyBZcHilDc7smIEds+gaSBEGnanqrXrAwnwTrxUyuCWP5ZgceGIW2zLY8uZ+eobSPHr/foZP7sF2TAIvJAJME3K9cdyUNlMTEZGVQaFbRERWNCfvs+NdvWx9a5Fm1aPVaLPxrG7sZCfNmomAgW0pLMdg05lF9u+apjzdpDLbJJ2PkSvGGTgpjZlYmvXFURSRKhqc8uu9hD6YbkQUBS8fUX+dNcr+YuD+ee1aSLLLYtt5fRx4Yo5qqUUy4zK8vQs7Eb3yhwBWiGmaHH5mjpCIeNKmOJwj3ZWkayDNzOgCu743dvQJw8L3xjj9nWs56bw1zE1UGd7ezZHn5iGCXF+ckbN6sOIK3CIisjIodIuIyIrnhz52BjJZg3Tk8vMbk0VRRLzLYG0ix/juCht2dNOuB5h2D/GURff6BNjektcYGQGG89o2X3s9GOYxP5xk2sUwTZ7/8TR23GRgU5Yt5/USehGmCxHBq+4mbhgG7WabwmCSoB1imAb1aoNGtbMu3WuFOK6F3w5wEjbpvMvkaIkd7xzCTZqUpxqc9o5B4kmHdK+NnYy0c7mIiKwY5i9/iIiIyMrwi4KcmfDp3ZCiXm1RKdXBDCgMxd6QwL0cEnmbVM4l9GFhpkW7GbH3J9PUSx6tmsf+J2YpjTWx4hGG+YsDcBiG5PuSGGaEHTew3M71dHeMZN7Bb/kk0jbZ3gRu0sK0jU7oN0Pya21Gzsmz5uQEuXUmViJU4BYRkRVFI90iIiJHudmIkXPyRKGBYYZE0Qo+ssoM2HROkb2PzJHMximN10kXYiyUmph2nHjOoj7nU55s0qp79A5nyA+6BG1YmGkTBhHpLhc30wnImX6XvuEsUwcXiIhIpB3Wn9aFFYc1m3NM7q8QegGJjEs8bdG3Povphp0zwoMV/HsWEZFVT6FbRETk50RRCMYbN817uRiRhVcLiSct7C6X0mSNZqMzqt9qBPSP5Nj9yBS5Ygw3aVGaaBJ5JuWZKvNHzyU3DNjy5j6S3Sa1GQ+/HdC3PkcqHyM34BKZne/Xs8nlLdkRxveU8do+vesydK2NLR45JiIispIpdIuIiKwyfs1kzyNTNCo+8xN11mzMM7SlwLM/ngAgnrKpzrfIdMVYM5KnVvKolzxmD8+QSDvkiylKUzWiCA49M8/Q5gLPPzp1zM8YoYfcUOdtRhiGJHpgUzEPGIRhgHYmFxGR1UKhW0REZBUxsNj/02kaVQ9MSOViHH5unpPPW8PGM3uZO1KjezCJ7dqkCjGe/eEUldkGBpDOx0imHeolDydm4bUCLNNg/Ply53ubBvmeFGEYUZluk18TJ7L8xZ/90vO9RUREVgOFbhERkVXEb0RUS+3F227KpOAkadV9ihvTbDyrC9MNacxFPPqfozQWOo+NgHrFI4wiFuaabDyjh9JMnWxXnMpsE4Cu/jS1+TahH1EPPcZsi/6tSQxXa7ZFRGT1UugWERFZRUzbwHZMfO/FUedUwSHfn6RWatFu+OT6YpiWiWkYmKZB5Ec4MQs7ZtJuhBiGwYEnZwGDtSd1kcw7jO2J8Johh58t0ax5uDGL8f0lLHuI/lPiGuUWEZFVS0eGiYiIrCKmG7L25K7F25ZjEku4HHhymrHnSxzcNcvT/3eCRskjCAJShRh23CIIQqIQ3LhJ33AW0zKw4wbPPzpJuifG2q0FGpU27bqP63aOBQPY89gUkWct19MVERFZdhrpFhERWUWiKKKw1iWe7qc61yKRjrH3J1MYP5eLvWbI+L4y607pZt9Pp8gUYvheSHE4S++6NFOHS5gOQITfDmhUPNJ9DpZt4qZeHrADL8BU7hYRkVVKoVtERGSViQiJFyBeiBE2TYKXTv02DFoNn0xPjG1vGSAKIZFxaVTbPP7dUVLZGIZpEPohTtzEsjoT5/pH8pQmG/heQLPuYdsmXYMprLjBCj+BTURE5FUpdIuIiKxiVgIy3XEWjm6GBmCYEf0b8jzz0BEs26a54OG1At70rmF6BjJM7C8TBhFu0qI7k6I80Wbs2RZTBxZwYhaNhTaFYopkwWbjWd1EaCM1ERFZvRS6RUREVpvAol7yCYOIZM5iw44u9j02S7XUwjQN1mzM06y1ITJpVNr0b8zhxmzq5TYjp/diuya+H5LrSYAZMrlvgWx3nFjKIZawiWdsuvrSDO1IERr+L69HRERkBVPoFhERWUWClsWeh6eplztHgVm2xbbz+tn85l7a9QgnAYZh8r1/2cfCXIvhk7s5tGsWrxWQyrlsPKtIvi/J1IEFmjWP3nVpxp6bYupAhVqphWEZjJzey+5HphjavhG0lltERFY5hW4REZFVwjAM5kbr1MttbMcknogT+iGHn6oQeD7VhQZda1J0D2TIFBI4MZsju+dp1Tuj1ZZrMbGvQrYrzvToArZrEoXgtwKchMW6oW6iKAIi1p2ax7RAB4WJiMhqp9AtIiKySpimSWWmQSxpY0Y2zz86BSGku2JsPbefhbkmc2M1HNshlXdxUzbjz5cBiCVt3JhFo9ImmXHBgNCP8JoBuWICyzE59NQcYRARBiHnvncEH2+Zn7GIiMjy0zndIiIiq0QYhmR7EiTTCfY+Nk0q5zK8vRsnZnHgiVmKwzniKRu/HTA7VsONWXStSZLtjuPELNqtgMAPsV2TZMYllXcp9CVxYjYHnpgl9ENMyyCdjzGxv4RXXe5nLCIisvwUukVERFaJKIroWpuEMMI0DbrWpHn+kUnmjtSYOrjAoV1zFHpzRJHBlnP6gIjuoTS+F+AmbEzTIJV3CYKQdtMj251godQkXYiRzLgksjFsxyTbmwAjolXTruUiIiKaXi4iIrKKWLGArsE0fRuylCbrOG5nBNuJWfheyDM/GCORdTnUnGPdqV0MbMszsCVPu+HTqntkeuJUpju7nHcPpFiYa9FueDRrHvG0QyzlUJqq48RMQs+AyABDp3SLiMjqpdAtIiKyihiGQUSAE7dpj9fwvRDLMkjlYtTLLZyYhWkZVOeajO7qrNE2TMj1xCj0Z9j3+CwT+8pYlkVxOMPEvjJ+O2TNphwLs018L8R2LNad3MXsWBXLTZEqamKdiIisXnoVFBERWUWiKMK0DCzHYP1pPaTyMTJdcTDA90K6BlLMj9dpNwNqlTahH3LwiRkqcy3K000aC22SORcnbtGs+YR+RHWuSXE4Q/9Ilu7BFMV1GaZHKzQXfEqTDUxTbzdERGT10ki3iIjIKpPqtkjmYsyP1ehek2RqtEqqEGNoWxe1cpNWzcM0DWJJG98LabcDFmabREFEFEW4SROv0QnbbtIi25vA90Oef3SKwA9x4zZOwqRabtG7bu1yP10REZFlpY+eRUREVhkzFrJuR5ZNb+ol1RXnlP81wEnn9mNZMD9WxzANnKTN1jf3M75vHoAwiLBjL75t8JoBh56ZI9edwLJNmgseqXwM0zIxDCCCKIR42iEMdVq3iIisXhrpFhERWYXMmE9u2MSwczz9f4+Q6UmQLcY55W1riCcdbNfkuUcm8FqdwJztjROGIRtO72H/z2aoL7SxXYNYxmEgkyeWsClN1nHjFo2qRyxlkelJkC5agHYxFxGR1UuhW0REZJUKw5DMgMHpvzFIZbqJYRh0Daaw3Ijx3VUy3XHiSYe+9VniWYvudUmsWIib6GdyfwXbNqlWGixMexBFrNmUY3T3PD3rkrhJi41v6gFLgVtERFY3hW4REZFVLIoi3Cz0ZGNHr3iEQP+2BH2bk5iWRRSGYIZEUUAEuEmozNYXv0csbUJkMHhyluEz8rRbPrGkBbYCt4iIiNZ0i4iIyMtEUQRmSBh5REbQuX2UmzEY2po/5vHrTingZCOMmE8siwK3iIjIURrpFhERkf8ZI6K4OUm+P0GrHhBLWThpgOiXfaWIiMiqo9AtIiIi/2MRIU4GnIyJwraIiMir0/RyERERERERkSWi0C0iIiIiIiKyRBS6RURERERERJaIQreIiIiIiIjIElHoFhEREREREVkiCt0iIiIiIiIiS0ShW0RERERERGSJKHSLiIiIiIiILBGFbhEREREREZElotAtIiIiIiIiskQUukVERERERESWiEK3iIiIiIiIyBJR6BYRERERERFZIgrdIiIiIiIiIktEoVtERERERERkiSh0i4iIiIiIiCwRhW4RERERERGRJaLQLSIiIiIiIrJEFLpFRERERERElohCt4iIiIiIiMgSUegWERERERERWSIK3SIiIiIiIiJLxF7uAk4Etr06f02r9XmvNOrjiU89PPGphyuD+njiUw9PfK93D/X/hLwRjCiKouUuQkRERERERGQl0vRyeZlGo8HHP/5xGo3GcpcivwL18cSnHp741MOVQX088amHJz71UE5kCt3yMlEUsX//fjQJ4sSmPp741MMTn3q4MqiPJz718MSnHsqJTKFbREREREREZIkodIuIiIiIiIgsEYVueRnHcXjf+96H4zjLXYr8CtTHE596eOJTD1cG9fHEpx6e+NRDOZFp93IRERERERGRJaKRbhEREREREZElotAtIiIiIiIiskQUukVERERERESWiL3cBcjx57HHHuNrX/saBw8exHVdTjrpJK677rrF+2dmZvjHf/xHnnrqKeLxOG9729t4//vfj2VZy1i1vBLP8/jEJz7BwYMH+dznPsf69esX7zt48CC33XYbe/fuJZvNcskll3DppZcuX7GyaGpqin/7t39j165dlEolurq6+LVf+zUuu+wybPvFP9vq4fHv/vvv5z/+4z8olUoMDw/z0Y9+lE2bNi13WfIKvv71r/Pwww9z5MgRXNdly5Yt/MEf/AEDAwOLj2m329xxxx089NBDeJ7Hjh07uOKKK8jn88tXuLyqf//3f+fOO+/kXe96F5dffjmgHp4I5ubm+PKXv8zPfvYzWq0W/f397Ny5k40bNwKd87rvvvtuvvOd71Cr1di2bRtXXHEFa9asWebKRV6dQrcc40c/+hG33HILv//7v8+pp55KGIYcOnRo8f4wDPmrv/or8vk8n/3sZ5mfn+fzn/88lmXx/ve/fxkrl1fy5S9/ma6uLg4ePHjM9Xq9zmc/+1m2b9/OlVdeyaFDh/jCF75AKpXine985zJVKy8YGxsjiiKuuuoq+vv7GR0d5ZZbbqHZbPKhD30IUA9PBA899BB33HEHV155JZs3b+Y///M/ufHGG/m7v/s7crnccpcnL/H0009z8cUXs3HjRoIg4K677uKzn/0sN910E/F4HIB//ud/5rHHHuNP//RPSSaT3HbbbfzN3/wNf/EXf7HM1ctL7dmzhwceeIDh4eFjrquHx7dqtcqnPvUpTjnlFD7xiU+QzWYZHx8nlUotPubee+/lvvvu4+qrr6ZYLPKv//qv3Hjjjdx00024rruM1Yu8Ok0vl0VBEHD77bfzwQ9+kIsuuoiBgQGGhoY477zzFh/z+OOPc/jwYf7kT/6E9evXc8YZZ/C7v/u7/Nd//Re+7y9j9fJSP/3pT3niiSf44Ac/+LL7vv/97+P7Pjt37mTt2rW89a1v5Td+4zf45je/uQyVykudfvrp7Ny5kx07dtDX18dZZ53Fe97zHh5++OHFx6iHx79vfvObvOMd7+Dtb387Q0NDXHnllbiuy3e/+93lLk1ewQ033MAFF1zA2rVrWb9+PVdffTUzMzPs27cP6HzQ9d///d98+MMf5tRTT2VkZISdO3fy3HPPsXv37mWuXn5es9nk7//+7/mjP/qjY8Kaenj8u/fee+nu7mbnzp1s2rSJYrHIjh076O/vBzqj3N/61re47LLLOPvssxkeHuaaa65hfn6eRx55ZJmrF3l1Ct2yaP/+/czNzWEYBtdddx1XXXUVf/mXf3nMSPfu3btZt27dMdOwTj/9dBqNBqOjo8tQtbySUqnELbfcwjXXXPOKn/ru3r2bk0466Zipyjt27GBsbIxqtfpGliqvUb1eJ51OL95WD49vvu+zb98+tm/fvnjNNE22b9+uN/cniHq9DrD4727fvn0EQXBMTwcHB+np6VFPjzO33norZ5xxBqeddtox19XD49+jjz7KyMgIN910E1dccQXXXXcd3/72txfvn5qaolQqHdPbZDLJpk2b1EM5ril0y6LJyUkAvvrVr3LZZZdx/fXXk0ql+MxnPrP4Jr5UKr1s3dML0yRLpdIbWa68iiiKuPnmm7nwwgsX1z+91Cv18YXb6uPxZ2Jigvvuu++YaePq4fGtUqkQhuEr9kj9Of6FYcjtt9/O1q1bWbduHdD5d2Xb9jEjp9B5DVRPjx8/+MEP2L9//ysueVMPj39TU1M88MAD9Pf3c8MNN3DRRRfxT//0Tzz44IPAi69vL12iox7K8U5ruleBf/mXf+Hee+/9hY/527/9W6IoAuCyyy7j3HPPBWDnzp388R//MT/84Q+58MILl7xWeXWvtY+PP/44jUaD3/7t336DKpPX6rX2cHBwcPH23NwcN954I295y1u0VlvkDXLbbbcxOjrKn//5ny93KfI/MDMzw+23384nP/lJre09QYVhyMaNGxc/NNmwYQOHDh3igQce4IILLlje4kR+BQrdq8B73vOeX/qHqq+vj/n5eQCGhoYWrzuOQ19fHzMzM0BnlGbPnj3HfG25XF68T5bOa+3jrl272L1798s+5b/++us5//zzueaaa15xtO2F2+rj0nmtPXzB3Nwcn/nMZ9i6dStXXXXVMY9TD49v2WwW0zRfsUfqz/Httttu47HHHuMzn/kM3d3di9fz+Ty+71Or1Y4ZKS2Xy+rpcWLfvn2Uy2U+/vGPL14Lw5BnnnmG+++/nxtuuEE9PM4VCoVj3odC533pj3/8Y+DF17dyuUyhUFh8TLlcPuaEFpHjjUL3KpDNZslms7/0cSMjIziOw9jYGNu2bQM66xKnp6fp7e0FYMuWLdxzzz2Uy+XFqT1PPPEEiUTiZX8k5fX1Wvv40Y9+lN/7vd9bvD0/P8+NN97Itddey+bNm4FOH++66y58319cE/zEE08wMDBwzLpheX291h7Ci4F7w4YN7Ny5E9M8djWQenh8s22bkZERdu3axTnnnAN03vzv2rWLSy65ZJmrk1cSRRFf+tKXePjhh/n0pz9NsVg85v6RkREsy+LJJ59cnA02NjbGzMwMW7ZsWY6S5SW2b9/OX//1Xx9z7Qtf+AIDAwNceuml9PT0qIfHua1btzI2NnbMtbGxscX3ocVikXw+z5NPPrkYsuv1Onv27OGiiy56o8sVec0UumVRMpnkwgsv5O6776a7u5ve3l6+8Y1vACy+OO3YsYOhoSE+//nP84EPfIBSqcRXvvIVLr74YhzHWc7y5aienp5jbr9w1E1/f//iqM3555/PV7/6Vb74xS9y6aWXMjo6yn333ceHP/zhN7xeebm5uTk+/elP09vby4c+9CEqlcrifS98yq8eHv9+8zd/k3/4h39gZGSETZs28a1vfYtWq6Upksep2267je9///tcd911JBKJxVkKyWQS13VJJpP8+q//OnfccQfpdJpkMsmXvvQltmzZosB2nEgkEotr8F8Qi8XIZDKL19XD49u73/1uPvWpT3HPPfdw3nnnsWfPHr7zne8szvYyDIN3vetd3HPPPaxZs4ZischXvvIVCoUCZ5999jJXL/LqjOiFhbwidEa277zzTr73ve/RbrfZtGkTl19+OWvXrl18zPT0NLfeeitPPfUUsViMt73tbXzgAx/AsqxlrFxezdTUFNdccw2f+9znjpl6dfDgQW677Tb27t1LJpPhkksu4b3vfe+y1SkvevDBB7n55ptf8b6777578b/Vw+Pf/fffzze+8Q1KpRLr16/nIx/5yOKMEzm+/M7v/M4rXt+5c+fiByXtdps77riDH/zgB/i+z44dO7jiiis0Nfk49ulPf5r169dz+eWXA+rhieAnP/kJd955JxMTExSLRd797ncfs6dJFEXcfffdfPvb36Zer7Nt2zb+8A//kIGBgWWsWuQXU+gWERERERERWSI6MkxERERERERkiSh0i4iIiIiIiCwRhW4RERERERGRJaLQLSIiIiIiIrJEFLpFRERERERElohCt4iIiIiIiMgSUegWERERERERWSIK3SIiIiIiIiJLRKFbREREREREZIkodIuIiIiIiIgsEYVuERERERERkSWi0C0iIiIiIiKyRBS6RURkVWu321x77bVce+21tNvtxevVapWrrrqKT37yk4RhuIwVioiIyIlMoVtERFY113W5+uqrmZiY4K677lq8fuutt1Kv19m5cyemqZdLERER+f9jL3cBIiIiy23z5s381m/9Fvfeey/nnHMO5XKZhx56iMsvv5yBgYHlLk9EREROYEYURdFyFyEiIrLcfN/n+uuvp9ls0mw2GRoa4s/+7M8wDGO5SxMREZETmObLiYiIALZt87GPfYypqSkajQY7d+5U4BYREZFfmUK3iIjIUY8//jgAnucxPj6+zNWIiIjISqDQLSIiAhw8eJCvfe1rXHDBBWzYsIEvfvGL1Ov15S5LRERETnAK3SIisur5vs/NN99MoVDgIx/5CDt37qRcLnP77bcvd2kiIiJyglPoFhGRVe+ee+7hwIEDfOxjHyORSDA8PMz73vc+HnzwQR577LHlLk9EREROYArdIiKyqu3bt4+vf/3rXHzxxZx66qmL19/73veyceNGbrnlFmq12jJWKCIiIicyHRkmIiIiIiIiskQ00i0iIiIiIiKyRBS6RURERERERJaIQreIiIiIiIjIElHoFhEREREREVkiCt0iIiIiIiIiS0ShW0RERERERGSJKHSLiIiIiIiILBGFbhEREREREZElotAtIiIiIiIiskQUukVERERERESWiEK3iIiIiIiIyBJR6BYRERERERFZIgrdIiIiIiIiIkvk/wFpSJE2E2WW2wAAAABJRU5ErkJggg==\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# ── t-SNE visualization ───────────────────────────────────────────────────────\n",
        "SAMPLE_SIZE  = 3000\n",
        "sample_rows  = np.random.choice(len(X_selected), SAMPLE_SIZE, replace=False)\n",
        "X_tsne_samp  = X_selected.iloc[sample_rows].values\n",
        "y_tsne_samp  = y_resampled.iloc[sample_rows].values\n",
        "\n",
        "print(f'Running t-SNE on {SAMPLE_SIZE} samples...')\n",
        "tsne   = TSNE(n_components=2, perplexity=40, n_iter=1000,\n",
        "              learning_rate='auto', init='pca', random_state=RANDOM_STATE)\n",
        "t_res  = tsne.fit_transform(X_tsne_samp)\n",
        "\n",
        "tsne_df = pd.DataFrame({'x': t_res[:, 0], 'y': t_res[:, 1], 'class': y_tsne_samp})\n",
        "\n",
        "plt.figure(figsize=(10, 7))\n",
        "sns.scatterplot(\n",
        "    data=tsne_df, x='x', y='y', hue='class',\n",
        "    palette='tab10', alpha=0.6, s=20\n",
        ")\n",
        "plt.title('t-SNE Visualization of Attack Classes (Post-SMOTE)')\n",
        "plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left')\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "oi6RDTVGi8OU",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7d2b44ac-bcb1-4833-a725-9ebe2c298176"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saved train processed → data/processed/train_processed_advanced.csv  shape=(336715, 38)\n",
            "Saved test  processed → data/processed/test_processed_advanced.csv   shape=(22544, 38)\n"
          ]
        }
      ],
      "source": [
        "# ── Save processed datasets ───────────────────────────────────────────────────\n",
        "df_final_train = pd.concat([X_selected, y_resampled], axis=1)\n",
        "\n",
        "# Test set — use same selected features\n",
        "X_test_features  = [f for f in selected_features if f in df_test_proc.columns]\n",
        "df_final_test    = df_test_proc[X_test_features + ['attack_class']].copy()\n",
        "\n",
        "TRAIN_PROC_PATH = os.path.join(PROC_DIR, 'train_processed_advanced.csv')\n",
        "TEST_PROC_PATH  = os.path.join(PROC_DIR, 'test_processed_advanced.csv')\n",
        "\n",
        "df_final_train.to_csv(TRAIN_PROC_PATH, index=False)\n",
        "df_final_test.to_csv(TEST_PROC_PATH,   index=False)\n",
        "\n",
        "print(f'Saved train processed → {TRAIN_PROC_PATH}  shape={df_final_train.shape}')\n",
        "print(f'Saved test  processed → {TEST_PROC_PATH}   shape={df_final_test.shape}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6IBZ8wmSi8OV"
      },
      "source": [
        "---\n",
        "# 📅 Week 4 — Supervised Model Training"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Ts3on4BEi8OV",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "04375c1b-fb52-4e6c-a8b6-91fe6806d4c0"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "X_train : (269372, 37) | X_val : (67343, 37)\n",
            "Classes : ['DoS' 'Probe' 'R2L' 'U2R' 'normal' 'other']\n"
          ]
        }
      ],
      "source": [
        "# ── Prepare signal arrays ─────────────────────────────────────────────────────\n",
        "df_train = pd.read_csv(TRAIN_PROC_PATH)\n",
        "df_test  = pd.read_csv(TEST_PROC_PATH)\n",
        "\n",
        "X_signal      = df_train.drop(columns=['attack_class']).values\n",
        "X_test_signal = df_test.drop(columns=['attack_class']).values\n",
        "\n",
        "le_w4    = LabelEncoder()\n",
        "\n",
        "# Get all unique classes from both train and test sets to fit the LabelEncoder\n",
        "all_classes = pd.concat([df_train['attack_class'], df_test['attack_class']]).unique()\n",
        "le_w4.fit(all_classes)\n",
        "\n",
        "y_master = le_w4.transform(df_train['attack_class'])\n",
        "y_test_l = le_w4.transform(df_test['attack_class'])\n",
        "\n",
        "X_train, X_val, y_train, y_val = train_test_split(\n",
        "    X_signal, y_master,\n",
        "    test_size=0.2, random_state=RANDOM_STATE, stratify=y_master\n",
        ")\n",
        "\n",
        "print(f'X_train : {X_train.shape} | X_val : {X_val.shape}')\n",
        "print(f'Classes : {le_w4.classes_}')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "B-hDEn6Oi8OW",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "571a11eb-cf23-4bb9-8a81-6f50cad349f6"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Starting GridSearchCV for Random Forest...\n",
            "Fitting 3 folds for each of 8 candidates, totalling 24 fits\n",
            "\n",
            "Best Hyperparameters : {'max_depth': 20, 'min_samples_leaf': 1, 'n_estimators': 100}\n",
            "Best CV F1 Score     : 0.9996\n"
          ]
        }
      ],
      "source": [
        "# ── Hyperparameter tuning for Random Forest ───────────────────────────────────\n",
        "print('Starting GridSearchCV for Random Forest...')\n",
        "\n",
        "param_grid = {\n",
        "    'n_estimators'    : [50, 100],\n",
        "    'max_depth'       : [10, 20],\n",
        "    'min_samples_leaf': [1, 2]\n",
        "}\n",
        "\n",
        "grid = GridSearchCV(\n",
        "    RandomForestClassifier(random_state=RANDOM_STATE, n_jobs=-1, class_weight='balanced'),\n",
        "    param_grid, cv=3, scoring='f1_macro', verbose=1\n",
        ")\n",
        "grid.fit(X_train, y_train)\n",
        "\n",
        "sentinel_brain = grid.best_estimator_\n",
        "\n",
        "print(f'\\nBest Hyperparameters : {grid.best_params_}')\n",
        "print(f'Best CV F1 Score     : {grid.best_score_:.4f}')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "3g56JSigi8OW",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1232feb9-f54a-4d03-a2dd-84f586f7d432"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Training: Random Forest...\n",
            "  Accuracy : 0.9997 | F1 Macro : 0.9997\n",
            "\n",
            "Training: Decision Tree...\n",
            "  Accuracy : 0.9982 | F1 Macro : 0.9982\n",
            "\n",
            "Training: Gradient Boosting...\n",
            "  Accuracy : 0.9912 | F1 Macro : 0.9912\n",
            "\n",
            "Training: XGBoost...\n",
            "  Accuracy : 0.9996 | F1 Macro : 0.9996\n",
            "\n",
            "--- Final Rankings ---\n",
            "            Model  Accuracy  Precision   Recall  F1 Macro\n",
            "    Random Forest  0.999718   0.999718 0.999718  0.999718\n",
            "          XGBoost  0.999555   0.999554 0.999555  0.999554\n",
            "    Decision Tree  0.998218   0.998221 0.998218  0.998217\n",
            "Gradient Boosting  0.991165   0.991168 0.991164  0.991162\n"
          ]
        }
      ],
      "source": [
        "# ── Train and compare all models ──────────────────────────────────────────────\n",
        "models = {\n",
        "    'Random Forest'     : sentinel_brain,\n",
        "    'Decision Tree'     : DecisionTreeClassifier(max_depth=15, random_state=RANDOM_STATE),\n",
        "    'Gradient Boosting' : GradientBoostingClassifier(\n",
        "                            n_estimators=50, max_depth=3,\n",
        "                            subsample=0.3, random_state=RANDOM_STATE),\n",
        "}\n",
        "if XGBOOST_AVAILABLE:\n",
        "    models['XGBoost'] = XGBClassifier(\n",
        "        n_estimators=100, max_depth=6, learning_rate=0.1,\n",
        "        eval_metric='mlogloss', random_state=RANDOM_STATE\n",
        "    )\n",
        "\n",
        "results = {}\n",
        "for name, model in models.items():\n",
        "    print(f'\\nTraining: {name}...')\n",
        "    model.fit(X_train, y_train)\n",
        "    y_pred    = model.predict(X_val)\n",
        "    acc       = accuracy_score(y_val, y_pred)\n",
        "    f1        = f1_score(y_val, y_pred, average='macro')\n",
        "    prec      = precision_score(y_val, y_pred, average='macro', zero_division=0)\n",
        "    rec       = recall_score(y_val, y_pred, average='macro', zero_division=0)\n",
        "    results[name] = {'Accuracy': acc, 'Precision': prec, 'Recall': rec, 'F1 Macro': f1}\n",
        "    print(f'  Accuracy : {acc:.4f} | F1 Macro : {f1:.4f}')\n",
        "\n",
        "results_df = pd.DataFrame(results).T.reset_index().rename(columns={'index': 'Model'})\n",
        "print('\\n--- Final Rankings ---')\n",
        "print(results_df.sort_values('F1 Macro', ascending=False).to_string(index=False))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "LLWDwSvRi8OX",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 425
        },
        "outputId": "c5b95624-3691-48a1-96be-19fae78befa1"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1300x900 with 4 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# ── Model comparison chart ────────────────────────────────────────────────────\n",
        "fig, axes = plt.subplots(2, 2, figsize=(13, 9))\n",
        "metrics  = ['Accuracy', 'Precision', 'Recall', 'F1 Macro']\n",
        "palettes = ['viridis', 'plasma', 'coolwarm', 'husl']\n",
        "\n",
        "for ax, metric, palette in zip(axes.flatten(), metrics, palettes):\n",
        "    sns.barplot(data=results_df, x='Model', y=metric, palette=palette, ax=ax)\n",
        "    ax.set_title(f'{metric} — All Models')\n",
        "    ax.set_ylim(0.7, 1.0)\n",
        "    ax.tick_params(axis='x', rotation=15)\n",
        "\n",
        "plt.suptitle('Week 4 — Supervised Model Comparison', fontsize=13)\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "42r3jlE8i8OX",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "0e99afa4-306a-4b34-c65a-dc89d95aace3"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Classification Report — Random Forest (Best)\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "         DoS       1.00      1.00      1.00     13469\n",
            "       Probe       1.00      1.00      1.00     13468\n",
            "         R2L       1.00      1.00      1.00     13469\n",
            "         U2R       1.00      1.00      1.00     13469\n",
            "      normal       1.00      1.00      1.00     13468\n",
            "\n",
            "    accuracy                           1.00     67343\n",
            "   macro avg       1.00      1.00      1.00     67343\n",
            "weighted avg       1.00      1.00      1.00     67343\n",
            "\n"
          ]
        }
      ],
      "source": [
        "# ── Classification report for best model ─────────────────────────────────────\n",
        "y_pred_best    = sentinel_brain.predict(X_val)\n",
        "unique_classes = sorted(np.unique(np.concatenate([y_val, y_pred_best])))\n",
        "class_names    = [le_w4.classes_[i] for i in unique_classes]\n",
        "\n",
        "print('Classification Report — Random Forest (Best)')\n",
