{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.pipeline import Pipeline\n",
        "from sklearn.compose import ColumnTransformer\n",
        "from sklearn.feature_extraction.text import TfidfVectorizer\n",
        "from sklearn.preprocessing import OneHotEncoder, LabelEncoder\n",
        "from sklearn.metrics import (\n",
        "    classification_report,\n",
        "    accuracy_score,\n",
        "    top_k_accuracy_score,\n",
        ")\n",
        "from sklearn.svm import SVC\n",
        "from imblearn.over_sampling import SMOTE\n",
        "from imblearn.pipeline import Pipeline as ImbPipeline\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import numpy as np"
      ],
      "metadata": {
        "id": "sAo63gMUPpe8"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LumISNZEPWuU",
        "outputId": "842efcfa-0562-4a33-f139-9bc617801de3"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading from https://www.kaggle.com/api/v1/datasets/download/tobiasbueck/multilingual-customer-support-tickets?dataset_version_number=9...\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 7.05M/7.05M [00:00<00:00, 91.4MB/s]"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Extracting files...\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Path to dataset files: /root/.cache/kagglehub/datasets/tobiasbueck/multilingual-customer-support-tickets/versions/9\n"
          ]
        }
      ],
      "source": [
        "import kagglehub\n",
        "\n",
        "# Download latest version\n",
        "path = kagglehub.dataset_download(\"tobiasbueck/multilingual-customer-support-tickets\")\n",
        "\n",
        "print(\"Path to dataset files:\", path)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "\n",
        "# Download latest version\n",
        "dataset_dir = kagglehub.dataset_download(\"tobiasbueck/multilingual-customer-support-tickets\")\n",
        "\n",
        "# Find the CSV file within the downloaded directory\n",
        "for filename in os.listdir(dataset_dir):\n",
        "    if filename.endswith(\".csv\"):\n",
        "        csv_file_path = os.path.join(dataset_dir, filename)\n",
        "        break  # Stop searching after finding the first CSV file\n",
        "\n",
        "# Now read the CSV file using pandas\n",
        "df = pd.read_csv(csv_file_path)"
      ],
      "metadata": {
        "id": "Gsu-ZbVNPz52"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 536
        },
        "id": "kBYMAaqzP0K4",
        "outputId": "419eed37-da99-426c-8339-0ee691f395bc",
        "collapsed": true
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                             subject  \\\n",
              "0  Unvorhergesehener Absturz der Datenanalyse-Pla...   \n",
              "1                           Customer Support Inquiry   \n",
              "2                      Data Analytics for Investment   \n",
              "3                 Krankenhaus-Dienstleistung-Problem   \n",
              "4                                           Security   \n",
              "\n",
              "                                                body  \\\n",
              "0  Die Datenanalyse-Plattform brach unerwartet ab...   \n",
              "1  Seeking information on digital strategies that...   \n",
              "2  I am contacting you to request information on ...   \n",
              "3  Ein Medien-Daten-Sperrverhalten trat aufgrund ...   \n",
              "4  Dear Customer Support, I am reaching out to in...   \n",
              "\n",
              "                                              answer      type  \\\n",
              "0  Ich werde Ihnen bei der Lösung des Problems he...  Incident   \n",
              "1  We offer a variety of digital strategies and s...   Request   \n",
              "2  I am here to assist you with data analytics to...   Request   \n",
              "3  Zurück zur E-Mail-Beschwerde über den Sperrver...  Incident   \n",
              "4  Dear [name], we take the security of medical d...   Request   \n",
              "\n",
              "              queue priority language      tag_1      tag_2       tag_3  \\\n",
              "0   General Inquiry      low       de      Crash  Technical         Bug   \n",
              "1  Customer Service   medium       en   Feedback      Sales          IT   \n",
              "2  Customer Service   medium       en  Technical    Product    Guidance   \n",
              "3  Customer Service     high       de   Security     Breach       Login   \n",
              "4  Customer Service   medium       en   Security   Customer  Compliance   \n",
              "\n",
              "           tag_4          tag_5       tag_6          tag_7 tag_8  \n",
              "0       Hardware     Resolution      Outage  Documentation   NaN  \n",
              "1   Tech Support            NaN         NaN            NaN   NaN  \n",
              "2  Documentation    Performance     Feature            NaN   NaN  \n",
              "3    Maintenance       Incident  Resolution       Feedback   NaN  \n",
              "4         Breach  Documentation    Guidance            NaN   NaN  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-91746a89-872f-4f45-8564-33c67c853525\" 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>subject</th>\n",
              "      <th>body</th>\n",
              "      <th>answer</th>\n",
              "      <th>type</th>\n",
              "      <th>queue</th>\n",
              "      <th>priority</th>\n",
              "      <th>language</th>\n",
              "      <th>tag_1</th>\n",
              "      <th>tag_2</th>\n",
              "      <th>tag_3</th>\n",
              "      <th>tag_4</th>\n",
              "      <th>tag_5</th>\n",
              "      <th>tag_6</th>\n",
              "      <th>tag_7</th>\n",
              "      <th>tag_8</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Unvorhergesehener Absturz der Datenanalyse-Pla...</td>\n",
              "      <td>Die Datenanalyse-Plattform brach unerwartet ab...</td>\n",
              "      <td>Ich werde Ihnen bei der Lösung des Problems he...</td>\n",
              "      <td>Incident</td>\n",
              "      <td>General Inquiry</td>\n",
              "      <td>low</td>\n",
              "      <td>de</td>\n",
              "      <td>Crash</td>\n",
              "      <td>Technical</td>\n",
              "      <td>Bug</td>\n",
              "      <td>Hardware</td>\n",
              "      <td>Resolution</td>\n",
              "      <td>Outage</td>\n",
              "      <td>Documentation</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Customer Support Inquiry</td>\n",
              "      <td>Seeking information on digital strategies that...</td>\n",
              "      <td>We offer a variety of digital strategies and s...</td>\n",
              "      <td>Request</td>\n",
              "      <td>Customer Service</td>\n",
              "      <td>medium</td>\n",
              "      <td>en</td>\n",
              "      <td>Feedback</td>\n",
              "      <td>Sales</td>\n",
              "      <td>IT</td>\n",
              "      <td>Tech Support</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Data Analytics for Investment</td>\n",
              "      <td>I am contacting you to request information on ...</td>\n",
              "      <td>I am here to assist you with data analytics to...</td>\n",
              "      <td>Request</td>\n",
              "      <td>Customer Service</td>\n",
              "      <td>medium</td>\n",
              "      <td>en</td>\n",
              "      <td>Technical</td>\n",
              "      <td>Product</td>\n",
              "      <td>Guidance</td>\n",
              "      <td>Documentation</td>\n",
              "      <td>Performance</td>\n",
              "      <td>Feature</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Krankenhaus-Dienstleistung-Problem</td>\n",
              "      <td>Ein Medien-Daten-Sperrverhalten trat aufgrund ...</td>\n",
              "      <td>Zurück zur E-Mail-Beschwerde über den Sperrver...</td>\n",
              "      <td>Incident</td>\n",
              "      <td>Customer Service</td>\n",
              "      <td>high</td>\n",
              "      <td>de</td>\n",
              "      <td>Security</td>\n",
              "      <td>Breach</td>\n",
              "      <td>Login</td>\n",
              "      <td>Maintenance</td>\n",
              "      <td>Incident</td>\n",
              "      <td>Resolution</td>\n",
              "      <td>Feedback</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Security</td>\n",
              "      <td>Dear Customer Support, I am reaching out to in...</td>\n",
              "      <td>Dear [name], we take the security of medical d...</td>\n",
              "      <td>Request</td>\n",
              "      <td>Customer Service</td>\n",
              "      <td>medium</td>\n",
              "      <td>en</td>\n",
              "      <td>Security</td>\n",
              "      <td>Customer</td>\n",
              "      <td>Compliance</td>\n",
              "      <td>Breach</td>\n",
              "      <td>Documentation</td>\n",
              "      <td>Guidance</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-91746a89-872f-4f45-8564-33c67c853525')\"\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-91746a89-872f-4f45-8564-33c67c853525 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-91746a89-872f-4f45-8564-33c67c853525');\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 id=\"df-66344810-2bc6-4005-a31d-82ac374ad1f1\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-66344810-2bc6-4005-a31d-82ac374ad1f1')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-66344810-2bc6-4005-a31d-82ac374ad1f1 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 20000,\n  \"fields\": [\n    {\n      \"column\": \"subject\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 18539,\n        \"samples\": [\n          \"Software crashes during data visualization due to potential memory compatibility issues with NAS-System, even after restarts and updates.\",\n          \"Personalizing Billing Settings in Dynamics\",\n          \"Improving Brand Expansion Digital Tactics Online\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"body\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 19998,\n        \"samples\": [\n          \"What are the system requirements for using your project management SaaS in conjunction with QuickBooks Online integration?\",\n          \"I am writing to request enhanced user authentication security, specifically multi-factor authentication, to improve the safety of my account and help protect it from unauthorized access.\",\n          \"Sehr geehrte Kundenservice, ich w\\u00fcrde gerne mehr \\u00fcber die Dienstleistungen zur Sicherung medizinischer Daten in Krankenhaus-IT-Systemen erfahren. K\\u00f6nnten Sie bitte detaillierte Informationen \\u00fcber die Sicherheitsma\\u00dfnahmen geben, einschlie\\u00dflich Verschl\\u00fcsselung, Firewalls und Zugriffskontrolle? Bitte stellen Sie auch relevante Zertifizierungen und die Einhaltung der Branche-Standard bereit. Zudem w\\u00e4re ich dankbar f\\u00fcr Beispiele erfolgreicher Umsetzungen und Fallstudien. Ich suche einen zuverl\\u00e4ssigen und vertrauensw\\u00fcrdigen Partner, der die Vertraulichkeit, Integrit\\u00e4t und Verf\\u00fcgbarkeit sensibler medizinischer Informationen gew\\u00e4hrleistet. Danke.\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"answer\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 19996,\n        \"samples\": [\n          \"Please investigate the issue and contact +1-800-123-4567 for assistance with potential solutions.\",\n          \"Sehr geehrte [name], ich bedaure die Probleme mit Ihren mehreren Integrationsproblemen zu h\\u00f6ren. Ich m\\u00f6chte dies genauer untersuchen. K\\u00f6nnten Sie bitte Details \\u00fcber die Docker-Aktualisierungen, die Sie k\\u00fcrzlich vorgenommen haben, und die genauen Fehlernachrichten, die Sie sehen, bereitstellen? Ich k\\u00f6nnte m\\u00f6glicherweise einen Anruf mit Ihnen vereinbaren, um dies weiter zu bereden, w\\u00e4ren Sie am [tel_num] zu sprechen? Bitte geben Sie mir einen geeigneten Zeitpunkt f\\u00fcr einen Anruf, damit wir das Problem so schnell wie m\\u00f6glich f\\u00fcr Ihr [acc_num] l\\u00f6sen k\\u00f6nnen.\",\n          \"Hello [Name], we will provide you with resources and guidelines for using MATLAB in data analytics. You can access tutorials and documentation via email. If you need further assistance, please contact us at [Tel Num] to discuss the next steps.\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"type\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          \"Request\",\n          \"Change\",\n          \"Incident\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"queue\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 10,\n        \"samples\": [\n          \"Returns and Exchanges\",\n          \"Customer Service\",\n          \"Billing and Payments\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"priority\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"low\",\n          \"medium\",\n          \"high\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"language\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"en\",\n          \"de\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_1\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 148,\n        \"samples\": [\n          \"Technical,Customer,Integration,Documentation,Guidance\",\n          \"Privacy\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_2\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 204,\n        \"samples\": [\n          \"Compliance\",\n          \"Outage\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_3\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 344,\n        \"samples\": [\n          \"Digital Marketing\",\n          \"Social Media Marketing\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_4\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 481,\n        \"samples\": [\n          \"AccessControl\",\n          \"Data Analysis\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_5\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 578,\n        \"samples\": [\n          \"Datenauswertung\",\n          \"GCP\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_6\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 566,\n        \"samples\": [\n          \"Workload\",\n          \"Brand\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_7\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 492,\n        \"samples\": [\n          \"Git\",\n          \"Notification\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_8\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 386,\n        \"samples\": [\n          \"Code\",\n          \"Demo\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.info()\n",
        "df.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 626
        },
        "id": "8UQjZ3Sa4tWG",
        "outputId": "184b3c3b-91bc-440b-c387-7334c1c27eda"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 20000 entries, 0 to 19999\n",
            "Data columns (total 15 columns):\n",
            " #   Column    Non-Null Count  Dtype \n",
            "---  ------    --------------  ----- \n",
            " 0   subject   18539 non-null  object\n",
            " 1   body      19998 non-null  object\n",
            " 2   answer    19996 non-null  object\n",
            " 3   type      20000 non-null  object\n",
            " 4   queue     20000 non-null  object\n",
            " 5   priority  20000 non-null  object\n",
            " 6   language  20000 non-null  object\n",
            " 7   tag_1     20000 non-null  object\n",
            " 8   tag_2     19954 non-null  object\n",
            " 9   tag_3     19905 non-null  object\n",
            " 10  tag_4     18461 non-null  object\n",
            " 11  tag_5     13091 non-null  object\n",
            " 12  tag_6     7351 non-null   object\n",
            " 13  tag_7     3928 non-null   object\n",
            " 14  tag_8     1907 non-null   object\n",
            "dtypes: object(15)\n",
            "memory usage: 2.3+ MB\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                                  subject  \\\n",
              "count                                               18539   \n",
              "unique                                              18539   \n",
              "top     Optimierung Ihrer Datenanalyse-Plattform erlei...   \n",
              "freq                                                    1   \n",
              "\n",
              "                                                     body  \\\n",
              "count                                               19998   \n",
              "unique                                              19998   \n",
              "top     Sehr geehrte Customer Support-Team, ich schrei...   \n",
              "freq                                                    1   \n",
              "\n",
              "                                                   answer      type  \\\n",
              "count                                               19996     20000   \n",
              "unique                                              19996         4   \n",
              "top     Sehr geehrter <name>, wir antworten Ihnen auf ...  Incident   \n",
              "freq                                                    1      7978   \n",
              "\n",
              "                    queue priority language      tag_1        tag_2  tag_3  \\\n",
