{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "nRSlxT4q5EHJ"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import random\n",
        "import tensorflow as tf\n",
        "from google.colab import files\n",
        "from statsmodels.tsa.seasonal import seasonal_decompose\n",
        "from sklearn.preprocessing import MinMaxScaler\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense\n",
        "from keras.layers import LSTM\n",
        "from tensorflow.keras.preprocessing.sequence import TimeseriesGenerator\n"
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# 1. Upload file dari PC\n",
        "uploaded = files.upload()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 74
        },
        "id": "gaeeT_rKVXTW",
        "outputId": "bb8399f9-3f79-4e82-92db-7f904bb66c84"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-5f634fe7-ce5e-492d-ae93-6e6a02a5000d\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-5f634fe7-ce5e-492d-ae93-6e6a02a5000d\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script>// Copyright 2017 Google LLC\n",
              "//\n",
              "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
              "// you may not use this file except in compliance with the License.\n",
              "// You may obtain a copy of the License at\n",
              "//\n",
              "//      http://www.apache.org/licenses/LICENSE-2.0\n",
              "//\n",
              "// Unless required by applicable law or agreed to in writing, software\n",
              "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
              "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
              "// See the License for the specific language governing permissions and\n",
              "// limitations under the License.\n",
              "\n",
              "/**\n",
              " * @fileoverview Helpers for google.colab Python module.\n",
              " */\n",
              "(function(scope) {\n",
              "function span(text, styleAttributes = {}) {\n",
              "  const element = document.createElement('span');\n",
              "  element.textContent = text;\n",
              "  for (const key of Object.keys(styleAttributes)) {\n",
              "    element.style[key] = styleAttributes[key];\n",
              "  }\n",
              "  return element;\n",
              "}\n",
              "\n",
              "// Max number of bytes which will be uploaded at a time.\n",
              "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
              "\n",
              "function _uploadFiles(inputId, outputId) {\n",
              "  const steps = uploadFilesStep(inputId, outputId);\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  // Cache steps on the outputElement to make it available for the next call\n",
              "  // to uploadFilesContinue from Python.\n",
              "  outputElement.steps = steps;\n",
              "\n",
              "  return _uploadFilesContinue(outputId);\n",
              "}\n",
              "\n",
              "// This is roughly an async generator (not supported in the browser yet),\n",
              "// where there are multiple asynchronous steps and the Python side is going\n",
              "// to poll for completion of each step.\n",
              "// This uses a Promise to block the python side on completion of each step,\n",
              "// then passes the result of the previous step as the input to the next step.\n",
              "function _uploadFilesContinue(outputId) {\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  const steps = outputElement.steps;\n",
              "\n",
              "  const next = steps.next(outputElement.lastPromiseValue);\n",
              "  return Promise.resolve(next.value.promise).then((value) => {\n",
              "    // Cache the last promise value to make it available to the next\n",
              "    // step of the generator.\n",
              "    outputElement.lastPromiseValue = value;\n",
              "    return next.value.response;\n",
              "  });\n",
              "}\n",
              "\n",
              "/**\n",
              " * Generator function which is called between each async step of the upload\n",
              " * process.\n",
              " * @param {string} inputId Element ID of the input file picker element.\n",
              " * @param {string} outputId Element ID of the output display.\n",
              " * @return {!Iterable<!Object>} Iterable of next steps.\n",
              " */\n",
              "function* uploadFilesStep(inputId, outputId) {\n",
              "  const inputElement = document.getElementById(inputId);\n",
              "  inputElement.disabled = false;\n",
              "\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  outputElement.innerHTML = '';\n",
              "\n",
              "  const pickedPromise = new Promise((resolve) => {\n",
              "    inputElement.addEventListener('change', (e) => {\n",
              "      resolve(e.target.files);\n",
              "    });\n",
              "  });\n",
              "\n",
              "  const cancel = document.createElement('button');\n",
              "  inputElement.parentElement.appendChild(cancel);\n",
              "  cancel.textContent = 'Cancel upload';\n",
              "  const cancelPromise = new Promise((resolve) => {\n",
              "    cancel.onclick = () => {\n",
              "      resolve(null);\n",
              "    };\n",
              "  });\n",
              "\n",
              "  // Wait for the user to pick the files.\n",
              "  const files = yield {\n",
              "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
              "    response: {\n",
              "      action: 'starting',\n",
              "    }\n",
              "  };\n",
              "\n",
              "  cancel.remove();\n",
              "\n",
              "  // Disable the input element since further picks are not allowed.\n",
              "  inputElement.disabled = true;\n",
              "\n",
              "  if (!files) {\n",
              "    return {\n",
              "      response: {\n",
              "        action: 'complete',\n",
              "      }\n",
              "    };\n",
              "  }\n",
              "\n",
              "  for (const file of files) {\n",
              "    const li = document.createElement('li');\n",
              "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
              "    li.append(span(\n",
              "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
              "        `last modified: ${\n",
              "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
              "                                    'n/a'} - `));\n",
              "    const percent = span('0% done');\n",
              "    li.appendChild(percent);\n",
              "\n",
              "    outputElement.appendChild(li);\n",
              "\n",
              "    const fileDataPromise = new Promise((resolve) => {\n",
              "      const reader = new FileReader();\n",
              "      reader.onload = (e) => {\n",
              "        resolve(e.target.result);\n",
              "      };\n",
              "      reader.readAsArrayBuffer(file);\n",
              "    });\n",
              "    // Wait for the data to be ready.\n",
              "    let fileData = yield {\n",
              "      promise: fileDataPromise,\n",
              "      response: {\n",
              "        action: 'continue',\n",
              "      }\n",
              "    };\n",
              "\n",
              "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
              "    let position = 0;\n",
              "    do {\n",
              "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
              "      const chunk = new Uint8Array(fileData, position, length);\n",
              "      position += length;\n",
              "\n",
              "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
              "      yield {\n",
              "        response: {\n",
              "          action: 'append',\n",
              "          file: file.name,\n",
              "          data: base64,\n",
              "        },\n",
              "      };\n",
              "\n",
              "      let percentDone = fileData.byteLength === 0 ?\n",
              "          100 :\n",
              "          Math.round((position / fileData.byteLength) * 100);\n",
              "      percent.textContent = `${percentDone}% done`;\n",
              "\n",
              "    } while (position < fileData.byteLength);\n",
              "  }\n",
              "\n",
              "  // All done.\n",
              "  yield {\n",
              "    response: {\n",
              "      action: 'complete',\n",
              "    }\n",
              "  };\n",
              "}\n",
              "\n",
              "scope.google = scope.google || {};\n",
              "scope.google.colab = scope.google.colab || {};\n",
              "scope.google.colab._files = {\n",
              "  _uploadFiles,\n",
              "  _uploadFilesContinue,\n",
              "};\n",
              "})(self);\n",
              "</script> "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saving data real bulanan 2019-2023 supremo.csv to data real bulanan 2019-2023 supremo.csv\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2fRF6mEW5QbK",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "outputId": "9c5a34de-8c62-4485-c563-35e2afec21e9"
      },
      "source": [
        "df = pd.read_csv('data real bulanan 2019-2023 supremo.csv', delimiter=';')\n",
        "df.head()"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Nomer  Tahun   Bulan  Produksi\n",
              "0      1   2019  Jan-19    170252\n",
              "1      2   2019  Feb-19    323468\n",
              "2      3   2019  Mar-19    616344\n",
              "3      4   2019  Apr-19    503524\n",
              "4      5   2019  May-19    277856"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-77cc3563-32de-44c0-a98a-971d7fc5d30e\" 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>Nomer</th>\n",
              "      <th>Tahun</th>\n",
              "      <th>Bulan</th>\n",
              "      <th>Produksi</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>2019</td>\n",
              "      <td>Jan-19</td>\n",
              "      <td>170252</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>2019</td>\n",
              "      <td>Feb-19</td>\n",
              "      <td>323468</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>2019</td>\n",
              "      <td>Mar-19</td>\n",
              "      <td>616344</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>2019</td>\n",
              "      <td>Apr-19</td>\n",
              "      <td>503524</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>2019</td>\n",
              "      <td>May-19</td>\n",
              "      <td>277856</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-77cc3563-32de-44c0-a98a-971d7fc5d30e')\"\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-77cc3563-32de-44c0-a98a-971d7fc5d30e 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-77cc3563-32de-44c0-a98a-971d7fc5d30e');\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-ef00452c-b58d-4f40-907e-e1e18e09bcba\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-ef00452c-b58d-4f40-907e-e1e18e09bcba')\"\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-ef00452c-b58d-4f40-907e-e1e18e09bcba 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\": 60,\n  \"fields\": [\n    {\n      \"column\": \"Nomer\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 17,\n        \"min\": 1,\n        \"max\": 60,\n        \"num_unique_values\": 60,\n        \"samples\": [\n          1,\n          6,\n          37\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Tahun\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 2019,\n        \"max\": 2023,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          2020,\n          2023,\n          2021\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Bulan\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 60,\n        \"samples\": [\n          \"Jan-19\",\n          \"Jun-19\",\n          \"Jan-22\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Produksi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 162557,\n        \"min\": 90528,\n        \"max\": 734748,\n        \"num_unique_values\": 60,\n        \"samples\": [\n          170252,\n          104272,\n          530084\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize=(9, 6))\n",