        "print(classification_report(y_val, y_pred_best, target_names=class_names))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "DMSMB25Yi8OY",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 478
        },
        "outputId": "5106ee9f-4da4-48fc-9c1b-b971481fdd2c"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# ── Confusion matrix ──────────────────────────────────────────────────────────\n",
        "cm = confusion_matrix(y_val, y_pred_best)\n",
        "plt.figure(figsize=(8, 6))\n",
        "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',\n",
        "            xticklabels=class_names, yticklabels=class_names)\n",
        "plt.title('Confusion Matrix — Random Forest (Tuned)')\n",
        "plt.xlabel('Predicted')\n",
        "plt.ylabel('Actual')\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "FrGU4DhXi8OY",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7594c839-2a1a-4581-d276-6eb2faac3291"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "✅ Model saved → models/sentinel_brain.joblib\n",
            "✅ Encoder saved → models/label_encoder.joblib\n"
          ]
        }
      ],
      "source": [
        "# ── Save model & encoder ─────────────────────────────────────────────────────\n",
        "joblib.dump(sentinel_brain, os.path.join(MODELS_DIR, 'sentinel_brain.joblib'))\n",
        "joblib.dump(le_w4,          os.path.join(MODELS_DIR, 'label_encoder.joblib'))\n",
        "print('✅ Model saved → models/sentinel_brain.joblib')\n",
        "print('✅ Encoder saved → models/label_encoder.joblib')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "QZ46BR1Qi8OY"
      },
      "source": [
        "---\n",
        "# 📅 Week 5 — Anomaly Detection (Unsupervised Learning)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "bST5fn31i8OZ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "23f3e7c9-8845-4fe4-b9f7-2f006339ad03"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Running Isolation Forest on full training set...\n",
            "Isolation Forest — Anomalies detected: 10092\n"
          ]
        }
      ],
      "source": [
        "# ── Isolation Forest ─────────────────────────────────────────────────────────\n",
        "print('Running Isolation Forest on full training set...')\n",
        "iso       = IsolationForest(contamination=0.03, random_state=RANDOM_STATE, n_jobs=-1)\n",
        "iso_preds = iso.fit_predict(X_signal)\n",
        "\n",
        "iso_plot_df             = df_train.copy()\n",
        "iso_plot_df['iso_score']  = iso.decision_function(X_signal)\n",
        "iso_plot_df['is_anomaly'] = (iso_preds == -1).astype(int)\n",
        "\n",
        "iso_anomaly_count = iso_plot_df['is_anomaly'].sum()\n",
        "print(f'Isolation Forest — Anomalies detected: {iso_anomaly_count}')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "G-RDZZrmi8OZ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "9fca14a4-a409-45d7-c8f2-25968c71f63f"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Running Local Outlier Factor...\n",
            "LOF — Anomalies: 250\n",
            "Running One-Class SVM...\n",
            "One-Class SVM — Anomalies: 439\n",
            "\n",
            "Anomaly Detection Comparison\n",
            "              Method  Anomalies Detected  Sample Size  Speed               Best For\n",
            "    Isolation Forest               10092       336715   Fast        Global outliers\n",
            "Local Outlier Factor                 250         5000   Slow Local/cluster outliers\n",
            "       One-Class SVM                 439         5000 Medium      Known normal data\n"
          ]
        }
      ],
      "source": [
        "# ── LOF & One-Class SVM on sample ─────────────────────────────────────────────\n",
        "SAMPLE_5K = 5000\n",
        "X_sample5 = X_signal[:SAMPLE_5K]\n",
        "\n",
        "print('Running Local Outlier Factor...')\n",
        "lof             = LocalOutlierFactor(n_neighbors=20, contamination=0.05)\n",
        "lof_labels      = lof.fit_predict(X_sample5)\n",
        "lof_count       = (lof_labels == -1).sum()\n",
        "print(f'LOF — Anomalies: {lof_count}')\n",
        "\n",
        "print('Running One-Class SVM...')\n",
        "oc_svm          = OneClassSVM(kernel='rbf', gamma=0.1, nu=0.05)\n",
        "oc_svm.fit(X_sample5)\n",
        "ocsvm_preds     = oc_svm.predict(X_sample5)\n",
        "ocsvm_count     = (ocsvm_preds == -1).sum()\n",
        "print(f'One-Class SVM — Anomalies: {ocsvm_count}')\n",
        "\n",
        "comparison = pd.DataFrame({\n",
        "    'Method'            : ['Isolation Forest', 'Local Outlier Factor', 'One-Class SVM'],\n",
        "    'Anomalies Detected': [iso_anomaly_count, lof_count, ocsvm_count],\n",
        "    'Sample Size'       : [len(X_signal), SAMPLE_5K, SAMPLE_5K],\n",
        "    'Speed'             : ['Fast', 'Slow', 'Medium'],\n",
        "    'Best For'          : ['Global outliers', 'Local/cluster outliers', 'Known normal data']\n",
        "})\n",
        "print('\\nAnomaly Detection Comparison')\n",
        "print(comparison.to_string(index=False))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "evI3dZ2ti8OZ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "561b5d3c-4dad-4f34-dfd5-a93aacec70c6"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x600 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# ── Anomaly visualization ─────────────────────────────────────────────────────\n",
        "fig, axes = plt.subplots(1, 2, figsize=(14, 6))\n",
        "\n",
        "sns.violinplot(\n",
        "    x='attack_class', y='iso_score',\n",
        "    data=iso_plot_df, palette='magma', ax=axes[0]\n",
        ")\n",
        "axes[0].axhline(0, color='red', linestyle='--', label='Anomaly boundary')\n",
        "axes[0].set_title('Isolation Forest Scores by Attack Class')\n",
        "axes[0].set_xlabel('Attack Class')\n",
        "axes[0].set_ylabel('Isolation Score')\n",
        "axes[0].legend()\n",
        "\n",
        "sns.countplot(\n",
        "    x='attack_class', hue='is_anomaly',\n",
        "    data=iso_plot_df, ax=axes[1]\n",
        ")\n",
        "axes[1].set_title('Anomaly Labels vs True Attack Categories')\n",
        "axes[1].set_yscale('log')\n",
        "\n",
        "plt.suptitle('Week 5 — Unsupervised Anomaly Detection', fontsize=13)\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "kqKhny6Wi8Oa"
      },
      "source": [
        "---\n",
        "# 📅 Week 6 — Model Evaluation & Fine-Tuning"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "t_Z9mnlsi8Ol",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "bb4386ac-bc4d-4404-f4bb-923f5f0d26af"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x700 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# ── ROC-AUC curves ────────────────────────────────────────────────────────────\n",
        "n_classes  = len(le_w4.classes_)\n",
        "y_val_bin  = label_binarize(y_val, classes=list(range(n_classes)))\n",
        "y_prob     = sentinel_brain.predict_proba(X_val)\n",
        "\n",
        "colors_roc = ['#2196F3', '#F44336', '#4CAF50', '#FF9800', '#9C27B0']\n",
        "\n",
        "plt.figure(figsize=(10, 7))\n",
        "for i, (cls_name, color) in enumerate(zip(le_w4.classes_, colors_roc[:n_classes])):\n",
        "    fpr, tpr, _ = roc_curve(y_val_bin[:, i], y_prob[:, i])\n",
        "    roc_auc     = auc(fpr, tpr)\n",
        "    plt.plot(fpr, tpr, color=color, lw=2, label=f'{cls_name}  (AUC = {roc_auc:.3f})')\n",
        "\n",
        "plt.plot([0, 1], [0, 1], 'k--', lw=1, label='Random Classifier (AUC = 0.500)')\n",
        "plt.title('ROC-AUC — Random Forest (One vs Rest per Class)')\n",
        "plt.xlabel('False Positive Rate')\n",
        "plt.ylabel('True Positive Rate (Recall)')\n",
        "plt.legend(loc='lower right')\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "p6i_ezQ8i8Om",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 362
        },
        "outputId": "47208957-5694-4b35-874b-de865847b207"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cross Validation F1 Scores : [0.9996 0.9997 0.9996 0.9997 0.9997]\n",
            "Mean CV F1                 : 0.9997\n",
            "Std  CV F1                 : 0.0000\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x400 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# ── 5-Fold Cross Validation ───────────────────────────────────────────────────\n",
        "skf       = StratifiedKFold(n_splits=5, shuffle=True, random_state=RANDOM_STATE)\n",
        "cv_scores = cross_val_score(\n",
        "    sentinel_brain, X_signal, y_master,\n",
        "    cv=skf, scoring='f1_macro', n_jobs=-1\n",
        ")\n",
        "\n",
        "print(f'Cross Validation F1 Scores : {cv_scores.round(4)}')\n",
        "print(f'Mean CV F1                 : {cv_scores.mean():.4f}')\n",
        "print(f'Std  CV F1                 : {cv_scores.std():.4f}')\n",
        "\n",
        "plt.figure(figsize=(8, 4))\n",
        "plt.bar(range(1, 6), cv_scores, color=sns.color_palette('husl', 5))\n",
        "plt.axhline(cv_scores.mean(), color='red', linestyle='--',\n",
        "            label=f'Mean = {cv_scores.mean():.4f}')\n",
        "plt.title('5-Fold Cross Validation F1 Scores — Random Forest')\n",
        "plt.xlabel('Fold')\n",
        "plt.ylabel('F1 Macro Score')\n",
        "plt.ylim(0.9, 1.0)\n",
        "plt.legend()\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "DSxcKTjvi8Om",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "be99233a-9191-44ae-c2ce-b2e6d04a09d7"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "=== Final Model Performance Summary ===\n",
            "            Model  Accuracy  Precision   Recall  F1 Macro\n",
            "    Random Forest  0.999718   0.999718 0.999718  0.999718\n",
            "          XGBoost  0.999555   0.999554 0.999555  0.999554\n",
            "    Decision Tree  0.998218   0.998221 0.998218  0.998217\n",
            "Gradient Boosting  0.991165   0.991168 0.991164  0.991162\n",
            "\n",
            "=== Best Model: Random Forest ===\n",
            "  Validation Accuracy : 0.9997\n",
            "  Mean CV F1          : 0.9997\n",
            "  Std  CV F1          : 0.0000\n"
          ]
        }
      ],
      "source": [
        "# ── Full metrics table ────────────────────────────────────────────────────────\n",
        "print('\\n=== Final Model Performance Summary ===')\n",
        "print(results_df.sort_values('F1 Macro', ascending=False).to_string(index=False))\n",
        "\n",
        "print('\\n=== Best Model: Random Forest ===')\n",
        "print(f'  Validation Accuracy : {accuracy_score(y_val, y_pred_best):.4f}')\n",
        "print(f'  Mean CV F1          : {cv_scores.mean():.4f}')\n",
        "print(f'  Std  CV F1          : {cv_scores.std():.4f}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DMD_CsL4i8Om"
      },
      "source": [
        "---\n",
        "# 📅 Week 7 — Alert Generation & Logging"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "USFZQFo_i8On",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c1bce0b3-25e8-4ba1-d255-b280d84d049f"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Simulating real-time detection on 22544 connections...\n",
            "True class distribution:\n",
            "attack_class\n",
            "normal    9711\n",
            "DoS       7458\n",
            "R2L       2885\n",
            "Probe     2421\n",
            "U2R         67\n",
            "other        2\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "# ── Load model and run real-time simulation ───────────────────────────────────\n",
        "sentinel_brain = joblib.load(os.path.join(MODELS_DIR, 'sentinel_brain.joblib'))\n",
        "le_alert       = joblib.load(os.path.join(MODELS_DIR, 'label_encoder.joblib'))\n",
        "\n",
        "X_test_alert = df_test.drop(columns=['attack_class']).values\n",
        "y_true_alert = le_alert.transform(df_test['attack_class'])\n",
        "\n",
        "print(f'Simulating real-time detection on {len(X_test_alert)} connections...')\n",
        "print('True class distribution:')\n",
        "print(df_test['attack_class'].value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "bCpQzk4pi8On",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "9d963113-e12f-4289-b873-61376a7f34f1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Processing 22544 connections in batches of 100...\n",
            "Total batches: 225\n",
            "-------------------------------------------------------\n",
            "Batch   20/225 | Intrusions in batch: 47\n",
            "Batch   40/225 | Intrusions in batch: 29\n",
            "Batch   60/225 | Intrusions in batch: 41\n",
            "Batch   80/225 | Intrusions in batch: 40\n",
            "Batch  100/225 | Intrusions in batch: 36\n",
            "Batch  120/225 | Intrusions in batch: 31\n",
            "Batch  140/225 | Intrusions in batch: 39\n",
            "Batch  160/225 | Intrusions in batch: 33\n",
            "Batch  180/225 | Intrusions in batch: 44\n",
            "Batch  200/225 | Intrusions in batch: 31\n",
            "Batch  220/225 | Intrusions in batch: 40\n",
            "-------------------------------------------------------\n",
            "Total connections processed: 22500\n"
          ]
        }
      ],
      "source": [
        "# ── Batch prediction loop ─────────────────────────────────────────────────────\n",
        "BATCH_SIZE    = 100\n",
        "all_alerts    = []\n",
        "total_batches = len(X_test_alert) // BATCH_SIZE\n",
        "\n",
        "print(f'Processing {len(X_test_alert)} connections in batches of {BATCH_SIZE}...')\n",
        "print(f'Total batches: {total_batches}')\n",
        "print('-' * 55)\n",
        "\n",
        "for batch_num in range(total_batches):\n",
        "    start       = batch_num * BATCH_SIZE\n",
        "    end         = start + BATCH_SIZE\n",
        "    X_batch     = X_test_alert[start:end]\n",
        "    true_batch  = y_true_alert[start:end]\n",
        "\n",
        "    preds       = sentinel_brain.predict(X_batch)\n",
        "    proba       = sentinel_brain.predict_proba(X_batch)\n",
        "    confidence  = proba.max(axis=1)\n",
        "\n",
        "    pred_names  = le_alert.inverse_transform(preds)\n",
        "    true_names  = le_alert.inverse_transform(true_batch)\n",
        "    timestamp   = datetime.now().strftime('%Y-%m-%d %H:%M:%S')\n",
        "\n",
        "    for i in range(BATCH_SIZE):\n",
        "        pred_class = pred_names[i]\n",
        "        severity   = SEVERITY_MAP.get(pred_class, 'Unknown')\n",
        "        all_alerts.append({\n",
        "            'timestamp'       : timestamp,\n",
        "            'connection_id'   : start + i + 1,\n",
        "            'predicted_class' : pred_class,\n",
        "            'true_class'      : true_names[i],\n",
        "            'confidence'      : round(float(confidence[i]), 4),\n",
        "            'severity'        : severity,\n",
        "            'is_intrusion'    : pred_class != 'normal',\n",
        "            'correct'         : pred_class == true_names[i]\n",
        "        })\n",
        "\n",
        "    if (batch_num + 1) % 20 == 0:\n",
        "        batch_alerts = sum(1 for r in all_alerts[-BATCH_SIZE:] if r['is_intrusion'])\n",
        "        print(f'Batch {batch_num+1:>4}/{total_batches} | Intrusions in batch: {batch_alerts}')\n",
        "\n",
        "print('-' * 55)\n",
        "print(f'Total connections processed: {len(all_alerts)}')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "U8XCdlWvi8On",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "3bd92349-de71-444c-bcf2-5521b5b67b80"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Total connections  : 22500\n",
            "Intrusions detected: 8254 (36.7%)\n",
            "Normal traffic     : 14246 (63.3%)\n",
            "Real-time Accuracy : 0.7583\n",
            "\n",
            "Predicted class distribution:\n",
            "predicted_class\n",
            "normal    14246\n",
            "DoS        6161\n",
            "Probe      2048\n",
            "R2L          25\n",
            "U2R          20\n",
            "Name: count, dtype: int64\n",
            "\n",
            "Severity breakdown:\n",
            "severity\n",
            "None        14246\n",
            "Critical     6181\n",
            "Medium       2048\n",
            "High           25\n",
            "Name: count, dtype: int64\n"
          ]
        }
      ],
      "source": [
        "# ── Build alerts DataFrame ────────────────────────────────────────────────────\n",
        "alerts_df    = pd.DataFrame(all_alerts)\n",
        "total        = len(alerts_df)\n",
        "intrusions   = alerts_df['is_intrusion'].sum()\n",
        "normal_count = total - intrusions\n",
        "accuracy_rt  = alerts_df['correct'].mean()\n",
        "\n",
        "print(f'Total connections  : {total}')\n",
        "print(f'Intrusions detected: {intrusions} ({intrusions/total*100:.1f}%)')\n",
        "print(f'Normal traffic     : {normal_count} ({normal_count/total*100:.1f}%)')\n",
        "print(f'Real-time Accuracy : {accuracy_rt:.4f}')\n",
        "print('\\nPredicted class distribution:')\n",
        "print(alerts_df['predicted_class'].value_counts())\n",
        "print('\\nSeverity breakdown:')\n",
        "print(alerts_df['severity'].value_counts())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "FECckV4di8On",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 202
        },