              "count               20000    20000    20000      20000        19954  19905   \n",
              "unique                 10        3        2        148          204    344   \n",
              "top     Technical Support   medium       en  Technical  Performance     IT   \n",
              "freq                 5824     8144    11923       5034         2795   3309   \n",
              "\n",
              "               tag_4         tag_5       tag_6       tag_7          tag_8  \n",
              "count          18461         13091        7351        3928           1907  \n",
              "unique           481           578         566         492            386  \n",
              "top     Tech Support  Tech Support  Resolution  Resolution  Documentation  \n",
              "freq            3436          2287         841         417            162  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-60aea361-b4c9-4b5c-85a5-c347e772163f\" 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>subject</th>\n",
              "      <th>body</th>\n",
              "      <th>answer</th>\n",
              "      <th>type</th>\n",
              "      <th>queue</th>\n",
              "      <th>priority</th>\n",
              "      <th>language</th>\n",
              "      <th>tag_1</th>\n",
              "      <th>tag_2</th>\n",
              "      <th>tag_3</th>\n",
              "      <th>tag_4</th>\n",
              "      <th>tag_5</th>\n",
              "      <th>tag_6</th>\n",
              "      <th>tag_7</th>\n",
              "      <th>tag_8</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>18539</td>\n",
              "      <td>19998</td>\n",
              "      <td>19996</td>\n",
              "      <td>20000</td>\n",
              "      <td>20000</td>\n",
              "      <td>20000</td>\n",
              "      <td>20000</td>\n",
              "      <td>20000</td>\n",
              "      <td>19954</td>\n",
              "      <td>19905</td>\n",
              "      <td>18461</td>\n",
              "      <td>13091</td>\n",
              "      <td>7351</td>\n",
              "      <td>3928</td>\n",
              "      <td>1907</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>unique</th>\n",
              "      <td>18539</td>\n",
              "      <td>19998</td>\n",
              "      <td>19996</td>\n",
              "      <td>4</td>\n",
              "      <td>10</td>\n",
              "      <td>3</td>\n",
              "      <td>2</td>\n",
              "      <td>148</td>\n",
              "      <td>204</td>\n",
              "      <td>344</td>\n",
              "      <td>481</td>\n",
              "      <td>578</td>\n",
              "      <td>566</td>\n",
              "      <td>492</td>\n",
              "      <td>386</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>top</th>\n",
              "      <td>Optimierung Ihrer Datenanalyse-Plattform erlei...</td>\n",
              "      <td>Sehr geehrte Customer Support-Team, ich schrei...</td>\n",
              "      <td>Sehr geehrter &lt;name&gt;, wir antworten Ihnen auf ...</td>\n",
              "      <td>Incident</td>\n",
              "      <td>Technical Support</td>\n",
              "      <td>medium</td>\n",
              "      <td>en</td>\n",
              "      <td>Technical</td>\n",
              "      <td>Performance</td>\n",
              "      <td>IT</td>\n",
              "      <td>Tech Support</td>\n",
              "      <td>Tech Support</td>\n",
              "      <td>Resolution</td>\n",
              "      <td>Resolution</td>\n",
              "      <td>Documentation</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>freq</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>7978</td>\n",
              "      <td>5824</td>\n",
              "      <td>8144</td>\n",
              "      <td>11923</td>\n",
              "      <td>5034</td>\n",
              "      <td>2795</td>\n",
              "      <td>3309</td>\n",
              "      <td>3436</td>\n",
              "      <td>2287</td>\n",
              "      <td>841</td>\n",
              "      <td>417</td>\n",
              "      <td>162</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-60aea361-b4c9-4b5c-85a5-c347e772163f')\"\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-60aea361-b4c9-4b5c-85a5-c347e772163f 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-60aea361-b4c9-4b5c-85a5-c347e772163f');\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 id=\"df-e2332d21-1936-435b-8e91-add907634e3a\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-e2332d21-1936-435b-8e91-add907634e3a')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-e2332d21-1936-435b-8e91-add907634e3a button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 4,\n  \"fields\": [\n    {\n      \"column\": \"subject\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"18539\",\n          \"Optimierung Ihrer Datenanalyse-Plattform erleichtern\",\n          \"1\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"body\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"19998\",\n          \"Sehr geehrte Customer Support-Team, ich schreibe Ihnen, um zu erkunden, wie wir unser Datenanalyse-System verbessern k\\u00f6nnen, um unsere Investitionsstrategien und Portfolioleistungen zu optimieren. Aktuell fehlen unseres Systems bestimmte Funktionen, die unerw\\u00fcnschte Barriere f\\u00fcr informierte Entscheidungen stellen. Wir planen, das System zu aktualisieren und zus\\u00e4tzliche Funktionen hinzuzuf\\u00fcgen, wie fortgeschrittene Datenvisualisierung, maschinelles Lernen und realzeite Datenverarbeitung. Durch diese Verbesserungen hoffen wir, signifikante Verbesserungen in unseren Investitionsleistungen und in der Gesamtportfolioleistung zu erzielen. Ich w\\u00fcrde es sehr sch\\u00e4tzen, wenn Sie mir Anhaltspunkte zu verf\\u00fcgbaren Optionen und deren Kosten geben k\\u00f6nnten. Dar\\u00fcber hinaus w\\u00e4re ich interessiert, zu erfahren, wie wir die Implementierungszeitr\\u00e4ume und die von Ihrem Team w\\u00e4hrend des \\u00dcbergangsprozesses bereitgestellten Unterst\\u00fctzung bewerten k\\u00f6nnen. Vielen Dank f\\u00fcr Ihre Zeit und Unterst\\u00fctzung bei diesem Thema. Ich freue mich auf Ihre Antwort im Laufe der n\\u00e4chsten Tage.\",\n          \"1\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"answer\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"19996\",\n          \"Sehr geehrter <name>, wir antworten Ihnen auf Ihren E-Mail-Aufruf zur Verbesserung Ihrer Datenanalyse-Plattform. Wir verstehen die Bedeutung Ihrer Anliegen und freuen uns, Ihnen dabei zu helfen, Ihr System zu verbessern. Um Ihre Anforderungen besser zu verstehen, m\\u00f6chten wir gerne eine Verabredung f\\u00fcr ein Telefonat einrichten, um spezifische Funktionen wie fortgeschrittene Datenvisualisierung, maschinelles Lernen und realzeit Datenverarbeitung zu besprechen. Dies wird uns erm\\u00f6glichen, Ihnen mehr Informationen zu verf\\u00fcgbaren Optionen und deren Kosten bereitzustellen. Wir k\\u00f6nnen auch \\u00fcber m\\u00f6gliche Implementierungszeitr\\u00e4ume und die von unserem Team w\\u00e4hrend des \\u00dcbergangsprozesses bereitgestellte Unterst\\u00fctzung diskutieren. Sind Sie verf\\u00fcgbar f\\u00fcr ein Telefonat in Ihrer Freizeit, am besten am <tel_num> auf einer Wochentags? Alternativ geben Sie uns bitte ein geeignetes Zeitfenster an, und wir werden die Verabredung f\\u00fcr Sie einrichten. Wir werden Ihnen auch vor dem Telefonat einige Informationen zur Plattform-Verbesserungs-Optionen und deren Kosten zusenden. Sie k\\u00f6nnen jederzeit mit uns in Kontakt treten, wenn Sie weitere Fragen haben. Wir freuen uns darauf, Sie bald zu erreichen und gemeinsam zu untersuchen, wie wir Ihnen mit einer verbesserten Datenanalyse-Plattform bei Ihren <acc_num>-Investment-Zielen helfen k\\u00f6nnen.\",\n          \"1\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"type\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          4,\n          \"7978\",\n          \"20000\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"queue\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          10,\n          \"5824\",\n          \"20000\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"priority\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          3,\n          \"8144\",\n          \"20000\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"language\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          2,\n          \"11923\",\n          \"20000\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_1\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          148,\n          \"5034\",\n          \"20000\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_2\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          204,\n          \"2795\",\n          \"19954\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_3\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          344,\n          \"3309\",\n          \"19905\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_4\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          481,\n          \"3436\",\n          \"18461\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_5\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          578,\n          \"2287\",\n          \"13091\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_6\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          566,\n          \"841\",\n          \"7351\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_7\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          492,\n          \"417\",\n          \"3928\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tag_8\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          386,\n          \"162\",\n          \"1907\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Fill and engineer text\n",
        "df[\"subject\"] = df[\"subject\"].fillna(\"\")\n",
        "df[\"body\"] = df[\"body\"].fillna(\"\")\n",
        "tag_cols = [col for col in df.columns if col.startswith(\"tag_\")]\n",
        "df[\"tags_combined\"] = df[tag_cols].fillna(\"\").agg(\" \".join, axis=1)\n",
        "df[\"text\"] = df[\"subject\"] + \" \" + df[\"body\"] + \" \" + df[\"tags_combined\"]\n",
        "df = df[df[\"queue\"].notna()]\n",
        "\n",
        "# Encode target\n",
        "le = LabelEncoder()\n",
        "df[\"queue_encoded\"] = le.fit_transform(df[\"queue\"])\n",
        "\n",
        "# Split by language\n",
        "df_en = df[df[\"language\"] == \"en\"]\n",
        "df_de = df[df[\"language\"] == \"de\"]\n",
        "\n",
        "# Training function with Top-2 scoring\n",
        "def train_branch(df_branch, lang_label, label_encoder):\n",
        "    print(f\"\\n=== Training SVC Model for {lang_label} ===\")\n",
        "    X = df_branch[[\"text\", \"priority\", \"type\"]]\n",
        "    y = df_branch[\"queue_encoded\"]\n",
        "\n",
        "    X_train, X_test, y_train, y_test = train_test_split(\n",
        "        X, y, stratify=y, test_size=0.2, random_state=42\n",
        "    )\n",
        "\n",
        "    text_transformer = Pipeline([\n",
        "        (\"tfidf\", TfidfVectorizer(stop_words=\"english\", max_features=5000))\n",
        "    ])\n",
        "    categorical_transformer = Pipeline([\n",
        "        (\"onehot\", OneHotEncoder(handle_unknown=\"ignore\"))\n",
        "    ])\n",
        "    preprocessor = ColumnTransformer([\n",
        "        (\"text\", text_transformer, \"text\"),\n",
        "        (\"cat\", categorical_transformer, [\"priority\", \"type\"])\n",
        "    ])\n",
        "\n",
        "    pipeline = ImbPipeline([\n",
        "        (\"preprocessor\", preprocessor),\n",
        "        (\"smote\", SMOTE(random_state=42)),\n",
        "        (\"clf\", SVC(C=10, kernel=\"rbf\", class_weight=None, probability=True))\n",
        "    ])\n",
        "\n",
        "    pipeline.fit(X_train, y_train)\n",
        "    y_pred = pipeline.predict(X_test)\n",
        "    y_probs = pipeline.predict_proba(X_test)\n",
        "\n",
        "    print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
        "    print(\"Top-2 Accuracy:\", top_k_accuracy_score(y_test, y_probs, k=2))\n",
        "    print(classification_report(y_test, y_pred, target_names=label_encoder.classes_))\n",
        "\n",
        "    return y_test, y_pred, y_probs, label_encoder.classes_\n",
        "\n",
        "# Run for both languages\n",
        "y_test_en, y_pred_en, y_prob_en, classes_en = train_branch(df_en, \"English\", le)\n",
        "y_test_de, y_pred_de, y_prob_de, classes_de = train_branch(df_de, \"German\", le)"
      ],
      "metadata": {
        "id": "VjJPDdJFRBt8",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ff07e411-1c9c-45a0-9ab7-d45558d61a77"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "=== Training SVC Model for English ===\n",
            "Accuracy: 0.6440251572327044\n",
            "Top-2 Accuracy: 0.7672955974842768\n",
            "                                 precision    recall  f1-score   support\n",
            "\n",
            "           Billing and Payments       0.86      0.80      0.83       260\n",
            "               Customer Service       0.51      0.62      0.56       372\n",
            "                General Inquiry       0.80      0.35      0.49        34\n",
            "                Human Resources       0.96      0.56      0.71        41\n",
            "                     IT Support       0.64      0.54      0.59       278\n",
            "                Product Support       0.58      0.59      0.58       447\n",
            "          Returns and Exchanges       0.86      0.47      0.60       116\n",
            "            Sales and Pre-Sales       0.66      0.38      0.48        66\n",
            "Service Outages and Maintenance       0.78      0.57      0.66        88\n",
            "              Technical Support       0.65      0.76      0.70       683\n",
            "\n",
            "                       accuracy                           0.64      2385\n",
            "                      macro avg       0.73      0.56      0.62      2385\n",
            "                   weighted avg       0.66      0.64      0.64      2385\n",
            "\n",
            "\n",
            "=== Training SVC Model for German ===\n",
            "Accuracy: 0.48824257425742573\n",
            "Top-2 Accuracy: 0.6639851485148515\n",
            "                                 precision    recall  f1-score   support\n",
            "\n",
            "           Billing and Payments       0.79      0.70      0.74       157\n",
            "               Customer Service       0.40      0.51      0.45       259\n",
            "                General Inquiry       0.14      0.05      0.08        19\n",
            "                Human Resources       0.71      0.19      0.29        27\n",
            "                     IT Support       0.44      0.30      0.36       180\n",
            "                Product Support       0.39      0.43      0.41       295\n",
            "          Returns and Exchanges       0.73      0.19      0.30        84\n",
            "            Sales and Pre-Sales       0.82      0.19      0.31        48\n",
            "Service Outages and Maintenance       0.62      0.25      0.36        64\n",
            "              Technical Support       0.51      0.66      0.57       483\n",
            "\n",
            "                       accuracy                           0.49      1616\n",
            "                      macro avg       0.55      0.35      0.39      1616\n",
            "                   weighted avg       0.51      0.49      0.47      1616\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Calculate top-1 and top-2 accuracy for each class for the German model\n",
        "top_1_accuracy_per_class_de = []\n",
        "top_2_accuracy_per_class_de = []\n",
        "\n",
        "for i, class_name in enumerate(classes_de):\n",
        "    top_1_accuracy = np.mean((y_test_de == i) & (y_pred_de == i))\n",
        "    top_2_accuracy = np.mean((y_test_de == i) & (np.argsort(y_prob_de, axis=1)[:, -2:] == i).any(axis=1))\n",
        "    top_1_accuracy_per_class_de.append(top_1_accuracy)\n",
        "    top_2_accuracy_per_class_de.append(top_2_accuracy)\n",
        "\n",
        "# Calculate the benefit of top-2 predictions for the German model\n",
        "benefit_de = np.array(top_2_accuracy_per_class_de) - np.array(top_1_accuracy_per_class_de)\n",
        "\n",
        "# Plot for German model\n",
        "plt.figure(figsize=(12, 6))\n",
        "x = np.arange(len(classes_de))\n",
        "plt.bar(x - 0.2, top_1_accuracy_per_class_de, width=0.4, label=\"Top-1 Accuracy\")\n",
        "plt.bar(x + 0.2, top_2_accuracy_per_class_de, width=0.4, label=\"Top-2 Accuracy\")\n",
        "plt.plot(x, benefit_de, color=\"red\", marker=\"o\", label=\"Benefit (Top-2 - Top-1)\")\n",
        "plt.xticks(x, classes_de, rotation=45, ha=\"right\")\n",
        "plt.xlabel(\"Target Classes\")\n",
        "plt.ylabel(\"Accuracy\")\n",
        "plt.title(\"Benefit of Top-2 Predictions for Each Target Class (German Model)\")\n",
        "plt.legend()\n",
        "plt.tight_layout()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 607
        },
        "id": "MitOk8kfT_5C",