        "plt.plot(df.index, df['Produksi'], color='blue', marker='o', markersize=2, linewidth=2, alpha=0.7)\n",
        "plt.title('Data Produksi')\n",
        "plt.xlabel('Bulan')\n",
        "plt.ylabel('Produksi')\n",
        "plt.show()"
      ],
      "metadata": {
        "id": "IctHV7x_M-vw",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 564
        },
        "outputId": "37b61cb6-f545-4c0b-a10a-a259e63bc449"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 900x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Changed period to 12 for monthly data\n",
        "results = seasonal_decompose(df['Produksi'], model='additive', period=12)\n",
        "results.plot()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "BuK5VqtkV064",
        "outputId": "4a858065-1f06-486a-fcf9-194abbbd026a"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 4 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Random Seed Untuk Reproduksi Data\n",
        "# Set random seeds di semua library\n",
        "seed_value = 42\n",
        "random.seed(seed_value)\n",
        "np.random.seed(seed_value)\n",
        "tf.random.set_seed(seed_value)"
      ],
      "metadata": {
        "id": "OGF2sq0XWQ6K"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1NoWcZEK6rPb"
      },
      "source": [
        "# Split data into training and testing sets\n",
        "train = df.iloc[:54].copy()\n",
        "test = df.iloc[54:].copy()"
      ],
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Prepocessing Data"
      ],
      "metadata": {
        "id": "86lxwp6PWwNS"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Prepocessing Data with MinMaxScaler\n",
        "scaler = MinMaxScaler()\n",
        "scaled_train = scaler.fit_transform(train[['Produksi']])\n",
        "scaled_test = scaler.transform(test[['Produksi']])\n",
        "\n",
        "print(\"=== Data Test ===\")\n",
        "print(\"Train Original:\", train['Produksi'].head(3).values)\n",
        "print(\"Train Scaled:\", scaled_train[:3].flatten())"
      ],
      "metadata": {
        "id": "xdvMcAEm8b4q",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c37c3487-7a82-491d-fb4a-180fa564b29a"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "=== Data Test ===\n",
            "Train Original: [170252 323468 616344]\n",
            "Train Scaled: [0.12375276 0.36158455 0.81620564]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Model LSTM"
      ],
      "metadata": {
        "id": "NTKpVM7VXIQG"
      }
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CqyTKCVt69Z9"
      },
      "source": [
        "# define generator\n",
        "n_input = 12\n",
        "n_features = 1\n",
        "generator = TimeseriesGenerator(scaled_train, scaled_train, length=n_input, batch_size=1)"
      ],
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ip6y5Ene7OM7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "993c6d52-708f-46fc-e44d-56539f73d091"
      },
      "source": [
        "X,y = generator[0]\n",
        "print(f'Given the Array: \\n{X.flatten()}')\n",
        "print(f'Predict this y: \\n {y}')"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Given the Array: \n",
            "[0.12375276 0.36158455 0.81620564 0.64107913 0.29078265 0.02133433\n",
            " 0.55775977 0.45020645 0.2241284  0.13337059 0.51362578 0.33075036]\n",
            "Predict this y: \n",
            " [[0.2472944]]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bQyGmvsi8HyR",
        "outputId": "324fd3dd-b19a-4a98-8336-6b83a0c26eb4"
      },
      "source": [
        "X.shape"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1, 12, 1)"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jm-T4H4I7UaV"
      },
      "source": [
        "# We do the same thing, but now instead for 1 months\n",
        "n_input = 12\n",
        "n_features = 1\n",
        "generator = TimeseriesGenerator(scaled_train, scaled_train, length=n_input, batch_size=1)"
      ],
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eJa-wFQf7jw6",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "6786bcb0-a0f2-4ea6-d806-377703a49b75"
      },
      "source": [
        "# Set seeds for reproducibility\n",
        "np.random.seed(42)\n",
        "random.seed(42)\n",
        "tf.random.set_seed(42)\n",
        "\n",
        "# define model\n",
        "model = Sequential()\n",
        "model.add(LSTM(100, activation='relu', input_shape=(n_input, n_features)))\n",
        "model.add(Dense(1))\n",
        "model.compile(optimizer='adam', loss='mse')"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.11/dist-packages/keras/src/layers/rnn/rnn.py:200: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
            "  super().__init__(**kwargs)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 193
        },
        "id": "7i4ucUNv7lbk",
        "outputId": "13927455-7b1e-4ea9-f5d9-5c97714213ed"
      },
      "source": [
        "model.summary()"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ lstm (\u001b[38;5;33mLSTM\u001b[0m)                     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m)            │        \u001b[38;5;34m40,800\u001b[0m │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │           \u001b[38;5;34m101\u001b[0m │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
              "│ lstm (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">LSTM</span>)                     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">100</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">40,800</span> │\n",
              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
              "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">101</span> │\n",
              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m40,901\u001b[0m (159.77 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">40,901</span> (159.77 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m40,901\u001b[0m (159.77 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">40,901</span> (159.77 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "p8yqUZaz7nwp",
        "outputId": "c19c66c6-afa9-4dd0-a7b4-f77126dc91d7"
      },
      "source": [
        "# fit model\n",
        "history = model.fit(generator,epochs=75)"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/75\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.11/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
            "  self._warn_if_super_not_called()\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 10ms/step - loss: 0.1512\n",
            "Epoch 2/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0735\n",
            "Epoch 3/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0713\n",
            "Epoch 4/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0660\n",
            "Epoch 5/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.0571\n",
            "Epoch 6/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0612\n",
            "Epoch 7/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0733\n",
            "Epoch 8/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0543\n",
            "Epoch 9/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0566\n",
            "Epoch 10/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0715\n",
            "Epoch 11/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0583\n",
            "Epoch 12/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0450\n",
            "Epoch 13/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0625\n",
            "Epoch 14/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0816\n",
            "Epoch 15/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0673\n",
            "Epoch 16/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0733\n",
            "Epoch 17/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0709\n",
            "Epoch 18/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0461\n",
            "Epoch 19/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 16ms/step - loss: 0.0550\n",
            "Epoch 20/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 18ms/step - loss: 0.0603\n",
            "Epoch 21/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 17ms/step - loss: 0.0574\n",
            "Epoch 22/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0430\n",
            "Epoch 23/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0410\n",
            "Epoch 24/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.0490\n",
            "Epoch 25/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0509\n",
            "Epoch 26/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.0584\n",
            "Epoch 27/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0448\n",
            "Epoch 28/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.0535\n",
            "Epoch 29/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0522\n",
            "Epoch 30/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.0549\n",
            "Epoch 31/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0458\n",
            "Epoch 32/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0458\n",
            "Epoch 33/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0415\n",
            "Epoch 34/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0357\n",
            "Epoch 35/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0378\n",
            "Epoch 36/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0458\n",
            "Epoch 37/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0401\n",
            "Epoch 38/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0474\n",
            "Epoch 39/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0525\n",
            "Epoch 40/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0488\n",
            "Epoch 41/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 13ms/step - loss: 0.0357\n",
            "Epoch 42/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 18ms/step - loss: 0.0416\n",
            "Epoch 43/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 18ms/step - loss: 0.0412\n",
            "Epoch 44/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 14ms/step - loss: 0.0291\n",
            "Epoch 45/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0439\n",
            "Epoch 46/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0609\n",
            "Epoch 47/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0342\n",
            "Epoch 48/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0386\n",
            "Epoch 49/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0511\n",
            "Epoch 50/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0444\n",
            "Epoch 51/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0331\n",
            "Epoch 52/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - loss: 0.0313\n",
            "Epoch 53/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0302\n",
            "Epoch 54/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.0496\n",
            "Epoch 55/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0368\n",
            "Epoch 56/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0466\n",
            "Epoch 57/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0499\n",
            "Epoch 58/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0435\n",
            "Epoch 59/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0466\n",
            "Epoch 60/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0478\n",
            "Epoch 61/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0376\n",
            "Epoch 62/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0434\n",
            "Epoch 63/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0409\n",
            "Epoch 64/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 16ms/step - loss: 0.0260\n",
            "Epoch 65/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 18ms/step - loss: 0.0366\n",
            "Epoch 66/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 11ms/step - loss: 0.0316\n",
            "Epoch 67/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0321\n",
            "Epoch 68/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.0344\n",
            "Epoch 69/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0467\n",
            "Epoch 70/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0326\n",
            "Epoch 71/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0488\n",
            "Epoch 72/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - loss: 0.0475\n",
            "Epoch 73/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 9ms/step - loss: 0.0292\n",