        "outputId": "f2026bb5-1c48-4bdc-f6f7-a79756955814"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1600x500 with 3 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABjYAAAHvCAYAAAD3tubNAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzs3XdYFFfbBvB76b0oECwICFheC9i7iBrFiiVGYxfLa9QYk2iivhpLbMSYqDGJxoBdFHvvwYItWLAr0hQ7SBOQfr4/+HbCuktTYCn377r20p05M/OcYXZ3Zp4558iEEAJERERERERERERERERlgIa6AyAiIiIiIiIiIiIiIiooJjaIiIiIiIiIiIiIiKjMYGKDiIiIiIiIiIiIiIjKDCY2iIiIiIiIiIiIiIiozGBig4iIiIiIiIiIiIiIygwmNoiIiIiIiIiIiIiIqMxgYoOIiIiIiIiIiIiIiMoMJjaIiIiIiIiIiIiIiKjMYGKDiIiIiIiIiIiIiIjKDCY2iIiIiKhErF+/HjKZDKdPn1Z3KBXa6dOnIZPJsH79+hLZ3siRIyGTyUpkWyWtQ4cOsLOzU3cYpVJJfN5L+lgmIiIiotKDiQ0iIiKicuLo0aOQyWSYNWuW0rxLly5BJpNBV1cXycnJSvPd3d2hoaGB6Ojokgj1vchvlOb1evr0qbrDxIsXLzB16lTUr18fxsbGMDExgZOTEwYNGoTdu3eXSAxBQUGYO3cuIiIiSmR7hTV37lzIZDJoaWnh/v37SvPlN6x/+umnD9rG3r1732vZzMxMVKtWDTKZDD/88MN7x/Ah4uLiMHfu3PdODMTGxkJfXx8ymQybNm0q2uCIiIiIiNRMS90BEBEREVHRaNu2LbS0tFTeCPX394eWlhbS0tJw4cIFdO7cWZqXkZGBgIAA1K9fHxYWFiUYceG0b99e5Q3a58+f49tvv0WjRo1QrVo1NUT2r0ePHqF58+ZISEjAkCFD8PnnnwMAQkJC4O/vj3Xr1qFfv37FHkdQUBDmzZunskVB+/bt8fbtW2hraxd7HPnJzMzEjBkzsGfPniJf97x58zBixAj06dOn0MseOXIEz549g4ODA9avX49Zs2aVeKuTuLg4zJs3D0B2y5DC2rJlC1JTU2Fvbw8fHx8MGzasiCNUv9J0LBMRERFRyWJig4iIiKicMDIyQrNmzRAYGIjk5GQYGBhI806fPo2PP/4Y169fx+nTpxUSG4GBgUhKSnqvm6clqWbNmqhZs6bS9MWLFwMARo8eXdIhKfnpp5/w6tUr7N27Fx4eHkrzX7x4oYaoFGloaEBPT0/dYQAAmjZtir179+LixYto1aqVusOReHt7w8HBAT///DM8PDxw+vRpuLm5lci2i+pGvbe3N9zc3ODh4YEpU6YgLCxM5eenLCtNxzIRERERlSx2RUVERERUjri5uSEtLQ3nz5+XpmVkZOD8+fNwdXWFq6sr/P39FZaRt/DIeeP2+fPn+Pzzz1GjRg3o6OigatWqGDduHF69eqW0zfj4eHz33XdwdHSErq4uLC0t8dlnnyEsLKxAMS9cuBAymQxffPEFsrKyClVfIQR8fHygr6+PIUOGFGrZ4vDw4UMAQKdOnVTOt7a2Vpp25coV9O3bFxYWFtDV1UXt2rWxcOFCZGRkKJSTt7549uwZPvvsM5ibm8PAwABdu3ZFcHCwVG7u3LkYNWoUgOy/qbybrpEjRwJQPS5Bzmnr1q1DvXr1oKurC1tbW/z4448q61LQuPMyZ84cGBgY4Ntvvy3wMtu3b0fbtm1hbGwMAwMDtGjRAjt37pTmR0RESK0rNmzYoNBVWUG8fPkSBw8exPDhw9G9e3dYWVnB29u7wPEB2cfBsGHDUKVKFejo6MDOzg7Tpk1DUlKSQjn5+CNRUVHw9PTERx99BENDQ2zevBn29vYAslueyOMv6Hge165dQ1BQEEaMGIHBgwdDS0sLPj4+KsvKj42LFy/C1dUVhoaGqFy5MsaMGYPExESFsvfv38eECRNQr149af83adIEf/31V74x7dmzBzKZDGvXrlU5v169enB0dIQQAgBw584dDBgwANWqVYOuri6sra3h5uaGQ4cOScuoOpazsrKwfPlyNGzYUOoKrnbt2hg9ejTS09PzjZOIiIiIyga22CAiIiIqR9zc3LBo0SKphQbwb4sMV1dXmJiY4Msvv0RSUhIMDQ0B/Htz0NXVFQDw+PFjtGrVCmlpaRg9ejQcHBwQEhKCP/74A/7+/rhy5QpMTU0BZCc1WrdujcePH8PT0xP16tXD8+fP8fvvv6NFixa4cuUKbG1tVcaamZmJSZMmYfXq1Vi8eDGmT59e6PqeOXMGISEhGDp0KMzMzN5jjxUtBwcHAMDatWsxZcqUfG+mHzp0CP369YOjoyO++eYbVKpUCRcvXsT333+PoKAg7NixQ6F8UlIS2rdvj5YtW2LRokUIDw/HihUr4OHhgdu3b0NTUxP9+vXD8+fP8eeff2LmzJmoW7euQmx5Wb16NV6+fInRo0fDzMwMmzdvxnfffYfq1atj8ODB7x13bqytrfHVV19h4cKF2L9/P3r37p1n+VmzZmHhwoVwd3fHDz/8AA0NDezZswcDBgzAqlWrMHHiRFhaWmLTpk0YNmwY2rVrh3HjxhUoFrmNGzciMzMTw4cPh5aWFoYMGYLVq1cjPj5eOu7zcvXqVXTs2BFmZmb473//i2rVquHGjRtYuXIlzp8/jzNnzii1yPj4449hbW2N2bNnIykpCd26dcMvv/yCr776Cn379pW6LzMyMipQHby9vWFkZIT+/fvD0NAQPXv2xIYNGzB//nxoaCg/2xYUFISePXti1KhRGDx4ME6fPg1vb29oaGjgzz//lMqdPn0aZ8+eRc+ePWFvb4+kpCTs2LEDY8eORVRUFGbMmJFrTL169YK1tTV8fHwwduxYhXmXLl3C3bt3pSTn69ev0bFjRwDA+PHjYWtri+joaFy5cgWXL19Gjx49ct3OwoUL8f3336NXr14YP348NDU1ER4ejv379yM1NZXdVhERERGVF4KIiIiIyo3k5GSho6MjWrVqJU1btGiRMDIyEunp6eLu3bsCgDh27JgQQoj09HRhaGgonJ2dpfK9e/cWlpaWIjIyUmHdgYGBQlNTU8yZM0eaNnnyZKGnpyeCgoIUykZERAhjY2MxYsQIadq6desEAOHv7y+Sk5NFnz59hLa2ttiwYcN713fo0KECgDh9+vR7r6MohYaGChMTEwFA2NjYiMGDB4tffvlFXLlyRans27dvxUcffSTatWsn0tPTFeb9/PPP0r6Sc3V1FQCEl5eXQtkff/xRABBHjx6VpuXc1+/y9/cXAMS6deuUplWpUkXExcVJ05OSkoSFhYVo2bLle8c9YsQI8e5lx5w5cwQAERgYKOLj44WFhYWoV6+eyMjIUIhn6dKl0jJXr14VAMSMGTOU6uTh4SGMjY1FQkKCNA2AwvFXUHXq1BGurq7S+6CgIAFA/P7770plXV1dha2trcK0hg0bitq1ayvEIoQQu3fvVtrv8n0zZMgQpXWHh4cLAAqft4J4+/atMDMzU6j73r17BQBx+PBhpfIAhEwmE5cuXVKY3r17d6GlpSXevHkjTUtMTFRaPjMzU7i6ugoTExORlpYmTVd1DM6YMUMAEHfu3FFYx5gxY4SmpqZ4+vSpEEKIffv2CQBi+/btedZV1bHcqFEjUbdu3TyXIyIiIqKyj11REREREZUj+vr6UksJebc3p0+fRuvWraGlpYW6devCyspK6n5K3ppD3g1VfHw8Dh48iN69e0NPTw/R0dHSy87ODo6Ojjh+/DiA7G6gtmzZgvbt26NatWoKZQ0NDdGyZUupbE4xMTH4+OOPcfLkSRw4cADDhw9/r7rGxcVh165dcHR0lFqbqFvNmjVx48YNTJw4EQCwdetWfPXVV2jatCkaNmyIq1evSmVPnDiBly9fYtSoUYiLi1PYf927dwcApf2noaGByZMnK0yTP9ku7wbrQ4waNUqhVYKBgQFatmypsO73iTsvJiYmmDVrFu7cuYMNGzbkWm7Lli2QyWQYMWKEwjajo6PRu3dvvHnzBhcvXnyPWv/rwoULuH//PkaMGCFNc3Z2houLS65dOeV069Yt3Lx5E4MHD0ZqaqpCjG3btoWhoaHKfTN16tQPijun3bt3Iy4uTqEO3bt3h6WlZa51aNWqFVq0aKEwrWPHjsjIyEBERIQ0Td7KCwBSUlLw+vVrxMTEoEuXLkhISMD9+/fzjG3s2LGQyWQKXXslJSVh+/bt6NatG6pWrQoA0jF45MgRJCQkFKzi/8/U1BRPnz5FQEBAoZYjIiIiorKFXVERERERlTNubm44d+4cAgIC0KlTJ5w/fx4zZ86U5rdv314aZ0Oe4JAPHP7gwQNkZWXB29s713EF5AMQR0VF4fXr1zh+/DgsLS1VllXV7c3IkSORmJiIs2fPom3btu9bTWzduhVv374t1KDhMTExSEtLe+9tGhkZ5dsdkJ2dHVatWoVVq1bh+fPnCAgIwKZNm3DgwAH07NkTd+7cQaVKlXDv3j0AgKenZ67revnypcL7qlWrKg2WXLlyZQDA69ev36dKClQNLl25cmWFdb9P3Pn5/PPPsWLFCsyZM0ehy6uc7t27ByEE6tSpU2TbfZe3tze0tbXRqFEjhISESNO7du0KLy8v3Lx5Ew0bNsx1efm+mTNnDubMmVPgGGvVqvVBcefk7e0NS0tLVK9eXaEOXbp0wY4dOxAdHQ0LCwuFZXL7uwOKx1ViYiLmzp0LPz8/REZGKi0TGxubZ2z29vbo3LkzNm3ahCVLlkBbWxt+fn548+YNxowZI5VzdXXF8OHDsX79emzZsgXNmjVD586dMXDgQPznP//JcxuLFi1Cnz590K5dO1StWhUdOnRAjx498Mknn0BHRyfPZYmIiIio7GBig4iIiKiccXNzw/z583H69GmYmJhI42vIubq64quvvkJiYiJOnz4NDQ0NtG/fHgCkgXuHDh2q8MR3Tvr6+gplO3fujO+++67A8Q0cOBDr1q3DDz/8gL1790rrKyxvb29oaWlJg2IXRL9+/XDmzJn32h6QfcN67ty5BS5fpUoVDBgwAAMGDMCQIUOwdetWHD58GEOHDpX239KlS+Hi4qJyefkT7HKampq5bku+vg+R1/rf3U5h4s6Pjo4OfvjhBwwdOhQrVqxQaj0g365MJsORI0dyjbNevXqF2m5OiYmJ8PPzQ3p6Oho1aqSyjI+PD5YvX57rOuT75ptvvoG7u7vKMubm5krTDAwMCh+wCuHh4fD394cQItdkyebNmzFlyhSFaQU9rgYPHoyDBw9i3LhxaN++PSpXrgxNTU0cPnwYv/zyC7KysvKNcdy4cRgwYAD279+P/v37w9vbG9bW1krjZmzYsAHTpk3DkSNHcO7cOSxbtgwLFy7E8uXLMWnSpFzX36pVK4SGhuLYsWPw9/eHv78/tm7digULFiAgIACVKlXKN0YiIiIiKv2Y2CAiIiIqZ1q1agU9PT34+/vDxMQE+vr6aNasmTTf1dUVGRkZOH36NM6fPw8XFxfpZqujoyNkMhnS0tLQuXPnPLdjaWkJMzMzJCQk5Fs2pyFDhqBTp04YNmwYevbsiQMHDhT6xm5QUBCuXbsGDw8PWFtbF3i5ZcuW5ftUeV5UPdleUC1btsTWrVvx9OlTAICTkxOA7O59CrP/CiK/Qcs/RHHFPXjwYCxbtgxLlixR2WWSk5MTjh49iho1akgDohclPz8/JCYmYtGiRVIdc1q5ciU2b96MH3/8Mdcn/+XLaWpqfvC+eZ+/4bp16yCEwNq1a2FmZqY0f9asWfDx8VFKbBREXFwcDh48iGHDhmH16tUK806ePFng9Xh4eMDKygre3t6oX78+zp8/j++++w5aWsqXpvXr10f9+vUxbdo0xMXFoUWLFpg+fTomTpyY5/6RD5zev39/AMDvv/+OiRMnwtvbG9OmTStwrERERERUejGxQURERFTO6OrqolWrVjh37hw0NTXRqlUrhRux9evXR+XKlbF06VIkJSVJ3VAB2d3PdO/eHbt378alS5fQsmVLhXULIRAdHQ1LS0toaGhgyJAh+O2337Bz50588sknSrG8evUKVlZWStMHDRoELS0tDB48GN26dcOhQ4fy7eIpp7/++gsACtUNFQA0adKkUOUL6/Tp02jRooVSK5SsrCwcOHAAAKSudLp27QorKyssWbIEAwcOVHqS/O3bt8jIyICxsXGh45Dvy5iYmPepRp6KK26ZTIYlS5aga9euWLx4sdL8YcOG4ddff8XMmTOxc+dOpVYGL1++xEcffSS9NzIyKlT9vb29UalSJUybNk3lTfakpCSMHDkS+/btw4ABA1Suo1GjRqhfvz5Wr16N//73v0qJsIyMDCQkJBSo1UBh/4ZZWVlYv349GjRooNCtU0537tzB3LlzERgYqJDsLAj5/n63ZdDz58+lz2NBaGtrY+TIkfjpp58wb948AMqf45iYGJiZmSl0ZWdmZgZ7e3s8fPgQKSkpubb0UtXVVuPGjaX1EhEREVH5wMQGERERUTnk5uYGf39/XLhwQbp5KCeTydCuXTvs3btXKpvTH3/8gbZt26J9+/YYPnw4GjVqhKysLISFhWHfvn0YPny41B3TwoULcf78eXz66af49NNP0bJlS+jo6ODRo0c4fPgwmjRpgvXr16uM8ZNPPoG2tjY+/fRTdO3aFUeOHIGJiUm+dUtJScGWLVtQtWpVabDq0uKnn37C+fPn0atXLzRu3BimpqZ48eIFdu3ahatXr8LNzU3qcsfQ0BAbN25Enz59ULt2bXh6esLR0RFxcXG4f/8+du/ejT179igkngqqWbNm0NDQwMKFCxEbGwtDQ0PY29ur7OKpsIoz7i5duqBTp044deqUyjrNnTsXc+fOhYuLCwYMGICqVavi+fPnuHr1Kg4fPqwwfkrLli1x8uRJeHl5oUaNGpDJZBg0aJDK7d6/fx8XLlzAyJEjVSY1AKB3797Q1taGt7d3rokNmUyGTZs2oWPHjmjYsCE8PT1Rr149JCcnIyQkBLt378bixYsL1H1a5cqV4ejoiG3btsHBwQEfffQRDA0N0atXL5Xljx8/jsjIyDyTff3798fcuXPh7e1d6MSGsbExunTpgs2bN0utwB49eoQ1a9bA3t6+UGO8jB07FkuXLoWvry9cXV2VWshs3LgRv/zyC/r27QtHR0doa2vjzJkzOHbsGD799NM8u6+rW7cuWrZsiRYtWkjHx59//gkdHZ1c//5EREREVPYwsUFERERUDuVMVuQcXyPntL1790JTUxPt2rVTmGdjY4OrV6/Cy8sL+/btw+bNm6GnpwcbGxv06tULn376qVTW1NQU58+fx7Jly+Dn54d9+/ZBS0sL1atXR9u2bXN9clzOw8MDu3fvRv/+/dGlSxccO3YMpqameS6ze/duxMXFYcKECQUaE6IkzZo1Czt27MDZs2dx7NgxxMTEwNDQEHXr1sWyZcswceJEhafQu3btisDAQCxZsgSbN29GVFQUzM3N4eDggK+//jrPgarzUqNGDfj4+MDLywuff/450tPTMWLEiCJJbBRn3ADg5eWFZs2aqRwzZM6cOWjatClWrlyJ5cuXIykpCVZWVqhfvz5WrlypUFbe/dDChQvx5s0bAMj1xra3tzeA7DFYcmNubg43NzecOHECkZGRsLGxUVnOxcUF169fx+LFi7F//36sXr0axsbGsLOzw8iRI9GpU6cC7QcA2LJlC7766ivMnDkTycnJsLW1zTWxUZA61K9fH7Vq1cK2bdvwyy+/FHp8m82bN2P69Ok4cOAANmzYACcnJyxcuBDa2toYNWpUgdfj6OgINzc3/P333yoTMR06dMD169dx8OBBPH/+HJqamrC3t8dPP/2U5/gaQPb4JocPH8bKlSsRHx8PKysrtGzZEjNmzICzs3Oh6ktEREREpZdMFMUog0REREREREQF1L17d1y8eBHPnj0rdIKFiIiIiEgj/yJERERERERERSMkJATHjh3D0KFDmdQgIiIiovfCFhtERERERERU7C5fvox79+5h5cqVuHfvHu7duwc7Ozt1h0VEREREZRBbbBAREREREVGx++OPP+Dp6YmEhARs2bKFSQ0iIiIiem9ssUFERERERERERERERGUGW2wQEREREREREREREVGZwcQGERERERERERERERGVGUxsEBERERERERERERFRmcHEBhERERERERERERERlRlMbBARERERERERERERUZnBxAYREREREREREREREZUZTGwQEREREREREREREVGZwcQGERERERERERERERGVGUxsEBERERERERERERFRmcHEBhERERERERERERERlRlMbBARERERERERERERUZnBxAYREREREREREREREZUZTGwQEREREREREREREVGZwcQGERERERERERERERGVGUxsEBERERERERERERFRmcHEBhERERERERERERERlRlMbBARERERERERERERUZnBxAYREREREREREREREZUZTGwQEREREREREREREVGZwcQGEQCZTIYOHTooTJs7dy5kMhlOnz6tlpgKq6zFW9ROnz4NmUyGuXPnqjUOOzs72NnZqW37HTp0gEwmU5jGfUNERCVp/fr1kMlkWL9+vbpDKVOKcr9V9PNCIiJ1UMd9hYiICMhkMowcObJY1l8epaenY86cOXBycoKuri5kMhn27t37XvuS5zyFM3LkSMhkMkRERKhl+7l9HlV9dkuauvdNWcXEBpUYmUym8NLU1ISFhQU6duyIrVu3qju8YlEavhwLIjk5GWZmZpDJZBg8eHCu5fL70S4PF9Hyk5mcL319fVhZWaFly5aYNGkSzp07V2zbLyvHjCqqkipERKQoMzMTa9euhaurKypVqgRtbW1YWVmhYcOGGDNmDPbv36/uEItNSSW45ReG7553Vq5cGR07dsSWLVuKPQYiIioevK9Qtvzzzz8YPXo0ateuDWNjY+jq6sLW1haffPIJ/Pz8kJmZWeIxLVu2DPPnz0fVqlUxdepUzJkzB3Xq1CnxOMoqOzs7hc+gtrY2KleujAYNGmDYsGHYsWMH0tLSimXbZfmeQ3m4X1Yaaak7AKp45syZAyA7S37//n3s27cP/v7+uHLlCn7++Wc1R/evSZMmYdCgQahRo4a6Qyl227dvR3x8PGQyGXbv3o3Xr1+jcuXK6g5LrUxNTTFlyhQAQEZGBmJiYnDjxg388ccf+O2339ClSxds3LgRH330kcJyp06dUkO0/9q4cSOSk5PVGkNu1L1viIjULTMzEz179sTRo0dhZmaGHj16oHr16khLS8OdO3ewdetW3L9/H71791Z3qB+kb9++aNmyJapUqaLWODw8PODi4gIASEtLQ1hYGPbv3w9/f3/cvXsXCxcuVGt8RET0/nhfIVu1atVw7949mJqaFsv631d6ejomT56M1atXQ1NTE66urujRowd0dXXx5MkT/P3339i1axf69++PnTt3lmhsBw8ehJGREU6cOAEdHR2FmEvjviytvvzyS5iZmSErKwsJCQl48OAB9uzZg82bN8PJyQmbN29G8+bNFZZZvHgxpk+fjmrVqqkl5tJ8n0/d+6asYmKDSty73eGcOnUKH3/8MZYvX47JkyeXmq5qLCwsYGFhoe4wSsSff/4JDQ0NTJ06FT/++CM2bNiAr7/+Wt1hqZWZmZnKrpvCwsIwevRoHD9+HO7u7rh48SL09PSk+Q4ODiUYpbLS+AMtp+59Q0Skbr6+vjh69CicnZ1x5swZpQvn5ORkXL58WU3RFR1TU9NScVOgT58+St1JXL16FU2bNsXPP/+M2bNnK/yGExFR2cH7Ctm0tbVLZWuDiRMnYu3atWjQoAF27NiB2rVrK8zPzMzE1q1b1dJS9dmzZ6hcubJCUgMovfuytJoyZYrS5yw+Ph6zZ8/Gr7/+ii5duuDSpUsK+7RKlSpqffClNN/nU/e+KavYFRWpXadOnVCnTh0IIRAYGAhAsYnW1q1b0aJFCxgZGSl8aSYnJ2Px4sVwcXGBoaEhjIyM0KpVK/j6+qrcTlpaGn744Qc4ODhAV1cX9vb2mDVrFlJTU1WWz6uZ2P379+Hp6Qk7Ozvo6urCysoK7dq1wx9//AHg3y6bAODMmTMKzfTePQG7fPkyPvnkE1hbW0NHRwc2Njb473//i2fPnqmM6+rVq3B3d4exsTFMTEzQuXNnXLx4Ma9dnKfbt2/j0qVL6NSpE7777jvo6Ojgr7/+UirXoUMHjBo1CgAwatQohTpFRETAzs4O8+bNAwC4ubkpzJcLDg7G9OnT0bRpU1haWkrNUMeNG4cnT57kGuPx48fRq1cvWFlZQVdXFzY2NvDw8MDJkyfzrV9KSgo++eQTyGQyTJw4EVlZWYXdRQpq1qyJQ4cOoU6dOggKCsLq1asV5qvqZiMtLQ0rV65E48aNYW5uDgMDA9jZ2SnUoSDHTM4+P4ODgzFw4EBYWVlBQ0NDOk7za5p58eJFdO7cGaampjA2NkbXrl1x5coVpXJ59e/47pgd8rjOnDkDQLF5eM4m07l1QZKamoolS5agQYMGMDAwgImJCdq1awc/Pz+lsjn3QUREBAYNGgQLCwvo6emhadOmOHjwYK51JyJStwsXLgDI/o5VdePfwMAAbm5uKpf19fWFm5sbzMzMoKenh7p162LBggUK5zFPnz6FpqYmGjVqlGsM3bp1g0wmw+3btxWmF+Z8RP5bk5aWhvnz56N27drQ1dWVkgjvdl0p/9149OgRHj16pPA7MXLkSMTGxsLAwAAODg4QQqiMu1evXpDJZCp/swqjSZMmqFSpElJSUvDmzRuFefLfrRcvXmDMmDGoVq0aNDU1FbrgLMx+unr1Kr788ks4OzujUqVK0NPTg5OTE7755hvExsYWOObY2Fi0b98eGhoaWLx4sdI2CnteeOrUKbi7u6NSpUrQ1dVFrVq1MH36dMTHxyuU++yzzyCTyfDw4UOF6SNGjIBMJkOnTp0Upr958wba2tpo3769NC3nseDv748OHTpIsfbo0QP37t0r8H4gIspLRb2vkNe4EM+fP8fEiRNhZ2cHHR0dWFpaol+/frh69apS2aL8vj5//jzWrl2LSpUq4dixY0pJDQDQ1NTEsGHDsHnzZoXpWVlZWL16NZo1awYjIyMYGhqiWbNm+OOPP1Rey8t/u6OjozFu3DhUqVIFurq6qFevHtatW6dQVn6NGx4ernA+Ij8e8tqXISEhGDBgAMzNzWFoaIjWrVvj0KFDee6HJ0+eYNKkSahZsyZ0dXVRuXJl9O7dWzo+c8p5nOzcuRPNmzeHgYEBKlWqhEGDBuHp06cqtxETE4P//e9/qF+/PgwMDGBqagpnZ2dMnz4dSUlJSmVnzJiBunXrQl9fH6ampujUqROOHz+eZz0Kw9TUFCtXrsTw4cMRHx+P6dOnK8zP7T7D/v370alTJ+nvV7VqVbi6uuL3338HUPh7DgkJCfj6669hZ2cHbW1t6fOSX3dQz549w7Bhw2BlZQV9fX00adJEZRd3+XXTriqu/O6X5XUPxs/PD+3bt4epqSn09fXRoEEDLF68WOX3jnwfJCUlYdq0aahRowZ0dXXh6OgILy+vXM+1yyq22KBSQf7BeveG7LJly3DixAn06tULbm5u0gVXXFwcOnbsiOvXr6Nx48bw9PREVlYWjh07hsGDB+POnTtYsGCBwvo//fRT7Nu3Dw4ODpg0aRLS0tLg4+ODW7duFSrWQ4cOYcCAAUhNTYW7uzs+++wzxMXF4caNG/jxxx/x+eefw8XFBXPmzMG8efNga2ur8MOY88vNx8cH48aNg66uLnr37g0bGxs8fPgQf/31Fw4cOIBLly4pPIF/4cIFdO7cGWlpaejXrx8cHR0RFBSEDh06oGPHjoWqh9yff/4JIPtLtFKlSujVqxd27dqFc+fOoV27dlK5kSNHwszMDPv27VPo2gHIbt0wZcoU7N27F2fOnMGIESNU3sDevXs3Vq9eDTc3N7Ru3Ro6Ojq4c+eOVN8rV64oNbubM2cO5s+fDyMjI/Tp0wc2NjZ49uwZLly4gM2bN6Nz58651i02Nha9e/fG+fPnpWZ9RcHAwABTp07FmDFjsGXLFqnLqtyMHDkSvr6+qF+/PoYPHw59fX08e/YMAQEBOHr0KDp37lzgYwYAQkND0aJFC9SqVQtDhgzB27dvYWJikm/cly9fxuLFi9G5c2dMnDgRISEh2L17N86ePYvjx48r/L0Lw8zMDHPmzMH69evx6NEjqVk4gHyflEpLS0PXrl1x5swZ1KlTBxMnTkRycjJ27tyJgQMHIigoCIsWLVJa7tGjR2jevDlq1qyJYcOGISYmBtu3b5eSRbndGCQiUid5N4/BwcGFWs7T0xPr1q1D9erV0b9/f5iZmeHSpUuYPXs2Tp06hRMnTkBLSwvVqlVD586dcfz4cdy6dQsNGjRQWM/z589x4sQJNGnSBPXr15emF/Z8RK5///4IDAxEt27d0KdPH1hZWamM387ODnPmzMHy5csBQOF308XFBebm5hg0aBDWrVuHkydP4uOPP1ZYPjIyEkeOHEGTJk3QtGnTQu27d127dg0xMTGwtbWFpaWl0vyYmBi0bNkSRkZG6NevHzQ0NKRuJwu7n9auXYs9e/bA1dUVnTt3RlZWFq5evYqff/4ZR44cweXLl2FsbJxnvI8fP4a7uztCQkKwceNGDB06VJr3PueFa9asweeffw5DQ0MMGDAAVlZWOH36NLy8vHDgwAGcP38eZmZmALJvEm7btg2nTp2Ck5OTtA5515IXLlxASkqK1OrlzJkzyMjIUEp4ANndfuzbtw/dunXD+PHjcffuXRw+fBiBgYG4e/duqX16kojKlop6X0GV8PBwtG3bFs+ePUPHjh3x2WefITIyEjt27MChQ4ewa9cu9OzZU2m5ovi+lt9jkCca8qKrq6vwftiwYdi6dStsbGwwZswYyGQy7NmzBxMmTEBAQIDKcbLi4uLQpk0b6Ojo4JNPPkFqaip27NgBT09PaGhoYMSIEQCyW3La2dkpnY/If/dy8/DhQ7Rq1QqvX79Gt27d4OLigpCQEPTp0wfdunVTucy1a9fQpUsXxMTEoGvXrujXrx+io6Oxd+9etG3bFnv27EH37t2Vlvv999+xf/9+9O7dG66urrh8+TK2b9+OGzduICgoSGF/hYeHw83NDY8ePUKTJk3w+eefIysrC8HBwfjll18wfvx4GBoaAsi+fu7QoQMiIiLQrl07uLu7IykpCQcPHoS7uzvWrFmDsWPH5rkfCuP777/Hxo0bcfDgQSQkJOR5v+LPP//Ef//7X1hbW6NXr16wsLDAq1evcPPmTaxbtw4TJkwo1D2HtLQ0dOzYETExMejSpQtMTExgb2+fb8yxsbFo3bo1zMzMMGrUKMTFxcHPzw9DhgzB06dPMW3atPfeHwW5X5abmTNnYvHixbCwsMDgwYNhZGSEI0eOYObMmTh27BiOHz+u1PooPT0dXbt2xbNnz9CtWzdoaWlh7969mD59OlJSUhT2X5kniEoIAKHqkDtx4oSQyWRCJpOJiIgIIYQQc+bMEQCEgYGBuHbtmtIyI0aMEACEl5eXwvS3b9+Krl27CplMJq5fvy5N37JliwAgWrZsKd6+fStNf/36tahZs6YAIFxdXRXWJY/B399fmhYVFSVMTEyEtra2OH36tFJckZGRSnV+d71yDx48ENra2sLBwUE8efJEYd7JkyeFhoaG6NOnjzQtKytL1K5dWwAQe/fuVSi/fPlyaf/mjDc/b9++Febm5sLU1FQkJycLIYQ4cOCAACCGDh2qVH7dunUCgFi3bp3K9anaZzk9efJEpKSkKE0/duyY0NDQEOPHj1eaDkDY29sr7SMhFPe3v7+/ACDmzJkjhBAiIiJC1K1bV2hra4vNmzerjEeV8PBwAUDY2trmWS4kJEQAEJqamiI9PV2abmtrq7BsXFyckMlkokmTJiIjI0NpPdHR0Qrv8zpm5LEBEDNmzFBZxtXVVelzJt83AMSvv/6qMG/v3r0CgHB0dBSZmZnSdPlnLDw8XGkb7+7rvLad07v7RgghFi1aJACIbt26KezHly9fCltbWwFAnD9/XuU+mDt3rsK6jh49Kq2LiKg0unbtmtDW1hYymUwMHTpU7Nq1Szr3yY38t7dv377Sb7Wc/Hd3+fLl0rStW7cKAOKbb75RWtePP/4oAIiVK1dK0wp7PiLEv9/3DRo0EFFRUbnG/O75gqrfAbnAwEABQPTv319pnryef/75p8pl3yX/DfPw8BBz5swRc+bMETNmzBCfffaZMDQ0FNWrVxdnz55VWk7++zJs2DCF3yQh3m8/RUREqPzt/+uvvwQAsWTJEoXp7+63oKAgUaVKFWFiYiJOnDihUPZ9zgsjIiKEjo6OMDY2Fvfu3VNY5vPPPxcAxNixY6VpoaGhAoD45JNPpGn3798XAMTHH38sAIiTJ09K86ZMmSIAKOxbeZ00NTUVygohxPTp01WezxMR5YX3FRTJr49GjBihML1Lly4CgFiwYIHC9PPnzwtNTU1RqVIl8ebNG2l6UX5fy/fFu79d+ZGfwzRq1EghtsTERNGkSRMBQGzZskVhGfnxMHr0aIXf3Dt37ghNTU1Rt25dpe3kdj6S276U/+blPN8S4t9r6XfPedLT04WDg4PQ1dVV+vs+ffpUVK1aVVhbWyvcG5EfJ8bGxuLmzZsKy3z22WcCgNi+fbvC9FatWgkAYtGiRUp1iYqKUjhGXV1dhUwmE76+vgrlYmNjhbOzs9DT0xMvXrxQWo8q8ut0VfcKcqpevboAIP7++29pmqr7DI0bNxY6Ojri5cuXKuuRU0HuOQAQnTp1EomJiUrzc7tnJf87DhgwQOG+SFhYmDA3Nxfa2toiNDRUmp7fvbGCfhfkpGrfXLhwQQAQNjY24vnz59L09PR00bNnTwFALFy4UOU+6Natm8K1w8uXL4WpqakwNTUVaWlpKmMoi5jYoBIj/6KQX2DOnDlT9O/fX2hqagoA4quvvpLKyj/wU6ZMUVpPdHS00NTUFE2bNlW5naCgIAFATJs2TZrWuXNnpS9UOfkXUkG+dH766ScBQEyePLnAdc7tBER+8Xfw4EGV8/v06SM0NTVFQkKCEEKIgIAAAUC0b99eqWxGRoZwcHAodGJj48aNAoAYN26cNC09PV1YW1sLPT09ERMTo1D+QxMbeWnQoIGwt7dXmCb/ot69e3e+y+e82X79+nXpRsC7J2X5KWhi4+3bt9IxnfMH+N2TpPj4eAFAtG7dWmRlZeW7/YKctH700UcqE0RC5J3YeDd58e4yOU+6Siqx4ejoKGQymdINFiH+vfEzatQoaVrOv4+qm0U1atQQlStXzjUGIiJ12759u7C2tpZ+QwCISpUqiT59+oj9+/crlXdxcRFaWloiNjZWaV5GRoaoXLmyaNasmTQtOTlZmJqaCmtra6XvyXr16gltbW2Fi8TCno8I8e/3/bs31OXeJ7EhhBBNmzYVWlpaChduGRkZonr16sLY2FjhJkde5L9hql76+vri22+/Vbk/AeR6Yf0++yk3WVlZwsTERLi5uSlMz7nfjh8/LoyNjUXVqlVFUFCQ0jre57xwwYIFuT4cERMTI4yNjYWenp7COYadnZ2oXLmydA7z22+/CQDi4sWLQlNTU2FdDRo0EIaGhgoXy/I6DRkyRGmbYWFhuSaziIhyw/sKilTdjI+MjBQARI0aNVTewBw6dKgAIDZs2KAUf1F8X+vr6wsAKq/x8iLfv8eOHVOad/LkSQFA6bdTnriKj49XWqZ9+/YCgNL5Q2ESG/J9aW9vr/L6U35OlPOcR57wmDp1qsp6yh9AOHTokDRNfpz873//Uyr/999/C0DxoZUrV64IAMLFxUXlNX5O8mM554MKOcnj/e233/Jcj1xBExstWrRQSsjkltgwMDBQuv+kSkETG6rOnYTIO7GhqakpwsLCcl0m54OVJZXYGDNmjAAg1qxZo1T+wYMHQkNDQ+k+mnwfPHz4UGmZ4cOHCwDi1q1bKmMoi9gVFZU4eb9yMpkMZmZmaNeuHUaPHq3QtF6uefPmStMCAwORmZmpcrwKILvJFQCFPiCvXbsGDQ0NtG3bVql8fk04c7p06RIA5NrcsDDk/R+fOXNGZR+Lr169QmZmJoKDg9GkSRNcu3YNAODq6qpUVlNTE23btkVoaGihYpA3EZWPnQEAWlpaGDJkCJYtW4ZNmzZh8uTJhVpnXoQQ2LJlC9avX48bN24gNjYWmZmZ0vx3m89dunQJMpkM7u7uBd5GQEAAfv75ZxgbG+Ps2bNwdnYusvhzEjn6JcxrTAsTExP06tULBw4cgIuLC/r374927dqhRYsWMDAweK9tOzs7KzXZLYh27dpBQ0N5aKUOHTrgzJkzuH79usrjq7i8efMGISEhqFatmspB2uTdaFy/fl1pnouLCzQ1NZWm29jYfNCYM0RExe3TTz9F37594e/vj4CAAFy/fh0BAQHYu3cv9u7di+HDh0v99iYnJ+PGjRuwsLCQuk14l66ursI5j76+Pj799FOsXbsWx44dk7o5uHr1Ku7cuYO+ffsqdCNR2PORnFSdp32ICRMmwNPTEz4+Ppg5cyYA4PDhw3jy5Ak+//xzGBkZFWp969atk7rtyMzMxJMnT7BhwwbMnTsX+/btw5UrV5TWaWdnp7JLrffZT+np6VizZg22bduGu3fvIj4+XqF/8Nz6y965cyeOHz8OJycnHDlyRGU3YO9zXihfRlU3Vebm5mjUqBHOnj2L+/fvS+dPHTt2hI+PD4KCgtCoUSP8/fffqFKlClq2bIkmTZpI3VJFRUXh9u3b6NKlC7S1tZXWr6oLMRsbGwAo1HgjRERyvK+QO/n1U7t27VR+J3fs2BGbN2/G9evXMXz4cIV56vy+lu9fVfvS1dUVmpqaKq8NnZycVHZ1lDPuwp5DyMm317ZtW5XXn/Jr6Zzk5wyPHj1SeWzJx666d++eUndUBd3/8mOoa9euKq/xVcUTHx+vMp6oqCgpnqIkv2eS1/0SABgyZAi++eYb/Oc//8GgQYPg6uqKNm3aqOwytCD09PTQsGHDQi9Xo0YNlV1WdejQAfPmzVN57BW3vM7datWqherVqyM8PBzx8fEK4/eZmprC0dFRaZnyeO7FxAaVuJw3hPNjbW2tNO3169cAsk9EVF1YyiUmJkr/j4+PR6VKlVT+qKvaRm7i4uIAQGkciPchr8fSpUvzLCevh7wfUHk/z+8qTD2A7B+tgIAA1KlTBy1btlSYN3LkSCxbtgxr164t0sTG119/jeXLl6NKlSro2rUrqlWrBn19fQCQ+krMKS4uDubm5lKZgrh+/TrevHmD1q1bq7xZXlTkg4RqamrC3Nw8z7Lbt2+Hl5cXtm7dKvVlqKenh08++QQ//fRTrn/T3BT2by2X37Hz7qChxU2+vdz6XZVPl3/ucsqtH1QtLa0PHiCeiKi4aWtro0uXLujSpQuA7Jvuu3btgqenJzZu3Ii+ffuiT58+iI2NhRACUVFR0g2cghg5ciTWrl2LDRs2SBfMGzZsAACpn2m5wp6P5PS+v0e5GTRoEL755husXbsW06dPh4aGhvQQxn//+98PWrempiZsbW3x/fffIzg4GFu2bMGvv/6KGTNmKJTLrU7vs58GDhyIPXv2oGbNmvDw8IC1tbX0YMLy5ctzHWj24sWLSE9PR4sWLaQL0He9z3nh+/zudurUCT4+Pjh16hScnZ3h7+8vHVOdOnXCjz/+iPj4ePz9998QQqgcXwNQ/butpZV9KZrzIRciooLifYXcFfV1VmG/r6tUqYKwsDA8ffq0UNfk8v377gOP8hjkYy8UJOb3iTu3mIDC/d7Kj60dO3bkuW5V51YF3f+FOYbk8Zw4cQInTpwoVDwfQn7PJL8Exddffw0LCwv8/vvvWLlyJZYvXw6ZTAZXV1csXbq00OOrWVlZ5ZtMUaW03S/Juc28PsuPHz9GXFycQmKjOD8TpU3eaT0iNVP1ZST/sH711VcQ2d2pqXz5+/srLBMTEyM9dZHTixcvChyP/MshtyfsCkNej/j4+DzrIX8ST17+5cuXKtdXmHoA/7bWuH//PmQymcJLPtjo7du3ceHChfeq37tevXqFlStXon79+njw4AE2b94MLy8vzJ07F3PnzlXZAsHMzAyxsbF4+/ZtgbczadIkjB8/HseOHUPv3r0LtWxhyI+vJk2aSD8OudHX18fcuXMRHByMx48fY/PmzWjbti02b96MTz75pNDbfp8faSD/YyfnD6H8qY+MjAyl8qpOgN+HfHu5HbvPnz9XiouIqDzS1NTEp59+iq+++goA8PfffwP49/uvUaNGeZ4rvHtzp3Xr1nBycsL+/fsRFxeH9PR0+Pr6wsLCQunJwMKej+T0vr9HudHX18fIkSMRERGB48ePS4OGt2jRokhbYLZo0QIA8M8//yjNy61Ohd1PV65cwZ49e9C5c2c8ePAA69atw+LFizF37lx8//33SEtLyzW+RYsWoXfv3li3bp00kG1u8RTmvPB9fnflTwiePHkSQUFBiImJkZIXHTt2RGZmJvz9/aWWG7kNWk5EpE7l+b6CKuq+zpK3aJH/NhRUXvs3IyMD0dHReQ5CXRw+5Pd23759eR5bHzKAc2GOIXk8K1asyDOedevWvXc87woJCcGTJ0+gpaWl1OJXleHDh+PSpUt4/fo1Dh06hNGjR+Ps2bPo2rWr1KKkoMrL/ZKc2+Q9k9wxsUFlTvPmzaGhoYFz584VeJnGjRsjKysLAQEBSvNOnz5d4PXIWzYcOXKkQOU1NDRyzYTK11XQejRu3BgAlJo5AtnZVlV1y01qaio2bdoEDQ0NeHp6YvTo0Uqvrl27AgDWrl0rLSdveplbnfKaHxYWhqysLHTp0gXGxsYK8548eYKwsDClZVq2bAkhBI4ePVrguslkMvzxxx+YMmUKjh8/jh49eiApKanAyxdEcnIyli1bBiC72WRh2NjYYMiQITh27BgcHR0REBAgPUEB5H3MfKiAgACVN0fkn4FGjRpJ0+StUCIjI5XKX7lyReX68zs+3mVsbAwHBwc8ffpUao6bk/wiQn7sExGVd/LfR3miwsjICPXq1cOdO3cQExNTqHWNGDECKSkp2L59Ow4dOoTo6GgMHjxY6SnTwp6PfAhNTc18fyM+//xzyGQyrFmzBt7e3sjMzPzg1hrvkje/L0wLv8Lup5CQEABA7969lR6A+Oeff/J88EJXVxc7d+7EgAEDsH79egwdOlTpwvl9zgvlv/Oqzn3j4uIQFBQEPT091K1bV5pubW2N//znPzh37px0PiZPbLRp0wa6uro4deoU/v77b6k7KyKisqC83FdQRf5dHBAQoPLGa3FfZ40bNw5A9sOUud0slsvZerFRo0bIysrC2bNnlcqdPXsWmZmZJX5tmHNfqvobqPq7l8S5lXwbx44dy/d8piTP9eTmz58PAOjVq5fS/Z+8mJmZoXv37li7di1GjhyJmJgYheOhsPccCuPx48eIiIhQmq6u+yU5t6nqOJMnj+zt7XNtoVERMLFBZY6VlRWGDBmCK1eu4IcfflD5pRAaGorw8HDpvXwMif/9739ISUmRpsfExGDBggUF3vaIESNgYmKCP/74Q+WP7ZMnTxTeV65cWeUXHZDdskBbWxtfffUVgoODleanpaUp/PC0bt0atWvXxtmzZ7Fv3z6FsqtWrSrU+Bq7du3C69ev0bVrV3h7e+Ovv/5Sevn5+cHQ0BB+fn5S87fKlSsDyP7CVyWv+XZ2dgCUTwgSExMxduxYlSdcX3zxBQDgm2++UfkkQl5PJ/zyyy+YMWMG/P390bVrVyQkJORatjDCw8PRo0cP3L9/H40aNcr3ZktUVBRu3bqlND0pKQmJiYnQ0tJSaGqb1zHzoR4+fIjff/9dYdq+fftw5swZODo6ol27dtJ0eT+0ORNbAHDr1i2sWLFC5frzOz5U8fT0hBAC06ZNUzguoqOj8cMPP0hliIjKA19fX5w4cULlBeiLFy+k79z27dtL07/++mukpaXB09NT5RNgsbGxUv+7OQ0fPhwaGhrYuHEjNm7cCADSeBM5FfZ85ENUrlwZUVFRed7Ud3JyQqdOnXDw4EGsXr0aZmZmGDRoUJFsH8jeX/InEgvTH3ph95P8vOfdC9FXr15h4sSJ+W5PW1sbvr6+GDp0KHx9fTFw4ECFJ1jf57xw6NCh0NbWxq+//iolXuRmz56NhIQEDB06VKkVbceOHZGcnIwVK1bAyclJ6h5LX18frVq1gp+fH0JDQ9GhQ4d8+/kmIiotyst9BVWqV6+Ojz/+GBEREUpjdF2+fBlbt26Fubk5+vbtW+B1FkabNm0wduxYvH79Gu7u7iofYsvKyoKvry+GDRsmTZNf982YMQPJycnS9OTkZEyfPh0AMHr06GKJOTfyfRkeHo5Vq1YpzJNfS7/Lw8MDDg4O+O2333D48GGV67148aJCHQurSZMmaN26NYKCguDl5aU0//Xr19Ix2rRpU7Rr1w67d++Gj4+PyvXdunVLZTdfhZWQkIDJkydj06ZNMDMzw5IlS/Jdxt/fX2XXcvJ4co5N+j73HAoqMzMT3333ncJ5enh4OFauXAktLS2F8XuaNm0KDQ0NbN26VeHvGBMTg2+//Vbl+t/3fgkALFiwQKHlSmZmJqZOnYqsrKwS/0yUNhxjg8qkVatW4eHDh/j++++xadMmtG3bFh999BGePXuGe/fuITAwEL6+vtLAP5999hm2b9+O/fv3o379+vDw8EB6ejp27tyJZs2aFTgpYGFhga1bt+KTTz6Bm5sbunXrhoYNGyIhIQE3b95EZGSkwolPp06dsG3bNvTq1QuNGzeGtrY22rdvj/bt26NOnTrw8fGBp6cn6tWrB3d3d9SqVQvp6el4/Pgxzp07B0tLS9y/fx9AdksEb29vfPzxx+jfvz/69esHR0dHBAUF4dSpU3B3dy9wywZ5N1RjxozJtYyJiYn0pODmzZsxceJEtGrVCgYGBli+fDlev34t9TX4xRdfwNTUFG5ubtDQ0MCMGTNw+/ZtKYs9a9YsWFtbY9CgQdi2bRtcXFzQpUsXxMfH48SJE9DT04OLiwuCgoIUYujSpQtmzZqFBQsWoG7duujTpw9sbGzw8uVLBAQEoGXLlli/fn2udVi0aBH09PQwZ84cfPzxxzh69Gi+42HIxcXFSQNrZWRkIDY2Fjdu3MDFixeRlZUFd3d3bNiwId9BvJ8+fYpGjRqhQYMGaNiwIWxsbJCQkICDBw/ixYsXmDx5ssITDHkdMx/K3d0d33zzDY4cOQJnZ2eEhIRg9+7d0NPTg4+Pj8LNCA8PDzg5OcHX1xdPnjxBixYt8PjxY+zbtw8eHh7w8/NTWn+nTp2wY8cO9OvXD927d4e+vj5sbW0VTlbfNXXqVBw5cgT79u2Ds7MzunfvjuTkZOzYsQOvXr3Ct99+q3JwPiKisujy5ctYsWIFrK2t0bZtW+k8JTw8HIcOHcLbt2/h4eGh0E2hp6cnrl69it9//x0ODg7o2rUratSogZiYGISHh+Ps2bMYNWoUVq9erbAtGxsbuLm54dSpU9DS0kKDBg1UPk1f2PORD9GpUycEBgbC3d0d7