        "outputId": "f8c69c3d-db7f-4022-fe64-0915489e2bf4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x600 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABKUAAAJOCAYAAABm7rQwAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzs3Xl4TGcbx/HvZI9EYstqSyT2pdRO7SrUUkUtbV9rUaWqtFQXS7VFS1GUUkJbW6mqlmrVUmpt7bVTxBaxJghZz/vHNMNIQkJkIn6f6zpXMs88c859zpyZZO55nvuYDMMwEBERERERERERyUR2tg5AREREREREREQeP0pKiYiIiIiIiIhIplNSSkREREREREREMp2SUiIiIiIiIiIikumUlBIRERERERERkUynpJSIiIiIiIiIiGQ6JaVERERERERERCTTKSklIiIiIiIiIiKZTkkpERERERERERHJdEpKiYhImly7do2XX34ZX19fTCYT/fr14/jx45hMJmbNmpUpMXzzzTeUKFECR0dHcuXKlSnbfJytXbsWk8nE2rVrLW2dO3cmICAgw7Yxa9YsTCYTx48fz7B1ZqRz587Rpk0b8ubNi8lkYvz48bYOKcMNGzYMk8nEhQsXbB1KtpCVz+lr167h7e3NnDlzbB2K3ENK779pldI5WK1aNQYOHJhxAYqIZBAlpUREbCjpH8fbF29vb+rVq8cvv/xi6/CsfPzxx8yaNYtevXrxzTff8L///S/FfsuXL2fYsGEZvv0DBw7QuXNngoKCmD59OtOmTUvWJylJlpYlMz4wLl68mHbt2lGkSBFy5MhB8eLFGTBgAFeuXEnT4+vWrWsVc548eahcuTIzZ84kMTHx4QafwT7++GOWLFli6zDS7Y033uDXX39l8ODBfPPNNzRu3Pihbu9u5+wrr7zyULedXkkfmtOyZDVz585Nd4IxISGB0NBQ6tatS548eXB2diYgIIAuXbrw999/P5xAM9iECRPImTMn7du3T3bf7t276dKlC4GBgbi4uODu7k758uUZOHAg//77rw2izRo6d+6MyWTCw8ODGzduJLv/8OHDlvN8zJgxNogwbQYNGsTkyZMJDw+3dSgiIlYcbB2AiIjABx98QGBgIIZhcO7cOWbNmsUzzzzDTz/9RLNmzWwdHgCrV6+mWrVqDB061NJmGAY3btzA0dHR0rZ8+XImT56c4YmptWvXkpiYyIQJEwgODk6xj5eXF998841V29ixYzl16hTjxo1L1vdh69GjB/7+/rz00ksUKlSIPXv2MGnSJJYvX8727dtxdXW95zoKFCjAyJEjATh//jxff/013bp149ChQ4waNeph70Iy06dPv6+E2Mcff0ybNm1o2bKlVfv//vc/2rdvj7OzcwZFmLFWr17Ns88+y5tvvplp23z66afp2LFjsvZixYplWgxpUbJkyWSvt8GDB+Pu7s67775ro6jSZu7cufzzzz/069cvTf1v3LhBq1atWLFiBbVr1+add94hT548HD9+nO+++47Zs2cTFhZGgQIFHm7gDyAuLo4JEybwxhtvYG9vb3Xf9OnT6dWrF/ny5ePFF1+kRIkSxMfH888///D1118zfvx4bty4kexxjwsHBweio6P56aefaNu2rdV9c+bMwcXFhZs3b9oourR59tln8fDw4IsvvuCDDz6wdTgiIhZKSomIZAFNmjShUqVKltvdunXDx8eHefPmZZmkVEREBKVKlbJqM5lMuLi4ZNr2gbtO23Nzc+Oll16yaps/fz6XL19O1p4ZFi1aRN26da3aKlasSKdOnZgzZw4vv/zyPdfh6elpFXvPnj0pXrw4kyZNYsSIEVYJwSSJiYnExsY+lOcmpe09CHt7+yz9QTciIiJDp4revHkTJycn7OxSH6xerFgxm5yv6eXj45MszlGjRpEvX74MiT8+Pp7ExEScnJweeF0P6q233mLFihWMGzcuWSJr6NChyZLeWdHPP//M+fPnkyVVNm7cSK9evahZsyY///wzOXPmtLp/7NixfPTRRxkWx/Xr13Fzc8uw9WUGZ2dnatasybx585Idv7lz59K0aVO+//57G0WXNnZ2drRp04avv/6a4cOHZ8kRjCLyeNL0PRGRLChXrly4urri4GD93UFiYiLjx4+ndOnSuLi44OPjQ8+ePbl8+bJVv4CAAJo1a8aff/5JlSpVcHFxoUiRInz99dfJtnXlyhX69etHwYIFcXZ2Jjg4mNGjR1tGwyRN0Tl27BjLli2zmv52Z02pzp07M3nyZIB0Td354osvKF26NM7Ozvj7+9O7d2+rKW4BAQGWEVpeXl6YTKYHGokVERFhSfy5uLjwxBNPMHv2bKs+Sfs2ZswYxo0bR+HChXF1daVOnTr8888/adrOnQkpgOeeew6A/fv331fsOXLkoFq1aly/fp3z588D5mPdp08f5syZYzmOK1asAOD06dN07doVHx8fnJ2dKV26NDNnzky23lOnTtGyZUvc3Nzw9vbmjTfeICYmJlm/lGpKJY1gK1u2LC4uLnh5edG4cWPLlCaTycT169eZPXu25Zzo3LkzkHr9nXudE2A+vmXKlGHfvn3Uq1ePHDlykD9/fj755JNkcU+cOJHSpUuTI0cOcufOTaVKlZg7d26qxzkpLsMwmDx5crJz+d9//+X5558nT548ludk2bJlVutIeu3Mnz+f9957j/z585MjRw6ioqJS3W5arV+/nueff55ChQrh7OxMwYIFeeONN1KcXnTgwAHatm2Ll5cXrq6uFC9ePMWRTFeuXKFz587kypULT09PunTpQnR09APFGRsby5AhQ6hYsSKenp64ublRq1Yt1qxZY9Xv9tfb+PHjCQoKwtnZmX379gHmY1mpUiVcXFwICgriyy+/tNTCutO3335LxYoVcXV1JU+ePLRv356TJ09a7q9bty7Lli3jxIkTluf1bnXSTp06xZdffsnTTz+d4sgqe3t73nzzzbuOkvrxxx9p2rQp/v7+ODs7ExQUxIgRI0hISLDqd/jwYVq3bo2vry8uLi4UKFCA9u3bExkZaemzcuVKnnrqKXLlyoW7uzvFixfnnXfeSXXbSZYsWUJAQABBQUFW7UkJijlz5iRLSAG4uLgwYsSIZMnjLVu20LhxYzw9PcmRIwd16tRhw4YNVn2SnqN9+/bxwgsvkDt3bp566ing1t+ppOfW1dWVsmXLWmooLV682PKeUrFiRXbs2GG17t27d9O5c2eKFCmCi4sLvr6+dO3alYsXL6YYw5EjRx7o/H7hhRf45ZdfrN6H/vrrLw4fPswLL7yQ4mPS8j4BaX//hbQd99Q8/fTTnDhxgp07d6apv4hIZtBIKRGRLCAyMpILFy5gGAYRERFMnDiRa9euJRtt0LNnT2bNmkWXLl3o27cvx44dY9KkSezYsYMNGzZYjWI5cuQIbdq0oVu3bnTq1ImZM2fSuXNnKlasSOnSpQGIjo6mTp06nD59mp49e1KoUCE2btzI4MGDOXv2LOPHj7dM0XnjjTcoUKAAAwYMAMzJoaSkyO3xnTlzhpUrVyab1pOaYcOGMXz4cBo2bEivXr04ePAgU6ZM4a+//rLs0/jx4/n666/54YcfmDJlCu7u7pQrV+6+jvWNGzeoW7cuR44coU+fPgQGBrJw4UI6d+7MlStXeP311636f/3111y9epXevXtz8+ZNJkyYQP369dmzZw8+Pj7p3n5SPY98+fLdV/xg/qBjb29vNYJn9erVfPfdd/Tp04d8+fIREBDAuXPnqFatmiVp5eXlxS+//EK3bt2IioqyfMC+ceMGDRo0ICwsjL59++Lv788333zD6tWr0xRPt27dmDVrFk2aNOHll18mPj6e9evXs3nzZipVqsQ333zDyy+/TJUqVejRowdAsg/Gt0vLOZHk8uXLNG7cmFatWtG2bVsWLVrEoEGDKFu2LE2aNAHMU5P69u1LmzZteP3117l58ya7d+9my5YtqX6YrF27tqV22p3T6c6dO0eNGjWIjo6mb9++5M2bl9mzZ9OiRQsWLVpkSTwmGTFiBE5OTrz55pvExMTcc+TPzZs3Uyw67uHhYXnswoULiY6OplevXuTNm5etW7cyceJETp06xcKFCy2P2b17N7Vq1cLR0ZEePXoQEBDA0aNH+emnn5KNfmnbti2BgYGMHDmS7du389VXX+Ht7c3o0aPvGu/dREVF8dVXX9GhQwe6d+/O1atXmTFjBiEhIWzdupXy5ctb9Q8NDeXmzZv06NEDZ2dn8uTJw44dO2jcuDF+fn4MHz6chIQEPvjggxSn4H700Ue8//77tG3blpdffpnz588zceJEateuzY4dO8iVKxfvvvsukZGRVtN63d3dU92HX375hfj4+FTr6KXFrFmzcHd3p3///ri7u7N69WqGDBlCVFQUn376KWBO4IWEhBATE8Nrr72Gr68vp0+f5ueff+bKlSt4enqyd+9emjVrRrly5fjggw9wdnbmyJEjaUpKbNy4kSeffNKqLTo6mtWrV1O3bt10TT1cvXo1TZo0oWLFigwdOhQ7OztCQ0OpX78+69evp0qVKlb9n3/+eYoWLcrHH3+MYRiW9iNHjvDCCy/Qs2dPXnrpJcaMGUPz5s2ZOnUq77zzDq+++ioAI0eOpG3bthw8eNAyynDlypX8+++/dOnSBV9fX/bu3cu0adPYu3cvmzdvTpawfNDzu1WrVrzyyissXryYrl27AuZRUiVKlEh2XCHt7xPpef9N73G/U8WKFQHYsGEDFSpUSNN+i4g8dIaIiNhMaGioASRbnJ2djVmzZln1Xb9+vQEYc+bMsWpfsWJFsvbChQsbgLFu3TpLW0REhOHs7GwMGDDA0jZixAjDzc3NOHTokNU63377bcPe3t4ICwuzWmfTpk2t+h07dswAjNDQUEtb7969jbT+eYmIiDCcnJyMRo0aGQkJCZb2SZMmGYAxc+ZMS9vQoUMNwDh//nya1p2kadOmRuHChS23x48fbwDGt99+a2mLjY01qlevbri7uxtRUVFW++bq6mqcOnXK0nfLli0GYLzxxhvpiiNJt27dDHt7+2THPCV16tQxSpQoYZw/f944f/68sX//fqNv374GYDRv3tzSDzDs7OyMvXv3JtuWn5+fceHCBav29u3bG56enkZ0dLRhGLeOyXfffWfpc/36dSM4ONgAjDVr1ljaO3XqZHU8V69ebQBG3759k8WfmJho+d3Nzc3o1KlTsj5Jr4Fjx44ZhpG+c6JOnToGYHz99deWtpiYGMPX19do3bq1pe3ZZ581SpcunWzbaQEYvXv3tmrr16+fARjr16+3tF29etUIDAw0AgICLHGvWbPGAIwiRYpYjnVatpfaMm/ePEu/lNY3cuRIw2QyGSdOnLC01a5d28iZM6dVm2FYPzdJr62uXbta9XnuueeMvHnzpinuJKVLlzbq1KljuR0fH2/ExMRY9bl8+bLh4+Njtb2k15uHh4cRERFh1b958+ZGjhw5jNOnT1vaDh8+bDg4OFi91xw/ftywt7c3PvroI6vH79mzx3BwcLBqv/N94W7eeOMNAzB27NiRpv53ntOGkfLz1bNnTyNHjhzGzZs3DcMwjB07dhiAsXDhwlTXPW7cuPt6H4yLizNMJpPV+79hGMauXbsMwOjXr1+yx1y8eNHy3nP+/HnL85iYmGgULVrUCAkJsTqPoqOjjcDAQOPpp5+2tCWdWx06dEi2/qS/Uxs3brS0/frrr5b33dvP2S+//DLZe1FKx3TevHnJ/vY96PndqVMnw83NzTAMw2jTpo3RoEEDwzAMIyEhwfD19TWGDx9uOX8//fRTy+PS+j6R1vff9Bz3lM7BJE5OTkavXr3uud8iIplF0/dERLKAyZMns3LlSlauXMm3335LvXr1ePnll1m8eLGlz8KFC/H09OTpp5/mwoULlqVixYq4u7snmw5TqlQpatWqZbnt5eVF8eLFra6itHDhQmrVqkXu3Lmt1tmwYUMSEhJYt27dQ93v33//ndjYWPr162dVY6d79+54eHikOM3hQS1fvhxfX186dOhgaXN0dKRv375cu3aNP/74w6p/y5YtyZ8/v+V2lSpVqFq1KsuXL0/3tufOncuMGTMYMGAARYsWTdNjDhw4gJeXF15eXpQsWZKJEyfStGnTZFPw6tSpY1XzyzAMvv/+e5o3b45hGFbPb0hICJGRkWzfvt1yTPz8/GjTpo3l8Tly5LCMarqb77//HpPJZFUAP8n91CxJ7znh7u5uNaLQycmJKlWqWJ3nuXLl4tSpU/z111/pjicly5cvp0qVKpZpSElx9OjRg+PHj1umnCXp1KlTmoraJ3n22Wct7we3L/Xq1bP0uX19169f58KFC9SoUQPDMCzTnM6fP8+6devo2rUrhQoVstpGSs/NnVf3q1WrFhcvXnyg6Yb29vaW0V2JiYlcunSJ+Ph4KlWqZDn/bte6dWurEVAJCQn8/vvvtGzZEn9/f0t7cHCwZSRcksWLF5OYmEjbtm2tzndfX1+KFi2a7D0yrZL2P6WpbWl1+/N19epVLly4QK1atYiOjubAgQOAuX4cwK+//prqtLKk0ZE//vhjui44cOnSJQzDIHfu3FbtSfuW0kixIkWKWN57vLy8WLp0KQA7d+60TFm7ePGi5Thfv36dBg0asG7dumSxpXblyFKlSlG9enXL7apVqwJQv359q3M2qf321/XtxzRpdGG1atUAUjy3MuL8fuGFF1i7di3h4eGsXr2a8PDwVEdbpvV9Iq3vv/dz3FOS9PdeRCSr0PQ9EZEsoEqVKlaFzjt06ECFChXo06cPzZo1w8nJicOHDxMZGYm3t3eK60gqBJ7kzg+hYP5n9Pb6U4cPH2b37t2pXonuznVmtBMnTgBQvHhxq3YnJyeKFCliuT+jt1m0aNFkhaZLlixpFVOSlJJHxYoV47vvvgPMUy9ur/cC4Ovrm+wx69evp1u3boSEhKSraHBAQADTp0+3FJUvWrRoiudAYGCg1e3z589z5coVpk2bxrRp01Jcd9Lze+LECYKDg5MlKu58XlJy9OhR/P39yZMnT1p36a7Se04UKFAgWdy5c+dm9+7dltuDBg3i999/p0qVKgQHB9OoUSNeeOEFatased8xJn1Ivt3t51CZMmUs7Xc+N/dSoEABGjZseNc+YWFhDBkyhKVLlyarKZd0PiZ9gL89lru58z0jKYFx+fJlPDw80rSOlMyePZuxY8dy4MAB4uLiLO0pHZc72yIiIrhx40aKV9y8s+3w4cMYhpFqwvd+i/Qn7fvVq1fv6/EAe/fu5b333mP16tXJkiBJz1dgYCD9+/fns88+Y86cOdSqVYsWLVrw0ksvWRJW7dq146uvvuLll1/m7bffpkGDBrRq1Yo2bdrctXh+EuO2qXNwK9F27dq1ZH1//PFH4uLi2LVrl9XVJw8fPgyYk62piYyMtEqApfYauPOcS9rPggULpth++7l+6dIlhg8fzvz585P9rbrzPTmlbd3P+f3MM8+QM2dOFixYwM6dO6lcuTLBwcHJauJB2t8n0vr+ez/HPSWGYajIuYhkKUpKiYhkQXZ2dtSrV48JEyZw+PBhSpcuTWJiIt7e3syZMyfFx9yZWErtima3fyhJTEzk6aefZuDAgSn2zWqXoM+KFixYQJcuXaza7vzgt2vXLlq0aEGZMmVYtGhRsgL2d+Pm5nbPBAWQbCRO0jfmL730UqofYu63LldWkpbzvGTJkhw8eJCff/6ZFStW8P333/PFF18wZMgQhg8f/tBjTM8oqbRISEjg6aef5tKlSwwaNIgSJUrg5ubG6dOn6dy5c7pG0NwuLccyvb799ls6d+5My5Yteeutt/D29sbe3p6RI0dy9OjRZP0f5FglJiZiMpn45ZdfUtyXu9WNupsSJUoAsGfPnmQ1sNLiypUr1KlTBw8PDz744AOCgoJwcXFh+/btDBo0yOr5Gjt2LJ07d+bHH3/kt99+o2/fvowcOZLNmzdToEABXF1dWbduHWvWrGHZsmWsWLGCBQsWUL9+fX777bdUn8M8efJgMpmSJTCDg4NxcHBI8eINderUAUjxghsAn376aarH485jndrzmlq8aTkX27Zty8aNG3nrrbcoX7487u7uJCYm0rhx4xRfAxlxfjs7O9OqVStmz57Nv//++0AX3Eiv+znuKbly5coD1TQUEcloSkqJiGRR8fHxwK1vsIOCgvj999+pWbNmhn3IDQoK4tq1a2lKeqRVer6BLVy4MAAHDx6kSJEilvbY2FiOHTuWoXHdvs3du3eTmJhoNbIgaQpNUkxJkr6dvt2hQ4csV+sKCQlh5cqVqW7v6NGjNG7cGG9vb5YvX37fH4zTy8vLi5w5c5KQkHDP41i4cGH++eefZN+gHzx48J7bCQoK4tdff+XSpUt3HS2V1vPiYZ0Tbm5utGvXjnbt2hEbG0urVq346KOPGDx4MC4uLulaV+HChVM8NqmdQxltz549HDp0iNmzZ1sVYL/zPEw6fmm9WuTDsGjRIooUKcLixYutzoGUpnumxNvbGxcXF44cOZLsvjvbgoKCMAyDwMDAeybU0/M+1aRJE+zt7fn222/vq9j52rVruXjxIosXL6Z27dqW9mPHjqXYv2zZspQtW5b33nuPjRs3UrNmTaZOncqHH34ImL+0aNCgAQ0aNOCzzz7j448/5t1332XNmjWpvj4cHBwICgpKtk03Nzfq1q3LH3/8wenTp62mKqcm6SIFHh4eD+U9Oi0uX77MqlWrGD58OEOGDLG0p/R+ndFeeOEFZs6ciZ2dHe3bt0+1X1rfJ9L6/psRx/306dPExsZaRmuJiGQFqiklIpIFxcXF8dtvv+Hk5GT557Ft27YkJCQwYsSIZP3j4+OtLlOdVm3btmXTpk38+uuvye67cuWKJTGWHm5ubpbH30vDhg1xcnLi888/t/q2esaMGURGRtK0adN0b/9ennnmGcLDw1mwYIGlLT4+nokTJ+Lu7m4ZHZBkyZIlnD592nJ769atbNmyxVLPxs/Pj4YNG1otScLDw2nUqBF2dnb8+uuvqU6TfBjs7e1p3bo133//fYpJiduvnPjMM89w5swZFi1aZGmLjo5Oddrf7Vq3bo1hGCmOOLr9OXVzc7PZOXHnJeKdnJwoVaoUhmFYTSdLq2eeeYatW7eyadMmS9v169eZNm0aAQEBVrW9HoakER+3Hx/DMJgwYYJVPy8vL2rXrs3MmTMJCwuzuu9BRj+lR0qxbtmyxerY3evxDRs2ZMmSJZw5c8bSfuTIEX755Rervq1atcLe3p7hw4cn2z/DMKzOAzc3txSneKWkYMGCdO/end9++42JEycmuz8xMZGxY8dy6tSpVPchKYYksbGxfPHFF1b9oqKikr3nli1bFjs7O2JiYgDzlLU7JY2aSeqTmurVq/P3338nax8yZAgJCQm89NJLKU7ju/NYVqxYkaCgIMaMGZNi/zuvyvowpHRMAcaPH//Qt12vXj1GjBjBpEmTUpyqnSSt7xNpff/NiOO+bds2AGrUqHHPviIimUUjpUREsoBffvnF8u1pREQEc+fO5fDhw7z99tuWWhd16tShZ8+ejBw5kp07d9KoUSMcHR05fPgwCxcuZMKECVaFUtPirbfeYunSpTRr1ozOnTtTsWJFrl+/zp49e1i0aBHHjx9P9zD/pEtO9+3bl5CQEOzt7VP9NtnLy4vBgwczfPhwGjduTIsWLTh48CBffPEFlStXtipgnVF69OjBl19+SefOndm2bRsBAQEsWrSIDRs2MH78+GTFjIODg3nqqafo1asXMTExjB8/nrx586Y65fF2jRs35t9//2XgwIH8+eef/Pnnn5b7fHx8ePrppzN8/243atQo1qxZQ9WqVenevTulSpXi0qVLbN++nd9//93yAbd79+5MmjSJjh07sm3bNvz8/Pjmm2/IkSPHPbdRr149/ve///H5559z+PBhy9SZ9evXU69ePfr06QOYz4vff/+dzz77DH9/fwIDA1Ost/IwzolGjRrh6+tLzZo18fHxYf/+/UyaNImmTZveV/Hqt99+m3nz5tGkSRP69u1Lnjx5mD17NseOHeP7779PU22fuzl06BDffvttsvakc6ZEiRIEBQXx5ptvcvr0aTw8PPj++++TTc0C+Pzzz3nqqad48skn6dGjB4GBgRw/fpxly5axc+fOB4ozLZo1a8bixYt57rnnaNq0KceOHWPq1KmUKlUqxQ/WKRk2bBi//fYbNWvWpFevXiQkJDBp0iTKlCljtQ9BQUF8+OGHDB48mOPHj9OyZUty5szJsWPH+OGHH+jRo4elNlLFihVZsGAB/fv3p3Llyri7u9O8efNUYxg7dixHjx6lb9++LF68mGbNmpE7d27CwsJYuHAhBw4cSPV9rkaNGuTOnZtOnTrRt29fTCYT33zzTbKEyurVq+nTpw/PP/88xYoVIz4+nm+++caSYAb44IMPWLduHU2bNqVw4cJERETwxRdfUKBAAauC2il59tln+eabbzh06JDVSLJatWoxadIkXnvtNYoWLcqLL75IiRIliI2N5dChQ8yZMwcnJydLAsbOzo6vvvqKJk2aULp0abp06UL+/Pk5ffo0a9aswcPDg59++umusTwoDw8PateuzSeffEJcXBz58+fnt99+S3X0WUays7Pjvffeu2e/tL5PpPX9NyOO+8qVKylUqBAVKlS4/wMgIpLRMuEKfyIikoqkyzbfvri4uBjly5c3pkyZYnXZ5yTTpk0zKlasaLi6uho5c+Y0ypYtawwcONA4c+aMpU/hwoWNpk2bJntsnTp1rC7XbhjmS1QPHjzYCA4ONpycnIx8+fIZNWrUMMaMGWPExsbedZ1Jl8EODQ21tMXHxxuvvfaa4eXlZZhMJiMtf2omTZpklChRwnB0dDR8fHyMXr16GZcvX7bqk3RZ7/ReCj2lS7+fO3fO6NKli5EvXz7DycnJKFu2rNU+3L5vn376qTF27FijYMGChrOzs1GrVi1j165dadr2nc/t7cudz0NK6tSpY5QuXTpN2+ndu3eK9507d87o3bu3UbBgQcPR0dHw9fU1GjRoYEybNs2q34kTJ4wWLVoYOXLkMPLly2e8/vrrxooVK5Jdhr1Tp07Jjmd8fLzx6aefGiVKlDCcnJwMLy8vo0mTJsa2bdssfQ4cOGDUrl3bcHV1NQCjU6dOhmGkfunytJwTqR2fO2P88ssvjdq1axt58+Y1nJ2djaCgIOOtt94yIiMjUz6gt0nt2B49etRo06aNkStXLsPFxcWoUqWK8fPPP1v1WbNmjQEYCxcuvOd2bt9eWs6Zffv2GQ0bNjTc3d2NfPnyGd27dzd27dqV7PVoGIbxzz//GM8995wl1uLFixvvv/++5f7UXlt3u6x8akqXLm0VZ2JiovHxxx8bhQsXNpydnY0KFSoYP//8c7Ln6PbXW0pWrVplVKhQwXBycjKCgoKMr776yhgwYIDh4uKSrO/3339vPPXUU4abm5vh5uZmlChRwujdu7dx8OBBS59r164ZL7zwgpErVy4DSHZOpyQ+Pt746quvjFq1ahmenp6Go6OjUbhwYaNLly7Gjh07LP1SOm4bNmwwqlWrZri6uhr+/v7GwIEDjV9//dXq9fXvv/8aXbt2NYKCggwXFxcjT548Rr169Yzff//d6jg8++yzhr+/v+Hk5GT4+/sbHTp0MA4dOnTP+GNiYox8+fIZI0aMSPH+HTt2GB07djQKFSpkODk5GW5ubka5cuWMAQMGGEeOHEmxf6tWrSyvq8KFCxtt27Y1Vq1aZelzt/ft1P5OpfSaS+n8OHXqlOW89vT0NJ5//nnjzJkzBmAMHTr0njGk9fzu1KmT4ebmdtc+qZ2/aXmfMIy0v/8aRtqOe0r7lpCQYPj5+RnvvffeXfdFRCSzmQwjk8Zvi4iIPEKOHz9OYGAgn376qdWVp0Qka2jZsiV79+7NlDpC2cWIESMIDQ3l8OHDqRb+luxpyZIlvPDCCxw9ehQ/Pz9bhyMiYqGaUiIiIiKSpd24ccPq9uHDh1m+fDl169a1TUCPqDfeeINr164xf/58W4cimWz06NH06dNHCSkRyXJUU0pEREREsrQiRYrQuXNnihQpwokTJ5gyZQpOTk5pqu0mt7i7uxMREWHrMMQG0npxARGRzKaklIiIiIhkaY0bN2bevHmEh4fj7OxM9erV+fjjjylatKitQxMREZEHoJpSIiIiIiIiIiKS6VRTSkREREREREREMp2SUiIiIiIiIiIikulUUyoFiYmJnDlzhpw5c2IymWwdjoiIiIiIiIjII8MwDK5evYq/vz92dqmPh1JSKgVnzpyhYMGCtg5DREREREREROSRdfLkSQoUKJDq/UpKpSBnzpyA+eB5eHjYOBoRERERERERkUdHVFQUBQsWtORXUqOkVAqSpux5eHgoKSUiIiIiIiIich/uVRJJhc5FRERERERERCTTKSklIiIiIiIiIiKZTkkpERERERERERHJdKop9QASEhKIi4uzdRgiWY6joyP29va2DkNERERERESyMCWl7oNhGISHh3PlyhVbhyKSZeXKlQtfX997FrYTERERERGRx5OSUvchKSHl7e1Njhw59KFb5DaGYRAdHU1ERAQAfn5+No5IREREREREsiIlpdIpISHBkpDKmzevrcMRyZJcXV0BiIiIwNvbW1P5REREREREJBkVOk+npBpSOXLksHEkIllb0mtEdddEREREREQkJUpK3SdN2RO5O71GRERERERE5G6UlBIRERERERERkUynpJTYxJIlSwgODsbe3p5+/foxa9YscuXKdV/rio2NJTg4mI0bN2ZskJKiCxcu4O3tzalTp2wdioiIiIiIiDzClJSylYQEWLsW5s0z/0xIeKib69y5MyaTybLkzZuXxo0bs3v37oe63dT07NmTNm3acPLkSUaMGEG7du04dOiQ5f5hw4ZRvnz5NK1r6tSpBAYGUqNGDWbNmmW1nyktx48fz/D9GTlyJJUrVyZnzpx4e3vTsmVLDh48+EDrvPM5u3MJCAjImODvMG3aNOrWrYuHhwcmk4krV65Y3Z8vXz46duzI0KFDH8r2RURERERE5PGgpJQtLF4MAQFQrx688IL5Z0CAuf0haty4MWfPnuXs2bOsWrUKBwcHmjVr9lC3mZJr164RERFBSEgI/v7+5MyZE1dXV7y9vdO9LsMwmDRpEt26dQOgXbt2ln08e/Ys1atXp3v37lZtBQsWzOhd4o8//qB3795s3ryZlStXEhcXR6NGjbh+/fp9r3PChAlWcQOEhoZabv/1118ZFb6V6OhoGjduzDvvvJNqny5dujBnzhwuXbr0UGIQERERERGR7M/B1gE8dhYvhjZtwDCs20+fNrcvWgStWj2UTTs7O+Pr6wuAr68vb7/9NrVq1eL8+fN4eXkBcPLkSQYMGMBvv/2GnZ0dtWrVYsKECZZROZ07d+bKlSs89dRTjB07ltjYWNq3b8/48eNxdHQEICYmhnfffZd58+Zx5coVypQpw+jRo6lbty5r166lXr16ANSvXx+ANWvWcPz4cfr168eVK1eYNWsWw4cPB24Vyw4NDaVz587J9mnbtm0cPXqUpk2bAuDq6oqrq6vlficnJ3LkyGHZ77CwMFq1asWqVauws7OjcePGTJw4ER8fH8A8QmvJkiX06tWLDz/8kIsXL9KsWTOmT5+Op6dnqsd2xYoVVrdnzZqFt7c327Zto3bt2ml8hqx5enom22auXLks+/LHH3/w1ltvsWvXLvLkyUOnTp348MMPcXAwv6zr1q1LmTJlAPjmm29wdHSkV69efPDBB3ctQt6vXz8A1q5dm2qf0qVL4+/vzw8//GBJCIqIiIiIiGRpw1L/TJelDIu0dQSZRiOlMoJhwPXr916ioqBv3+QJqaR1ALz+urlfWtaX0nrS6Nq1a3z77bcEBweTN29eAOLi4ggJCSFnzpysX7+eDRs24O7uTuPGjYmNjbU8ds2aNRw9epQ1a9Ywe/ZsZs2axaxZsyz39+nTh02bNjF//nx2797N888/T+PGjTl8+DA1atSwTGv7/vvvOXv2LDVq1LCKrV27dgwYMIDSpUtbRgW1a9cuxf1Yv349xYoVI2fOnPfc58TERJ599lkuXbrEH3/8wcqVK/n333+TrfvIkSN89913/PTTT6xYsYIdO3bw6quvpum4JomMNL+J5MmTJ12PS6vTp0/zzDPPULlyZXbt2sWUKVOYMWMGH374oVW/2bNn4+DgwNatW5kwYQKfffYZX331VYbEUKVKFdavX58h6xIREREREZHHj0ZKZYToaHB3f/D1GAacOgV3GZFj5do1cHNL8+p//vln3P+L8/r16/j5+fHzzz9jZ2fOTS5YsIDExES++uorqxFKuXLlYu3atTRq1AiA3LlzM2nSJOzt7SlRogRNmzZl1apVdO/enbCwMEJDQwkLC8Pf3x+AN998kxUrVhAaGsrHH39smaaXJ08ey6if27m6uuLu7o6Dg0OK99/uxIkTlu3cy6pVq9izZw/Hjh2zTOH7+uuvKV26NH/99ReVK1cG4ObNm3z99dfkz58fgIkTJ9K0aVPGjh17z3jAnPzq168fNWvWtIxUymhffPEFBQsWZNKkSZhMJkqUKMGZM2cYNGgQQ4YMsTynBQsWZNy4cZhMJooXL86ePXsYN24c3bt3f+AY/P392bFjxwOvR0RERERERB5PGin1GKlXrx47d+5k586dbN26lZCQEJo0acKJEycA2LVrF0eOHCFnzpy4u7vj7u5Onjx5uHnzJkePHrWsp3Tp0tjb21tu+/n5ERERAcCePXtISEigWLFilnW4u7vzxx9/WK0jo9y4cQMXF5c09d2/fz8FCxa0qilVqlQpcuXKxf79+y1thQoVsiSkAKpXr05iYiIHDx5k/fr1Vvs1Z86cZNvp3bs3//zzD/Pnz081lrSs5177Ur16datpeDVr1uTatWtWV8WrVq2aVZ/q1atz+PBhEhIS+Pjjj61iCAsLS1cMrq6uREdHp+sxIiIiIiIiIkk0Uioj5MhhHrV0L+vWwTPP3Lvf8uWQljpEOXLcu89t3NzcCA4Ottz+6quv8PT0ZPr06Xz44Ydcu3aNihUrppggSao5BVhqRyUxmUwkJiYC5mmB9vb2bNu2zSpxBVhGaWWkfPnysWfPngxfb2oqVarEzp07LbeTalEl6dOnDz///DPr1q2jQIEC972ezPDKK6/Qtm1by+20jjhLcunSJavzQkRERERERCQ9lJTKCCZT2qbRNWoEBQqYi5qnVA/KZDLf36gR3JHQeRhMJhN2dnbcuHEDgCeffJIFCxbg7e2Nh4fHfa2zQoUKJCQkEBERQa1ate47NicnJxISEtK0vSlTpmAYxl2LdwOULFmSkydPcvLkSctoqX379nHlyhVKlSpl6RcWFsaZM2csSZrNmzdjZ2dH8eLFcXV1tUrsJTEMg9dee40ffviBtWvXEhgYeNdYUltPWpUsWZLvv//ear83bNhAzpw5rZJhW7ZssXrc5s2bKVq0KPb29uTJk+eBal79888/1K1b974fLyIiIiIiIo83Td/LTPb2MGGC+fc7EyhJt8ePf2gJqZiYGMLDwwkPD2f//v289tprXLt2jebNmwPw4osvki9fPp599lnWr1/PsWPHWLt2LX379rWaEnY3xYoV48UXX6Rjx44sXryYY8eOsXXrVkaOHMmyZcvSHGtAQADHjh1j586dXLhwgZiYmBT71atXj2vXrrF37957rrNhw4aULVuWF198ke3bt7N161Y6duxInTp1qFSpkqWfi4sLnTp1YteuXaxfv56+ffvStm3bu9aT6t27N99++y1z584lZ86cluOclPDLaK+++ionT57ktdde48CBA/z4448MHTqU/v37W+pJgTnB1r9/fw4ePMi8efOYOHEir7/++l3XHR4ezs6dOzly5AhgnpK5c+dOLl26ZOkTHR3Ntm3bLHXGRERERERERNJLSanM1qoVLFoEt9UsAswjpBYtMt//kKxYsQI/Pz/8/PyoWrUqf/31FwsXLrSMdsmRIwfr1q2jUKFCtGrVipIlS9KtWzdu3ryZrpFToaGhdOzYkQEDBlC8eHFatmzJX3/9RaFChdK8jtatW9O4cWPq1auHl5cX8+bNS7Ff3rx5ee6559JUk8lkMvHjjz+SO3duateuTcOGDSlSpAgLFiyw6hccHEyrVq145plnaNSoEeXKleOLL76467qnTJlCZGQkdevWtRxjPz+/ZOvOKPnz52f58uVs3bqVJ554gldeeYVu3brx3nvvWfXr2LEjN27coEqVKvTu3ZvXX3+dHj163HXdU6dOpUKFCpZi6LVr16ZChQosXbrU0ufHH3+kUKFCDzQaTkRERERERB5vJsNIaR7Z4y0qKgpPT08iIyOTJWNu3rzJsWPHCAwMTHOB7RQlJMD69XD2LPj5Qa1amTJlLzvavXs3Tz/9NEePHn3gulXDhg1jyZIlVvWeHlV169alfPnyjB8/PsPXXa1aNfr27csLL7yQap8Me62IiIiIiIhkhGFpvNK9rQ2LtHUED+xueZXbqaaUrdjbg+rxZIhy5coxevRojh07RtmyZW0dTrZ34cIFWrVqRYcOHWwdioiIiIiIiDzClJSSbKFz5862DuGxkS9fPgYOHGjrMEREREREROQRp6SUyG2GDRvGsGHDbB1Ghli7dq2tQxARERERERFJlQqdi4iIiIiIiIhIplNSSkREREREREREMp2SUiIiIiIiIiIikumUlBIRERERERERkUynpJSIiIiIiIiIiGQ6JaVERERERERERCTTKSklIiIiIiIiIiKZzsHWAWQnAW8vy7RtHR/VNM19TSbTXe8fOnQow4YNe8CIrN28eZNXXnmFbdu2sX//fpo1a8aSJUvS/PiePXvy1VdfMX/+fJ5//vkMjU1EREREREREbE8jpR4DZ8+etSzjx4/Hw8PDqu3NN9/M8G0mJCTg6upK3759adiwYboeGx0dzfz58xk4cCAzZ87M8NjSKzY21tYhiIiIiIiIiGQ7Sko9Bnx9fS2Lp6cnJpPJctvb25vPPvuMAgUK4OzsTPny5VmxYoXlscePH8dkMjF//nxq1KiBi4sLZcqU4Y8//rjrNt3c3JgyZQrdu3fH19c3XfEuXLiQUqVK8fbbb7Nu3TpOnjxpdX9MTAyDBg2iYMGCODs7ExwczIwZMyz37927l2bNmuHh4UHOnDmpVasWR48eBaBu3br069fPan0tW7akc+fOltsBAQGMGDGCjh074uHhQY8ePQAYNGgQxYoVI0eOHBQpUoT333+fuLg4q3X99NNPVK5cGRcXF/Lly8dzzz0HwAcffECZMmWS7Wv58uV5//3303V8RERERERERLIDJaUecxMmTGDs2LGMGTOG3bt3ExISQosWLTh8+LBVv7feeosBAwawY8cOqlevTvPmzbl48eJDiWnGjBm89NJLeHp60qRJE2bNmmV1f8eOHZk3bx6ff/45+/fv58svv8Td3R2A06dPU7t2bZydnVm9ejXbtm2ja9euxMfHpyuGMWPG8MQTT7Bjxw5L0ihnzpzMmjWLffv2MWHCBKZPn864ceMsj1m2bBnPPfcczzzzDDt27GDVqlVUqVIFgK5du7J//37++usvS/8dO3awe/duunTpcj+HSUREREREROSRpppSj7kxY8YwaNAg2rdvD8Do0aNZs2YN48ePZ/LkyZZ+ffr0oXXr1gBMmTKFFStWMGPGDAYOHJih8Rw+fJjNmzezePFiAF566SX69+/Pe++9h8lk4tChQ3z33XesXLnSMi2wSJEilsdPnjwZT09P5s+fj6OjIwDFihVLdxz169dnwIABVm3vvfee5feAgADefPNNyzRDgI8++oj27dszfPhwS78nnngCgAIFChASEkJoaCiVK1cGIDQ0lDp16ljFLyIiIiIiIvK4yBIjpSZPnkxAQAAuLi5UrVqVrVu3ptp3+vTp1KpVi9y5c5M7d24aNmyYrH/nzp0xmUxWS+PGjR/2bjxyoqKiOHPmDDVr1rRqr1mzJvv377dqq169uuV3BwcHKlWqZOlTunRp3N3dcXd3p0mTJg8U08yZMwkJCSFfvnwAPPPMM0RGRrJ69WoAdu7cib29PXXq1Enx8Tt37qRWrVqWhNT9qlSpUrK2BQsWULNmTXx9fXF3d+e9994jLCzMatsNGjRIdZ3du3dn3rx53Lx5k9jYWObOnUvXrl0fKE4RERERERGRR5XNR0otWLCA/v37M3XqVKpWrcr48eMJCQnh4MGDeHt7J+u/du1aOnToYKlvNHr0aBo1asTevXvJnz+/pV/jxo0JDQ213HZ2ds6U/XkcLV++3FJbydXV9b7Xk5CQwOzZswkPD8fBwcGqfebMmTRo0OCe67/X/XZ2dhiGYdV2Z10oMNfEut2mTZt48cUXGT58OCEhIZbRWGPHjk3ztps3b46zszM//PADTk5OxMXF0aZNm7s+RkRERERERCS7svlIqc8++4zu3bvTpUsXSpUqxdSpU8mRI0eqV12bM2cOr776KuXLl6dEiRJ89dVXJCYmsmrVKqt+zs7OVgW+c+fOnRm780jx8PDA39+fDRs2WLVv2LCBUqVKWbVt3rzZ8nt8fDzbtm2jZMmSABQuXJjg4GCCg4OtEoPptXz5cq5evcqOHTvYuXOnZZk3bx6LFy/mypUrlC1blsTExFQLrZcrV47169enmGgC8PLy4uzZs5bbCQkJ/PPPP/eMbePGjRQuXJh3332XSpUqUbRoUU6cOJFs23eeh7dzcHCgU6dOhIaGEhoaSvv27R8oiSciIiIiIiLyKLPpSKnY2Fi2bdvG4MGDLW12dnY0bNiQTZs2pWkd0dHRxMXFkSdPHqv2tWvX4u3tTe7cualfvz4ffvghefPmTXEdMTExxMTEWG5HRUXdx948mt566y2GDh1KUFAQ5cuXJzQ0lJ07dzJnzhyrfpMnT6Zo0aKULFmScePGcfny5XtOPdu3bx+xsbFcunSJq1evsnPnTsB8xbmUzJgxg6ZNm1rqMCUpVaoUb7zxBnPmzKF379506tSJrl278vnnn/PEE09w4sQJIiIiaNu2LX369GHixIm0b9+ewYMH4+npyebNm6lSpQrFixenfv369O/fn2XLlhEUFMRnn33GlStX7nmcihYtSlhYGPPnz6dy5cosW7aMH374warP0KFDadCgAUFBQbRv3574+HiWL1/OoEGDLH1efvllSzLvzmSgiIiIiIiIyOPEpiOlLly4QEJCAj4+PlbtPj4+hIeHp2kdgwYNwt/f31L0GsxT977++mtWrVrF6NGj+eOPP2jSpAkJCQkprmPkyJF4enpaloIFC97/Tj1i+vbtS//+/RkwYABly5ZlxYoVLF26lKJFi1r1GzVqFKNGjeKJJ57gzz//ZOnSpZa6T6l55plnqFChAj/99BNr166lQoUKVKhQIcW+586dY9myZZZi6rezs7PjueeeY8aMGYC50HqbNm149dVXKVGiBN27d+f69esA5M2bl9WrV3Pt2jXq1KlDxYoVmT59uqXGVNeuXenUqRMdO3a0FBmvV6/ePY9TixYteOONN+jTpw/ly5dn48aNlqvyJalbty4LFy5k6dKllC9fnvr16yerd1a0aFFq1KhBiRIlqFq16j23KyIiIiIiIpJdmYw7C+xkojNnzpA/f342btxoVUh74MCB/PHHH2zZsuWujx81ahSffPIJa9eupVy5cqn2+/fffwkKCuL3339PsRB1SiOlChYsSGRkJB4eHlZ9b968ybFjxwgMDMTFxSWtu/rIOn78OIGBgezYsSPVEU6SdoZhULRoUV599VX69+9v63AeqsfttSIiIiIiIlncME9bR5A2wyJtHcEDi4qKwtPTM8W8yu1sOn0vX7582Nvbc+7cOav2c+fO4evre9fHjhkzhlGjRvH777/fNSEFUKRIEfLly8eRI0dSTEo5OzurELo8dOfPn2f+/PmEh4fTpUsXW4cjIiIiIiIiYlM2nb7n5ORExYoVrYpDJxUtv33k1J0++eQTRowYwYoVK6hUqdI9t3Pq1CkuXryIn59fhsQtcj+8vb354IMPmDZtmgrvi4iIiIiIyGPPpiOlAPr370+nTp2oVKkSVapUYfz48Vy/ft0ykqRjx47kz5+fkSNHAjB69GiGDBnC3LlzCQgIsNSecnd3x93dnWvXrjF8+HBat26Nr68vR48eZeDAgQQHBxMSEmKz/XxUBQQEYMMZntmKjqOIiIiIiIjILTZPSrVr147z588zZMgQwsPDKV++PCtWrLAUPw8LC8PO7taArilTphAbG0ubNm2s1jN06FCGDRuGvb09u3fvZvbs2Vy5cgV/f38aNWrEiBEjNEVPRERERERERCSLsGmh86zqbgW5VLxZJG30WhERERERkSxFhc4zTVoLndu0ppSIiIiIiIiIiDyelJQSEREREREREZFMp6SUiIiIiIiIiIhkOiWlREREREREREQk0ykpJSIiIiIiIiIimc7B1gFkK5lZyT8d1fhNJtNd7x86dCjDhg17wICsrV27lnHjxrF161aioqIoWrQob731Fi+++GKaHh8SEsLvv//O5s2bqVy5cobGJiIiIiIiIiK2p6TUY+Ds2bOW3xcsWMCQIUM4ePCgpc3d3T3Dt7lx40bKlSvHoEGD8PHx4eeff6Zjx454enrSrFmzuz42LCyMjRs30qdPH2bOnGnzpFRcXByOjo42jUFEREREREQku9H0vceAr6+vZfH09MRkMllue3t789lnn1GgQAGcnZ0pX748K1assDz2+PHjmEwm5s+fT40aNXBxcaFMmTL88ccfd93mO++8w4gRI6hRowZBQUG8/vrrNG7cmMWLF98z3tDQUJo1a0avXr2YN28eN27csLr/ypUr9OzZEx8fH0s8P//8s+X+DRs2ULduXXLkyEHu3LkJCQnh8uXLAAQEBDB+/Hir9ZUvX95qpJjJZGLKlCm0aNECNzc3PvroIxISEujWrRuBgYG4urpSvHhxJkyYkCz2mTNnUrp0aZydnfHz86NPnz4AdO3aNVkyLi4uDm9vb2bMmHHPYyIiIiIiIiKS3Sgp9ZibMGECY8eOZcyYMezevZuQkBBatGjB4cOHrfq99dZbDBgwgB07dlC9enWaN2/OxYsX07WtyMhI8uTJc9c+hmEQGhrKSy+9RIkSJQgODmbRokWW+xMTE2nSpAkbNmzg22+/Zd++fYwaNQp7e3sAdu7cSYMGDShVqhSbNm3izz//pHnz5iQkJKQr1mHDhvHcc8+xZ88eunbtSmJiIgUKFGDhwoXs27ePIUOG8M477/Ddd99ZHjNlyhR69+5Njx492LNnD0uXLiU4OBiAl19+mRUrVliNWvv555+Jjo6mXbt26YpNREREREREJDvQ9L3H3JgxYxg0aBDt27cHYPTo0axZs4bx48czefJkS78+ffrQunVrwJx8WbFiBTNmzGDgwIFp2s53333HX3/9xZdffnnXfr///jvR0dGEhIQA8NJLLzFjxgz+97//We7funUr+/fvp1ixYgAUKVLE8vhPPvmESpUq8cUXX1jaSpcunaYYb/fCCy/QpUsXq7bhw4dbfg8MDGTTpk189913tG3bFoAPP/yQAQMG8Prrr1v6JU09rFGjBsWLF+ebb76xHLPQ0FCef/75hzJ9UkRERERERCSr00ipx1hUVBRnzpyhZs2aVu01a9Zk//79Vm3Vq1e3/O7g4EClSpUsfUqXLo27uzvu7u40adIk2XbWrFlDly5dmD59+j0TRDNnzqRdu3Y4OJjzpR06dGDDhg0cPXoUMI+EKlCggCUhdaekkVIPqlKlSsnaJk+eTMWKFfHy8sLd3Z1p06YRFhYGQEREBGfOnLnrtl9++WVCQ0MBOHfuHL/88gtdu3Z94FhFREREREREHkUaKSUPbPny5cTFxQHg6upqdd8ff/xB8+bNGTduHB07drzrei5dusQPP/xAXFwcU6ZMsbQnJCQwc+ZMPvroo2Trv9O97rezs8MwDKu2pNhv5+bmZnV7/vz5vPnmm4wdO5bq1auTM2dOPv30U7Zs2ZKm7QJ07NiRt99+m02bNrFx40YCAwOpVavWPR8nIiIiIiIikh1ppNRjzMPDA39/fzZs2GDVvmHDBkqVKmXVtnnzZsvv8fHxbNu2jZIlSwJQuHBhgoODCQ4OJn/+/JZ+a9eupWnTpowePZoePXrcM545c+ZQoEABdu3axc6dOy3L2LFjmTVrFgkJCZQrV45Tp05x6NChFNdRrlw5Vq1aleo2vLy8rOo6RUVFcezYsXvGtmHDBmrUqMGrr75KhQoVCA4OtozeAsiZMycBAQF33XbevHlp2bIloaGhzJo1K9n0QBEREREREZHHiUZKPebeeusthg4dSlBQEOXLlyc0NJSdO3cyZ84cq36TJ0+maNGilCxZknHjxnH58uW7Tj1bs2YNzZo14/XXX6d169aEh4cD4OTklGqx8xkzZtCmTRvKlClj1V6wYEEGDx7MihUraNq0KbVr16Z169Z89tlnBAcHc+DAAUwmE40bN2bw4MGULVuWV199lVdeeQUnJyfWrFnD888/T758+ahfvz6zZs2iefPm5MqViyFDhliKpN9N0aJF+frrr/n1118JDAzkm2++4a+//iIwMNDSZ9iwYbzyyit4e3vTpEkTrl69yoYNG3jttdcsfV5++WWaNWtGQkICnTp1uud2RURERERERLIrjZR6zPXt25f+/fszYMAAypYty4oVK1i6dClFixa16jdq1ChGjRrFE088wZ9//snSpUvJly9fquudPXs20dHRjBw5Ej8/P8vSqlWrFPtv27aNXbt2WYqp387T05MGDRowY8YMAL7//nsqV65Mhw4dKFWqFAMHDrRcXa9YsWL89ttv7Nq1iypVqlC9enV+/PFHS42qwYMHU6dOHZo1a0bTpk1p2bIlQUFB9zxOPXv2pFWrVrRr146qVaty8eJFXn31Vas+nTp1Yvz48XzxxReULl2aZs2aJbuKYcOGDfHz8yMkJAR/f/97bldEREREREQkuzIZdxbYEaKiovD09CQyMhIPDw+r+27evMmxY8cIDAzExcXFRhFmnuPHjxMYGMiOHTsoX768rcN55F27do38+fMTGhqaaoIuu3jcXisiIiIiIpLFDfO0dQRpMyzS1hE8sLvlVW6n6XsimSAxMZELFy4wduxYcuXKRYsWLWwdkoiIiIiIiIhNKSklkgnCwsIIDAykQIECzJo1yzKdUERERERERORxpU/GclcBAQFohueD03EUERERERERsaZC5yIiIiIiIiIikumUlLpPGvUicnd6jYiIiIiIiMjdKCmVTo6OjgBER0fbOBKRrC3pNZL0mhERERERERG5nWpKpZO9vT25cuUiIiICgBw5cmAymWwclUjWYRgG0dHRREREkCtXLuzt7W0dkoiIiIiIiGRBSkrdB19fXwBLYkpEksuVK5fltSIiIiIiIiJyJyWl7oPJZMLPzw9vb2/i4uJsHY5IluPo6KgRUiIiIiIiInJXSko9AHt7e33wFhERERERERG5Dyp0LiIiIiIiIiIimU5JKRERERERERERyXRKSomIiIiIiIiISKZTUkpERERERERERDKdklIiIiIiIiIiIpLplJQSEREREREREZFMp6SUiIiIiIiIiIhkOiWlREREREREREQk0ykpJSIiIiIiIiIimU5JKRERERERERERyXRKSomIiIiIiIiISKZTUkpERERERERERDKdklIiIiIiIiIiIpLplJQSEREREREREZFMp6SUiIiIiIiIiIhkOiWlREREREREREQk0ykpJSIiIiIiIiIimU5JKRERERERERERyXRZIik1efJkAgICcHFxoWrVqmzdujXVvtOnT6dWrVrkzp2b3Llz07Bhw2T9DcNgyJAh+Pn54erqSsOGDTl8+PDD3g0REREREREREUkjmyelFixYQP/+/Rk6dCjbt2/niSeeICQkhIiIiBT7r127lg4dOrBmzRo2bdpEwYIFadSoEadPn7b0+eSTT/j888+ZOnUqW7Zswc3NjZCQEG7evJlZuyUiIiIiIiIiIndhMgzDsGUAVatWpXLlykyaNAmAxMREChYsyGuvvcbbb799z8cnJCSQO3duJk2aRMeOHTEMA39/fwYMGMCbb74JQGRkJD4+PsyaNYv27dvfc51RUVF4enoSGRmJh4fHg+2giIiIiIiIiNjeME9bR5A2wyJtHcEDS2texaYjpWJjY9m2bRsNGza0tNnZ2dGwYUM2bdqUpnVER0cTFxdHnjx5ADh27Bjh4eFW6/T09KRq1appXqeIiIiIiIiIiDxcDrbc+IULF0hISMDHx8eq3cfHhwMHDqRpHYMGDcLf39+ShAoPD7es4851Jt13p5iYGGJiYiy3o6Ki0rwPIiIiIiIiIiKSfjavKfUgRo0axfz58/nhhx9wcXG57/WMHDkST09Py1KwYMEMjFJERERERERERO5k06RUvnz5sLe359y5c1bt586dw9fX966PHTNmDKNGjeK3336jXLlylvakx6VnnYMHDyYyMtKynDx58n52R0RERERERERE0sim0/ecnJyoWLEiq1atomXLloC50PmqVavo06dPqo/75JNP+Oijj/j111+pVKmS1X2BgYH4+vqyatUqypcvD5in423ZsoVevXqluD5nZ2ecnZ0zZJ9EREREREREHjcBby+zdQj3dPz+J1jJQ2LTpBRA//796dSpE5UqVaJKlSqMHz+e69ev06VLFwA6duxI/vz5GTlyJACjR49myJAhzJ07l4CAAEudKHd3d9zd3TGZTPTr148PP/yQokWLEhgYyPvvv4+/v78l8SUiIiIiIiIiIrZl86RUu3btOH/+PEOGDCE8PJzy5cuzYsUKS6HysLAw7OxuzTKcMmUKsbGxtGnTxmo9Q4cOZdiwYQAMHDiQ69ev06NHD65cucJTTz3FihUrHqjulIiIiIiIiIiIZByTYRiGrYPIaqKiovD09CQyMhIPDw9bhyMiIiIiIiKSpT0a0/desHUIaTMs0tYRPLC05lUe6avviYiIiIiIiIjIo0lJKRERERERERERyXRKSomIiIiIiIiISKZTUkpERERERERERDKdklIiIiIiIiIiIpLplJQSEREREREREZFMp6SUiIiIiIiIiIhkOiWlREREREREREQk0ykpJSIiIiIiIiIimU5JKRERERERERERyXRKSomIiIiIiIiISKZTUkpERERERERERDKdklIiIiIiIiIiIpLplJQSEREREREREZFMp6SUiIiIiIiIiIhkOiWlREREREREREQk0ykpJSIiIiIiIiIimU5JKRERERERERERyXRKSomIiIiIiIiISKZTUkpERERERERERDKdklIiIiIiIiIiIpLplJQSEREREREREZFMp6SUiIiIiIiIiIhkOiWlREREREREREQk0ykpJSIiIiIiIiIimU5JKRERERERERERyXRKSomIiIiIiIiISKZTUkpERERERERERDKdklIiIiIiIiIiIpLplJQSEREREREREZFMp6SUiIiIiIiIiIhkOiWlREREREREREQk0ykpJSIiIiIiIiIimU5JKRERERERERERyXRKSomIiIiIiIiISKZLd1IqICCADz74gLCwsIcRj4iIiIiIiIiIPAbSnZTq168fixcvpkiRIjz99NPMnz+fmJiYhxGbiIiIiIiIiIhkU/eVlNq5cydbt26lZMmSvPbaa/j5+dGnTx+2b9/+MGIUEREREREREZFs5r5rSj355JN8/vnnnDlzhqFDh/LVV19RuXJlypcvz8yZMzEMIyPjFBERERERERGRbMThfh8YFxfHDz/8QGhoKCtXrqRatWp069aNU6dO8c477/D7778zd+7cjIxVRERERERERESyiXQnpbZv305oaCjz5s3Dzs6Ojh07Mm7cOEqUKGHp89xzz1G5cuUMDVRERERERERERLKPdCelKleuzNNPP82UKVNo2bIljo6OyfoEBgbSvn37DAlQRERERERERESyn3Qnpf79918KFy581z5ubm6Ehobed1AiIiIiIiIiIpK9pbvQeUREBFu2bEnWvmXLFv7+++8MCUpERERERERERLK3dCelevfuzcmTJ5O1nz59mt69e6c7gMmTJxMQEICLiwtVq1Zl69atqfbdu3cvrVu3JiAgAJPJxPjx45P1GTZsGCaTyWq5vd6ViIiIiIiIiIjYXrqTUvv27ePJJ59M1l6hQgX27duXrnUtWLCA/v37M3ToULZv384TTzxBSEgIERERKfaPjo6mSJEijBo1Cl9f31TXW7p0ac6ePWtZ/vzzz3TFJSIiIiIiIiIiD1e6k1LOzs6cO3cuWfvZs2dxcEhfiarPPvuM7t2706VLF0qVKsXUqVPJkSMHM2fOTLF/5cqV+fTTT2nfvj3Ozs6prtfBwQFfX1/Lki9fvnTFJSIiIiIiIiIiD1e6k1KNGjVi8ODBREZGWtquXLnCO++8w9NPP53m9cTGxrJt2zYaNmx4Kxg7Oxo2bMimTZvSG5aVw4cP4+/vT5EiRXjxxRcJCwt7oPWJiIiIiIiIiEjGSvfV98aMGUPt2rUpXLgwFSpUAGDnzp34+PjwzTffpHk9Fy5cICEhAR8fH6t2Hx8fDhw4kN6wLKpWrcqsWbMoXrw4Z8+eZfjw4dSqVYt//vmHnDlzpviYmJgYYmJiLLejoqLue/siIiIiIiIiInJv6U5K5c+fn927dzNnzhx27dqFq6srXbp0oUOHDjg6Oj6MGNOlSZMmlt/LlStH1apVKVy4MN999x3dunVL8TEjR45k+PDhmRWiiIiIiIiIiMhjL91JKQA3Nzd69OjxQBvOly8f9vb2yepTnTt37q5FzNMrV65cFCtWjCNHjqTaZ/DgwfTv399yOyoqioIFC2ZYDCIiIiIiIiIiYu2+klJgvgpfWFgYsbGxVu0tWrRI0+OdnJyoWLEiq1atomXLlgAkJiayatUq+vTpc79hJXPt2jWOHj3K//73v1T7ODs737VwuoiIiIiIiIiIZKx0J6X+/fdfnnvuOfbs2YPJZMIwDABMJhMACQkJaV5X//796dSpE5UqVaJKlSqMHz+e69ev06VLFwA6duxI/vz5GTlyJGAujr5v3z7L76dPn2bnzp24u7sTHBwMwJtvvknz5s0pXLgwZ86cYejQodjb29OhQ4f07qqIiIiIiIiIiDwk6U5Kvf766wQGBrJq1SoCAwPZunUrFy9eZMCAAYwZMyZd62rXrh3nz59nyJAhhIeHU758eVasWGEpfh4WFoad3a0LBJ45c8ZSXB3MRdfHjBlDnTp1WLt2LQCnTp2iQ4cOXLx4ES8vL5566ik2b96Ml5dXendVREREREREREQeEpORNNQpjfLly8fq1aspV64cnp6ebN26leLFi7N69WoGDBjAjh07HlasmSYqKgpPT08iIyPx8PCwdTgiIiIiIiIiWVrA28tsHcI9HXd5wdYhpM2wSFtH8MDSmlexS/WeVCQkJJAzZ07AnKA6c+YMAIULF+bgwYP3Ga6IiIiIiIiIiDxO0j19r0yZMuzatYvAwECqVq3KJ598gpOTE9OmTaNIkSIPI0YREREREREREclm0p2Ueu+997h+/ToAH3zwAc2aNaNWrVrkzZuXBQsWZHiAIiIiIiIiIiKS/aQ7KRUSEmL5PTg4mAMHDnDp0iVy585tuQKfiIiIiIiIiIjI3aSrplRcXBwODg78888/Vu158uRRQkpERERERERERNIsXUkpR0dHChUqREJCwsOKR0REREREREREHgPpvvreu+++yzvvvMOlS5ceRjwiIiIiIiIiIvIYSHdNqUmTJnHkyBH8/f0pXLgwbm5uVvdv3749w4ITERERkcfAME9bR5A2wyJtHYGIiEi2ku6kVMuWLR9CGCIiIiIiIiIi8jhJd1Jq6NChDyMOERERERERERF5jKS7ppSIiIiIiIiIiMiDSvdIKTs7O0wmU6r368p8IiIiIiIiIiJyL+lOSv3www9Wt+Pi4tixYwezZ89m+PDhGRaYiIiIiIiIiIhkX+lOSj377LPJ2tq0aUPp0qVZsGAB3bp1y5DAREREREREREQk+8qwmlLVqlVj1apVGbU6ERERERERERHJxjIkKXXjxg0+//xz8ufPnxGrExERERERERGRbC7d0/dy585tVejcMAyuXr1Kjhw5+PbbbzM0OBERERERERERyZ7SnZQaN26cVVLKzs4OLy8vqlatSu7cuTM0OBERERERERERyZ7SnZTq3LnzQwhDREREREREREQeJ+muKRUaGsrChQuTtS9cuJDZs2dnSFAiIiIiIiIiIpK9pTspNXLkSPLly5es3dvbm48//jhDghIRERERERERkewt3UmpsLAwAgMDk7UXLlyYsLCwDAlKRERERERERESyt3Qnpby9vdm9e3ey9l27dpE3b94MCUpERERERERERLK3dCelOnToQN++fVmzZg0JCQkkJCSwevVqXn/9ddq3b/8wYhQRERERERERkWwm3VffGzFiBMePH6dBgwY4OJgfnpiYSMeOHVVTSkRERERERERE0iTdSSknJycWLFjAhx9+yM6dO3F1daVs2bIULlz4YcQnIiIiIiIiIiLZULqTUkmKFi1K0aJFMzIWERERERERERF5TKS7plTr1q0ZPXp0svZPPvmE559/PkOCEhERERERERGR7C3dSal169bxzDPPJGtv0qQJ69aty5CgREREREREREQke0t3UuratWs4OTkla3d0dCQqKipDghIRERERERERkewt3UmpsmXLsmDBgmTt8+fPp1SpUhkSlIiIiIiIiIiIZG/pLnT+/vvv06pVK44ePUr9+vUBWLVqFXPnzmXRokUZHqCIiIiIiIiIiGQ/6U5KNW/enCVLlvDxxx+zaNEiXF1deeKJJ1i9ejV58uR5GDGKiIiIiIiIiEg2k+6kFEDTpk1p2rQpAFFRUcybN48333yTbdu2kZCQkKEBioiIiIiIiIhI9pPumlJJ1q1bR6dOnfD392fs2LHUr1+fzZs3Z2RsIiIiIiIiIiKSTaVrpFR4eDizZs1ixowZREVF0bZtW2JiYliyZImKnIuIiIiIiIiISJqleaRU8+bNKV68OLt372b8+PGcOXOGiRMnPszYREREREREREQkm0rzSKlffvmFvn370qtXL4oWLfowYxIRERERERERkWwuzSOl/vzzT65evUrFihWpWrUqkyZN4sKFCw8zNhERERERERERyabSnJSqVq0a06dP5+zZs/Ts2ZP58+fj7+9PYmIiK1eu5OrVqw8zThERERERERERyUbSffU9Nzc3unbtyp9//smePXsYMGAAo0aNwtvbmxYtWjyMGEVEREREREREJJtJd1LqdsWLF+eTTz7h1KlTzJs3L6NiEhERERERERGRbO6BklJJ7O3tadmyJUuXLs2I1YmIiIiIiIiISDaXIUkpERERERERERGR9FBSSkREREREREREMp2DrQOYPHkyn376KeHh4TzxxBNMnDiRKlWqpNh37969DBkyhG3btnHixAnGjRtHv379HmidInIPwzxtHcG9DYu0dQQiIiIiIiKSTjYdKbVgwQL69+/P0KFD2b59O0888QQhISFERESk2D86OpoiRYowatQofH19M2SdIiIiIiIiIiKS+WyalPrss8/o3r07Xbp0oVSpUkydOpUcOXIwc+bMFPtXrlyZTz/9lPbt2+Ps7Jwh6xQRERERERERkcxns6RUbGws27Zto2HDhreCsbOjYcOGbNq0KVPXGRMTQ1RUlNUiIiIiIiIiIiIPj82SUhcuXCAhIQEfHx+rdh8fH8LDwzN1nSNHjsTT09OyFCxY8L62LyIiIiIiIiIiaaOr7wGDBw8mMjLSspw8edLWIYmIiIiIiIiIZGs2u/pevnz5sLe359y5c1bt586dS7WI+cNap7Ozc6o1qkREREREREREJOPZbKSUk5MTFStWZNWqVZa2xMREVq1aRfXq1bPMOkVEREREREREJOPZbKQUQP/+/enUqROVKlWiSpUqjB8/nuvXr9OlSxcAOnbsSP78+Rk5ciRgLmS+b98+y++nT59m586duLu7ExwcnKZ1ioiIiIiIiIiI7dk0KdWuXTvOnz/PkCFDCA8Pp3z58qxYscJSqDwsLAw7u1uDuc6cOUOFChUst8eMGcOYMWOoU6cOa9euTdM6RURERERERETE9kyGYRi2DiKriYqKwtPTk8jISDw8PGwdjohtDfO0dQT3NizS1hGIiMiDeBT+1oD+3oiI3EXA28tsHcI9HXd5wdYhpE02+HuT1ryKrr4nIiIiIiIiIiKZTkkpERERERERERHJdEpKiYiIiIiIiIhIplNSSkREREREREREMp2SUiIiIiIiIiIikumUlBIRERERERERkUynpJSIiIiIiIiIiGQ6JaVERERERERERCTTKSklIiIiIiIiIiKZTkkpERERERERERHJdEpKiYiIiIiIiIhIplNSSkREREREREREMp2SUiIiIiIiIiIikukcbB2AyOMq4O1ltg4hTY672DoCERERERGR+2eXmECVU3shJg5ymqCQPdiZbB2WoKSUiIiIiIiIiGRTIQc3MnTVNPyvXrjV6GGCxi5Q0tF2gQmg6XsiIiIiIiIikg2FHNzIlCUf43t7QgogyoDvbsD+ONsEJhZKSomIiIiIiIhItmKXmMDQVdPMv6fWacVNSDQyLSZJTkkpEREREREREclWqpzai//VC3dPekQZEJaQWSFJClRTSkRERCQbexQurKGLaoiISEbzvnY5bR2vaqSULWmklIiIiIiIiIhkKxFuudLWMaeuwmdLSkqJiIiIiIiISLbhEneT/21Pw0hhDxMUsn/4AUmqNH1PRERERERERLIFr2uXmb74A8qfPUycyQ4HIxGDVEbkNHYBO42UsiUlpSRrGOZp6wjubVikrSMQERERERGRVJSIOMZX339AgajzXHbJSc9W75I7Ooqhq6bhf/XCrY4eJnNCqqSj7YIVQEkpEREREREREXnE1T36F5OWfoJ77A2O5slP1zZDOZHbH4CVRatS5dRe5seMMNeQKmSvEVJZhJJSIiIiIiIiIvLI6rTtJ4asmo69kcjGQuXo1XIwka45Lfcn2tmzuVA5cNHIqKxGSSkREREREREReeTYJybw/qrpdN7+MwALyj7NeyGvEmev5NOjQkkpEREREREREXmkuMdEM3HpaOr9uw2AUXU6M7VqazBpWt6jREkpEREREREREXlk5I+MYMai4ZS4cIIbDs680aw/K4rXtHVYch+UlBIRERERERGRR0L5MweZvngEXtevEOGWm26th7DHr6itw5L7pKRUNhfw9jJbh5Amx11sHYGIiIiIiIhkZc8c+JPPln2GS3ws+70C6NpmKGc9vGwdljwAJaVEREREREREJOsyDF7dvJCB674GYFVQZfo2f4vrzjlsHJg8KCWlRERERERERCRLckyIY+SKSbT5ZxUAMyu24MP63Ui0s7dxZJIRlJQSEREREZuwS0ygyqm9EBMHOU1QyB7sdNUkERExy3Ujii9/+JiqJ/8h3mTHsIY9+fbJprYOSzKQklIiIiIikulCDm5k6Kpp+F+9cKvRwwSNXaCko+0CExGRLCHw0mlmLhpG4OWzXHVypc+zb/NHkYq2DksymJJSIiIiIpKpQg5uZMqSj5PfEWXAdzegLUpMiYg8xqqF7WbqDx+T6+Y1Tnl407XNEA55Bdg6LHkIlJQSERERkUxjl5jA0FXTzL+n1mnFTSjuoKl8IiKPoed3r+SjXyfjlBjPDr/idG/9Hhfccts6LHlIlJQSERERkUxT5dRe6yl7KYkyICwBAvSvqojI48JkJPLmum/ovXkhAD+XqMWAZ/oR4+hs48jkYdJfehERERHJNN7XLqet41Xj4QYiIiJZhkvcTcYuG0fTgxsA+Lx6O8bVehHDlOqYWskmlJQSERERkUxR4Eo4IQc3pq1zTk3dExF5HHhdu8T0xSMof/YwsXYOvN3kNRaXaWDrsCSTKCklIiIiIg+PYVDl1F66/v0jTx/egr2RaG4G7pp2Oh0PhexVV0pEJBsrEXGMGYs+IP/V81x2yUnPVu+ytWAZW4clmUhJKRERERHJcE7xcTQ9sJ6uf/9I2XNHLe3rAiqw068YfTYtwOAuxc5/j4XDCfCsK+TW9A0Rkeym7tG/mLT0E9xjb3A0T366thnKidz+tg5LMpmSUiIiIiKSYfJev8ILO3/hfzuW433dXD/qpoMTi0vXJ7Ricw57FQZgr08QQ1dNsy567mGCEGe4Afx2E04kwJRrEOICTzqCSaOmRESyg07bfmLIqunYG4lsLFSOXi0HE+ma09ZhiQ0oKSUiIiIiD6z4+eN0/etHWu5bi3NCHADh7nn4+slmzHsihMs5PK36/1q8BiuLVqXKqb3MjxlhriF1+3S9Ig6w5Ib5Knw/34QD8dDCBXJq1JSIyKPKPjGBIaum0Wn7MgAWlH2a90JeJc7e0caRia0oKSUiIiIi98VkJFLv6N90/ftHnjqxy9K+y7coMyo/yy/Fa971g0ainT2bC5UDlxT65LaDTjlgcyysjoEj8fDFNWjqCmX04UVE5FHjHhPNpB9HU/fYNgBG1u3Ml1VaaxTsYy5LfNU0efJkAgICcHFxoWrVqmzduvWu/RcuXEiJEiVwcXGhbNmyLF++3Or+zp07YzKZrJbGjRs/zF0QEREReWzkiL1Bx20/sWr6K8z8/gOeOrGLBJMdPxd/ilYvfsqzHT9jaam6D/7Nt50JajhDTzfws4ObwPc3YFE0RCdmyL6IiMjDlz8ygkXfvkXdY9u44eBMz5bv8GXVNkpIie1HSi1YsID+/fszdepUqlatyvjx4wkJCeHgwYN4e3sn679x40Y6dOjAyJEjadasGXPnzqVly5Zs376dMmVuVelv3LgxoaGhltvOzs6Zsj8iIiIi2VX+yAg6bv+ZDrt+xSPmOgBRzm7MeyKEr59sxmnP5P+7ZQgve+jmButjYF0s7I2HE9ehuQsU06gpEZGsrPyZg0xfPAKv61eIcMtNt9ZD2ONX1NZhSRZh86TUZ599Rvfu3enSpQsAU6dOZdmyZcycOZO33347Wf8JEybQuHFj3nrrLQBGjBjBypUrmTRpElOnTrX0c3Z2xtfXN3N2QkRERB4Nwzzv3cfWhkXaOgJrhkHF0/vp+vePND60CXvDPELp39z+hFZqwfdlGhDt5Prw47A3Qd3/klA/3IALiTDvBlSINxdCd9a37SIiWc0zB/7ks2Wf4RIfy36vALq2GcpZDy9bhyVZiE2TUrGxsWzbto3Bgwdb2uzs7GjYsCGbNm1K8TGbNm2if//+Vm0hISEsWbLEqm3t2rV4e3uTO3du6tevz4cffkjevHlTXGdMTAwxMTGW21FRUfe5RyIiIiLZg2NCHE0ObqDbXz/yRPhhS/ufhZ9gRuWWrC1SEcNkg0oQ/vbQw81cZ2pzLOyIg3/joaUrBNj8+1YREQEwDF7dvJCB674GYFVQZfo2f4vrzjlsHJhkNTb9y33hwgUSEhLw8fGxavfx8eHAgQMpPiY8PDzF/uHh4ZbbjRs3plWrVgQGBnL06FHeeecdmjRpwqZNm7C3t0+2zpEjRzJ8+PAM2CMRERGRR1vu6Eg67PqVjtt/xvfaJQBi7B35oXQ9Qiu14KBXgG0DBHA0mUdHFXeAH2/AFQNmR0NVJ2jgbL5fRERswik+jo9/nUSbf1YBMKPSs3xUryuJdsk/i4tky6+T2rdvb/m9bNmylCtXjqCgINauXUuDBg2S9R88eLDV6KuoqCgKFiyYKbGKiIiIZAXBF8Lo+vePtNq7Bpf4WAAi3HLz9ZNNmVu+CZdyZMGpjwEO8Io7/HrTPGJqSywc/W/UVH59+BERyWy5bkTx5Q8fU/XkP8Sb7BjWsCffPtnU1mFJFmbTpFS+fPmwt7fn3LlzVu3nzp1LtR6Ur69vuvoDFClShHz58nHkyJEUk1LOzs4qhC4iIiKPHZORSJ1/t9P17x+pfXyHpf0fnyBmVHqWn0vWevAr6D1sziZo4QolHOCnm+ZaUzOuQy0nqO1srkUlIiIPXeCl08xcNIzAy2e56uRKn2ff5o8iFW0dlmRxNk1KOTk5UbFiRVatWkXLli0BSExMZNWqVfTp0yfFx1SvXp1Vq1bRr18/S9vKlSupXr16qts5deoUFy9exM/PLyPDFxEREXkkucbepPXe1XT5eylBl04BkGCy47ei1ZhZqQV/FSj96F2mu5gj9LKH5TfNV+dbFwuH/xs15a1RUyIiD9XatfzwzQBy3bzGKQ9vurYZwqGsMN1bsjybT9/r378/nTp1olKlSlSpUoXx48dz/fp1y9X4OnbsSP78+Rk5ciQAr7/+OnXq1GHs2LE0bdqU+fPn8/fffzNt2jQArl27xvDhw2ndujW+vr4cPXqUgQMHEhwcTEhIiM32U0RERMTW/KLO03H7MjrsWkGum9cAuOrkyoJyjZhVsTmncj3iVy7OYQdtckCJOHNy6mwiTLsO9Z2hmhPYPWKJNhGRR0FoKPToQa74eHb4Fad76/e44Jbb1lHJI8LmSal27dpx/vx5hgwZQnh4OOXLl2fFihWWYuZhYWHY2d26skuNGjWYO3cu7733Hu+88w5FixZlyZIllClTBgB7e3t2797N7NmzuXLlCv7+/jRq1IgRI0Zoip6IiIg8liqcPkDXv3+kycENOBiJAJzI5UtoxRYsKtuQa9ntakhlHKGwvXk63+F4WBkDB/8bNZXbBlcMFBHJjhIT4d13YdQoAH4qUYs3n+lHjKM+d0va2TwpBdCnT59Up+utXbs2Wdvzzz/P888/n2J/V1dXfv3114wMT0REROTRExcHixfzw9dDqXD2oKV5U6GyzKz0LKuCKmfvKyHltIMOruYC6L/ehLAEmHINGrlARcdHb3qiiEhWEh0NHTvC99+bb7/3Hn1jq2CYlPiX9MkSSSkRERERySCXLsH06TBpEpw6RQUgxt6BpSXrElqpBft8itg6wsxjMsGTThDoAD/egBMJsOwmHIyD5q7goQ9PIiLpdvYsPPss/PUXODrCV19Bx44Yby+zdWTyCFJSSkRERCQ7OHAAJkyA2bPhxg1zm7c344o2ZE6FJo93fY/cdtApB2yOhVUxcOS/UVPPuEIZB42aEhFJq927oVkzOHkS8uSBH36A2rVtHZU8wvT1kIiIiMijyjDgt9+gSRMoWRKmTjUnpJ54wlx4NiyMCU+98HgnpJKYTFDdGXq6gb8d3AQW34BFNyA60dbRiYhkfcuWQc2a5oRUsWKwZYsSUvLANFJKRERE5FETHQ3ffmseGbVvn7nNZIIWLaBfP6hTR6N/UuNlD13dYH0srI+BffFw4jq0cIFijraOTkQka5o40fz3JTER6tUz15LKrS885MEpKSUiIiLyqDh9Gr74Ar78Ei5eNLe5u0PXrtC3LwQF2Ta+R4W9Ceo6QzEHWHIDzifCvBtQPh4au4CzEnoiIgDEx5uTUZMnm29362b+O+TkZNOwJPtQUkpEREQkq/vrLxg/Hr77zvwBASAgwJyI6toVPD1tGd2jy98eerjB6hjYFAs74+BYPDzrai6OLiLyOIuKgnbtYMUK8+3Ro+GttzQSVzKU/tqKiIiIZEXx8bBkCYwbBxs33mqvXdv8rXWLFmBvb6vosg8HEzRygeL/jZq6YsDX0VDVCRo4g6M+fInIY+jECXNB83/+AVdX85TxVq1sHZVkQ0pKiYiIiGQlV66YL689cSKEhZnbHB2hfXt4/XWoWNGm4WVbhR3gFXf47SZsj4MtsXAkHp5zhfxK/onIY2TLFvMXHxER4OsLP/0ElSrZOirJppSUEhEREckKLiaYEyFjCsD16+a2fPmgVy/z4udn2/geB84maO4KJRxg6U24mAgzrsNTTlDH2dbRiYg8fN99B506wc2b5iu5/vQTFCxo66gkG1NSSkRERMRWDAOO/ZeMOvRfrSjioEwZ8xS9F14wT5uQzFXUEV51gOU34J9485X6DsdDu3/Mz42ISHZjGDByJLz7rvl206Ywbx7kzGnbuCTbU1JKREREJLPFGbDnvyliEYm32os5wBcroH59FZK1NVcTtM4BJeJg2U0ITzRPnRwxAgYMUD0vEck+YmKgZ0+YPdt8u18/GDNG73OSKZSUEhEREcksVxPh71j4Ow6iDXObI1De0VxYO689NGhg0xDlDqUdoZA9/HQTDsfCoEGwdKn5w1tQkK2jExF5MBcvmguYr1tnTkJ9/jm8+qqto5LHiJJSIiIi8sAC3l5m6xDS5LiLjTZ8NgE2x8I/cZA0MMrTBFWcoIKTeVSOZF057aCDKxQeby42v2GDudbKmDHm0QUa1SYij6KDB81X2DtyBDw8zPWkQkJsHZU8ZuxsHYCIiIhItpRowP44CL0O067D7v8SUgXt4XlX6OsONZyVkHpUmEzQtSvs2QN16piL0ffqBU2awOnTto5ORCR91q6F6tXNCanChWHjRiWkxCaUlBIRERHJSDcN2BQDE6/BdzcgLMH8H1dZB3jZDbq6QSlHsFMy6pEUEACrV8O4ceDiAr/+ai5+PmeOuVCwiEhWFxoKTz8Nly9DtWqwZQuULm3rqOQxpaSUiIiISEa4lAi/3IRxV+G3GLhimEdBPeUEr7tDqxyQX0VjswU7O3Mh4B07oHJluHIFXnoJnn8ezp+3dXQiIilLTIS33zaP+oyPh3btzEl2Hx9bRyaPMSWlRERERO6XYcDxeJgfbR4ZtTUWYoF8dtDMBd5whwYu4KF/ubKlEiXMU14++AAcHOD7782jppYutXVkIiLWoqPNifPRo82333sP5s4FV1fbxiWPPRU6FxEREUmveMNctHxzLJxLvNUe7ADVnKCIvYpfPy4cHOD996FpU+jYEfbuhWefhc6dYfx48PS0dYQi8rg7exZatIC//wYnJ/jqK/jf/2wdlQigkVIiIiIiaXctEdbehPHX4Meb5oSUA1DJEXq7wYs5IMhBCanH0ZNPmj/wvfWW+fmfNQvKlTNPjRERsZVdu6BqVfP7U9688PvvSkhJlqKklIikyC4xgWphu2FPnHlqSqKKt4rIYyw8AX68YU5G/REL1w3wMEEDZ+ifE5q6Qj7Vi3rsubjAJ5/AH39AkSIQFgYNGsDrr5unzoiIZKZly+Cpp+DkSShWDDZvhlq1bB2ViBVN3xORZEIObmToqmn4X71wq9HDBI1doKSj7QITEclMiQYcioctsXA84VZ7fnvzFL2SDmCvEVGSglq1zKMT3noLpk6Fzz+HFSvg66/NIxZERB4mw4CJE+GNN8zFzevVM9e8y53b1pGJJKORUiJiJeTgRqYs+Rjf2xNSAFGG+dLm++NsE5iISGaJMWBLDEy6BgtumBNSJqC0A3TLAS+7QRlHJaTk7tzdYcoU+OUX8PeHQ4egRg1zceHYWFtHJyLZVXw89OljHqGZmAjdupmT4kpISRalpJSIWNglJjB01TTz76l1WnFTU/lEJHu6nAi/3oRxV2FFDFw2wAWo6QSvu0ObHFBAg8wlnRo3hn/+gRdeMH9A/Ogj82ipPXtsHZmIZDdRUdC8OXzxhbm23ejRMH26ubi5SBal/6xEBIAcsTdotWeV9ZS9lEQZEJYAAXr7EJFHh11iAlVO7YWYOMhpgkL2YGcyT3EISzBP0TsQD0k597x25il65RzBSSOi5AHlzg1z5sBzz8Err8DOnVCpEnzwAbz5JtirHpmIPKATJ6BZM3MS3NX11nuOSBanT5Uijxm7xAQKXQmnxPnjlIw4Tonzxyhx/jiFr4SnfSV/xpiL/Ba2B3cNuBSRrC3FOnk5TeaaUCcT4GzirfYge6jqBMG6gp48BG3amIsO9+gBP/0Eb78NS5fC7NkQHGzr6ETkUbVlC7RoARER4Odnfl+pVMnWUYmkiZJSItmY542rlDh/3LxEHKPk+eMUu3CCHHExKfa/5JKTPDev3nvFRxPg6A3z73nszCMOCtlDYQfIbdIHORHJMpLq5CVz1YCt/9XIc8A8IqqqE3hrxIo8ZL6+8OOPMGuWuebLxo3wxBPw6afQq5f+hopI+nz3HXTqBDdvmt9LfvoJCha0dVQiaaaklEg24JAQT5FLp6xHP0Ucx+/axRT733Rw4mC+whzwCuCAdwAHvAI46BXAFRd3/pzaDd+rF1KvKeWKudjvyUQ4lwiX/lt2/vfhzt1kHkFVyMGcqPKx0z/YImIT5jp5X5p/T62TM9DHDdyVjJJMZDJBly5Qvz507gxr10Lv3rBkCcycCQUK2DhAEcnyDAM+/th88QSApk1h3jzImdO2cYmkk5JSIo8Sw8Dr+mVKRpin3BU/f5yS548TfOEkTonxKT7kpKcPB7wC2O8VwAHvQA54BXA8tx+Jdil/ABveoAdTlnxMIql8iGvuCiUdzb/fNOBkPJxIMNdkOZ0A1wzYG29ewFwkuOB/CarC9uBvrytWichD43HzGuXOHuaJs4eod/Qv/K+mnJy3iAEuGOCeKeGJWCtcGFatgkmTYNAgWLkSypQxX8r9pZf0pY6IpCwmxjwN+Ouvzbf79YMxY1SfTh5JSkqJZFHOcTEUvXjSkoBKGv2U90ZUiv2vOrlywCvQMvJpv1cgh7wKc805R7q2+2vxGvRq+U7y+iseJmjscishBeBigqKO5gUgzjAnpsIS4ES8uVbLTeBwvHkB87tOgf+m+xVygIL2KiIsIvfFKT6OEuePUf7MQZ44e4jyZw8TdOlU+ld0VVcUFRuys4O+faFRI/MUnK1boWNH86ipqVPBy8vWEYpIVnLxormA+fr15iTUxInmqb8ijyglpURszTAoEBVBidum3ZU4f5zAy2ewNxKTdU8w2XEst/9tU+/MiahTHt4Z9o3qr8VrsLJoVaqc2sv8mBHWV6q6G0eT+ap8AQ6AMyQaEJ5oTlCF/ZesijbgeIJ5IRZMgJ+dOUFV+L9kVQ4VTxeROxgGAZfPUP7sIXMC6swhSkUcxTkh+SjR47n82OVXjCsu7nTaseze686pxLhkASVKwIYNMGoUDB8OixfDn3/CtGnw7LO2jk5EsoKDB81X2DtyBDw8zPWkQkJsHZXIA1FSSiQzRUWZL9O6ezcjfvuJEhHmKXgesdEpdr/k6sH+pMSTVwD7vQM5nLcgMY7ODz3URDt7NhcqBy6O9+6cGjuTebqevz1Uxzz3/ULirQTViXiINOBMIpyJhc3/PS6f3a3C6YXtwVNJKpHHTZ7oyP+STwctiahcN68l63fJ1YNdfkXZ5VeMnX7F2eVXlMs5PAFzTamnj2y5e508j/+S7iJZgYODuT5M06bm0VL//AMtW5pHUE2YAJ6eto5QRGxlzRpo3RouXzZP/V22DEqXtnVUIg9MSSmRhyEhwfwNxu7dt5Y9e+DYMUuX/93WPdbOgSP5CprrPnkFctCrMPu9Aznvljt71ZMwmcDL3rxU/K8tMvG/mlT/jaY6n2hOXF1IhO3/FU/3NN0qnF7Y3py0yk7HReQx5xJ3k9Ln/rUkoMqfPUTByHPJ+sXYO/KPT5A5AeVfnJ1+xQjL5Zvq+0Ginf296+Q1drn3KFCRzFahAvz9NwwZYr4q3+zZsHo1hIZCgwa2jk5EMtvMmdCzJ8THQ7Vq5um9Pj62jkokQygpJfKgLlwwJ5xuT0D984/5sqwpyZ8fypVjyiW3/0ZBBfBvngLE2z+mL0dPOyhnZ74cO0D0fyOpkhJVZxPNo6n2xJkXgBz/jWxIqksVH2/+dllEsjy7xASCLp6i/Nn/ElBnDlH8/HEc7piunIiJo3kLmEc/+Rdjp18xDnoVJs4+faM301UnTyQrcXaG0aOhRQvzSKmjR6FhQ+jTx9yeI301I0XkEZSYCO+8Y37NA7RrZ05Ou7raNi6RDKRPcSJpFRsLBw5YJ59274azZ1Pu7+oKZctCuXK3lrJlIU8eAEa/nYY6J4+jHHZQwg5K/PdBMdYwF0xPGkl16r+6VAfizQsxMC8X1KgBtWqZl6pV9cdaJIvwuXqB8mcO/TcC6iBlw4/gHnsjWb8It9yW0U87/Yqxx68oV53dMiSG+66TJ5IV1KwJO3fCwIEwZYr5Sn2//mq+6la1araOTkQeluho+N//zPXlAN5/H4YNM18cQSQbUVJK5E6GYb4S07kEOJcIEYnm3z9yM4/ISUmRItbJp3LlzG26LOuDczJBkIN5AUgw4EzCrdFUJ+Ph+nXzZbRXrjT3cXSESpWgdm1zkqpmTciVy2a7IPK4cI+Jpmz44f9GQJmviOd77VKyftcdXdjjG3xbEqo44TnzPtRpuRlSJ0/EVtzd4YsvzPWlunaFw4fNf9sGDTJ/SHVysnWEIpKRzp41j5L8+2/z6/urr8wJKpFsSEkpebzFGbeSTucSIeK/nzdSujx4ornA6J3Jp9KlIWfOTA/9sWVvgoIO5qUm5iRi6z/Nl8Vdvx7WrTP/Id+0ybyMHm3+oFu2rDlBlZSo8vOz9Z6IPNri4sxTl7duhS1b+O2n1QRfPIkd1u+f8SY7DnoF/FeIvBg7/YtxJG9BEu2UtBdJt0aNzK+7vn3h229h5EhYvtw8aqpcOVtHJyIZYdcuaN4cTp6EvHnhhx/M/7uKZFNKSsnjwTDgym2jn84lmJNRFxNT7m/CXEzb2w587MHHDkYdgIIFVWA7qzGZbiUIe/c2P9f//nsrSbV+vfkb5aTplpMnmx8XFHRrul+tWhAcrOdWJDWGYb5Qw38JKLZuhe3brWrnFfvv50lPn/8SUEXZ6V+cvd5B3HBysU3cItlR7tzwzTfmUVOvvGL+AFupEnzwAbz5pmosijzKli2D9u3h2jUoVsx8OzjY1lGJPFT6qyXZz03j1oin20dAxabSP4cJfO3A+7/kk489eNmBwx0JikKFHnrokgFMJnPCKSgIOnc2t4WHWyepdu0yF4w9ehRmzTL38fW1TlKVLavpl/L4ungR/vrLOgl14ULyfrlyQZUqUKUKXffbsduvKBfccmd6uCKPpdat4amnzFfk+vFHGDwYli41X6mvaFFbRyci6WEYMHEivPGGubh5/fqwaJE5CS2SzSkpJTZll5hAlVN7ISYu/YVnEw3zSKfbRz6dSzBfqS0l9piTTUkjn5KSUO4qFpjt+frC88+bF4ArV2DjxltJqr/+MieuFi40L2Ceqlmz5q0kVaVK5ishiWQ3N2+aiygnJZ+2boUjR5L3c3KC8uXNSaiqVc0/g4MtBVdX6+INIukWkBGvm+Iv0+aZQIb8Pg2PTZuILl2WkXW78G2FZzBMD/4/zvFRTR88RpEMlCGvm4csXa+b+Hh4/XVz3TiAbt3MFzVwVA1EeTwoKSU2E3JwY9ov0X09heRTRCIkpLJyD9Ot5FPSzzx25npEIrlywTPPmBeAGzfMiamkmlQbN0JkpLlOx/Ll5j4uLuYP4klJqurVVUtMHj2JiXDokPUIqF27zPWh7lSsmHUC6oknlJgVyYpMJhaVbcjGwuX4dPl4ap7YzYiVU2l0aDMDn3mdsx5eto5Q5PEzzDNt/W4a8H00HPnvQ01DZ8j/HXy08OHFdrthkZmzHZG7UFJKbCLk4EamLPk4+R1RBnx3A6rEmxNISdPvrqcy+skRc9LJ+44RUK5KPkk6uLqaC6DXrg3vvmv+xmrXLuspf+fPwx9/mBcwT+0rX/5W4fSnngIv/eMvWUx4uHUC6q+/zAnXO3l5mZNPSQmoypU1ZUDkEXPGw5uX2n1Ix+3LeHvtLGqd2MmvM/swrGEPFpeur7qJIlnNlUSYGw3nE82fylu5Jv9iXuQxoKSUZDq7xASGrppm/j21TltT+NY+j531tDsfe8ht0j9ZkvEcHKBiRfPSr595nv/Bg9ZJquPHYds28zJunPlxJUpYX+GvcGFb7oU8bq5dM5+PSVPwtmwxX7nnTq6u5nM7KQFVtaq5Zp7eS0UeeYbJjtkVm7Mu8Ek++/kzKpw9yGfLxhFyaBPvhPTholsuW4coIgCn4mH+DfMX7+4m6JAD/FXLVB5PSkpJpqtyaq/1lL3UlHCAog63Co876QOT2IjJZE44lSgB3bub206etE5S7d0LBw6Yl+nTzX0KFrw13a92bShZUh/8JWPEx8O+fbdGQG3ZYj4HE++4oqjJBKVLWyegSpfW1blEsrljefLT5qVP6Lnle/r9OZeQw5upeHo/74b05tdiNdK3srROQ7I1TUOSR8U/cbDkhrkMiY+dOSHlqRq38vjSf6WS6byvXU5bx1KOUFZDWCWLKlgQXnjBvID5amV//nkrSbVtmzlxNXeueQHIm9c8zS8pUVWhgopYyr0Zhvlcuj0BtW0bREcn71uggHUC6sknVftM5DGVYGfPF9XbsrZIJcYu+4yS54/z5Q8f833pegxv2JMoF3dbh5ilZbti2mJ7hgHrY2FNjPl2MQdo7aov3uWxlyVSspMnTyYgIAAXFxeqVq3K1q1b79p/4cKFlChRAhcXF8qWLcvypELE/zEMgyFDhuDn54erqysNGzbk8OHDD3MXJB0i3NNYpySn3qDlEZI3Lzz7LIwZY04aREbC77/DkCFQr555ytTFi+bLdr/5pjlhkDs3PP00fPABrFmTcpIhJQkJsHYtzJtn/pmQWsV/yXQZ8dxcuQIrV8JHH0GLFuDnZ54K2rat+fxav958rnh4QIMG5svAL1kCp0+bk1eLFsHAgVCnjhJSIsI+nyI823EcX1RrQ4LJjtZ717BiZh+eOrbD1qGJPD7iDfjx5q2EVFUnaKeElAhkgZFSCxYsoH///kydOpWqVasyfvx4QkJCOHjwIN7e3sn6b9y4kQ4dOjBy5EiaNWvG3LlzadmyJdu3b6dMmTIAfPLJJ3z++efMnj2bwMBA3n//fUJCQti3bx8uLi6ZvYtyh60FSnMmZz58r15IPSvqYYJCmlctjzA3N3PCoEED8+3YWNi+3XrK35Ur5sTV77+b+zg6mmv9JNWkqlkzebHpxYvNlw0+depWW4ECMGECtGqVKbtmS1n5m+sUryh6r+cmNtZcVP/2YuQHDybv5+Bgvvrd7VfDK14c7LLEd0siksXFOjjySZ3O/B5Ulc+WfUbAlbN8+937zH6yKaPqdOGGk/4/FskIdokJVDm1F2LizF+wF7I3X2FvwQ0ISwAT0MQFKjvZOlSRLMNkGEYqlzXLHFWrVqVy5cpMmjQJgMTERAoWLMhrr73G22+/nax/u3btuH79Oj///LOlrVq1apQvX56pU6diGAb+/v4MGDCAN998E4DIyEh8fHyYNWsW7du3v2dMUVFReHp6EhkZiYeHRwbtqW1k1Q9wt199L8WPVG2z4NUnMrhWQVZ9bu503OUFW4dwb49iHYnERHMNoNuTVKdPW/cxmaBMmVs1qa5ehR49zMO/7+wH5hEy2TwxlVVfN2l6TyvhAJcS4XQinE4wL+EJ5poSd8ptgvz2txY/e3DI4G9T9Z6WdT2Gz80j8bxAtnhuXGNvMnhtKB13mLd9LLcfA5r2Z3v+kin213OTdT2u0/ey6nOT4pdTbibAgOuAM9AmBwTbfFzILY/j6+YxfU+zhbTmVWz6ioiNjWXbtm0MHjzY0mZnZ0fDhg3ZtGlTio/ZtGkT/fv3t2oLCQlhyZIlABw7dozw8HAaNmxoud/T05OqVauyadOmNCWl5OH7tXgNerV8J/kbt4cJGrtkvYSUSEazs4OyZc3Lq6+aE03HjlknqQ4dgj17zMsXX6S+rqQkVc+e5hE1jo7m9ZtM5p93/n63+zK6373WkbQ8wtJ0RdHvb5j/4sakcJ/r7QkoO/PPHBoBJSIPxw0nF4Y06sVvRavx6fLxBF4+y8I5g/iyaivG13yRWAf9D/bIUBH6LOP2L6esXP/vf7QcQCc381XERcSKTZNSFy5cICEhAR8fH6t2Hx8fDhw4kOJjwsPDU+z/f/buO67G9/8D+PtuEam0RJOMIiLRkGTPECpbKLuPWUZkz4zsmb1piAhlj8oemUVCGaU0NV+/P/qd+3OO8hnfj3NOnOv5eHwfH+77Pn3fztV9Xdf9vq/x4cMH/rzg2I+u+V5+fj7l5//5pJCZmfnv/iHM/+RsAzs6X8+aWr6Lo8P5C/8c4ir3az+gMr8+6b7l0SLSciZydibt7HSyehdHLd/FkeOrO1Q7PfmvP5qaWrqu1a9GkKj6BwmwO3lFBI4jcByVcHIEIirh5KiE4whl/s4R6P+v4+j//yv6uT+v+fM6/P/nS0Q+L3zd///s/79OPTfz73cULf7//8lT6agn4VFQ1X/9xBzDML+ea7WbUeeRG2lu5FbqG3eRxkUfp7YJt2lKjyn0VKdO+dOQWB+tQmBlU7H8o5dT8hyRFnvhxDDlqUBjB6Vn6dKlNH/+fGmHIRa/xrDenkQ082+v+t38GmVDRPT7v936XoUsm0OH/tzp76/Urk2koVE6PbCkpHQUleDP3//9R3/+L9f9L4B/vCC45v/2/1AxLF5M5O392+64WCHvm3KxOq1ikr1yIaooZeNWul7hmDFk9jmRzuyfSuTiQnTlisyuX0hUUcqmHDK+tiTRD8qmuJgoP1/0fwUFkjn25QvR372cygJRuzAiR0exfCcVRYW9b0TIZntTkUk1KaWlpUXy8vL08eNHkeMfP34kXV3dcj+jq6v7l9cL/vvx40eqWbOmyDVNmzYt92fOnDlTZEpgZmYmGRgY/Ot/D8MwjNgI1Wd/aedO6XZ4BEkqSSfDpHnds2dEAQF//93Y2f22CSmGYX5xffoQ2duXTgMPDSU6eLDsNe/fE/XrJxPrF1ZYwcGlZfD9SyBJlg0gnuTOf/18SYl4/90/Q0qKtCNgmApJqkkpJSUlat68OUVFRVHv3r2JqHSh86ioKJowYUK5n7G1taWoqCiaNGkSf+z8+fNka2tLRES1a9cmXV1dioqK4pNQmZmZFBMTQ2PHji33Z1aqVIkqVar00/5dDMMwP13r1qVvQt+/L39EEseVnm/dWvKxfR+HvIytl1BcXPogUNHLhmEY5q/o6BAdO1b63/T0sucF9dvYsUTa2rJX10tbcTHRmDHltzOCY6NGEWVmEhUViW+EUGGhZP/d/6tKlUT/p6T013//L8eePiWaPPnvY/qnLxgZRsZIffrelClTaNiwYWRlZUUtW7akgIAAysnJoeHDhxMR0dChQ0lPT4+WLl1KREQTJ06kNm3a0KpVq6h79+50+PBhun37Nm3bVjqPl+M4mjRpEi1atIjq1atHtWvXpjlz5lCtWrX4xBfDMMwvR16+dGh+v36lSQ7hTqlgPaKAAPaQIA2sbBiG+V1cu1Z+QkrYp0+lO8IyFU9aGtH/P0NJjKLiz0/y/NdjCgqSXauxQweiVavYyymG+R9JPSnl5uZGnz9/Jj8/P/rw4QM1bdqUIiIi+IXKk5KSSE7uz0Xh7Ozs6ODBgzR79myaNWsW1atXj0JDQ8nc3Jy/xsfHh3JycmjUqFGUkZFB9vb2FBERQZUrV5b4v49hGOan6dOndEROeWtJBASw6RTSxMqGYZjfwT+dXlSjBlG1auKNhRGVlUX03RIm5WrcmMjYWDKJICWl0o1IZB17OcUw/wkH/K8r0/6+MjMzSU1Njb5+/UqqqqrSDodhGEZUcTHR1aulDw81a5a+eWMdnYqBlQ3DML+yS5eI2rb9++suXvztF2yucFjZVHzlLUJvYMBeTjEy65/mVVhSqhwsKcUwDMMwDMPInOLi0lE2fzcN6fVrlnCXNFY2vwb2copheP80r8LGWzIMwzAMwzAM8+c0JKKya/KwaUjSxcrm1yAvXzpSbcCA0v+y8mCYv8WSUgzDMAzDMAzDlBKskaenJ3pcX7/0OJuGJD2sbBiG+Q2x6XvlYNP3GIZhGIZhGJnGpiFVXKxsGIb5BfzTvIrUd99jGIZhGIZhGKaCEUxDYioeVjYMw/xG2PQ9hmEYhmEYhmEYhmEYRuJYUophGIZhGIZhGIZhGIaROJaUYhiGYRiGYRiGYRiGYSSOJaUYhmEYhmEYhmEYhmEYiWNJKYZhGIZhGIZhGIZhGEbiWFKKYRiGYRiGYRiGYRiGkTiWlGIYhmEYhmEYhmEYhmEkTkHaAVREAIiIKDMzU8qRMAzDMAzDMAzDMAzD/FoE+RRBfuVHWFKqHFlZWUREZGBgIOVIGIZhGIZhGIZhGIZhfk1ZWVmkpqb2w/Mc/i5tJYNKSkooOTmZqlWrRhzHSTuc315mZiYZGBjQ27dvSVVVVdrhMEJY2VRcrGwqLlY2FRcrm4qJlUvFxcqm4mJlU3Gxsqm4WNlIFgDKysqiWrVqkZzcj1eOYiOlyiEnJ0f6+vrSDkPmqKqqssqhgmJlU3Gxsqm4WNlUXKxsKiZWLhUXK5uKi5VNxcXKpuJiZSM5fzVCSoAtdM4wDMMwDMMwDMMwDMNIHEtKMQzDMAzDMAzDMAzDMBLHklKM1FWqVInmzp1LlSpVknYozHdY2VRcrGwqLlY2FRcrm4qJlUvFxcqm4mJlU3Gxsqm4WNlUTGyhc4ZhGIZhGIZhGIZhGEbi2EgphmEYhmEYhmEYhmEYRuJYUophGIZhGIZhGIZhGIaROJaUYhiGYRiGYRiGYRiGYSSOJaUYhmEYhmEYhmEYhmEYiWNJKYZhmAqE7T3BMP8eu28qJlYuDMMwjCSUlJRIOwTmP2BJKUYsWMXAMP8bjuOkHQJTju8frtnDdsUiuG++fPki5UgYgU+fPvHlsmPHDvr27ZuUI2IEWB+NYf49dt9UXMXFxSQnV5rWePTokZSjYf4XLCnF/HQlJSV8xXDq1Cm6du2alCNihJX3MM0a2oolMDCQJkyYIO0wmP8HgDiOowsXLpCfnx8VFxez5GEFcfLkSXry5AkREc2cOZPWrFlDhYWFUo6KiYqKombNmtGTJ09o0qRJNHHiREpJSZF2WAyJ9tECAgJo1apVrA9QgQj6aM+ePePrNkb6hO+b+Ph4unXrFn39+pXy8/OlHBlz7NgxWrFiBRERTZkyhUaOHEmZmZlSjor5t1hSivmpAPCV9vTp02nq1Kn0+PFjSktLk3JkDNGfD9exsbG0fft2Wrx4MT1+/JgvM0b6CgsL6eHDh/T48WNph8LQn/dMUFAQubq6UkZGhshbODZiSnrS09Np8+bN5ODgQO7u7hQQEEAuLi6kqKgo7dBkXvv27UlPT48cHBxo586ddO3aNapduzZLflQAgvbex8eHVq5cSUVFRfTp0ycpR8UQ/dnehISEUJ8+fSgsLIyVTQUg/Gzj6+tLzs7O1L17d+ratStNmzaNPn78KOUIZdunT5/I19eX2rZtS4GBgbRjxw5SVVWVdljMvwWGEYPFixdDW1sb165dQ3FxsbTDYYQcP34cNWrUQLt27dCjRw9wHIeNGzciNzdX2qHJvJKSEgBAYmIiqlatiu3bt0s5IgYAoqOjoaamVqY8ioqKpBQRIxAfHw89PT0oKioiKCgIAFBQUCDlqGRXcXExX48tXLgQVapUgb6+Pu7evYvCwkIpR8cIbN++HVpaWrh37x5/rKioSKT8GOk4deoUlJWVsX79enz58kXa4TBCVqxYAR0dHZw/fx4A4Obmhho1auDmzZtSjkw2CT9ftm7dGnJycpg0aZIUI2L+CzY8gvkpiouL+T+npaXR6dOnafXq1dSqVSt6//49RUZGkoeHB82dO1eKUTKPHj0iLy8vWrx4MUVFRdH+/fuJiOjz58+krKws5egYwZQwIyMjGjt2LJ09e5YyMjLYaBwpu3XrFrVu3Zo8PDwoPT2dQkNDqV+/ftSyZUs6dOiQtMOTOcL3w5cvX6hBgwZkZ2dHEydOpEePHpGioiIVFxez+0YK5OTkiOM4WrRoEd28eZPu3btHxsbG1K9fP4qOjhbpKzDSAYCeP39OAwYMoKZNm9LTp09p27ZtZGlpSe3ataMDBw6wcpICAPT161dau3YtzZ49myZMmEBKSkr0+vVr2rhxI2trpAgA5eTk0IULF2jRokXUoUMHOnv2LIWHh9PChQvJxsaG8vPz2bp5EgSh0Wv79u2j4uJimjFjBq1du5aWL1/O2v9fkIK0A2B+fcXFxSQvL09ERCkpKaShoUGVKlWiixcvUvXq1SkwMJA+fPhA6urqdPjwYcrIyKC1a9dKOWrZ9OnTJ7KwsKCRI0fSy5cvqV27duTp6cknC798+UIaGhr8EHJGfITXJ1i+fDl9/PiR3NzcyNramoiIHB0dadCgQfT8+XOytrZmZSJhwt+3qqoqhYeH044dO+jo0aOkpKREGhoa1KRJExo5ciQ5ODiQnp6elCOWDcL3zZQpUyg2NpZ27dpFhYWFNGPGDOratStFRESQubk5/5mPHz9SjRo1pBWyTBC+X8LDw2nXrl104MABql+/Pl29epVsbW1p2LBhtH//frK1tSUiooULF5KPjw9VqlRJmqH/9gRlI/ivoJy2bNlCderUoX379pG+vj45OzvT7du3yd/fn3r37k0qKipSjly2cBxHampqRESUnJxMnz59oiVLltD9+/cpKSmJ3r17Ry9evGAvdyVEuE7jOI7k5eXp27dvZG9vT2fPnqV+/fqRv78/eXp6Un5+Pu3fv59MTU2pVatWUo789yfcD1i9ejVt2rSJjh8/Tk2bNqVatWqRl5cXEZUuIyNw8+ZNvu1hKigpjM5ifiPnz5/HjBkzAADjx4+Hk5MTMjMzsWzZMjg4OEBJSQnTp0/HpUuXAACTJ0/GiBEjpBmyTNuzZw8aNmyIFy9ewNjYGKNGjeKHv546dQoDBgxARkaGlKOULSdOnMDhw4dRr149tGjRAl26dMHdu3dRXFyMiRMnokuXLmxqpQQJpq5kZ2ejpKQE+fn5KCkpweTJk2FgYAAPDw9cv34dAJCeng4LCws8evRImiHLpJSUFDg7OyMqKoo/dv/+ffTs2RMGBga4f/8+AKB///5YtmyZtMKUOadPn8aoUaPg5+cHAMjLy+PP2draok6dOli1ahU6deoEY2NjNgVWzISnt3z9+hXp6ekAgMLCQowePRqNGzfGypUr+Trsxo0bsLGxQXJysjTClXlFRUWYO3cumjVrBnl5eTg7O2P37t3IysrC1KlT0b17d3bPSIDwffP27Vv+z23btkWzZs2gpqaGHTt2iFzTtm1b7NmzR6JxyrpHjx7B09MTx48fFzm+ceNGyMvLY/78+Xj69Cl69eqFzp07s6nJFRwHsPFtzP+moKCAZs6cSVeuXKHKlSvT48eP6fr169SwYUMqKCig9PR0ys7OJhMTE/4zjo6OZGVlRStXrpRi5LIB//+WJy4ujrKzs8na2po+fPhAgwcPpps3b1K/fv1oz549/BuH6dOn08OHD+ngwYNUvXp1aYf/2xJ+w7No0SLy8/Oj9PR0+vbtGz1+/JiWLVtGnz9/JjU1NdLT06PExETat28fmZiYiHyW+fkE90xERARt3bqVvn79SsrKyrR27VqqW7cupaWlkaamJn/9jBkz6NSpU3Tp0iXS0tKSYuSyZcOGDbRixQqqVasWHTp0iGrXrs2fe/jwIc2bN4/CwsLI0tKSUlNT6fnz52zxcwl49+4ddevWjV6+fEmDBw+m7du3ExFRfn4+PxqqX79+lJGRQUpKSnTixAlSVFRk9ZqYfD8a98yZM5Senk56enq0atUqMjMzo5ycHKpatSoRlY567969O1WuXJlCQkLYyFwxE7Q3d+7coQcPHlBRURFZWVmRpaUlPXr0iBITE8nJyYm/ftiwYaSoqEjbtm1j94sYCd83CxcupIiICPL39yc7Ozt68OABubm5kZqaGsXExFBBQQHl5eXRwIEDKTs7my5cuMDPHGHE6+TJkzRs2DBSUlKiXbt2UdeuXUVGtwUGBpKnpyeZmZmRoqIi3bp1i/UDKjppZsSYX19xcTFat24NjuMwatQo/rhwNjo7OxuxsbHo1KkTmjRpwhY7lQDB93/8+HEYGRlh8eLFSExMRFFRERYuXIj69etjypQpSE1NxZMnTzBjxgxUr16djfgQM+H74tGjR1i+fDkiIiLKXHf27FnMnTsXqqqq4DgO48ePl2SYMu3EiRNQVlbG/PnzcfjwYbRt2xYqKiqIj4/nr4mKisKoUaOgoaEhslAwIxnPnz+HhYUFlJSUyl1g9tOnT9i9ezf8/f359oa1Oz+foD4Trteio6Ph4OCABg0aICwsjD+en5/P//nz58/8Z1i5iN/s2bNRo0YNBAYG4t69e9DR0YGNjQ0+fPgAAMjJycGePXvQsWNHWFhY8BsFsE1qxO/48ePQ0tJCly5d0KZNGxgbG2PJkiUi1yQlJcHb2xvVq1fH48ePpRSp7Jk5cyZq1KiBY8eO4eXLlwBKR37u3bsXampqsLCwgIODA1q1aoWmTZvy9w0bySY548ePh7y8PKZOncqPAhVuj+Li4nD58mW+TFh7U7GxpBTzrwl3JlNTUzFp0iQMHz4cdnZ28PX15c8LKuijR49iwIAB6NKlC6u0JejChQuoWrUqNm/ejK9fv/LHCwoK4OPjg+bNm0NRURFNmzZFo0aN2MO1GM2cOVPk7xEREeA4jt+hEii9r76/L168eIH58+fDxsYGz58/l1i8siorKwvt27fnp3u9ffsWtWvXFkm4p6WlYcWKFejWrRtL4krAjx6MExISYGJiAltb27+dasTam5/v+2lhBQUFfPt+/fp12Nvbw8nJCWfPnuWv+/6BgE2lEL/ExEQ0a9YMp0+fBgCcO3cO1apVw5YtW/hrkpOTMW/ePAwbNowlccVMuC569OgRdHV1sWnTJgBAbGwslJWVMWXKFP6aM2fOYOjQoWjQoAHro0nQw4cP0aBBA5w5c6bMucLCQrx69Qo+Pj6YO3cutm7dypIeYvZXCXIPDw/Url0bW7duRWZmJn/99+0L6wdUfCwpxfwrP6oYsrOzMW3aNFhbW4skpoDSTPXNmzf5z7JK++cTnvNeUlKCkpISjB49GiNHjhS5TvC2uqioCJ8/f0ZYWBji4uL4N6bMz3fnzh04OjqK/N4/ffoUkydPRqVKlfh1CQTlJiD487Nnz/i3dYx4ffr0CbVr18aLFy/w+fNn6OnpiSSk9u/fj5ycHGRnZ7O11yRAuL25fv06QkJC8ODBAz4J9fLlSxgZGaFNmzZISUnhr2XJDvESLpfly5ejXbt2sLOzg7OzM98WXbt2Da1bt0bPnj1x7tw5aYUq8x48eABjY2MAQHh4OFRUVLB582YApcnEwMBAAKUjQAT3DXt4+/lOnTrF/1nQFwgJCUHr1q0BAK9fv4ahoSHGjBnDX5eQkIC8vDyEhoYiKSlJsgHLuHPnzkFHR4evz4T7Z4Lk+/fYfSMewu3NoUOHMGvWLKxYsQIhISH88WHDhqFevXrYtm0bn5hifj0sKcX8T9auXYuhQ4fCy8uLnz6RmpoKb29v2NnZYerUqUhNTYWjo6PIwuZsOPjPt3LlSnh6epZZDLtbt27w9PQEUPZ7f/bsmcTiY/58SD5y5Ah/LD4+HmPGjIGioiKCg4P568p7oG7Tpk2ZIf3Mfyf4rr99+8Yfc3Jywrx58/gHBEEH9NOnT+jduzcOHz4slVhlmY+PD2rWrAkjIyNoaGigS5cu/MiP+Ph41K5dG23btsW7d++kHKls8fX1haamJgICAjBr1iy0atUKWlpaiI2NBQBcvnwZjo6OaNWqFWJiYqQc7e+vvLYjLy8PNjY2GDduHKpVq4Zt27bx5x4/fgwbGxtcuXLlL38G89/cvn0bhoaGGDZsmMjxsLAw9OjRA3FxcTAwMMCoUaP4xMb169f5JRYY8SrvZWBMTAyMjIwQGRnJnxOUzc6dO0WOM5Lh7e0NHR0ddO3aFVZWVtDU1MS0adP48+7u7jA1NcWaNWuQk5MjxUiZ/xVLSjH/iHBSY/bs2dDS0oKLiwtatWoFdXV1fl2ctLQ0zJkzBw0bNoSenh6aN28uspYE8/MFBwfzSSbhaXr9+/eHlZUV/3dBY/v582fMnj2bDQWXsMTERHAch+7du/PHEhISMG7cOKipqfFvfb5/KDhy5AiqVauGp0+fSjLc357ge46MjMSyZcv4+2Hq1KlQVVVF586dRa6fMWMGGjVqxN5YS1hgYCC0tbVx+fJlZGVl4fTp03Bzc4O1tTX/YJCQkICqVati3LhxUo5WdiQlJaFRo0Yiux5lZGSgX79+0NHR4df3uHDhAsaOHcteSInZ96PXQkNDUVRUhLy8PPzxxx9QV1eHh4cHf01eXh66d++O7t27s7IRs8zMTKxduxbNmzcXeUl79epV6OjooGrVqiIjpADAy8sLvXr1YiNyxez7333B35OSkmBqaop+/fqJLJ1QWFiIjh07wsvLS6JxyrqzZ8+iRo0a/HIXnz9/xvbt26GsrAxfX1/+OmdnZ7i5ubHk+i+KJaWYf+XNmzeYM2cOoqOjAZQOOfbw8IC8vDyfmMrMzMTDhw8RHh7O5llL0LVr1zBw4EDcuHEDAPDkyRNoaGhgwIABItfNmDEDpqambMtnMSuvUYyKikLNmjXRs2dP/lh8fDzGjx8PDQ0NHDx4sMxn3r17J7LINvPzHD9+HFWqVMG8efP4BWQzMzPRrVs3NGvWDH/88QfWr1+P4cOHQ01NjSVypWDs2LEYNGiQyLEbN26gU6dOGDt2LH/s/fv3bPqEBD158gQqKip8X0DwMJecnIxGjRph5cqVZepAlvwQD+Hv9d27d7Czs4O2tjbfJ3vx4gW6du0KS0tLeHh4wM/PD23atEHjxo3ZouZiJrgHsrKysH79elhYWIgkplavXg2O47Bu3Tq8ePECiYmJmDZtGjQ0NNii5hK0evVquLu7Y8iQIXjy5AmA0tFqGhoa6N69O5YsWYJ9+/bB0dERjRs3Zs80ErZjxw6Ym5uLtPG5ublYtWoVzMzMEBcXxx8X1GUsMfXrYUkp5h8LCgoCx3EwNTUVmf6VnJwMT09PKCoqlrt2BHtQEB/hSjc0NBQNGjSAu7s7bt++DQA4duwYdHR00KRJEzg7O6NXr16oXr067t69K62QZc7y5cuxe/du/u8XLlyAtra2SGIqISEBgwYNQseOHUU+yx4UxOfx48cwMDDg1/QSlp6eDh8fH7Rp0wZWVlYYOHAgW9RcwgR12+TJk9GxY0fk5eWJnF+5ciU0NDT4ETkCrL35+X7Uube0tMSECRNEvvNv376hRYsWmD17tqTCY/6ft7c3WrVqhe7du6NGjRpQVVXFyZMnAZRO2ff390fLli3Rt29fTJo0iS1qLiGCdlw4MSU8lW/WrFnQ0NCAjo4OmjVrBlNTU9ZHEzPhvpWfnx+0tLQwcOBAtGjRApUrV+anh9++fRv9+/dH3bp1YWNjAxcXF7ZhkxRERERAR0cHt27dEjl+8+ZNVKtWjX8ZL8D6zr8mlpRi/rHbt29j0KBBUFJSwvXr1wH82VlNTk7G6NGjwXFcmUqDEa+LFy/i6NGjAEoXAbSyssLgwYPx8OFDAKXDkCdMmIARI0Zg2rRpbD0pCRs+fDjk5eVF1pMSJKZ69erFH3v37h1rSMXo+wfrEydOwMzMrMwmAd/Ly8tjD20S8KPf/S1btkBVVRVnzpwRKZ9Tp06hRYsW+Pz5s6RClEnC5ZKdnS0yRXzRokWwsbHBmjVr+GP5+fmwtbWFv7+/JMOUeXv27EG1atVw69YtpKenIzExEUOGDEHVqlX5xBRQto5jD9aSlZGRgXXr1sHCwgLDhw/nj9++fRvnz59HdHQ0Pn78KMUIZcvHjx8xffp0fsTn169f4enpCWVlZYSHhwMordOys7NFXoCwPoF4/Kgf8Pz5c7Ro0QLjx48XeYZ58+YNzM3NRdbFY35dHAAQw3ynpKSE5OTkyhx//vw5TZkyhWJiYigyMpKaNm1KAIjjOHr37h0dOHCApk6dSgoKClKIWjb179+fbt26RQkJCUREdOTIEfL39yczMzOaOHEiWVlZ8dcKyooRjx/dN5MmTaKtW7fS7t27yc3NjYiILl68SAMHDqS6devS1atX//ZnMP+N4Hf/8uXL1KZNG9q5cyf5+vpSSkoKEREVFRXx9dbt27dJUVGRLCwspBmyzBD+nT9z5gwVFhYSAOrVqxcREbm7u9OJEydo69atZGFhQZqamjRgwABSUFCg06dPszpNAubPn09RUVH0+vVrcnV1JVdXV2rWrBlNmTKFrl69Stra2mRnZ0cXL16k9PR0un//PusHSNDSpUvpwoULdP78ef5Yfn4+DRkyhKKioujw4cPUsWNH1geQEMH3/PjxY3r+/DkpKytTw4YNydjYmDIyMmjfvn0UGBhITZs2pd27d0s7XJl09OhR6t+/P5mZmdHBgwf59j4vL48mTZpE+/fvp+DgYOrcubPI59g9JB7C3+v27dspKSmJsrKyyNPTkxo1akRBQUE0a9YsatGiBXXp0oVMTExo7ty5lJGRQdHR0azf/DuQVjaMqbiEM9X79+/HkiVL4OPjg5iYGJSUlODVq1fo3bs3dHV1+TVWvn/7xt4iiJ/gO4+Pj0fjxo2xZcsW/tzRo0dhZWUFd3d3kWGtbI61ZAiPvhHw8vJC5cqVcfjwYf4eO3PmDFtoVoIiIyPBcRzOnj2LxMREaGhoYPr06SLXFBcXY8KECVi7di0bRSABwnXSpEmToKGhASMjI2hpacHW1hYvX74EAHh4eEBPTw+amppo3LgxmjVrxtbDESPh73TFihXQ0tLCihUrsGjRIlhYWMDR0RHh4eEoKCjAwYMH4ezsDCcnJ4wePZpNb5GCxYsXQ1NTky83QR/s5MmT4DgO2tra/CLBrFzES1CnBQUFwdDQEA0bNkTLli3RvHlzvs+cnp6OdevWwcrKCi4uLlKMVnYlJiZi8ODBUFBQwKVLlwD8We/l5uZizJgx4DiO7RwqAcLtjbe3N9TU1NCtWzfUr18ftWrVwrJlywCUjnB3dnZG5cqV0bRpUzg6OrL25jfCklLMD3l7e6NGjRoYNWoUHBwcYGZmxlcMDx8+RN++faGnp8dv/8xIXnFxMTIzM9G/f/8yHZvjx4/DxMQEo0ePFtnynhGv48ePg+M4XL16tcw5T09PVK9eHUFBQWUaUPZgLV6vXr3C+vXrsW7dOgCla98sW7YMderUwZQpU5Cbm4tnz55h9uzZ0NDQYLsdSoBwQurx48ewtLTEnTt38ObNGzx79gyNGzdGo0aN8OnTJwClu1WdOnUKYWFhbBMNCXn8+DF8fX353UEB4MGDB+jfvz/atWuHV69e8ceF6zRWLuIh3E4I3z8JCQlo0qQJPDw8kJWVxR+Pjo7GH3/8gcGDB6NWrVpIS0uTaLyy6sKFC9DQ0MDmzZsBAGFhYZCXl0fNmjX5qWLp6elYvnw5WrduzTaeEbMf9a8SExPRs2dPaGpq8otlC+6rnJwcLF++nNVlEpSWloaePXuKPFf6+PjA3NwcGzZsAFBaLm/evMHr16/LJOGZXxtLSjHlCg4OhqGhIb9g9vHjx6GgoMCvXQSULpzZpk0bODk5SStMmXT//n2sXbtW5FhsbCwUFRVFtucGShc/F35oYH6+8rYUdnJygq6uLv9mWtDJiYmJgby8PDiO47ezZ8Tv+fPnaNSoEWrWrCmyw2FycjI2bdoEHR0d6OjooG7dujAxMWGLzEpYYGAgunbtCldXVxQWFvL3S25uLurWrYvevXuX+zn2ZlS8rl27Bo7joKioiP3794uce/ToEbS0tLBr164yn2MjcsVD+HvdvXs3pk+fjq1btyIlJQUAsGHDBtja2sLV1RXx8fF4+PAhunfvjuHDh+PevXvQ1tbGqVOnpBX+b6m8ZEd2djbGjBkDPz8/AKU7gxoaGsLV1RVdu3aFrq4u7t+/D6B0jakvX75INGZZI1xGsbGxiI2N5Z9tgNL1PLt37w4tLS1+573vy5UlPcRv/fr10NfXh42NDd68eSNybsKECTA0NCyz4QnAXuj+TlhSiinX+vXr0aNHDwDA4cOHoaqqik2bNgEo3UFEsBPVq1evWIUgAYLO6OXLlzFw4EAYGRmhZcuW2L9/P195jxkzBoMHD0ZaWhp7WJOCEydO8BsAFBcXw9nZGVpaWnxiCgDu3bsHX19frFmzhnVyxEz4AS4uLg7jx4+HmpoaZsyYIXJdcXExPn/+jODgYFy9ehXv37+XdKgyLSMjA3/88Qdq1aoFW1tb/rig83ngwAHUrVsXSUlJLNkhBQEBAeA4DlOnTsW3b99EyqBDhw6YMGGCFKOTHcLf+5w5c1C1alV06dIFCgoK6N27N2JiYlBcXIxdu3ahZcuWkJOTg7GxMZo1a4aSkhK8f/8eJiYmuHz5shT/Fb8XQd/3zZs3OHz4MBITE/lz169fx9WrV5GRkQFLS0uMGjUKQOnSCoJEL5tlIH7C983s2bNhYmKCevXqoVq1avD39+f7yu/fv0ePHj1Qo0YNPHjwQFrhyrQrV66gadOmUFFR4Rczz8/PBwCkpqZCRUWFX3ye+T2xpBQjQlBBL126FB4eHrh+/TpUVFT4hBQA7Nu3D3PnzkV2djZ/jCWmxC88PBx16tTBsWPHkJKSggEDBqBVq1YwMTFBaGgoFi5ciAYNGrAGVUKEf+fj4uJQtWpVDB48mB9lI0hMVa9eHYGBgbh06RJ69uyJoUOH8p9jiSnxunbtGt+pefHiBSZOnAhdXV2RkYaC9QgYySivrYiPj8fMmTNRqVIlLFiwQORccHAwTExMWLJQzP6qDV+8eDHk5OSwbt06fmpYdnY2GjZsWKa8GPF6+PAhevfujZs3bwIoHTltaWmJHj168MeA0uljDx484MvV29sbjRs3ZtPEfhLB9/ro0SM0bNgQ3bt3x/nz58tcFxERATs7Oz5hdf36dXTr1g3jxo3D8+fPJRqzLFu4cCFq1KiBy5cvIzc3FxMnTgTHcZg1a5ZIYsrGxgbdunWTcrS/v/Lam4KCAkRHR6NOnTqwt7dHTk4Of+7FixcwNDTk1/5ifk8sKSXjftQRvX37Nj/NSHjKXm5uLrp06YKxY8eyt9YSIPiO3759Cw8PD349HIH79+9j5syZMDIygrOzMziOw8CBA0U+y/x83799mzp1KmrVqgVFRUX07t1bZPqXp6cntLS0YGxsDBsbG5YEkZCvX7+iYcOGMDAw4BNTz58/x5QpU9CgQQOsX7+ev5Yl1SVD+Ht+9eoVEhMT+fshJSUF06dPh6GhIXx9ffHp0ye8fPkSnTt3hqOjIysjMRKuz7Zs2YLJkydjypQpOHv2LF8+8+fPB8dx6NatGyZNmgQnJyc0btyY1WcStGHDBnTs2BEdO3ZERkYGf/zWrVto3rw5nJycykwLj46Oxvjx46Gurs4vss38N4L75cmTJ6hevTpmzJiB169fl3vtnj17oKCgwG/YMGvWLAwaNEhk3S9GvJ4+fYoePXrwU1dDQ0Ohrq4Od3d3KCgowNfXl1939fPnz6ytETPh7/fy5csICwtDXFwcP9AhJiYGBgYGsLa2xv79+3H69Gl069YNzZo1Y7NAfnMsKSXDhDuihw8fxooVKxAZGYmPHz8CANatWwdlZWUsWbIET548wY0bN9C5c2dYWFjwIzxY4kP8YmNj4ezsDEtLS36BzO8fBGJiYrBp0yZYWVmxkVIStGbNGqipqeHatWu4e/cuQkNDoaGhgX79+uHOnTv8dQ8ePMCTJ0/YoowSVFJSgujoaFhaWsLMzIzvdD59+hRTp05Fo0aNsHz5cilHKZsEiXQDAwPUrVsXR48eRUFBAT5+/AgfHx/Iy8tDU1MTw4YNQ+/evZGbmwuAJQ/F4fsEe9WqVTFgwADUq1cPFhYW8PT05O+d5cuXg+M4dOjQAcHBwfwDAktMScapU6egq6sLbW3tMhtp3LlzBy1btkSrVq1E1su5du0afHx8+LVymJ8jOzsbXbt2xaRJk8qc+/z5M785Q1paGtq1awdNTU20a9cOVapUwcOHDyUdrkxLTU3F1q1bkZubi6tXr0JPT49fNHvEiBHgOA5eXl4i7Qtra8TPx8cHampqMDQ0ROXKlTFo0CB+enF0dDRMTU35svHx8eGn9LPE1O+LJaUYzJw5E5qammjQoAHq1q0LT09PJCUlobCwEGvWrIG6ujpq1qyJpk2bokuXLmz7TQmLjo6GlZUVFBUVsXHjRv54cXFxmaQgeziQrP79+2P48OEixy5duoSqVauiT58+fBJRGLtvxKO8BHlJSQlu3bqFxo0biySmnj17htGjR6NFixZskVkJEO7gBwcHQ1NTE8ePH8fZs2fh6ekJDQ0NrF69GkDporMzZsxAw4YNRdb/Km+BU+bniY+PR4cOHUQ2Z1i9ejVsbW0xadIkvt5auXIl5OXlsW3bNgCsPhOXHz0UX758GYaGhhg4cCC/WLZAdHQ0RowYUeazgpGizM+TmZkJKysrkc1loqKiMGPGDGhqaqJp06bw8PAAUDq9f/HixZg+fTrb1VXMfnTfCEamTZo0CYMHD+bbk5kzZ6JDhw5o06YNS0SJmXAf7dq1a6hbty4uXbqEr1+/IiQkBB06dED37t0RExMDALh58ybMzc3Rrl07vmzYTuK/N5aUkkGCm7ukpARfvnxBz549+WHdGzduhL29Pfr3788voP327VvcunULL168YCM9pOTevXto06YN7O3tcfLkSf44G6kmHUVFRSgpKUHfvn0xaNAgAKX3hCApuHjxYlSqVAnu7u64desW/zlWXuJ19epVtG/fXuSYIDFlamoKCwsLkTWmBKNCGcnYt28fAgICRKZOAqUjdKpVq8YnRBISEjBz5kw0aNCAT1Yx4uPv749GjRrBzs4O7969449nZWXBz88PzZs3x4cPH/jjixYtQuXKlREQECCNcH97wg/HSUlJiIuLQ0lJCZ8AjIiIgJGREYYOHfrDkdHsAVu8UlNToampiblz5yIzMxMrV66Eubk5unXrhqVLl2LWrFkwNTUVeZHI2n/xEv5+g4ODsXnzZkRFRSEzMxNA6YuNdu3aYfDgwQBKk7W9evVifWoJW716NWbNmoU//vhD5Pj58+dhaWmJ6dOnAyjtU9+8eRNGRkbo1KkTewEiA1hSSsYId1Rev36NxMRE9OzZE58/f+aP79ixA/b29hgwYAA/D/5HP4P5uQQN4q1bt7Bv3z6sXLkSr169AvBnYqp79+4iO1CwRlT8fvQ7v2PHDnAcxw85FpTFmjVr0LVrV5iYmGDAgAEia0wx4lFSUoKwsDDUqlVLZKFSQZkIyqpOnTrsbZsUJCQkoE6dOuA4DvPmzQMgOvqpc+fO/I6vQOmOVr6+vtDR0Smzlh7z33xfn8XFxUFbWxscx+Hs2bMi596+fQuO4xASEiJyfNasWdDU1ER6erqYo5UtwmUzZ84cNGnSBNWqVUOnTp2wd+9efirrmTNnYGxsjOHDh4tM12PET9Cm7Nq1CxzHwdjYGMrKyli7di0/Eio7OxtNmjTBxIkTpRip7BDuB0+dOhU6OjowNDREw4YNMXLkSH46paAf0KNHDzRp0gSNGzdmy5GI2fffq6urKziOg4ODg8iGWUDpFPHq1auLtCsxMTFQUVFBz549JREuI0UsKSWjZs6cCT09PRgZGUFPTw9JSUki53fs2AFHR0d06tSJ7dYiYcePH0fNmjXRunVrtG3bFoqKiti1axeA0mRVmzZt0LNnzzIPCYx4CDeoJ0+exL59+3D9+nV+xM3QoUOhoqKC06dP48uXL8jMzISTkxMOHTqEK1euoH79+ujevXuZqRbMz5ebm4vw8HDUrVsXHTt2FDl3/vx5dOnSBe3bty832c6IV35+Pk6dOgUrKys0atSIfxAQjC4cP348+vTpI/KZV69eYf78+YiPj5d4vLLgxo0b/MiohIQEaGpqom3btnj8+DF/zdu3b1G/fn2cO3euzOdTU1MlFqusmTdvHnR1dREcHIyUlBTY2dmhcePGWL16NZ+YioiIQKVKlbBw4UIpRyu7Hj16hDNnzojsDlpSUoK8vDw4OTlh5cqV/DFG/B48eIBu3brh7t27+Pr1K9atWwd7e3v069ePHxm9Z88eDBkyBFOnTuXbITYKR/yEBz9MmjQJioqKOHbsWJnp/RYWFiLXAqXPPqzf9vtjSSkZIdwgRkVFoWbNmggJCcHcuXPRpEkT2NnZ8SNyBNauXYtx48axkVESdPfuXejo6CAwMBBA6SKZHMdh0aJFfDnExsaiadOmcHNzK/OWgfm5hO+bKVOmoEaNGqhRowb/BvTbt2/IyMjAmDFjoKCggAYNGqB27doi6xdFRkaiadOmItNimP9OUDYJCQm4d+8e4uLi+HOnT59GvXr10KFDBxQUFKCgoADz5s3DmDFj+Ac6RjKWLFnCT2EpKChAREQE6tati5YtWyIrKwt5eXkoLi5Gq1atMGzYMACi9x2bKi4egn7A4sWLkZKSAqB0d0p1dXW0aNECAQEBCAsLQ48ePdCoUSP20CZBgt30BInAS5cuoUqVKmjZsiUaNGiAdevW8fVYdHQ0Kxsp+KvvvLi4GLNnz4ahoSESEhIkGJVsO3ToEDp16gQ3NzeR0U/btm1Dq1at4ObmxiemhNdZY22M+AUEBKBTp0549OgRf2z48OFQUVHBzp078eTJEyQnJ6Njx45wdHRkSVwZxZJSMmbLli1YsWKFyHSI0NBQdOjQAQ4ODmW2tRVUDCwx9XP96Ps8deoUnJycAJSueWNgYIBRo0bx579+/QqgtNOamJgo/kBlmHCjeP/+fbRv3x53795FcnIyli5dipYtW8LDw4OfghQZGYk9e/Zg586dfCdHkJhiiZCfS1A2QUFB0NfXR7169SAnJwdXV1ecP38eAHDu3DnUr1+ff5hTUVFhux5JWElJCby9vcFxHD/aU5CYMjExQa1atdC6dWsMGzYMpqam/Kgp1iGVjMmTJ6NJkyZYunQpPyL6+fPn0NHRAcdxGDFiBMaPH8+3Vyz5IRnJycnYtWsX8vPzceHCBWhpafEvqszNzdGoUSPMmzdPZBoyKxvJEXzXb968wf79+0XKISQkBJMmTYKWlha/VisjfkVFRfD29uZfCgorKSnB9u3b4eDggPbt27Mpx1Jw48YNaGhooH///iIjcQW7H2poaGDEiBFo06YN3w9gz52yhyWlfnPCN/Xnz59hZWUFjuMwd+5ckesEiam2bduWGSLJHhB+LkGZJCcnIzY2VqQzuXHjRlhaWiIpKQlGRkYYNWoUf31wcDCGDx/ORkdJiOD3/tChQ+jRoweGDRsmsgNIQEAAWrRogREjRpRbJsLlyu6hn+/GjRtQUVHBpk2bEB8fjzNnzqBDhw7o2LEjoqKiAADp6elYuXIl1q9fj+fPn0s54t9feZ3IoqIizJ8/H3Jycti5cyeAPxNTrVq1go6Ojsiaa+yt9c8nXC7ff79Tp05Fw4YNsXTpUn4x81evXkFbWxsuLi5syoSYlXfPFBYW4suXLyguLoabmxu8vb359qRv374wNjaGl5cXa1ckpLyRm69fv4aGhobIYs03b95Ehw4d0K1bN5EHb+bnK+++ycvLw4oVK1C7dm2MHz+e33EPKC3DgIAAjBkzhiU7xOz771d4rVwdHR24uLiI3B9TpkwBx3E4ceIEf4z1A2QTS0rJCMHipbGxsejcuTN0dXXx9u1bkWvCwsJgYWGBcePGSSNEmSCorB8/fozmzZvzc98FXr16hTZt2qBq1apwd3cX+Yy3tzd69OjB3vKI2fnz5xEbGwsAyMnJwdixY6Gvrw8rKyuR6wSJKTs7O/Tu3Zstni1hS5YsgaOjo8ix6OhoODo6YujQoVKKigHAj+IUdEaLioowd+5cyMnJ8SOm8vPzcfr0aTRp0gQODg78Z9mID/HZunUrtmzZUiaJPmXKFNSqVQvLly/np/I9e/YM6urqcHJyYtvYi4lgRAAAXLx4EZcuXRJ5WCsuLoajoyOmTJnCHxs0aBDOnj0rsosyIx6C7/bLly/Iycnh75v09HQYGRnBw8ND5PsvKChAQkIC0tLSpBKvrBBOely7dg1RUVH8i6jCwkIsWbIENjY2+OOPP5CTkyPyWTb7Q3KE11oTfO+xsbHQ0tKCs7OzyJILQ4cORbVq1cpdu5CRHSwpJQNiY2NhZGSEmzdvAih9cGvTpg3q1atXJjF19epVVlmLiaBSfvz4MdTV1eHt7Y07d+6IXJObm4sZM2bAxMQEc+bMQV5eHl6+fImZM2dCQ0ODvX0Ts0+fPqFz584wMzPjdzT68uULZs+eDSMjI0yfPl3kofnbt29YtGgRPD092X0jYcuWLYOVlRU/NVJwfwUHB0NBQaHMVGRGfITviVOnToHjOERGRgL4s1wKCwsxbdo0KCoq4siRIwD+HDHVtGlTNGnShN1DP9nLly9FRjp1794d9erVw549e8okpjp37ow6depg1qxZ/E5VL1++BMdxcHV1FUmgMP+Ni4sLgoKC+L97e3tDTU0NxsbGqFq1Kg4ePAigtH0ZNGgQbG1tMWrUKLRp0wbm5ub8/cbuF/ER1FsnT55E69at0bx5c5iamiIoKAgPHz5ESEgISwhK2YwZM2BsbAxLS0tUq1YNLi4ueP78OfLz87FgwQLY2tpi8uTJIiOmAJbIFZf09HR+hFN8fDw4jsOoUaP4EbiC7z06OhqKiooYMWKEyDOQp6cnOI7jE4yM7GFJKRnw4cMH1KtXD7Nnz+aPRUdHo23btqhfv365CzCzt9XikZqaipYtW2L69OllzgkeEvLy8jB58mSYmZlBWVkZlpaWMDU1FRlRxYjPuXPn0KdPHzRv3hwxMTEAShNTPj4+sLa2hq+vr8jDQEFBAXv7JmbCi5oLhIaGguM4nDp1SuTaW7duwczMrMzGDYx4REZGYvPmzfwOeZ8/f4a7uztUVFT4zqXgvrh27Rrk5eXBcRxOnjwJoDRZFRYWBjs7O7ZO3k90+PBhODg4wNvbW+Tl0+DBg2FmZobdu3eLPKxNmDAB9erVw4gRI1BSUsKXWXx8PJ49eybx+H9XOTk5GDRoECpVqoTTp0/j1atXMDU1RWxsLO7cucOPKBRsDvDp0ycMGzYMPXv2hJubG1tvRYLCw8OhrKwMf39/3Lt3D56enpCTk8OtW7ekHZrMW7duHWrUqMGPal+xYgXk5ORw+fJlAH++MKxTpw4CAgKkGapMCAsLw7hx43Do0CG+jgoPD4eSkhLGjh3LJ6aA0pfvjRo1AsdxmDNnjsjPGT9+PGtvZBhLSv1mvh/SLfj7vn37oK+vz4/+AICYmBh06NABqqqq/JtRRrxevnwJS0tLPHjwgC+jmzdvYuXKlTA1NUW/fv1w9OhRAMD79+9x+PBh3Llzh1+ElhGf73eo7Nmzp0hiKi0tDd7e3rCxscGcOXN+OG+e+bkE3+uJEyfQsGFDrFmzhj83YcIEqKioIDQ0FGlpaSgqKoKPjw9MTU3ZdvUSsGvXLhgaGmLYsGEibzzT0tIwcuRIVK5cWeSt55MnTzBp0iTs3btXZM2IwsJCtlbeT7Rjxw6oqqpi9erV/Oha4RdNrq6uMDMzw86dO/m2f/Dgwbh06ZJI34G9nBKP9PR0TJgwAUpKSpg3b57IS6ri4mIsXboUcnJy2LBhAwCUGaXG1lsRr+LiYuTn56Nfv378y9ykpCTUq1cPHh4eZa5lJG/kyJFYuHAhAODIkSNQV1fHpk2bAICfspeXl4edO3eyekzMAgMDoaOjgxkzZiA6OhrAn/fF6dOnIScnhzFjxvDPMdnZ2Zg6dSquXLnClw3rPzMAS0r9toS33QSAuLg42NnZYceOHSLHr169Ci8vL1ZpS8itW7fAcRwuXboEANi8eTNsbGxgY2MDDw8PtG3bFpaWlrhx44aUI5Udwo3hP0lMTZ8+HXXq1MHWrVslHqusCg0NhbKyMjZu3Ciyvk1BQQH++OMPKCgowNTUFC1atICmpiYbVSgBBw4cQNWqVXH48GF8+fKlzPn09HS4u7ujUqVK2Lx5M38/ubq68tewh+uf79KlS6hRowY/RVKY8C6gw4YNg7m5OczNzWFlZQVTU1M2LUzMhL/XzMxMeHl5geM49OrVq8x1y5Ytg6KiIvz9/UXOsYc38RF8t4IRhI0aNcLFixeRmZmJWrVqieyEvGXLFvayUAry8/NRVFQEa2trHDhwALGxsVBRUcHmzZsBlLYpCxYsQFhYmMjn2DOOeAQHB6NatWo4evQo8vPzRc4J6ruwsDAoKyvD2dkZs2fPRpcuXWBtbS2y5iTDACwp9Vu6dOkSOI6Dm5ubyLDVefPmoVatWmUW/hNgFYNkDB8+HBzHwcLCAoqKili0aBH/EP3s2TOoqalh+/btUo7y93f37l2+UfxRYurChQvo1asXLC0t+TdAqamp2LRpE7tfJOTTp0+wtbXF6tWrAZR2StPT03HkyBF+Ol9kZCS2bduGzZs3i0zxY8Tj/fv3sLa2LpOYLSgowIMHDxAfH893SGfMmAFlZWXUr18fLVu25Ed9sIfrn0vwfa5YsQI9e/YU+X6vXr2KefPmoWvXriI77+7atQtz587F7Nmz+QQhq9fEQzghlZSUhJKSEmRlZWHatGlQUFDgd54SbpNmzZoFe3t7dq9I0LFjx9CjRw8ApX21QYMGwcDAAGPHjuXrruzsbPTo0QNr1qxhZSNmN27c4Kd1z5kzB6GhoQBK6zlDQ0MoKipi7969/PXp6elo3749li5dKpV4ZUVJSQlyc3Ph5uaGBQsWiJx7+/YtQkNDsW3bNn7q+IULF9CtWzfY29ujV69erB/AlIslpX4D39/UBQUFuHLlCsaMGYP69evD3NwcGzZswOXLl9GjRw/+QYJ1PqUjNTUVBw8exMqVK8tsU//x40fY2dkhODhYStHJhhkzZsDU1BRnzpz5R4mp3r17o0WLFrhy5YrIz2H3kPglJyfDyMgIISEhKCgogJ+fH+zs7FC1alVoaGjg4sWL0g5R5iQmJqJevXoiIzq3b98ONzc3cBwHExMTkfVvnj9/jpcvX/IP5myElPjMmTMHrVu35nc98vHxgaOjI0xNTeHq6goFBYUyU5AEWH0mHsIJqfnz58PV1RXh4eEAStcrHD9+PBQVFfljwm1See0TIx4vX75Es2bNsGXLFhQXF2PHjh2oXbs2bGxsREaBzJw5E/Xq1WPrFopZfHw8rK2tMXDgQHh4eIDjODx8+BBA6ayDLl26oEmTJnjy5AmA0pclXbt2hbW1NavLJKCoqAj29vYiSSl/f3/06NEDCgoK0NPTQ5UqVfhd9jIzM5Gfny+y+QnDCOMAgJhfVklJCcnJyRERUU5ODlWtWpUKCwtJUVGRcnJyqKSkhObMmUMJCQl08eJFys/PJycnJwoODpZy5LJHuKx+ZM6cOXT8+HE6f/486evrSygy2fPhwwfq27cvKSgo0MyZM6lz587EcRwBII7jiIhE/nzx4kXy8/OjevXq0c6dO0XOMeLn7u5OJ0+eJDk5OWrVqhW1bduWJk6cSNbW1mRubk6BgYHSDlGmfPjwgUxNTWnMmDE0ePBgWrx4MT19+pQsLS3JxcWFnj59SoGBgTR58mTy8PAQ+ew/qQeZ/11wcDB5e3uTnp4epaSkUGFhIU2dOpWcnZ1JX1+fdu/eTePGjaMHDx6QiYkJKwsJmjVrFm3bto127dpFVlZWVLNmTSIiysjIoNmzZ9P27dspNDSUunbtKvI51t6I3927d+no0aP07t072r59OykrK1NhYSH5+PjQxYsXSVdXlywsLCgxMZHOnz9PFy5coKZNm0o77N/e/v37ycfHh9LT0yk4OFjk3jh+/Djt2LGDbty4QUZGRqSgoEBKSkp07do1UlRUpOLiYpKXl5di9L+3wsJCcnZ2ptTUVHJxcaGzZ89SUlIS9enTh1xcXEhLS4sGDhxI6urqFBISQnJycnx7w+o0pjwK0g6A+d8Jd+7XrFlDV65cofT0dOrQoQN5enpSjRo1iIgoICCAvnz5QufPn6fdu3dTVFQUHTx4kAYOHCjN8H97gkr369evpKamVqbzL1wpR0dHU1BQEO3YsYMuXbrEElJiVFxcTLq6uhQaGkq9evWiJUuWEADq0qWLSGJK+M9t27altWvX8p1Q1piKh+D7jouLo7dv31Jubi517dqVtmzZQl27dqXc3FxycXEhZWVlIiKqW7cuGRoasg6OBJWUlJCuri5t3LiRPDw86NChQ1StWjXy9/en5s2bk46ODllZWdG6desoPT29zOdZEkS8+vTpQ9++faP4+HjKzMykadOmkaamJikqKhJRad3VpEkT0tLSYmUhQXfu3KHg4GA6duwYtW3bVuScuro6LV68mIiIunfvTjdu3CAbGxv+PKvbfh5BvzkvL4+KioqI4zhSUVGhgIAACgoKIhMTE759UVRUpOXLl9OBAwcoKiqK7t27R2ZmZnT9+nUyMzOT8r/k9yYoJwMDA1JTU6MaNWrQoUOHqH79+mRiYkJERP369aMWLVrQ3bt36f3796Svr09OTk4kLy9PRUVFpKDAHnHFBQApKirS3r17qW/fvhQSEkJKSkp04MABqlu3LqmpqVFhYSHp6+uTkpJSmbJgdRpTHjZS6jcwc+ZM2rFjB/n6+tLHjx8pMjKSatWqRVu2bKGaNWuKPLC9e/eOZsyYQdra2rRmzRr2MCdmQUFBFBkZSX5+fvxb0e8dP36cNm3aRIWFhbRp0yZq3LixhKOUPYI3aJ8/f6aePXuSoqIizZw5s0xiiqjsGx020kM8BN9zUFAQeXt7U7Vq1UhRUZHev39PJ06coJYtW/LXfvr0iTZs2EAbN26k69evk6mpqRQjl13v3r2j1NTUMiMGPn78SP369aMxY8bQoEGDpBOcDPq7uik/P59cXFxITU2N9u7dy9p+Mfq+3bh8+TINHDiQIiMjyyQ0CgsLSUFBgfLy8mjTpk00adIk9kAtBoL74+nTpzR79mx68eIFGRsb09ixY6ljx440efJkOnr0KE2dOpUmT55MSkpK0g5Z5nxfh339+pXvF+zatYv09PRo8eLFVKdOnR/+DDZCSnyE6zVB4q+wsJDy8/NJRUVF5Nrc3Fzq1asX2dvb09y5c6URLvOLYU9Wv7jDhw9TSEgInTlzhiZNmkT29vb06NEjev78OQ0dOpQ+fPhAHMdRYWEhERHp6+uTvb09nTx5kjIzM1mnVAwEed63b9/S5MmTqVmzZj9MSBERWVlZ0fz58+nYsWMsISVGJSUl/J8FHRZtbW06ceIEFRYW0tKlS+ns2bN8oysox+/vEZaQEg+O4yg6OppGjhxJs2bNogcPHtDOnTvp48ePdOXKFf668+fP08SJE2nv3r0UGRnJElJiFhISQocOHSpzHADp6+uXSUh9+fKFPDw8qKSkhPr37y+hKGULACouLi5zvLzRuEREeXl5dO/ePerduze9fv2adu3aRRzHidSJzM8laDdycnKIqPThOjc3l090FBQU8NdevHiRTpw4QVWqVKFp06aRgoICFRUVST7o35gg2fHgwQOytbWlypUrU5cuXSghIYH++OMPun79Oq1YsYI6d+5MJ06coB07dvD3GCsLyRBOSEVERNDp06fp4cOHpKqqSsOHD6eBAwfS+/fvae7cufT69WsiIhoyZAidPXtW5OewhNTPtX79erpz5w4RkUjfWEFBgR8xpaKiwh8vLi6mt2/fkouLC6WlpZGvr6/UYmd+MWJftYr5qV69eoVbt27hzZs3KCoqwoULF/DHH38AAE6cOAENDQ1s3LgRu3fvhrq6OpycnPjdDwT8/PzQpEkTZGRkSOOfIBMiIyOxfv16jBkzpsw2qYzkCS80e//+fVy8eBEfP35EdnY2AODDhw+wtrZG69atRRY/ZyRr165dGDZsGIDSuk6w65FAUVER3rx5g507d7Jd9iRgy5Yt4DgOly5d+ttr09LSsHbtWnTv3h2Wlpb8IudswdmfT3gr+sOHD+Px48c/vDY3Nxfu7u7o2LEjunbtyspFgvz9/dGvXz/+7y1btoSlpaVI+5Kbm4suXbpgzpw50ghRpjx9+hRVqlTB/Pnz+WMvXryAtrY2Ro0aBaB097ZBgwbB1tYWmzdvZosxS4jwPTF16lRoaGjA0NAQ+vr68PPz489t2bIFbdq0QaNGjWBvb4+aNWuyMhKj+/fvo1KlShg2bBgePHjAH/9RHzktLQ1eXl7o2rUrWrVqxdob5l9hSalfyJ49e9CgQQNUr14dmpqa8PPzQ05ODjIyMpCRkQFbW1ssWbIEQOkuB2ZmZtDW1saECRMAlD6Yp6WloXv37rhz5440/ym/vQkTJoDjOJiamiI1NVXa4cg04cZz1qxZqFOnDmrWrIl69eph8eLFeP36NYDSxJStrS3atGmDkJAQ6QQrowRlNHPmTHTt2hXv37+HoaEhRo0axZ87cuQIfH19UVxczJKGEhAYGAglJSUcP378H11/4cIF9OzZE2PHjuUfEtjDws8XExODypUrIzY2FtOnT4euri6SkpL+8jNnzpzB8ePH+QcDVi6SsWjRIvTu3RtAaR13+fJlNGzYEPXq1cPevXuxefNmdOrUCebm5qxMxOzbt2/o2rUratasiWvXrgH48z5wcXFB//79+ReIGRkZGDp0KMzMzLBjxw6pxSwLhHeYBEp3dm3WrBnu37+P+/fvY/369VBUVIS3tzd/TVhYGObPn4+JEyfyZciSHuJz/vx51K5dG0OHDv3bxFRWVhbGjh2LBQsWsPaG+ddYUuoXsXXrVlSuXBnr16/HpUuXMGTIEFStWhV79uwBADx8+BC1atXit6x//fo13NzcEBQUxI8SEVQgbOSOZMyePRtycnJ8GTHStWjRItSsWRPnz58HAAwcOBC6urqYPHkyv7Xzhw8fYGJiIjI6h/n5EhISsGjRInh6eiIsLIyvmy5duoS2bdtCQ0MDI0aMAPDnKLeJEydiyJAh/Og2Rnz27dsHjuMwc+ZMAKUd/r9LBBYXF+PDhw/8dewhQTzi4+MxevRoVKtWDerq6vyoKeHRoALllVl51zH/XXm/7wcPHkTNmjWRlpYGoPS7f/nyJfr16wczMzM0b94c/fv3Z6MJJOTKlStwdHREz549cfr0aQDAu3fvUKlSJWzZsgXAn/fHly9fMGrUKP6lFfPzff8ssnLlSvTv3x/jxo3jyyE7OxtbtmyBgoICfHx8yv057L4RH0Ebcu7cORgZGf1lYkpQZsLlwcqG+TdYUuoXcODAAXAch0OHDokcNzMzQ9++fQEASUlJaNmyJYYOHYpLly6hc+fOcHJy4isJ4Y4oG2Xwcwm+zw8fPuD169ciUyvGjh2LypUrs5E3UiD8O5+QkIB27dohKCgIQOnIAVVVVTg5OUFPT08kMfXlyxfWkIrR/fv3oaenB0dHRzRr1gxycnLYsGEDACA1NRV9+/aFvr4+9u3bBwD4+PEjZs2aBW1tbTx58kSaocuErVu3guM4ODg4QEdHB+Hh4QD+XTKDtTE/n/B3umLFCnAcB1VVVX7Ux/cjDhjpOHDgAI4cOYL4+HgEBgbCzs4OX758KXPd58+fkZmZyZcZG00gGdeuXYO9vT1cXFywZ88eGBgYYPz48SLXCNp/dj+JT//+/TFo0CD+75mZmZg+fTqqVauGjh07ilybnZ3Nv5hnLwwlS7hd+SeJqe8/yzD/BktK/QIGDBgADQ0NhISEIDMzkz/eq1cvDBw4EAUFBSgsLERAQAAsLS1hYGAABwcH/u0bezMqPoJKNyQkBNbW1jAwMECHDh34UR5A6VQ+ZWVlhIaGSitMmSPcGD5+/BipqakICwtDZmYmrl+/jpo1a2LTpk0AADc3N9SsWRMjRowQWX+NJaZ+vgcPHqBq1aqYNWsW8vPz8eHDB7Rp0wba2tr8FKTk5GS0b98ejRo1gra2NhwcHGBkZIS7d+9KOfrf38qVK1GpUiWcPHkSnz9/hoeHB9TV1flRBayTKR3CbXhKSgru37+PGzduYMyYMVBXV8e5c+cAsMSGNBw8eBBXr14FUDr1qE6dOjA3N4euri5MTU3BcRycnJzg7++P8PBw3L59GykpKSLtC7uvJOvq1auwt7eHiooKunfvzh9n94/kPHv2jB8pJbgX3rx5g4ULF4LjOAQEBIhcn5OTg9WrV8PBwYHdL2L2V8+MZ86c+VeJKYb5N1hS6hfh5uaGhg0b8lPBIiIiICcnhwsXLvDXFBcX49OnT4iLi+MrFdbIit/Zs2ehrKyM9evXIz4+HsuXLwfHcTh48CB/zcSJE8FxHE6ePCnFSGWDcIPq5eWFpk2b4sOHD3xCd/z48Rg+fDh/b0yaNAkWFhYYO3YsS+CKUWpqKqpVq4ZevXqJHO/Zsyc0NTWRnJzMjyjIzMzE7du3sWbNGpw5c+Zv18xhfo6OHTti7969/N/j4+Ph6enJElNSJFwnLViwAB4eHvzC88+fP8eIESNQvXp1REVF8detX78ez58/l3isskawEYAgKQgAeXl5AMAnDqtVqwYDAwP06NED2traqFatGoYMGSKtkGVCSkrK314TExODVq1aoWfPnvyUfoDVb5K2adMm1K1bF9++fQNQ+lLKz88PKioqWLdunci1eXl5fPmwchIP4fZm9+7dmD17NiZPnow7d+7wdVtERES5iSmG+a9YUqqCE36b1q9fPzRt2hQTJ05EtWrVsHv3bgCllUh5D9PsAVu8SkpKUFhYiPHjx8PX1xdA6VQjAwMDeHl5lbnex8cHT58+lXSYMuvLly/o27cvLl68KHJ80KBBcHFxwdevXwGULnJ68uRJvpPD7hvx+PTpE0aMGAEVFRVERkYCAJYtWwZ5eXmYmprCzc0NhoaG8Pb25keFso6nZJw7dw4bN27k/y681odwYurMmTMA2AOBNMyYMQNaWlo4evSoyBTxly9fYuTIkahSpQpWrVqFDh06wNzcnI30FLOtW7dCXl7+h1PzBffIgAED4O/vD6A0WSLYOZkRjyNHjqBSpUqIjY3922sFU/n69OmDU6dOSSA65nuxsbEwMTGBra0tn5h69+4d5s6dC1VVVX5qvzDW/oifj48PtLW14e7uDktLS9jY2GDDhg3IyckBUPoyvk6dOnBycsLLly+lHC3zu2BJqV+AcAemf//+4DgOI0aM4Ed6sApaurp37461a9fi/fv30NPTE9kx7NixY/w6RozkrF27FsbGxmjTpg3evXsncm7RokVo0KABOnfujObNm8PU1JS/x1hCSry+fPmC0aNHo3Llyhg6dCh0dXURFhaG7OxsJCUl4ciRI+jRowdUVVVhbW2NrKwsaYf82/