            "Epoch 74/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - loss: 0.0352\n",
            "Epoch 75/75\n",
            "\u001b[1m42/42\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.0514\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 448
        },
        "id": "OjDsOKR67rs8",
        "outputId": "8ddc1625-0ad3-43a6-8a86-c9fe659250b5"
      },
      "source": [
        "loss_per_epoch = model.history.history['loss']\n",
        "plt.plot(range(len(loss_per_epoch)),loss_per_epoch)"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7d84945de490>]"
            ]
          },
          "metadata": {},
          "execution_count": 16
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiwAAAGdCAYAAAAxCSikAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAXSRJREFUeJzt3XtYlGX+P/D3M8McOKNyGBAUjyCioKiIWWZS6FpJua25lWZmW5tly379lW1pu23RyTYrN7PNDtuWZgfLMsrwWOIBxBQFFE8gMhxUjnKceX5/zMwDowPMIMwM8H5d11xXztwz8zzhxnvv+3N/bkEURRFERERETkzm6AsgIiIiag8DCxERETk9BhYiIiJyegwsRERE5PQYWIiIiMjpMbAQERGR02NgISIiIqfHwEJEREROz8XRF9AZ9Ho9zp8/D09PTwiC4OjLISIiIiuIooiqqioEBQVBJmt7DqVHBJbz588jJCTE0ZdBREREHVBQUIDg4OA2x/SIwOLp6QnAcMNeXl4OvhoiIiKyRmVlJUJCQqTf423pEYHFtAzk5eXFwEJERNTNWFPOwaJbIiIicnoMLEREROT0GFiIiIjI6TGwEBERkdNjYCEiIiKnx8BCRERETo+BhYiIiJweAwsRERE5PQYWIiIicnoMLEREROT0GFiIiIjI6TGwEBERkdPrEYcfdpX6Jh1eTclFfZMez94aAaUL8x0REZEj8DdwGwQI+M8vp/HfvWdR16Rz9OUQERH1WgwsbVDIBZhOvK5rZGAhIiJyFAaWNgiCAJVxGai+Ue/gqyEiIuq9GFjaoXKRAwDqmxhYiIiIHIWBpR3SDAtrWIiIiByGgaUdKoUpsHCGhYiIyFEYWNqhNi0JsYaFiIjIYRhY2tE8w8IlISIiIkdhYGmHqei2jjMsREREDsPA0g4W3RIRETkeA0s7mgMLZ1iIiIgchYGlHezDQkRE5HgMLO2Qim7Zmp+IiMhhGFjaoeYMCxERkcMxsLSDjeOIiIgcj4GlHdwlRERE5HgMLO1QsdMtERGRwzGwtIMzLERERI7HwNKO5l1CnGEhIiJyFAaWdrAPCxERkeMxsLSDS0JERESOx8DSDrWCMyxERESOxsDSDmmGhTUsREREDsPA0g5T0W0dl4SIiIgchoGlHezDQkRE5HgdCiyrV69GaGgo1Go1YmNjsX///lbHHj16FLNnz0ZoaCgEQcAbb7xxzZ9pTyy6JSIicjybA8uGDRuQlJSEFStW4ODBg4iKikJCQgJKSkosjr98+TIGDx6Ml156CRqNplM+0564rZmIiMjxbA4sr7/+OhYtWoQFCxYgIiICa9asgZubG9atW2dx/Pjx4/Hqq6/i7rvvhkql6pTPtCcefkhEROR4NgWWhoYGZGRkID4+vvkDZDLEx8cjLS2tQxfQkc+sr69HZWWl2aOrqKUaFi4JEREROYpNgaWsrAw6nQ4BAQFmzwcEBECr1XboAjrymcnJyfD29pYeISEhHfpua3CGhYiIyPG65S6hZcuWoaKiQnoUFBR02XeZim6b9CKadAwtREREjuBiy2BfX1/I5XIUFxebPV9cXNxqQW1XfKZKpWq1HqazmYpuAcMsi4u8W2Y8IiKibs2m375KpRIxMTFITU2VntPr9UhNTUVcXFyHLqArPrMzKV2a/xVxWYiIiMgxbJphAYCkpCTMnz8f48aNw4QJE/DGG2+gpqYGCxYsAADMmzcP/fv3R3JyMgBDUe2xY8ekfy4sLMShQ4fg4eGBoUOHWvWZjiSXCVDIBTTqRPZiISIichCbA8ucOXNQWlqK5cuXQ6vVIjo6GikpKVLRbH5+PmSy5lmJ8+fPY8yYMdKfX3vtNbz22muYMmUKduzYYdVnOprKRY5GXRO73RIRETmIIIqi6OiLuFaVlZXw9vZGRUUFvLy8Ov3zY57figs1DfjxiRsQpvHs9M8nIiLqjWz5/c0KUiuoFaZut1wSIiIicgQGFis0nyfEJSEiIiJHYGCxgmmnEGtYiIiIHIOBxQoq45JQHdvzExEROQQDixW4JERERORYDCxWaA4snGEhIiJyBAYWK5ja83OGhYiIyDEYWKygNp3YzBoWIiIih2BgsQJnWIiIiByLgcUKKgWLbomIiByJgcUKpqJbbmsmIiJyDAYWK3BJiIiIyLEYWKzAbc1ERESOxcBiBamGha35iYiIHIKBxQpcEiIiInIsBhYrSH1YuCRERETkEAwsVuAMCxERkWMxsFhBKrplDQsREZFDMLBYQerDwiUhIiIih2BgsYJKYVwS4gwLERGRQzCwWIF9WIiIiByLgcUKzYGFMyxERESOwMBiBbWCu4SIiIgciYHFCs27hLgkRERE5AgMLFZQcYaFiIjIoRhYrNCyhkUURQdfDRERUe/DwGIFU2ABOMtCRETkCAwsVjC15gcYWIiIiByBgcUKCrkAQTD8M3uxEBER2R8DixUEQeB5QkRERA7EwGIl9mIhIiJyHAYWK7E9PxERkeMwsFjJVHjLGRYiIiL7Y2CxkmmGpY7dbomIiOyOgcVKKgUPQCQiInIUBhYrSUtC3CVERERkdwwsVmLRLRERkeMwsFiJ25qJiIgcp0OBZfXq1QgNDYVarUZsbCz279/f5viNGzciPDwcarUao0aNwpYtW8xeLy4uxv3334+goCC4ublh+vTpOHHiREcurcu0PACRiIiI7MvmwLJhwwYkJSVhxYoVOHjwIKKiopCQkICSkhKL4/fs2YO5c+di4cKFyMzMRGJiIhITE5GVlQUAEEURiYmJOHXqFL755htkZmZi4MCBiI+PR01NzbXdXSdq7nTLJSEiIiJ7E0RRFG15Q2xsLMaPH4+3334bAKDX6xESEoLHHnsMTz311FXj58yZg5qaGnz33XfScxMnTkR0dDTWrFmD48ePIywsDFlZWRg5cqT0mRqNBi+++CIefPDBdq+psrIS3t7eqKiogJeXly23Y7UnvziMDekFWJoQhkenDu2S7yAiIupNbPn9bdMMS0NDAzIyMhAfH9/8ATIZ4uPjkZaWZvE9aWlpZuMBICEhQRpfX18PAFCr1WafqVKp8Msvv9hyeV1K2tbMGRYiIiK7symwlJWVQafTISAgwOz5gIAAaLVai+/RarVtjg8PD8eAAQOwbNkyXLp0CQ0NDXj55Zdx7tw5FBUVWfzM+vp6VFZWmj26GmtYiIiIHMfhu4QUCgW++uorHD9+HH379oWbmxu2b9+OGTNmQCazfHnJycnw9vaWHiEhIV1+nWzNT0RE5Dg2BRZfX1/I5XIUFxebPV9cXAyNRmPxPRqNpt3xMTExOHToEMrLy1FUVISUlBRcuHABgwcPtviZy5YtQ0VFhfQoKCiw5TY6hH1YiIiIHMemwKJUKhETE4PU1FTpOb1ej9TUVMTFxVl8T1xcnNl4ANi6davF8d7e3vDz88OJEyeQnp6OWbNmWfxMlUoFLy8vs0dXk/qwsNMtERGR3bnY+oakpCTMnz8f48aNw4QJE/DGG2+gpqYGCxYsAADMmzcP/fv3R3JyMgBgyZIlmDJlClauXImZM2di/fr1SE9Px9q1a6XP3LhxI/z8/DBgwAAcOXIES5YsQWJiIm655ZZOus1rx7OEiIiIHMfmwDJnzhyUlpZi+fLl0Gq1iI6ORkpKilRYm5+fb1Z7MmnSJHz66ad45pln8PTTT2PYsGHYtGkTIiMjpTFFRUVISkpCcXExAgMDMW/ePDz77LOdcHudh0tCREREjmNzHxZnZI8+LJsyC/HEhkOYPNQXnzwY2yXfQURE1Jt0WR+W3owzLERERI7DwGIl1rAQERE5DgOLlaQ+LNwlREREZHcMLFZSK7gkRERE5CgMLFZip1siIiLHYWCxEs8SIiIichwGFis117BwSYiIiMjeGFisZNolVMcZFiIiIrtjYLGSaUlIpxfRpGNoISIisicGFiuZloQA1rEQERHZGwOLlUwzLAADCxERkb0xsFhJJhOglLMXCxERkSMwsNhA2trMbrdERER2xcBiA54nRERE5BgMLDYwFd7WsRcLERGRXTGw2IDdbomIiByDgcUGShcW3RIRETkCA4sNVApTe37OsBAREdkTA4sN1FwSIiIicggGFhtIMyxcEiIiIrIrBhYbsOiWiIjIMRhYbNDcOI4zLERERPbEwGIDqQ8LZ1iIiIjsioHFBlKnW+4SIiIisisGFhuo2IeFiIjIIRhYbGBaEmLRLRERkX0xsNhAreAMCxERkSMwsNhAmmFhDQsREZFdMbDYgH1YiIiIHIOBxQYqLgkRERE5BAOLDaQ+LFwSIiIisisGFhtwWzMREZFjMLDYgDUsREREjsHAYgO1gruEiIiIHIGBxQZcEiIiInIMBhYbqBTsdEtEROQIDCw2YA0LERGRYzCw2MAUWOoauSRERERkTwwsNuCSEBERkWN0KLCsXr0aoaGhUKvViI2Nxf79+9scv3HjRoSHh0OtVmPUqFHYsmWL2evV1dVYvHgxgoOD4erqioiICKxZs6Yjl9alTDMsDU16iKLo4KshIiLqPWwOLBs2bEBSUhJWrFiBgwcPIioqCgkJCSgpKbE4fs+ePZg7dy4WLlyIzMxMJCYmIjExEVlZWdKYpKQkpKSk4JNPPkF2djaeeOIJLF68GN9++23H76wLmAILwFkWIiIiexJEG6cKYmNjMX78eLz99tsAAL1ej5CQEDz22GN46qmnrho/Z84c1NTU4LvvvpOemzhxIqKjo6VZlMjISMyZMwfPPvusNCYmJgYzZszAP//5z3avqbKyEt7e3qioqICXl5ctt2OTRp0ew/72AwDgtxW3wNtV0WXfRURE1NPZ8vvbphmWhoYGZGRkID4+vvkDZDLEx8cjLS3N4nvS0tLMxgNAQkKC2fhJkybh22+/RWFhIURRxPbt23H8+HHccsstFj+zvr4elZWVZg97cJEJkAnGa2AvFiIiIruxKbCUlZVBp9MhICDA7PmAgABotVqL79Fqte2Of+uttxAREYHg4GAolUpMnz4dq1evxg033GDxM5OTk+Ht7S09QkJCbLmNDhMEQToAkd1uiYiI7Mcpdgm99dZb2Lt3L7799ltkZGRg5cqVePTRR/Hzzz9bHL9s2TJUVFRIj4KCArtdq0rBXixERET25mLLYF9fX8jlchQXF5s9X1xcDI1GY/E9Go2mzfG1tbV4+umn8fXXX2PmzJkAgNGjR+PQoUN47bXXrlpOAgCVSgWVSmXLpXca9mIhIiKyP5tmWJRKJWJiYpCamio9p9frkZqairi4OIvviYuLMxsPAFu3bpXGNzY2orGxETKZ+aXI5XLo9c43iyEtCXGGhYiIyG5smmEBDFuQ58+fj3HjxmHChAl44403UFNTgwULFgAA5s2bh/79+yM5ORkAsGTJEkyZMgUrV67EzJkzsX79eqSnp2Pt2rUAAC8vL0yZMgVLly6Fq6srBg4ciJ07d+Ljjz/G66+/3om32jl4ACIREZH92RxY5syZg9LSUixfvhxarRbR0dFISUmRCmvz8/PNZksmTZqETz/9FM888wyefvppDBs2DJs2bUJkZKQ0Zv369Vi2bBnuueceXLx4EQMHDsQLL7yAhx9+uBNusXOxhoWIiMj+bO7D4ozs1YcFAH7/zh6kn72ENffGYHqk5bodIiIial+X9WGhljMsXBIiIiKyFwYWG7HoloiIyP4YWGwkFd1yWzMREZHdMLDYqHmXEGdYiIiI7IWBxUZcEiIiIrI/BhYbSUW3XBIiIiKyGwYWG6kVnGEhIiKyNwYWG7GGhYiIyP4YWGzE1vxERET2x8BiI6notpEzLERERPbCwGIjU9FtHWdYiIiI7IaBxUbNjeM4w0JERGQvDCw2Yh8WIiIi+2NgsRGLbomIiOyPgcVG7MNCRERkfwwsNmINCxERkf0xsNhIas3PJSEiIiK7YWCxkanoto4zLERERHbDwGIjFt0SERHZHwOLjbitmYiIyP4YWGzUXMPCwEJERGQvDCw2UhtnWHR6EU06hhYiIiJ7YGCxkWmGBeAsCxERkb0wsNhIKWdgISIisjcGFhvJZIIUWrhTiIiIyD4YWDrAtLXZUi+W4so67MkrQyPrW4iIiDqNi6MvoDtSKWSoqrc8w/Ln/x1ExtlL0HipcV/cQPxxwgD0cVc64CqJiIh6Ds6wdIDUi+WKGZbLDU3IzL8EANBW1uHVH3MxMTkVy746jOPFVXa/TiIiop6CgaUDmrvdmgeW7KJK6EXAz1OFlXdFYWSQF+qb9PhsfwFu+dcuzFu3H8WVdY64ZCIiom6NgaUDVApTt1vzJaEj5yoAAKP7e2N2TDC+e2wyPv9THGZEaiATgF3HS/HH9/aitKre7tdMRETUnTGwdIA0w3LFktCRwkoAQGR/bwCAIAiYMKgv3rk3BluTpiDIW42TpTW45z97caGaoYWIiMhaDCwd0NqSUFahYYZllDGwtDTEzwOfLpoIf08VjhdX497396P8coPN3731WDHiklPxt6+PoLKusQNXT0RE1P0wsHSApSWh2gYdTpQYCmtHBV8dWAAg1Ncdny6aCF8PFbKLKnHf+/tRUWt96DhyrgKPfXYQRRV1+N++fMSv3ImUrCKIongNd0NEROT8GFg6wFIflmMtCm4DvNStvneovwc+XRSLvu5KHCmswP0f7EeVFTMl2oo6PPjxAdQ16jEhtC8G+bqjpKoeD39yEA/9NwNFFbXXfmNEREROioGlA5qXhJpnWNpaDrrS8ABPfLIwFj5uCmTml2PBBwdQcbn10FLboMOij9NRXFmPYf4e+M/94/DDkuvx2E1D4SITsPVYMW5+fRc+TjsDnZ6zLURE1PMwsHSA1IelRQ3LEWNgibQisABARJAXPlkYC0+1C9LPXsK013fgq4Pnrlre0etFJH1+CEcKK9DXXYn354+Hl1oBtUKOv94Shu8fvx5jBvigur4Jy785ihe3ZHfSXRIRETkPBpYOUCuu3iVkywyLSWR/b3y2aCKG+nugrLoBSZ//hrnv7UVeSbU05vWtx/FDlhZKuQzv3heDAf3czD4jTOOJLx6ehGUzwgEAGw4UoK6RZxwREVHPwsDSAc0zLIZgUNeowwljyLAlsACG0LLl8euxNCEMaoUMe09dxIxVu/DqjzlYvz8fb2/PAwAk3zkK40P7WvwMuUzAousHI9Bbjer6JuzILenorRERETklBpYOUCnMtzUfK6qETi/C10OFAC+VzZ+ndJHh0alDsfUvU3BTuD8adSJWbz+Jp746AgB45MYhmB0T3OZnyGQCbosKAgB8+9t5m6+BiIjImXUosKxevRqhoaFQq9WIjY3F/v372xy/ceNGhIeHQ61WY9SoUdiyZYvZ64IgWHy8+uqrHbm8Lndl0a2pw+2o/l4QBKHDnxvS1w3vzx+HNffGINDbsNMoYWQAlt4SZtX7bzcGltTsEqt2HhEREXUXNgeWDRs2ICkpCStWrMDBgwcRFRWFhIQElJRYXobYs2cP5s6di4ULFyIzMxOJiYlITExEVlaWNKaoqMjssW7dOgiCgNmzZ3f8zrqQaUnItK35SAfqV1ojCAKmR2rwc9IUfLIwFm//cSxkMutC0MggLwz2dUd9kx5bjxVf87UQERE5C5sDy+uvv45FixZhwYIFiIiIwJo1a+Dm5oZ169ZZHL9q1SpMnz4dS5cuxYgRI/D8889j7NixePvtt6UxGo3G7PHNN99g6tSpGDx4cMfvrAtd2ek2y8YdQtZwV7lg8jBfKOTW/4gEgctCRETUM9kUWBoaGpCRkYH4+PjmD5DJEB8fj7S0NIvvSUtLMxsPAAkJCa2OLy4uxvfff4+FCxe2eh319fWorKw0e9iTVMPSqDMvuG2lw6093R5tCCy/nCjDxRrbW/8TERE5I5sCS1lZGXQ6HQICAsyeDwgIgFartfgerVZr0/iPPvoInp6euPPOO1u9juTkZHh7e0uPkJAQW27jmrXsw9JccKuEpo0Ot/YyxM8DI4O80KQXseVIkaMvh4iIqFM43S6hdevW4Z577oFa3fov/2XLlqGiokJ6FBQU2PEKW/RhadKZLQddS8FtZzIV327mshAREfUQNgUWX19fyOVyFBebF3QWFxdDo9FYfI9Go7F6/O7du5Gbm4sHH3ywzetQqVTw8vIye9hTyxmW5h1Cjl8OMrnVGFj2n7kIbUWdg6+GiIjo2tkUWJRKJWJiYpCamio9p9frkZqairi4OIvviYuLMxsPAFu3brU4/v3330dMTAyioqJsuSy7k4puG/U2t+S3h/4+rhgf2geiCHx3mLMsRETU/dm8JJSUlIT33nsPH330EbKzs/HII4+gpqYGCxYsAADMmzcPy5Ytk8YvWbIEKSkpWLlyJXJycvDcc88hPT0dixcvNvvcyspKbNy4sd3ZFWdgCiwVtY0d7nDb1W7nbiEiIupBbA4sc+bMwWuvvYbly5cjOjoahw4dQkpKilRYm5+fj6Ki5mLPSZMm4dNPP8XatWsRFRWFL774Aps2bUJkZKTZ565fvx6iKGLu3LnXeEtdT6UwLAkVltdCpxfRz10pNXpzFjNGBUIuE3D4XAVOl9U4+nKIiIiuiSBeeTxwN1RZWQlvb29UVFTYpZ4lu6gSM1btlv48ZbgfPnpgQpd/r63ue38fdp8oQ9LNw/H4tGGOvhwiIiIztvz+drpdQt2BaUnIxNmWg0xaLgv1gFxKRES9GANLB6iNS0ImzlRw21JCpAZKFxnySqqRo61y9OUQERF1GANLB1w1w+IEHW4t8VIrMDXMDwDwzSEW3xIRUffFwNIBqhYzLH3dlQhysoLblmZF9wcAfJx2Bjla+x5hQERE1FkYWDqg5QyLM3W4tSRhpAaTh/ricoMOiz5Ox6VrPF+ItTBEROQIDCwd4CITIDNmlFH97dtl11ZymYC35o5BSF9XFFysxeLPDqJJp7fpM+oadVj3y2lMfDEVN/9rF2obdF10tURERJYxsHSAIAhSe35n3SHUUh93Jd6bNw5uSjl+zbuA5B9yrHpfXaMO7/9yGte/sh3/+O4YtJV1yCupxracki6+YiIiInMMLB00sJ8b1AoZxg7s4+hLsUq4xgsr7zIcefD+L6fxZca5Vse2DCrPf3cMpVX16O/jiklD+gHgoYpERGR/Lo6+gO7qs0UTUVXXBH9P5y24vdKMUYF47KaheGtbHpZ9fQRD/D0QHeIDwHDy9K95ZdhyRIutx4pRUdsIwHAu0eKbhmL22GCcKKnCzDd/wbbcElTWNcJLrXDg3RARUW/CwNJBfdyV6OOudPRl2Owv8cORXVSJn7NL8PB/M7Dsd+HYkVuKn48Vo6q+SRoX3McVi6cOxZ1jg6E0FhlHBHphsJ87TpXWYOvRYsyOCXbUbRARUS/DwNLLyGQC/jUnGnf8ew/ySqqxZP0h6bUALxVmRAZiRqQG40L7Qi4z3/0kCAJujwrCGz+fwObD5xlYiIjIbhhYeiFPtQJr74vB3Pf2wkUmw/RIDX43SoMxIX0gk7W9RfvW0YbA8suJMlysaUDfbjjLRERE3Q8DSy812M8D+56Ot/l9Q/09EBHohWNFlUjJ0uKPsQO64OqIiIjMcZcQ2ez2aNOhioV2+b6dx0sRl5yK7dxOTUTUazGwkM1mjgoEAOw7fRHFlXVd/n2bMgtRVFGHLUeKuvy7iIjIOTGwkM1C+rph7AAfiCLw/eGuDxFHz1cAAM5dqu3y7yIiIufEwEIdcluUYVlo8+GubSJX26BDXkk1AKDg0uUu/S4iInJeDCzUITNHB0ImAJn55Si42HVBIkdbCb3xvMWiijqbz0EiIqKegYGFOsTfU42Jg42t+rtwluXo+Urpn3V6EUUVXV8zQ0REzoeBhTpMWhb6revqWFoGFoB1LEREvRUDC3XY9JEauMgEZBdVIq+kqku+45ix4NbUdZd1LEREvRMDC3VYH3clbhjuB6BrZlmadHrkaA1BaEJoXwCcYSEi6q0YWOia3BZl6Mmy+bfzEEWxUz/7ZGkN6pv08FC5YPIwXwDAOc6wEBH1SgwsdE1ujtBA5SLDqbIapGRpO/WzswoNy0ERgV4I6esGADh3kTMsRES9EQMLXRMPlQsWTh4EAFj29RFordjF8+qPOZj4Ymq7dS+mgtuIIC8E93EFwBkWIqLeioGFrtkT8cMR2d8L5Zcb8X8bf4Ne3/rS0Ie/nsbq7SehrazD5+nn2vxcU4fbkS0CS1FlHRqa2IuFiKi3YWCha6Z0keGNOWOgVsjwS14Z1v162uK47Tkl+Md3x6Q/b2vjMENRFHGsyDDDMjLIG34eKqhcZBBFoKiCy0JERL0NAwt1iqH+Hnj21ggAwCspuTh2Rf+UHG0lHvssE3oRuHV0IOQyAXkl1ci/YHmJp+BiLarqmqCUyzAswAOCILRYFmo7sDQ06fHOjpPI0Va2OY6IiLoPBhbqNH+cMADxIwLQoNPjiQ2ZqGvUAQBKquqw8MN0VNc3YeLgvnj9D9EYN7APAGBbTrHFz8oyLgeFaTyhkBv+mpoKb9s7CmDLkSK8nJKDF77P7pT7IiIix2NgoU4jCAJenj0Kvh4qHC+uxks/5KCuUYeHPs5AYXktBvm6Y829MVC6yHBTuD8AYFtuqcXPalm/YmLtDItpd1FXnnFERET2xcBCnaqfhwqv3TUaAPDhnjO4e+1eHCooh4+bAuvuHw8fNyUASIFl78kLqKlvuupzTDuEzAOLcYalnZ1CpmZzRRV1nd4bhoiIHIOBhTrdjWH+uH9SKADgUEE5FHIBa+6NwSBfd2nMUH8PhPR1RYNOj1/zyq76jOYtzd7ScyHGwNLeDIupdqW+SY/yy43XdC9EROQcGFioSzw1IxwjAg2zIy/cMUo62dlEEATcFGaYZdmea75bqKSqDqVV9RAEYESgp/S8Nb1YSqrqUFbdIP1ZW8nTnYmIegIXR18A9UxqhRxf/3kSSirrMaCfm8UxU8P98VHaWWzPKYUoihAEwwGHptmVIX4ecFM2/xU1Fd0WV9ajrlEHtUJ+1WfmFJk3o9NW1EnBiYiIui/OsFCXUSvkrYYVAJg4uB9cFXJoK+uknisAcLTw6oJbAOjjpoCb0hBSzpdbXha6citzkRWdd4mIyPkxsJDDqBVyXDfUcKjhtuzmZSFLBbeAYRkpRCq8tRxYso0zLMbJGmjZZI6IqEdgYCGHat7ebCmweF81vr06lmzjTM3oYB8ArGEhIuopGFjIoaaG+wEw7Ca6UF2PyrpG5Bv7p1w5wwK03YuloUmPk6XVhs8NM3wul4SIiHqGDgWW1atXIzQ0FGq1GrGxsdi/f3+b4zdu3Ijw8HCo1WqMGjUKW7ZsuWpMdnY2br/9dnh7e8Pd3R3jx49Hfn5+Ry6PupFAb1eMCPSCKAI7ckullv79fVylni0ttdXt9lRZNRp1IjxVLhg3sC8AWHV6NBEROT+bA8uGDRuQlJSEFStW4ODBg4iKikJCQgJKSiwfZLdnzx7MnTsXCxcuRGZmJhITE5GYmIisrCxpzMmTJzF58mSEh4djx44dOHz4MJ599lmo1eqO3xl1G9NaLAu1Vr9i0tYMi2k5KDzQExpvw98dBhYiop7B5sDy+uuvY9GiRViwYAEiIiKwZs0auLm5Yd26dRbHr1q1CtOnT8fSpUsxYsQIPP/88xg7dizefvttaczf/vY3/O53v8Mrr7yCMWPGYMiQIbj99tvh7+/f8TujbmOqMbDsOl6K3wrKAViuXwGau91aqmExbWkO13hJgaWqvgnVFjrpEhFR92JTYGloaEBGRgbi4+ObP0AmQ3x8PNLS0iy+Jy0tzWw8ACQkJEjj9Xo9vv/+ewwfPhwJCQnw9/dHbGwsNm3a1Op11NfXo7Ky0uxB3Vd0iA/6uitRVdeElKNaAK3PsJh2CZVVN6C2QWf2WraxJX94oCc8VC7wVBt6uHCWhYio+7MpsJSVlUGn0yEgIMDs+YCAAGi1Wovv0Wq1bY4vKSlBdXU1XnrpJUyfPh0//fQT7rjjDtx5553YuXOnxc9MTk6Gt7e39AgJCbHlNsjJyGUCpgw3FMk2NOkBACP7Ww4sXq4u8FQZgkhhufksi2lJyNQoLpDLQkREPYbDdwnp9YZfULNmzcJf/vIXREdH46mnnsKtt96KNWvWWHzPsmXLUFFRIT