du3h66uLpydndGrVy+FchMmTMDJkyfx8uVLfPHFF4UaayunvXv3Sk/eyQcPP3DgAF6/fo1mzZph/PjxBV5XYfdTs2bN0KZNG+zevRutW7dG27Zt8fLlSxw5cgS1a9dG1apV892mpqYmNmzYAD09Pfz111/o168fdu7cCV1d3fc6L7Szs8Py5csxceJENG7cGJ9++iksLS1x5swZXLx4EXXq1FF5c6RTp05YtWoVXr16hX79+inNkydvchtfg4iotCoP9xVys3r1arRp0wbTpk3D8ePH0bRpU0RGRmLHjh3Q0NDAunXrCvUkfWH99ttv0NTUxOrVq1G3bl106NABzs7O0NXVxdOnT/H333/jyZMnCuc8gwcPxr59++Dn54d69eqhT58+kMlk2Lt3L8LDwzFw4MBC95hQVHVp1aqV1CuE/Fp6z5496NWrFw4cOKBQXltbG7t370bXrl3Ro0cPtG7dGi4uLjAwMEBkZCQCAwMRFhaG58+fK9y0L6zNmzejQ4cOmDlzJnbt2oUOHTpACIGHDx/i+PHjuH//vvSgxdatW9GxY0eMHj0aK1euRIsWLWBmZoYnT57g5s2buH37Ni5evAgrK6sCb3/58uUwMzODEAIJCQl48OABzp49i6SkJNSqVQubN29GrVq18l1P3759YWRkhJYtW8LOzg5CCJw7dw6BgYFo0qQJOnfuLJV9n3sOBdWwYUNcvnwZTZo0QZcuXRAXFwc/Pz/ExcXhxx9/hIODg1S2SpUqGDJkCDZt2gQXFxf06NEDCQkJOHz4MNq3b69yoPG87pflpnXr1vj222/x448/on79+vjkk09gaGiII0eO4Pbt22jbti2mTZv2wXUv0wRRCQEgCnrIzZkzRwAQ/v7+uZZJTU0Vv/76q2jVqpUwMTEROjo6wsbGRnTs2FH88ssvIjo6Wqn8vHnzhL29vdDR0RG2trZi5syZIiUlRQAQrq6uBY7h9u3bYtiwYaJq1apCW1tbWFlZifbt24s1a9YolHv58qX47LPPhJWVldDQ0BAAxJw5cxTK3Lx5U4wYMULUqFFD6OjoCHNzc1GvXj0xbtw4cerUKaVtX7lyRXTt2lUYGRkJIyMj0alTJ3HhwoUC7TMhhHjw4IEAID766CORlpaWZ9nz588LAMLZ2VmaduTIEdGyZUthaGgo/U3Dw8Ol+Zs2bRLOzs5CT09P6W+elJQkZs6cKRwcHISurq6oXr26mDBhgoiOjhaurq65Hh+HDh0SXbt2Febm5kJHR0dUr15d9OnTR2H/+Pv7q9y/Qgjx448/CgCiUaNGIioqKs86h4eHS3HLX7q6usLS0lK0aNFCTJo0SZw7dy7X5W1tbYWtra30PjY2VsybN0+4ubmJqlWrCh0dHWFtbS1cXV3F1q1bRVZWlsLyeR0z8thGjBiR6/ZV7cec++bChQuiU6dOwtjYWBgZGYmPP/5Y/PPPPyrX9fjxY/Hpp58Kc3NzoaenJ5o2bSp27dqV677OyMgQM2bMEPb29kJLS0vpc/XuvpF7+/atWLhwoahXr57Q09MTRkZGok2bNmLr1q1KZfPbB3kdR0RE6vb48WOxatUq0adPH1GrVi1hbGwstLW1hbW1tejWrZvYtGmTyMzMVLnsgQMHRI8ePYSlpaXQ1tYWH330kWjWrJn43//+J+7du6dymU2bNkm/ZT/99FOesRXmfCS/79p169YJAGLdunUK0xMTE8X48eNFtWrVhKamZq7f5xkZGcLCwkIAELdv384zblVGjBih9FsOQBgbG4tmzZqJH3/8Ubx9+1ZpOVXng+8qzH56/fq1+Pzzz4Wtra3Q1dUVNWvWFDNmzBBJSUkqfxNz229ZWVli0qRJAoDo0qWLSE5Olua9z3nhsWPHxMcffyzMzMyEjo6OcHBwENOmTROxsbEq6xwbGyudk/j5+SnMu3DhgrR/7969q7RsbnWSK8g+JyLKifcVCn6N+OTJEzF+/HhRo0YNoa2tLSpXriw8PDxUXv8V1/f1pUuXhKenp3BychKGhoYK1/Pbt29XOu/JzMwUv/32m2jSpInQ19cX+vr6onHjxmLVqlUqz5Hyikt+PpDzfoUQuV+X5rUvHz58KPr37y9MTU2FgYGBaNmypTh48GCe++3ly5fiu+++E/Xq1RP6+vrC0NBQODo6iv79+4tNmzaJ9PR0qWxex0lecUVHR4tvv/1W1KpVS+jq6gpTU1Ph7OwsZs6cKZKSkhTKJiQkiIULF4rGjRsLQ0NDoaenJ+zs7ET37t3FmjVrRGJioqrdqMTW1lbh/EpLS0uYm5uL+vXri6FDh4odO3aI1NRUlcuq+pv88ccfok+fPsLe3l7o6+sLc3Nz4eLiIry8vERCQoLC8u97z0Eut/0sX8/Tp0/FkCFDhKWlpdDV1RWNGjUSW7ZsUbmulJQUMXXqVFGtWjWhra0tHBwcxKJFi0R6enqux2Ve98tyO16FEMLX11e0adNGGBkZCV1dXfGf//xHLFiwQOX5bF77oKD3DcsSmRAq2vsQERERERGpQVhYGBwdHdGmTZsS7Q+aiIiIiIjKDnaCSkREREREpcZPP/0EIQQmTZqk7lCIiIiIiKiUYosNIiIiIiJSq8ePH2Pr1q14+PAh1q1bh4YNG+LatWscjJqIiIiIiFRiYoOIiIiIiNTq9OnTcHNzg4GBAdq2bYs//vgDNWvWVHdYRERERERUSjGxQUREREREREREREREZQbbdhMRERERERERERERUZnBxAYREREREREREREREZUZTGwQEREREREREREREVGZwcQGERERERERERERERGVGVrqDqC8i42NRUZGhrrDICKiCkhLSwvm5ubqDoOIiIiIypDyeB/D0tISUVFR6g6jWFWEOgKsZ3lTEepZEeoIFF09C3Mfg4mNYpaRkYH09HR1h0FERERERERElK/ydh9DJpMByK6XEELN0RSPilBHgPUsbypCPStCHQH11ZNdURERERERERERERERUZnBxAYREREREREREREREZUZTGwQEREREREREREREVGZwcQGERERERERERERERGVGUxsEBERERERERERERFRmcHEBhERERERERERERERlRlMbBARERERERERERERUZnBxAYREREREREREREREZUZTGwQEREREREREREREVGZwcQGERERERERERERERGVGUxsEBERERERERERERFRmcHEBhERERERERERERERlRlMbBAREREREeVi/fr1MDMzK9QyI0eORJ8+fYolHiIiIiIiYmKDiIiIiIgqqNwSEKdPn4ZMJkNcXBwGDhyI4ODgkg+OiIiIiIhypaXuACo62V+71R1CqSHG9FN3CERERERECvT19aGvr6/uMIiIiIiISkSWTBMZmaJQy0THxhdTNLljYoOIiIiIiCgX69evx5QpUxAXFydNW7BgAVauXIm3b99i4MCBsLCwwNGjRxEUFKSw7E8//YRly5YhLS0NgwYNwvLly6GtrV2yFSAiIiIiKoSMTIHDQU8LtYxHc/sS7xqqVCU27t69i/379yM8PByxsbGYOnUqmjdvrrLsn3/+iZMnT2LEiBHo0aOHND0xMRE+Pj64evUqZDIZWrRogVGjRkFPT08q8+jRI3h7eyM0NBQmJiZwd3eHh4eHwvovXryI7du3IyoqCtbW1hgyZAgaN25cPBUnIiIiIqIyYcuWLVi4cCF+//13tGnTBtu2bcOyZctgb2+vUM7f3x9VqlSBv78/QkJCMHDgQLi4uGDs2LFqipyIiIiIqPwoVWNspKamws7ODqNHj86z3D///IOHDx/C3Nxcad7KlSsRGRmJWbNmYfr06bh37x7WrFkjzU9OTsaCBQtgYWGBJUuWYOjQodixYwdOnjwplXnw4AFWrFiBjh07wsvLC82aNcPSpUvx+PHjoqssERERERGp3cGDB2FkZKTw6tatW67lf/31V4wePRqjRo1CrVq18P3336NBgwZK5czNzbFq1SrUqVMHPXv2RI8ePXDq1KnirAoRERERUYVRqhIbjRo1wqBBg3JtpQEAMTEx8PHxweTJk6Glpdjg5MmTJwgKCsL48ePh5OSEOnXqwNPTExcuXEBMTAwAICAgABkZGZgwYQJsbGzQpk0bdOvWDQcPHpTWc/jwYbi4uKB3796oXr06Bg0ahJo1a+Lo0aPFU3EiIiIiIlILNzc3BAUFKbz++uuvXMs/ePBA6XpF1fVLvXr1oKmpKb2vUqUKXr16VXSBF5OcA6cD2V1xmZmZqTUmIiIiIqJ3larERn6ysrLw66+/onfv3rCxsVGaHxwcDENDQzg4OEjTGjRoAJlMhpCQEKlM3bp1FZIizs7OePbsGRITE6Uy7z515ezsjIcPH+YaW3p6OpKTk6XX27dvpXkymSzXF/0rr/3EF1988cVX4V9ERJQ/Q0NDODo6KryqVav2wet9dywNmUyGrKysD17vyJEjIZPJMH78eKV5EydOhEwmw8iRIz94O3IDBw5EcHBwka2PiIiIiKgolKoxNvKzb98+aGpq5to0PC4uDiYmJgrTNDU1YWRkJD1xFBcXBysrK4Uy8ieQ4uLipLKmpqYKZUxNTRUGDHzXnj17sHPnTum9vb09vLy8YGlpmWednuc5t2KpUqWKukMgIiIiIspT7dq1ERgYiOHDh0vTAgMDSzQGGxsbbNu2Db/88gv09fUBACkpKdi6dStq1KhRpNvS19eXtkFEREREVFqUmcRGWFgYDh8+DC8vr1L5FGrfvn3Rs2dP6b08xqioKGRkZKgrrDLl+XOmeYiIipKWlla+CXYiIiqcL774AmPHjkXTpk3RunVrbN++HTdv3kTNmjVLLIbGjRsjNDQUu3fvxpAhQwAAu3fvRo0aNRQGMc/KyoKXlxf+/PNPvHjxArVq1cLs2bPxySefSGUOHz6MKVOmIDIyEi1btsSIESMUtrV+/XpMmTJFeshr5MiRiIuLw969e6UyU6ZMQVBQEE6fPg0A6NChAxo0aABNTU1s2LABOjo6WLBgAQYPHoxJkyZh586d+Oijj/Drr7/mOZ4JEREREVFuykxi4969e0hISMCECROkaVlZWdi4cSMOHz6M3377DWZmZkhISFBYLjMzE4mJiVKrDDMzM6WWF/L3OcvEx8crlImPj8+zb1ltbW2l5uZyQohclyt9KRr1yWs/ERERERGVBkOGDEFYWBimTp2KlJQUfPrppxg5ciT++eefEo3D09MT69atkxIbPj4+GDVqlJRcAIDFixdj8+bNWL16NZycnHD27FkMHToUlpaWcHV1RWRkJPr164eJEydi3LhxuHLlCr755psiiW/Dhg349ttv8c8//2D79u34/PPPsWfPHvTt2xczZ87EL7/8gmHDhuHx48cwMDAokm0SERERUcVRZhIb7du3Vxr3YuHChWjfvj3c3NwAALVq1UJSUhLCwsKkJ6Zu374NIQQcHR2lMr6+vsjIyJDG2bh58yaqVq0KIyMjqcytW7fQo0cPaVs3b96Ek5NTsdeTiIiIiIhKxvr161VO79Chg/TQzciRI5XGrJg9ezZmz54tvf/444+l643c1rt8+fIPDVfB0KFDMWPGDDx69AgAcP78eWzbtk1KbKSmpmLRokU4efIkWrVqBQCoWbMmAgICsGbNGri6uuKPP/6Ag4MDli1bBiC7m61bt27By8vrg+NzdnbGrFmzAAAzZszAkiVLYGFhgbFjxwIAvv/+e/zxxx+4efMmWrZs+cHbIyIiIqKKpVQlNlJSUvDixQvp/atXrxAREQEjIyNYWFjA2NhYobyWlhbMzMxQtWpVAED16tXh4uKCNWvWYOzYscjIyICPjw9at26NSpUqAQDatm2LHTt2YPXq1fDw8EBkZCSOHDmi0OS6e/fumDt3Lg4cOIDGjRvj/PnzCA0Nxbhx40pgLxARERERUWmVnJyM1atXo2vXrtDU1ISvry9OnjyJEydOlGgclpaW6NGjB9avXw8hBHr06AELCwtpfkhICJKTk/Hxxx8rLJeWloZGjRoByG4V36JFC4X58iTIh2rYsKH0f01NTVSuXFnhQbWPPvoIQPY1HxERERFRYZWqxEZoaCjmzZsnvd+4cSMAwNXVFRMnTizQOiZPngxvb2/Mnz8fMpkMLVq0gKenpzTfwMAAs2bNgre3N6ZPnw5jY2P0798fnTt3lsrUrl0bkydPxrZt2+Dr64sqVapg2rRpRT4QHxERERERlS0ymQyHDx/GwoULkZKSgtq1a2PXrl0K1xMlxdPTE5MmTQIA/PbbbwrzEhMTAQCHDh1CtWrVFObp6uq+9zY1NDSUupBNT09XKvduN70ymUxhmnxMwqysrPeOhYiIiIgqrlKV2KhXrx78/PwKXP7dk3cAMDIywpdffpnncra2tpg/f36eZVq1alVkTysREREREVH5oK+vj5MnT6o7DACAu7s70tLSIJPJ0LVrV4V5//nPf6Crq4vHjx/D1dVV5fJ169bF/v37FaZdunQpz21aWlri9u3bCtOCgoJyHW+QiIiIiKg4aKg7ACIiIiIiIio8TU1N3Lt3D3fv3oWmpqbCPGNjY0ydOhVfffUVNmzYgNDQUFy7dg2//vorNmzYAAAYP348Hj58iGnTpuHBgwfYunVrruOOyHXs2BFXrlzBxo0b8fDhQ8yZM0cp0UFEREREVNyY2CAiIiIiIiqjTExMYGJionLeDz/8gNmzZ2Px4sWoW7cu3N3dcejQIdjb2wMAatSogV27dmHv3r1wdnbG6tWrsWjRojy317VrV8yePRvffvstmjVrhjdv3mD48OFFXi8iIiIiorzIxLsdpFKRioqKUtnnrJzsr90lGE3pJsb0U3cIRETlira2NiwtLdUdBhERERGVIfndxyhrZDIZqlSpgufPnyuNEVReVIQ6AqxneVMR6llW65iWpYHDQU8LtYxHc3toZKZ+cD0Lcx+jVI2xQURERERERERUVty9exf79+9HeHg4YmNjMXXqVDRv3lxl2T///BMnT57EiBEj0KNHD2l6YmIifHx8cPXqVchkMrRo0QKjRo2Cnp6eVObRo0fw9vZGaGgoTExM4O7uDg8PD4X1X7x4Edu3b0dUVBSsra0xZMgQNG7cuHgqTkREpGbsioqIiIiIiIiI6D2kpqbCzs4Oo0ePzrPcP//8g4cPH8Lc3Fxp3sqVKxEZGYlZs2Zh+vTpuHfvHtasWSPNT05OxoIFC2BhYYElS5Zg6NCh2LFjB06ePCmVefDgAVasWIGOHTvCy8sLzZo1w9KlS/H48eOiqywREVEpwhYbRERERERU7qRnpiMxPRGJ6UlIzUxFlshElshClhColJQFq/RUaBilARpagIb2/790AF1zQLcSIJOpuwpEVAY0atQIjRo1yrNMTEwMfHx88L///Q9LlixRmPfkyRMEBQVh8eLFcHBwAAB4enpi8eLFGDZsGCpVqoSAgABkZGRgwoQJ0NLSgo2NDSIiInDw4EF07twZAHD48GG4uLigd+/eAIBBgwbh1q1bOHr0KMaNG1cMNSciIlIvJjaIiIiIiKhMSMlIxavkV3iV/Aov///f6JTXSExLRFJ6EhLTk5D0/6/0rNz7h//6qS3MX7+G7kebVReQaWYnOPQscrwss//V////G9sDZrUBfY5lRES5y8rKwq+//orevXvDxsZGaX5wcDAMDQ2lpAYANGjQADKZDCEhIWjevDmCg4NRt25daGn9ewvH2dkZ+/btQ2JiIoyMjBAcHIyePXsqrNvZ2RmBgYG5xpaenq4wloZMJoO+vr70//JCXpfyVKd3VYQ6AqxneVMR6lkR6gior55MbBARERERUamRJbLwLPE5wuLDEJHwCM8Sn0vJjPi0hKLbUF7XXSITSInOfuVH1xwwrQ2Y1fr/f2sDprUAUydASy//5YmoXNu3bx80NTXRrVs3lfPj4uJgYmKiME1TUxNGRkaIi4uTylhZWSmUMTMzk+bJy5qamiqUMTU1ldahyp49e7Bz507pvb29Pby8vAo8aGtZY21tre4Qil1FqCPAepY3FaGeZa2OT1/FwNjYuNDLlXQ9mdggIiIiIiK1SM1MxaOERwiLj0BYXBjC4sPxKOExUjJT1B1awaXGAq8uZb9ykmkARraAZRPgo9bZL4tGgKaOeuIkohIXFhaGw4cPw8vLq1Q+rdu3b1+FVh7yGKOiopCRkaGusIqcTCaDtbU1Xrx4ASGEusMpFhWhjgDrWd5UhHqW1TqmZ8rw5s2bApfP/v2wKJJ6amlpFTjBzsQGERERERGViOT0ZNx5fRc3o2/jVtQthCdEIEtkqSWWYr/HKLKAN+HZr7D/fyJaUy870WHVCrD+/2SHwUfFHAgRqcu9e/eQkJCACRMmSNOysrKwceNGHD58GL/99hvMzMyQkKDYGi0zMxOJiYlSqwwzMzOllhfy9znLxMfHK5SJj4+X5quira0NbW1tlfPK0g24ghJClMt65VQR6giwnuVNRahn2atj4U6U5XUr6XoysUFERERERMUiJSMFd1/fw83oW7gVfRshcaFqS2Qokanh4jIzBXhxPvt18/+nGdsD1m2B6l0AG/fsMTyIqFxo3749GjRooDBt4cKFaN++Pdzc3AAAtWrVQlJSEsLCwlCzZk0AwO3btyGEgKOjo1TG19cXGRkZ0jgbN2/eRNWqVWFkZCSVuXXrFnr06CFt6+bNm3Bycir2ehIREakDExtERERERFRkXiS9xIVnF3H5xT8IjnmIDFF+ujMpFvJWHQ83ZXdfZdkMsOkG2PbMbt1BRKVaSkoKXrx4Ib1/9eoVIiIiYGRkBAsLC6U+yrW0tGBmZoaqVasCAKpXrw4XFxesWbMGY8eORUZGBnx8fNC6dWtUqlQJANC2bVvs2LEDq1evhoeHByIjI3HkyBGMGDFCWm/37t0xd+5cHDhwAI0bN8b58+cRGhqKcePGlcBeICIiKnlMbBARERER0Qd5lPAYF59dwsXnlxAWH67ucAqm9HV3n9191avL2a+rcwHD6oBdn+xXVVdAg5dvRKVNaGgo5s2bJ73fuHEjAMDV1RUTJ04s0DomT54Mb29vzJ8/HzKZDC1atICnp6c038DAALNmzYK3tzemT58OY2Nj9O/fH507d5bK1K5dG5MnT8a2bdvg6+uLKlWqYNq0aahRo0YR1ZSIiKh04ZkxEREREREVWkhcKC48u4gLzy7haeJTdYdTPiU9Ae6syn7pVspOcNQeCVRpp+7IiOj/1atXD35+fgUu/9tvvylNMzIywpdffpnncra2tpg/f36eZVq1aoVWrVoVOBYiIqKyjIkNIiIiIiIqkPjUeJx67I8Tj07iSVlPZqhjjI0PkRoDPPDJfpk6AbVGArVHAIbV1B0ZEREREVGJY2KDiIiIiIhylSWycP1VEI4/Ool/ngdyzIzSIP4hEPg/4Mr32YOO1x4F2HkAmjrqjoyIiIiIqEQwsUFEREREREqikqNx8vEpnHh0ClFvo9QdTtEray02VBGZQOSR7JdeZcBxCFDHE6jsrO7IiIiIiIiKFRMbREREREQkuR9zH7se7sU/zwORhSx1h1N8SuPg4R8i5TVwe2X2q6ob4PIdYNNV3VERERERERULJjaIiIiIiCo4IQSuvLyKXQ/34M7ru+oOhz7UM//sV2UXwOVboOangIamuqMiIiIiIioyTGwQEREREVVQmVmZOPPkHHaH7MGjhMfqDqdklYeuqPLzOgg4NRj4539Aw2+yu6nS0ld3VEREREREH4yJDSIiIiKiCiYlIxXHHx3H3pAD5XP8jIKoCIkNuTfhwPlJwNV5QIPJQL2JgK65uqMiIiIiInpvTGwQEREREVUQGVkZOBZxAtsf7EBsaqy6w1Gr8jbERoGkRAGBs4EgL6DB19ndVGkbqjsqIiIiIqJCY2KDiIiIiKicE0LgzJOz2HLPFy+SX6o7nNKhIrXYeFd6InBtPnD/T6DpfKC2J8fgICIiIqIyhYkNIiIiIqJy7GbULXjfXo+w+DB1h0KlTfIL4Ow44PZKoMVSoIa7uiMiIiIiIioQJjaIiIiIiMqhyDeR8Lm9AVdeXlV3KKVUBW6x8a6Y28CRbkD1LkDLpUDlhuqOiIiIiIgoT0xsEBERERGVIykZKdhyfxsOhB5EpshUdzilV0Xuiio3T44Du04CtUYCzRYAhlXUHRERERERkUpMbBARERERlROBL65g9Y0/8eptlLpDKf0q5OjhBSCygAc+QOh2oNl8oP6XHH+DiIiIiEodJjaIiIiIiMq4mJQY/HnzL5x/dlHdoZQhbLGRp4wk4OI3QIgv0H4tYOGi7oiIiIiIiCRMbBARERERlVFZIgtHwo9h493NSM5IVnc4VB5FXQH2NAMafI3MRguhqctLSCIiIiJSPw11B0BERERERIX3KOERvj07A6tv/smkxvvgGBsFl5WBxId3scfjNF5ei1F3NERERERETGwQEREREZU1+0MP4KvT0/AgNljdoZRdTGwUmNCpjKPrhyA+IgmHhp7DpcW3kZHCgemJiIiISH3YjpiIiIiIqIyIS43D8mu/4urLa+oOhSqQ+4+/RPxTfQDZY4vf2RCKp+dfwe3npqhUy0TN0RERERFRRcQWG0REREREZcCVl1fxxd9fMalRZNhioyDeGnbGBd+GStPjQt5g/6dncW9buBqiIiIiIqKKji02iIiIiIhKsfTMdKy/sxEHwg5B8GZ80WFXVPkS2iY4vmVErvMzUzJxYe5NPLsYjbY/uEDXRLsEoyMiIiKiioyJDSIiIiKiUupxQiSWXvkZEQkR6g6lHGJiIz8hryYjOtw433IRx54h+nYc3JY1gZVLpRKIjIiIiIgqOnZFRURERERUCl14dhHfnPmWSY1iImNiI0+pRu1wdkOTApdPfJqMg0MDcNP7YTFGRURERESUrVS12Lh79y7279+P8PBwxMbGYurUqWjevDkAICMjA9u2bcP169fx6tUrGBgYoEGDBhg8eDAqVfr3qaDExET4+Pjg6tWrkMlkaNGiBUaNGgU9PT2pzKNHj+Dt7Y3Q0FCYmJjA3d0dHh4eCrFcvHgR27dvR1RUFKytrTFkyBA0bty4ZHYEEREREVVYQgj43t+ObQ/82PVUcWJXVLkSWgY4uWMMIGSFWy5DIHDpXcTcS0DbhS7Q0tUspgiJiIiIqKIrVS02UlNTYWdnh9GjRyvNS0tLQ3h4OPr37w8vLy988803ePbsGX788UeFcitXrkRkZCRmzZqF6dOn4969e1izZo00Pzk5GQsWLICFhQWWLFmCoUOHYseOHTh58qRU5sGDB1ixYgU6duwILy8vNGvWDEuXLsXjx4+Lr/JEREREVOG9zXiLxf/8CN8H25nUKHbcv7l5FD8RL+6bvvfyoQef4NCQACS9fFuEURERERER/atUJTYaNWqEQYMGSa00cjIwMMDs2bPRunVrVK1aFbVq1YKnpyfCwsIQHR0NAHjy5AmCgoIwfvx4ODk5oU6dOvD09MSFCxcQExMDAAgICEBGRgYmTJgAGxsbtGnTBt26dcPBgwelbR0+fBguLi7o3bs3qlevjkGDBqFmzZo4evRoyewIIiIiIqpwXiS9xLdnZ+Di80vqDqWCYGJDlTSjZvj7r1YfvJ7o23HY/8kZvLoRUwRREREREREpKlVdURVWcnIyZDIZDAwMAADBwcEwNDSEg4ODVKZBgwaQyWQICQlB8+bNERwcjLp160JL69+qOzs7Y9++fUhMTISRkRGCg4PRs2dPhW05OzsjMDAw11jS09ORnp4uvZfJZNDX15f+T/njfiIiIqKK6mbULSwJXIo3aW/UHUrFwa6olAhNXfjv+xwiq2ief0uOSsXhYefRZr4znPrUKJJ1EhEREREBZTixkZaWhi1btqBNmzZSYiMuLg4mJiYK5TQ1NWFkZIS4uDipjJWVlUIZMzMzaZ68rKmpYtNrU1NTaR2q7NmzBzt37pTe29vbw8vLC5aWlnnW43mecyuWKlWqqDsEIiIiohJ3NOI4Vt/4E5kiU92hVCx8pkbJ07fj8eRmpfwLFkJmWhbOTr+OuNBENPvmP0W6biIiIiKquMpkYiMjIwO//PILAGDMmDFqjiZb3759FVp5yFsfREVFISMjQ11hlSnPnzPNQ0RUlLS0tPJNsBORem1/sAOb721VdxgVk8hSdwSlSoZhQ5xY5Vps67+59iFSYlLRZr4LNDSZVSIiIiKiD1PmEhvypEZ0dDS+//57qbUGkN3yIiEhQaF8ZmYmEhMTpVYZZmZmSi0v5O9zlomPj1coEx8fL81XRVtbG9ra2irnCZF7M3ee0v8rr/1EREREVJ4IIfDX7XXYH3pA3aFUXOyKSiJkWjh7/AtkpRfvEIzBux4jJS4Nbj83hZauZrFui4iIiIjKt1I1eHh+5EmNFy9eYPbs2TA2NlaYX6tWLSQlJSEsLEyadvv2bQgh4OjoKJW5d++eQiuKmzdvomrVqjAyMpLK3Lp1S2HdN2/ehJOTU3FVjYiIiIgqiMysTCy/tpJJDbVjYkPuZdYYhP9TMi38Hp96gWOjLyLtTXr+hYmIiIiIclGqEhspKSmIiIhAREQEAODVq1eIiIhAdHQ0MjIy8PPPPyMsLAxffPEFsrKyEBcXh7i4OClJUb16dbi4uGDNmjUICQnB/fv34ePjg9atW6NSpey+Ytu2bQstLS2sXr0akZGRuHDhAo4cOaLQjVT37t1x48YNHDhwAE+fPoWfnx9CQ0Ph7u5e4vuEiIiIiMqPtMw0LPrHC39HnlZ3KMQWGwCATMM6OL764xLd5osrr3FoWACSo1JKdLtEREREVH6Uqq6oQkNDMW/ePOn9xo0bAQCurq4YMGAArly5AgD49ttvFZabM2cO6tWrBwCYPHkyvL29MX/+fMhkMrRo0QKenp5SWQMDA8yaNQve3t6YPn06jI2N0b9/f3Tu3FkqU7t2bUyePBnbtm2Dr68vqlSpgmnTpqFGjRrFVnciIiIiKt+S05Mx/9JC3Hl9V92hEAC22ACETAMXzkxGekrJdwsVcz8BBwefQ7f1bWBczSD/BYiIiIiIcihViY169erBz88v1/l5zZMzMjLCl19+mWcZW1tbzJ8/P88yrVq1QqtWrfLdHhERERFRfhLTEjHr/ByExoflX5hKCBMbrzVGIPhcVbVt/01kMo6MOI/um9rCqIq+2uIgIiIiorKnVHVFRURERERU3iSnv8Xciz8wqVHayLLUHYFaZRnUxNE13dUdBt48ScbhEeeR9PKtukMhIiIiojKkVLXYICIiIiIqT1IzUzH/0gI8iA1Wdyj0DlkFbrEhIMM/l6cg9Y22ukMBALx5nJTdcmNjWxhY6ak7HKJCuXv3Lvbv34/w8HDExsZi6tSpaN68OQAgIyMD27Ztw/Xr1/Hq1SsYGBigQYMGGDx4sDQOKAAkJibCx8cHV69elbrUHjVqFPT0/v08PHr0CN7e3ggNDYWJiQnc3d3h4eGhEMvFixexfft2REVFwdraGkOGDEHjxo1LZkcQERGVMLbYICIiIiIqBulZ6Vh02YtjapRaFTexEafzGe6cLF3jB8ZHJOHIqPN4G80BxalsSU1NhZ2dHUaPHq00Ly0tDeHh4ejfvz+8vLzwzTff4NmzZ/jxxx8Vyq1cuRKRkZGYNWsWpk+fjnv37mHNmjXS/OTkZCxYsAAWFhZYsmQJhg4dih07duDkyZNSmQcPHmDFihXo2LEjvLy80KxZMyxduhSPHz8uvsoTERGpERMbRERERERFLDMrEz8GLsO1V9fVHQrlqmImNrL0quHon33UHYZKcaGJODzqAt7GpKo7FKICa9SoEQYNGiS10sjJwMAAs2fPRuvWrVG1alXUqlULnp6eCAsLQ3R0NADgyZMnCAoKwvjx4+Hk5IQ6derA09MTFy5cQExMDAAgICAAGRkZmDBhAmxsbNCmTRt069YNBw8elLZ1+PBhuLi4oHfv3qhevToGDRqEmjVr4ujRoyWzI4iIiEoYu6IiIiIiIipCWSILP19bgUvPL6s7FMpTxUxsXL/9NZJjddQdRq7iHr7B8XGX0H1jG2gb8HKVyp/k5GTIZDIYGBgAAIKDg2FoaAgHBwepTIMGDSCTyRASEoLmzZsjODgYdevWhZbWv58JZ2dn7Nu3D4mJiTAyMkJwcDB69uypsC1nZ2cEBgbmGkt6ejrS09Ol9zKZDPr6+tL/ywt5XcpTnd5VEeoIsJ7lTUWoZ0WoI6C+evJMkYiIiIioCP0W9AfOPjmn7jAoXxVv8PAEvX4IOuCQf0E1i74dB/+vrqDz7y2goVm+bwRQxZKWloYtW7agTZs2UmIjLi4OJiYmCuU0NTVhZGSEuLg4qYyVlZVCGTMzM2mevKypqalCGVNTU2kdquzZswc7d+6U3tvb28PLywuWlpbvWcPSzdraWt0hFLuKUEeA9SxvKkI9y1odn76KgbGxcaGXK+l6MrFBRERERFREtt33w/FHJ/MvSOonq1gtNoTuRzj616fqDqPAIs+8xIV5N9B2vou6QyEqEhkZGfjll18AAGPGjFFzNNn69u2r0MpD/qRtVFQUMjIy1BVWkZPJZLC2tsaLFy8gRPn87q8IdQRYz/KmItSzrNYxPVOGN2/eFLh89u+HRZHUU0tLq8AJdiY2iIiIiIiKwLmn57H1/jZ1h0EFVnYuLovC7ZAv8SZKT91hFMoDv0cwqmoAl/G11B0K0QeRJzWio6Px/fffS601gOyWFwkJCQrlMzMzkZiYKLXKMDMzU2p5IX+fs0x8fLxCmfj4eGm+Ktra2tDW1lY5ryzdgCsoIUS5rFdOFaGOAOtZ3lSEepa9Ohauxay8biVdTw4eTkRERET0gYJjg7H82kqICnazvGyrOF1RJRl0xz87/6PuMN7L1eX38HBfpLrDIHpv8qTGixcvMHv2bKWuPWrVqoWkpCSEhYVJ027fvg0hBBwdHaUy9+7dU2hFcfPmTVStWhVGRkZSmVu3bims++bNm3ByciquqhEREakVExtERERERB8gKjkaCy4tQVpmmrpDqXAiDofh1LhjOPzpfgR8ewaxwbG5ln3zOAFXvC7j1Lhj6DhpBVb8/VypzJbLgM0MwPxr4Osd72wrGqj1PZDwtqhrUbyETiUc2zBU3WF8kIBZ1/HsUpS6wyBSKSUlBREREYiIiAAAvHr1ChEREYiOjkZGRgZ+/vlnhIWF4YsvvkBWVhbi4uIQFxcnJSmqV68OFxcXrFmzBiEhIbh//z58fHzQunVrVKpUCQDQtm1baGlpYfXq1YiMjMSFCxdw5MgRhW6kunfvjhs3buDAgQN4+vQp/Pz8EBoaCnd39xLfJ0RERCWBXVEREREREb2ntxlv8cOlhYhNzf2GOhWPZwFPcHfdbTQY7wyzWuYIPxCKf+ZfQIdVnaFrpqtUPjM1EwYfGaJK62p49NddvNsVVXQiMGYzsH4EUNMC6PEb0LE20LNh9vwJvsCSvoCJfglUrgg9eDIZsU8M8i9YimWlC/w95Qo8drnCuFrZrguVP6GhoZg3b570fuPGjQAAV1dXDBgwAFeuXAEAfPvttwrLzZkzB/Xq1QMATJ48Gd7e3pg/fz5kMhlatGgBT09PqayBgQFmzZoFb29vTJ8+HcbGxujfvz86d+4slalduzYmT56Mbdu2wdfXF1WqVMG0adNQo0aNYqs7ERGROjGxQURERET0HrJEFn668gvCEyLUHUqFFLY/FDYf28Kmky0AoMF4F7y8+hKRpx7Bsb/ymAxmTuYwczIHADxb/wDvJjbCogBTfWBg0+z3brWAey+yExu+gYC2JtCvUbFWqci9NeyI81tc1B1GkUiNS8OpL/5BT9920NLVVHc4RJJ69erBz88v1/l5zZMzMjLCl19+mWcZW1tbzJ8/P88yrVq1QqtWrfLdHhERUXnArqiIiIiIiN7Dxrub8c+LQHWHUSFlpWchPjQOls6W0jSZhgyWDS0R+yDmvdbpZAUkpwHXHwMxSUDgI6BhNSA2CZi9H1g1qKiiLxlCyxgnfEepO4wi9fpuPC7MuaHuMIiIiIioFGBig4iIiIiokAJfXMHuh3vVHUaFlfYmFSJLQNdUT2G6jpkuUuNSC7gWxRYb5obAhhHA8PVA8yXAwCbAkTvZY248eg10+xWo/T1Qfz6w86ry2p7HA4O9s8fh0PgcmKLiIe0Td7Pnm0wBhq0D0v4dBxjxb7PnPXpdwPDzERY9GVGhxvkXLGMe7o3E3a3h6g6DiIiIiNSMiQ0iIiIiokJ4/fY1frm2EuKdG+NUtshU/P36NgJufQ+E/ACERQN7g4Dq5sC1mcCjGOBJHPD7IGD0JuBVguKyqemApREwqzvgXF15e1lZwGAfYHx74OK3wJVHwJ/n/p0/fU/2PNvKH163VKM2OL2+6YevqJS6vPgWXl5/v5Y5RERERFQ+MLFBRERERFRAmSITS6/8jDdpb9QdSoWmY6wLmYYMqfEpCtPT4lJVDhyuWu6JqbdpwM5rgBDA1tHZJfV1gDrWwPF7QK2PgMsRisvYWQArBgLDWwLvNCQBkD04eXQiMMEVqFcV6N0wewwPALgQCgRGAF92LGDoedVKywAnd44DhOzDV1ZKZaUL/D35H7yNTsm/MBERERGVS0xsEBEREREV0JZ7vrjz+q66w6jwNLQ1YOpghuibUdI0kSUQfSsK5rUrffD6M7KALAE0twca1wAys4CMTEBfGwgIAdIzs6cVhqUxUMUUOH43eyyPcyHZY3ikZwKfbwXWDAE0i+Dq7HHCBLy4Z/rhKyrlkqNScXbmdXWHQURERERqwsQGEREREVEBXH8VhF3Be9QdBv2/mr0d8PjEI0T+/RhvIt/g1pobyEzJhE2nGgCA6yuu4t6mO1L5rPQsxIfHIT48DhkZWXgan4agSCDklfK6I2MAPW3gRTzwLC57YPH0zOyWFQ+jgPsvgGa2hYtXJgP8xgI/HAbqzQMa2QCebYAlRwG32tnba/MjUHsOsMr//fZJulETnFrb+v0WLoOenH2Fu1vC1B0GEREREamBlroDICIiIiIq7WJTYvHz1RXIQiEf06diU7VtdaQmpCF42z2kxqbCxN4Uzb9vBV2z7H6g3kYlQ5ajN6aU2Lc49/Vp6f2yE0lYdgJwdQJOf/NvOSGAcVuAlQOBzZeBatOzW1LUrAw8jQdeJgCrBwPVzAsfc1tHIHDGv++DXwIbLwHX/we0X5bdFVW3ekD9H4D2TkBDFWN15EZo6MD/wASIrIr17No/S++iaktLmDmUv4HSiYiIiCh3TGwQEREREeVBCIGfr65AXGqcukOhd9h3rwn77jVVzmu9oJ3CewMrQ/Tc0wcA8PVTW7hqHYYGHiotJ5MBAdOy/z+2LZCUCiSkZHcjNXAtkJgKjGlbNPH/dwuw7JPsbq+uRwIDmgAGOtnJljMPC5fYeJY6HpFBRTDyeBmTmZKJ09Ouote29tDUqVhJHSIiIqKKjGd+RERERER5OBx+FEFRN9QdBhU1UbDWN4a62UmN2CTg2F3Aw7loNu99HqhkCPR2/ne8jvTMf/8tzBgeGYYNcHxNh6IJrAx6fTceV1feU3cYRERERFSCmNggIiIiIsrFi6SXWH9no7rDoOIgE3nOPnYHOHoHCI8GTtwF3H4B6lgDo/5/CIsZe4Dh6xSXCYrMfiWmAlFvsv9/95nyul8lAAsOA78OzH5vbgjUtQaWnwIuhgGn7gNtHApWDSHTwrkTXyArvWJf2t32CcHzy9HqDoOIiIiISgi7oiIiIiIiUkEIgV+vr0JKZoq6Q6FikXeTiPi3wIy9wJM4oJIB0L8RsLAPoK2ZPf95PPA4RnGZRgv//f/Vx8DWQMC2EhCxSLHcl37AN52Bqmb/Tls/AhixAVjpD0zrAjSzK1gtXonRCLtsVbDC5ZjIAs797zr6HXCDlj4vc4mIiIjKO57xERERERGpcOzRCdyMvq3uMKjY5J3Y+LRp9is360cqTxOrC7Zl3zHK05rbA/fmFmx5uUzDWjj2U5fCLVSOvXmSjKsr76PFd/XVHQoRERERFbOK3V6ZiIiIiEiFmJQYrL+9Qd1hUHEq4BgbpZWQaeDi2S+RnqKp7lBKlTsbwxB9O07dYRARERFRMWNig4iIiIjoHWtu/oWkjGR1h0HFSVa2ExuvNYbjwdlq6g6j1BGZAgHfByErM+8xVIiIiIiobGNig4iIiIgoh8vP/8GFZxfVHQYVMxnK7o3vLAN7HF3TQ91hlFqv78bj7pYwdYdBRERERMWIiQ0iIiIiov+XlpmGP2/+pe4wqCSU4a6oAgOnIPWNtrrDKNWurbiPpJdv1R0GERERERUTJjaIiIiIiP7fvtADePU2St1hUEkoo11RxekMwu3jtuoOo9RLT8rAP1531B0GERERERUTJjaIiIiIiADEpcZhR/AudYdBJabsJTay9KriyJ/91B1GmRF2+Cle3YhRdxhEREREVAyY2CAiIiIiArD5ni/eZrDrmoqj7I2xEXT7ayTH6qg7jDKFrTaIiIiIyicmNoiIiIiowouIf4QTj06qOwwqUWWrxcYb/b64fsBR3WGUOS+vxSD82DN1h0FERERERYyJDSIiIiKq8Lxvr0NWGR5Mmt5H2fl7C10rHPEeqO4wyqwrP99FVnrZ+XsTERERUf6Y2CAiIiKiCi3wxRUERd1QdxhU4jLVHUCB3Qn9Em9e6qk7jDIr4VES7vqGqzsMIiIiIipCTGwQERERUYWVKTKx7s4GdYdB6lBGWugkGXTD5R311B1GmRf0ezBSE9LVHQYRERERFREmNoiIiIiowjr3JACRb56oOwxSB1npHzxc6Jjj2Mah6g6jXEiNS8MtnxB1h0FERERERURL3QHkdPfuXezfvx/h4eGIjY3F1KlT0bx5c2m+EAJ+fn44deoUkpKSUKdOHYwZMwZVqlSRyiQmJsLHxwdXr16FTCZDixYtMGrUKOjp/dt0+9GjR/D29kZoaChMTEzg7u4ODw8PhVguXryI7du3IyoqCtbW1hgyZAgaN25c/DuBiIiIiEqEEAJ+wbvUHQapi8gCZOoOIm/BTycjNtJQ3WGUG/e2hKHhaEfoGGurOxQiIiIi+kClqsVGamoq7OzsMHr0aJXz9+3bhyNHjmDs2LFYtGgRdHV1sXDhQqSlpUllVq5cicjISMyaNQvTp0/HvXv3sGbNGml+cnIyFixYAAsLCyxZsgRDhw7Fjh07cPLkSanMgwcPsGLFCnTs2BFeXl5o1qwZli5disePHxdf5YmIiIioRF14dgmRbyLVHQapTekeYyPF0A0BmxupO4xyJe1NBu5sDlN3GERERERUBEpVYqNRo0YYNGiQQisNOSEEDh8+jH79+qFZs2awtbXFpEmTEBsbi8DAQADAkydPEBQUhPHjx8PJyQl16tSBp6cnLly4gJiYGABAQEAAMjIyMGHCBNjY2KBNmzbo1q0bDh48KG3r8OHDcHFxQe/evVG9enUMGjQINWvWxNGjR0tmRxARERFRsfML3qHuEEitSu8YG0LLGMe3eao7jHLpzoYwpCdlqDsMIiIiIvpApSqxkZdXr14hLi4ODRs2lKYZGBjA0dERwcHBAIDg4GAYGhrCwcFBKtOgQQPIZDKEhIRIZerWrQstrX974XJ2dsazZ8+QmJgolWnQoIHC9p2dnfHw4cNiqx8RERERlZx/XgQiLD5c3WGQmggAslI8xkbY60mICjFWdxjlUmpcGu5t42efiIiIqKwrVWNs5CUuLg4AYGpqqjDd1NRUmhcXFwcTExOF+ZqamjAyMlIoY2VlpVDGzMxMmicvm9d2VElPT0d6err0XiaTQV9fX/o/5Y/7iYiIiEqK34Od6g6BSKVUo9Y4vVy5BTsVndvrQvGfITWhpaep7lCIiIiI6D2VmcRGabdnzx7s3PnvBbK9vT28vLxgaWmZ53LPizuwMiTnIPBERERExSXo1Q08iA1WdxikTqX0eRqhqY9Tu8YBopQGWE68jU7FA78I1BvukH9hIiIiIiqVykxiQ96qIj4+Hubm5tL0+Ph42NnZSWUSEhIUlsvMzERiYqK0vJmZmVLLC/n7nGXi4+MVysTHx0vzVenbty969uwpvZe3PoiKikJGBvtwLYjnz5nmISIqSlpaWvkm2IkqIr9gttag0ikycQKe3zVTdxgVwp2NYfjP0JqQaTCJRERERFQWlZnEhpWVFczMzHDr1i0pkZGcnIyQkBB06dIFAFCrVi0kJSUhLCwMNWvWBADcvn0bQgg4OjpKZXx9fZGRkSGNs3Hz5k1UrVoVRkZGUplbt26hR48e0vZv3rwJJyenXOPT1taGtra2ynlC5N5/L0+j/5XXfiIiIiIqCo8SHuFW9G11h0FqJjRK33lnulFjnPq1jbrDqDDePElG5OmXqNHRWt2hEBEREdF7KFWDh6ekpCAiIgIREREAsgcMj4iIQHR0NGQyGbp3747du3fjypUrePz4MVatWgVzc3M0a9YMAFC9enW4uLhgzZo1CAkJwf379+Hj44PWrVujUqVKAIC2bdtCS0sLq1evRmRkJC5cuIAjR44otLbo3r07bty4gQMHDuDp06fw8/NDaGgo3N3dS3yfEBEREVHRORJ+TN0hUGlQysZ2Exo68D84EVkZperyrNy7uyVM3SEQERER0XsqVS02QkNDMW/ePOn9xo0bAQCurq6YOHEiPDw8kJqaijVr1iA5ORl16tTBzJkzoaOjIy0zefJkeHt7Y/78+ZDJZGjRogU8PT2l+QYGBpg1axa8vb0xffp0GBsbo3///ujcubNUpnbt2pg8eTK2bdsGX19fVKlSBdOmTUONGjVKYC8QERERUXFIyUiBf+QZdYdBpUDpSmsAz9PGIfJ6ZXWHUeE8vRCF+PBEmNobqTsUIiIiIiqkUpXYqFevHvz8/HKdL5PJMHDgQAwcODDXMkZGRvjyyy/z3I6trS3mz5+fZ5lWrVqhVatWeQdMRERERGXG6SdnkZyRrO4wqBQQMgGUkt6oMgzr4fhSN3WHUTEJ4J5vOFrObKDuSKgMu3v3Lvbv34/w8HDExsZi6tSpaN68uTRfCAE/Pz+cOnUKSUlJqFOnDsaMGYMqVapIZRITE+Hj44OrV69KD2iOGjUKenp6UplHjx7B29sboaGhMDExgbu7Ozw8PBRiuXjxIrZv346oqChYW1tjyJAhaNy4cfHvBCIiIjVgW2ciIiIiqhCOhB9VdwhECoRMEwEnv0Bmqqa6Q6mwHu55jPTkDHWHQWVYamoq7OzsMHr0aJXz9+3bhyNHjmDs2LFYtGgRdHV1sXDhQqSlpUllVq5cicjISMyaNQvTp0/HvXv3sGbNGml+cnIyFixYAAsLCyxZsgRDhw7Fjh07cPLkSanMgwcPsGLFCnTs2BFeXl5o1qwZli5disePHxdf5YmIiNSIiQ0iIiIiKvfuxzxAWHy4usOg0qKU9EUVJTwReomDV6tT2psMhOyPVHcYVIY1atQIgwYNUmilISeEwOHDh9GvXz80a9YMtra2mDRpEmJjYxEYGAgAePLkCYKCgjB+/Hg4OTmhTp068PT0xIULFxATEwMACAgIQEZGBiZMmAAbGxu0adMG3bp1w8GDB6VtHT58GC4uLujduzeqV6+OQYMGoWbNmjh6lEl9IiIqn5jYICIiIqJyj601KCdRChIbmQZOOLamq7rDIADBOx6pOwQqp169eoW4uDg0bNhQmmZgYABHR0cEBwcDAIKDg2FoaAgHBwepTIMGDSCTyRASEiKVqVu3LrS0/u1N3NnZGc+ePUNiYqJUpkEDxW7VnJ2d8fDhw2KrHxERkTqVqjE2iIiIiIiK2pu0Nwh4ekHdYRBJhEwDl85PQVoyL8dKg+g78YgLewOzmsbqDoXKmbi4OACAqampwnRTU1NpXlxcHExMTBTma2pqwsjISKGMlZWVQhkzMzNpnrxsXttRJT09Henp6dJ7mUwGfX196f/lhbwu5alO76oIdQRYz/KmItSzItQRUF89eSZNREREROXahWcXkZaVln9BqjjUfG0ZozkU909XU28QpCBk/xM0nVJX3WEQlag9e/Zg586d0nt7e3t4eXnB0tJSjVEVH2vr8t/1X0WoI8B6ljcVoZ5lrY5PX8XA2LjwD3yUdD2Z2CAiIiKicu3c0/PqDoFKGzUmNrL0bXF0VS/1BUAqhR18giZf1in3T1RSyZK3qoiPj4e5ubk0PT4+HnZ2dlKZhIQEheUyMzORmJgoLW9mZqbU8kL+PmeZ+Ph4hTLx8fHSfFX69u2Lnj17Su/lx39UVBQyMjIKUMOyQSaTwdraGi9evIAQQt3hFIuKUEeA9SxvKkI9y2od0zNlePPmTYHLZ/9+WBRJPbW0tAqcYGdig4iIiIjKrbjUONyKvq3uMKi0UeO96yvXvkJKgrb6AiCV3jxJxstrMbBuUlndoVA5YmVlBTMzM9y6dUtKZCQnJyMkJARdunQBANSqVQtJSUkICwtDzZo1AQC3b9+GEAKOjo5SGV9fX2RkZEjjbNy8eRNVq1aFkZGRVObWrVvo0aOHtP2bN2/Cyckp1/i0tbWhra36+6gs3YArKCFEuaxXThWhjgDrWd5UhHqWvToW7mRZXreSricHDyciIiKicuv804vIElnqDoNKGzUlNuJ0B+LWUTv1bJzyFXrgibpDoDIoJSUFERERiIiIAJA9YHhERASio6Mhk8nQvXt37N69G1euXMHjx4+xatUqmJubo1mzZgCA6tWrw8XFBWvWrEFISAju378PHx8ftG7dGpUqVQIAtG3bFlpaWli9ejUiIyNx4cIFHDlyRKG1Rffu3XHjxg0cOHAAT58+hZ+fH0JDQ+Hu7l7i+4SIiKgksMUGEREREZVb554GqDsEIgBAll4VHF3TT91hUB7CjzxFq/81gIY2n/+jggsNDcW8efOk9xs3bgQAuLq6YuLEifDw8EBqairWrFmD5ORk1KlTBzNnzoSOjo60zOTJk+Ht7Y358+dDJpOhRYsW8PT0lOYbGBhg1qxZ8Pb2xvTp02FsbIz+/fujc+fOUpnatWtj8uTJ2LZtG3x9fVGlShVMmzYNNWrUKIG9QEREVPKY2CAiIiKicun12xjce31f3WFQaaSGFhs37n6NpBjdkt8wFVhqfDqeXoiCjetH6g6FypB69erBz88v1/kymQwDBw7EwIEDcy1jZGSEL7/8Ms/t2NraYv78+XmWadWqFVq1apV3wEREROUEH0UhIiIionLp/LPzyAK7oSJVSraP4zf6Hri2L/d+7qn0eOz/Qt0hEBEREVEBMLFBREREROXSuafn1R0ClVaykmuyIXQtccxnUIltjz5M5JmX6g6BiIiIiAqAiQ0iIiIiKndiU+LwICZY3WFQqVVyLTbuhE9B/Av9EtsefZik52/x+l68usMgIiIionwwsUFERERE5c6NqBsQJdzdEJUhspI5NpINu+Ly9nolsi0qOuyOioiIiKj0Y2KDiIiIiMqd66+C1B0ClWYl0BOV0DbDsY3Di39DVOQiTzOxQURERFTaMbFBREREROVOUNQNdYdApVkJJDaCn09GzGPD4t8QFbmoW3F4G52i7jCIiIiIKA9MbBARERFRufIo4RFiUmLVHQZVYCmGHRCwqbG6w6D3JTiIOBEREVFpx8QGEREREZUr7IaK8lWMY2wILSOc2OZZbOunkvEi8LW6QyAiIiKiPDCxQURERETlyvVX7IaK1Of/2LvzuKrq9A/gn3P3DbjsIIvIJi4I7gvmVi6pZWqTZYvpaIuWVtM01ljTYmP7r5rGclJTR3PJNMdcyjTLLXdzFxFRFBAQLjvc9fcHcpUEZblw7r183q8XL7jnnnN4ngPKvd/nfL/P+bxnkJ3iKXYY1EhZB1jYICIiInJmLGwQERERkdswWUw4fvWE2GGQs2uiHhtGXS/8vLBn05ycmlXRpVKUZJWJHQYRERER1YKFDSIiIiJyG6fzzsBoMYodBjm7Jihs2KQqbFv7JGBrhs7k1Cy4HBURERGR82Jhg4iIiIjcxun8M2KHQC1UeulUXD7uLXYY5EBcjoqIiIjIebGwQURERERu42x+itghkCtwcPNwk7Yztv6nr0PPSeLLOpArdghEREREVAsWNoiIiIjIbaQYzokdArUwNokcv2yaBquZb63cjeFcMcrzK8QOg4iIiIhqwFffREREROQWDBUG5JTliB0GuQIHztjIMj2BCwf9HHY+ci45xwxih0BERERENWBhg4iIiIjcApehojpzUH9vs7YDfpg3yDEnI6eUd7pA7BCIiIiIqAYsbBARERGRW2Bhg5qTTZBi17ZnYamQih0KNaG804Wifv/t27dDEAQYDIZb7hcREYGPP/7YYd93wIABeO655xx2PiIiIiJHY2GDiIiIiNzCWQMLG1Q3ggOWosrBRKTsDnJANOTMrjpwxkZWVhaeffZZREZGQqlUIiwsDPfccw+2bt1a6zF9+vRBZmYmvLy8AACLFi2CXq+/ab/9+/fjiSeecFisRERERM5OJnYARERERESOkMLCBtVZ4wobFk00fvi/YQ6KhZxZ4YUSmMstkKkaNzMnLS0NSUlJ0Ov1eP/99xEfHw+TyYQffvgB06ZNw+nTp286xmQyQaFQICjo9gU0f3//RsVHRERE5Go4Y4OIiIiIXF5+eT4MFVwLn+qoET02bBCwd89zMJbyHrGWwGaxIT+58ctRTZ06FYIgYN++fRg7dixiY2PRoUMHvPDCC/jtt98AAIIg4PPPP8e9994LrVaLt99+u9pSVNu3b8fEiRNRUFAAQRAgCAJef/11ADcvRWUwGPDkk08iMDAQKpUKHTt2xPfffw8AuHr1Kh566CGEhIRAo9EgPj4ey5cvb3SORERERM2Jr8aJiIiIyOVlFGeKHQK5kkYsRZUvfwSntoU6MBhydldPF8C/k3eDj8/Ly8PmzZvx9ttvQ6vV3vT8jUtLvf7663jnnXfw8ccfQyaTITU11f5cnz598PHHH+O1117DmTNnAAA6ne6m81mtVtx9990oKirC0qVLERUVhZMnT0IqrZx1Ul5ejq5du+Jvf/sbPD09sWHDBjz66KOIiopCjx49GpwnERERUXNq8IyNN954A8eOHav1+ePHj+ONN95o6OmJiIiIiOoss4SFDaqHBtY1rOpwbP7iHsfGQk4v/0zjZmykpKTAZrMhLi7utvuOHz8eEydORGRkJMLDw6s9p1Ao4OXlBUEQEBQUhKCgoBoLGz/99BP27duHNWvWYPDgwYiMjMTIkSNx9913AwBCQkLw4osvIjExEZGRkXj22WcxbNgwrFq1qlF5ugKOYxAREbmPBhc2Tp48iYKC2qf7FxYW4uTJkw09PRERERFRnWWwsEH10cAZGwcOPY+yQoWDgyFnV3ChpFHH22x1/33r1q1bo74XABw5cgShoaGIjY2t8XmLxYK33noL8fHx8PHxgU6nww8//ICLFy82+ns7O45jEBERuY8mW4oqKysLarW6qU5PRERERGTHpaioqRUo/4Rjm9uIHQaJoCi9cYWNmJgYCIJQY4PwP6ppqar6ut378Pfffx+ffPIJPv74Y8THx0Or1eK5556D0Whs9Pd2dRzHICIich31Kmxs374dv/zyi/3xmjVrsHXr1pv2Ky0txYULF9C5c+fGR0hEREREdBuZJVlih0AuRKhn83CrKgibvry/aYIhp1ecUQqr2QqJrGELHvj4+GDo0KH497//jenTp99UvDAYDNX6bNyKQqGAxWK55T6dOnXCpUuXkJycXOOsjV27dmHUqFF45JFHAFT25EhOTkb79u3rlpCL4TgGERGRe6rXKzOj0YjCwkIUFlauMVpWVmZ/XPVRVFQEmUyGwYMH46mnnmqSoImIiIiIbsQeG1QftnouRXX09AsoyVU2UTTk7KwmG0qyyhp1jn//+9+wWCzo0aMHvv32W5w9exanTp3Cp59+it69e9f5PBERESguLsbWrVuRm5uL0tLSm/bp378/+vXrh7Fjx2LLli04f/48Nm3ahM2bNwOonEGyZcsW7N69G6dOncKTTz6JK1euNCo/Z8ZxDCIiIvdUrxkbQ4YMwZAhQwAA06ZNw8SJEx2yBigRERERUUPllxtQZm7coCO1LEI9uocXq+/FwbU19yqglqP4chk8Qhu+TFRkZCQOHTqEt99+G3/5y1+QmZkJf39/dO3aFZ9//nmdz9OnTx889dRTGDduHK5evYp//OMfeP3112/a79tvv8WLL76Ihx56CCUlJYiOjsY777wDAJg1axZSU1MxdOhQaDQaPPHEE7jvvvtu2XvClXEcg4iIyD0Jtvp0MhOZ1WrFqlWrsGPHDhgMBvj4+KB///4YO3YshGvzyW02G1atWoWtW7eipKQEcXFxmDx5MoKDg+3nKS4uxsKFC3Hw4EEIgoCePXti4sSJUKlU9n0uXLiABQsW4Ny5c/D09MSwYcMwatSoeseck5MDk8lU6/PC/DX1Pqe7sk0eI3YIRERuRS6Xw9/fX+wwiJrcyaun8Lcdr4gdBrmQ5wVfDMpacNv9bEo/fLv4XyjIdK819zdeXY1Dxb8hs+ISFBIlotRtcb//BAQpQgAAuaYrmJn6ZI3HPtXqr+jmkVTjcwszP8Huwp+rbeug6Yznw/4BADBZTVh85TMcKd4HL6k3Hg58Eu21CfZ9N+etRZ4pB+MDn3BEmg7V753OiLkvXOwwiJrF7cYxXI0gCAgODkZmZiZcaAisXlpCjgDzdDctIU9XzdFolWDjkcv1OmZUjzaQWCoanWd9xjEa3Ty8rKwMOTk5KCkpqTFwR67T+d1332HLli2YNm0aQkNDkZqairlz50Kj0WD48OEAgHXr1mHTpk2YNm0aAgICsHLlSrz99tv46KOPoFAoAACffvop8vPzMWvWLFgsFsydOxfz5s3DjBkzAFSurTl79mzEx8djypQpuHjxIj7//HNotVrcddddDsuHiIiIiBrvatlVsUMgFyPUcSmqk2kz3K6oAQBnSk9goP5uRKhiYLVZsCZ3KT5Kfx1vtfkXlBIVfGR++DDqq2rH/Gr4EZvz1qKjtsstz91R2wUTg561P5YJ8uvnKPgBF8rP4eXwd3G85BC+zPwIH0UtgiAIyDFewQ7DFsxq/YFjk3WQ4gzOCnMnzTmOQURERE2jwYWNwsJCLFy4EHv37oXVaq11v5UrVzb0W9wkOTkZ3bp1Q5culS+mAwICsHPnTqSkpAConK2xceNGjBkzBt27dwcAPPPMM5gyZQr279+PpKQkXLp0CUeOHMGcOXMQFRUFAJg0aRLmzJmDRx99FD4+Pti5cyfMZjOmTp0KmUyGsLAwpKWl4fvvv2dhg4iIiMjJ5FcYxA6BXExdyhql2iH4bUV8k8cihqoZFFUmBU3H8+cm4EL5OcRqOkAiSOEl8662z6Hi39DdMwkqya0LPTJBdtOxVTKNl5Cg64EQZTj85YH4JmcRii2F8JB5YemVLzDW/zGopZrGJddESrPLxQ6BHECMcQwiIiJqGg0ubPznP//BwYMHcffddyMuLg46nc6RcdUoNjYWW7duRUZGBlq1aoW0tDScOXMGjz32GAAgOzsbBoMBnTp1sh+j0WgQHR2N5ORkJCUlITk5GVqt1l7UAID4+HgIgoCUlBT06NEDycnJaNeuHWSy65cnISEB69atQ3FxcY25mkymalM1BUGAWq22f023x+tEREREDWFgYYPq6XY9NmxyL/z43wnNFI34Sq2VDai10prf06WVpyC94jweDqx5eaobnSk9judTJkAj0SJO0wmj/cdDJ/UEAIQp22BP4XYYrRU4UXIYXlJv6KSe+K3wF8glcnTx6OW4pByswmAUOwRyADHGMYiIiKhpNLiw8fvvv2PEiBF45JFHHBnPLd13330oKyvD888/D4lEAqvVigcffBB33HEHAMBgMAAAvLy8qh3n5eVlf85gMMDT07Pa81KpFDqdrto+AQEB1fbR6/X252p68bN27VqsXr3a/rhNmzZ49913b7smWOYtn21ZbuyDQkRERFRXhgr3bHhLTeg2S1GdvTIdVy80vFG0K7HarFiZvQDR6nYIUbaucZ+dBT8hWBGKaHXcLc/VUdsFXTx6w08egBxjFtbkLsXHl97CK+HvQCJIkeR1Jy5VpOG1tGehk3riqVZ/RYm1GOtyv8Zfw2Zjbc4y7CvagQB5EB4Pehbect+mSLlBylnYcAtijGMQERFR02hwYUOpVDZ7Q9I9e/Zg586dmD59un15qEWLFsHb2xsDBgxo1lj+aPTo0Rg5cqT9cdXsg5ycHJjNZrHCcimZmSzzEBE5kkwmY/NwahEKWdigerrVjI1yXT/s+L+uzRiNuJZd+Q8uV1zA38Ln1Pi80VqBvYW/YqTvA7c9Vw/PO+xfhyojEKqMwMvnn8KZ0uNop02ATJDdNOtjYeanuNN7JC5WnMfh4r14PeJjbM5bi+XZX2JqyMzGJedAFfksbLgDMcYxiIiIqGk0uLBxxx13YN++fRg6dKgj47mlpUuXYtSoUUhKSgIAhIeHIycnB9999x0GDBhgn1VRUFAAb+/r67oWFBQgIiICQOXMi8LCwmrntVgsKC4uth+v1+vtszeqVD2u2ueP5HI55HJ5jc/dqhs8F1+67lbXiYiIiKg2hcYisUMgV1PLi3CbTIstKyY3bywiWnblPzhash8vhf0TPnK/Gvc5WLQbRqsRfTwH1vv8/oog6KSeyDZloR0Sbnr+dOkxZBjT8XjQNHyTsxjx2i5QSlTo5pGEbfkb6/39mhJnbLgHMcYxiIiIqGk0uLDRq1cvnDx5Em+//Tbuuusu+Pr6QiKR3LRfZGRkowK8UUVFxU3fQyKR2AfEAwICoNfrcezYMXsho7S0FCkpKRgyZAiAyj4dJSUlSE1Ntcd2/Phx2Gw2REdH2/dZvnw5zGazvc/G0aNH0apVK67BSURERORkik3FYodALqfmG2rSDNOQfdazxufcic1mw9fZX+Jw8W/4a9hs+CsCa913R8FPSNR1h4fMq9Z9apNnykWJpajGZuImqxHLrszDlOAXIBGksNqssF1bIsxiM8MKS72/X1Nijw33IMY4BhERETWNBhc2XnvtNfvXR48erXW/lStXNvRb3KRr165Ys2YN/Pz8EBoairS0NHz//fcYOLDy7iFBEDB8+HCsWbMGwcHBCAgIwIoVK+Dt7Y3u3bsDAEJDQ5GYmIh58+ZhypQpMJvNWLhwIfr06QMfHx8AQN++ffHNN9/giy++wKhRo5Ceno5NmzZhwoSW00CQiIiIyFUUG0vEDoFcjFBDjw2jrie2fdxbhGia37Lsedhb+CueCXkFKokaBeZ8AIBaooFCorTvd8WYibNlJzEj9NUazzPr/DSM8XsUXTx6odxahvW5K9HFoze8ZHrkGLPwTc5iBMiD0UHT+aZj119dhXhtV4SrKgeQo9Vx+CZnMZI878Q2w0ZEq9s1QeYNZ6mwwlxmhkzd4LfQ5ATEGMewWq1YtWoVduzYAYPBAB8fH/Tv3x9jx461L2Fts9mwatUqbN26FSUlJYiLi8PkyZOr9aEsLi7GwoULcfDgQQiCgJ49e2LixIlQqVT2fS5cuIAFCxbg3Llz8PT0xLBhwzBq1CiH5UJERORMGvyq7Omnn3ZkHHUyadIkrFy5EvPnz0dBQQF8fHwwePBg3H///fZ9Ro0ahYqKCsybNw+lpaWIi4vDK6+8AoVCYd9n+vTpWLBgAd588037C4JJkybZn9doNJg1axYWLFiAmTNnwsPDA2PHjsVdd93VrPkSERER0e1xxgY1lk2qwrbvngJsLWOh2O2GzQCA99NnVds+MehZJHndaX+8q+AneMt80V6TWON5soyXUWatLCxKIMGlijTsLvwZpZYS6GXe6KBNxCi/hyGXVF+y93LFBRwo2oV/RPyffVtXjz44U3Yc76W/gkBFCKYEv+CIVB2q3GCCjoUNlybGOMZ3332HLVu2YNq0aQgNDUVqairmzp0LjUaD4cOHAwDWrVuHTZs2Ydq0aQgICMDKlSvx9ttv46OPPrKPZXz66afIz8/HrFmzYLFYMHfuXMybNw8zZswAULlaxezZsxEfH48pU6bg4sWL+Pzzz6HVajmWQUREbkmwsbFBk8rJyYHJZKr1eWH+mmaMxrnZJo8ROwQiIrcil8vZIJNahHu+Gy12CORiXlTo0D99qf1xesVz+HHuAPECIpdw/+Y74RXBpYmpft555x14eXlVK6p88MEHUCgUmD59Omw2G5588kmMHDkS9957L4DKIsWUKVMwdepUJCUl4dKlS3jhhRcwZ84cREVFAQCOHDmCOXPm4PPPP4ePjw9+/PFHLF++HF9++aV9Se1ly5Zh//79+Pjjj+sV8+3GMVyNIAgIDg5GZmam2/b2bAk5AszT3bSEPF01R6NVgo1HLtfrmFE92kBiqWh0nvUZx+DtJkRERETksixW51qHn1zEDUtRmbSJ+OmzfiIGQ67CarKKHQK5oNjYWGzduhUZGRlo1aoV0tLScObMGTz22GMAgOzsbBgMBnTq1Ml+jEajQXR0NJKTk5GUlITk5GRotVp7UQMA4uPjIQgCUlJS0KNHDyQnJ6Ndu3b2ogYAJCQkYN26dSguLq6xX6jJZKpWwBAEAWq12v61u6jKxZ1y+qOWkCPAPN1NS8izJeQIiJdngwsbc+fOve0+giCIMtWTiIiIiFoGi42FDaq/qrdcNokcv26eBqvp5ubBRH9kNbvOnZZUMzHGMe677z6UlZXh+eefh0QigdVqxYMPPog77rgDAGAwGAAAXl5e1Y7z8vKyP2cwGODp6VntealUCp1OV22fgICAavvo9Xr7czUVNtauXYvVq1fbH7dp0wbvvvuu2874DQoKEjuEJtcScgSYp7tpCXm6Wo6Xs/Pg4eFR7+OaO88GFzZOnDhx0zar1QqDwQCr1QpPT08olcoajiQiIiIicgwWNqhhKgeos8xTkHbAPQfwyPGsZs7YcHVijGPs2bMHO3fuxPTp0xEWFoa0tDQsWrQI3t7eGDBggEO/V32NHj0aI0eOtD+uutM2JycHZrNZrLAcThAEBAUFISsry6WWgqmPlpAjwDzdTUvI01VzNFkEFBUV1Xn/yr8ffg7JUyaTNf1SVP/+979r3G42m/HTTz9hw4YNePXVVxt6eiIiIiKi2+JSVNQwNli07fDj+3fefleia6wm1xmQoJqJMY6xdOlSjBo1CklJSQCA8PBw5OTk4LvvvsOAAQPssyoKCgrg7e1tP66goAAREREAKmdeFBYWVjuvxWJBcXGx/Xi9Xm+fvVGl6nHVPn8kl8shl8trfM6VBuDqymazuWVeN2oJOQLM0920hDxdL8f6LSlVlVtz5+nwOdcymQzDhg1DQkICFixY4OjTExERERHZccYGNYRNELBr+3SYK6Rih0IuhD023FdTjmNUVFRAIqk+9CKRSOwDPwEBAdDr9Th27Jj9+dLSUqSkpCA2NhZAZZ+OkpISpKam2vc5fvw4bDYboqOj7fucOnWq2kyLo0ePolWrVjUuQ0VEROTqmmwx2datW+PUqVNNdXoiIiIiIhY2qEH25UYjZU8rscMgF8OlqNxfU4xjdO3aFWvWrMGhQ4eQnZ2Nffv24fvvv0f37t0BVC7fMXz4cKxZswYHDhzAxYsX8dlnn8Hb29u+T2hoKBITEzFv3jykpKTg9OnTWLhwIfr06QMfHx8AQN++fSGTyfDFF18gPT0du3fvxqZNm6otNUVEROROGrwU1e0cPXqUPTaIiIiIqElZrBxopPr7VXcUdzzji4B5bWAp5+8Q1Y2NvypurynGMSZNmoSVK1di/vz5KCgogI+PDwYPHoz777/fvs+oUaNQUVGBefPmobS0FHFxcXjllVegUCjs+0yfPh0LFizAm2++CUEQ0LNnT0yaNMn+vEajwaxZs7BgwQLMnDkTHh4eGDt2LO666y6H5kNEROQsGlzYWL16dY3bS0pKcOrUKZw/fx6jRo1qcGBERERERLdjA0caqWF2BP+MzjOKEPNFIowF7tMkl5qOVNlkCx5QMxFjHEOtVuPxxx/H448/Xus+giBg3LhxGDduXK376HQ6zJgx45bfq3Xr1njzzTcbGioREZFLaXBh45tvvqlxu1arRWBgIKZMmYI772QzPiIiIiJqOgqp4vY7EdXisPcBFD9bjG7z+6Esyyh2OOTkWNhwfRzHICIich8NLmysXLnSkXEQEREREdWbSqoWOwRycWd1p1HydBEGLr4HJanlYodDTkyqZLN5V8dxDCIiIvfBW06IiIiIyGUppQpI+JKWGilDeRkbJq6ERyeV2KGQE5OxsEFERETkNBrdPPzkyZM4dOgQcnJyAAD+/v7o0qUL2rdv3+jgiIiIiIhuRRAEKGUKlJl5pz01jkGej2/GLcafPB5D0a4KscMhJ8SlqNwHxzGIiIhcX4MLG2azGR9//DH2798PANBoNACA0tJSrF+/Hj169MCMGTMgkzW6dkJEREREVCuVVM3CBjlEubQMy0bOx0Oej6Nkk0XscMjJSFWcseHqOI5BRETkPhrVPHz//v245557MHLkSOj1egBAQUEB1q9fj/Xr12P16tV48MEHHRUrEREREdFNVDIlwBvsyUGsggXL+i/AnzwegWkVBzfpOqmCMzZcHccxiIiI3EeDX5nt3LkT/fv3xyOPPGJ/MQAAXl5eeOSRR9CvXz/s2LHDETESEREREdVKJWVfBHK8b7oshenPBRA4lk0ABJkAuZaFLlfHcQwiIiL30eCX6QaDAdHR0bU+HxMTA4PB0NDTExERERHViUrGwgY1jQ0xa2GYdhkS3qnf4qm8FRAEQewwqJE4jkFEROQ+GvwK3cfHBydPnqz1+ZMnT8LHx6ehpyciIiIiqhOtXCt2COTGfg7ZgovTT0Luwbv1WzK1r1LsEMgBOI5BRETkPhpc2Ojfvz/27NmD//znP8jIyIDVaoXVakVGRga+/PJL7NmzBwMGDHBgqEREREREN/NVcRCKmtYBv99w7Nk9UPkrxA6FRKLyYWHDHXAcg4iIyH00+LajMWPG4MqVK9i6dSu2bt0KiaSyRmK1WgFUvmAYPXq0Y6IkIiIiIqqFr9pX7BCoBTjteQIlU4vQb9FwlFwoFzscamacseEeOI5BRETkPhpc2JBIJJg2bRpGjhyJw4cPIycnBwDg7++Pzp07o3Xr1g4LkoiIiIioNr4qFjaoeaSrL2Lzn1dj+Mr7UXSCxY2WhIUN98BxDCIiIvdRr8KG0WjEokWLEBYWhrvvvhsA0Lp165v++G/cuBFbtmzB448/DpmMa9ESERERUdPx44wNakZXFblYPX4J7l//GIp+Y3GjpVCxsOGyOI5BRETknurVY+Onn37CL7/8gi5dutxyvy5duuDnn3/Gtm3bGhUcEREREdHt+KrZY4OaV5m0FMvvnQ/tYA5+thQaPxY2XBXHMYiIiNxTvQobe/bsQc+ePREYGHjL/YKCgtCrVy/s2rWrUcEREREREd2Or8pP7BCoBTJLzFh253wox1rFDoWagUeYVuwQqIE4jkFEROSe6lXYuHjxIuLi4uq0b9u2bXHhwoUGBUVEREREVFc6hRZqmUrsMKiFWtl9CayPFwOC2JFQU/IMZ2HDVXEcg4iIyD3Vq7BhNpvrvNakTCaDyWRqUFBERERERPXhwwbiJKL/xa1G8dNZkMjr9faKXIRcI4UmgMVTV8VxDCIiIvdUr1fePj4+uHjxYp32vXjxInx8uN4xERERETW9YG2Q2CFQC/dT+GZkTE+GTCsVOxRyMA/O1nBpHMcgIiJyT/UqbMTHx+PXX39FQUHBLfcrKCjAr7/+ivj4+EYFR0RERERUF+EeYWKHQITf/Hfi1PT9UPrKxQ6FHIjLULk2jmMQERG5p3oVNkaNGgWTyYQ333wTZ8+erXGfs2fP4s0334TJZMK9997rkCCJiIiIiG6ltWe42CEQAQBOeB3Fb9O2QBOqFDsUchDP1ixsuDKOYxAREbmnui00eU1gYCCef/55fPLJJ5g1axYCAwMRHh4OlUqF8vJypKenIysrC0qlEjNmzEBQEJcEICIiIqKmF87CBjmRC5o0lD6xBkO/Hovi0+Vih0ON5NlaJ3YI1AgcxyAiInJP9SpsAECXLl3w/vvvY926dTh06BD2799vf87b2xt33nknRo0ahcDAQIcGSkRERERUm3CPMEgggRVWsUMhAgDkKHLw3aNLMXrtIyg6wOKGK9NHeYgdAjUSxzGIiIjcT70LGwAQEBCAKVOmAADKyspQVlYGtVoNtVrt0OCIiIiIiOpCIVUgSBuIjJJMsUMhsiuWFmPFmAUY5zERxT8bxQ6HGkCQCvCN8xQ7DHIAjmMQERG5l3r12KiJWq2Gj48PXwwQERERkajYZ4OckUliwrIhX0I1SuxIqCG82uggUzfofkByYhzHICIicn2NLmwQERERETkD9tkgZ2UTbFjRexGER8sAQexoqD78OniJHQIRERER1YCFDSIiIiJyCxGercUOgeiW1nZYidIncyDIWN1wFb7t9WKHQEREREQ14JxaIiIiInILbb3bih1CnZRdLcPpJSeQfegKLEYLtEE6JDzbGfpobwDAmRWnkLHzMspzyyCRSeAVpUfbh9vBO9an1nOmbT6PC5vPoyy7FACgC/NA7ANxCOh6vRHuiYXHcOnni5AqZYh7tD1C+4fZn8vYdRmXtl9Ej7/3bqKsqcqPERvQ59l+aPVFDMxlFrHDodvw66AXOwQiIiIiqgELG0RERETkFvw1fvBX+yOnLEfsUGplLDZi98u/wjfeHz1e7QOllwIlmSWQaxX2fXStdOg4pRM0gVpYjRakrj+HvW/sxsC5g6H0UtZ4XrWvCnGPtoc2WAfYgEs/X8T+d35Dvw8HwiPcE1f2ZyJjxyX0/EcflGSW4PfPDiGgcwAUnkqYSkw4s+wker2R1FyXocXbHfgrOs0oQty8bjDmm8QOh2ojAL7tuBQVERERkTNyucJGXl4eli5diiNHjqCiogJBQUGYOnUqoqKiAAA2mw2rVq3C1q1bUVJSgri4OEyePBnBwcH2cxQXF2PhwoU4ePAgBEFAz549MXHiRKhUKvs+Fy5cwIIFC3Du3Dl4enpi2LBhGDWKHf+IiIiInFkH33bYfsl5Cxvn1pyF2k+DxGe72LdpArXV9gnpF1btcfuJHZH+0wUUXSiEspN/jecN7B5c7XHcI+1x4YfzyE/Og0e4J4ouFcO3ox/00d7QR3vjxIJjKL1SCoWnEqeWnEDrYW2g9tc4KEuqi6P6wyh+pgg9F9yJsowKscOhGni10UGudbm3zERERETNzmazNfv3dKlXacXFxXj11VfRoUMHvPLKK/D09ERmZia02utvBtetW4dNmzZh2rRpCAgIwMqVK/H222/jo48+gkJReSfcp59+ivz8fMyaNQsWiwVz587FvHnzMGPGDABAaWkpZs+ejfj4eEyZMgUXL17E559/Dq1Wi7vuukuU3On2fvj2EbFDcBpDxy4VOwQiIiJRtPdth+2XfhU7jFpd2Z8F/84BOPjePlw9kQuVrxqth7VB6yERNe5vNVlx8cc0yDQyeEZ41ul72Cw2ZOy+DEu5Bd5tK5ev8ozwxMUf02AsNqL0SimsRgs0wVrknbyKglQD4p9IcFSKVA+p2hSUPlmMu/57H4pTysUOh/4gqJuv2CEQERERObWicjNSc0pxueAsnhnUvD0PXaqwsW7dOvj6+mLq1Kn2bQEBAfavbTYbNm7ciDFjxqB79+4AgGeeeQZTpkzB/v37kZSUhEuXLuHIkSOYM2eOfZbHpEmTMGfOHDz66KPw8fHBzp07YTabMXXqVMhkMoSFhSEtLQ3ff/89CxtERERETqy9bzuxQ7il0isluLD5PCLvjUb0/bEwpBhwYsFRSGQShA0Kt+93ZX8WDn20H5YKC5TeKvR6PQkKz5qXoapSeKEAu2b+CqvRCqlKiq4ze8AjrLIYEtA5ECH9Q7Hzr79AqpAiYXoXyJQyHJv3OxKmd0HaD+eRtiEVCk8FOj2dCI/wuhVRqPGylFlYP2E57l3zEIoOs7jhTIJ7+okdAhEREZFTstls+D29EBeulgEA0nJLcaVrIAJu857FkVyqsHHgwAEkJCTgo48+wsmTJ+Hj44MhQ4bYiw3Z2dkwGAzo1KmT/RiNRoPo6GgkJycjKSkJycnJ0Gq19qIGAMTHx0MQBKSkpKBHjx5ITk5Gu3btIJNdvzwJCQlYt24diouLodPpborNZDLBZLq+Pq4gCFCr1fav6fZ4nRyH15KIiFqqcI9weMh1KDIVix1KjWw2G/RR3oh7pD0AwCtSj6KLhbjww/lqhQ3feD/0+2ggjIVGXNyShoMf7Effd/tDqa/9jYKulQf6fTQQplIzMndfxu+fHkLv2X3txY22D7ZD2wevF36SV56GX4I/JFIBKd+cQb+PByH7QBaOfHIQd3w4sImuANWkQF6AVX/6Cg94TEDRr0axw6FrgnuwsEFERERUk6slJntRI8hLiUfviGrWogbgYoWN7OxsbNmyBSNGjMDo0aNx7tw5fPXVV5DJZBgwYAAMBgMAwMureoM3Ly8v+3MGgwGentXvQJNKpdDpdNX2uXEmCADo9Xr7czUVNtauXYvVq1fbH7dp0wbvvvsu/P1rXge5Subtkm5BbuyDQo3Da0lERC2VIAiI84nD/isHxA6lRipvFXRhHtW26UI9kLkno9o2mUoGWbAO2mDAu60Ptk3dgvStFxA9NrbWc0vkksrm4QD0UXoUpBhw/vtUdHo68aZ9iy8V4dIv6ej34UCkb70An/a+UHopEZwUgt8/OwxzmQkytbzxCVOdVUgqsGzYfDzo8ThKN1jFDqfF00fpoPFX3X5HIiIiohboXHYJAKC1rxqJ4V5oF+IFwVLRrL02XKqwYbVaERUVhfHjxwOoLB5cvHgRW7ZswYABA0SNbfTo0Rg5cqT9cdUd8zk5OTCbzWKF5VIyM1nmcRReSyICAJlMdtsCO5E76uDX3mkLG95xvii5XH02SUlGMTS3a9xttcFistTre9msNlhrOMZms+Ho50fQYWJHyNSyyv0slW9AbBar/VhqflaJFV/fsRBjPR+CZXnz3vFG1XEZKiIiIqKalVSYkVVQAQCICtDeZu+m41KFDW9vb4SGhlbbFhoair179wK4PquioKAA3t7e9n0KCgoQERFh36ewsLDaOSwWC4qLi+3H6/V6++yNKlWPq/b5I7lcDrm85rvablWp4oJB1zVnRc/d8VoSEVFLFu/XUewQahV5TxR2vfwrzq4+g1ZJITCczcfFH9MQf21WhbncjJTVyQjsHgSltwrGIiMubExFeV45WvUJsZ9nz2s7EdSrFdoMjwQAnPrvCQR0CYTaXw1zmRmXf72Eqydy0fO1PjfFcHHLBSi8lAjsXjnD0zvOF8krTyP/TB6yD12BLswDcq2i6S8G1erbhOW42+NeqBb4wmbh6zoxBPfgjQHkOHl5eVi6dCmOHDmCiooKBAUFYerUqfYlsm02G1atWoWtW7eipKQEcXFxmDx5crWZ+MXFxVi4cCEOHjwIQRDQs2dPTJw4ESrV9ZlFFy5cwIIFC3Du3Dl4enpi2LBhGDVqVLPnS0RE7i01pxQAEOChgIdKvPKCSxU22rZti4yM6tP0MzIy7HejBgQEQK/X49ixY/ZCRmlpKVJSUjBkyBAAQGxsLEpKSpCamorIyMo3gsePH4fNZkN0dLR9n+XLl8NsNtv7bBw9ehStWrWqcRkqIiIiInIeMfpo+Ki8kVeeL3YoN9HHeKPb33ri9NKTOLvqDDQBGrSfFI/Q/mEAAEEioPhSEdJ/vghToRFyDwX00Xr0efuOag29S7NKYCyssD82FlTgyCcHUZFfAZlGBs8IL/R8rQ/8E6svr1phKEfK6jNIeqeffZt3rDci743Gvtl7oPRSImF61ya+ClQXmyL/h37PDIL/vAhYyrk0VbMSgOCevmJHQW6iuLgYr776Kjp06IBXXnkFnp6eyMzMhFZ7/Q7XdevWYdOmTZg2bRoCAgKwcuVKvP322/joo4+gUFQWmj/99FPk5+dj1qxZsFgsmDt3LubNm4cZM2YAqBz7mD17NuLj4zFlyhRcvHgRn3/+ObRarb0vKRERUWPZbDak51X21hBztgbgYoWNESNG4NVXX8WaNWvQp08fpKSkYOvWrXjiiScAVC7/NHz4cKxZswbBwcEICAjAihUr4O3tje7duwOonOGRmJiIefPmYcqUKTCbzVi4cCH69OkDHx8fAEDfvn3xzTff4IsvvsCoUaOQnp6OTZs2YcKECaLlTkRERER1IwgCugV2xY8XfhI7lBoFdg9CYPegGp+TKqToNrPnbc9x53+GVnuc8EyXOn1vpV5107EAEDsuDrHj4up0Dmo+vwZvQ+cZ3RDzRSKMBVzetrn4tfeCyptLgZFjrFu3Dr6+vpg6dap92409PW02GzZu3IgxY8bYxy2eeeYZTJkyBfv370dSUhIuXbqEI0eOYM6cOfZZHpMmTcKcOXPw6KOPwsfHBzt37oTZbMbUqVMhk8kQFhaGtLQ0fP/99yxsEBGRwxjKzDBZbJBJBfh7iDvL26UKG9HR0XjxxRfx9ddf49tvv0VAQAAmTJiAO+64w77PqFGjUFFRgXnz5qG0tBRxcXF45ZVX7Hc5AMD06dOxYMECvPnmm/YpnJMmTbI/r9FoMGvWLCxYsAAzZ86Eh4cHxo4dyxcDRERERC6iR1B3py1sENXHYe8DKH62GF2/7IfyK0axw2kRwgbWXHgkaogDBw4gISEBH330EU6ePAkfHx8MGTLEPr6QnZ0Ng8GATp062Y/RaDSIjo5GcnIykpKSkJycDK1Way9qAEB8fDwEQUBKSgp69OiB5ORktGvXzr7qBAAkJCRg3bp1KC4u5uoTRETkELlFla9H/bQKe49psbhUYQMAunbtiq5da58eLwgCxo0bh3HjxtW6j06ns0/XrE3r1q3x5ptvNjhOIiIiIhJPYkACFFIFjBYOBJPrO6s7jZKpRRi46B6UnC8XOxy3Fz6IhQ1ynOzsbGzZsgUjRozA6NGjce7cOXz11VeQyWQYMGCAvZ+nl5dXteO8vLzszxkMBnh6elZ7XiqVQqfTVdvnxpkgwPUeoQaDocbChslkgslksj8WBAFqtdr+tbuoysWdcvqjlpAjwDzdTUvI0x1zzC2qXA7X74bZGmLl6XKFDSIiIiKi21FKlUjw64T9Vw6IHQqRQ2QoL2PDpJW455txKDrK4kZT0Qap4NdeL3YY5EasViuioqIwfvx4AECbNm1w8eJFbNmyBQMGDBA1trVr12L16tX2x23atMG7775r72PqboKC3L9o2RJyBJinu2kJebpajpez8+Dh4XHTdqvVhrySKwCA1oHe8NBVX7qzufNkYYOIiIiI3FLP4O4sbJBbMcjz8c2Di/En3WMo2l1x+wOo3lrfGSx2CORmvL29ERoaWm1baGgo9u7dC+D6rIqCggJ4e3vb9ykoKEBERIR9n8LCwmrnsFgsKC4uth+v1+vtszeqVD2u2uePRo8ejZEjR