v27RtGjRoFc3NzLF++nD8uPMpWkJiqXr06IiIiALB2R5Ju3LgBExMTfpoYIPr9JyUlYfr06TA3N4ezszObui9m27ZtQ6VKlcq07QEBAfzahAJjxoxBu3btALAFgCUhJycHnTt3hqGhIW7duvW311+/fh3m5uYYOHAg/8DNiMePXp7fu3cPDRo0QIsWLUQSU/PnzwfHcf94B1jm59iyZQuMjIz4XdrDwsLAcRyaNWuGNWvWIDc3FwBw4sQJ9OnTh7UzzE/DklIVSFhY2A/PCXdgBgwYAHNzc+zbt4+vHBjJKykpQVFRESZOnIhBgwbB2NgYHh4e/LnMzEyMHDkSy5cvZ9MoJezixYswNzdH9erV8ebNGwCiD9nLli2Dl5cXxo8fz7YUlrAvX77w01kXLVrEHxc8ZOfk5CA5ObnMwx0jPu/fv8fEiRNhbW2NZcuW8ce/T0yNHj0aHMfh5s2b0ghTZp09exbGxsZ8XSasqKiIr7vS0tLYwtlidv36dXAch8WLF4sc79mzJ1q2bInU1FQAfz6Ab9q0Cc2aNZN4nLJIePevnj17Ql9fH7dv3/7bz0VHR7Nd9sRMOHHx7NkzvHz5UmTnUEFiysrKip8mlpSUhMDAQFaXSVB+fj6WLVuG1atXAwCCgoKgrq6ONWvWoE+fPtDT08PatWvL7ILMElPMz8CSUhWEIBMtqAjKI/zQ7OLigiZNmmDr1q38mwVGvIR32cvJyeHfqt24cQNVqlRBvXr18OnTJwClFfSsWbNgZGTEhraK2Y+2Qr9+/ToMDAz4t9RA2S2IBVinR7I+fvyI8ePHo1KlSvx6LGzHI+lKSUnBhAkT/jIx9ezZMyxbtozdL2JUXn128OBBKCsr8+2LYCQUAERGRuL8+fMi/QP2gCA+UVFR6NKlC2xsbPj1VPr06YPGjRvziQ3hOiw0NBRt2rRh9ZoECH7vb9++jZCQEHAcB3Nz8380YooRH+Hf/Xnz5sHU1BR169aFrq4uzp49y5+7f/8+TE1NYW1tXeaFO2tzxEO4rRD0j1+9eoUPHz4gISEBDRs25J9LHz16BDU1NdSrVw8HDhwAwPprzM/FklIVRE5ODtasWQN5eXmsXLnyh9cJdzzbtWuHwYMHSyI85v+FhISgQYMGsLS0hIuLC59wCg0NhaKiIjp37oyuXbvC1dUVGhoabMcwMRNuUM+dO4ft27cjJCQEz549A1D6VrtWrVro3Lkzfx3r3FQMgql8SkpK/EKzrIMjXf8kMfVXx5if59ixY/waXnl5ebC0tET79u1Fphjl5OSgU6dOWLp0qbTClEmXLl1C7969YWVlhdatW8PS0pIf2Slchwmmv7D1CiUnJCQEKioqmDVrFgYNGgRzc3Po6+uzxFQFMHfuXNSoUQPh4eF4+/YtnJycoKqqKrK5xv3791G9enWMHDlSipHKBuH6aOPGjdi8ebPIchdhYWFo1KgRn2yPiopC//79sXDhQlaXMWLBklIVgPDNvWnTJnAch+3bt//wevZGVDqePXuGmjVrYvXq1Zg7dy46d+6MOnXq8Lsc3bx5Ez4+Phg0aBCWLl3Kdj+SIB8fHxgaGsLBwQF2dnYwNzfnFy69du0a9PX10a1bNylHKVuEH85+lGz68uULxo0bB47jyixIz0iHcGJKeI0pNr1VclJSUlC7dm10796d32E3ODgYzZs3h6WlJU6fPo09e/agS5cuaNKkCUsQSohwPXbx4kX07t0bysrK/GLnwuXg6OiI+vXrl/tZRjzS09Nhbm4OPz8//lhycjI6derEElNSdufOHbRp04YfGXXixAlUr14d7du3h4KCAvbt28df+/LlS9beSJC3tzd0dHSwdetWfPjwgT9+5MgRNGjQAEePHuWTiFOnTuXPszJifjaWlJIy4Y5KQEAAZsyYAQUFBXAcV2Y7VGHCySiWmBIf4fJ58uQJvL29+b/fvn0bXbp0gZGRET8y50fTwxjx2bNnD2rWrInr168DAFauXIlKlSqJLI55/fp1yMnJYcqUKdIKU2YIrw0l7EcdmNTUVEyePBlPnjwRe2zMP5OSkgIvLy/Y2dnxO4sy4lNewiI2NhYtW7aEk5MTbty4AaB0qni3bt2gq6uLpk2biixqzh4QxOdHCXZBYqp58+b8OmvFxcXo2rUrGjZsKDLNkhG/1NRUmJiY4OjRowD+LKu3b9/yI9zZeniSERUVhdDQUP7vL168wNq1a1FSUoILFy5AV1cX69evB1A666N69erYunWryM9gdZr4HTlyBLVq1eJHdQpLT09Hx44dYWhoiFq1asHS0pKv01iSnREHDgCIkbo5c+bQtm3baMOGDZSVlUXR0dG0Y8cOWrVqFU2ePFna4ckkAMRxHF24cIFu3LhBr1+/pq9fv9Lx48f5a+7evUu+vr708uVLOnXqFJmamkoxYtk0bdo0ys3NpU2bNlFISAgNGzaM/P39afTo0ZSTk0NpaWlkaGhIjx49ooYNG5K8vLy0Q/7tnT59mtauXUuqqqpkZWVF06dPJyKi4uLicr//kpISkpOTk3SYzF/48OED+fj4UOXKlWnr1q3EcZy0Q/otFRUVkYKCAhERff78mbS1tflzt2/fpjFjxlDNmjVp5syZZGdnR0REiYmJpKGhQdWqVSOO40R+BvNz+Pr6UvPmzcnZ2Zk4juP7A0Qk8udLly7R2rVr6d27d7Rx40by9/enhw8f0uPHj0lRUZGVjYTZ2dmRvr4+HT16lIhKy6qkpIT69etHJ06cIDMzM7pz5w5VrlxZypH+vi5evEjt27enDh060NixY8nZ2ZmIiNLS0khTU5OGDBlC1apVo/Xr15OcnBy5u7tTTEwM6ejo0OXLl1lbIyYRERHUrl07UlJS4o8tXbqULl++TGFhYSQvL0/y8vIi9Vt2djbFxsZSbm4ude3aleTl5VmdxogNewqoAL5+/UpRUVHk5+dHLi4uNGLECFqxYgUtXryYpk6dSps3b5Z2iDKJ4zgKDw+n7t2704kTJygmJobOnz9P9+/f56+xtLSkJUuWkI6ODrm5uVFhYSGxPK9kCL5njuOoXr16dP78eRo6dCifkCopKaHg4GA6efIkFRQUUOPGjUleXp6Ki4ulHPnv7caNG9S7d28yNTWlb9++0ZEjR8jV1ZWI6IffP0tIVTy6uroUEBBAW7Zs4R/KmZ9n165dlJOTw3fuN2zYQGPGjKGHDx/y11hZWdHmzZvp8ePH5OfnRxcuXCAiImNjY1JVVSWO46ikpIQ9IPxkWVlZdOzYMQoICKCIiAj+IU24zRH82dHRkSZOnEhGRkZkY2NDDx48YAkpCRB8/5mZmZSVlcUfHzduHL148YL8/PyIqLSs5OXlSV9fn86fP0/nz59nCSkxy8jIIKLS5Pm+ffsoODiYiIg0NTUpKyuLHj9+TLq6unx/IDs7m/bs2cMnpFhb8/OtWbOG5syZQ4qKiiLHnz59Sunp6aSkpMSXB8dxVFxcTJcuXaK8vDxq164d9ejRgz/P6jRGbKQwOov5TlpaGnR0dMoscP7p0ye0adMGHMeJLDrLSEZGRgZmzJiBwMBAAKXT93r06AFtbW3ExcWJXHv//n0kJSVJI0yZ8aNpqqtWrYK8vDwqV66MXbt28cczMjLQoUMHzJ49W0IRMk+fPsXu3bv53Vqys7Oxb98+mJubo0+fPvx1bA2cXwubIv5zHT16FHXq1MHkyZP5XaaCg4NRq1YtjBgxgt/VTWDv3r1QUVFB27Zt2bo4Yib4XU9NTYW9vT0cHBxw8uRJ/viPpvJFRERg5syZfN3G6jjxCw0NRbt27WBmZoZly5YhMTEReXl58PPzQ+PGjdG9e3ds3rwZw4cPh7q6Or8YPSN+EyZMwMCBA2FnZ4d27drhxIkT/LmJEyeiSpUqmDRpElq0aAELCwt+qh5ra8RHUCc9fPgQ2dnZAIDTp09DR0cHmzdvFrn2w4cPcHJywunTpyUeJyO72OtpCSspKSlzTENDg1xdXSksLIyePn3KH9fW1qZGjRpR8+bNKTw8nL09kKD79++TkZERnTlzhnR1dYmIyMzMjDZv3kzW1tbUpk0bkbKysLAgAwMDaYX72xOe3hUeHk4nTpygy5cvExHRlClTaNiwYSQnJ0cNGjSgxMRESkhIIDc3N8rIyKC5c+dKM3SZkZiYSAMGDKCpU6dSlSpViIioatWq1LdvX5oxYwa9ePGC3NzciIjYm7ZfDBvJ9nN1796d3N3d6ebNmzR9+nTKzs4mZ2dn2rFjB0VGRtKaNWtERkxxHEft2rUjExMTsrS0lGLkskNTU5O2bt1Knz9/pvXr19O5c+f+csRU586dacmSJaSgoMBGSElATEwMubu7U4sWLahTp060du1amj17Nr1584ZmzZpFfn5+lJOTQ9u2baMXL17QxYsXqXbt2tIO+7dXUFBAAKh27dqkqKhI+/fvJ47jKCAggEJCQoiIyN/fn8aNG0fPnj2jhg0b0q1bt/hROKyt+fkEz53y8vJ09uxZsrCwoGPHjlFhYSFZWlpSjx49aNeuXbRy5UrKysqihw8fkqenJ6WkpFCnTp2kHD0jU6SaEpMxwm8Anjx5grt37/J/Dw8Ph52dHUaNGsUvmp2VlYWePXuKLNjMFpeTjIKCAgwaNAgcx/EjpQTevXuH3r17g+M4vqwY8RH+nZ8yZQp0dHSgq6sLc3NzTJw4EUDpgoy9evWCqqoqdHV1YWVlhVatWrFFgCUoLS0NixYtgqGhIfr27StyLi8vDwcPHoSenh6GDBkipQgZRvqEN8OYN28eWrdujalTp/IbA5w6dQpGRkZwd3fHyZMn+bpNeBFgNppA/KZMmYJBgwbB3NwcysrKaNy4Mc6cOcO3R6wvJj2JiYlYunSpyAyCM2fOwNzcHAMHDsTDhw/545mZmfxoREY8Ll++jMOHD4vUS7m5uTAwMMDOnTvx8eNHODg4oF27dggLC+OvEYzWAdjIQnEpr54aM2YMqlatit27dwMA4uPjMWPGDGhpaUFdXR3169dn/WdGKlhSSgq8vb2hp6cHVVVV2NjYIDY2FkDpLmL29vYwNDREjx490KRJE5HtnlknSLIKCwvh5uaG6tWr4/LlyyLn3rx5g/79++P58+dSik72vHjxAq1atcKDBw/w5MkTrFmzBnXr1sWYMWP4a86dO4fw8HBcu3aN7yCxzo7kpKWlYdWqVahbty68vLxEzuXm5uLo0aNISEiQUnQMI13CbXhgYCA8PT1Rq1YtqKioYOrUqcjKygJQ+oBta2sLXV1dGBkZwcLCgu16JEHbtm1D9erVcefOHbx58wavXr2Cubk5rKysEBERwRJTUlJSUoJ3796hVq1aqF69epmp+eHh4WjUqBGGDRuGK1euSClK2RIREQGO46CiogJra2scP36cf+G+bds2DB06FEBp4sPBwQEdO3bEoUOHRH4Gu4/EQzhJ+H1iaezYsVBSUuITUwUFBfjw4QPCwsIQExPD+s+MVLDd9yRAeOpRSEgIzZgxg1auXEna2tr0xx9/UE5ODm3YsIHatm1LDx8+pOvXr9OdO3dIV1eX5s2bRwoKCj/ctYr57/D/Q/IfPXpEb968ISKixo0bk5GRERER9e3bly5dukQhISHk4ODAf46VieTs3LmTjh8/TjVq1KAdO3aQvLw8ff36lQ4dOkQrV66ktm3b0vbt28t8ju3qJh6Ce+bJkyf06tUrUlZWpkaNGpGuri59/vyZ9uzZQ3v27KG2bdvSunXrpB0uw1QoCxYsoDVr1tCmTZtITU2N9u7dS8+ePaM2bdrQkiVLqGrVqvT8+XN6//49ffnyhZydndmuRxLk4+NDDx8+pIiICL4NSUtLI1tbW6pWrRotWrSIOnfuzNoWKdm3bx9NmTKFrK2tafXq1VS/fn3+XEREBI0cOZKcnJwoICCALWouZufPnycvLy+qW7cu5eTkkIGBAUVHR9P48eNJWVmZli5dSnv27CEHBwdKTEyk7t27U4cOHWjt2rXSDv23BqEd9DZv3kzR0dFUp04d6tSpE9na2hJR6aYAgYGBtH37durbty9VrVpV5GewZxxG4qSaEpMxR44cwbJly7BmzRr+WFFREVq3bg0zMzNERkbyWWnhDDfLVIvf8ePHUb16dTRr1gyKioqwtbXF8uXL+fN9+/aFrq4uIiMjpRilbMrKyoK3tzcMDAxgb28vci4jIwNbtmxBgwYN0K9fPylFKFsEbzWDgoJgbGyM+vXro0WLFrC1tcWLFy8AlG7S4O/vj6ZNm2L48OHSDJdhKoySkhKkpqbC2toaGzZs4I/n5uZi1qxZqF27Nnx8fPipfMLYFArxE3zHEydOhJ2dHX9cMP0rKCgIioqKaNasGa5fvy6VGJlSe/bsQa1atTB58mTEx8eLnDt37hwbkStB4eHhsLe3h6enJ4KCgnD27FnY2dlhyJAh4DgOgwcPxrdv3wAAycnJrC4TM+GRZwsXLoSqqiqGDBmCmjVrolOnTiIbAo0bNw5Vq1bFli1bRKaWM4w0sKSUhOTn50NDQwMcx5WZ1lJcXIw2bdqgSZMmCA0NZUkoCbt//z40NTWxZcsWZGZm4sWLF5g4cSKaN2/O74hYXFyMLl26oE6dOmx9AjErb72UpKQkzJ8/H6qqqmWG7H/9+hWrVq2Cq6srW2tFQiIjI6Gurs7v2HL8+HFwHIfatWvzO1N++vQJ8+fPh52dHT58+CDNcBmmwigqKoK1tTVmzZoFQPQBws7ODtra2hg+fDjy8vKkFaLM+FF7ERMTAzk5Ofj7+4scP378OFxdXeHp6ckerCVAcG/cuXMHR48exa5du5CcnMyf37FjB/T09DB58mSWhJIC4borNDQU1tbWcHV1RUJCArKzs3Hnzh0MHz4c9+/fB/DX08mYn+/u3bsYPnw4P5X1+fPn6NOnDxwdHbFz507+uoEDB8LR0VFaYTIMj03fkwDB8O/s7GxycHCg7OxsOnjwIDVv3pwfXllSUkKNGzcmS0tL2rdvn5Qjlg2Cctm/fz8tX76cbt68SSoqKkRE9PbtW1q2bBk9fvyYgoKCSEtLi4qKiujjx4+kp6cn5ch/X8LT7R4+fEiZmZmkr69PxsbGlJ2dTStXrqQjR46Qm5sbzZs3j/9cTk4OValShTiOY1P2xCw7O5smTZpEhoaG5OfnRykpKWRtbU3W1taUmppKr1+/psjISKpbty6lpqaSnJwcaWhoSDtshpG48uqi/Px8GjZsGH3+/JkOHjxIOjo6fD/gjz/+oJs3b5KDgwP5+/uzekyMIDS95dChQ/Tq1SsyMzOjli1bkr6+Pvn7+9Ps2bPJ19eXhg0bRhzH0dixY8nOzo58fX2JiE1vESdB+QQHB9OoUaOoUaNGFBcXRy1btqTBgwfTwIEDiYgoMDCQFi5cSJ06daKZM2eyHfYkTPg+OnXqFC1YsICMjY1p6tSpZG1tzV/H+mWStX//ftqyZQsVFBRQWFgYv4v406dPac6cOfTlyxcaOnQoubu7E9Gf5SNcngwjcdLMiP2u/mq0xtevX2FiYoIWLVrg3r17IudKSkrY2wMxES4Twdudjx8/Aih9w1O7dm1+0XLB+QcPHoDjOFy8eFGywcoo4bdus2bNQt26dVG/fn3o6+tj/PjxePPmDT59+oS5c+fCzMwM8+fP/8ufwYhPVFQUrl+/jvT0dDRr1gyjR48GAOzduxccx0FVVRVPnjyRcpQMIz3Cbc6LFy/w5s0bvHnzBkDp7mGampro06cPEhISUFBQgMLCQvTt2xc7duzg6zE28lM8hNsJHx8faGlpoXHjxqhXrx769u2Lly9fAgA2b94MVVVV6OvrQ19fH02bNmULzkvQxYsXoaOjg+3btwMAbt++DQUFBdjZ2YmM9NiwYQMaNmzIRuSKkZeXFz8K+nvC98LJkyfRsmVL9O/fHzdu3JBUeMx3Ll26BBsbG6ipqeHo0aMi554+fQoXFxeYm5vj1KlTAErLkLU3jLSxpNRPJnxTb968GV5eXujZsyeuXbuG1NRUAKWJqTp16qBly5b8sFZhLDElHs+fP8f+/fsBAMeOHUPz5s2RmpqKhw8fQl1dHXPnzhWZU52cnAwLCwtcu3ZNWiHLpNWrV6NGjRq4dOkSAGDUqFFQV1fnyyE5ORnz589H9erVERgYKM1QZcJfPXydPHkS9vb2SEpKAlD6ENG5c2cMHz6c7UzJyCzhe8bX1xempqYwMDCAnp4ev6bk48ePoauri2bNmsHGxgbNmzdH/fr1+fafPSCI38OHD+Hq6orbt28DAA4cOIAOHTqgU6dOfP315s0bREREICIigi8btsSC+BUUFGD+/PmYPHkyACAhIQEmJiZwc3ND27ZtYWpqin379vHXZ2RkSCvU315WVhbq1KmDhg0b/rBdF67zTp06BVtbW3Tq1AmPHj2SVJgy6a+SSbGxsbC3t0fXrl0REREhcu7Ro0fw9fVlz5tMhcKSUmIyffp01KhRA2PHjoWLiwtq1KiB1atX4+3btwBKE1P16tWDkZER/1aOEa+lS5eC4zhMmDABHMfxW6ECwK5du8BxHGbPno179+7h8+fPmDFjBvT09PD+/XspRi07iouLUVxcjL59+/JreYWGhkJNTY1fu0iwzsr79+8RGBjIGlQxE3Q0r127hoCAAOzbtw/Z2dn8+a1bt6Jy5cr8PTJz5ky4u7uLXMMwsmrZsmXQ1NTEmTNnEB4ejuXLl4PjOPj4+AAoHa27Zs0aeHt7w8/Pj092sHpN/A4dOgQHBwd069ZNZJ3I48ePo0OHDujcuXO5D9SsbCTn8ePHePLkCbKysmBjY4MRI0YAAJ48eQJVVVVYWFhgz549ANjINXFLS0uDjY0NGjRogGfPnpV7jXAZHDt2DB4eHiy5Lkbf10WHDh1CQEAADh06hKysLADAlStX0Lp1azg5OeHs2bP/6OcwjLSwpJQY7Nq1C0ZGRrh79y6A0mw1x3HQ09PDkiVL+Ae49PR0uLi4sApBgpycnKCgoABPT08ApY2ooCHds2cPatSoAT09PZiZmUFfX58vQ0Y8vu9I5ufnw97eHrGxsbh27RpUVFSwZcsW/tzatWv5RRsF2P0jXuHh4VBUVIS9vT04jkPv3r35UWuvX79G69atUbNmTXTu3BlVqlRhb0YZmSV4ACspKUF+fj46deqExYsXi1xz5MgRcByHgwcPlvsz2CgcyVixYgUaNWoEfX19fPr0SeTc8ePH0aVLF1haWiIxMVFKETKCtv3ChQto0qQJP0rnxo0bcHR0xIABA/gpsYx4CPevEhMTUa9ePTg4OPyjxJQAS0z9fNOmTUPnzp358pk8eTK0tbXRoEEDmJmZoVu3bkhPTwdQmphycHBAr169cOLECSlGzTB/ja0695MVFhZScXExTZs2jZo1a0ahoaHUsWNH2rNnDw0ZMoQWLFhABw4coNevX5O6ujodPXqU5OXlqbi4WNqh/7YgtJZ/pUqVqE2bNrRz507auXMncRxHHMcRABo6dChduXKFX/g8OjqamjVrJsXIf29Xrlyh1atX0+rVq+nTp09ERKSkpEQmJibUt29f6tSpE23atIlGjx5NRESZmZkUEhJCDx8+FPk5bKFZ8RDcN2FhYbR27Vq6evUqPXnyhJ4/f05LliyhGzdukLGxMa1atYqGDx9OZmZmdPv2bTI3N5dy5AwjeQD4hXyfPn1KSkpK9PLlS/5YcXExFRUVkaurK7m7u9PBgwcpPz+fioqKRH6OgoKCxGP/3aGc/Xy8vb1p0qRJpKamRhMnTqR3797x5/r27UuDBg0iBwcHMjAwkGSojBBB256bm0vZ2dn0+vVrIiKKiIighg0b0rZt28jQ0FCaIf72BGUwc+ZMmjx5MqmoqNDVq1fJ1dWVXrx4Ueb68hbJZguc/1yFhYWkp6dHaWlpNGzYMEpISKDExESKioqiW7du0fz58+nLly/Us2dPysjIoNatW9PixYvpxYsXdP36dWmHzzA/xHbfE4OEhASqUqUKFRYWUs+ePWnYsGE0efJkSk5OJjMzMyopKaHNmzfT4MGD2U4HYib4fu/du0cAyNLSkoiI5s6dS4sXL6Zt27bRiBEj+Ovfvn3LOqESsHfvXlq8eDF169aNzMzMaNSoUfy5uLg4GjVqFH39+pUePXpERETp6ek0aNAgyszMpCtXrrBElBgJ7pn379+ToqIirV27lnr16kUtW7YkotIHbhcXFzIwMKB58+bxO+yw3XUYWSXcjk+bNo2Cg4MpPj6epkyZQufOnaPQ0FCqX78+v1vbpEmT6NWrVxQWFiblyH9/wvXS+/fvSUFBgZSUlKh69epERLR+/Xo6evQo1a5dm5YuXVru7rqsbpOupKQkcnFxoaysLFJQUKC3b9/SxYsXqWnTptIOTSZs3LiRfH19KSIigjQ0NOjz58/k5eVF37594+s2RrK+fftG+/fvp+3bt5OysjKpqKjQkSNHqGrVqlRcXEynT5+mJUuWkJKSEp04cYLU1dXpwYMHZG5uzvrPTIXFWlkxMDExoZo1a9K7d++osLCQ2rRpQ0REqampNHToUFqyZAkNGDCAiMp/q8D8HBDaUrhHjx509uxZSkhIICKi+fPn06xZs2jMmDEUGBhIWVlZtGTJEnJ1daXs7Oxy36wyP8e+fftozJgxtGTJElq2bBmfkFqzZg2dPHmSGjVqRBMnTiSO46hmzZpkb29PXbp0oU+fPtGlS5fYyEIx4ziOjh07Rq1btyZzc3Py9/enmJgY/ryZmRkdP36cUlJSaMqUKfybN1aXMbJIOCF1//59SkhIoH379pGcnBw5OzuTvr4+TZ8+nRISEkheXp7y8/MpLi6OatasKeXIf3/CyaQFCxaQq6srNWnShCZOnEjBwcFEROTl5UWurq70+vVrmj17NiUlJZX5OSwhJR6Cftb9+/cpNjb2h9cYGhrSgQMHaNy4cTRkyBCKiYlhCSkJio+Pp27dupGNjQ3Vr1+fWrVqRWFhYSQnJ0eDBw+m58+fSztEmVFSUkJERJUrV6bBgweTh4cHZWZm0qNHj6hq1apEVDq6rVu3bjRr1iwqLi4mOzs7ys7OJgsLC9Z/Zio2iU8YlCHh4eHQ0tLCvn37cOfOHTg5OWHQoEH8ebYWjvidPXsWKioq2LRpk8hipgJ+fn7gOA7W1tZQUVHBnTt3pBCl7Hjy5AkaN27MrxMl4OLiAo7j0KlTJ5w7dw4AkJKSgmXLlmH58uXYs2cP2/lIQl69egUzMzOsWLECBw8eRIsWLWBvb4+goCCR6x4/fgxbW1t+5z2GkWX79++Hg4MD2rVrJ7LQ/6FDh9CxY0eoqamhbdu2sLCwQKNGjVBQUACALdAsCXPmzIGmpiaCg4MRHh6OLl26oE6dOiK7t61fvx4NGjTAwoULpRip7BD83gcFBaF27drw8fFBcnJyudeyNYmka+jQobC0tOT/LuiDrV+/HhzHwdDQkPUDJED4Prh37x6ys7NRUFCAwMBAGBsbw8XFhW9XgNJnzKNHj2LUqFHseZP5JbDpe/+D8oZy4wfT8Nzd3SksLIxUVFRIV1eXrl+/ToqKipIKVWYBoMLCQho2bBhpamrShg0b+DUJjh8/TsXFxTRnzhyqVKkSRURE0MePH6l169ZUp04daYf+Wzt37hyNHj2azpw5Q/Xr1yc5OTkaP348nTt3jtauXUtr1qwhRUVFGjNmDPXs2bPM5wXTXxjxuHfvHu3Zs4cKCwtp/fr1JCcnR8+ePaOJEycSABozZgz16dOHv76wsJDVZ4xMevHiBaWnp5O8vDxZWVnRpk2bKCAggDIzM+nx48ekpaXFX/vy5Uu6fPkyJSQkkI6ODnl5eZGCggIVFRWxNaTELCoqiiZNmkTbt28nGxsbunDhAvXo0YOsrKwoJSWFFi5cSP379yciouPHj5OzszNrYyTkzJkz1KdPHwoICKBBgwaRioqKtEOSaT+apnr9+nUaNGgQjR07lqZPn84fDwoKovPnzxPHcbRhwwZ234iR8DOmr68vnT17lmbNmkXOzs6Un59P+/fvp61bt1LdunVp7969fL9MuExZ/5mp6FhS6l8Srhj2799PlStXpj59+pCcnJzIOeGb/+bNmyQnJ0dWVlYkLy/POqJi9H1ycOTIkZSRkUFTp06lXbt2UVJSEiUlJZGcnBzp6OhQZGQkq6QlaPHixbRmzRpKTU3lj6WkpFBxcTHp6+vT06dPydPTkwDQoUOH2CKmElJSUkK5ubk0btw4OnPmDDVu3JguXLjAn3/y5AlNmjSJFBQUaMiQIfz04x8l4xnmd7Znzx5avnw5vX//nlRUVMjV1ZXWrFlDhw4dIj8/P7K0tKSAgIC/nKLHHhAk4927d7Rp0yZauHAhnT9/noYOHUpLly4lOzs76t27N3379o1mzZrFb6hBxMpGEnJzc8nd3Z1MTU1pwYIFlJWVRUlJSRQUFEQaGhrk7u7OklQSJNyWh4aG0ps3b6h58+b8Oqzz5s2jy5cvU5cuXWjWrFn08eNHGjduHDVp0oSWLFlCROy+kYSFCxfShg0baO/evdSiRQvS0NAgotI1pvbt20fbtm2jBg0a0M6dO0lJSUnK0TLMvySN4Vm/KuGhk4mJiahVqxYcHR1x+vRpka2gBcobLsmGUIpfTEwM4uPjAQCbN2+Gvb09KlWqBDc3NwQFBeHbt29Yu3YtOnXqhPz8fClHK1sOHz6MKlWq8FP0hAnuoeXLl6Nbt24iU2AY8RDUV4Ih348ePcKIESOgra2NTZs2iVz79OlTWFtbw9nZGZmZmRKPlWEqgi1btqBSpUrYsmULzp8/j/Hjx6NGjRpYvXo1AGDdunVo1aoV3N3dkZKSAoC1+9IiqN9ycnJQXFyM3r17Y/bs2Xxb06tXLzRu3BhDhgxBSUkJm0opYU5OTujZsyeSk5MxatQoODo6onHjxqhatSrGjRsn7fBkhvDv/fTp01GtWjWYm5tDUVERkyZNwrt375CWloZ58+ZBT08PampqMDY2RpMmTUSmizHiU1JSguTkZDRr1gz79+8XOSdoX/Ly8hAYGAgDAwPMnTtXClEyzH/Dhuv8C4IhkN7e3vThwwfS1dWlu3fvkre3NwGgLl26iIyYKu+NAXuLIF4FBQXUr18/0tDQoPDwcBozZgx16tSJ0tLSqEWLFnzZvHz5khQVFdmCfxLWokULUlBQoK1bt1L9+vXJyMiIPycnJ0dZWVl09epVatCgAb9oIyM+HMdRbGwseXl5UVhYGJmbm5O3tzcVFxfTgQMHSEFBgTw9PYmIyNTUlPbu3UuVK1ematWqSTlyhpG80NBQGjt2LJ04cYKcnJyIiKhly5Z0/fp1unz5Mk2ePJm8vLyIiOjo0aPk6+tLCxYsKHdHN0b8BCM/qlSpQllZWRQXF0ctWrQgOTk5+vr1K1WuXJlmz55NLi4uxHEc2+BEjFDOqFpXV1dasWIFGRgYUO/evWn06NHUv39/CggIoOPHj1Nubi5VqVJFShHLDkG53L59m+7evUtnz54lW1tbfpfk3Nxc8vX1pblz59LEiRMpIiKC1NXVqWPHjmz2h4RwHEd5eXn09u1bMjExIaI/p+bJy8vTt2/f6Nu3bzR48GDS1tambt26STlihvn3WC3yL23fvp0CAwMpKiqKdHR0CAA5OTmRn58fcRxHnTt3LjOVj5EcJSUlunHjBrVr145cXV3pwIEDVKdOHX6tqPj4eNq6dSvt37+frly5QsrKylKOWLbUqVOHtmzZQsOHD6dKlSqRt7c3v4vOmzdvyNPTkz59+kQhISFExKaHScLnz5+poKCAXFxcKCgoiExNTcnb25v8/f1p165dJCcnRyNHjiQiYls/MzIrPz+fzp49S3Xq1KE3b97wx1VVValx48aUlZXFP0R7eXkRx3G0fv162r17N/n6+kox8t/fP2kn5OXlycHBgU6ePEmFhYV05coVys7Opn79+hHHcT9cT4f57wTlEx0dTVeuXKHCwkJq0qQJDR48mDp06EBPnz6ltm3b8tc/ffqU9PT0WKJDgjZv3kw3b94kbW1tatmyJRERDR06lOTk5GjhwoX8+p/m5ub8GmxEpVP2WDn9fOXVaVpaWsRxHEVGRpKNjQ3JycnxUyZv375NcXFx5Onpyb8wYdMpmV+OlEZo/bKmTZuGzp07A/hzutGXL19gamqKJk2a4NSpU2ynEAkSDDsWDF8VfPfv3r2DsbEx7O3t+al8N2/ehKurKywtLXH//n3pBMygqKgI27dvh6KiIvT19dGlSxd06NAB1tbWsLa25oeDsykvklFcXIwzZ86gVatWsLW1xadPnwCU7q43cuRImJmZYc+ePVKOkmGkLzk5GRMnTkTLli2xZMkSAMDp06fBcRyioqIAiNZbx44dY/WYmAn3tzIyMv7y2suXL2PEiBFo3rw5nJ2d+baG9dnELygoCNWrV4ezszP69++PqlWrYtKkSSLXPHv2DNOmTYO6ujoePnwopUhl04IFC6CgoABTU1O8evVK5Ny+ffvQsGFD9O/fv8w55ucTbjNSU1ORkZGB9PR0AMCMGTPQuHFj7NixQ+T6Tp06YdCgQWwKMvNLYwud/0OCjLOXlxfdvn2bbt68SUREeXl5pKysTCdPniRnZ2dq27YtzZkzhxwcHKQc8e8J5bw9iIqKos2bN1NgYCCpqanx17x//57s7OyoXr16tGPHDjI2NqabN2+SsbHxXy5Ay0jG/fv3aceOHfTixQsyNDQkS0tLGj16NBsOLkaCe+PBgwfUoEEDqly5Mn/8zJkztHTpUiopKaETJ06QlpYWPXjwgLZt20be3t5kbGws3eAZpgL48OEDLV68mO7du0dGRkZ08uRJWr9+PQ0bNowfbfP9qBv2xlo8hL/nxYsX0+3bt2ndunVkYGDww88UFhZSUVERVa5cmTiOY22NmAh/ry9evKAOHTrQ9OnTafz48fT8+XOysrKiIUOG0KZNm4iI6Nq1a7R37166ceMGHThwgCwsLKQZ/m+tvH40Ueloqblz55KnpyeNHTuW9PX1+XPbtm2jS5cu0f79+9mIQjHKzs7mF/hfvHgxXb58mV69ekUtW7akESNGkKWlJU2fPp0uXLhA1tbWpKOjQ3fu3KGMjAy6e/cuKSoqshkGzK9Levmwiu1Hb85iY2MhLy+PZcuWiRw/ceIEhgwZAnNzc3Tq1EkSIcocQZl8+vQJt27dwp07dwAA0dHRUFBQwIABA/D161cAf75pOHXqFDiOg52dHZKSkqQTOPOvsJEFP5/wwuRv376FpaUlunXrhry8PP54YWEhgoKCoKenh86dO/MjpthmAAwjKjk5GV5eXqhRowZ69erFH2d1l3R4e3ujVq1a2LFjBxITE//yWuGRBGyE1M936NAh/s+FhYUASkeoWVtbAyjdJEhfXx9jxozhr3v8+DGKi4tx9epVvH//XrIByxjh3/n09HQkJyeLnF++fDn09PTg5+eHd+/e/e3PYH6evXv3Yt68eQAAX19faGpqIjg4GKdOnYKjoyPU1dWRlZWF169fY+/evWjdujX69OkDLy8v/l4T/JdhfkUsKVUO4U7LgQMHsGDBAhw7doxPaqxatQpKSkrw8/PDmzdvkJiYiO7du2PVqlV48OABOI7D5cuXpRX+b0nQCMbFxaFVq1bo0qUL+vTpw1fAMTEx0NDQgIuLi8gQ/oiICDg5OaFJkyZ4/fq1NEJn/gIbaix+qamp0NLSwrZt2wCU7tCyadMm2Nraol+/fiKJqeLiYrRq1Qocx6FDhw4oKipiZcQw5fjw4QO8vLxgY2Mj8pKK3S+Sdfr0adSqVQvR0dH8sczMTDx//pztEiphL1++hJaWFtq1aydy/ObNm7Czs8PVq1dhaGiIUaNG8Qnc27dvw93d/W+Ticx/J5xMWrBgAVq3bg11dXWMGzcOZ8+e5c8tW7YM+vr6mDdvHt68eSONUGXOli1bwHEcTp8+jY8fP8LGxoafEh4REQFVVVVs3br1L38GS0gxvzqWlPqOcIfSx8cHWlpasLCwQL169eDs7Iznz58DALZu3Qo1NTXo6emhVq1asLCwwLdv3xAXF4c6derg6dOn0von/HYEZfL48WOoq6tj1qxZePPmTZm3NdHR0dDU1ETfvn0RHx+Pb9++wc/PD3PmzGGVNSOzcnJyMGXKFCgpKWHXrl0AShNTO3bsQIsWLeDi4sI/IBQVFWH06NHYuXPnD9+SMgxTKiUlBV5eXrCzs4Ovr6+0w5FJO3bsgI2NDQDg7t27WLhwIerWrQs1NTWMHz8eaWlpUo5QdiMekA8AADA0SURBVOTn5yMsLAyNGjVCx44d+eNxcXFo2rQpVFRU4O7uLvKZyZMno1OnTqycJGj27NnQ0dHB7t27ERkZCVNTU7Rv3x5Hjhzhr1mxYgXk5eVF1i5ixGPv3r1QVFREeHg4AODFixeoWbMmPnz4gLCwMKioqGDz5s0AgNzcXGzZsoVfK5dhficsKSVEeOj9gwcP4Obmhtu3bwMADh8+jI4dO6JDhw548uQJACApKQmnT59GZGQk/9kZM2agSZMm+Pjxo+T/Ab+xtLQ02Nvb448//hA5/n1i6t69e9DV1YWenh7Mzc2hoaHBFjVnZN7Xr18xZ84ccByHAwcOAPgzMWVlZYXWrVsjJCQEXl5eaNiwYZkh/QzDlC8lJQVDhgyBp6cnGyUlZuVNG7px4wY4jkPv3r2hp6eHoUOHYufOndizZw8UFRVx7949yQcqwwoKCnDq1Ck0aNAAHTp04I/v3LkTHMfBx8cHN27cwOPHjzFlyhS2qLmERUZGomHDhrh27RqA0vtHSUkJpqamsLOzQ3BwMH/t/v372ZRkMdu1axc4jhNJ4r558wbt2rXDvHnzoKamxiekAOD+/fvo27cvrly5Io1wGUasWFIK4LPTAocOHULr1q3RtWtX5OTk8MeDg4PRsWNHdOzYEQ8ePBD5zJMnTzBy5EhUr16dJUHEIC4uDiYmJrh8+XK5HVPhh4FPnz5h7dq12LBhA168eCHJMBmmQiksLBS5NwRT8/bu3QugNDF18uRJODo6wsjICBYWFrh79660wmWYX1JaWhrfLrHElHgIt/tPnz5FSkoKP7omLCwMgwcPxv79+/mEenp6Olq0aIGYmBipxCuLBL/7+fn5OHnyJBo0aCAylW/NmjUwNzeHqqoqLCws0LRpU5Y0lLAnT55g/fr1AEqnhWloaGDPnj14/fo1NDQ04OjoiJ07d4p8hiWmxGPbtm2Qk5ODh4cHatWqBS8vL/7cyJEjwXEcvL29+WPZ2dno1q0bunTpwtb1Yn5LMr/73qpVq+jKlSsUGhpKAEhOTo5WrFhB+/bto/T0dLpz5w7VqFGDvz4kJIS2b99OHz58oKCgIKpduzYVFRXR1atXKSQkhEaNGkXm5uZS/Bf9ng4ePEjDhg2jgoIC4jiuzO5GRES5ubn08OFDsrGxkVKUDCN9SUlJFBoaSn/88QcR/blD1YoVK2jlypXUtm1bOnbsGO3cuZPc3d2JqHQ3nsTERKpevTqpq6tLL3iG+YWV1y4xP5evry8dOHCA5OXlqWnTpjR37lxq0qQJFRYWkqKiIhUVFVF+fj65uLhQZmYmXblyhZWJFOTl5VFUVBRNmzaNatWqRRcuXCAiooSEBPr69StVrVqVtLW1SUNDQ8qRypb8/HzKyckhZWVl6tu3L9na2pKvry/JyclR69atKT4+noYMGUIrVqyQdqi/tYCAAJoyZQqFh4dT165daevWrTR79mxyc3OjDRs2EBFR79696fr169S/f39SVFSke/fuUWpqKr/LHmtvmN+NzO+D26NHD5o0aRK/TXrTpk3Jx8eHNDU1KSAggCZOnEgrVqwgQ0NDIiJydnamvLw8un37NhkZGRERkYKCArVp04bs7OyoUqVK0vzn/LaMjY1JQUGBgoODqW/fvuVWxDt37qSwsDA6deoUKSkpSSFKhpGu4uJi2rRpE4WEhNC3b9/Ix8eH5OTkaMmSJbRq1So6cuQIOTo6Uv369WnEiBEkLy9PQ4YMIY7jqHbt2tIOn2F+aewB4eeD0PbmZ8+epd27d1NgYCDFxcXR1atXydXVlQ4cOEDNmzen3NxcOnDgAO3du5e+fftGN27cIDk5OfbwJkaC8rlz5w7du3ePOI6jVq1akampKbVv355WrlxJ06ZNo/bt21NUVBSZmJhIO2SZVqlSJapUqRJlZWVRcnIyqaiokJycHH379o3q1q1L06dPp27dukk7zN9es2bN6ODBg9S1a1ciIurfvz9xHEe+vr5ERLRhwwYKDQ0lX19fevHiBRUVFZGdnR3Nnz+fFBQUqKioiBQUZP4RnvnNyOxIqfnz59PcuXP5v0dERNDQoUNp8eLF5OnpSUREGzdupCNHjpChoSEtXbqUDAwMyvyc4uJikpeXl1jcsur9+/dkaWlJNjY2tG7dOj4hKNxhnTZtGikqKtKSJUv4Ywwja96/f0/+/v4UHR1N7u7ulJWVRcuXL6d9+/bxHaCcnBzy9/enBQsW0KFDh8jNzU3KUTMMw/zYgQMH6NmzZ6Strc2PAr158yb5+/tTXFwcHT58mJo1a0YhISF0584dmjdvHnt4EzNB/ys4OJi8vLyoZs2aVLVqVXry5AmFhISQvb09ffv2jSIjI2nGjBlUpUoVio2NlXbYvz3hfvGPfP78mVxdXUlDQ4OsrKzo0qVL9OXLF4qJiWGJXAkSLqvMzEw6fPgw+fr6ioyYys/PFxnwwJ47md+WdGYNStetW7egpqaGzp0788fu3r2LMWPGoFGjRiK7TWzYsAGtW7fG0KFD8fr1aylEywgEBQWhUqVKGDJkCOLi4vjjOTk5mDlzJoyMjPjdERlGlqWkpGDChAlo0KABFBQU+K2FhXehzMrKwuLFi/mNGxiGYSoK4TVTYmJi0LFjR1SpUgUrV64Uue7mzZvo06cPzMzMcOvWLZFzbC0c8bty5Qq0tLSwbds2AKX9a47joKyszK/XmpeXh6CgILRo0QJv3ryRZri/PeH7JjU19S+vvXbtGtq3bw8bGxt069YNBQUFZX4GI1lfv37F1q1boa2tXWZjJ4b53cnkSKm8vDy6cOECeXt7k56eHp0/f56IiB4/fkxbtmyhyMhImjZtGnl4eBAR0ebNm2ndunU0YMAA8vPzk2boMq2kpIS2b99OEyZMoLp165KtrS1VrlyZ3r9/T9HR0RQREUHNmjWTdpgMUyF8/PiRlixZQpcuXaKhQ4fS1KlTiYhERg7gH7xRZRiGkZaFCxcSx3FUp04d2rx5M6WkpNC5c+eoTp06/DUxMTHk4+NDtWrVokOHDkkx2t+XYOSM8AiavLw8Wr58OQGg+fPn0/v378nOzo7at29PxcXFdOTIEYqIiCBHR0fKz8+nwsJCUlFRkfK/5PclXDb+/v706NEj8vX1pQYNGpS5VtD2Z2ZmkoKCAikrKxPHcWxkYQWQmZlJR44codGjR9OaNWto4sSJ0g6JYSRCppJSrq6u1L9/f+rTpw8/pHjatGmkr69PkZGRRET06NEj2rp1a5nEVHBwMPXq1YsNmawAYmNjyd/fn+Lj46latWpkZ2dHI0eOpHr16kk7NIapUD58+ECLFy+mW7dukbOzM02fPp2I2PBvhmEqJuEH65MnT9Lo0aPp3LlzZG5uTqdPn6ZVq1ZRUVER7dq1SyQxFRcXR2ZmZmzKkRgIyiQxMZHOnTtHlpaWZGVlRUREd+/epfz8fDI3N6eOHTuShYUFbd26la5fv06tW7cmotLlMTp16iTNf4JM8fb2pr1791JAQABZW1uL3Cd/hU3ZqzgyMjLo8uXL1KNHD9ZXY2SGzCSlcnNzycPDg4KDgyk4OJi6dev2l4mpbdu20YULF2jUqFEiWWr2MFcxsHJgmH9GkJi6d+8etW/fnubPny/tkBiGYf7S/v376fXr18RxHM2ePZs/HhYWRuvXr6eCggLavXt3mQ0a2IP1zyX4Ph89ekT9+vWjRo0akYeHR5nFsGNjY2n8+PG0b98+MjU1pbi4OFqwYAEZGRnR8P9r786jqizXN45/2YAgo6aIs4hToB5T8DiTU2VOpZGmKZVTSIamlnWcc8gBzaOmKIiomAMKVISKSJpThEqSqViQlYgzCqgx//4o908qyzoqCNdnLVbu/Q4877K93e+17+d+XnkFFxeXYrqCsiU8PBxfX18iIiJwc3MD4Oeff+b06dM8+uijxTw6+SdUvSZlRZn4l/vGjRtYWVmxbNkyhg0bxrPPPktUVBSWlpZ07doVPz8/zpw5Q9euXQFo2rQpr776Ki1atCAuLo7CwkJuZXcKQkqG2z90lpFcVeQfqVq1KhMnTqRBgwYcOHCAy5cvF/eQRESKuPXveGFhIQUFBbz99ttMnTqVpKSkIvv17t0bX19fLC0t6dGjB2lpaUW2K5C6twwGAydPnuTxxx+nb9++LF269A9XZzt//jyHDx8mLy8PgI0bN5KVlcW0adMUSD1AP/30EzVq1MDNzY3jx48zd+5cHnvsMVq2bGmcwi8PFwVSUlaU+kqpbt260aRJE/z8/IBfSiL/85//EBgYSERExO8qpmrVqmXsMZWSkoKTkxMGg0G9V0TkoXb+/HkAHB0di3kkIiJ/7PLly1SqVIm8vDw6duzId999x6ZNm+jQoUORwGnz5s0cOHCABQsW6MvC++jnn3/Gy8uLKlWqGFcDA8jNzeX8+fNcv37d2LOoZ8+eREVF0bJlS44fP86+ffto1qxZcQ291Puj+5IdO3bwyiuv8Nhjj3Hq1Cnatm2Lm5sbVatWZcCAARw5coTHHnuseAYsIvInSn0o9fXXX9OwYUMsLCzIzc3F3Nz8T4OpCRMmYG5uzldffWU8h8rBRURERO6fFStWcOTIEcaMGYOLiwu5ubm0aNECgKCgINzd3f/wy0FN579/8vLy6Ny5M/369WPUqFHAL8HH9u3bCQoKolKlSjg7OxMTE8PNmzdZt24dN27coEePHurzeR/dfl/y3XffYWpqipmZGbVq1WLjxo2EhYXRs2dPOnfuTM2aNfn222/x8vIiODj4Dxufi4gUt1IfSt3i5+dHdHQ0W7duxdbW9o7BVGRkJGFhYYSEhCiIEhEREXkA/Pz88Pf3p0+fPgwZMsQYTDVv3hyDwUBQUBBubm6qWn+AMjIyaNWqFR06dGDcuHGEhYWxZs0amjRpgoeHBzY2NsyaNYu+ffsyf/784h5umXB7hdSUKVPYvn0758+fx8HBgUGDBjFmzBjjPvn5+dy4cYOBAweSmZlJbGys7m1EpEQqM6HUvn376N69O927dycgIKBIMLVq1SoiIiJ4+umnycnJoVy5coC+fRMRERG51+5Ugb58+XL++9//0qNHD4YNG2YMptzd3Tl37hx79uxRw+YHLDY2lqeeeooaNWpw5coV5s+fT5cuXahfvz65ubn07NmTatWqERwcXNxDLVNmzJjBokWL2LJlC7Vr1+bdd99l3bp1HDt2DFdXV27evElYWBiBgYFkZGTwxRdfYG5urtkfIlIilcruabt27SIxMZG0tDQmT56Mra0t7du3JyYmhqeffpohQ4YQFBREhQoVmD17NgaDgR49erB//37atGljPI8CKREREZF769ZN8RdffIGTkxNVq1YFYOTIkRQUFLB48WIKCgrw8fGhQYMGxMfHM3ToUE0JKwadO3cmJSWFCxcuUKdOHSpXrmzcZmpqir29PbVq1TI2q1cl2/2XmZnJwYMHWbVqFZ06dSIyMpKPP/6Y5cuX4+rqSl5eHqampty8eZN27doxbdo0zMzMtJKbiJRYpa5SKjAwkIkTJ9K0aVOOHz+OnZ0dX3/9Nebm5gDExcXx9NNP06VLF4KCgrC1tSU9PZ1Vq1YxZswYvVmLiIiI3Ae3V6DHxcXRsWNHpk6dytChQ3FwcDDut2jRIiZMmICvry+DBw/mX//61x+eQ4pPTk4OM2bMICgoiN27dyswvI9+29T88uXLNGnShIiICK5evYqnpyfz58/H29ub7OxsFi5cSO/evXFxcTEGwHrdiEhJVqrqN1esWMHIkSPx9/cnIiKCzz//nKysLBISEozf4LRq1YqoqChiY2MZNmwYGRkZVKxYkfHjxxu/RRARERGReyc7O9t4UxwVFUWrVq0YN24cAQEBrF69mgsXLhj3HTlyJNWrVycwMJDPP/8cwPg5TjfWxS8kJIQ333yTgIAAIiMjFUjdZ7+tPrO2tuaJJ57A39+ffv36sWDBAry9vQE4e/YsBw4c4Pjx40Wm6el1IyIlWakJpSIiIhg5ciRhYWH06dMHGxsbatSogbW1NcHBwXTq1ImlS5dy+vRpWrduTVRUFKGhocybN6/IeVQpJSIiInLv7Nixw7gU/dixY/H19eXKlSvMnDmTAQMG8MEHHxAcHMzFixcBuHDhAr169cLPz4+RI0cCmhZWUiQlJbFq1Sp++uknPvvsM5o3b17cQyq1CgoKjH8OCAigd+/eAFhaWvLYY4+xZs0aevTowYsvvghAeno6o0aNIisri759+xbLmEVE/olSkcBkZ2ezY8cOnJ2dSUlJMT7/4osvkpmZiZ2dHTY2NowdO5azZ88ydepUWrVqxbFjx7Q0qoiIiMh9VKtWLQwGA7Vr1yYjI4P4+HgeeeQRAGbOnImJiQkrV67k1KlTtGrVivDwcAwGA4sXLwY09agkadSoEZs2bcLCwgJ7e/viHk6pdXtD8tjYWE6ePElkZCTe3t74+/szduxYLl68yIoVK+jbty+WlpZcuXKFzMxM4uPjMTU11etGRB4apaanVFpaGnPnziUuLo4XXniBffv28d133xEWFkbdunUB8PLyIjo6mmPHjhVp1KjGfyIiIiL3j7e3NytXrqRRo0acOHECoMiKx0uXLiU8PJzU1FTq1q3Lxx9/jLm5+e/66YiUJW+++SbR0dF4eHhw+PBhEhMT6dGjB5s2bQJg/fr1nDp1ivPnz9O4cWNGjhyppuYi8tApNaEUwLlz55g1axaffvop165dIzExkRo1anDjxg2srKxYuXIlgYGBfPLJJzg6Ohb3cEVERERKpVth0q3/7tmzh6tXrzJ16lQA9u7di62tLT///DOWlpbAL5XvV69epUqVKpiYmOjGWsq0Xbt28fzzz/PRRx/RoUMHMjMz2bhxI9OmTcPDw4MNGzb84XGqkBKRh02p6SkFULVqVSZNmkSvXr2oW7eu8c3aysqKvLw8tmzZgrOzM1WqVCnmkYqIiIiUTgUFBcbqpvT0dNLS0ujQoQPPPPMMGzZsIDc3l/bt23Pjxg1jIBUcHMzPP/+Mo6MjJiYmFBQUKJCSMi0tLQ0bGxtatGgBgK2tLf379+eNN95g06ZNxn5rULT/lAIpEXnYlKpQCsDR0ZF33nmHNm3aEBoaip+fHwB9+/YlNTWVkJAQ4zd3IiIiInLvFBYWGnvhTJ8+neeff57GjRszbNgwAgMDcXFxITQ0FBMTE9zd3YmOjqZr164EBARga2trPM/tK4eJlCW37lFcXV0xMTEhNjbWuM3Ozo5evXrh6OjI+vXrGTp0KKDXi4g83ErlO1jVqlWZOHGisVmmo6MjSUlJfPXVV8Z51upPICIiInJv3fp8NXXqVJYsWcLo0aOJiIjgxx9/ZPr06aSkpODq6kpYWBgODg6MGTOGwsJCdu/ejcFg0JeGUubcXuUE//8acnBwoEGDBoSEhHDw4EHjdktLSzp16sScOXP44osv2L59+wMdr4jIvVaqekr91rlz55gwYQIXL17ko48+wtzcXP0JRERERO6jH3/8kf79+zN9+nSefPJJYmNj6dWrF0uWLGHIkCFFet4kJSXRsGFD9ZCSMun2VfY++ugjUlNTMTExoX///jzyyCPs2bMHX19fatWqhYeHB+7u7rz33nvY29vz/vvv4+bmxqRJk/D19S3mKxER+edKdSgFv/QysLe3x2Aw6MOOiIiIyH129uxZOnfuzJ49ezh48CCDBw9m/vz5eHt78/PPP7Nx40ZatWqFi4uL8Zjbb85FyoLbV5Z8++232bRpEw4ODlhYWJCWlkZMTAxOTk4cOHCA1atXExUVhZ2dHZUrVyYmJgYLCwvatWuHt7c3gwcPLuarERH550r9v/4VK1bEYDCoYaaIiIjIPXbs2DH27NnD7t27jc9lZ2djZmbGwoULGTJkCHPnzsXb2xuAkydPEh4ezvnz54ucR4GUlDW3AqnFixezbt06QkND+fLLL3n55ZdJSUmhffv2nDhxgrZt27J48WK++eYbYmJi2Lt3LxYWFrz99tv88MMPeHh4FPOViIj8b8rMJwB92BERERG5d4KDg3nuuecYMGAAgwcP5pVXXgGgbt26DBgwgPnz5zN48GB8fHwAuH79OpMmTSI7O1s30lJm5efnG/+cnp7O119/zYIFC3B3dycyMpI33niDWbNmUb9+fbp160ZycjLly5enQoUK1KhRg4MHD+Lp6cnatWv55JNPqFOnTjFejYjI/06lQyIiIiLyt6xYsQJfX19WrVpF06ZNCQgIYOXKlTz55JMMGDCAN954g9TUVJYuXUpubi65ubkkJydz8eJFjhw5Yqxi15eGUpbc3k/t+PHjuLq6MnDgQOrVq0diYiK+vr7MmTMHHx8fHBwcGDFiBC4uLnz33XfUrl0bgDZt2tC+fXtmz55Nw4YNi/NyRETuCX0SEBEREZG7FhERwciRI9myZQuDBg2iWbNmvPTSS+Tl5ZGamgqAlZUVy5Yt47///S8XLlwgIyODDh06kJCQYFx4RoGUlCXR0dG89NJLAIwePZrXXnuNGzdu0KlTJ2rXrk18fDz169dn0KBBAFSuXJlhw4YxYcIEatSoAfz/Sn1jxoxRICUipYYqpURERETkrmRnZ7Njxw6cnZ35/vvvjc/PmzcPgMOHD/PWW2/h4ODA0KFDGTVqFKNGjSpyjvz8fPX5lDIlNzeXU6dOkZiYSPPmzTl9+jRffvklVlZWxn3Onz/PwYMHMTU1JTMzk+DgYBo0aMCMGTOAolVWIiKlSalffU9ERERE7p20tDTmzp1LXFwc/fv3Z//+/SQlJTF+/Hjq1avHunXrSExM5PTp09ja2rJs2TK6dOlS3MMWKXY9evRg27Zt9O7dm4iICADj6uA//vgjffr04fjx4zg5OWEwGDh69KgCXBEp9RRKiYiIiMjfcu7cOWbNmkVkZCQZGRkkJiYWmWJkMBgICQkhJSWF//znP7qxljKpsLDQuMoewJw5c8jMzCQ6OprGjRsTHBwM/H8wlZqayvbt28nPz2fIkCGYmZmpQkpESj2FUiIiIiLyt50/f57Zs2ezf/9+XnjhBcaPHw9ATk4O5cqVK7KvbqylLJs7dy5t2rTBw8ODmzdvEhgYSFBQEM2aNTMGUwCHDh3C3d3d+FivGxEpC9RhUkRERET+NkdHR9555x3atGnDli1bmDt3LgDlypUrsuw9oBtrKbOysrKIi4ujY8eO7N69m/Lly+Pl5cXQoUM5duwYAwYMIC0tjSeffJL33nuP2+sF9LoRkbJAlVIiIiIi8o+dO3eO2bNnc/jwYTp16sTMmTOLe0gixebW9NXbp+6lpqYyZcoU1q1bR3R0NB07duTatWuEhoaycOFCrl27Rq1atdi7dy/m5ubFfAUiIg+WQikRERER+Z+cO3eOt956C0tLS1asWFGkj45IWXTp0iUqV65sDKdSU1OZNGkS69evZ+fOnTz++OPcvHmTq1evkpSURIcOHTA1NTX2lxIRKSsUSomIiIjI/+zKlStUqFDhd1UiImXB7f/Ph4aG4uXlRXx8PE2aNDFuO3PmDGPGjOHTTz9lz549/Pvf/y5yDvWQEpGySD2lREREROR/9sgjj2AwGCgoKFAgJWXO7f/PN2jQgI4dO9KzZ0+++eYbTExMKCgooGbNmgwYMIDs7Gxat25NQkJCkXMokBKRskiVUiIiIiIiIv9AQkICJ06c4Ntvv6VGjRp069aNmjVrkpycjK+vL0ePHmX79u00adIEgAMHDrBmzRoaN26Mj4+PpuqJSJmnUEpERERERORvCgoKYsaMGTg4OJCenk5ycjLOzs4MHz6cCRMmkJyczOjRozl06BBr166levXqTJ48GUdHR/z9/QHUQ0pEyjyFUiIiIiIiIn/Dhg0bGDp0KKtWreKpp57C2tqa06dPM2LECE6dOoW3tzdTp04lOTmZ6dOnExISQr169bCxseHLL7/E3NxcvddERFAoJSIiIiIictcuX75Mv3796NGjB2PHji2y7fz587z88sscPXqULVu20LZtWwDi4+MpKCjA3d1dq+yJiNxGjc5FRERERETu0rVr1/j6669xcXEp8nxBQQGOjo4EBweTmZlJaGiocVvLli1p1aoVpqam5OfnK5ASEfmVQikREREREZG7dP36dfLz87k14SQvLw8Ag8FATk4Ojo6O9O3bl2PHjpGTk0NBQUGR47XKnojI/1MoJSIiIiIicpecnJwwNzfnww8/BMDMzIz8/HwAypUrB0BOTg6VKlWiXLlyGAy65RIRuRO9Q4qIiIiIiNyFgoICbG1tGTt2LBs3buTdd98FilY/Xb9+nXPnztG8efPiGqaIyENDk5lFRERERETuwq2qp+eee46vvvqKGTNmkJ6ezpgxY7C2tuby5cuMHz+eK1euMG7cuGIerYhIyafV90RERERERP6mpKQkVqxYwbJly7C2tiYvLw9XV1fKlStHTEwM5ubm5Ofnq4eUiMifUCglIiIiIiJym8LCQkxMTP5yv+zsbNLS0ti9ezd5eXm4uLjQpk0bDAYDeXl5WmVPROQvKJQSERERERH5VUFBgXGaXn5+Pjdv3sTGxsa4/fbA6k7h1e3nEBGRO9M7pYiIiIiICEXDpHnz5vH888/zr3/9i2nTprFv3z6AIiHUnaqpFEiJiNwd1ZOKiIiIiIjw/2HSxIkTWbVqFZMnT+aFF17Ax8eHw4cPU69ePapVq1bMoxQRKT0USomIiIiIiPwqMTGR8PBwtmzZQvv27YmPjycjIwNPT0+qVat21/2mRETkr6muVERERERE5Dbly5enffv2hIaG0rlzZxYvXsxLL71EVlYWO3bsIDMzs7iHKCJSKiiUEhERERGRMqmgoMD451vrP+Xm5nL27FkWLVrEiBEjmDt3Lt7e3gAcOXKEDz74gB9++KFYxisiUtoolBIRERERkTLn9qbmK1asYPbs2WRnZ+Pm5sYzzzzD2LFjGTlyJD4+PgBkZ2czf/58zMzMcHV1Lc6hi4iUGuopJSIiIiIiZc6tQOrNN99kw4YNjBs3jrS0NJycnBgyZAhpaWkEBwdTvXp1MjMz2b17N6mpqSQkJGAwGIqEWiIi8s+YFN6qUxURERERESnlbm9UvnnzZkaPHk14eDitW7cusl9CQgIffvgh4eHh1KtXD2dnZ5YsWYKZmRl5eXmYmen7fRGR/5VCKRERERERKfXWrl2Ll5dXkeemTp3K0aNHiYiIMIZVvw2c0tPTqVixovGxAikRkXtH9aYiIiIiIlKqrVy5krCwsCKNzQGysrK4cuUKOTk5xuopMzMzcnJyiIiIIDs7u0ggVVhYqEBKROQeUiglIiIiIiKl2rPPPsvWrVsxGAzs37/f+Hy9evVITExk79693D6B5MaNGwQEBPDJJ58UOc+t4EpERO4NTd8TEREREZFS6/aG5Lt378bT0xNfX1+mTJkCQM+ePYmPj+eDDz7A1dUVMzMzRo8ezZUrVzhw4ACmpqbFOXwRkVJNoZSIiIiIiJR6Fy5cwMLCgjlz5vDJJ5/Qv39/Jk+eDMDAgQM5ePAgly5don79+pQvX549e/Zgbm5Ofn6+gikRkftEE6JFRERERKRU27hxI6GhoWzduhVvb29MTU1Zv349JiYmTJo0iQ8//JBDhw5x9epVLC0tadu2LQaDQU3NRUTuM73DioiIiIhIqZaVlcXOnTtJTk6mXr16DB8+HICQkBAKCwuZPHky7u7uRY4pKChQICUicp9p+p6IiIiIiJQahYWFxobkt/eT6tGjBxYWFmzYsAELCwvOnDnDihUrCA8Pp1evXrz33nvFOWwRkTJJq++JiIiIiEipcfsKebcCKYDnnnuOtLQ0UlJSAKhZsyavvvoqXbp04YcffkDf1YuIPHiqlBIRERERkYfe7VVRmzdvZvLkyfj7+9OgQQNq1qxJVlYWbm5udOjQgcDAQONxFy9epHLlypiYmBSpshIRkftPlVIiIiIiIvLQuxVITZw4kYyMDFq0aIGPjw9eXl6EhIRgY2PDokWLSEhIYM+ePcbjHBwcFEiJiBQTde4TEREREZGH1u0VUiEhIcyZM4e9e/cybNgwtm/fzmeffcawYcOIiIjA3t4ea2trjh07xuOPP17kPAqkREQePE3fExERERGRh15kZCRHjhzB2dmZQYMGFdl29OhR1q9fz/79+zl48CBdunRh586dxTRSERG5RaGUiIiIiIg81A4dOsTAgQM5e/Ysq1aton///uTm5mJubm6spMrOzubmzZusWbOG1157DTMzTRoRESluCqVEREREROSh8tv+T1evXmXNmjX4+fnRpEkTtm3bBkB+fj6mpqZ/eExeXp6CKRGRYqZG5yIiIiIi8tAoKCgoEi5dv36dChUq8OqrrzJx4kSSk5MZOnQoAKampuTn5wO/7xmlQEpEpPgplBIRERERkYfC7U3NFyxYwMCBA3Fzc8PPz4+UlBSGDx+Or68vhw8fZvjw4cAvwVRBQUFxDltERO5A0/dEREREROSh8s4777B69WomTJiAtbU1EyZMoHPnzqxdu5aCggLWrFlDUFAQzs7ObNmypbiHKyIid6CaVREREREReWgcOnSIsLAwIiIiaN26NYcOHSIzM5NnnnkGa2trAIYMGUJWVhYnTpwoUl0lIiIli96dRURERESkxMrOzi7yuLCwEHt7e1q3bs3mzZvp1KkTS5YswcvLi6ysLHbu3ImVlRW+vr4EBwdjMBg0fU9EpIRSKCUiIiIiIiVSdHQ0ixcv5ssvvzQ+l5OTw9mzZwkMDGTEiBHMnTuXkSNHAhAXF8fy5cs5efIkVlZWmJiYUFhYqEopEZESSu/OIiIiIiJS4qxevZohQ4bw/fffF1k5r127dnh4eDBixAjGjh2Lj48P8EtF1aJFizAYDDRs2NC4/29X3RMRkZJDPaVERERERKRE2bhxI6NGjWL16tV069YNOzu7Ittff/11zp07R3BwME5OTqSnpxMVFUVqaioJCQnGKXuqkBIRKdm0+p6IiIiIiJQYFy9epF+/fnh6evLaa68Zn8/KyuKbb77BzMwMNzc3Tp06xZw5c4iJiaF+/fo4Ozvj7++PmZkZeXl5mJnp+3cRkZJO79QiIiIiIlKiXLhwgRo1ahgfL1++nNjYWLZu3YqjoyOurq7s2rWLoKAgLl26ROXKlY37KpASEXl4qJ5VRERERERKlIyMDD799FNiY2Px9PRk+fLlODg4sGPHDpYsWcL333/PjBkzAKhQoYLxuMLCQgVSIiIPEb1ji4iIiIhIieHg4EBwcDDPPfccsbGx2NrasmjRIpo1a0alSpVIT0/H3t6e/Px8gCIhlJqai4g8XBRKiYiIiIhIidKlSxe+/fZbsrKyqFu37u+229raUr169WIYmYiI3EtqdC4iIiIiIg+Fixcv8sorr3Dp0iX279+PqalpcQ9JRET+B6qUEhERERGREu3SpUsEBgayb98+Lly4YAyk8vPzFUyJiDzE1OhcRERERERKtDNnzrB//37q16/PgQMHMDc3Jy8vT4GUiMhDTtP3RERERESkxLt69Sr29vaYmJioQkpEpJRQKCUiIiIiIg+NwsJCrbInIlJKaPqeiIiIiIg8NBRIiYiUHgqlRERERERERETkgVMoJSIiIiIiIiIiD5xCKREREREREREReeAUSomIiIiIiIiIyAOnUEpERERERERERB44hVIiIiIiIiIiIvLAKZQSERERKYWCg4OpUKFCcQ9DRERE5I4USomIiEiZYmJi8qc/06ZNK9axRURE3NW+n332Gd27d6dSpUpYWVnh6urKuHHjSE1Nvb+DFBEREblHFEqJiIhImZKWlmb8WbRoEXZ2dkWeGz9+/N86X05Ozn0a6Z2tWLGCrl27UrVqVbZu3crx48fx9/fn2rVrLFiw4IGPR0REROSfUCglIiIiZUrVqlWNP/b29piYmBgfX79+nRdffBFHR0dsbGxo2bIlMTExRY53cnJixowZeHl5YWdnx4gRIwAICAigVq1aWFlZ0adPHxYuXPi76XMfffQRLVq0wNLSEmdnZ6ZPn05eXp7xvAB9+vTBxMTE+Pi3zpw5g6+vL76+vgQFBdGxY0ecnJzw8PAgMDCQKVOm/OFxycnJPPPMM396bcuWLaNBgwZYWlri6OiIp6encduWLVto2rQp5cuXp1KlSnTt2pXr168btwcGBuLi4oKlpSWPPvooy5YtM27Lyclh1KhRVKtWDUtLS+rUqcN77713578kERERKRPMinsAIiIiIiVFVlYW3bt3Z9asWVhYWLB27Vp69epFUlIStWvXNu7n5+fHlClTmDp1KgD79+/H29ubuXPn0rt3b2JiYpg8eXKRc+/duxcvLy8WL15Mhw4dSE5ONgZaU6dOJT4+nipVqrB69Wq6deuGqanpH44xNDSUnJwc3nrrrT/cfqc+Un91bYcOHcLX15d169bRtm1brly5wt69e4FfqssGDBjAvHnz6NOnD5mZmezdu5fCwkIA1q9fz5QpU1i6dCnNmzcnISGB4cOHY21tzUsvvcTixYv5+OOP2bx5M7Vr1+ann37ip59+uvu/GBERESmVTApvfZoQERERKWOCg4MZM2YMV69eveM+TZo0wdvbm1GjRgG/VDQ1b96c8PBw4z4vvPACWVlZREZGGp8bNGgQkZGRxnN37dqVLl268M477xj3CQkJ4a233uLs2bPALz2lwsPDefbZZ+84Hh8fH9avX8+1a9fu6bWFhYXxyiuvcObMGWxtbYvsd+TIEdzc3Dh9+jR16tT53Xnq16/PjBkzGDBggPG5mTNnEhUVxYEDB/D19eWbb74hJiYGExOTPx23iIiIlB2aviciIiLyq6ysLMaPH4+LiwsVKlTAxsaGEydO8OOPPxbZz93dvcjjpKQk/v3vfxd57rePjx49yrvvvouNjY3xZ/jw4aSlpXHjxo27HmNhYeE/Cnb+6tqeeOIJ6tSpg7OzM4MHD2b9+vXGcTVr1owuXbrQtGlTnn/+eQICAkhPTwfg+vXrJCcnM3To0CLXNnPmTJKTkwF4+eWX+eqrr2jUqBG+vr5ER0f/7fGLiIhI6aPpeyIiIiK/Gj9+PDt37sTPz4/69etTvnx5PD09f9fM3Nra+m+fOysri+nTp9O3b9/fbbO0tLzr8zRs2JBr166RlpZGtWrV7vq4v7o2W1tbjhw5wu7du4mOjmbKlClMmzaN+Ph4KlSowM6dOzlw4ADR0dEsWbKEiRMnEhcXh5WVFfBLT61WrVoV+Z23piC2aNGC77//nm3bthETE0O/fv3o2rUrW7Zsuevxi4iISOmjSikRERGRX+3fv5+XX36ZPn360LRpU6pWrcrp06f/8rhGjRoRHx9f5LnfPm7RogVJSUnUr1//dz8Gwy8fyczNzcnPz//T3+Xp6Um5cuWYN2/eH26/03S9u7k2MzMzunbtyrx580hMTOT06dPExsYCv0wtbNeuHdOnTychIYFy5coRHh6Oo6Mj1atXJyUl5XfXVbduXeO57ezs6N+/PwEBAWzatImtW7dy5cqVP71WERERKd1UKSUiIiLyqwYNGhAWFkavXr0wMTFh8uTJFBQU/OVxr7/+Oh4eHixcuJBevXoRGxvLtm3bikyzmzJlCj179qR27dp4enpiMBg4evQox44dY+bMmcAv/ap27dpFu3btsLCwoGLFir/7XbVq1eL9999n1KhRZGRk4OXlhZOTE2fOnGHt2rXY2NiwYMGCv31tkZGRpKSk4OHhQcWKFYmKiqKgoIBGjRoRFxfHrl27ePLJJ6lSpQpxcXFcvHgRFxcXAKZPn46vry/29vZ069aN7OxsDh06RHp6OmPHjmXhwoVUq1aN5s2bYzAYCA0NpWrVqndsyi4iIiJlgyqlRERERH61cOFCKlasSNu2benVqxdPPfUULVq0+Mvj2rVrh7+/PwsXLqRZs2Zs376dN954o8i0vKeeeorIyEiio6Np2bIlrVu35v333y/SOHzBggXs3LmTWrVq0bx58zv+Ph8fH6Kjo0lNTaVPnz48+uijDBs2DDs7O8aPH/+Prq1ChQqEhYXRuXNnXFxc8Pf3Z8OGDTRu3Bg7Ozs+//xzunfvTsOGDZk0aRILFizg6aefBmDYsGEEBgayevVqmjZtyuOPP05wcLCxUsrW1pZ58+bh7u5Oy5YtOX36NFFRUcYKMRERESmbtPqeiIiIyH0wfPhwTp48yd69e4t7KCIiIiIlkqbviYiIiNwDfn5+PPHEE1hbW7Nt2zbWrFnDsmXLintYIiIiIiWWKqVERERE7oF+/fqxe/duMjMzcXZ25vXXX8fb27u4hyUiIiJSYimUEhERERERERGRB07dJUVERERERERE5IFTKCUiIiIiIiIiIg+cQikREREREREREXngFEqJiIiIiIiIiMgDp1BKREREREREREQeOIVSIiIiIiIiIiLywCmUEhERERERERGRB06hlIiIiIiIiIiIPHAKpURERERERERE5IH7P3PzweNpkUPCAAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Calculate top-1 and top-2 accuracy for each class\n",
        "top_1_accuracy_per_class_en = []\n",
        "top_2_accuracy_per_class_en = []\n",
        "\n",
        "for i, class_name in enumerate(classes_en):\n",
        "    top_1_accuracy = np.mean((y_test_en == i) & (y_pred_en == i))\n",
        "    top_2_accuracy = np.mean((y_test_en == i) & (np.argsort(y_prob_en, axis=1)[:, -2:] == i).any(axis=1))\n",
        "    top_1_accuracy_per_class_en.append(top_1_accuracy)\n",
        "    top_2_accuracy_per_class_en.append(top_2_accuracy)\n",
        "\n",
        "# Debug check\n",
        "print(\"Top-1:\", top_1_accuracy_per_class_en)\n",
        "print(\"Top-2:\", top_2_accuracy_per_class_en)\n",
        "\n",
        "# Ensure all lists are the same length\n",
        "assert len(classes_en) == len(top_1_accuracy_per_class_en) == len(top_2_accuracy_per_class_en), \"Length mismatch!\"\n",
        "\n",
        "# Calculate the benefit of top-2 predictions\n",
        "benefit_en = np.array(top_2_accuracy_per_class_en) - np.array(top_1_accuracy_per_class_en)\n",
        "\n",
        "# Plot\n",
        "plt.figure(figsize=(12, 6))\n",
        "x = np.arange(len(classes_en))\n",
        "\n",
        "plt.bar(x - 0.2, top_1_accuracy_per_class_en, width=0.4, label=\"Top-1 Accuracy\")\n",
        "plt.bar(x + 0.2, top_2_accuracy_per_class_en, width=0.4, label=\"Top-2 Accuracy\")\n",
        "plt.plot(x, benefit_en, color=\"red\", marker=\"o\", label=\"Benefit (Top-2 - Top-1)\")\n",
        "\n",
        "plt.xticks(x, classes_en, rotation=45, ha=\"right\")\n",
        "plt.xlabel(\"Target Classes\")\n",
        "plt.ylabel(\"Accuracy\")\n",
        "plt.title(\"Benefit of Top-2 Predictions for Each Target Class (English Model)\")\n",
        "plt.legend()\n",
        "plt.tight_layout()\n",
        "plt.show()\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 663
        },
        "id": "4b4Zj4naDot2",
        "outputId": "2a5dbb83-4a4a-4c83-89df-fd86b5c348c8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Top-1: [np.float64(0.08763102725366877), np.float64(0.0960167714884696), np.float64(0.005031446540880503), np.float64(0.009643605870020965), np.float64(0.06289308176100629), np.float64(0.11069182389937107), np.float64(0.022641509433962263), np.float64(0.010482180293501049), np.float64(0.020964360587002098), np.float64(0.2180293501048218)]\n",
            "Top-2: [np.float64(0.0909853249475891), np.float64(0.11614255765199162), np.float64(0.004612159329140462), np.float64(0.009224318658280923), np.float64(0.07505241090146751), np.float64(0.16058700209643606), np.float64(0.018448637316561847), np.float64(0.007966457023060796), np.float64(0.01761006289308176), np.float64(0.26666666666666666)]\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}