0KCgrsecnUBUzbmwGgr7sSGi/L9UuCICBYKrxtrmMpq65HaVU9ACAswNDOP8D4GUXsxUJE1O3ZFFh8fX0hl8tRXFxs9nxxcTE0Go3F92g0mjbH+/r6wsXFBREREWZjRowY0eouIZVKBS8vL7MHdW83DPeDXGbo9jYyyEtq02+JpV4sucbloIH93OBunIExzbAUsxcLEVG3Z1NgUSqViImJQWpqqvScXq9Hamoq4uLiLL4nLi7ObDwAbN26VRqvVCoxfvx45Obmmo05fvw4Bg4caMvlUTfm7apAzMA+AFovuDWx1O1WWg7SNIdXjbch2LAXCxFR92fz4YdJSUmYP38+xo0bhwkTJuCNN95ATU0NFixYAACYN28e+vfvj+TkZADAkiVLMGXKFKxcuRIzZ87E+vXrkZ6ejrVr10qfuXTpUsyZMwc33HADpk6dipSUFGzevBk7duzonLukbuH/JYRh9fY83DtxQJvjLM2wmFryh7c43Zk1LEREPYfNgWXOnDkoLS3F8uXLodVqER0djZSUFKmwNj8/HzJZ88TNpEmT8Omnn+KZZ57B008/jWHDhmHTpk2IjIyUxtxxxx1Ys2YNkpOT8fjjjyMsLAxffvklJk+e3Am3SN3FuNC++GDBhHbHhVioYTEdehjecoZFqmFhYCEi6u4EURRFR1/EtaqsrIS3tzcqKipYz9ILZBdVYsaq3ejjpkDm8lvQpNMjYvmPaNDpsWvpVOmEaNO4fu5KZDx7s4OvmoiIrmTL72+H7xIispVpSejS5UZU1zfhVFkNGnR6uCvl0mtA85LQhZoG1DXqLH4WERF1Dwws1O14qhXwcVMAMNSxmApuwzSekMmadxd5uyqgVhj+ipdU1tv/QomIqNMwsFC3JBXeXqxFjnFLs6lhnIkgCC3qWNiLhYioO2NgoW6peWvzZeRIhx5evf4pHYLIXixERN0aAwt1Sy1PbTZtaR6h8bxqXKCxFwu3NhMRdW8MLNQtmU5tPlJYIc2ehFkILKYZFm5tJiLq3hhYqFsK6WuYOUk/c1H6s6dacdU4Uw0L2/MTEXVvDCzULZlmWPTGLkItG8a1xBkWIqKegYGFuqWW/VYAy/UrANvzExH1FAws1C25KV3Qz10p/fnKLc0mphmWkqo6NOn0drk2IiLqfAws1G0FG88UAixvaQYAX3cVXGQC9CJQVt1gr0sjIqJOxsBC3ZZpWchVIceAFuGlJZlMQACbxxERdXsMLNRtmQJLmMYT8hYt+a+kYR0LEVG3x8BC3da4gX0BANcN7dfmOO4UIiLq/lwcfQFEHXVzRAB+feomBBqXfFrDXixERN0fAwt1a/19XNsdE8gZFiKibo9LQtTjsYaFiKj7Y2ChHk+aYankLiEiou6KgYV6PNO25uKKeoii6OCrISKijmBgoR7P31MNQQAadHpcrGHzOCKi7oiBhXo8pYsMvh4qACy8JSLqrhhYqFfgIYhERN0bAwv1CqY6Fi17sRARdUsMLNQrOHqGpay6Hr+cKHPIdxMR9QQMLNQrOLI9f32TDn94Nw33vr8P+09ftPv3ExH1BAws1CtIMywO6MXy/i+ncaq0BgCQfpaBhYioIxhYqFeQaljsPMNyvrwWb6XmSX/O1VbZ9fuJiHoKBhbqFQK9DWcOFVXU2bV53AvfZ6O2UQcvteHYLgYWIqKOYWChXsF0YvPlBh2q6pvs8p2/5pXh+yNFkAnAyj9EAwDySqrR0KS3y/cTEfUkDCzUK7gq5fBxUwAAii0sCzXp9J0689LQpMeKb48CAO6bOBDxI/zhqXJBk17EqbLqTvseIqLegoGFeg3TLMuVO4W255Qg9sVU3P/BgU77rg/3nEZeSTX6uSuRdEsYBEFAmMYTAJeFiIg6goGFeg3NFb1YdHoRr/+UiwUfHsCFmgbsPF7aKWcNFVfWYdXPJwAAT84Ih7erYWbHFFiyixhYiIhsxcBCvUZgi14sF2sacP8H+/HmNsMOHqWL4X8KGWcvXfP3vPB9NmoadIgO8cHvxwZLz4dLMyyV1/wdRES9DQML9RoaL8NOoV/zynDrm7ux+0QZ1AoZ/jUnCneO6Q/g2vukpJ28gG9/Ow9BAJ6fFQmZTJBeCw/0AgDkcEmIiMhmLo6+ACJ70XgbTmzef8YQSgb5uuOde8ciXOOFJp2I9QcKcPAaZ1he3JINAPjjhAEYFext9trwAMMMS1FFHSouN8LbWARMRETt4wwL9RpBPq7SPyeMDMA3i69DuMYw6xEzsA8A4LdzFahv0nXo83O1VThSWAGFXEDSzcOvet3bVYEg47JUbjFnWYiIbMHAQr1G7KB+mDshBP+YNRJr7o2Bl7p5hmOQrzv6uSvR0KRHVmHHaky+OVQIALgxzB/9PFQWxzQvC7GOhYjIFgws1GsoXWRIvnM05sWFQhAEs9cEQcBY4yxLRgfqWPR6Ed8cOg8AmBUd1Oo4004h1rEQEdmGgYXIaJwUWGyvYzmYfwmF5bVwV8oRPyKg1XHh7MVCRNQhHQosq1evRmhoKNRqNWJjY7F///42x2/cuBHh4eFQq9UYNWoUtmzZYvb6/fffD0EQzB7Tp0/vyKURddi40ObAYmvX203G5aCESA3UCnmr40w1M7naKrueaURE1N3ZHFg2bNiApKQkrFixAgcPHkRUVBQSEhJQUlJicfyePXswd+5cLFy4EJmZmUhMTERiYiKysrLMxk2fPh1FRUXS47PPPuvYHRF10MggbyjlMpRVN+DshctWv69Rp8f3h4sAAInR/dscO9jPHQq5gOr6Jpy7VHtN10tE1JvYHFhef/11LFq0CAsWLEBERATWrFkDNzc3rFu3zuL4VatWYfr06Vi6dClGjBiB559/HmPHjsXbb79tNk6lUkGj0UiPPn36dOyOiDpIrZBLW5HTbVgW2n2iFJcuN8LXQ4lJQ/q1OVYhl2GInweAnrMsJIoidHrOFhFR17IpsDQ0NCAjIwPx8fHNHyCTIT4+HmlpaRbfk5aWZjYeABISEq4av2PHDvj7+yMsLAyPPPIILly40Op11NfXo7Ky0uxB1BnGdaDw1lRse+voILjI2/+fVLhUeNv9/96Kooi57+3FDa9sR8XlRkdfDhH1YDYFlrKyMuh0OgQEmBcVBgQEQKvVWnyPVqttd/z06dPx8ccfIzU1FS+//DJ27tyJGTNmQKez3A8jOTkZ3t7e0iMkJMSW2yBqVYyNhbc19U346WgxgLZ3B7UUpuk5HW9PlFRj76mLKCyvxebD5x19OUTUgznFLqG7774bt99+O0aNGoXExER89913OHDgAHbs2GFx/LJly1BRUSE9CgoK7HvB1GOZtjYfL662asbg5+xi1DbqMLCfG6JDfKz6jvAetLV567Fi6Z+/zix04JUQUU9nU2Dx9fWFXC5HcXGx2fPFxcXQaDQW36PRaGwaDwCDBw+Gr68v8vLyLL6uUqng5eVl9iDqDL4eKgzydQdg2Krcnk3GX9Kzovtf1dulNeGBhsByuqymw111LamobYTezrUkP7UILBlnLyHfhmLla1Vd34Rdx0tR19h5/w6JyHnZFFiUSiViYmKQmpoqPafX65Gamoq4uDiL74mLizMbDwBbt25tdTwAnDt3DhcuXEBgYKAtl0fUKUzLQu0dhHihuh67TpQBsH45CAA0Xmp4qV2g04vIK6nu+IW2sOt4KaL/8RNe+ym3Uz7PGsWVdfitoBwAEGHs4Gva3t2VKusa8VbqCUx+eRvmrduPl1Nyuvw7icjxbF4SSkpKwnvvvYePPvoI2dnZeOSRR1BTU4MFCxYAAObNm4dly5ZJ45csWYKUlBSsXLkSOTk5eO6555Ceno7FixcDAKqrq7F06VLs3bsXZ86cQWpqKmbNmoWhQ4ciISGhk26TyHqmwtv0M23PsGw5UgSdXsSo/t7Szh9rCILQ3KK/qHOWhd7/5TREEfjv3rN2m3H4OdswuxId4oOFkwcBMCwLdVV/mfLLDXj9p1xc99I2rNx6HOXGJbstR4rY04aoF7A5sMyZMwevvfYali9fjujoaBw6dAgpKSlSYW1+fj6Kioqk8ZMmTcKnn36KtWvXIioqCl988QU2bdqEyMhIAIBcLsfhw4dx++23Y/jw4Vi4cCFiYmKwe/duqFSWz2Mh6krNByGWo1Gnb3WcNa34WyN1vG3lEMTSqnr8Z/cp1NQ3tftZ2oo67D5RCgCoqmvCjlzLPZE6m6l+5eaIAEyP1MBVIcfpshr8dq6iU7+nrlGHl37IwXUvbcOb2/JQVdeEYf4eeP0PUXBVyFFcWY+j57v/jisiaptLR960ePFiaYbkSpYKZe+66y7cddddFse7urrixx9/7MhlEHWJIX4e8HZVoKK2EcfOVyLKQjFtwcXLSD97CYIA3BZle2Bp60whnV7EQ/9NR2Z+OQouXsbfZ0W2+VlfZxaiZenK15mFmB7Ztcup1fVN2JNnaD1wS0QA3FUuuGVkAL45dB5fHzxndQGyNf69PQ9rdp4EYFh6euymoUgYqYFMJmDLES1+zi7G9pwSRPb37rTvJCLn4xS7hIiciUwmtKhjsbws9O1vhtmVuMH9EOCltvk7TC36c4qunhn4ZO9ZZOaXAwA+Tz+H8ssNrX6OKIr4IsOwS+6B6wzLMttyStp8T2fYdbwUDTo9Qvu5Yai/YTkscYyhy+/mw0VtzkzZau8pQy3R0oQwfP/4ZMwYFQiZzFDgPG2EPwAgNcc+s0pE5DgMLEQWxLTRQO5STQM+TzeEhPZa8bfGNMNSUlWPSzXN4aKwvBavGItIXRVy1Dbq8L99+a1+zqGCcpwsrYFaIcNfbh6GEYFeaNSJ+P5IUavv6Qwtl4NMu6OuH+oLXw8lLtY0SEtU10qvF3HMGOriRwRctRNrapghsPx2rhwXqus75TuJyDkxsBBZ0LLwtmVB57lLl/H7NXtw9sJl9HVXIiGy9e35bfFQuSC4jyuA5mUhURTx7KYs1DToEDOwD/4xayQA4KM9Z9DQZHnG4ouMcwCAGZGB8FQrcMcYw/LUpi7sidKo02ObcUbj5ojm+3eRy6Tlsa8Ods73n714GdX1TVC5yDDEz/2q1zXeakQEekEUgR25nROSiMg5MbAQWTA62AcuMgElVfXSIYVHz1fgzn/vwcnSGgR6q7H+oYnwdlV0+DukZSFji/7vDhdhW04JlHIZXrpzFGZF94e/pwolVfXY/NvVXWTrGnXS0tTvY4IBALdH9YcgAAfOXELBxa7piXLgzEVU1Daij5sCYwf4mL125xjDdWw9Voyqumtv1X/0vKGANzzQq9VjD0zLQtu4LETUozGwEFngqpRjpLGIM+PsJfyaV4Y57+5FSVU9wgI88dWfJ2F4gOc1fYe0U0hbhfLLDfj75qMAgEenDsWwAE8oXWSYPykUAPDe7lNXbd01hIImBHmrETfYcOiixlstHcD4TQd6otQ16rDgg/346+e/oamVOhTTctBN4QFXhYjI/l4Y4ueO+iY9fsiyfFyHLbIKDWEuMqj15pBTww2BZdfx0k6tnSEi58LAQtQK07LQ2l2ncP8H+1Fd34SJg/vi84fjEOjtes2fb6pjydZW4YXvs1FW3YDhAR545MYh0ph7YgfAVSFHjrYKe06aHwhqWg6aHRMsFaECzXU1X3WgJ0pKlhbbc0vx5cFzePXHq5vQiaJoVr9yJUEQcIex+LYzlqVMMywjg1rfARQV7IN+7kpU1TfhwBnrD63sSQ6cuYjof/yEzw/wmBLquRhYiFphCizHiirRqBMxc3QgPnpgwjUtA7U0wtiiP6uwAhszzkEQgOQ7R0Pp0vw/Sx83Jf4wzrDM8t7uU9LzLXuvzB4bbPa50yM1UCtkOFVagyOFtvVE+Wx/c4Hvu7tOXTVLk6OtwrlLtVC5yHDDcF+LnzHLGJjSTl1AUUWtTd/fkiiKUn+VkW3MsMhlAqaE+QEAtvfSZaH3dp1C+eVGbMxgYKGei4GFqBUxoX1gmrhYOHkQ3rp7DFQu8k77/NB+7lC6yKAzNlGZN3GgtDuppQXXDYIgGIpKTxgbzZl6r4wP7YNQX/NiVE+1QiqGteVAwpOl1dh3+iJkAqSQ9OSXh5HVIvSYZlcmD/WFm9JyG6eQvm6YENoXotjcXK8jtJV1uFjTALlMkGajWjMt3DDb46x1LCt/ysXMN3fjYk3nbzevrGuUCo4Pn6vgshj1WAwsRK3w91Tjrblj8fYfx+DZWyPMll06g4tchqHGlv6B3mosnR5ucVyorztuMS6/GFrwN/deMRXbXsm0W2jzb+dbrUW50nrj7MrUMH8k3zkaN4b5oa5Rjz/9N0PaMtzWclBLiZ2wLGSqXxnm7wG1ou2geP1wX7jIBJwsrcHZCzUd/s6uUFpVj3d2nMTR85X4+Vhx+2+w0U9Hi9Fg/BnXN+k77bgHImfDwELUhpmjA3HraNs72dry+W5KOV6ePRoeqtYbTz94/WAAhrqUn7NLpN4rvxtluaPt9cP80NddibLqBvySV9buddQ36fClcSvy3AkDIJcJWHX3GAzydUdheS0e/fQgCi5expHCCggCMG1E24Fl5qhAKOUy5GirsO/UhTbHtsaa+hUTL7UC40INs1PONsvydeY5NBln0do7ULMjvr1iB1lmQfunjBN1RwwsRA706NShOLziFtww3K/NceMG9kFUiA8amvRI+vwQgObeK5Yo5DLcNtoQZqxZFvrpaDEu1jRA46XGjcZ6EG9XBdbeFwN3pRx7T13EvHX7AQBjQnzg59n2OV/ebgrMjjHMsvxtUxbqm2w/kNE0w9JW/UpLzrgsJIoiNrQohM1opXNyR12orseveeYnhh8ydkkm6mkYWIgcrLX+Ii0JgoBF1xta71fVGQ5EbG05yOQOYzHuj0e1qG7nEEVTse0fxoeYXc+wAE/8a040AOB0mWGppWWzuLY8OT0cvh5K5JVUY82OU+2/4QrHjDMs1p4RZNrevO/URasOjbSHg/mXcLK0BipjIfXJ0hqzzsbX6ocsrXRiuGl3VmZBead9PpEzYWAh6iamj9Sgv49hO3XL3iutiQr2xiBfd9Q16vHT0dZ7opwpq8GekxcgtCi2bemWkRo8ET9M+nN79SsmPm5KLL/N0K139fY85JVUW/U+ALhY04DzFXUAmndTtWeInzsG9nNDg05v1TKYPZhmV2aODpQ69XbmLItpOej2qCDpwMnTZZ0bioicBQMLUTfhIpdhyTRDcHhg8qB2i4AFQZB6sry78xQqW+k8u974S3XKcD8E93GzOObxm4bhsZuGIunm4dJhh9a4bXQgpob5oUGnx9NfHYFeb11fGFP9yiBf91aXva4kCIJ0ttC2bMcvC1XXN+G7w4YzneaMC8G4gX0BABn5nRNYiipqpb4zM0cHwsdNicHGHWOHzpV3yncQORMGFqJu5A/jQ5DxTDwWTh5k1fi5E0Lg66FEbnEVHvo4HXWN5rUkDU16acfR3AkDWv0cmUzAX28Jw+PThrU6xhJBEPB8YiTclHLsP3MRG9Kt6xNiql+JsLJ+xeQm47LQ9twSm5vmdbbvD5/H5QYdBvm6Y8Kgvs0Hap7pnMDy/eEiiMat7UHGmbdo41EJmaxjoR6IgYWom+nnobrq1OLW+Hup8eGCCfBQuWDvqYt4Yv0hqe8LAPycXYyy6gb4e6qkX/adLbiPG/56SxgA4MUt2SiprGv3PaYZlkgrdgi1FDu4L9yUcpRU1UtN5xzFtBz0h3EhEAQBMcZdTL+dK2/1MEtbbG6xHGQyZoDhOzI7aRaHyJkwsBD1cJH9vbF2XgyUchlSjmrxzKYsafbBVGx717hgKKwo/u2o+yeFYnSwN6rqmvCc8cyktljT4dYSlYsck4caOvD+nN35PU+slVdShYP55ZDLBGm31GBfd/RxU6C+SS8Fso46e6EGv52rgEwAZrTY2j7GWMdyqKDc6uU3ou6CgYWoF5g0xBer7o6GIBhCyr+2HkfBxcvYfcJQnHr3+NaXgzqDXCbgpTtHQy4TsOWIVmpAZ0lVXaO0I8nWwAI0FwV/nHZWanhnb6bZlalh/vD3VAMwLI9Jy0LXWHhrqo25bqgvfD2at5iHaTyhVshQVdeEU2XO1UCP6FoxsBD1EjNGBeKfiZEAgDe35eFP/80AAFw/zBchfS0X23amiCAvLDI2wFv+TVarW62zjZ1aA73V6OfRdr8XS2ZF90e4xhMXaxrw3OZjHb/gDmpo0uMrYxO+OeNDzF6LMRXeXmNg+dZ45MFtUeZNDRVyGUb39wHAZSHqeRhYiHqRe2IHIunm4QAMhzoCwB/bKLbtbEumDcOAvm4oqqjD2l2We7PY0uHWEqWLDK/+PgpymYDNv51vc0t3V9iWU4wLNQ3w81Rhaph5Q0BTN970s5c6XBScq61CbnEVFHIBCSOv7okzxlR4y34s1MMwsBD1Mo/dNBTz4wYCAHw9VO222e9Mrko5npphODPp/d2nLB4GaGuHW0tGBXtLsznPbMpCRa3lLd1dwbQcNHts8FVNAUf194ZCLqC0qh7nLnXsJOvvDhtmV6YM97d4cripHws73nZfhwrKseyrI6i4bL+/t90BAwtRLyMIAlbcNhKvzB6NdfePg9LFvv8ZmD5Sg5FBXqhp0OHdnSevev2ojR1uW/NE/DAM9nNHSVU9XvjePktD2oo67DxuODnZUhM+tUIu3VdHzhUSRbG5WVy05TOuTDuFcrSVuNzgHB1/yTYv/5CDz/bn4/1fbO8Q3ZMxsBD1QjKZgD+MD8HoYB+HfPf/Gbc5f5R2xmybc12jDieMHXGvZYYFMISDV2aPhiAAn6efwy5jkOhKX2QUQC8CE0L7YrCf5QZ7McZAkd6BfixHCitw9sJluCrkiB9heRu6xluNQG819CJw+Ny17UZyBu/tOoWJL6Yi4V+78NDH6Ujeko1P9+Vjz8kyFFuxRb67adLpcci4nLct1/ENEJ0JAwsR2d2NYX4YO8AHdY16vL09T3r+eHEVdHoRfd2VCPRWX/P3jAvti/lxoQCAZV8duarQVxRFpJ+5iOe/O4YtR4qu6bvySqrx4Z6zAAwN/lq/po7vFPrI+PnTRvjDTdn66d7RLbY3d1eiKOKVlBy8sCUb2so65BZX4adjxXh31yk8/fUR/PG9fYh9MRUbDuQ7+lI7VY62CrXGBo9ZhZXQVvS8UNZRDCxEZHeCIOD/EgyzLJ/tz0fBxcsAzOtXrG2O156lCWEI7uOKwvJavJKSAwAoLK/F29tOYOprO/D7NWl4/5fTeGL9Iek6bHXsfCXmvJuGsup6DPP3wMwWvVGuNNa4tTm3uKrV4xIsyTh7CV8ePAcA7XY6lgpvu+lOIb1exN83H8O/dxiWDJcmhOHDBePx99tH4v5JoZga5ocgY6A1bfHuKa4Msts5yyJpPaITEXWhSUN8cd3Qfvg17wLeTD2BV++KuuYdQpa4q1zw0p2jce/7+/Bx2lnkFFXhwNmLMG3ScVPK0cdNicLyWrz2Uy5W3T3Gps8/mH8J96/bj8q6JowM8sLHD0yAq1Le6nh/TzUG9HVD/sXLyMwvx5Thfq2ONdHpRSz/JguAoTbGVKfSGtPrB/PLIYpip4U/W+SVVOFUaQ3iRwS0e+5VSzq9iKe+PIyNGecgCMDzsyJx78SBV43LLqrEjFW7cfDsJTTp9Fadet4dmAKLj5sC5ZcbsS2npM1jM3qTnvETJqJuyVTL8uXBczhZWo2sDna4bc/kYb6427hMs/+MIaxMHNwXr90VhQN/i8e798UAAL45dB5ZhdbXfezJK8O9/9mHyromjBvYB589NNGq3jHjbGwg9+m+szh6vhJeahc8OT283fGRQd5wkRl2I513wJJCVV0j7lqThof+m4FH/pfRas+dKzU06fH4+kxszDgHmQCsvCvKYlgBgLAAT3iqXVDToJN69/QEpr8Tf75xCADglxNlV50B1lsxsBCRw4wZ0AfxI/yhF4HXfsxFjrE3zLXuELLkbzNH4N6JA7Bk2jDs/n9Tsf6hOPw+JhjuKhdE9vfGLOOum+Qfsq3qkbItpxj3f3gAlxt0mDzUFx8vnAAvK0+WHisFlvZ3Cl2orserP+YCAP4vIcyqQOSqlCM80BOAY7Y3f5x2FpeMW3J/PFqMO//9K85eaLvzbl2jDo98koHvDxdBIRfw73vG4s6xV++0MpHJBCn4mU6t7u6KK+tQWF4LmWA4jDTAS4XaRh32nrrg6EtzCgwsRORQSTcbZll+yNKivkkPD5ULBnZB511PtQL/TByFv9w83GJn3/+7JQxKuQy/5l3ALuORBa357vB5PPRxBhqa9Lg5IgD/mT+uzSLYK5kKbw/ll6NJ1/ZBiC+n5KCyrgkRgV64J9bybIMlY0I69yDE48VVOGNFu/+quka8t9uwHfdPUwbD31OF48XVuP3tX7H7xNU7tS7WNODfO/Iw9bUdSM0pgcpFhvfmjcP0yNbrgEzGDzJ0Du4pgeWgcXYlXOMFT7Wi+fTxHNaxAAwsRORgEUFeuHV08y+niEAvm2oeOktIXzfcZ2yol7wl2+xU65a+zDiHxz/LRJNexKzoIPz7nrFQK1qvWbFkuL8nPFWG5YwcbevLGQfzL+HzdEOh7fOJIyG34d9LZ3a8/emoFtPf2IXpq3bhZGl1m2M/TjuL8suNGOLnjv+XEI7Nj01GdIgPKmobMX/dfry36xREUUR2USWe/OIw4pJT8UpKLooq6uDrocJHD0zAjWHWnRw+PtQUWDreObgziaKI6vqmVv/utMe0HGQ6c+qmcENTx9ScEqe4P0dj0S0ROdxfbh6OLUeKoBcNAcZRFk8dis/TC5CjrcKmzELMjjFfkthwIB9PfXUEogjcPT4EL9wxyqYQYSKTCRgzsA92HS9FxtlLFpfAWhbazh4bLJ1DZC3T1uaswgo0NOk73CAw4+wlPL4+E3oRqGvUY+nG37Dx4UkW77vl7Mrj04ZBLhMQ4KXG+ocm4tlNWdiYcQ4vbMnGp/vzpQMuASCyvxcWTBqEmaMDbQp/o4O9oXSRoay6HmcuXMYgX/cO3WNn0OlF/OHdNCl0qBUyuCtd4KqUw13pgqH+Hnjtrqg2C7Iz8s0Dy3VD+0HpIsO5S7U4UVKN4QGeXX8jTowzLETkcEP8PDDP2C9lWisN0eyhj7sSf75xKABg5U+5ZsWOn+w9iye/NISV+yYOxIsdDCsm7RXefrY/H1mFlfBUu0jHGdhikK87vF0VqG/SI0db2aFrPFlajQc/OoC6Rj2uG9oPHioXHMwvx7pfTlscb5pdGeznjltHN3fiVSvkeOX3o/HcbRGQywScLquBXCZg5uhAfPFwHDYvnozZMcE2z1SpXOSICjaEPUcvC313+LzZz7KuUY8LNQ04d6kWucVV+P5IkXSsgiV1jTqp4NsUWNyULogb3A8AsI3LQgwsROQcVtwWgf1/m4brh7W/zbcrLbguFIHeapyvqMNHe84AAD749TSe2ZQlvf6PWSOvedkqppXAIooiCi5elgpt/3rzcPh52n5qtSAILfqxlNv8/pKqOsxftx+XLjciKtgb780bh2dmjgAAvPpTLvJKzJeGquubmmdXbhp2VZgTBAH3XzcIn/8pDstmhOOXJ6di9R/HYlxo32vadi0tC512XGBp0umx6ucTAAxHQmQ8E4/d/28qfnziBnz950mYZ1xq/OZQ64Elq7ACjToRvh4qBPdxlZ43Bfht2QwsXBIiIqcgCAL8Pa+9u+21UivkSLp5OJZ+cRhvb89DTYMOb6Yafhn9acpgPDU9vFP6mkSH+EAuE1BYXou/bz4KbUUdzl64jPyLl6VtwOEaz1a39VpjTEgf7Mgtxd5TFzB/UqjV76uub8IDHx7AuUu1CO3nhvfvHw83pQvmjA/Bliwtdh0vxdIvfsMXLZaGPtpzxjC74uuO26Isn3MEGIKaKax1BkNgOYn0DnQO7izf/nYep8pq4OOmwIPXD4aHygX9Wrzu66HCx2ln8avxOIEAr6v/njfXr/iY/f2aGuYP4CjSz15E+eUG+Lgpu/ReauqboJDL7H7GmDWc74qIiBzszrHBCNd4oqquSQorj900tNPCCmBoaDfCuPX4g1/P4IcsLY4VVUphZZix5uFaGqJNDTfMVv2QpbVqCzUANOr0eOSTDGQVVqKfuxIfPTABvsat1IIg4KU7R8FT5YLM/HL8xzijYja7Mu3q2ZWuNHZgHwgCcLqsBiVVrfecySupxsQXU3H32jTsySvrtCLWJp1e+jvy0A2GsHKlkL5uGDewD0QR+LaVWZYrC25bvjcswBN6EdLBml3l3KXLmPhiKu79z74OFw53JQYWIqIryGUCnmxRN5J083D89ZawTu8Y+9T0EZg+UoP5cQPx7K0ReH/+OPycdANynp+OrUlTrrkfzehgH+nU6Ke/ykJjO1uoRVHEU18ewe4TZXBVyLHu/vEY2M+8kDXIxxXP3GpYGlq59TjySqqsnl3pCt6uCoQZi1Ez2jhQ8t2dJ6GtrMPeUxfxx//swx/eTcOvnRBcvs4sxJkLl9HXXSmdW2VJ4pj+0vgriaKIg/mWAwsATDVub+7qOpavDxaiqr4J+89cxBcZBV36XR3BwEJEZMGNw/2w8q4ovHPPWDw+bViXfMfkYb5Yc18M/j4rEgsnD8K0EQEY6u9pc/FpW5bNGIG+7krkFldJsyCteXtbHr48eA5ymaFxW5Rxp9GV/jAuBFOG+6GhSY+kz3+TPvexaUPtOrtiYqpj2d9K4W355QZ8+5thZmPmqEAoXWQ4cOYS7vnPPty1Jg2/nOhYcGnU6fHmNsPsysNTBsPdwuyKycxRgXCRCThWVInjxeZb2fMvXkZZdQOUcpnFYylMdSw7ckvb7dvTUaIoSv+OAODVH3NRZcNZV/bAwEJEZIEgCJgdE4wZbRxk2B30cVfib78zzIi8mXoC+RcsH/D4/eEirNx6HIDh/B7T/6u3RBAEvDTbsDR0+FxF8+zKaPvOrpiYGsiltzLD8kXGOdQ36TEi0Atv/3EMdi2divsnhULpIkP62Uu49/19ePLLwzZ/75cZ51BwsRa+Hsp2a436uCul/jKbrphlMS0HRfb3shhWx4T4wMdNgYraRhzsos7FOdoqnCiphlIuw8B+biirbjA7Sd0ZdCiwrF69GqGhoVCr1YiNjcX+/fvbHL9x40aEh4dDrVZj1KhR2LJlS6tjH374YQiCgDfeeKMjl0ZERFe4c2x/xA3uh7pGPZ75Juuq2YTD58rx142HAAAPXDcIf4xt/7C9QG9XPHtrhPTnx6YNddgBhOONnYOPnq+46twivV7EJ3vPAjBsRxcEARpvNZ67fSR2/z9DcJHLBHyefg5pJ61vgd/QpMdb2wy/0B+eMsSqTsd3GJeFvjl0HvoWNSKt1a+YuMhl0iGZVy4LNer02Pzbefzfxt+QXdSx7esAsNk4u3JjmB9W3Gb4ua775bRV3Y3txea/XRs2bEBSUhJWrFiBgwcPIioqCgkJCSgpsby2tmfPHsydOxcLFy5EZmYmEhMTkZiYiKysrKvGfv3119i7dy+CghyT0omIeiJBEPDCHZFQymXYdbwU3x0ukl4rqqjFgx+lo65Rj6lhfvibceuyNe4aF4xF1w/CnHEhDptdAQzhKbiPK/Ti1UcR/JJXhjMXLsNT5SKdF2US4GUILnMnGA7GfHFLtlmQaMvGjAIUltfCz1Nl9U6uaSP84aFyQWF5rdmuJtOsSVu7p26S6liKARi2nb/x83Fc99I2PPZZJr7IOIfFnx5EQ5PtS0aiKGKzsUfM7dFBmBrmjxuG+6FRJ+KFLdk2f15XsTmwvP7661i0aBEWLFiAiIgIrFmzBm5ubli3bp3F8atWrcL06dOxdOlSjBgxAs8//zzGjh2Lt99+22xcYWEhHnvsMfzvf/+DQmHdAWJERGSdwX4eeHSqoSne3zcfQ0VtIy43NOHBj9JRUlWP4QEeeHPuGJtqUARBwN9mRuDl34922OyKSWv9WP5rnF2ZbTzo0pIn4ofDQ+WCI4UVZnUcralv0uFt4+zKn28cYnXNkVohx4xIDYDm4tuqukbkGhv7jR3QemCZMtwPcpmA48XV+NN/03HdS9vwxs8nUFJVDz9PFbxdFThZWiP1DrJFZkE5Ci7Wwk0px7TwAAiCgOW3joBcJmDrsWL80s7ZWvZi09+whoYGZGRkID4+vvkDZDLEx8cjLS3N4nvS0tLMxgNAQkKC2Xi9Xo/77rsPS5cuxciRI9u9jvr6elRWVpo9iIiobQ/fOBiD/dxRVl2Pl37IQdKG33D0fCX6uivx/vzx8LTytGln1PJcIZPC8lqkZhtmJO6d2Poyl6+HCo/cOASAodi0ZYdjSz4/UICiijoEeKkwd0L7y2ctmZaFvj98HvVNOvxWUAG9CAT3cYW/hf4sJj5uSmkG5sejxWjUiYgZ2Advzh2DX5+8SapTeuPn4yipbH17tyWm5aCbIwKkowOG+nviPuPM0T++O9plxb62sCmwlJWVQafTISAgwOz5gIAAaLVai+/RarXtjn/55Zfh4uKCxx9/3KrrSE5Ohre3t/QICQmx5TaIiHollYscL94xCoCh9X/KUS2UchnW3hdj8QTr7sRUx5JZcElaFvlsXz70IhA3uB+G+rd9Ds/CyYMQ6K1GYXktPvj1TKvjCstr8aZxdmXx1KE27+iKHdwPAV4qVNY1YUduabv1Ky396YbB6O/jirtigvHdY5Px5SOTcHtUEJQuMvw+JhjRIT6oadDhRRuWcXR6UVoivP2KLelPxA+Dj5sCx4ur8dn+fBvusms4fJdQRkYGVq1ahQ8//NDqHgfLli1DRUWF9CgocL794kREzmji4H74fYtDHV+aPQrjQm07WNEZDfX3QB83Beoa9Th63nDg4/oDhl+yplO426JWyLE0IQwA8O/tebhQXX/VmIKLlzHn3TSUVtVjsK87/jDe9v+zLJcJmBVtmGXZlFl41YGHbZk2IgC/PnUTXr0r6qoePTKZgH/MGglBADYdOo99p6wrIN536gJKq+rh7aq46lgMHzcl/nrzcADA61uPo/xyg1Wf2VVsCiy+vr6Qy+UoLi42e764uBgajcbiezQaTZvjd+/ejZKSEgwYMAAuLi5wcXHB2bNn8de//hWhoaEWP1OlUsHLy8vsQURE1vnb70bglogAPHtrBO4cG9z+G7oBQRCkE60PnLmIlKNalFU3wN9ThZsjAtp5t0FidH+MDPJCVX0TVhm715oUXLyMu9fulY4r+N+iWKhcOtYvJ9EYWFKzS3DQOMPSVv2KtUYH++Du8YYlqhXfWreMYyq2nRGpsdiOf+6EAQgL8MSly4144+cTV71uTzYFFqVSiZiYGKSmpkrP6fV6pKamIi4uzuJ74uLizMYDwNatW6Xx9913Hw4fPoxDhw5Jj6CgICxduhQ//vijrfdDRETt6OOuxNp547Bw8iBHX0qnmjDI8Ev/wJlL+CTNUGw7d8IAKKwsCJbJBKkW5H/78nGy1HDA49kLNZjzbhoKy2sx2Ncd6x+KQ6C3a1sf1aYRgZ4IC/BEg06P6vomuCnlCNe0vWRlraUJYfB2VSBHW4X/7Wt7GaehSY8tRwzlGVcuB5m4yGXS9vX/7j3r0G3ONi8JJSUl4b333sNHH32E7OxsPPLII6ipqcGCBQsAAPPmzcOyZcuk8UuWLEFKSgpWrlyJnJwcPPfcc0hPT8fixYsBAP369UNkZKTZQ6FQQKPRICwsrJNuk4iIejrT0tau46XYf+Yi5DLBqp4yLU0a6otp4f7Q6UW89EMOTpfV4O61e3G+og6D/dyx/qGJ0Hhf2yGdgiBg1pjmgBAd4tNpu6z6uivxf8alrZU/5aLMwtKWyS95paiobYSfpwqxg/u1Om7yMF/cO3EA/jUnGgP7Oa7WyeZ/Q3PmzMFrr72G5cuXIzo6GocOHUJKSopUWJufn4+iouY9/pMmTcKnn36KtWvXIioqCl988QU2bdqEyMjIzrsLIiLq9SKDvKFWyFBvLLpNGBlg8WTk9iz7Xbi0pffOf/+Kooo6DPX3wPqHJra5k8cWpjoWwLr6FVv8ccIAjAzyQmVdE15NyW11nOkgxpmjAtvdzv7PxFG4PSqo08/TsoUgdtaRlQ5UWVkJb29vVFRUsJ6FiKgXu3ttGvaeMvRi+XRRLCYN8e3Q5zyz6Qg+2WtYUhke4IH/PTgRfp6qTrtOAFjwwX5szy3Fl4/ESfU3nSXj7EXMfsfQPuSzRRMRN8R8BqW2QYeYf27F5QYdvvrzpE6poekIW35/O3yXEBERUWeZYFwWGuLnjrg2ljna80T8cAz2dUfMwD74dFHnhxUAeHPuGPz4xA2dHlYAIGZgX8w2FlTPfW8vHvo4HYcKyqXXt+WU4HKDDsF9XDGmlUMunU37hx8QERF1E/fGDUReaTXunzTompYvfD1U+DlpCmRdePq0p1qBME3XNetbfmsEahub8EOWFj8dK8ZPx4oxaUg//PnGofj2N0On3dscvMxjCy4JERER9WB5JVVYs/MUNmUWoumKs5J+WHI9RgQ67vcml4SIiIgIgKHN/mt3RWGn8XRqtcLwqz8swLPTtlPbA2dYiIiIepGy6nqkZGkRN6Qfhvh5OPRabPn9zRoWIiKiXsTXQ4V7J7Z/XIGz4ZIQEREROT0GFiIiInJ6DCxERETk9BhYiIiIyOkxsBAREZHTY2AhIiIip8fAQkRERE6PgYWIiIicHgMLEREROT0GFiIiInJ6DCxERETk9BhYiIiIyOkxsBAREZHT6xGnNYuiCMBwTDURERF1D6bf26bf423pEYGlqqoKABASEuLgKyEiIiJbVVVVwdvbu80xgmhNrHFyer0e58+fh6enJwRB6NTPrqysREhICAoKCuDl5dWpn+2seM+8556K98x77qm66z2LooiqqioEBQVBJmu7SqVHzLDIZDIEBwd36Xd4eXl1q78EnYH33DvwnnsH3nPv0B3vub2ZFRMW3RIREZHTY2AhIiIip8fA0g6VSoUVK1ZApVI5+lLshvfcO/Ceewfec+/QG+65RxTdEhERUc/GGRYiIiJyegwsRERE5PQYWIiIiMjpMbAQERGR02Ngacfq1asRGhoKtVqN2NhY7N+/39GX1Gl27dqF2267DUFBQRAEAZs2bTJ7XRRFLF++HIGBgXB1dUV8fDxOnDjhmIvtBMnJyRg/fjw8PT3h7++PxMRE5Obmmo2pq6vDo48+in79+sHDwwOzZ89GcXGxg6742r3zzjsYPXq01EwqLi4OP/zwg/R6T7tfS1566SUIgoAnnnhCeq6n3fdzzz0HQRDMHuHh4dLrPe1+TQoLC3HvvfeiX79+cHV1xahRo5Ceni693tP+GxYaGnrVz1kQBDz66KMAeu7P2YSBpQ0bNmxAUlISVqxYgYMHDyIqKgoJCQkoKSlx9KV1ipqaGkRFRWH16tUWX3/llVfw5ptvYs2aNdi3bx/c3d2RkJCAuro6O19p59i5cyceffRR7N27F1u3bkVjYyNuueUW1NTUSGP+8pe/YPPmzdi4cSN27tyJ8+fP484773TgVV+b4OBgvPTSS8jIyEB6ejpuuukmzJo1C0ePHgXQ8+73SgcOHMC7776L0aNHmz3fE+975MiRKCoqkh6//PKL9FpPvN9Lly7huuuug0KhwA8//IBjx45h5cqV6NOnjzSmp/037MCBA2Y/461btwIA7rrrLgA98+dsRqRWTZgwQXz00UelP+t0OjEoKEhMTk524FV1DQDi119/Lf1Zr9eLGo1GfPXVV6XnysvLRZVKJX722WcOuMLOV1JSIgIQd+7cKYqi4f4UCoW4ceNGaUx2drYIQExLS3PUZXa6Pn36iP/5z396/P1WVVWJw4YNE7du3SpOmTJFXLJkiSiKPfPnvGLFCjEqKsriaz3xfkVRFJ988klx8uTJrb7eG/4btmTJEnHIkCGiXq/vsT/nljjD0oqGhgZkZGQgPj5eek4mkyE+Ph5paWkOvDL7OH36NLRardn9e3t7IzY2tsfcf0VFBQCgb9++AICMjAw0Njaa3XN4eDgGDBjQI+5Zp9Nh/fr1qKmpQVxcXI+/30cffRQzZ840uz+g5/6cT5w4gaCgIAwePBj33HMP8vPzAfTc+/32228xbtw43HXXXfD398eYMWPw3nvvSa/39P+GNTQ04JNPPsEDDzwAQRB67M+5JQaWVpSVlUGn0yEgIMDs+YCAAGi1Wgddlf2Y7rGn3r9er8cTTzyB6667DpGRkQAM96xUKuHj42M2trvf85EjR+Dh4QGVSoWHH34YX3/9NSIiInrs/QLA+vXrcfDgQSQnJ1/1Wk+879jYWHz44YdISUnBO++8g9OnT+P6669HVVVVj7xfADh16hTeeecdDBs2DD/++CMeeeQRPP744/joo48A9Pz/hm3atAnl5eW4//77AfTMv9dX6hGnNRPZ6tFHH0VWVpbZOn9PFRYWhkOHDqGiogJffPEF5s+fj507dzr6srpMQUEBlixZgq1bt0KtVjv6cuxixowZ0j+PHj0asbGxGDhwID7//HO4uro68Mq6jl6vx7hx4/Diiy8CAMaMGYOsrCysWbMG8+fPd/DVdb33338fM2bMQFBQkKMvxW44w9IKX19fyOXyqyqsi4uLodFoHHRV9mO6x554/4sXL8Z3332H7du3Izg4WHpeo9GgoaEB5eXlZuO7+z0rlUoMHToUMTExSE5ORlRUFFatWtVj7zcjIwMlJSUYO3YsXFxc4OLigp07d+LNN9+Ei4sLAgICeuR9t+Tj44Phw4cjLy+vx/6cAwMDERERYfbciBEjpKWwnvzfsLNnz+Lnn3/Ggw8+KD3XU3/OLTGwtEKpVCImJgapqanSc3q9HqmpqYiLi3PgldnHoEGDoNFozO6/srIS+/bt67b3L4oiFi9ejK+//hrbtm3DoEGDzF6PiYmBQqEwu+fc3Fzk5+d323u2RK/Xo76+vsfe77Rp03DkyBEcOnRIeowbNw733HOP9M898b5bqq6uxsmTJxEYGNhjf87XXXfdVW0Jjh8/joEDBwLomf8NM/nggw/g7++PmTNnSs/11J+zGUdX/Tqz9evXiyqVSvzwww/FY8eOiQ899JDo4+MjarVaR19ap6iqqhIzMzPFzMxMEYD4+uuvi5mZmeLZs2dFURTFl156SfTx8RG/+eYb8fDhw+KsWbPEQYMGibW1tQ6+8o555JFHRG9vb3HHjh1iUVGR9Lh8+bI05uGHHxYHDBggbtu2TUxPTxfj4uLEuLg4B171tXnqqafEnTt3iqdPnxYPHz4sPvXUU6IgCOJPP/0kimLPu9/WtNwlJIo9777/+te/ijt27BBPnz4t/vrrr2J8fLzo6+srlpSUiKLY8+5XFEVx//79oouLi/jCCy+IJ06cEP/3v/+Jbm5u4ieffCKN6Wn/DRNFw27VAQMGiE8++eRVr/XEn3NLDCzteOutt8QBAwaISqVSnDBhgrh3715HX1Kn2b59uwjgqsf8+fNFUTRsC3z22WfFgIAAUaVSidOmTRNzc3Mde9HXwNK9AhA/+OADaUxtba345z//WezTp4/o5uYm3nHHHWJRUZHjLvoaPfDAA+LAgQNFpVIp+vn5idOmTZPCiij2vPttzZWBpafd95w5c8TAwEBRqVSK/fv3F+fMmSPm5eVJr/e0+zXZvHmzGBkZKapUKjE8PFxcu3at2es97b9hoiiKP/74owjA4n301J+ziSCKouiQqR0iIiIiK7GGhYiIiJweAwsRERE5PQYWIiIicnoMLEREROT0GFiIiIjI6TGwEBERkdNjYCEiIiKnx8BCRERETo+BhYiIiJweAwsRERE5PQYWIiIicnoMLEREROT0/j/2+Qseb83qpQAAAABJRU5ErkJggg==\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "h6h-fell70_S"
      },
      "source": [
        "last_train_batch = scaled_train[-12:]"
      ],
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cwwv8O-p79bN"
      },
      "source": [
        "last_train_batch = last_train_batch.reshape((1, n_input, n_features))"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "v-4WD4t78MpJ",
        "outputId": "4230e182-987d-4552-d38f-3e4008b1b5c4"
      },
      "source": [
        "model.predict(last_train_batch)"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 208ms/step\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.4963334]], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZbojFADE8StA",
        "outputId": "8f9ed59e-0baf-49f8-cfcf-3058263832a7"
      },
      "source": [
        "scaled_test[0]"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0.55599019])"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_MP-5Wez8jbY",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "66466528-55a0-4154-a2a1-eefee5eaf096"
      },
      "source": [
        "test_predictions = []\n",
        "\n",
        "first_eval_batch = scaled_train[-n_input:]\n",
        "current_batch = first_eval_batch.reshape((1, n_input, n_features))\n",
        "\n",
        "for i in range(len(test)):\n",
        "\n",
        "    # get the prediction value for the first batch\n",
        "    current_pred = model.predict(current_batch)[0]\n",
        "\n",
        "    # append the prediction into the array\n",
        "    test_predictions.append(current_pred)\n",
        "\n",
        "    # use the prediction to update the batch and remove the first value\n",
        "    current_batch = np.append(current_batch[:,1:,:],[[current_pred]],axis=1)"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 50ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 54ms/step\n",
            "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_mhvFuEy8sB7",
        "outputId": "a8dea1c4-d5d3-4e57-d1c7-4074042b2f88"
      },
      "source": [
        "test_predictions"
      ],
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[array([0.4963334], dtype=float32),\n",
              " array([0.39764243], dtype=float32),\n",
              " array([0.30865282], dtype=float32),\n",
              " array([0.41367564], dtype=float32),\n",
              " array([0.93297577], dtype=float32),\n",
              " array([1.0614182], dtype=float32)]"
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "YYSqV10E9hlO",
        "outputId": "19cd2350-7f08-4538-cb64-47ebb24b0675"
      },
      "source": [
        "test.head()"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "    Nomer  Tahun   Bulan  Produksi\n",
              "54     55   2023  Jul-23    448708\n",
              "55     56   2023  Aug-23    412512\n",
              "56     57   2023  Sep-23    299914\n",
              "57     58   2023  Oct-23    368213\n",
              "58     59   2023  Nov-23    523068"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-4c144d1f-faa6-40a2-a627-96477cf644cb\" 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>Nomer</th>\n",
              "      <th>Tahun</th>\n",
              "      <th>Bulan</th>\n",
              "      <th>Produksi</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>54</th>\n",
              "      <td>55</td>\n",
              "      <td>2023</td>\n",
              "      <td>Jul-23</td>\n",
              "      <td>448708</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>55</th>\n",
              "      <td>56</td>\n",
              "      <td>2023</td>\n",
              "      <td>Aug-23</td>\n",
              "      <td>412512</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>56</th>\n",
              "      <td>57</td>\n",
              "      <td>2023</td>\n",
              "      <td>Sep-23</td>\n",
              "      <td>299914</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>57</th>\n",
              "      <td>58</td>\n",
              "      <td>2023</td>\n",
              "      <td>Oct-23</td>\n",
              "      <td>368213</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>58</th>\n",
              "      <td>59</td>\n",
              "      <td>2023</td>\n",
              "      <td>Nov-23</td>\n",
              "      <td>523068</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-4c144d1f-faa6-40a2-a627-96477cf644cb')\"\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-4c144d1f-faa6-40a2-a627-96477cf644cb 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-4c144d1f-faa6-40a2-a627-96477cf644cb');\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-92ec49fd-eb8b-4041-9893-9298dc41f11b\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-92ec49fd-eb8b-4041-9893-9298dc41f11b')\"\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-92ec49fd-eb8b-4041-9893-9298dc41f11b 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": "test",
              "summary": "{\n  \"name\": \"test\",\n  \"rows\": 6,\n  \"fields\": [\n    {\n      \"column\": \"Nomer\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 55,\n        \"max\": 60,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          55,\n          56,\n          60\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Tahun\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 2023,\n        \"max\": 2023,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          2023\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Bulan\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 6,\n        \"samples\": [\n          \"Jul-23\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Produksi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 135373,\n        \"min\": 299914,\n        \"max\": 686476,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          448708\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BHHzjNDK9EJZ"