9ofV91pm5OTA7PZffr6CIKAoKAgZGVlwWaziR1Ok2gJOQLM0920hDxdNUeTRUBRUdFN2/OKjTBbbVBIBUitFSi6tixV5d8PP4fkKZPJ6lxgZ2GDiIiIiNxS96BuECDABtd5E0F0O+WSMiy7Zz4e8nwcJZstYofjdiKGtBI7BHIzbdu2RUZGRrVtGRkZ9kGbgIAA6PV6HDt2zF7IKC0tRUpKCoYMGQIAiI2NRUlJCVJTUxEZGQkAOH78OGw2G6Kjo+37LF++HGaz2d5n4+jRo2jVqlWt/TXkcjnkcnmNz7nSAFxd2Ww2t8zrRi0hR4B5upuWkKfr5VjzklI5xZWFDF+P6v01qnJr7jwlzfadiIiIiIiakY/KB9H6qNvvSORirIIFywYsgPwB97mj2hmofBQI7OYrdhjkZkaMGIGzZ89izZo1yMrKws6dO7F161YMHToUQOVdrsOHD8eaNWtw4MABXLx4EZ999hm8vb3RvXt3AJUzPBITEzFv3jykpKTg9OnTWLhwIfr06QMfHx8AQN++fSGTyfDFF18gPT0du3fvxqZNm6rNyCAiImoMe+NwneI2ezYPztggIiIiIrc1IKwfzhpSxA6DqEl802UpRniMhuIrL9isYkfj+iIGt4JE6j7NPck5REdH48UXX8TXX3+Nb7/9FgEBAZgwYQLuuOMO+z6jRo1CRUUF5s2bh9LSUsTFxeGVV16BQnF94Gj69OlYsGAB3nzzTQiCgJ49e2LSpEn25zUaDWbNmoUFCxZg5syZ8PDwwNixY3HXXXc1a75EROSebDYbDKUmAICvloUNIiIiIqIm1T+0H746vgRmG+9sJ/e0IWYtBk4bDO95YbAaWd1ojOhRYWKHQG6qa9eu6Nq1a63PC4KAcePGYdy4cbXuo9PpMGPGjFt+n9atW+PNN99scJxERES1KTVaYLbaIBEAD7VzlBS4FBURERERuS0vpRe6BnYROwyiJvVzyBZcnH4Scg/neJPpirwitAjs4iN2GEREREROqaC08kYxD5UMEsE5ZriysEFEREREbu3O8IFih0DU5A74/YZjz+6Byt85lgZwNdH3cbYGERERUW0MZZXLUOk1cpEjuY6FDSIiIiJya92CusJD4SF2GERN7rTnCeyauhna1iqxQ3EpggSIHhUudhhERERETquwrHLGhpeahQ0iIiIiomYhl8jRP+SO2+9I5AbS1Rex+c+r4dGBxY26Cu7pB12wWuwwiIiIiJxWVeNwLyfprwGwsEFERERELcAgLkdFLchVRS5Wj18Cj54sbtRF9H2crUFERERUm3KTBRVmKwDAk4UNIiIiIqLmE+MdjXAPrqFPLUeZtBTLR82HdrDzvPl0RnKdDG2GBIsdBhEREZHTKri2DJVOKYVM6jzlBOeJhIiIiIioCQ2LGCp2CETNyiwxY9md86EcaxU7FKcVO7Y1ZE505yERERGRsymwL0PlPP01ABY2iIiIiKiFuDN8EDQyjdhhEDW7ld2XwPp4MSCIHYlzESRAh0fbiB0GERERkVOrmrHhpXGum0FY2CAiIiKiFkEjV+Ou8EFih0Ekiv/FrUbx01mQyPkWsEr4oCB4hGrFDoOIiIjIqRWVVxY2PFWcsUFEREREJIqRUcMh4UtgaqF+Ct+MjOnJkGmlYofiFDo8GiV2CEREREROzWazoaTiWo8NlXO9huS7OiIiIiKql8cffxyCIOCdd96ptv27776DIDj3WjfB2mB0D+omdhhEovnNfydOTd8Ppa9z3XHX3HziPBHc00/sMIiIiIicWpnRAqsNkAiARsHCBhERERG5OJVKhXfffRf5+flih1JvY2LuEzsEIlGd8DqKvdN+giZUKXYoounwaKTYIRARERE5veIKCwBAq5Q53U1sLGwQERERUb3dddddCAoKwpw5c2rd59tvv0WHDh2gVCoRERGBDz/8sNrzERER+Oc//4lJkybBw8MD4eHh+M9//lNtn/T0dDzwwAPQ6/Xw8fHBqFGjkJaW1qjY2/u2Q5xP20adg8jVpWnOY8sTa6CLU4kdSrNT+ysRdU+o2GEQEREROb3ia8tQaZXONVsDYGGDiIiIiBpAKpXin//8J/71r3/h0qVLNz1/8OBBPPDAA3jwwQdx7NgxvP7663j11VexaNGiavt9+OGH6NatGw4fPoypU6fi6aefxpkzZwAAJpMJQ4cOhYeHB3bs2IFdu3ZBp9Nh2LBhMBqNjYp/TPR9jTqeyB3kKHLw3aNL4dGtZRU3Ov05BlInW0qBiIiIyBkVl1fO2NApZSJHcjMWNoiIiIioQUaPHo3ExET84x//uOm5jz76CHfeeSdeffVVxMbG4vHHH8czzzyD999/v9p+w4cPx9SpUxEdHY2//e1v8PPzw88//wwAWLlyJaxWK+bPn4/4+Hi0a9cOX331FS5evIjt27c3KvZewT0R4dm6UecgcgfF0mKsGLMAuoEKsUNpFmp/JeIejBA7DCIiIiKXUOykjcMBFjaIiIiIqBHeffddLF68GKdOnaq2/dSpU0hKSqq2LSkpCWfPnoXFYrFv69Spk/1rQRAQFBSE7OxsAMDvv/+OlJQUeHh4QKfTQafTwcfHB+Xl5Th37lyj4hYEAQ+3e6hR5yByFyaJCcuGfAnVKLEjaXqd/hwDmRO+MSciIiJyRvbChhPO2HC+iIiIiIjIZfTr1w9Dhw7Fyy+/jMcff7zex8vl8mqPBUGA1WoFABQXF6Nr165YtmzZTcf5+/s3KN4b9QruibbesTiTn9zocxG5Optgw4reizDacxxsS9WATeyIHI+zNYiIiIjqzmK1ocxY+d7MGQsbnLFBRERERI3yzjvvYP369dizZ499W7t27bBr165q++3atQuxsbGQSut2t3SXLl1w9uxZBAQEIDo6utqHl5eXQ2J/pN14h5yHyF2s7bASpU/mQJAJYoficJ0mc7YGERERUV2VXJutIZcKUDjha0MWNoiIiIioUeLj4/Hwww/j008/tW/7y1/+gq1bt+Ktt95CcnIyFi9ejM8++wwvvvhinc/78MMPw8/PD6NGjcKOHTtw/vx5bN++HdOnT6+xYXlDJAYkoJNfvEPOReQufozYgCvPnoNM7T5FALW/EnHjIsQOg4iIiMhlFFdcbxwuCCxsEBEREZEbevPNN+1LSAGVsy1WrVqFFStWoGPHjnjttdfw5ptv1mu5Ko1Gg19//RXh4eEYM2YM2rVrhz//+c8oLy+Hp6enw2J/tP3DDjsXkbvYHfgrkmccgsJbfvudXUDik7GcrUFERERUD8XllTM2tErnfA3lfItjEREREZFTW7Ro0U3bIiIiUFFRUW3b2LFjMXbs2FrPk5aWdtO2I0eOVHscFBSExYsXNyTMOovzaYvugd2w/8qBJv0+RK7mqP4wip8pQs8Fd6Iso+L2BzgpfZSOvTWIiIiI6sneOFzlnCUEztggIiIiohbv0fYPQ4DzTa8mEluqNgU/P7kOumiV2KE0WI+/dYRExre+RERERPVx41JUzoiv7oiIiIioxWvjFYHBre8UOwwip5SlzML6Ccvh0dn1ihuhdwQgrF+g2GEQERERuZyqpah0TroUFQsbREREREQAJnR4FB4KD7HDIHJKBfICrPrTV/DopxA7lDoTZAJ6zuwodhhERERELsdotsJksQEAtFyKioiIiIjIeXkqPPFY+0fEDoPIaVVIKrBs2HxoRrjG28h2D0ZAH8ViJREREVF9Vc3WUMslkEmcc8le13hFSkRERETUDIa0vgux3jFih0HktKwSK76+YyGkDzl3M3GllxxdnokTOwwiIiIil1TVOFzrpP01ABY2iIiIiIjsJIIETyc8CQlfJhPd0rcJy1HxRB4EqXPewdf9xQ5Q6l1n2SwiIiIiZ2JvHO6ky1ABLGwQEREREVUTrY/C0DZDxA6DyOltivwfrj5zAVKVc72tDO7ph7Z/ai12GEREREQuy9kbhwMsbBARERER3eSxdg/DS+EpdhhETu/X4G1InXEUCi/nuJtPqpKi71uJYodBRERE5NLsMza4FBURERERkevQKXSY1HGi2GEQuYTD3gdw+NmdUAWKv/RTl2fbwjNcK3YYRERERC7LarOh5FqPDZ3KeWdsOG/JpQ6+++47fP311xg+fDgef/xxAIDRaMSSJUuwe/dumEwmJCQkYPLkydDr9fbjcnNz8eWXX+LEiRNQqVTo378/xo8fD6n0+g/qxIkTWLJkCdLT0+Hr64uxY8diwIABzZsgEREREYlmUPgA/Jb5G/Zk7hU7FCKnd1Z3GiVTizBw0T0oOV8uSgx+HbzQ8fFoUb43ERERkbvIKzbCagMkAqBROG9hw2VnbKSkpGDLli1o3br62qmLFy/GwYMH8cILL+CNN95Afn4+PvzwQ/vzVqsVc+bMgdlsxuzZszFt2jRs374dK1eutO+TnZ2Nd955Bx06dMB7772HESNG4IsvvsCRI0eaKz0iIiIicgLTEqdCr9SLHQaRS8hQXsaGSSvh0UnV7N9bkAno+3ZnSJy0mTkRERGRq8gurAAAaJUyCILzvrZyycJGeXk5/vWvf+HJJ5+EVnt9mnFpaSm2bduGCRMmoGPHjoiMjMTUqVNx5swZJCcnAwB+//13XLp0Cc8++ywiIiLQuXNnjBs3Dj/88APM5sopNj/++CMCAgLw2GOPITQ0FMOGDUOvXr2wYcMGUfIlIiIiInF4KT3xbOepYodB5DIM8nx88+BiePRRNuv3TZgSA984r2b9nkRERETuKKugcvat1okbhwMuWtiYP38+OnfujE6dOlXbnpqaCovFgvj4ePu2kJAQ+Pn52QsbycnJCA8Pr7Y0VWJiIsrKypCeng4AOHv2bLVzAEBCQoL9HERERETUcvQI6o4hre8SOwwil1EuKcOye+ZDO6x53gwHJHqj87S2zfK9iIiIiNzdlcLKwoYzNw4HXLDHxq5du3D+/HnMmTPnpucMBgNkMlm1WRwA4OXlBYPBYN/nxqJG1fNVz1V9rtp24z5lZWUwGo1QKG5uimcymWAymeyPBUGAWq22f023x+vkOLyWREREjjU5fhKO5hxDVukVsUMhcglWwYJlAxbgT56PwLSq6d52KjxkGPBBN0hkLnnPHrVA7BVKRETOLrugcikqZ24cDrhYYSM3NxeLFi3CrFmzaiwuiGnt2rVYvXq1/XGbNm3w7rvvwt/f/5bHZTZ1YC4kODhY7BDcBq8lERGRY6llajzXdTpe2fEqrLCKHQ6Ry/imy1KM8BgNxVdesDXBP50+ryfAI1Tj+BMTNYFb9Qo9dOgQXnjhBWg0GixYsAAffvgh3nrrLQDXe4Xq9XrMnj0b+fn5+OyzzyCVSjF+/HgA13uFDh48GM8++yyOHz+OL774Anq9HomJic2dKhERuTDO2GgCqampKCgowN/+9jf7NqvVilOnTmHz5s34+9//DrPZjJKSkmqzNgoKCux3Ouj1eqSkpFQ7b0FBgf25qs9V227cR61W11pQGT16NEaOHGl/XHXHfE5Ojr13B91aZibLPI7Ca0lEACCTyW5bYCeiuuvg2x5jY0fjm+RvxQ6FyKVsiFmLgdMGw3teGKxGx1U3YkaHIWpEqMPOR9SUbuwVumbNGvv2ql6hM2bMQMeOHQEAU6dOxfPPP4/k5GTExsbae4W++uqr0Ov1iIiIwLhx47Bs2TI88MADkMlk1XqFAkBoaChOnz6NDRs2sLBBRER1ZjRbkVdsBADonLzHhksVNuLj4/HBBx9U2/b555+jVatWGDVqFPz8/CCVSnHs2DH06tULAJCRkYHc3FzExsYCAGJjY7FmzRoUFBTYl5s6evQo1Go1QkMrXxTHxMTg8OHD1b7P0aNH7eeoiVwuh1wur/E5m81W63FcMOi6W10nqh9eSyIioqbxcLuHcCbvDI7mHhc7FCKX8nPIFnSb3gtt5nWEqajxN355ttai96xOt9+RyEnc2Cv0xsLG7XqFxsbG1tordP78+UhPT0ebNm1q7RW6aNGipk6NiIjcSHZhBWwA5FIBCidf6tOlChtqtRrh4eHVtimVSnh4eNi3Dxo0CEuWLIFOp4NGo8HChQsRGxtrL0okJCQgNDQUn332GR5++GEYDAasWLECQ4cOtRcmhgwZgh9++AFLly7FwIEDcfz4cezZswczZ85s3oSJiIiIyKlIBSle6v4intv+InLLcsUOh8ilHPD7DcXPFiHxyySU5xgbfB6pQoKBH3aDXOtSb2epBWOvUHFV5eJOOf1RS8gRYJ7upiXk6Yo5ZhVW9tfQKmV1jlusPN3uleCECRMgCAI+/PBDmM1me9OtKhKJBDNnzsT8+fMxa9YsKJVK9O/fH+PGjbPvExAQgJkzZ2Lx4sXYuHEjfH198dRTT3H6JhERERHBS+mFl3u8hJk7/g6T1XT7A4jI7rTnCZRMLUK/RcNRcqG8Qefo83oC/DrqHRsYURNxx16hriooKEjsEJpcS8gRYJ7upiXk6Uo5lp4rAQB461Tw8PCo17HNnafLFzZef/31ao8VCgUmT55crZjxR/7+/nj55Zdved4OHTrgvffec0SIRERERORmYr1j8GSnyfjsyOdih0LkctLVF7H5z6sxfOX9KDpRv+JGh8ciETsm/PY7EjkJ9goVnyAICAoKQlZWltsu29wScgSYp7tpCXm6Yo7Jl3IAAEqpDUVFRXU6pvLvh59D8qxPr1CXL2wQEREREYlhaMQQJOefxY8XfhI7FCKXc1WRi9Xjl+D+/z2Gor11K24E9/JDj5c6NHFkRI7ljr1CXZXNZnPLvG7UEnIEmKe7aQl5ulKOWQWVS1HVp3F4VW7NnadzdwAhIiIiInJiT3V6AjH6aLHDIHJJZdJSLB81H9rBt7/fziNUg0H/1x0SJ29iSfRHVb1Cb/y4sVeoRqOx9wo9fvw4UlNTMXfu3Fp7haalpeHIkSM19grNzs7G0qVLcfnyZfzwww/Ys2cPRowYIWb6RETkYq4UVN5wolM6/3wI54+QiIiIiMhJyaVyvNzjb/jLLy8hvyJf7HCIXI5ZYsayO+djnOdjqPi25qKFTCPFXf/uAZW3c/UnIHIU9golIiJnUFxuRnGFBQCgrceMDbGwsEFERERE1Aj+Gj/8o/csvLxzFsrMZWKHQ+SSVnZfgns97odksQ64cQUDAej3zy7waeslWmxEjsZeoURE5IyqlqHy1sghkzr/LFnnj5CIiIiIyMlF6SPxco+XIBN43xBRQ/0vbjWKn86CRH79bWqPlzqgzbBWIkZFRERE1DJkFVYuQxXopRI5krphYYOIiIiIyAE6ByRiepdpECCIHQqRy/opfDMypidDppWiw4RIxE9kDxsiIiKi5lA1Y4OFDSIiIiKiFmZg2AA81v4RscMgcmm/+e+E8F4hes7sKHYoRERERC3GlarChqdS5EjqhoUNIiIiIiIHuj92DEZGjhA7DCKX1TkgEQ8N/BMEgbOfiIiIiJpLVgGXoiIiIiIiatGmxE9CUqveYodB5HLaesfilR5/g1wiFzsUIiIiohbDarPhSmHVjA0WNoiIiIiIWiSJIMFfuj6PboFdxQ6FyGWEe4ThH71nQSVzjTfTRERERO4ir9gEk8UGqUSAr04hdjh1wsIGEREREVETkEvleKXn39A9sJvYoRA5vQjPCPyz72x4KDzEDoWIiIioxbEvQ+WphETiGsuBsrBBRERERNRE5BI5Xu75EnoGdRc7FCKnFeUViX/2fRNeSk+xQyEiIiJqkbIKXatxOMDCBhERERFRk5JL5JjZ4yX0Du4pdihETifWOwazk97kTA0iIiIiEV0pqCxsBHmxsEFERERERNfIJDL8rftf0YcNxYns2vnE4a0+r0On0IodChEREVGLlnltKaogL9fpdcbCBhERERFRM5BKpHip21/QNyRJ7FCIRNfBtz3e6PMaNHKN2KEQERERtXicsUFERERERLWSSqR4sdvzuCt8kNihEImmk188Xu/9GtQytdihEBEREbV4JrMVV4uNAFjYICIiIiKiWkgFKWZ0eRbj4x4UOxSiZjcgtB9e7/MqVDLXedNMRERE5M6uFFbABkCtkMJDJRM7nDpznUiJiIiIiNzIQ3HjEKgJwL8Oz4XZZhY7HKIm92DbB/Bwu4fEDoOIiIiIbpBVWLkMVbCXEoIgADaRA6ojFjaIiIiIiEQyKHwgfNW+mLP3XZSYS8UOh6hJyAQZnun8NO7kEmxERERETifLUNk4PNDTtWbUcikqIiIiIiIRJfh3wrv9/gk/tZ/YoRA5nFauxRt9XmNRg4iIiMhJZVwrbLTSq0SOpH5Y2CAiIiIiEllrz9b4oN+7iPRqI3YoRA4TqAnE+/3moJN/vNihEBEREVEtMguuLUXFwgYREREREdWXr9oH797xT/QNSRI7FKJGa+cThw/6v4MwjzCxQyEiIiKiWthsNmQVuOaMDfbYICIiIiJyEiqZCn/r/iJi9TFYdHIJrDar2CER1dt9Uffi8Q6PQSqRih0KEREREd1CXokJ5SYrpALg72I9NljYICIiIiJyMqNjRiFaH4X3DnwAQ0WB2OEQ1YlWpsGMLtPRu1VPsUMhIiIiojrIvNZfI8BTCZlEEDma+uFSVERERERETijevyM+GfgROvp2EDsUotuK8orExwM/ZFGDiIiIyIVUNQ53tf4aAAsbREREREROy0flg9l938ADsfdDgGvdQUUtx90RQ/F+v3cQpA0SOxQiIiIiqocsF20cDnApKiIiIiIipyYVpHi0/cPo4NcBnxz6F/LK88QOiQgAoJapMDXhKQwI6y92KERERETUAFUzNlp5uV5hgzM2iIiIiIhcQJeARPx70KcYGDZA7FCIEO/XEZ8O/D8WNYiIiIhcWKYLL0XFGRtERERERC5Cp9Diha4z0KdVL/z7yBcwVBjEDolaGJVUhcc7PIrhbe6GIHB5NCIiIiJXVVxhRmG5GQAQrFeKHE39sbBBRERERORiegX3RHvfdvji9y+x4/JOscOhFiLeryOmd57GXhpEREREbqBqtoa3Vg6VXCpyNPXHwgYRERERkQvyVHjipe5/QVKr3pj7+zwUGgvFDoncFGdpEBEREbmfjPxr/TVccBkqgIUNIiIiIiKXlhTSBx382mPBsa+w/dKvYodDbqaTX0c8y1kaRERERG4nPb8MABDmoxY5koZhYYOIiIiIyMXplXr8pdvzuLvNMMw7Oh+pBalih0Quzl/tj0kdJ6BvSJLYoRARERFRE7iUVzljI8ybhQ0iIiIiIhJRe992+L8B7+OHtC1YeuprLk9F9aaUKjE2ZjTGxNwHpdT1mkgSERER0e3ZbDZcyqucsRHqw6WoiIiIiIhIZBJBgrvbDMUdIUlYdmo5NqZthtVmFTsscgF3hPTFxA4T4K/xEzsUIiIiImpC+aUmlBgtkAhAMHtsEBERERGRs9ApdHgyYQqGRgzBf47Nx7Hc42KHRE4q0isST8T/GR382osdChERERE1g/RrszWCvVSQSyUiR9MwLGwQEREREbmxCK/W+Gfft3A4+wiWnVqOM/nJYodETqKVNhjj2v4JA8L6QyK45htaIiIiIqq/qv4arroMFeBihY21a9di3759uHz5MhQKBWJjY/HII4+gVatW9n2MRiOWLFmC3bt3w2QyISEhAZMnT4Zer7fvk5ubiy+//BInTpyASqVC//79MX78eEilUvs+J06cwJIlS5Ceng5fX1+MHTsWAwYMaMZsiYiIiIgcp3NAIjoHJOLAlYP4+tQKnDWkiB0SiaSqoNE/rB+kgvT2BxARERGRW7mUX9VfwzUbhwMuVtg4efIkhg4diqioKFgsFixfvhyzZ8/GRx99BJWqsrq0ePFiHDp0CC+88AI0Gg0WLFiADz/8EG+99RYAwGq1Ys6cOdDr9Zg9ezby8/Px2WefQSqVYvz48QCA7OxsvPPOOxg8eDCeffZZHD9+HF988QX0ej0SExPFSp+IiIiIqNG6BXZFt8Cu2Je1H1+fWoFzBalih0TNhAUNIiIiIgJgbxwe5s3CRrP4+9//Xu3xtGnTMHnyZKSmpqJ9+/YoLS3Ftm3bMGPGDHTs2BEAMHXqVDz//PNITk5GbGwsfv/9d1y6dAmvvvoq9Ho9IiIiMG7cOCxbtgwPPPAAZDIZfvzxRwQEBOCxxx4DAISGhuL06dPYsGEDCxtERERE5BZ6BHVHj6Du+C1zL5afXoVUFjjcFgsaROLhyhNERORszBYrMg1VS1GxsCGK0tJSAIBOpwMApKamwmKxID4+3r5PSEgI/Pz87IWN5ORkhIeHV3uBkJiYiPnz5yM9PR1t2rTB2bNnq50DABISErBo0aJaYzGZTDCZTPbHgiBArVbbv6bb43VyHEdcy0e3fOqASNzDfwdPFzsEIiKiJtMruCd6BffEsdzjWH9uA/Zm7YPVZhU7LHKADr7tcU/kCPRq1ZMFDSKRcOUJIiJyNpkFFbDYALVCCh+tXOxwGsxlCxtWqxWLFi1C27ZtER4eDgAwGAyQyWTQarXV9vXy8oLBYLDvc2NRo+r5queqPldtu3GfsrIyGI1GKBSKm+JZu3YtVq9ebX/cpk0bvPvuu/D3979lHpm3zbTlCA4OFjsEt8Fr6Vi8nkRE1BLE+3VEvF9HZJdmY0PqJvx44ScUm4rFDovqSSlVYkBoP4yIHI42XhFih0PU4nHlCSIicjZpuZWTBcJ91C59o7nLFjYWLFiA9PR0vPnmm2KHAgAYPXo0Ro4caX9c9UuRk5MDs9ksVlguJTOTZR5H4bV0LF5PclUymey2BXYioj8K0ARgYscJeCjuQWy/9Au+T92AC4UXxQ6LbiNQE4gRbe7G4NZ3QqfQiR0OEdWCK080v6pc3CmnP2oJOQLM0920hDydNceqwkYbf41DYhMrT5csbCxYsACHDh3CG2+8AV9fX/t2vV4Ps9mMkpKSarM2CgoK7C8A9Ho9UlJSqp2voKDA/lzV56ptN+6jVqtrnK0BAHK5HHJ5zVN3bDZbrbk416+1uG51nah+eC0di9eTiIhaIpVMiWERQzAsYgiO5RzHTxe3YU/mbygzl4kdGl0jFaToHJCIuyOGoltQV0gEidghEdEtuMvKE64qKChI7BCaXEvIEWCe7qYl5OlsOaYbzgEAusSE1LhKyeXsPHh4eNT7vM2dp0sVNmw2GxYuXIh9+/bh9ddfR0BAQLXnIyMjIZVKcezYMfTq1QsAkJGRgdzcXMTGxgIAYmNjsWbNGhQUFNj/6B89ehRqtRqhoaEAgJiYGBw+fLjauY8ePWo/BxERERFRSxLv3xHx/h0x1fIk9mbuw/b0X3E4+wjMNs5MFkO0PgoDwwagX2hf6JV6scMhojriyhPiEAQBQUFByMrKctub1lpCjgDzdDctIU9nzNFksSL1SiEAwFturHGVEpNFQFFRUZ3PWfn3w88hedZn5QmXKmwsWLAAO3fuxEsvvQS1Wm2/M0Gj0UChUECj0WDQoEFYsmQJdDodNBoNFi5ciNjYWHtRIiEhAaGhofjss8/w8MMPw2AwYMWKFRg6dKh9xsWQIUPwww8/YOnSpRg4cCCOHz+OPXv2YObMmWKlTkREREQkOqVUiX6hd6Bf6B0oqCjEzss78XP6LziTnyx2aG4vzCMUd4T0Rd+QJIR5hIodDhHVkzutPOGqbDabW+Z1o5aQI8A83U1LyNOZcrx4tRQWqw06pRS+WnktcdVvjaGqczR3ni5V2Pjxxx8BAK+//nq17VOnTsWAAQMAABMmTIAgCPjwww9hNpuRkJCAyZMn2/eVSCSYOXMm5s+fj1mzZkGpVKJ///4YN26cfZ+AgADMnDkTixcvxsaNG+Hr64unnnqKDbeIiIiIiK7xUnpiRORwjIgcjsySTPyWsQ8HrhzAyaunOZPDAQQIiPRqg26BXZEU0oeNwIlcFFeeICIiZ3I+x7H9NcTkUoWNVatW3XYfhUKByZMnVytm/JG/vz9efvnlW56nQ4cOeO+99+odIxERERFRSxOsDcbomFEYHTMKpaZSHM7+HQevHMTB7EPIK88XOzyX4SHXoXNAIroEdkaXgC7wVunFDomIGokrTxARkTM5X9U43E97mz2dn0sVNoiIiIiIyLlp5BokhfRGUkhv2Gw2nCtIxcErh3Ao+zBS8s/BaDWKHaLTkECCSH0kugZ2RrfALojxjoFUkIodFhE5EFeeICIiZ3LjjA1Xx8IGERERERE1CUEQEK2PQrQ+CuPa/glmqxmpBak4nXcGp/LO4HTeGeSW5YodZrPRK70Q6x2Ltt6xaOsTixh9DDRytdhhEVET4soTRETkLMpNFmQaygEAbfxY2CAiIiIiIqoTmUSGWO9YxHrH4t6oewAAV8uuXit0nEZqwXlcKLyIQmOhyJE2nlamQahHKGK9Y9DWpy3aesciSBsodlhERERE1EKdyy6BDYCvVg4vjVzscBqNhQ0iIiIiIhKNr9oXSSF9kBTSx77NUGHAhcKLSC+6hMvFGcgozsDl4gzklObACquI0VYngQQBGn+EeoQiRNcKIboQhHqEIFQXAm+Vt9jhERERERHZnc4sBgC0DdaJHIljsLBBRERERERORa/UQ++vR4J/p2rbTVYT8svzkV9uQF55PgwV+cgrz6/cVlG5raCiABWWChgtRhitRlhtdS+ECBAgk8igkMihkWuhV3pBr9TDW6WvjOkPXwdqAiCXuv7dbkRERETk/s5kVRU2PESOxDFY2CAiIiIiIpcgl8gRoAlAgCagzseYrWYYLSYYrRWVny1GWGwWyCVyyCVyKKSVn+XXPhMRERERuZsKsxWp1xqHxwVxxgYREREREZFTk0lkkElk0IBNuomIiIioZTqXXQKL1QZvrRz+Hgqxw3EIidgBEBERERERERERERFR0zidWQSgcraGIAgiR+MYLGwQEREREREREREREbmpqsbhcW7SXwNgYYOIiIiIiIiIiIiIyC1VmCw4f62/Rttg9+ivAbCwQURERERERERERETklk5cLoLZaoOfToEAN+mvAbCwQURERERERERERETklg5fLAAAdG7t5Tb9NQAWNoiIiIiIiIiIiIiI3I7VasOR9EIAQOdwL5GjcSwWNoiIiIiIiIiIiIiI3ExKdgmKy83QKqSIDXKf/hoACxtERERERERERERERG7n0IXKZag6hXlCKnGfZagAFjaIiIiIiIiIiIiIiNyKzWar1l/D3bCwQURERERERERERETkRlKyS5BdWAGFTIKOIZ5ih+NwLGwQEREREREREREREbmR7aevAgB6RuqhVkhFjsbxWNggIiIiIiIiIiIiInITJRVm7D+fDwDo39ZP5GiaBgsbRERERERERERERERuYs+5fJgsNoR6qxDprxE7nCbBwgYRERERERERERERkRuw2mz4+VQuAKB/nB8EQRA5oqYhEzsAIiIiIiIiIiIiIiJXZRWkMFtsN22/nJ0Hk0UAcHNxQSYVILFZHB7L3tR8ZBjKoVZI0SfK2+HndxYsbBARERERERERERERNZDZYsPGI5dv2u7h4YGioqIajxmeGAKFg9dTMlusWHsws/L88QHQKN13+J9LURERERERERERERERubhfk68ip8gIT7UMgzv4ix1Ok2Jhg4iIiIiIiIiIiIjIhV0tNmLNgcrZGvckBkEpl4ocUdNiYYOIiIiIiIiIiIiIyEVZrDb8Z3saSowWtPHTYEBbX7FDanIsbBARERERERERERERuSCbzYbVBzKQfKUEKrkETw2MgEzq/sP+7ts9hIiIiIiIiIiIiIhIJFabDTabDYIgNMn5bTYblu+9jC0ncgAAj/UJQ4Cnskm+l7NhYYOIiIiIiIiIiIiIqJ6Ky824lF+Gi3kV+D29EMXlZlSYrTBZrDCZrbDYKveTSgRIJYBMIoFGIYVGKQUECVp5KRDirUKQlwpSSf2KHzlFFVi6+xKOXioEADzaOxS9o30cnaLTYmGDiIiIiIiIiIiIiBrFKkhhrhrJr4PL2XmwQQIJLPZtFmvlDAeJIEAQ0GQzHeqrtMKMy4ZyXM6v+ijDZUM5CsvMdTreYrXBYgWMsKDUaAGKgYtXy+zPyyQCgvUqhHqrEOqjRoi3CqHeanhr5ZDccA1KKsw4n1OKvan52JuaD5PFBqlEwMS+YUiKcf++GjdiYYOIiIiIiIiIiIiokeo7sA8AMqkAic1y+x1dgNliw8Yjl2t8zmazodxsRWGZGcXlZpSZLDBZJZAKNpSUm1BusqLcZIHxD9dPEACVXAqtQmqf6aC59rVWKYNOde2z8vpnnUoGrVIGpaxufSZsNhvKTVYUlZtRUGaCodSE7EIjcooqcKWwAlkFFTCUmmo93k+nQLBejTKjGR4qGVRyCRQyCeRSAXovTxQVFV0rbNhgsthQarSgtMICb50SVwrKcDm/HBVmK9LzypCeVwacy7efWyIAOqUMEglgMttQYqz+uxIXrMNjfcIQrFfVKVd3wsIGERERERERERERUR2YLVYYzVaYrDaYLTaYLFaYLZWD1lZIsTM5GxIBkAhC5Yek8m782mYeDE8MgcLN+jxbrDYUlptRWGZCYZn52ofppqJFXdhsQJnRgjJj/Ys/cqkApUxybRmoGz4EAWarDcZrP8sKs7VOBSkfrRwh3iq00lfOqKj8WgWVXAqjVVJjUUcll8Ikl1bbVjWvovJnb4XVZsPVYiMu5ZXjUn4ZLuVVFjuyCsphsQGF5dVnhfho5YgP9UTvKB/EBmlvO6ulvgW3+v+UxMHCBhERERERERERkYuxClIYTVYUV5hx8fQl5BeWwmSxwWqzXWtYDCjlEmgUMqiv3eHurZVDCqvYoTsNm82GCrMVxeVmFJabUXTjR5kZRRVWFJaZUFReOcug6NrMgoaQCJWzM2SSyoF22bVB9rTcMqgVEihllR8qhRT+PqWoKCuBUiZAJZNCKb/23LWZACq51L6/pJ59GRzJarMhp8iIS3ll1/pMlONMZhFKKmovQuhUUngoZdAopNB7aNC1tSdOXjJcuzYCZFIJqjKy2WywAvYCksliQ8dQPYwmM0oqzCiusFT7XFJhQXGFGSXlZlhsgMlig8lS94KIUiaBp1oGT5UM/p5KBHgqEehR+bmVtwoahfT2J2kAiSDA30MJfw8lOrf2sm83W6z230egsk+Hj1YBdT3juNVMmpoMSwyp1/nFwsIGERERERERERGRE7PabMgtMuJiXhnSr5ZVfs4rw9ViY73OI5MK8NUq4KuTw1enRKCnEoFelZ8DPJV1XrrHWRnNVnsRorjCfO1rC4oqqgoTlQPiReWWyscV5novHXUj+8wMCSBAgEImQbnJAqsNsFpt1e58t9oAo9kGI6oPtOfW+DPMqnMMCqkA5bVCh0ImgUwqQH6tQFBZKBAgl0rshQO5tLKwIpcK9kKL/esbj5FUHmO1XV86qdRogaHUhNwiI66WGHG12AhTLddPIRPgqZLDSy2rLBao5fBQyao1yPbw8EDnCE9cMZTeOkn59S97RvvCar31z+zGgpXRbAUEAUazBdZry0FZrDbIpBIopBLIZZU/N51SBuUNMyuaY4kwiUSA0XqLf3OCBFq1DFr19U0yqQC4ydJljcXCBhERERERERERkZOoMFtx6VrhIj2vDBevVt4Nf6uZAkpZ5QCtVKhc8qhq7Nhsvb5UkslSuXTSlcLKvgFA8U3n8dbKK4sdNxQ8qooecmnzFj2sNhtKKiz22RPFFWZIMoy4dOWqvUhRZC9gVO5nNDdsNoVMKsBDJbvpQ6OUIy2nGIprsyOqPkslldf4j0sADUsMweYb7oy32Wyw2ip/DharDWaL9frXVhssFhvahXjBbLGgwmRFhdmCCrMNEpkS+YXFqDBbUG6yXnvOev2x2QrbtbF9o8UGo8WMogZf6caRSQWE6CsbXgfrNbicVwJPdWV/i6Zo/G222qpd47r448+lLppjibCG5OKOS5c1FAsbREREREREREREzcxms8FQarLPvrh4tfLzlcIK+6D1jWRSAaHeKoT5qBHuo0GQtwbH0/OhkEng5VnZoPhWrDYbescGILewAnklRuQWVSC7sALZheXILqxAqdGC/BIT8ktMOJ1ZveghAPDRKRDoqYS3Vg5PVeVd+B6qyrvcFdLKu95vHPi32XBtWazK2QtWG2CyWFFmrBycLzNZUGayoNxorb4E1A0Fi5quw+1IJQK0Sik8VHLolLJrjaSllTMGlBJ4qCq3eahk156X1joIX1vfhLoSBAFSATfMUrh5CaH+7QJumoEgVyhgMtY+G0ciEVButFQWQqqKHibLtaWXKgtZZmvV58ptVhtgMlsrn68qslx73nxtmaeq4ovphkKMRMC1Rt1SaBSVP3c/nQK+N3xU5dfY6+VMbjub4g9cpS+FO2Fh4zY2b96M9evXw2AwoHXr1pg0aRKio6PFDouIiIiIiIiIqBqOYTgni9WG/BITMgvKkWEoR0Z+OS4bKr+urSGyp1qGUG8NQn3UCPOp/Bzopaq2jI8NQEpWYZ3jkAgCvLUK7D2bAwCQCkCwlwLBXgrYbDYYLbbKfgXl1/sVSKUSZBeWo9xkxdViY72XvnIEjUJqn0Hhr9dBDjPUShkuXS29VkwRqs2oqK1R98guIbUuYWSyocaR6eYYrK7prn0PD49bFqqGJYbgp+OZ9fo+VbMWpAIglQLK28zAqWps3VLVdzZFc/WlqG/BBXDfogsLG7ewe/duLFmyBFOmTEFMTAw2bNiAt99+Gx9//DG8vLxufwIiIiIiIiIiombAMYzmV7VUUlVz6aqP/FILcosqkFtsRF6xEYZSI2prCSARgEAvFUJ9NCgpN8JLLYenWgbVDWv95xaVIbeo7KZjHTmQKggClDIBSpkCPtrr20d2CYXlWgPjqtkdhWVmFJabKptrl5tgNFsrPyyVn01mG8pNFggCKj8gXPtcOShb1efherNoAR1C9fbZFdeXgpJD94eeDFUzGWwANtVzZkBDlzBqqTiA7pz4e3wdCxu38P333+POO+/EwIEDAQBTpkzBoUOH8PPPP+O+++4TNzgiIiIiIiIiomtcfQzDarve1Pf6R+VsB0uNz93wUdPztspjrVYbtBfKkF9QCIvVCqu1anmkyvPbrh1rtdW83Wi5ob+ByYpysxXGG/oe1HUgVxAArUIKD7UMnjcM3muVlQP3DekB0BzMVhs2/55x03adQgKdonK2xx81JJdhia2w+chllBtNyL3FJJSqmQzuOlDrTDiATs6OhY1amM1mpKamVvvjL5FIEB8fj+TkZPECIyIiIiIiIiK6gTONYZRWmPHxltRbFCFQY2GiIb0UnEVVwaKqWKFTyZFTWA6NQgqNUgq1QgpVEzVSJiJqqVjYqEVhYSGsViv0en217Xq9HhkZN1eqTSYTTCaT/bEgCFCr1ZDJbnOJg/wdEa57kMsbdbivf4yDAnF98kZeSwCI9mnlgEjcgyOu51t7TjsgEvfwau+4Rp8jc6MDAnETwcNrf+62f4OIiIiIyC3UdwwDaMQ4xm0oIYFNkEIiBSRSoDHvpgQBkAoCJBIBEkGA5FoT5qrHlb0UKntHSCSCfV+p5No2QYBUIkAmlQA2GyQSQCqpXFpHcu044dp5BaFy6R3JtWWTpNf6NMilApRyKWSCALlMgEIqrfwsk0AhlUCtkFZbKgmoXI5n15nseuWqkMvg56lu0DGCIECjUUIlscB2mwpRfb9PY+Jy9DE35ulMcTn6e9Tl5+kqudxKVZ7OFldDj6lp/9v9LF0pl1sRBAFymRQSify2/wfdTn3+Bgm2xn43N5WXl4ennnoKs2fPRmxsrH370qVLcfLkSfzzn/+stv+qVauwevVq++OkpCTMmDGj2eIlIiIiIiIiopapvmMYAMcxiIjItdWvA0wL4unpCYlEAoPBUG27wWC46Q4IABg9ejQWLVpk/5gyZUq1Ox+cVVlZGf72t7+hrOzmJlRUf7yejsXr6Vi8no7Da0lEREREzqS+YxiA645j1FdLeO3eEnIEmKe7aQl5toQcAfHyZGGjFjKZDJGRkTh+/Lh9m9VqxfHjx6vd/VBFLpdDo9FU+3DE8jVNzWaz4fz5842eJkSVeD0di9fTsXg9HYfXkoiIiIicSX3HMADXHceor5bw2r0l5AgwT3fTEvJsCTkC4uXJxbdvYeTIkfj3v/+NyMhIREdHY+PGjaioqMCAAQPEDo2IiIiIiIiIyI5jGERE1JKwsHELffr0QWFhIVatWgWDwYCIiAi88sortU7jJCIiIiIiIiISA8cwiIioJWFh4zaGDRuGYcOGiR1Gk5HL5bj//vvdcrqpGHg9HYvX07F4PR2H15KIiIiInJG7j2E0REt47d4ScgSYp7tpCXm2hBwB8fIUbO6+yBcREREREREREREREbkNNg8nIiIiIiIiIiIiIiKXwcIGERERERERERERERG5DBY2iIiIiIiIiIiIiIjIZbB5ODlEVauWy5cvw8/PDyqVSuSIiIiIiIiIiKgl2Lx5M9avXw+DwYDWrVtj0qRJiI6Ovu1xu3btwieffIJu3brhpZdeaoZIG64+OW7fvh1z586ttk0ul2PZsmXNEWqj1PdnWVJSguXLl2Pfvn0oLi6Gv78/JkyYgC5dujRj1PVXnzxff/11nDx58qbtnTt3xssvv9zUoTZYfX+WGzZswI8//ojc3Fx4enqiZ8+eGD9+PBQKRTNGXX/1ydNsNuO7777DL7/8gry8PLRq1QoPP/wwEhMTmzfoejp58iT+97//4fz588jPz8eLL76IHj163PKYEydOYMmSJUhPT4evry/Gjh2LAQMGODQuFjao0Ww2GwRBwPfff48NGzbghRdeQExMjH07VSoqKsKhQ4dw5swZeHh4oF+/fggJCeF1cjCr1QoAkEg4IY3EUVhYiKNHj8JoNCIhIQG+vr5ih0RERERE5LZ2796NJUuWYMqUKYiJicGGDRvw9ttv4+OPP4aXl1etx2VnZ+O///0v2rVr14zRNkxDclSr1fjkk0+aOdLGqW+eZrMZs2fPhqenJ1544QX4+PggNzcXGo1GhOjrrr55vvjiizCbzfbHRUVF+Otf/4revXs3Z9j1Ut8cd+7cia+//hpPP/00YmNjkZmZiblz50IQBEyYMEGEDOqmvnmuWLECO3bswJNPPomQkBD8/vvveP/99zF79my0adNGhAzqpqKiAhERERg0aBA++OCD2+6fnZ2Nd955B4MHD8azzz6L48eP44svvoBer3doEYcjf+QwnTp1gkQiwdWrVwGAg/XXlJeX47///S+ee+45rF+/HhaLBRaLBZcvXwbA6+RoEomERY06SktLw+7duwFcLwhRwxQUFODrr7/GU089haeeegpr167Fli1b8Pbbb+Po0aMArs9sIyIiIiIix/n+++9x5513YuDAgQgNDcWUKVOgUCjw888/13qM1WrFv/71LzzwwAMICAhoxmgbpiE5CoIAvV5f7cPZ1TfPbdu2obi4GH/9618RFxeHgIAAtG/fHhEREc0beD3VN0+dTlft53j06FEolUr06tWrmSOvu/rmeObMGbRt2xZ9+/ZFQEAAEhISkJSUhJSUlGaOvH7qm+eOHTswevRodOnSBYGBgRgyZAg6d+6M9evXN3Pk9dO5c2c8+OCDt52lUeXHH39EQEAAHnvsMYSGhmLYsGHo1asXNmzY4NC4OGOD6s1qtcJms0EikUAQBPvAfHh4OBQKBS5cuIBu3bpBJmt5v15VA5c3Fiv27duHffv22f/QWq1WGI1GLtdVR2VlZUhJSUFsbCyUSmWNMzJunPWSnJyMAwcOQKfToXv37ggODhYlbmdkNpur/bvcuXMnNm3ahD59+rDAVk/FxcXQ6XT2xwUFBdi6dSs6deqEp59+GgqFApcvX8Z7772Hn376CZ06deI1JiIiIiJyMLPZjNTUVNx33332bRKJBPHx8UhOTq71uNWrV8PT0xODBg3CqVOnmiHShmtojuXl5Zg6dSpsNhvatGmDhx56CGFhYc0QccM0JM+DBw8iJiYGCxYswIEDB+Dp6YmkpCTcd999TnvDY0N/njfatm0b+vTp47TjSg3JsW3bttixYwdSUlIQHR2NK1eu4PDhw7jjjjuaKer6a0ieJpPppqW1FAoFzpw505ShNruzZ88iPj6+2raEhAQsWrTIod+n5Y08U6Pd+MfBarVCIpHYP7dp0wZpaWkoKChw6+VX/rh8lNVqrVbkudG+ffvQrl07+/p6EonEaf/4OKNt27Zh8+bNmDJlin1W0B8JggCj0YglS5bgwIED9iLb+vXr8dxzz6FDhw4iRC6+oqIi7N27F7t370Z5eTnatWuHAQMG2F/MdunSBRs3bsTVq1fd+t+rI5SXl+PAgQP45ZdfkJ6ejuDgYMTHx2PUqFGQSqUIDw9HVFQUdDqd/f+BkJAQeHh4IDs7GwaDwSXukCIiIiIiciWFhYWwWq03vdbW6/XIyMio8ZjTp09j27ZteO+995ohwsZrSI6tWrXC008/jdatW6O0tBT/+9//MGvWLHz00UdO+96vIXleuXIFOTk56Nu3L15++WVkZWVh/vz5sFgs+NOf/tQMUddfQ/K8UUpKCtLT0/H00083UYSN15Ac+/bti8LCQrz66qsAAIvFgsGDB2PMmDFNHW6DNSTPhIQEfP/992jXrh0CAwNx/Phx7Nu3z+1W0TAYDDctxeXl5YWysjIYjUaH9U1hYYNqVFufAqvViuPHj+PXX3/FhQsX0KFDB/Tu3Rtt27YFULkc1bp165CbmwtfX1+36x9hNBphtVpvKkxUXafs7GxkZWUhNjbWvk/VLJaTJ0/Cx8cHly5dglqtRlhYGLy8vCCVSt3uOjlCVbEsOjoavr6+uHTpEjp16gSDwYDk5GR4enoiLi7Ovv+RI0dw7NgxvPHGGwgMDAQALFq0CMuXL8eLL77YIgaVq64ZAOTl5WHx4sXIy8tDx44dERoaijVr1uDEiRN44YUXEBAQgMDAQGi1Wvz+++8YNGgQfw//ICsrC1u2bMGjjz6KH3/8EYcPH0ZUVBTuv/9+nDlzBsuWLYNcLseQIUOgVCoRHByM7OxsXL16FSaTCT///DPOnj2LgQMHtojfPyIiIiIiZ1dWVoZ//etfePLJJ+Hp6Sl2OE0mNjYWsbGx1R4///zz2LJlCx588EERI3Msm80GT09PPPnkk5BIJIiMjEReXh7+97//OW1ho7G2bduG8PDwWzbhdkUnTpzA2rVrMXnyZMTExCArKwtfffUVVq9ejfvvv1/s8Bxm4sSJ+OKLL/Dcc89BEAQEBgZiwIABt1xWjmrHwgYBuHnGQW1T9nbu3In169cjMjISd955J44ePYpPPvkEL7/8MsLCwtCxY0esWLECGRkZaNu2rVsMkv7+++/Yu3cvzp07B4VCAV9fX0REROCuu+6yL0Vz/PhxfPXVV8jOzoZer0dAQADuvvtudOvWDffeey82bdqEOXPmQKVSISwsDKWlpcjJyUG/fv3w5z//2S2uU2PVVkwLCQmBTqdDWloatm7diq+//hpqtRoWiwVDhgzB8OHDoVQqsWXLFtx9991QKpXYvHkzjh07hqNHj8LHxwd5eXluO7Bc9fuZnp6OkJAQDBo0CLGxsSguLoa3tzfuvfdeREVFAai8a2fu3Lk4fPgwhg4dCp1Oh9jYWBw4cICFjRpcunQJ33//PYYNGwZBEDB48GD07NkTUqkUbdu2RW5uLg4dOoT+/ftDqVSiXbt22Lt3L/76179CrVZDrVbDx8cHnTp1AnDzTC8iIiIiImocT09PSCQSGAyGattrmzFddYf/u+++a99WtaT0gw8+iI8//hhBQUFNGXK91TfHmshkMrRp0wZZWVmOD9BBGpKnXq+HTCarNo4QEhICg8Fw01LMzqIxP8/y8nLs2rUL48aNa7oAHaAhOa5cuRL9+vXDnXfeCaByufvy8nL85z//wZgxY5xyabGG5Onp6YmXXnoJRqPRPm6zbNky+w267kKv16OgoKDatoKCAqjVaofN1gBY2GixbDabvU8GUH0w2Wg0YuvWrThw4ABat26N4cOHw8/PD2azGQEBAfjzn/9sv1N+8ODB+Mtf/oIdO3bggQcegJ+fH7y8vHDhwgWUl5e79JJLBw8exGeffQaLxYLu3btj6NCh0Gq1+O2337Bu3TokJydj4sSJ8PLywtq1axEeHo63334bGRkZ+N///oeFCxciKioKERERmDhxIh566CFUVFSgsLAQgiAgLS0NX375Jfr06YN27dqJna7DVf2O1bZE1x8LGTf+DhYUFNinrOl0OgQEBODo0aPIzMzESy+9hJiYGHz33XfYtGkTPDw8cNddd0GlUuGrr77CN998Az8/PyQkJGDEiBFo06YN1Gp1M2TcvP74+5mUlIRdu3bhX//6F5544gnEx8fj8ccfB3B9QF2pVEImk0EulwOonE0UHx+PVatWAai9oOnutm3bhiNHjuCxxx6Dn5+ffeZLSEgIwsPD8dtvv+Gee+6x72+xWCCVSqHT6VBSUmK/0ys2NhYeHh5ITEzE5MmTYbVakZqaik8++QRlZWX2F2hEREREROQYMpkMkZGROH78uL2pbdVKE8OGDbtp/1atWuGDDz6otm3FihUoLy/H448/Dj8/v2aJuz7qm2NNrFYrLl68iM6dOzdlqI3SkDzbtm2LXbt2VVu9IDMzE97e3k5Z1AAa9/P87bffYDabnbrvBNCwHCsqKm4aO3L2MYrG/CwVCgV8fHxgNpuxd+9e9O7duzlCbjYxMTE4fPhwtW1Hjx6tNpPMEZzzXzk1iRuLGTcONpeUlGD//v0oLi5Gv379kJaWhmPHjiEqKgqHDh3CmTNn8NZbb0EmkyE2NhZWqxXbtm3Dzz//jEuXLqGiogJpaWm4cuUKQkJCEBMTg4sXL8JgMCAoKMhl71L29fVFQEAA7rvvvmr/wfTs2RN79+7F3LlzsX37diQlJeHEiRP4v//7P6hUKkRGRmLq1KmYMmUKDh06hEGDBkGlUtmLPFVV2MjISHz77bc4f/482rVr57LX6Y+qXlDc+Dt2Yy+Wqu1//AN16tQprFmzBikpKQgMDMQdd9yBpKQk6PV6REZGYuvWrejXr5992bMxY8YgOzsbP//8M+666y5ERUXh5MmT+OCDD+Dt7W0/r9lsRk5ODvz9/ZvvIjSDqt/PUaNGoU+fPgCAqKgofPrpp9i9ezfi4+Pt17vqd8tgMCAnJweJiYkAKnuTxMbGoqSkBBcvXkR4eLiIGYknKCgIubm5uHLlSrU3Ml5eXoiIiMCBAwdwzz33wGw2QyKRQCqVory8HAcPHkTfvn3t+/v4+MDf3x9msxlGoxEajQZxcXF46KGH8O2338Jms+Guu+4SI0UiIiIiIrc1cuRI/Pvf/0ZkZCSio6OxceNGVFRUYMCAAQCAzz77DD4+Phg/fjwUCsVN73u0Wi0AOPX7ofrkCFQ2R4+JiUFQUBBKSkrwv//9Dzk5OU5/s1V98xwyZAh++OEHLFq0CMOGDUNWVhbWrl2Lu+++W8Qsbq++eVbZtm0bunfvDg8PDxGirp/65ti1a1ds2LABbdq0sS9FtXLlSnTt2tWpCxz1zfPs2bPIy8tDREQE8vLy8M0338Bms2HUqFEiZnF75eXl1WZ8ZWdnIy0tDTqdDn5+fvj666+Rl5eHZ555BsD1f5tLly7FwIEDcfz4cezZswczZ850aFwsbLQgVQPKRqMRcrkc//3vf5GYmIj169cjLy8PRqMRu3fvBgA88cQTiIiIQGJiIt5//30cPnzY/p/Jxo0bsXPnTnTv3h3PPPMMjh07hnXr1iErKwshISFISEjAsWPHkJOT43RTOOsjODgYHh4eSE5ORu/evavdAdCjRw/88ssv2L17N1q3bg21Wm1/MWQ2m6FQKNCmTRucO3cOSUlJNc5c2bZtG8xms30g1R2KGsD1inrVEkkZGRlo3bo1Bg4ciIiICACV1+jUqVPYsGED7rnnHsTGxmL16tXQarV49dVXcejQIWzcuBHp6el46qmn0Lp1awQGBtqnCFf9LHr06IEdO3bAaDSiS5cuWL58OQ4ePIhevXpBp9OhtLQU27dvh9lsxpAhQ1x6BtEfVf1+pqam2gsbEokEV69etU/r++Mf/2XLlqFv377w8fGxb6vqtXHw4EH7C3mbzQaDwYDS0lKEhIRU+913RxEREbBYLEhPT0eHDh3s/xbVajViYmJw8OBBWK1WyGQy+0yjvXv3ory83F7YqLpGEREROHnyJLKyshAZGQmr1Yp+/fohLy8PK1euRGFhIcaMGeM2hUwiIiIiIrH16dMHhYWFWLVqFQwGAyIiIvDKK6/Yl4LJzc11+dfe9c2xuLgY8+bNg8FggFarRWRkJGbPno3Q0FCRMqib+ubp5+eHv//971i8eDH++te/wsfHB3fffTfuu+8+cRKoo4b8zmZkZOD06dOYNWuWCBHXX31zHDt2LARBwIoVK5CXlwdPT0907doVDz30kEgZ1E198zSZTFixYgWys7OhUqnQuXNnPPPMM/YxRWd17tw5vPHGG/bHS5YsAQD0798f06ZNQ35+PnJzc+3PBwQEYObMmVi8eDE2btwIX19fPPXUU/YbbR1FsFWNFJLLq61HAVC5jqTNZsOSJUtw8OBBLF++HBMnToTNZsMDDzyAkSNH4uzZs5g7dy5CQ0MxY8YMyGQyVFRU4P3334dOp8Nzzz2H9PR0fPrpp+jcubO92rhv3z58+umnGDduHO655x6UlJTgiSeewJ/+9Cen/2NyO/PmzUN+fj5eeOEF+2Bx1YDk2rVr8dNPP2HQoEE4fPgwhg8fjj59+sBkMkEul2P+/Pm4fPky/vGPfyAjIwM//vgjIiIiUFhYiBMnTiArKwv9+/fHmDFjRM7SsW5cIqlHjx5o1aoVtm/fDrlcjjvvvBMGgwHl5eUoLCyEXC63N2JesGABPvroI/j6+gKonGL5ySef4JNPPoG3tzf+/e9/o6KiAi+99JL9j8K5c+fw2muv4cMPP0RQUBBWrVqFrVu3IjIyEhKJBKmpqdBqtbj//vvRvXt3SKVSMS+Nw82bNw/Z2dno2rUrDh8+jLNnz6KsrAyvv/66fXmzqt/XH3/8ERs2bMDf//53BAQEVJtF8+WXX9qLSHv27MGxY8dw5swZhIeH4/333xc5y+Yxe/ZsBAcHY8KECZDJZPbrdvr0abz33nt44YUX0LFjRwBAYWEhXnvtNQwePBgjRoyo9n/v0aNHsXz5cgwbNgz9+/e3L1tVVWTz8fFBr169xEyViIiIiIiIiMjlccaGG6ntjupdu3Zh6dKlCA0NRdu2bXHfffdBIpGgX79++PXXX+2DdTExMejWrRsOHz5sH6irWoN/w4YNAAAPDw/7jA8AyMvLw7Zt26BQKHDmzBkMGjQIWq0WDz/8MOLj45sh66bVsWNHbNq0CZcuXUJkZGS1vhFVSxvJ5XIEBATg119/RZ8+fSCXy1FYWIjz588jODgYAOyV2l9++QVWqxVt27bF+PHj0bp1a7FSazI1LZEUGxuLZcuWYc+ePdBoNEhOTsbjjz+O/v37A6j8HfX19bUXNQCgV69e+Pzzz3Hy5EkMGDAAYWFh2LhxI1JSUhATE2M/LjQ01P67/6c//Qm9evXCvn37UFpaimHDhrnF72FtOnXqhC+//BJXr17FHXfcgZCQEFy9ehWZmZmIiYmBTCazL0H1ww8/YNCgQQgICABw/f8LQRAQFxeHbdu24cUXX0SrVq3QpUsXPPbYY4iOjhYzvWbVpUsX/P7778jNza22hJ63tzdatWqF48eP2/+vXLduHZRKJUaMGAGg8lqaTCZIJBK0adMGpaWlyMjIAAB7MU2j0WD48OHiJEdERERERERE5GZY2HAxtc3KMJvNOHToEH799VcYjUb069cPCQkJ8PDwgJ+fH3x8fJCbm4tp06bZG93Gx8dj+/bt1c6VmJiI77//Hvn5+QgMDIQgCGjXrh1WrFiBrKwsBAUFoVu3bvjll1+wb98+5OXlYfTo0ejVqxf8/PygUqlgs9ncZgAvJiYGmzZtQkpKir2wUXW9tFotDAYD2rdvj8jISMyZMwcfffQR+vTpg8OHD8NoNOL+++8HUDmoOW7cOKhUKpefAns7VUsknT171l7YiI6OhkQigVarhaenJ2Qymb2oAVQ2XNJqtfbfsaq73AMCAnDp0iUAQJs2bSCTyfDZZ59h0KBBKCsrw2+//Ybhw4dXm4EQHh7u1GujOlJUVBSCg4MxYMAADB48GACQnJyMBQsWIDU1FZMnTwYA7NixA3q9HkOGDMGxY8dw8OBBHDp0CO+99x5UKhUSEhIwe/ZsREVFufWSU7fSsWNH7NixA+np6fbCBgB4enrCx8cH2dnZAIDz58/j96T0JjgAAB3dSURBVN9/xyOPPIKTJ09i3759OHz4MLp3745x48bBw8MDL730Elq1aiVmOkREREREREREbo2FDRdw4/r2Nw463rhG+7Zt2/Ddd9+hW7duEAQBS5cuxb59+/DCCy8gJCQE3t7eMJvN0Ov19uJIp06dYDQakZWVZR8IjoyMhEKhsDdwBirXRVMqldizZw9Gjx6Nhx9+GB06dEBWVhbat29v75vgjnx8fKDVapGWllZt+9WrV7Fhwwa0atUK4eHhUCgU+Otf/4rt27dj2bJlCAsLw4QJE6r1GFGr1c0cvTiUSiX8/f1x5coV+7bi4mJkZGRg/PjxKCkpQWpqKlJTUxEZGQkACA0Nxa5du3Dy5EkEBQVBKpXiypUrsFgs9r4YQUFB8Pb2hoeHByoqKpCcnIwxY8bYexy0xAF5Hx8f6HQ6nD9/3r4tJiYGTzzxBP7xj38gMjISnTp1wooVK2A2m/HEE09AEAS0b98ed999N2Syyj8Ber3ePquopQoODoZCocCJEyfQvXt3++9TeXk5Tp06ZV/Xc/PmzUhPT8c777wDhUKBdu3aYeTIkejbty/kcjlsNhtCQkLETIWIiIiIiIiIyO2xsOECqgbYSktLceTIEaxduxYqlQq9e/fG8OHDkZubi2+++QbDhw/H6NGjYbPZ0KdPH7z22ms4cuQIEhMTERUVhUuXLqGkpARardY+YBwcHIxTp06hS5cukMlkUKvViIqKwv79+5GUlAQA0Ol0GDx4sH3gUyKRoEuXLmJdjmYlk8kQFhaG9PR0e4EpLS0N27dvR0VFBaZMmQKFQgGz2YzExES0b9/e3oujJYuPj8f69euxcuVKZGZmYt++fYiOjkbfvn1x7tw57N+/H2lpafbCRmxsLNq2bYv//ve/UCqVaN++PbZu3QqZTIYBAwYAAFq1aoUHH3wQYWFh1Zasasmqfj8vXLiA4uJi6HQ6WK1WREVF4b777sN///tfex8IvV6PxMREziSohVwuR5cuXbB+/XpERESgc+fOKC0txU8//YTQ0FB7z5LIyEhERkYiISGhWuGyirvPyCIiIiIiIiIicgYsbLiAiooKfPDBB/D19YXNZkP//v1RXl6OxYsXQ6fTISwsDMXFxfalaGw2G9q2bYuIiAgcOnQIiYmJCAsLgyAISE5ORufOne1L/XTp0gWnTp1CSUkJvLy8AFQuyXL48GGYzWbIZDLIZDI8/PDDYl4CUcXHx2Pfvn144403kJeXh4KCArRv3x7jxo1DbGwsANjvfGdRo1J0dDTKysrw008/YcCAAZg1axbat28PAAgMDIRWq602y0Cn0+Gxxx6DyWTCmjVr8MUXX8DPzw8PPPAA/Pz87PslJiY2dypOLz4+Hr///jtSUlKqXZ8RI0agb9++NQ6+U81GjRqF7OxsbNmyBevWrYPBYEB4eDjGjRtn75czdOhQkaMkIiIiIiIiIiIWNlyAUqmE2WzG7t278dRTT9n7Fly+fBkHDhyAIAgICgpCamoqOnXqBLPZDIVCgZiYGFy8eBFA5WCyt7c3Tp06hc6dO9tngXTu3BkbNmyAwWCwFzZGjRqFMWPGiJOsE2rdujVatWoFnU6H4cOHo0uXLvbm6VQzHx8fBAYGwtfXt1pRzGazwd/fHwEBAcjIyEBpaSk0Gg1sNhtkMhmefPJJXL58GV5eXtDpdCJm4Dpat26N0NBQe3Gtqlm1Wq1uMcufOdKUKVOQlZWF/Px8ewN2IiIiIiIiIiJyLhyxcRG9e/dGbm4u2rRpY9/WoUMH7NmzB/n5+QgODsahQ4fQqVMn+8CmSqVCWVkZAMDb2xu+vr44fPgwxo8fbx+si4+Px/vvv1+t2XLV8VRJr9dj5syZYofhUmpaIgm43hcmICAAly9fRl5eHjQaTbXle9ifoH70ej1mzJghdhhuJSgoiDNdiIiIiIiIiIicWMvrtuui4uLioNVqcfnyZfu26OhomM1mlJeXo1OnTvj5559x9OhRSKVSXLhw4aY+GfHx8bjjjjtgNpvt57DZbNWKGkSOEh8fD4PBgJSUFACA1Wq1FzCGDBmCf/zjHwgNDRUzRCIiIiIiIiIiInJBnLHhIqrWd7906RK6desGAAgNDYWHhwdyc3MxZswYHD9+HF9++SU0Gg2ysrIQHx+Pu+66y36Ofv363XReNrqlpvLHJZKqlj8DKmcTERERERERERE1RGZmJhYsWICzZ8+irKwML774IkpLSzF37lz8f3v3HlR1nf9x/AkekusREYRFUbyAconkYogWmKhJq666eSvXrW0vlk5tamum622V0TLLWs1prcZuipqhqSnqCnERUhBFt0Sz0hAEAwSBI+Lh98cO59eJi1pa4b4eM85wPp/3+Xw+3+OM45wXn8/nn//8Jx07dmzx/VOnTiUwMJCpU6f+RCsWkZtNwUYrYWdnh6enJ0VFRZhMJuzt7TEYDHTo0IFjx45RXFzMzJkzyc3N5dtvvyUgIABvb++fe9nyP0xHJImIiIiIiIjcvoqKiti2bRtHjx6lrKwMg8FAly5diIqKYvDgwdxxxx23bO5Vq1ZRXFzMxIkTcXR0pEePHuTl5d2y+X6p6urqSEpKIjk5mfPnz2NjY4Obmxu9evVi+PDhOu5bbmsKNlqRvn37smvXLs6dO0f37t0tbd26dcNoNALQp0+fn3GFIiIiIiIiIiJyu8vJyWHFihXY2dkRHR2Nj48PdXV1fP7557zzzjucPXuWv/zlL7dk7traWvLz8xkzZgzDhg2ztEdHR9O/f3/s7Oxuyby/RMuXLyc3N5cBAwYQGxvL1atXKSgoICcnh169einYkNuago1WxN/fn8zMTKu24ODgn2k1IiIiIiIiIiLyv6a4uJiXX34ZDw8P5s2bR/v27S19w4YNo6ioiJycnFs2f0VFBQCOjo5W7ba2trd0l8gvzalTp8jJyWHChAmMGTPGqs9sNlNVVfWTraW2thaDwWB1DLnIraZgoxXp2LEjM2fO/LmXISIiIiIiIiIi/6O2bt2KyWRiypQpVqFGAy8vLx544AHL66tXr/Lhhx+SkpLCt99+S/v27RkwYABjx4612l0xdepUfHx8GDVqFOvWrePMmTO0b9+esWPHEhMTA8DGjRvZvHkzAO+++y7vvvsuHh4erFq1iuTk5EZ3bNTX17Nlyxb27NnDpUuX8PPz4w9/+EOTz1VVVcWmTZvIysri4sWLdOjQgdjYWEaOHGn5wr64uJhp06YxadIkHB0d2bp1K99++y1du3blscceo2fPnlZjFhQUkJCQwPHjxzGZTLi7u9OvXz8mTpxoqSktLWXDhg0cPnyYqqoqvLy8GD58OIMGDWrx7+H8+fMA9O7du1Gfra0tLi4uVm2lpaUkJCSQm5tLZWUl7du3p0+fPjz66KOW+1HPnz/Pe++9R15eHleuXKFr16789re/JSwszDLO8ePHWbhwIU899RRnz55l//79lJeX8+abb+Lk5MTJkyfZuHEj+fn5XL16lR49ejBx4sQm1ynyYyjYEBERERERERERkeuSnZ2Np6cnvXr1uq76NWvWkJKSQr9+/Rg+fDgnT54kMTGRgoICnnnmGavaoqIiXnzxRQYNGkRMTAz79+9n9erVdO/eHR8fHyIjI3FycmLdunUMGDCA0NBQ7O3tm507ISGBLVu2EBoaSmhoKF9++SWLFy+mrq7Oqu7y5cssWLCA0tJSBg8ejLu7OydOnGD9+vWUl5fzyCOPWNWnp6dTU1PD4MGDsbGxYevWrbz44ou8+uqrlpDg66+/Zt68eRgMBmJjY+nYsSNFRUVkZ2dbgo3y8nLmzJkDwP3334/RaCQ3N5c1a9ZQU1PDr3/962afzcPDA4DU1FR69epFmzZtmq0tLS1l9uzZVFdXExsbS6dOnSgtLSUzM5PLly9jMBgoLy9n7ty51NbWEhcXh7OzMykpKSxbtowZM2Zw9913W435wQcfYDAYGDFiBHV1dRgMBo4dO0Z8fDzdu3dn7Nix2NjYkJyczKJFi1i0aFGj4Efkx1CwISIiIiIiIiIiItdUXV1NaWkpERER11X/1VdfkZKSwqBBg5gyZQrw3y/w27Vrx0cffcSxY8esjlk/d+4cCxcuJCAgAID+/fvz+OOPs3//fiZPnkzXrl1xcHBg3bp1dOvWjejo6GbnrqioYNu2bYSFhTFr1ixsbGwAWL9+PR9++KFV7fbt2ykqKuL555/nV7/6FQBDhgzBzc2Nbdu2MXz4cNzd3S31Fy5cYOXKlTg7OwPg7e3N888/z5EjRwgPDwfgzTffBGDZsmVW73344YctP2/YsAGz2czy5cstOyyGDh3Kyy+/zKZNmxgyZEizx2v5+fkRGBjIvn37OHToEMHBwfTu3Zvw8HCr+QDef/99ysvLiY+Pp0ePHpb28ePHU19fD0BiYiIXL15k0aJFlt0VgwcPZubMmaxbt46IiAiro6auXLnC0qVLLeurr6/nX//6F0FBQTz33HOWz3vIkCFMnz6dDRs2MHfu3Ob+ukRumA4+ExERERERERERkWuqqakBwMHB4brqDx8+DMDw4cOt2keMGAHQ6C6Ozp07W0INAKPRiLe3N8XFxTe81qNHj1JXV8ewYcMsX7IDTe6CyMzMJCAgACcnJyoqKix/7rzzTsxmM5999plVfVRUlCXUgP8/DqrheKiKigo+++wz7rvvvkYhQ8Na6uvrycrKIjw8nPr6eqt5+/TpQ3V1NadPn272+WxsbJgzZw4TJkzA2dmZ9PR03njjDZ544gleeuklyx0bZrOZgwcPEh4ebhVqfH89hw8fpmfPnlZHRtnb2zN48GBKSkr45ptvrN4XExNjFbp89dVXFBYWcs8991BZWWl5FpPJRHBwMJ999hlms7nZ5xG5UdqxISIiIiIiIiIiItfUEGg0BBzXUlJSgo2NDV5eXlbtrq6uODk5ceHCBav274cAAE5OTj/oIuyGsRt2YDQwGo04OTlZtRUWFvL111/zxz/+scmxLl682OI6G0KOhnU2BBw+Pj7Nrq+iooKqqir27t3L3r17m61piZ2dHWPGjGHMmDGUlZXxn//8h507d3LgwAHatGnDk08+SUVFBTU1NXTp0qXFsS5cuICfn1+j9k6dOln6vztGwz0mDQoLCwFYtWpVs3NUV1dbBUIiP4aCDREREREREREREbkmR0dH2rdvz9mzZ2/ofd/dMdGS7x519F0NxyXdKvX19YSEhDBy5Mgm+729va1e34x1NtTee++9lsvRv69r167XPV7DpeyRkZHMmDGDAwcOMHXq1Ot+/436/hFZDc8zadIkfH19m3xPS/ehiNwoBRsiIiIiIiIiIiJyXcLDw9m7dy/5+fn4+/u3WOvh4UF9fT2FhYV07tzZ0l5eXk5VVVWTOzRuloaxCwsL8fT0tLQ37JT4Lk9PT0wmEyEhITdl7ob5WgqAjEYjDg4OmM3mmzYvgMFgoEuXLhQWFlJZWWmZ58yZMy2+z93dnXPnzjVqLygosPS3pOGZHR0db+rziDRHd2yIiIiIiIiIiIjIdRk5ciRt27ZlzZo1lJeXN+ovKipi586dAISGhgJYXjfYvn07AGFhYbdsnSEhIbRp04Zdu3ZZ7aTYsWNHo9qoqCjy8/PJzc1t1FdVVcXVq1dvaG6j0UhAQAD79+9vdNxWw1psbW2JjIwkKyurydDhWsdQFRYWNhq7Yb35+fk4OTlhNBqxtbWlb9++ZGdn88UXXzSqb1hPaGgop06dIj8/39JnMpnYt28fHh4eVsFUU7p3746npycfffQRJpPphp9H5EZpx4aI/OyKi4uZNm0akyZNanbb582yceNGNm/ezMaNG2/pPCIiIiIiIiK3Iy8vL5566ileeuklnn76aWJiYvDx8aGuro4TJ06QmZnJwIEDAfD19SUmJoa9e/dSVVVFYGAgp06dIiUlhb59+xIcHHzL1mk0GhkxYgSJiYksXbqU0NBQvvrqKw4fPoyLi4tV7ciRIzl06BDLli0jJiaG7t27c/nyZc6cOUNmZiarVq3CaDTe0PyPPvoo8+bNY9asWcTGxtKxY0dKSkrIycnhhRdeAOChhx7i+PHjzJkzh9jYWDp37sylS5c4ffo0eXl5vPXWW82O//XXX7Ny5UpCQ0Pp3bs3zs7OlJaWkpKSQllZGY888ojlyKyHHnqIo0ePsmDBAss8ZWVlZGZmsmjRIpycnBg1ahTp6enEx8cTFxeHs7MzKSkpFBcXM2PGjGaP32pga2vLlClTiI+PZ/r06QwcOBA3NzdKS0s5fvw4Dg4OPPvsszf0GYq0RMGGyP+A3bt388Ybb9CzZ0/i4+Mb9X/zzTdkZGQwcODARpc/7d69m7Zt21r+U/JLVVtbS1JSEhkZGRQUFFBXV4e7uzshISHExcU1Og9TRERERERERH6YiIgIli9fzrZt2zh48CBJSUnY2dnRpUsXJk+eTGxsrKV2ypQpeHp6kpyczKeffoqrqyujRo1i7Nixt3ydEyZM4I477mDPnj0cP34cPz8/5s6dy9KlS63q2rZty8KFC9myZQuZmZl88sknODg44O3tzbhx43B0dLzhuX19fVmyZAkJCQns2bOH2tpaPDw8iIqKstS4uroSHx/P5s2bycrKYvfu3bi4uODj48PDDz/c4vgBAQGMHz+e3NxcduzYQUVFBfb29nTr1o2HH36Yfv36WWrd3NyIj49nw4YNpKWlUVNTg5ubG3369KFt27aWtSxevJj33nuPXbt2UVtbS9euXZk1a9Z176wJCgpiyZIlbN68md27d2MymXB1daVnz54MGTLkhj9DkZbY1N/q23dE5Gf397//ndLSUkpKSnjllVfw8vKy6s/MzGTFihXMnz+foKAgq74ZM2bg4uLCggULbtn6fuyOjYqKCuLj4zl9+jRhYWGEhIRgb2/PuXPnSE9Pp7y8nPXr1wPasSEiIiIiIiIiItLaaceGyG2uuLiYEydOMHPmTF5//XVSU1N/kt+K+CmtXr2aL7/8kunTp1v9RgLA+PHjLaGGiIiIiIiIiIiItH4KNkRuc6mpqTg5OREWFka/fv1IS0uzCjaSk5NZvXo1AAsXLrS0z58/n9WrV1NSUgLAuHHjAAgMDGTBggVcunSJLVu2cOTIEYqLi7G1taVXr1489NBD+Pr6Wq2htraWxMRE0tPTuXDhAk5OTvj7+zNp0qRGu0ca1NfX8/rrr5OcnMxf//pXIiMjm6w7efIkOTk5xMbGNgo1AOzs7Jg8eXKLn9H+/fv55JNPOHv2LNXV1Xh6ehIXF8fQoUOt6r744gs2bNjA6dOnLdspg4KCeOKJJyw16enpbNu2jcLCQmxsbHB3dyc2NpYHHnigxTWIiIiIiIiIiIjI9VGwIXKbS0tLIzIyEoPBwIABA0hKSuLUqVP07NkT+O+ZjHFxcXz88ceMHj2aTp06AdCpUyd+//vf89Zbb2Fvb8/o0aOB/565CHD+/HkOHjxIVFQUHTt2pLy8nL1797JgwQJWrFiBm5sbAGazmWXLlpGXl0f//v2Ji4vDZDJx9OhRzp4922SwYTabWb16NQcOHOCZZ55p8SzHQ4cOARAdHf2DP6OkpCR8fHyIiIigTZs2ZGdns3btWsxmM8OGDQPg4sWLLF68GKPRyG9+8xucnJwoKSkhKyvLMs7Ro0dZuXIld955p+UszIKCAj7//HMFGyIiIiIiIiIiIjeJgg2R29jp06cpKCjg0UcfBaB379506NCBtLQ0S7Dh6elJQEAAH3/8MSEhIVZ3bNx9990kJCTg4uLSKDjo0qULK1euxNbW1tIWHR3N008/zb///W8efPBBAFJSUsjLy2Py5MkMHz7cUjtq1CiauuLn6tWrvPrqqxw6dIi//e1v3HXXXS0+Y0FBgWU9P9TChQu54447LK+HDRvGkiVL2LFjhyXYOHHiBFVVVcydO5cePXpYaidMmGD5OScnBwcHB+bMmWP1uYiIiIiIiIiIiMjNo2/eRG5jqamptGvXjuDgYABsbGyIiooiPT0ds9n8o8a2s7OzfHlvNpuprKzE3t4eb29vvvzyS0tdVlYWLi4uxMXFNRrDxsbG6nVdXR0rVqwgOzub2bNnXzPUAKipqQHAwcHhBz/Ld0ON6upqKioqCAwM5Pz581RXVwPg5OQEQHZ2NnV1dU2O4+joyOXLlzl69OgPXouIiIiIiIiIiIi0TDs2RG5TZrOZjIwMgoKCKC4utrT7+fmxfft28vLyris4aGn8nTt3kpSURHFxsVVQ4uzsbPn5/PnzeHt706ZNm2uOmZiYiMlk4rnnnrPaOdKShkCjpqbGEj7cqM8//5xNmzaRn5/P5cuXrfqqq6txdHQkMDCQyMhINm/ezI4dOwgKCqJv377cc8892NnZAXD//fdz4MAB4uPjcXNzIyQkhP79+9OnT58ftC4RERERERERERFpTMGGyG3q2LFjlJWVkZGRQUZGRqP+1NTUHxVsfPjhhyQkJHDfffcxfvx4nJ2dsbGxYd26dU0eMXU97rrrLnJzc9m6dSuBgYFWOyma4+3tDcCZM2cICAi44TmLior4xz/+gbe3N5MnT6ZDhw4YDAYOHz7Mjh07LIGNjY0NM2bMID8/n+zsbI4cOcJrr73G9u3bWbJkCfb29rRr144XXniB3NxccnNzOXz4MMnJyURHRzNt2rQbXpuIiIiIiIiIiIg0pmBD5DbVcAzVY4891qgvKyuLgwcPUltbe13hQVMyMzMJCgri8ccft2qvqqrCxcXF8trT05OTJ09SV1eHwdDyPzl+fn4MGTKEZcuWsWLFCp555plr7vSIiIggMTGR1NTUHxRsZGdnc+XKFWbNmoW7u7ul/fjx403W+/v74+/vz8SJE0lLS+OVV14hPT2d2NhYAAwGAxEREURERGA2m1m7di179+7lwQcfbPKidBEREREREREREbkxumND5DZUW1vLp59+SlhYGP369Wv0Z9iwYdTU1HDo0CEA7O3tgf+GEt9nb2/fZHtTl2MfOHCA0tJSq7bIyEgqKyvZtWtXo/qmdnaEhITw1FNPceTIEV599dVr3gXi7+9Pnz592LdvH59++mmj/rq6Ot5+++1m39/wHN9dS3V1NcnJyVZ1ly5darReX19fAK5cuQJAZWVlo7G7du1qVSMiIiIiIiIiIiI/jnZsiNyGDh06RE1NDREREU32+/n5YTQaSU1NpX///vj6+mJra8vWrVuprq7Gzs6O4OBg2rVrR7du3dizZw8ffPABXl5elsvIw8PD2bx5M6tXr8bf358zZ86QlpaGp6en1VwxMTF88sknvP3225w6dYqAgAAuX75MXl4eQ4cOpW/fvo3Wd/fdd/P444+zatUqHB0d+fOf/9zi806bNo3Fixfz4osvEh4eTnBwMPb29hQWFpKRkUFZWRmTJ09u8r133XUXBoOBZcuWMXjwYEwmE/v27cNoNFJWVmapS0lJISkpib59++Ll5UVNTQ379u3DwcGBsLAwANasWcOlS5cIDg6mQ4cOlJSUsGvXLnx9fenUqVOLzyAiIiIiIiIiIiLXR8GGyG0oNTUVOzs7QkJCmuy3tbUlLCyM1NRUKisrcXV15U9/+hOJiYmsWbMGs9nM/PnzadeuHQ8++CAXLlxg27Zt1NTUEBgYSHBwMKNHj8ZkMpGenk5GRgbdunXj2Wef5f3332801+zZs9myZQtpaWlkZWXh4uJC79696dKlS7PPEB0djclkYu3atTg4OPC73/2u2Vqj0cjixYvZvXs3GRkZbNiwgbq6Ojw8PAgPD+eBBx5o9r3e3t5Mnz6dhIQE3nnnHVxdXRk6dChGo5HXXnvNUhcYGMipU6fIyMjg4sWLODo60qNHD5588kk6duwIwL333su+fftISkqiqqoKV1dXoqKiGDduXJM7XEREREREREREROTG2dT/0Ft+RUREREREREREREREfmL6FWIREREREREREREREWk1FGyIiIiIiIiIiIiIiEiroWBDRERERERERERERERaDQUbIiIiIiIiIiIiIiLSaijYEBERERERERERERGRVkPBhoiIiIiIiIiIiIiItBoKNkREREREREREREREpNVQsCEiIiIiIiIiIiIiIq2Ggg0REREREREREREREWk1FGyIiIiIiIiIiIiIiEiroWBDRERERERERERERERaDQUbIiIiIiIiIiIiIiLSaijYEBERERERERERERGRVuP/AGGi3jYArg9hAAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# ── Alert visualizations ──────────────────────────────────────────────────────\n",
        "fig, axes = plt.subplots(1, 3, figsize=(16, 5))\n",
        "\n",
        "# Predicted class bar chart\n",
        "class_counts = alerts_df['predicted_class'].value_counts()\n",
        "sns.barplot(x=class_counts.index, y=class_counts.values, palette='husl', ax=axes[0])\n",
        "axes[0].set_title('Predicted Attack Distribution')\n",
        "axes[0].set_xlabel('Attack Class')\n",
        "axes[0].set_ylabel('Count')\n",
        "axes[0].tick_params(axis='x', rotation=15)\n",
        "\n",
        "# Severity pie chart\n",
        "sev_counts  = alerts_df['severity'].value_counts()\n",
        "colors_sev  = [SEVERITY_COLOR.get(s, '#999') for s in sev_counts.index]\n",
        "axes[1].pie(sev_counts.values, labels=sev_counts.index,\n",
        "            colors=colors_sev, autopct='%1.1f%%', startangle=90)\n",
        "axes[1].set_title('Severity Breakdown')\n",
        "\n",
        "# Confidence distribution\n",
        "sns.histplot(alerts_df['confidence'], bins=30, kde=True, color='steelblue', ax=axes[2])\n",
        "axes[2].set_title('Prediction Confidence Distribution')\n",
        "axes[2].set_xlabel('Confidence Score')\n",
        "\n",
        "plt.suptitle('Week 7 — SentinelNet Alert Analysis', fontsize=13)\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ERmAHpedi8Oo",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "3aa97418-71c3-466e-ced0-d15d3d121691"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saved full alert log → alerts/alerts.csv\n",
            "Saved intrusions log → alerts/intrusions_only.csv\n",
            "Saved text alert log → alerts/alert_log.txt\n",
            "Saved dashboard JSON → alerts/dashboard_data.json\n",
            "\n",
            "Files in alerts/:\n",
            "  alert_log.txt                       (5,340 bytes)\n",
            "  dashboard_data.json                 (49,933 bytes)\n",
            "  intrusions_only.csv                 (474,629 bytes)\n",
            "  alerts.csv                          (1,319,938 bytes)\n"
          ]
        }
      ],
      "source": [
        "# ── Save alert logs ───────────────────────────────────────────────────────────\n",
        "# Full CSV\n",
        "csv_path = os.path.join(ALERTS_DIR, 'alerts.csv')\n",
        "alerts_df.to_csv(csv_path, index=False)\n",
        "print(f'Saved full alert log → {csv_path}')\n",
        "\n",
        "# Intrusions-only CSV\n",
        "intru_path = os.path.join(ALERTS_DIR, 'intrusions_only.csv')\n",
        "alerts_df[alerts_df['is_intrusion']].to_csv(intru_path, index=False)\n",
        "print(f'Saved intrusions log → {intru_path}')\n",
        "\n",
        "# Human-readable text log\n",
        "log_path = os.path.join(ALERTS_DIR, 'alert_log.txt')\n",
        "with open(log_path, 'w') as f:\n",