      },
      "source": [
        "true_predictions = scaler.inverse_transform(test_predictions)\n",
        "test['Predictions'] = true_predictions"
      ],
      "execution_count": 24,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Calculate the absolute difference between 'Produksi' and 'Predictions'\n",
        "test['Error'] = abs((test['Produksi'] - test['Predictions'])/test['Produksi'])*100\n",
        "\n",
        "# Display the updated DataFrame with the new 'Error' column\n",
        "test\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 237
        },
        "id": "qX-ypp5gqywe",
        "outputId": "cdf51a7b-276c-404c-9d20-101654afbcca"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "    Nomer  Tahun   Bulan  Produksi    Predictions      Error\n",
              "54     55   2023  Jul-23    448708  410275.896811   8.565059\n",
              "55     56   2023  Aug-23    412512  346697.208602  15.954637\n",
              "56     57   2023  Sep-23    299914  289368.318543   3.516235\n",
              "57     58   2023  Oct-23    368213  357026.118258   3.038155\n",
              "58     59   2023  Nov-23    523068  691569.649933  32.214100\n",
              "59     60   2023  Dec-23    686476  774314.817148  12.795614"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-6c37cd53-8020-4e64-a885-728057b0d0bd\" 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>Nomer</th>\n",
              "      <th>Tahun</th>\n",
              "      <th>Bulan</th>\n",
              "      <th>Produksi</th>\n",
              "      <th>Predictions</th>\n",
              "      <th>Error</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>54</th>\n",
              "      <td>55</td>\n",
              "      <td>2023</td>\n",
              "      <td>Jul-23</td>\n",
              "      <td>448708</td>\n",
              "      <td>410275.896811</td>\n",
              "      <td>8.565059</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>55</th>\n",
              "      <td>56</td>\n",
              "      <td>2023</td>\n",
              "      <td>Aug-23</td>\n",
              "      <td>412512</td>\n",
              "      <td>346697.208602</td>\n",
              "      <td>15.954637</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>56</th>\n",
              "      <td>57</td>\n",
              "      <td>2023</td>\n",
              "      <td>Sep-23</td>\n",
              "      <td>299914</td>\n",
              "      <td>289368.318543</td>\n",
              "      <td>3.516235</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>57</th>\n",
              "      <td>58</td>\n",
              "      <td>2023</td>\n",
              "      <td>Oct-23</td>\n",
              "      <td>368213</td>\n",
              "      <td>357026.118258</td>\n",
              "      <td>3.038155</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>58</th>\n",
              "      <td>59</td>\n",
              "      <td>2023</td>\n",
              "      <td>Nov-23</td>\n",
              "      <td>523068</td>\n",
              "      <td>691569.649933</td>\n",
              "      <td>32.214100</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>59</th>\n",
              "      <td>60</td>\n",
              "      <td>2023</td>\n",
              "      <td>Dec-23</td>\n",
              "      <td>686476</td>\n",
              "      <td>774314.817148</td>\n",
              "      <td>12.795614</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-6c37cd53-8020-4e64-a885-728057b0d0bd')\"\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-6c37cd53-8020-4e64-a885-728057b0d0bd 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-6c37cd53-8020-4e64-a885-728057b0d0bd');\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-28f8a1ef-bf86-4560-9d6e-2a74e45d30f9\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-28f8a1ef-bf86-4560-9d6e-2a74e45d30f9')\"\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-28f8a1ef-bf86-4560-9d6e-2a74e45d30f9 button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "  <div id=\"id_85c1151b-ff84-4e78-a6f6-b6e223847fd7\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('test')\"\n",
              "            title=\"Generate code using this dataframe.\"\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",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_85c1151b-ff84-4e78-a6f6-b6e223847fd7 button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('test');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "test",
              "summary": "{\n  \"name\": \"test\",\n  \"rows\": 6,\n  \"fields\": [\n    {\n      \"column\": \"Nomer\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 55,\n        \"max\": 60,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          55,\n          56,\n          60\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Tahun\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 2023,\n        \"max\": 2023,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          2023\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Bulan\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 6,\n        \"samples\": [\n          \"Jul-23\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Produksi\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 135373,\n        \"min\": 299914,\n        \"max\": 686476,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          448708\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Predictions\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 202710.51944779765,\n        \"min\": 289368.3185427189,\n        \"max\": 774314.8171477318,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          410275.8968113661\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Error\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 10.827651517282698,\n        \"min\": 3.0381550194809446,\n        \"max\": 32.21410025711023,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          8.565058610195031\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# ... (Your existing plotting code) ...\n",
        "\n",
        "# Calculate MAPE (assuming you already have y_true and y_pred)\n",
        "def mean_absolute_percentage_error(y_true, y_pred):\n",
        "    y_true, y_pred = np.array(y_true), np.array(y_pred)\n",
        "    return np.mean(np.abs((y_true - y_pred) / y_true)) * 100\n",
        "\n",
        "y_true = test['Produksi'].values\n",
        "y_pred = test['Predictions'].values\n",
        "\n",
        "mape_final = mean_absolute_percentage_error(y_true, y_pred) #Calculate and assign mape_final\n",
        "\n",
        "# ... (Rest of your plotting code) ...\n",
        "\n",
        "mape_text = f\"MAPE: {mape_final:.2f}%\" #Now mape_final is defined\n",
        "\n",
        "plt.annotate(mape_text,\n",
        "             xy=(0.05, 0.95),\n",
        "             xycoords='axes fraction',\n",
        "             fontsize=12,\n",
        "             bbox=dict(boxstyle='round', facecolor='white', alpha=0.8))\n",
        "\n",
        "\n",
        "plt.figure(figsize=(14, 7))\n",
        "\n",
        "# Plot data aktual\n",
        "plt.plot(test.index, test['Produksi'],\n",
        "         label='Data Aktual',\n",
        "         color='blue',\n",
        "         marker='o',\n",
        "         markersize=5,\n",
        "         linewidth=2,\n",
        "         alpha=0.7)\n",
        "\n",
        "# Plot prediksi\n",
        "plt.plot(test.index, test['Predictions'],\n",
        "         label='Prediksi Model',\n",
        "         color='red',\n",
        "         linestyle='--',\n",
        "         marker='x',\n",
        "         markersize=6,\n",
        "         linewidth=2)\n",
        "\n",
        "# Tambahkan detail grafik\n",
        "plt.title('Perbandingan Data Aktual vs Prediksi Model', fontsize=16, pad=20)\n",
        "plt.xlabel('Tanggal', fontsize=12)\n",
        "plt.ylabel('Produksi', fontsize=12)\n",
        "plt.grid(True, which='both', linestyle='--', linewidth=0.5)\n",
        "plt.legend(fontsize=12)\n",
        "\n",
        "# Rotasi label tanggal jika terlalu padat\n",
        "plt.xticks(rotation=45)\n",
        "\n",
        "# Tambahkan anotasi MAPE\n",
        "mape_text = f\"MAPE: {mape_final:.2f}%\"\n",
        "plt.annotate(mape_text,\n",
        "             xy=(0.05, 0.95),\n",
        "             xycoords='axes fraction',\n",
        "             fontsize=12,\n",
        "             bbox=dict(boxstyle='round', facecolor='white', alpha=0.8))\n",
        "\n",
        "# Highlight area error\n",
        "plt.fill_between(test.index,\n",
        "                 test['Produksi'],\n",
        "                 test['Predictions'],\n",
        "                 color='orange',\n",
        "                 alpha=0.1,\n",
        "                 label='Error')\n",
        "\n",
        "plt.tight_layout()  # Adjust layout\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "fjvREAUvjxQw",
        "outputId": "c10aeeb4-bc29-4919-b109-5079c8b3b08c"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x700 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABW0AAAKxCAYAAAAozI5pAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzs3Xd4FIUWxuHf7qYnpFBDgNA7KB0RRZQmTUVRkN4UG3YRryCCFRUV7BVQURRRroiKSrPARTrSpNfQQiAhvezcP9ZsCAlJgGRnknzv8/jc3Z3Z3bPjfjPek9kzNsMwDERERERERERERETEEuxmFyAiIiIiIiIiIiIiWdS0FREREREREREREbEQNW1FRERERERERERELERNWxERERERERERERELUdNWRERERERERERExELUtBURERERERERERGxEDVtRURERERERERERCxETVsRERERERERERERC1HTVkRERERERERERMRC1LQVEREpRmrUqIHNZsv2j6+vL5GRkfTr14/ff//dY7U8/fTT2Gw2nn76aY+9Z1E43+eYOXMmNpuNYcOGmVKXVZ37/bPb7YSEhFC9enW6devG+PHj2bp1q9llFpkbbrjB/dk3b96c57rDhg3DZrMxc+ZMzxRXBPbt24fNZqNGjRpml3JBrLSvzM+F7oOWLVuGzWajY8eORVbTxXx3M+vK/Gf9+vV5rt+4cWP3uqNGjbrEigumsI9bHTt2xGazsWzZskJ5PRERkbOpaSsiIlIMtW/fnqFDhzJ06FC6d++O0+nkq6++4pprruHVV181uzwpBbp168bQoUMZMmQIXbt2pUaNGqxYsYLnnnuOxo0bc8stt3D8+PFCez9PNKryc+TIEX744Qf3/Y8++qjQ36MkNHqtRPtK83z88cfnXfa///2vRP9xR0REpDB4mV2AiIiIXLhRo0ZlO/sqOTmZ0aNH88knnzB27Fh69epFvXr1zCuwBOjTpw9XXHEFISEhZpdiSePGjcvRQE1PT+err77i4Ycf5ptvvmHr1q2sWLGCsLAwc4osZLNmzSIjI4MqVapw+PBhPvvsM6ZMmYKPj4/Zpcl5FOd9pZn7oBdeeIFx48ZRuXLlC35uZGQkycnJfP7557zyyiv4+vrmWCezodu6dWtWr159yfWKiIiURDrTVkREpATw8/PjrbfeIjAwkIyMDL755huzSyr2QkJCaNCgwUU1LUorLy8vBgwYwF9//UX58uXZvn07jz76qNllFZrMRtPUqVOpVasW0dHR/Pe//zW5KrkQxWlfaeY+qHLlyjRo0OCiGsbe3t4MGjSImJgY5s+fn2N5YmIic+bMoUqVKnTr1q0QqhURESmZ1LQVEREpIYKCgqhfvz7gmkN5th07djB69Ghq166Nn58fISEhdOjQgc8++yzX1zp7Tt/vv/9O7969qVChAna7Pdefbe/fv58hQ4ZQuXJl/Pz8qFevHk8//TRJSUk51k1LS+Ozzz5j4MCBNGjQgODgYPz9/alfvz73338/UVFR+da0YcMGbr75ZsqXL4+vry+NGjVi6tSpGIaR63OTkpJ4+umnqVu3Lr6+vlSuXJmhQ4dy4MCB827PgsyTTEtLY8qUKTRu3Bh/f3/KlSvHzTffzLZt2877un/88QfXX389oaGhBAUF0bp1az755BMga17suf766y/Gjh1LmzZtCA8Px8fHh0qVKtG7d29+/fXXfOtPSEjgiSeeoE6dOvj6+hIeHs7QoUM5fPjweeu8FJGRkUyaNAmATz75hGPHjl3S5+nYsSPXXnstAMuXL882N/PsWasnTpxg+vTp9OjRg5o1a+Lv709wcDCtWrViypQpJCcnX/RnWr58OTt37qRcuXL06dOH4cOHAxc/IuGnn34iODgYPz8/5syZ454dO2vWLACGDx+e7XNmzuAsyIzZzHmu5+4Htm7dysSJE2nfvj1VqlTBx8eHcuXK0blzZ7766quL+hznOn36NP7+/jgcjjy/X3379sVmszFt2jT3Y7GxsYwfP56mTZsSGBiIr68vERERtG/fnqeeeoq0tLRCqfF8+8qz8zdjxgzatWtHSEhIjm0ZFRXFww8/TMOGDQkICKBMmTK0bt2aN998k/T09FzfszD3QXk5ceIEV155JTabjX79+pGSkuJeNnfuXDp37ky5cuXw9vamXLlyNGrUiDvuuINNmzZle51LHdMxYsQIIPcRCXPnzuXMmTMMGTIEh8OR5+v89ddf3HbbbURERODj40PFihXp3bs3v/zyy3mfczHbOtPatWsZOHAgkZGR+Pr6UrZsWbp165ZtLIqIiIinqGkrIiJSgsTFxQFk+znq3Llzufzyy3n//ffx8fGhR48etGrVinXr1jF48GD3/7nOzdy5c+nYsSN79uyhc+fOdOnSJcdPXffu3UvLli35+eefufrqq+nSpQtRUVFMmjSJLl265GiUHTt2jMGDB7Nw4ULCwsK4/vrrue6664iPj+eNN96gWbNm7Nq167w1LVq0iLZt27J9+3a6dOlCu3bt2LFjB48++igPPfRQjvUTExO57rrrmDRpEkeOHKFr165cffXVLFq0iBYtWrB3794CbdtzpaWl0aNHDyZPnkxkZCQ9e/YkMDCQb7/9liuvvDJHwwxgzpw5XHPNNSxatIjIyEhuuOEGAgICGD58OOPGjTvve/3nP/9h6tSpJCcn07JlS2666SaqVq3K999/T5cuXbI1vs4VGxvLlVdeybvvvkujRo3o3r07hmHwySef0L59e2JjYy/q8+dnwIAB2Gw20tPTWbp06SV9nuuvv959Rl6lSpXcM0qHDh1K37593estWrSIBx54gE2bNlG9enVuuukm2rRpwz///MO4ceO47rrrsjWxLkRmc3bgwIH4+PgwbNgw7HY7v/zyCwcPHryg13rvvffo1asX3t7e/Prrr/Tv35+goCCGDh1K7dq1geyzWIcOHUqzZs0uqu6zvfrqq0yePJmYmBiaNm3KzTffTP369Vm6dCn9+vXj4YcfvuT3CA0NpU+fPjidTj799NNc1zl58iQLFizAx8eHQYMGAa6cXnXVVTz33HMcO3aMTp06uevbs2cPzzzzDAkJCZdcX6bc9pWZxowZw6hRo/Dy8qJnz560bdvW3cz97bffaNKkCa+99hrJycl06dKF9u3bs3v3bsaMGUPPnj1zNJeLah90rh07dtCuXTtWrlzJ2LFjmTNnjvvzTZ48mdtuu43ly5fTpEkTbr31Vq644gocDgcfffQRS5YsKZQaMjVu3Jg2bdrw66+/5shHZpYy//BxPh988AHt2rVj7ty5hIeH07dvX+rWrcv3339P165d3X8YOtulbOtp06bRpk0bPv/8c8qVK8cNN9xA48aNWbZsGT179mTy5MkXsSVEREQugSEiIiLFRvXq1Q3AmDFjRo5lGzduNOx2uwEYH3/8sWEYhrFp0ybD19fX8PPzM+bNm5dt/X379hlNmzY1AGPWrFnZll1zzTUGYADGW2+9lWstEydOdK9z4403