        "    f.write('=' * 60 + '\\n')\n",
        "    f.write('       SENTINELNET — INTRUSION ALERT LOG\\n')\n",
        "    f.write(f'       Generated: {datetime.now().strftime(\"%Y-%m-%d %H:%M:%S\")}\\n')\n",
        "    f.write('=' * 60 + '\\n\\n')\n",
        "    f.write('SUMMARY\\n')\n",
        "    f.write(f'  Total connections  : {total}\\n')\n",
        "    f.write(f'  Intrusions detected: {intrusions} ({intrusions/total*100:.1f}%)\\n')\n",
        "    f.write(f'  Normal traffic     : {normal_count} ({normal_count/total*100:.1f}%)\\n')\n",
        "    f.write(f'  Real-time Accuracy : {accuracy_rt:.4f}\\n\\n')\n",
        "    f.write('SEVERITY BREAKDOWN\\n')\n",
        "    for sev, cnt in alerts_df['severity'].value_counts().items():\n",
        "        f.write(f'  {sev:<12}: {cnt}\\n')\n",
        "    f.write('\\nATTACK CLASS BREAKDOWN\\n')\n",
        "    for cls, cnt in alerts_df['predicted_class'].value_counts().items():\n",
        "        f.write(f'  {cls:<12}: {cnt}\\n')\n",
        "    f.write('\\n' + '=' * 60 + '\\n')\n",
        "    f.write('CRITICAL & HIGH SEVERITY ALERTS (first 50)\\n')\n",
        "    f.write('=' * 60 + '\\n\\n')\n",
        "    critical = alerts_df[alerts_df['severity'].isin(['Critical', 'High'])]\n",
        "    for _, row in critical.head(50).iterrows():\n",
        "        f.write(\n",
        "            f'[{row[\"timestamp\"]}] '\n",
        "            f'ID:{row[\"connection_id\"]:>6} | '\n",
        "            f'SEVERITY: {row[\"severity\"]:<10} | '\n",
        "            f'CLASS: {row[\"predicted_class\"]:<8} | '\n",
        "            f'CONFIDENCE: {row[\"confidence\"]:.2f}\\n'\n",
        "        )\n",
        "print(f'Saved text alert log → {log_path}')\n",
        "\n",
        "# JSON dashboard data\n",
        "dashboard = {\n",
        "    'summary'    : {\n",
        "        'total'       : int(total),\n",
        "        'intrusions'  : int(intrusions),\n",
        "        'normal'      : int(normal_count),\n",
        "        'accuracy'    : round(float(accuracy_rt), 4),\n",
        "        'generated_at': datetime.now().strftime('%Y-%m-%d %H:%M:%S')\n",
        "    },\n",
        "    'by_class'   : alerts_df['predicted_class'].value_counts().to_dict(),\n",
        "    'by_severity': alerts_df['severity'].value_counts().to_dict(),\n",
        "    'alerts'     : alerts_df[alerts_df['is_intrusion']].head(200).to_dict(orient='records')\n",
        "}\n",
        "json_path = os.path.join(ALERTS_DIR, 'dashboard_data.json')\n",
        "with open(json_path, 'w') as f:\n",
        "    json.dump(dashboard, f, indent=2)\n",
        "print(f'Saved dashboard JSON → {json_path}')\n",
        "\n",
        "print('\\nFiles in alerts/:')\n",
        "for fname in os.listdir(ALERTS_DIR):\n",
        "    size = os.path.getsize(os.path.join(ALERTS_DIR, fname))\n",
        "    print(f'  {fname:<35} ({size:,} bytes)')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tTS7eCFHi8Oo"
      },
      "source": [
        "---\n",
        "# 📅 Week 8 — Documentation & Project Summary"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "LHzrhLy_i8Oo",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "4f97c747-ffd9-47d4-9afd-c6d4e4912767"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "============================================================\n",
            "       SENTINELNET — PROJECT SUMMARY\n",
            "============================================================\n",
            "\n",
            "Dataset       : NSL-KDD\n",
            "Train samples : 336,715 (after SMOTE balancing)\n",
            "Test  samples : 22,544\n",
            "Features used : 37\n",
            "\n",
            "Attack classes: ['DoS', 'Probe', 'R2L', 'U2R', 'normal', 'other']\n",
            "\n",
            "--- Best Model: Random Forest ---\n",
            "  Best Hyperparameters  : {'max_depth': 20, 'min_samples_leaf': 1, 'n_estimators': 100}\n",
            "  Validation F1 (macro) : 0.9997\n",
            "  Validation Accuracy   : 0.9997\n",
            "  5-Fold CV F1 Mean     : 0.9997 ± 0.0000\n",
            "\n",
            "--- Alert Generation ---\n",
            "  Connections processed : 22,500\n",
            "  Intrusions detected   : 8,254 (36.7%)\n",
            "  Real-time Accuracy    : 0.7583\n",
            "\n",
            "--- Anomaly Detection ---\n",
            "  Isolation Forest anomalies : 10,092\n",
            "  LOF anomalies (5k sample)  : 250\n",
            "  OC-SVM anomalies (5k)      : 439\n",
            "============================================================\n"
          ]
        }
      ],
      "source": [
        "# ── Final performance dashboard ───────────────────────────────────────────────\n",
        "print('=' * 60)\n",
        "print('       SENTINELNET — PROJECT SUMMARY')\n",
        "print('=' * 60)\n",
        "print(f\"\\nDataset       : NSL-KDD\")\n",
        "print(f\"Train samples : {len(X_signal):,} (after SMOTE balancing)\")\n",
        "print(f\"Test  samples : {len(X_test_alert):,}\")\n",
        "print(f\"Features used : {X_signal.shape[1]}\")\n",
        "print(f\"\\nAttack classes: {list(le_w4.classes_)}\")\n",
        "print(f\"\\n--- Best Model: Random Forest ---\")\n",
        "print(f\"  Best Hyperparameters  : {grid.best_params_}\")\n",
        "print(f\"  Validation F1 (macro) : {f1_score(y_val, y_pred_best, average='macro'):.4f}\")\n",
        "print(f\"  Validation Accuracy   : {accuracy_score(y_val, y_pred_best):.4f}\")\n",
        "print(f\"  5-Fold CV F1 Mean     : {cv_scores.mean():.4f} ± {cv_scores.std():.4f}\")\n",
        "print(f\"\\n--- Alert Generation ---\")\n",
        "print(f\"  Connections processed : {total:,}\")\n",
        "print(f\"  Intrusions detected   : {intrusions:,} ({intrusions/total*100:.1f}%)\")\n",
        "print(f\"  Real-time Accuracy    : {accuracy_rt:.4f}\")\n",
        "print(f\"\\n--- Anomaly Detection ---\")\n",
        "print(f\"  Isolation Forest anomalies : {iso_anomaly_count:,}\")\n",
        "print(f\"  LOF anomalies (5k sample)  : {lof_count}\")\n",
        "print(f\"  OC-SVM anomalies (5k)      : {ocsvm_count}\")\n",
        "print('=' * 60)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import joblib, os\n",
        "from google.colab import files\n",
        "\n",
        "# Save everything needed for inference\n",
        "joblib.dump(sentinel_brain,  'models/sentinel_brain.joblib')   # already done\n",
        "joblib.dump(le_w4,           'models/label_encoder.joblib')    # already done\n",
        "joblib.dump(ohe,             'models/ohe_encoder.joblib')      # NEW — needed for preprocessing\n",
        "joblib.dump(freq_map,        'models/freq_map.joblib')         # NEW — needed for preprocessing\n",
        "joblib.dump(scaler,          'models/scaler.joblib')           # NEW — needed for preprocessing\n",
        "joblib.dump(selected_features, 'models/selected_features.joblib')  # NEW — feature list\n",
        "\n",
        "# Download all of them\n",
        "for f in ['sentinel_brain.joblib','label_encoder.joblib',\n",
        "          'ohe_encoder.joblib','freq_map.joblib',\n",
        "          'scaler.joblib','selected_features.joblib']:\n",
        "    files.download(f'models/{f}')\n",
        "    print(f'⬇ Downloading {f}...')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 121
        },
        "id": "aUrMwG4F1MWr",
        "outputId": "082b3db7-ee09-4816-d3ff-833b8e642a01"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "download(\"download_5cd6dcb3-6a0e-4421-a7b9-52bc7ef334b6\", \"sentinel_brain.joblib\", 13691057)"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "⬇ Downloading sentinel_brain.joblib...\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "download(\"download_4c6cc33e-c77a-40d6-8c22-801e0058a933\", \"label_encoder.joblib\", 516)"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "⬇ Downloading label_encoder.joblib...\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "download(\"download_4f90b2b1-0f18-4515-a4d0-7575278b7fcf\", \"ohe_encoder.joblib\", 1262)"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "⬇ Downloading ohe_encoder.joblib...\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "download(\"download_b19c06cb-a5cb-428f-8ee5-f1cc7f1e7ba5\", \"freq_map.joblib\", 1256)"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "⬇ Downloading freq_map.joblib...\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "download(\"download_5fa8a406-d1ee-42e3-a87c-cc9022935b07\", \"scaler.joblib\", 2639)"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "⬇ Downloading scaler.joblib...\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "download(\"download_f86f7d46-1ed4-46a4-bf8c-a7082e00e19b\", \"selected_features.joblib\", 640)"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "⬇ Downloading selected_features.joblib...\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os, time\n",
        "\n",
        "os.system(\"pkill -f ngrok 2>/dev/null\")\n",
        "os.system(\"pkill -f cloudflared 2>/dev/null\")\n",
        "os.system(\"pkill -f flask 2>/dev/null\")\n",
        "os.system(\"fuser -k 5001/tcp 2>/dev/null\")\n",
        "time.sleep(2)\n",
        "print(\"✅ Cleaned up\")"
      ],
      "metadata": {
        "id": "gECQhMhllimH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import threading, time, subprocess, re, os, requests\n",
        "from flask import Flask, request, jsonify\n",
        "from flask_cors import CORS\n",
        "import pandas as pd, numpy as np\n",
        "\n",
        "flask_app = Flask(__name__)\n",
        "\n",
        "# ← This is the key fix: explicit CORS for all origins + all headers\n",
        "CORS(flask_app, origins=\"*\",\n",
        "     allow_headers=[\"Content-Type\", \"cf-access-client-id\", \"ngrok-skip-browser-warning\"],\n",
        "     methods=[\"GET\", \"POST\", \"OPTIONS\"])\n",
        "\n",
        "@flask_app.after_request\n",
        "def after_request(response):\n",
        "    response.headers.add('Access-Control-Allow-Origin', '*')\n",
        "    response.headers.add('Access-Control-Allow-Headers', 'Content-Type,cf-access-client-id')\n",
        "    response.headers.add('Access-Control-Allow-Methods', 'GET,POST,OPTIONS')\n",
        "    return response\n",
        "\n",
        "@flask_app.route('/health')\n",
        "def health():\n",
        "    return jsonify({'status': 'online', 'model': 'sentinel_brain'})\n",
        "\n",
        "@flask_app.route('/predict', methods=['POST', 'OPTIONS'])\n",
        "def predict():\n",
        "    if request.method == 'OPTIONS':\n",
        "        return jsonify({}), 200\n",
        "    try:\n",
        "        data = request.get_json(force=True)\n",
        "        rows = data.get('rows', [])\n",
        "        df = pd.DataFrame(rows)\n",
        "        for col in COLUMNS:\n",
        "            if col not in df.columns:\n",
        "                df[col] = 0\n",
        "        if 'label' not in df.columns:\n",
        "            df['label'] = 'normal'\n",
        "        df_proc, _, _, _ = preprocess(df, is_train=False,\n",
        "                                       ohe=ohe, freq_map=freq_map, scaler=scaler)\n",
        "        model_feats = (list(sentinel_brain.feature_names_in_)\n",
        "                       if hasattr(sentinel_brain, 'feature_names_in_')\n",
        "                       else selected_features)\n",
        "        for f in model_feats:\n",
        "            if f not in df_proc.columns:\n",
        "                df_proc[f] = 0\n",
        "        X = df_proc[model_feats].values\n",
        "        preds = sentinel_brain.predict(X)\n",
        "        proba = sentinel_brain.predict_proba(X)\n",
        "        classes = le_w4.inverse_transform(preds)\n",
        "        out = [{'predicted_class': cls, 'severity': SEVERITY_MAP.get(cls,'Unknown'),\n",
        "                'confidence': round(float(conf), 4), 'is_intrusion': cls != 'normal'}\n",
        "               for cls, conf in zip(classes, proba.max(axis=1))]\n",
        "        return jsonify({'status': 'ok', 'results': out})\n",
        "    except Exception as e:\n",
        "        import traceback\n",
        "        return jsonify({'status': 'error', 'message': str(e),\n",
        "                        'trace': traceback.format_exc()}), 500\n",
        "\n",
        "def run_flask():\n",
        "    import logging\n",
        "    logging.getLogger('werkzeug').setLevel(logging.ERROR)\n",
        "    flask_app.run(host='0.0.0.0', port=5001, debug=False, use_reloader=False)\n",
        "\n",
        "os.system(\"fuser -k 5001/tcp 2>/dev/null\")\n",
        "time.sleep(1)\n",
        "threading.Thread(target=run_flask, daemon=True).start()\n",
        "time.sleep(2)\n",
        "print(\"✅ Flask running — CORS fixed\")"
      ],
      "metadata": {
        "id": "qkIZqRQ-ln-I"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import threading, time, subprocess, re, os, requests\n",
        "from flask import Flask, request, jsonify\n",
        "from flask_cors import CORS\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "\n",
        "# ── Flask app ────────────────────────────────────────────────────────────────\n",
        "flask_app = Flask(__name__)\n",
        "CORS(flask_app, origins=\"*\")\n",
        "\n",
        "@flask_app.route('/health')\n",
        "def health():\n",
        "    return jsonify({'status': 'online', 'model': 'sentinel_brain'})\n",
        "\n",
        "@flask_app.route('/predict', methods=['POST'])\n",
        "def predict():\n",
        "    try:\n",
        "        data = request.get_json(force=True)\n",
        "        rows = data.get('rows', [])\n",
        "        df = pd.DataFrame(rows)\n",
        "        for col in COLUMNS:\n",
        "            if col not in df.columns:\n",
        "                df[col] = 0\n",
        "        if 'label' not in df.columns:\n",
        "            df['label'] = 'normal'\n",
        "        df_proc, _, _, _ = preprocess(df, is_train=False,\n",
        "                                       ohe=ohe, freq_map=freq_map, scaler=scaler)\n",
        "        model_feats = (list(sentinel_brain.feature_names_in_)\n",
        "                       if hasattr(sentinel_brain, 'feature_names_in_')\n",
        "                       else selected_features)\n",
        "        for f in model_feats:\n",
        "            if f not in df_proc.columns:\n",
        "                df_proc[f] = 0\n",
        "        X = df_proc[model_feats].values\n",
        "        preds = sentinel_brain.predict(X)\n",
        "        proba = sentinel_brain.predict_proba(X)\n",
        "        classes = le_w4.inverse_transform(preds)\n",
        "        out = [\n",
        "            {\n",
        "                'predicted_class': cls,\n",
        "                'severity': SEVERITY_MAP.get(cls, 'Unknown'),\n",
        "                'confidence': round(float(conf), 4),\n",
        "                'is_intrusion': cls != 'normal'\n",
        "            }\n",
        "            for cls, conf in zip(classes, proba.max(axis=1))\n",
        "        ]\n",
        "        return jsonify({'status': 'ok', 'results': out})\n",
        "    except Exception as e:\n",
        "        import traceback\n",
        "        return jsonify({'status': 'error', 'message': str(e),\n",
        "                        'trace': traceback.format_exc()}), 500\n",
        "\n",
        "# ── Start Flask in background ────────────────────────────────────────────────\n",
        "def run_flask():\n",
        "    import logging\n",
        "    log = logging.getLogger('werkzeug')\n",
        "    log.setLevel(logging.ERROR)  # suppress request logs\n",
        "    flask_app.run(host='0.0.0.0', port=5001, debug=False, use_reloader=False)\n",
        "\n",
        "threading.Thread(target=run_flask, daemon=True).start()\n",
        "time.sleep(2)\n",
        "\n",
        "# Quick health check\n",
        "try:\n",
        "    r = requests.get(\"http://localhost:5001/health\", timeout=3)\n",
        "    print(\"✅ Flask is up:\", r.json())\n",
        "except Exception as e:\n",
        "    print(\"❌ Flask not responding:\", e)\n",
        "    raise\n",
        "\n",
        "# ── Install cloudflared ───────────────────────────────────────────────────────\n",
        "print(\"Installing cloudflared...\")\n",
        "os.system(\"wget -q https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64 -O /usr/local/bin/cloudflared\")\n",
        "os.system(\"chmod +x /usr/local/bin/cloudflared\")\n",
        "v = os.popen(\"cloudflared version\").read().strip()\n",
        "print(\"✅ cloudflared:\", v)\n",
        "\n",
        "# ── Start tunnel ─────────────────────────────────────────────────────────────\n",
        "lines = []\n",
        "\n",
        "def read_output(proc):\n",
        "    for line in proc.stdout:\n",
        "        decoded = line.decode(\"utf-8\", errors=\"ignore\").strip()\n",
        "        if decoded:\n",
        "            lines.append(decoded)\n",
        "\n",
        "cf_proc = subprocess.Popen(\n",
        "    [\"cloudflared\", \"tunnel\", \"--url\", \"http://localhost:5001\"],\n",
        "    stdout=subprocess.PIPE,\n",
        "    stderr=subprocess.STDOUT\n",
        ")\n",
        "threading.Thread(target=read_output, args=(cf_proc,), daemon=True).start()\n",
        "\n",
        "# Wait and scan for URL\n",
        "print(\"Waiting for tunnel URL\", end=\"\")\n",
        "public_url = None\n",
        "for _ in range(30):\n",
        "    time.sleep(1)\n",
        "    print(\".\", end=\"\", flush=True)\n",
        "    all_text = \"\\n\".join(lines)\n",
        "    match = re.search(r'https://[a-z0-9\\-]+\\.trycloudflare\\.com', all_text)\n",
        "    if match:\n",
        "        public_url = match.group(0)\n",
        "        break\n",
        "\n",
        "print()  # newline after dots\n",
        "\n",
        "if public_url:\n",
        "    print(\"=\" * 55)\n",
        "    print(f\"  ✅ PUBLIC URL : {public_url}\")\n",
        "    print(f\"  Health       : {public_url}/health\")\n",
        "    print(f\"  Predict      : {public_url}/predict\")\n",
        "    print(\"=\" * 55)\n",
        "    print(\"\\n👆 Copy the PUBLIC URL above → paste into SentinelNet frontend\")\n",
        "else:\n",
        "    print(\"❌ Could not find tunnel URL. Output so far:\")\n",
        "    print(\"\\n\".join(lines[-20:]))\n"
      ],
      "metadata": {
        "id": "ikEEmW21olCD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Download real NSL-KDD test set directly\n",
        "import requests as req\n",
        "\n",
        "url = \"https://raw.githubusercontent.com/defcom17/NSL_KDD/master/KDDTest+.txt\"\n",
        "r = req.get(url)\n",
        "with open(\"/content/KDDTest+.txt\", \"wb\") as f:\n",
        "    f.write(r.content)\n",
        "\n",
        "print(\"✅ Downloaded KDDTest+.txt\")\n",
        "print(\"Rows:\", len(r.text.strip().split('\\n')))\n",
        "print(\"\\nNow download this file from Colab:\")\n",
        "print(\"  Files panel (left sidebar) → right-click KDDTest+.txt → Download\")\n",
        "print(\"Then drag it into the SentinelNet upload zone\")"
      ],
      "metadata": {
        "id": "l-3PfW_2pGkR"
      },
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.10.0"
    },
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "accelerator": "GPU"
  },
  "nbformat": 4,
  "nbformat_minor": 0
}