GomJie5lBw8eNOrVq2cAxrhx47I9Ly4uzvjvf/9rpKSkZHs8NTXVeOKJJwzA6NGjR473O7umd999N9uyxYsXGzabzXA4HMbBgwezLXv00UcNwGjQoIFx+PBh9+MJCQnGjTfe6H7NiRMnZnvejBkzDMAYOnRotseXLl3qfk7z5s2NI0eOuJclJSUZ3bp1MwDjzjvvzPa8w4cPG0FBQQZgTJs2Lduy5cuXG4GBge7XPdcPP/xgREVF5Xh8xYoVRnBwsOHt7W0cOnQo1/oBo1u3bkZsbKx7WUxMjNGsWTMDMJ5//vkcr5uXzNdcunRpvuvWqVPHAIzx48df8ufJ3O7XXHPNed9v69atxsqVK3M8HhMTY3Tt2tUAjJdeeinfus91+vRpw9/f3wCMDRs2uB/P/Hc9efLkXJ83dOjQbHl1Op3G2LFjDcCoXbu28c8//+T7nHPt3bvXAIzq1auft97M/cTevXuzPb5s2TJj9+7dOdbfvn27UbVqVQMwVq1adcHvd65ffvnFnbncTJs2zQCMW265xf3YrFmzDMDo3r27kZqamm39jIwMY9myZTn2GXm50H2lYWR9t4ODg3P9Hh05csQoV66cYbPZjLffftvIyMhwL4uOjjauu+46AzAmTZqU7XlFtQ86Owu//fabUbZsWcPhcOTYPyYnJxv+/v5GUFCQsX379hyfa9++fca2bduyPZbf9zA3mXXVrl3bMAzDeO+993LkY8eOHQZgdOjQwTCMrOPIyJEjs73Wpk2bDC8vL8NmsxmffPJJtmU//PCD4ePjYwDGzz//nG3ZxW7rn376ybDZbEb58uWN5cuX56glMx/Lli3LtizzuFSQ/aGIiMiF0pm2IiIixVxsbCw//PADN998M06nk4iICG677TYAnnvuOVJSUnj22We5+eabsz2vevXq7jOepk+fnutrX3fdddxzzz15vr+/vz/vvvsu/v7+7seqVq3K1KlTAXj77beznW1bpkwZbrjhhhwXb/L29ub5558nIiKCn376iTNnzuT6fjfffDOjR4/OUWe3bt3IyMjIdlZnUlIS7733HgCvvfYaERER7mUBAQG8++67+Pn55fn5zsdmszFjxgzCw8Pdj/n5+bnP/jr3Z/4fffQR8fHxtGvXjvvvvz/bsg4dOnD33Xef9726d++e61zLdu3ace+995KWlnbe2aqBgYHMmDGD4OBg92NhYWHuM3vPN16hMJQvXx5wnVl5tkv5PHlp2LAhV1xxRY7Hw8LCeOONNwDX2eMX6osvviApKYmWLVty+eWXux8fOXIk4PopvXGe0RyZkpOT6d+/Py+99BJXXHEFK1eu9PgFsK655hpq1aqV4/H69eszYcIEAL7++utLfp9OnTpRvXp1tm/fzsqVK3MsnzFjBpD9TMvMERpdunTB29s72/p2u51rrrnmki/4lte+8myPPvport+j119/nZMnT3Lvvfdy9913Y7dn/V+pcuXK8cknn+Dt7c2bb77p/j4U5T4o0xdffEGXLl1ITU1lwYIFOfaPcXFxJCUlUatWLfdYiLNVr16dBg0aXFINuenfvz8BAQHMnDnTvT0yxyXk9QsPcJ31mp6eTp8+fRg8eHC2Zd27d+fOO+8E4OWXX3Y/finbeuLEiRiGwbvvvkuHDh2yLWvatCmvvvoqgHs/IiIi4gleZhcgIiIiF2748OG5/rS0du3azJs3j8DAQJxOJz/++CMA/fr1y/V1WrVqRVBQEOvXryc5OTnH/6E9+6fn59O1a9dsjctMvXr1oly5cpw8eZJ169Zx5ZVXZlu+ceNGFi9ezN69e0lISMDpdAKQnp6O0+lk165dNG/ePMfr9u7dO9c6GjZsyE8//ZRtjua6des4c+YM5cuX5/rrr8/xnPDwcLp27cp3332X7+c8V2RkZLYG3tl1ADnmeS5fvhxw/bw+NwMHDuSVV1457/udPHmShQsXsnnzZk6dOuX+CfbOnTsB+Oeff3J9XqtWrXJtkJ6vzsKU+e80tzm9F/t58pORkcGyZctYsWIFR44cISkpCcMw3E2ji3ndDz/8EMjZaLrxxhspV64ce/fuZcmSJXTq1CnX50dHR9OpUydWrFjBzTffzGeffZbtjxyeFB8fz48//sj69euJjo4mNTUVgCNHjgAXv93PZrPZGDp0KJMnT2bmzJm0a9fOvWzDhg1s2LCBypUrZ8tk69atAXjppZcoV64cvXr1omzZspdcS0H2lec6335v4cKFwPn3p1WqVKFu3bps3bqVnTt3Uq9evSLdBwE8//zzjB8/nsqVK7Nw4cJcx2hUqFCBGjVqsGnTJh555BFGjhxJo0aNLur9LkRwcDC33HILn376KcuWLaNDhw588sknlClThltvvTXP5y5btgzgvPN8R44cyZtvvsnvv/9ORkYGDofjord1dHQ0f/31F/7+/uc9vnTs2BGAFStW5P2hRURECpGatiIiIsVQ+/btqVOnDoD74ixXXHEF119/PV5ersP7yZMn3XMbq1Wrlu9rnjx5kipVqmR7LK+LHWWqWbPmeZfVqFGDkydPcujQIfdjCQkJDB48mG+//TbP182s/VyRkZG5Pp55JunZZ/Vmvm9enyOv+vOSXx3nzk7Nr5a8avzggw946KGH8pzpWRjbq7BFR0cD5Gi+XcrnycvOnTvp06cPW7ZsKbTX3bhxI2vXrsXPz48BAwZkW+bj48PAgQOZPn06H3/88Xmbtk888QTp6el07dqVuXPnZjtD05MWLFjA8OHDc5z5fLaL2e65GT58OM888wxffvklr7/+urtJnXmW7bkXoerYsSOPP/44L7/8MkOHDsVms1G3bl3at2/PjTfeSO/evS9quxVkX3mu82Vxz549AFx99dX5vu+JEyeoV69eke6D/vzzT5YvX46fnx+//fabex5ybj755BP69u3Lq6++yquvvkrZsmVp27YtXbp0YfDgwe6z4gvbiBEj+PTTT/n4449JTEwkKiqKUaNGERAQkOfzMv+YdL5tk/lZk5OTOXnyJBUrVrzobb13714MwyApKSnXGcdnO3HiRJ7LRURECpOatiIiIsXQqFGj8r2ieOZZjgBDhw7N9zVz+z+rhXU24Nk/HX/iiSf49ttvadCgAS+++CKtW7emfPny7p8+X3nllaxcufK8Pzc3q+F1routI7ezTvN6fO3atYwePRqHw8GUKVPo3bs3kZGRBAQEYLPZeP/99xk9erTlttepU6fcF/1p2rSp+/FL/Tx56du3L1u2bKFXr16MHTuWRo0aERwcjLe3N6mpqfk2ZHKTOULEy8uLXr165Vie2QD95ptvOH36NKGhoTnWufXWW5k/fz6//vorM2fOzPen4Zfq7OxnOnz4MP369SMpKYmxY8cycOBAatSoQVBQEHa7nZ9//plu3bpd1HbPTY0aNbj22mtZsmQJ3377LQMGDCAtLY3PP/8cyP0iVC+++CJ33XUXCxYs4I8//uDPP/9kxowZzJgxg9atW7N06dJcz4zNS0H2lec6334vc7v27ds33zrKlSt3Qe95MRo3boy3tzdr1qxhzJgxzJs377y1X3311ezbt4+FCxeyfPlyVqxYwaJFi/jxxx+ZOHEi33777Xn/6HAprrnmGvdZzUePHgXyH43gaZn/XoOCgrjllltMrkZERCSLmrYiIiIlVPny5fH39ycpKYlXXnmlyM6kyutq3Pv27QNcM24zffXVVwB8+eWXXHbZZTmek/nz+MKQeeZwZh151VjUqlSpwj///HPe9zvf43PnzsUwDMaMGcPYsWNzLC/M7VWYPv/8cwzDwNvbm2uvvdb9eFF9nu3bt7Np0yYqVqzIt99+m+Msyot53ZSUFGbPng24xgr8+eef5103OTmZ2bNnc++99+ZY1rVrV+666y569erFqFGjiI+PzzHXuKAy/7hxvpnPaWlp7lEHZ1uwYAFJSUn06dOHKVOm5FheFN+j4cOHs2TJEmbMmMGAAQNYsGAB0dHRXHnllbnOVgVXs3fMmDGMGTMGgNWrVzNo0CBWr17NSy+95J4ZbYZq1aqxc+dOHn/8cVq1alWg5xTlPig0NJTvvvuOXr168eOPP9K9e3e+//57goKCcl3f39+fvn37usc/nDhxgvHjx/P+++8zYsQI9u/ff1F15MVmszFs2DAmTJjAr7/+SsOGDbONyzifKlWqsHv3bvbs2UOTJk1yLM8869nPz899Jv/FbuvMX6LYbDY+/vhjy/xhUEREREckERGREsrhcNClSxcgq1FaFH7++WeOHz+e4/EffviBkydPUqZMGVq2bOl+PCYmBnBd/OZcixYtcv+kvjC0bNmSoKAgoqOj+fnnn3MsP3bsWK6PF4XMi9t88cUXuS7PPAPxXHltr+TkZObNm1dIFRaeAwcO8PTTTwOumZQVKlRwL7vYz5PZrExPT891eebrRkRE5Pqz988++6zgH+Bf33zzDTExMURERJCenu6ejXvuP2+//TaQdVZubjp06MDixYsJCwvjgQce4Pnnn891vfw+Z4UKFfDx8SEmJibX3C1atCjX5+a13Q3DOO/371LccssthISEsGTJEg4ePJjrBcjy07p1a/fFEDds2FDoNV6I7t27Axe2Py3qfVBwcDA//fQTXbt2Zfny5XTu3JlTp04V6LkVKlTgpZdeAlyZLejzLlTmPqBcuXI5LpJ2PpkzZGfOnJnr8swLml199dXuvF/sto6IiOCyyy7jzJkz/PTTTwWqT0RExBPUtBURESnBJk6ciI+PD4899hizZs3K9WfTmzdv5ptvvrno90hKSuLuu+8mKSnJ/VhUVBSPPPIIAHfddVe2C5xlXgDr3Ktw//PPP9x1110XXUdu/P393VcZf+ihh7KdgZhb3UVp5MiRBAQE8Mcff/DWW29lW/bnn3+6G3/nytxes2bNynZ2ZXJyMvfcc0+eZzp7Wnp6Ol988QVt27YlOjqaRo0auZtCmS7282Serb1z5073RcvOVq9ePRwOB3///bf7IkaZFixYwGuvvXbBnyezCTto0KBs81fP1b9/f3x8fFi/fn2ejcXWrVuzbNkywsPDefLJJxk3blyOdTI/5/nm8np7e7v/ADB+/Phsmd64cSP33Xdfrs/L3O5ff/11thxkZGTw1FNPFckFlvz9/enfvz9Op5MpU6bw008/ERAQkOuFvL799lt+++23HPuotLQ0dyMtt4azJz322GOEhoby6quvMnXqVPdF3M62d+/ebH8g8MQ+KCAggAULFnDzzTezatUqOnbsyLFjx9zL9+/fz4cffpjrvOIFCxYAEBYW5p5zXdiqVq3K8ePHiY6O5oEHHijQcx544AG8vLyYP39+jj+4/Pzzz7z33nsAPProo+7HL2VbP/vss4DrDwqZ2+RshmGwatUqj/2RT0REBNS0FRERKdFatGjh/j+8w4YNo3r16nTr1o1BgwbRo0cPqlWrRtOmTS/pTNwhQ4awbNkyatWqxW233cYNN9xAvXr12L59O+3atcvxc+aJEydis9mYMGECl112GbfffjudOnWiadOm1KpViyuvvPKSPvO5Jk+eTJs2bdi6dSv16tXjhhtu4LbbbqNWrVr89ttvDBkypFDf73yqVq3Ke++9h91u57777uPyyy9nwIABdOzYkQ4dOrgb1t7e3tmeN3z4cKpXr8769eupWbMmffr0oW/fvlSvXp2vv/66wE2Qwvbiiy8ybNgwhg0bRr9+/ejYsSNly5ZlwIABHD16lL59+7Js2bIcM14v9vNERkbSqlUrjh8/TtOmTRk0aBCjRo1yNz7Lly/PfffdR0ZGBp06daJjx44MGDCAli1bcsMNN/DYY49d0Ofbu3cvS5YsAfKfCR0WFuaed5vX2bbgmu/7+++/ExkZyZQpU7j33nuzzZG96aabsNvtTJ8+nS5dujBixAhGjRqV7Yr3zz77LD4+PnzwwQc0bNiQW2+9lSuvvJLWrVvTsWPHXJubvXv3pmXLlhw6dIh69erRq1cv+vXrR+3atZkyZQqPP/54gbfNhcg8q/att94iPT2dvn37UqZMmRzrLV++nGuuuYZKlSrRtWtXBg0axI033kjVqlX56aefqFKlSq7jNDypatWq/Pe//yUsLIxHH32UatWq0alTJwYNGkTv3r2pU6cOtWrV4s0338z2PE/sg3x8fPjqq68YPHgwmzZtokOHDhw8eBBwzZe+4447KF++PG3atKFfv37069ePFi1aMHjwYGw2Gy+//HKef5jwtKZNm/LWW29hs9kYPHgwLVu2ZODAgVx11VVcf/31pKSk8PTTT9O1a9dsz7vYbd27d2+mTZtGTEwMN9xwA3Xr1qVXr14MHDiQrl27Eh4ezhVXXOHeJ4iIiHiCmrYiIiIl3K233sqWLVt46KGHCA0N5c8//2TevHls3bqVOnXq8OKLL/Lcc89d9OvXrFmTNWvWcO211/Lbb7+xaNEiKleuzFNPPcWvv/6a48I4N998M8uXL6dTp04cOXKE7777juPHj/P000/z448/5mhaXqrAwECWLl3KhAkTqFSpEosWLeK3336jU6dOrFmz5qKv3H4xBg0axJIlS+jSpQv79u3jv//9L2fOnOGDDz5wzzg9d/ZwaGgoa9as4Z577iE0NJQff/yRlStX0rVrV9atW0ezZs08Vv/ZFi1axKxZs/jkk0/48ccf2bNnD+3atWP8+PFs3bqVuXPnZhuLkOlSPs+8efMYMGAAcXFxfPnll3z00UfMmTPHvfy1117jo48+onnz5qxdu5YffviBgIAA5syZwzPPPHNBn2/GjBkYhkGrVq1o1KhRvutnNoNmz55NcnJynuvWqVOHP/74g3r16vH2228zbNgwMjIyALjsssuYN28e7dq1Y9WqVcycOZOPPvqIdevWuZ/ftm1bli9fTteuXTl69CgLFy4kMTGRadOmuUcQnMvLy4tly5bxn//8hypVqrB48WKWLVtG8+bNWblyJddff31BN80Fadu2LY0bN3bfP99ohGHDhjFu3DgaNGjg/v6sXLmSatWq8fzzz7Nx48Zss7HN0qFDB7Zs2cKECROoWrUqq1evZu7cuWzYsIFKlSoxceJEPvjgg2zP8dQ+yOFwMGvWLO6++2527NjB1Vdfza5du6hduzavv/46vXr14vTp0/zwww8sXLiQhIQEhgwZwurVqxk5cmSh1FCY7rzzTlasWEHfvn2Jioriq6++Yvv27fTo0YOff/6ZiRMn5njOpWzr+++/n/Xr13PnnXdis9lYvHgx8+fPZ/fu3TRv3pzp06df9CxqERGRi2EzCusSsSIiIiJy0T755BOGDh1K7969s51VKSIiIiIipY/OtBURERHxkAMHDnD06NEcj//555/u2YwXcpEmEREREREpmXJeWldEREREisSSJUsYOXIkl19+OZGRkTgcDnbv3s3GjRsBV8O2T58+JlcpIiIiIiJm03gEEREREQ/Zvn07r7zyCr///jvHjh0jISGB0NBQmjVrxogRI7j99tvNLlFERERERCxATVsRERERERERERERC9FMWxERERERERERERELUdNWRERERERERERExELUtBURERERERERERGxEDVtRURERERERERERCxETVsRERERERERERERC1HTVkRERERERERERMRC1LQVERERERERERERsRA1bUVEREREREREREQsRE1bEREREREREREREQtR01ZERERERERERETEQtS0FREREREREREREbEQNW1FRERERERERERELERNWxERERERERERERELUdNWRERERERERERExELUtBURERERERERERGxEDVtRURERERERERERCxETVsRERERERERERERC1HTVkRERERERERERMRC1LQVERERERERERERsRA1bUVEREREREREREQsRE1bEREREREREREREQvxMruA0szpdBIVFUWZMmWw2WxmlyMiIiIiIiIiIiJFyDAMzpw5Q0REBHb7+c+nVdPWRFFRUVSrVs3sMkRERERERERERMSDDh48SNWqVc+7XE1bE5UpUwZw/UsKDg42uZqitXHjRi6//HKzyxCRPCinItamjIpYn3IqYm3KqIj1lYacxsXFUa1aNXdf8HzUtDVR5kiE4ODgEt+09fHxKfGfUaS4U05FrE0ZFbE+5VTE2pRREesrTTnNb1SqLkQmHhEaGmp2CSKSD+VUxNqUURHrU05FrE0ZFbE+5TSLmrbiEXnN6BARa1BORaxNGRWxPuVUxNqUURHrU06zqGkrHrF582azSxCRfCinItamjIpYn3IqYm3KqIj1KadZ1LQVERERERERERERsRA1bcUjatWqZXYJIpIP5VTE2pRREetTTkWsTRkVsT7lNIuX2QVI6ZCcnOy+bRgG27dvZ//+/aSkpJhYlRQ1m81GmTJlaNasGWFhYWaXI/k4O6ciYj3KqIj1Kaci1qaMilifcppFTVvxiKioKKpVq8Z3333Hhx9+SFRUlNkliQfZ7XZatWrF+PHjiYiIMLscOY/MnIqINSmjItannIpYmzIqYn3KaRY1bcVjvv76a1588UW6dOnC+PHjadq0KX5+fthsNrNLkyLidDo5efIkv//+OzNnzmT06NG8//77VK5c2ezSREREREREREQsy2YYhmF2EaVVXFwcISEhxMbGEhwcbHY5RerMmTNcf/319OzZkyeeeEKN2lLo+PHjDB48mI4dO/LEE0+YXY7kIj09HS8v/S1PxKqUURHrU05FrE0ZFbG+0pDTgvYDdSEy8YjZs2eTkpLCsGHD1LAtpSpWrEiPHj1YunQpGRkZZpcjudiyZYvZJYhIHpRREetTTkWsTRkVsT7lNIuatuIRO3bsICIiQvNMS7k2bdoQExPDsWPHzC5FcqGB7yLWpoyKWJ9yKmJtyqiI9SmnWdS0FY8pU6aM2SWIyTK/A4mJiSZXIrkp6WNaRIo7ZVTE+pRTEWtTRkWsTznNoqateERYWJjGIoi+AxZXo0YNs0sQkTwooyLWp5yKWJsyKmJ9ymkWNW3FI44ePXreZTNnzsRms2Gz2fjjjz9yLDcMg2rVqmGz2ejVq1eur3H69Gn8/Pyw2Wxs27Yt13Uy5+lm/hMcHMzll1/O1KlTSUlJca/39NNPZ1vv3H/y+ix5eeedd7j11luJjIzEZrMxbNiwXNdbvHgxI0aMoF69egQEBFCrVi1GjRrFkSNHLuj9vvzyS9q1a0dgYCChoaFceeWVLFmyJNs6sbGxjB07lrp16+Lv70/16tUZOXIkBw4cyLben3/+SYsWLShTpgwdO3Zk+/btOd7v/vvvp1u3bhdUo1jLpk2bzC5BRPKgjIpYn3IqYm3KqIj1KadZSvbl2KRY8fPz4/PPP+eqq67K9vjy5cs5dOgQvr6+533u3LlzsdlshIeHM3v2bJ599tlc1/P19eXDDz8EXI3eefPm8eijj7J69WrmzJmTbd133nmHoKCgHK8RGhp6gZ/MZcqUKZw5c4Y2bdrk2YB9/PHHiYmJ4dZbb6Vu3brs2bOHN998k++//54NGzYQHh6e73s9/fTTTJ48mb59+zJs2DDS0tLYvHkzhw8fdq/jdDrp0qULW7du5Z577qFevXrs2rWLt99+m0WLFrFt2zbKlClDbGwsN954I1dccQV33nknM2fO5JZbbmHTpk04HA7ANSj8gw8+YO3atRe1bUREREREREREJIuatuIRoaGhxMbG5rlOjx49mDt3LtOnT8fLK+ur+fnnn9OyZUuio6PP+9zPPvuMHj16UL16dT7//PPzNm29vLwYNGiQ+/4999xD27Zt+fLLL3n11VezXSitb9++lC9fvqAfMV/Lly93n2WbWzM406uvvspVV12F3Z51Ivz111/PNddcw5tvvnnez5bpf//7H5MnT2bq1Kk89NBDea63evVq3nzzTe6991734/Xr12fEiBH8+uuv9OnTh5UrV5KUlMTXX3+Nn58f119/PTVr1mTXrl3Ur18fgAcffJA77riDRo0aFXRziAVVr17d7BJEJA/KqIj1Kaci1qaMilifcppF4xHEI5xOZ77r3H777Zw8eZJffvnF/Vhqaipff/01AwYMOO/zDhw4wO+//07//v3p378/e/fuZcWKFQWqy26307FjRwD27dtXoOec+965jQrITfXq1Qs007VDhw7ZGraZj5UtW/a8ox/O9vrrrxMeHs4DDzyAYRjEx8fnul5cXBwAlSpVyvZ45cqVAfD39wcgKSkJPz8//Pz8AChbtiyQdTGx+fPns379eiZNmpRvbWJtGRkZZpcgInlQRkWsTzkVsTZlVMT6lNMsatqKR2Q2CPNSo0YN2rVrxxdffOF+7McffyQ2Npb+/fuf93lffPEFgYGB9OrVizZt2lC7dm1mz55d4Np2794NQLly5bI9HhMTQ3R0dLZ/Tp8+nW2dIUOG0LBhwwK/18WKj48nPj6+QGf+Ll68mNatWzN9+nQqVKhAmTJlqFy5Mm+++Wa29Vq1akVgYCATJkxgyZIlHD58mOXLlzN27Fhat25N586dAWjevDmxsbFMnTqV/fv3M3HiREJCQqhfvz4pKSk88sgjTJo0ibCwsCL57OI5hw4dMrsEEcmDMipifcqpiLUpoyLWp5xmUdNWLGXAgAHMnz+fpKQkAGbPns0111yTbWzBuWbPns2NN97oPjO0X79+fPXVV6Snp+e6fmYDdvfu3bzwwgvMnz+fyy67zP1T/0z169enQoUK2f654oorCumTXpjXX3+d1NRU+vXrl+d6p06dIjo6mj///JMJEyYwbtw4vvzyS5o1a8aYMWN477333OuWL1+eL7/8ktjYWDp16kTVqlXp2LEjERERLFmyxD2iokaNGrz44os8/vjj1KhRg/fee4933nmHgIAApk6dSkBAAHfddVeRfn4RERERERERkdJEM23FIyIiIvKdaQtw22238eCDD/L9999z/fXX8/333zN9+vTzrr9p0yb+/vtvXnjhBfdjt99+O88//zyLFi2iZ8+e2dZPSEigQoUK2R678sor+fTTT3O89rx58wgODs72WGBgYLb7y5Yty/czXarffvuNSZMmcdttt3HdddfluW7mKISTJ08yZ84cd5O3b9++NG3alGeffZbRo0e7169QoQLNmzfnvvvuo3HjxmzYsIGXXnqJ4cOHM3fuXPd6jz76KIMHD2bv3r3Ur1+fsLAwoqKi3E3v9PR0HnzwQf773/8SHh7Oa6+9Rvv27Ytga0hRat68udkliEgelFER61NORaxNGRWxoKefBocDJkwAzsnpM89ARoZrnVJITVvxiBMnThRovQoVKtC5c2c+//xzEhMTycjIoG/fvudd/7PPPiMwMJBatWqxa9cuAPz8/KhRowazZ8/O0bT18/NjwYIFAPj6+lKzZk2qVq2a62t36NChUC9EdjG2b99Onz59aNKkCR9++GG+62eebezt7Z1tu9ntdvr168fEiRM5cOAAkZGR7Nmzh2uvvZZPPvmEW265BYAbb7yRGjVqMGzYMH788Ue6d+/ufo1KlSplm3/7+OOP06lTJzp16sT48eNZvHgxX375JUuXLqVnz57s27eP0NDQQtoS4gk7duygSZMmZpchIuehjIpYn3IqYm3KqIgFORzw1FOu2xMmZOX0mWdcj0+ebG59JlLTVjwiLS2twOsOGDCAO+64g6NHj9K9e/fzNv4Mw+CLL74gISGBRo0a5Vh+/Phx4uPjCQoKcj/mcDjcs1qt7uDBg3Tt2pWQkBB++OEHypQpk+9zypYti5+fH6GhoTgcjmzLKlasCLhGKERGRjJz5kySk5Pp1atXtvVuuOEGAP78889sTduz/e9//+Prr79m8+bNgGuu8IQJE2jXrh3t2rXjvffe4/vvv2fQoEEX/LnFPAkJCWaXICJ5UEZFrE85FbE2ZVTEgiZMgLQ0V4P25EkSbr89e8P23zNwSyM1bcUjfHx8Crxunz59GD16NP/73//48ssvz7ve8uXLOXToEJMnT85xMbBTp05x5513Mn/+/GLZODx58iRdu3YlJSWFxYsXU7ly5QI9z26306xZM1avXk1qamq27R4VFQXgHg9x7NgxDMPIcWXGzAb7+WYCG4bB/fffzwMPPEDt2rXdr3323OGIiAgOHz5cwE8rVnH2HzhExHqUURHrU05FrE0ZFbEQw4DVq2HGDMi8IP20abR++21XE7eUN2xBTVvxkHLlyhV4REJQUBDvvPMO+/bto3fv3uddL3M0wmOPPYafn1+O5S+//DKzZ88u0qbtgQMHSExMpEGDBoX2mgkJCfTo0YPDhw+zdOlS6tate0Hv369fP/73v/8xa9Ys7rjjDgCSk5OZPXs2jRo1cjdX69Wrh2EYfPXVVwwbNsz9/C/+3Vmeb97TzJkzOXjwIE8++aT7sUqVKrF9+3a6du1KWloau3btIjw8/KK3gZijTp06ZpcgInlQRkWsTzkVsTZlVMQCjh2Dzz5zNWu3bMmx2J6WBj4+pb5hC2raioccOXLkgtYfOnRonstTUlKYN28eXbp0ybVhC66f+U+bNo3jx4+7RwNciK+//jrXv8R26dLFPdt1yJAhLF++HMMw8n29BQsWsHHjRsB1NuumTZt49tln3bVedtllAAwcOJC//vqLESNGsG3bNrZt2+Z+jaCgIG666Sb3/dzef/To0Xz44Yfce++97Nixg8jISD799FP279/vnucLMGzYMF555RVGjx7N+vXrady4MevWrePDDz+kcePG9OnTJ8dnOHPmDP/5z394/vnns41r6Nu3L5MnT8bpdPLnn3+SnJxMjx498t0mYi0bNmygbdu2ZpchIuehjIpYn3IqYm3KqIgFTJ0KL7+c/bEAf6hVHTZvx+ntjT011TUioZQ3btW0lWJp4cKFnD59Os8zcXv37s3UqVOZM2cO999//wW/x913353r40uXLs12Qa6CmjdvHrNmzXLfX79+PevXrwegatWq7qbthg0bAPj444/5+OOPs71G9erVszVtc+Pv78+SJUsYO3YsH3/8MQkJCTRr1oyFCxfSrVs393rlypVjzZo1PPXUUyxYsIB3332XcuXKMWLECJ5//vlcR1o888wzVK1aNduZuQCTJk3ixIkTTJo0ifDwcL7++mv3GAYRERERERERKYX+/hvCwyGzP5CRAgNvzmratm0Og2+F/Ufh5enwnzGs7nELbZf8lu3iZKWVzSjIKYJSJOLi4ggJCSE2Npbg4GCzyylS//nPfzhw4ACfffaZ2aWIibZs2cLQoUOZM2eOfppkQefOJhYRa1FGRaxPORWxNmVUxANiYlwzamfMgLVr4fnn4NExkBYH6QngTIUPv4LOnaBeXXjxNXjmFZjwKDwykqiYDCJqNi7RFyMraD9QZ9qKR9hsNrNLEJF82O12s0sQkTwooyLWp5yKWJsyKlJEMjLgl19cjdr58yE1NWvZxx/C6N5g9wIvf/AKgnvuOuu5TlfDdtxDkBaH3f5v/yizUXvOxdNLEzVtxSNOnz5tdgkiko/9+/frAnIiFqaMilifcipibcqoSCHbsQNmzoRPPoHDh3Mub9YIBt0K9jKui4vl5slHst3df+gE4dX/vVPCzrC9UGraikfYbDbS09PNLkNMlvkdcDgcJlciIiIiIiIiIhdt/nzI5QLmlC8Lt90AQwZA08YeL6skUdNWPKJhw4bMmzePjIwMNexKsSNHjgAQGhpqbiGSq8yL4YmINSmjItannIpYmzIqcpGcToiPh8z5q4YBHdqBvz8kJYHDAV07wOB+0L3b+c+qLYDLGtYonJpLAA10EY+oVq0acXFxrFu3zuxSxERLliyhYcOGhIWFmV2K5GLv3r1mlyAieVBGRaxPORWxNmVU5ALt3++6EFidOvDAA+BMg9RYSDwEjlMwZig8Mw52/AVffwY39r6khi3A3oPHCqn44k9n2opHVKxYkcjISF588UXee+89ypcvb3ZJ4mE//PADS5cu5aGHHjK7FDmPM2fOmF2CiORBGRWxPuVUxNqUUZECSEqCb7+Fjz+GJUtcZ9UCHD8Gzz0AAV5g8wZHAEws/JmzZ+KTCv01iys1bcUjAgICmDZtGqNHj+bmm2/mqquuomnTpvj7+2Oz2cwuT4pIRkYGJ0+e5Pfff2fr1q3ccMMN9O/f3+yy5Dz8/f3NLkFE8qCMilifcipibcqoyHkYBqxa5bqo2Jw5EBubfbnNBm0uh+jTUKdekZbi739pZ+qWJDbDyGyZi6fFxcUREhJCbGwswZlzQUqotLQ0vL29OX78ON9//z2//vor+/fvJyUlxezSpAjZbDbKlClDy5Yt6dKlC507d8Zu11QWq8rMqYhYkzIqYn3KqYi1KaMiuThyBDp1gm3bci6rWQ0G3gID+0NktaKvJS2ONFsQ3sFVi/69TFTQfqCatiYqTU3bVatW0bZtW7PLEJE8KKci1qaMilifcipibcqoSC6cGVC/Puza7bof6A83Xg+D+8PV7V1n2XpKWhyrNh+jbftrPPeeJihoP1DjEUREREREREREREqyjRthxgzYtw/mz4eMFMhIdF1Y7PZe8OsfMPg2uPkmKBNkcrECatqKh1SpUsXsEkQkH8qpiLUpoyLWp5yKWJsyKqXOyZPw+eeuZu369VmPb/gNalUCZxrYfWHswzBurHl1nqVKeDmzS7AMNW3FI3x8NEhaxOqUUxFrU0ZFrE85FbE2ZVRKhfR0+PlnV6P2u+8gNTX7cl8fWPMX1OkLXmXMqTEPPj5qVWbSFYHEI/bu3Wt2CSKSD+VUxNqUURHrU05FrE0ZlRLNMGD8eKheHXr2hK+/zt6wbdEEXp0Eu9bBgAFgt+YfMfYeOGZ2CZah9rWIiIiIiIiIiEhxZrPB2rUQFZX1WIWy0O8mGHw7NGlkWmlycXSmrXhE06ZNzS5BRPKhnIpYmzIqYn3KqYi1KaNSIjidsHQp3HMPpKW5zrBNT4LkaLi9B3h5QY/rYM77sHMdTHmmWDVsmzaobnYJlqGmrXjEwYMHzS5BRPKhnIpYmzIqYn3KqYi1KaNSrO3bB5MmQe3acN118M47sGAeJByEhP2QfAx6dIYda2Dup9C7J3h7m131BTsYFW12CZah8QjiEadPnza7BBHJh3IqYm3KqIj1Kaci1qaMSrGTmAjffOO6qNiSJTmXf/EpdGoOjgCwe4EPEODxKgvV6bgEs0uwDDVtxSN8fX3NLkFE8qGcilibMipifcqpiLUpo1JsrFkD778PX34JcXHZl9lscN2VMKgf3NATvP3MqbGI+PoWv7ODi4rNMAzD7CJKq7i4OEJCQoiNjSU4ONjscoqU0+nEbtc0DhErU05FrE0ZFbE+5VTE2pRRKTYeeghefz37Y7UiYWBfGNQfqlYxpawilxaH01EGe1AJ/Xz/Kmg/UHsr8YjVq1ebXYKI5EM5FbE2ZVTE+pRTEWtTRsVyUlLg66/h+HHXfcMJ6Qlw+w2u+0EBMOhmWDQXNq2AcY+U3Ibtv1Zv3GV2CZah8QgiIiIiIiIiIiKesn69a07t7NkQEwMvvQgP3AmpsZCRCPUrwey3oVMnKBNkdrViEjVtxSPCw8PNLkFE8qGcilibMipifcqpiLUpo2Kq6GhXk3bGDNi4MfuyGR/BqB7g8AOvYLDZ4aYbzanTZOEVw8wuwTLUtBWPCAwMNLsEEcmHcipibcqoiPUppyLWpoyKx6Wnw6JFrkbtd99BWlr25X6+0KszDO4HPmVdFxkr5QIDdMHATGraikfs3r2b8uXLm12GiORBORWxNmVUxPqUUxFrU0bF42bNglGjcj7esikMuhVuvQXCQj1elpXt3neU8lXqm12GJahpKyIiIiIiIiIiciliYyExESpXdt13ZsANXcHPD5KToWI56HcjDL4dGjcyt1YpFtS0FY9o1Eg7JBGrU05FrE0ZFbE+5VTE2pRRKXROJyxd6hp/8M03MHAgvDMd0hMgLRa8k+GpB6F2bejWBby9za7Y8hrVq2Z2CZZhN7sAKR2OHj1qdgkikg/lVMTalFER61NORaxNGZVCs3cvTJwItWpB586uC4wlJcGXc+DENkg+BgbgHQoPjIFePdSwLaCjx0+ZXYJl6Exb8YiYmBizSxCRfCinItamjIpYn3IqYm3KqFySxESYNw8+/hiWLcu5PDQYbu0NKXYICfN4eSVFzOl4s0uwDDVtxSO89RclEctTTkWsTRkVsT7lVMTalFG5aDt2QKtWcOZM9sftdriuPQzuB717gK+vOfWVIN7eDrNLsAybYRiG2UWUVnFxcYSEhBAbG0twcLDZ5YiIiIiIiIiISHo6eJ11nmN6CtStB/sOuO7Xrg4D+8KgflClijk1lkRpceAdAgGVza6kSBW0H6iZtuIRq1atMrsEEcmHcipibcqoiPUppyLWpoxKnlJSYO5c6NEDunUDw+m6oFjSMUg6CCNvg8F94eevYeOf8PjDatgWgVUbdphdgmVoPIKIiIiIiIiIiJQ+hgHr18OMGfD553D23OO/f4PICmCzgd0PHnrQdVuKluYBuKlpKx5RsWJFs0sQkXwopyLWpoyKWJ9yKmJtyqi4nTgBs2e7mrWbNuVcXrUy7D8AteuATT9S96SK5UPNLsEy1LQVjwgJCTG7BBHJh3IqYm3KqIj1Kaci1qaMChkZ0K8ffPcdpKVlX+bnCzd0hcH9oWMH10XGxONCggPMLsEy9A0Uj9i5c6fZJYhIPpRTEWtTRkWsTzkVsTZlVHA4IPZ09oZt68th2rOwez3MeBeu66iGrYl27okyuwTL0Jm2IiIiIiIiIiJScpw+DXPmwMKFMH8+2ICMREg7A7f3gL83Qr8bYcgAaNjA5GJFcmczDEMjfk0SFxdHSEgIsbGxBAcHm11OkYqNjdVPUUQsTjkVsTZlVMT6lFMRa1NGSzinE5YsgY8/hm+/heRk1+Pzv4DrWkNGMmAHwwscvuCl8xgtJy2O2GQvQirVMbuSIlXQfqDO9xaPiI6ONrsEEcmHcipibcqoiPUppyLWpoyWULt3w1NPQc2a0KULfPFFVsMW4NefwAC8Q8EnBHwD1bC1sOiYM2aXYBlq2opH6OAoYn3KqYi1KaMi1qecilibMlrCfP01dOwIderAM8/AgQNZy8JC4M7B8MdCmPI8ePmDzWZaqVJw0TFxZpdgGfrTgniEXUO8RSxPORWxNmVUxPqUUxFrU0ZLmKVLYfnyrPt2O3S6CgbfBr16gK+vebXJRbM7lNNMmmlrotI001ZERERERERE5IIdOgSffAJ33gnly4MzDdIT4a8/4OpeULcGDOwLA/tBRITZ1cqlSIsD7xAIqGx2JUVKM23FUlavXm12CSKSD+VUxNqUURHrU05FrE0ZLUaSk+HLL+H666F6dXjySfjkY0g6Bgn7IfEgNKkNv30P6/+Axx5Sw7aEWL1pl9klWIbGI4hHOJ1Os0sQkXwopyLWpoyKWJ9yKmJtyqjFGQasXQszZrguJnbqVPbls2bCyF5g9wPvMNeM2pbNTSlVio4zQznNpKateET58uXNLkFE8qGcilibMipifcqpiLUpoxZ14gR89hl8/DFs3pxzeWQVGHgzDLodvEM9Xp54VvmyGh+aSU1b8QgdHEWsTzkVsTZlVMT6lFMRa1NGLWrOHHj44eyP+fvBDV1hSH/ocLXrImNSKpQvW8bsEixD33rxiO3bt5tdgojkQzkVsTZlVMT6lFMRa1NGLWDzZti7N+t+Rgr07QE+Pq77bZrBG8/B7vXw8TvQ8Ro1bEuZ7bsOm12CZehMWxERERERERERKRqnTrnOpp0xA1avhrvvhmlTIO0MpMeDfyq89Ty0bAn165ldrYhl2AzDMMwuorSKi4sjJCSE2NhYgoNL9syOmJgYypYta3YZIpIH5VTE2pRREetTTkWsTRn1oIwMWLzY1aj99ltISclaFhoMW5eAfwB4+YPdx7w6xVrS4ohJdFC2cl2zKylSBe0H6hxz8YjY2FizSxCRfCinItamjIpYn3IqYm3KqAfs2gXjx0ONGtCtm+sM27Mbtpc1hP88CF4h4BOihq3kEBuXaHYJlqGmrXjE8ePHzS5BRPKhnIpYmzIqYn3KqYi1KaNFbNUqqFsXnnsODh3KerxcGNw1BFb8CCt/hXtHQ2CAeXWKpR2PPm12CZahmbYiIiIiIiIiIlJwhgExMVCuXNb9Zo2hSgQcjgKHAzpfBYP7Qc/uWRcaE8mPzewCrEMzbU1UmmbaioiIiIiIiEgxd/AgzJoFM2e6RiD8/COkJ0JaHKQnwIezITEVBvaD8HCzq5XiJi0OvEMgoLLZlRQpzbQVS1m3bp3ZJYhIPpRTEWtTRkWsTzkVsTZl9CIlJcEXX0DXrlC9OkyYALt3w5IlsPVPSDzoatw6AuDuu+GRB9SwlYu2bvNus0uwDI1HEI9IS0szuwQRyYdyKmJtyqiI9SmnItamjF4Aw4DVq2HGDFfD9tyLuNlscM0VcCYRvMNc90UKQVpahtklWIaatuIRZcuWNbsEEcmHcipibcqoiPUppyLWpowWUFIStGkDmzfnXFajKgy8BQb2h+qRnq9NSryyoUFml2AZatqKR4TrpxEilqecilibMipifcqpiLUpo+dhGNnPlPXzhfJnNbgD/OHGbjCkP1zVHuyatClFJ7ximNklWIaSJh6xdetWs0sQkXwopyLWpoyKWJ9yKmJtyug5/v4bHn7YdVat0wkZKZB6ChIOwO094IoW8NYLsHs9fPgWdLhaDVspclt3HDS7BMvQmbYiIiIiIiIiIqVBTIxrRu2MGbB2bdbjP3wFHVqAMxXsvjDgdhg02Lw6RURNW/GM2rVrm12CiORDORWxNmVUxPqUUxFrK7UZzciAX35xNWrnz4fU1OzLfbxh69/Q8Qrw0jxRMVftGhpjkknntYtHJCQkmF2CiORDORWxNmVUxPqUUxFrK5UZffFFqF4duneHr77K3rBt1ghemQi71sF994Ldx7w6Rf6VkJhidgmWoaateMTRo0fNLkFE8qGcilibMipifcqpiLWVyozu2weHD2fdL18W7hkG//sZ/vwF7r4TypU937NFPO7o8VNml2AZatqKiIiIiIiIiBRXTicsXw4jRrhm1hoGpCdBcjT06woOB3S/Fj5/F3auhZefg6aNza5aRPJhMwzDMLuI0iouLo6QkBBiY2MJDg42u5wi5XQ6sesqkyKWppyKWJsyKmJ9yqmItZW4jO7fD7Nmuf7Zs8f12Osvw6h+kJ4ARgbYfCEmHipVNLdWkYJIi8PpKIM9qIrZlRSpgvYDS9DeSqxs06ZNZpcgIvlQTkWsTRkVsT7lVMTaSkRGk5Jg9mzo3Blq1oSJE7MatgDz5kJ6IjgCwCcMvAPUsJViZdP2/WaXYBleZhcgpUNKigZJi1idcipibcqoiPUppyLWVqwzumEDvPMOzJkDcXHZl9ls0PEKGHQb3NgbvP1NKVGkMKSkpJldgmWoaSseERoaanYJIpIP5VTE2pRREetTTkWsrVhndOlSeP/97I/VrAYDb4GB/SGymjl1iRSy0OBAs0uwDDVtxSOqVdMBRMTqlFMRa1NGRaxPORWxtmKR0dRU+P57aNIE6tUDwwkZSdC3G4z1Al9vuPF6GNwfrm7vOstWpASpFlHe7BIsQzNtxSP+/vtvs0sQkXwopyLWpoyKWJ9yKmJtls7oxo3w4INQpQrccgu8OR1ST0HCAUjYD8HAvI9h9wb44E3ocJUatlIi/a2Ztm4601ZERERERERExNNOnoTPP4cZM2D9+uzLZs+G8SPBLwi8yoDNAZ07mVOniJhCTVvxiJo1a5pdgojkQzkVsTZlVMT6lFMRa7NERtPT4eefXY3a775zjUM4m68P9OgEQ/qBf3lwOMypU8QkNSMrmV2CZahpKx6Reu6BSEQsRzkVsTZlVMT6lFMRa7NERn/9FXr2zPl488Yw6Fa4rS+UDfN8XSIWkZqabnYJlqGZtuIRhw8fNrsEEcmHcipibcqoiPUppyLW5vGMxsXBnj1Z950ZcM0VEP7vmYQVysJ9I2DVL/DHz3DXHWrYSql3+OhJs0uwDEs1bWvUqIHNZsvxz7333gtAcnIy9957L+XKlSMoKIhbbrmFY8eOZXuNAwcO0LNnTwICAqhYsSKPPfYY6enZu/TLli2jRYsW+Pr6UqdOHWbOnJmjlrfeeosaNWrg5+dH27Zt+euvv7ItL0gtIiIiIiIiIlKKOJ2wdCkMGQLh4XDvvZCeBMnRkLAPUg7D0w/BnPdh5zqY8gw0aWR21SJiQTbDMAyzi8h04sQJMjIy3Pc3b95Mly5dWLp0KR07duTuu+9m4cKFzJw5k5CQEO677z7sdjt//vknABkZGTRr1ozw8HBefvlljhw5wpAhQ7jjjjt4/vnnAdi7dy9NmjThrrvuYtSoUSxevJgHH3yQhQsX0q1bNwC+/PJLhgwZwrvvvkvbtm15/fXXmTt3Lv/88w8VK1YEyLeWgoiLiyMkJITY2FiCg4MLazNaUlpaGt7e3maXISJ5UE5FrE0ZFbE+5VTE2oo0o/v2waxZMHOm63Ymmw02L4GICmD3A4ef6zERySktjjRbEN7BVc2upEgVtB9oqabtuR588EG+//57du7cSVxcHBUqVODzzz+nb9++AGzfvp2GDRuycuVKrrjiCn788Ud69epFVFQUlSq5fm7w7rvv8vjjj3PixAl8fHx4/PHHWbhwIZs3b3a/T//+/Tl9+jQ//fQTAG3btqV169a8+eabADidTqpVq8aYMWMYN24csbGx+daSm5SUFFJSUtz34+LiqFatWqlo2m7atInLLrvM7DJEJA/KqYi1KaMi1qecilhboWc0MRHmzXNdVGzp0pzLQ8pA317w6P0QGVl47ytSUqXFsWn3KS5r0c7sSopUQZu2lr0QWWpqKp999hkPP/wwNpuNtWvXkpaWRufOnd3rNGjQgMjISHejdOXKlTRt2tTdsAXo1q0bd999N1u2bKF58+asXLky22tkrvPggw+633ft2rU88cQT7uV2u53OnTuzcuVKgALVkpsXXniBSZMm5Xh8zZo1BAYG0qJFC7Zt20ZSUhJlypShZs2abNq0CYDq1avjdDo5ePAgAM2aNWPXrl3Ex8cTGBhIvXr1WL9+PQBVq1bF4XCwf/9+AC677DL27dtHXFwcfn5+NG7cmLVr1wIQERGBn58fe/6ds9OkSRMOHTrE6dOn8fHxoVmzZu7REOHh4QQFBbFr1y4AGjZsyLFjx4iJicHLy4uWLVvy119/YRgGFSpUICwsjB07dgCuv2ju2bOHEydOYLfbad26NWvWrCEjI4Ny5cpRsWJFtm3bBkDdunWJi4tzj5to27Yt69atIy0tjbCwMCIiItiyZQsAtWvXJjExkSNHjgDQqlUrNm/eTHJyMiEhIURGRvL3338DrvEb6enpHDp0CIAWLVqwfft2EhMTCQoKonbt2mzcuBGAyH8PqAcOHADg8ssvZ/fu3cTHxxMQEECDBg1Yt26de3t7eXmx79+/pjZt2pQDBw4QGxuLn58fTZo0Yc2aNQBUrlyZgIAAdu/eDUDjxo2Jiori1KlTeHt706JFC1atWgVApUqVCA4OZufOne7tffz4cU6ePInD4aBVq1asXr0ap9NJhQoVKFu2LP/88w8A9erV49SpU5w4cQKbzUabNm1Yu3Yt6enplC1blkqVKrm3d506dYiPj+fo0aMAtGnThg0bNpCamkpoaChVq1Z1/5GjVq1aJCcnExUVBUDLli3ZsmULycnJBAcHU6NGjWzf2YyMDPf2bt68OTt27CAhIYGgoCDq1KnDhg0bAKhWrRp2uz3bd3bv3r2cOXMGf39/GjZs6N7eVapUwcfHh71797q398GDBzl9+jS+vr5cdtllrF692v2dDQwMdG/vRo0acfToUWJiYnJs74oVKxISEuLe3g0aNCA6Opro6Gj3dzZze5cvX57y5cuzfft293c2NjaW48eP5/jOli1blvDwcLZu3er+ziYkJLi3d+vWrdm0aRMpKSmEhoZSrVo193e2Zs2apKamumdvFfU+IioqCsMwTNlH1K9fn5iYGO0jtI/QPiKPfUR8fDyJiYmm7SPM/O8I7SO0jygu+4ioqCiSkpJK5X9HaB+hfURx2EecOnWKunXrFso+IsLPjypXX439zBnOZthsxLVpRchdg/mren0MH18q2vwIiY1n5x7Xd6lBnSpEx8QRHXMGu8NG68vqsHrTLpwZBuXLlqF82WC273Jlt26tysTGJXI8OhZs0LZZXdZt3kNaWgZlQ4MIrxjK1h2u7VC7RjgJickcPX4agNaX12bT9gOkpKQRGhxAtYjy/L3d9b2rGVmR1NR0Dh+NcX1nm9Zi265DJCWlUibIn5rVKrJpmyvn1atWcO0jolyzRps1rsGufUeJT0gmMMCXerUiWL/Ztc2qRpTDYbez/9AJAC5rWJ19h44TdyYJPz8fGterytpNrn1CRHgYfj4+7DngymOT+tU4dDSG07EJ+Ph40axRDf7a4NonhFcMJSjAj137XN+lhnWrciz6NDGn4vHystOyaW3+2rgTwwkVygcTFhzIjn+3d/3aEcScjufEyTjsdhutL6/Dmr93k5HupFxYGSqWC2Zb5vauGU5cfBLHTsQC0LZ5XdZt2UtaajphoYFEVCzLlh2ufWXt6pVITE7lyLFTALS6rDabdxwgOTmNkOAAIs/a3jWqVXTtI478u72b1GT7nigSE1MICvKjdmQ4G7e6ch5ZpTwABw5HA3B5oxrsPnCU+PhkAgJ8aVArgnWZ27tyWdc+4qDrGNK0QSQHoqKJjUvEz8+bJvUiWbPJtU+oXCmMAD8fdu93be/G9aoRdTyGU6cT8PbxokXjmqxa79onVKoQQnCQPzv3/ru961Th+Mk4Tp46g8PLTqumtVm9cRdOp0GFcsGUDQ3in92u7NarVZlTcQmciI7DZoc2l9dl7d+7SU93UjYsiErlQ9m20/WdrVMjnPizvrNtGlfk6PHTJK1aVaL/O+LsEzrzYtkzbb/66isGDBjAgQMHiIiI4PPPP2f48OE5PlibNm249tprmTJlCnfeeSf79+9n0aJF7uWJiYkEBgbyww8/0L17d+rVq8fw4cOzNWV/+OEHevbsSWJiIqdOnaJKlSqsWLGCdu2yOvtjx45l+fLlrFq1qkC15KY0n2m7detWGjXSnB4RK1NORaxNGRWxPuVUxNouKaMpKeDrm3XfmQ4dOsCfrpO7qBUJA/vCoP5QtcqlFytSGqXFsXVfHI0ub2N2JUWq2J9p+9FHH9G9e3ciIiLMLqXQ+Pr64nv2Tr4UqVmzptkliEg+lFMRa1NGRaxPORWxtgvOaEoKLFjgGn+waxds3QJGCqTFQ/oZGHYT1KwMg2+H9u00q1akENSsVin/lUoJu9kF5Gb//v38+uuvjBo1yv1YeHg4qampnD59Otu6x44dIzw83L1O5s9czl6euSyvdYKDg/H396d8+fI4HI5c1zn7NfKrRbLLPEVdRKxLORWxNmVUxPqUUxFrK3BG16+H+++HKlXg1lvhhx9gxw745WtI2A+pJwE73D4Q3nsDrrpSDVuRQrJp2z6zS7AMSzZtZ8yYQcWKFenZs6f7sZYtW+Lt7c3ixYvdj/3zzz8cOHDAPcagXbt2/P333+55UAC//PILwcHB7p9AtGvXLttrZK6T+Ro+Pj60bNky2zpOp5PFixe71ylILSIiIiIiIiJSTERHw7Rp0KwZtGgBb7wBJ09mLa8S7rrvVQa8Q8Hhp0atiBQpy41HcDqdzJgxg6FDh+LllVVeSEgII0eO5OGHH6Zs2bIEBwczZswY2rVr577wV9euXWnUqBGDBw/mpZde4ujRo4wfP557773XPZbgrrvu4s0332Ts2LGMGDGCJUuW8NVXX7Fw4UL3ez388MMMHTqUVq1a0aZNG15//XUSEhIYPnx4gWuR7KpXr252CSKSD+VUxNqUURHrU05FLObpp8HhgAkTgHMy+swzkJHhWmf4cJg9G9LSsj/fzxd6dYbB/eDajq7XEpEiVb1qBbNLsAzLNW1//fVXDhw4wIgRI3Ise+2117Db7dxyyy2kpKTQrVs33n77bfdyh8PB999/z9133027du0IDAxk6NChTJ482b1OzZo1WbhwIQ899BDTpk2jatWqfPjhh3Tr1s29Tr9+/Thx4gRPPfUUR48epVmzZvz0009UqlSpwLVIdk6n0+wSRCQfyqmItSmjItannIpYjMMBTz3luj1hQlZGn3nG9Xhmr8Buy96wbdkUBt0Kt94CYaEeLVmktHM6DbNLsAybYRjaGiYp6NXiSoJVq1bRtm1bs8sQkTwopyLWpoyKWJ9yKmJBmQ3aJ59kT0YGtebMgX37YNLT8MTDrouK/bEMBo+BfjfCkAHQqKHJRYuUUmlxrNp8jLbtrzG7kiJV0H6g5c60FREREREREREpFBMmQFwcPPcctTIf63k9PDQIEg4Admh3BexYC97eJhYqIpKdmrbiEc2aNTO7BBHJh3IqYm3KqIj1KaciFmQYsHNn9sfK+ICB64JimRcT07haEUto1rim2SVYht3sAqR02LVrl9kliEg+lFMRa1NGRaxPORWxoK++gv/+F3D1aQGoUw+8/LMatiJiGbv2HTG7BMvQmbbiEfHx8WaXICL5UE5FrE0ZFbE+5VTEYqKj4ayLnO+a/BR10xLhmVfABox7yLzaRCSbqCN2fvk5mDWbvWnVBrp0gYgIs6syl5q24hGBgYFmlyAi+VBORaxNGRWxPuVUxGKuuw4SE123e3Umpef10KC66/4zr7j+V41bEdP9usSHyS+U4egxG2np6fyyGD76CCZOhE6dzK7OPGraikfUq1fP7BJEJB/KqYi1KaMi1qeciljI99/D33+7boeUgddfpF75Cq77mY3aDKc5tYmIW9QRO5NfKMORo3aSkqBCRS8iqsCBAzBpEjRqBJUrm12lOTTTVjxi/fr1ZpcgIvlQTkWsTRkVsT7lVMQiYmPhrruy7r8wHipXZv3mvVmPjXsInnzE87WJSDY/L/Zl9x4v4s7YSUu3sf8AxMdDZCQcPw4//2x2heZR01ZERERERERESo6MDLimg+t2p/YwZKC59YhIrmJjbXw2x5/YMzYyLxUYGJiBvz/Y7a5rBR4/bm6NZtJ4BPGIqlWrml2CiORDORWxNmVUxPqUUxGLKFsWZrwNva6EZi1dnR+gakQ5kwsTkUybt3jx8utBREfbwTDAgCpVbZQtB97e4HS6Hq5Y0exKzaOmrXiEw+EwuwQRyYdyKmJtyqiI9SmnIhaRkQIp0dDzevAKcD/ssOvHxiJmMwyY+40fn80JwHA6qVA2hagjAQSH2KkcYSctzYbT6ZppW7EidO1qdsXm0R5LPGL//v1mlyAi+VBORaxNGRWxPuVUxGRJSa6OUMpJyEjO1rAF2H/ohEmFiQi4xiE89UwZPv0iACMjHYwM2rR18P77UDnCzu7dsGOHk927ISwMJk4svRchA51pKyIiIiIiIiLF3cqVcOON8PLzcMMV4B1sdkUicpa/N3vxyrQgYk7ZwJmGzW5nwAAHtw3wx26Htle4Ljq2Zk00rVpF0rVr6W7YAtgMwzDMLqK0iouLIyQkhNjYWIKDS/YBJSkpCX9/f7PLEJE8KKci1qaMilifcipikpQUaN4ctm1z3Z85DW7tm2O1pORU/P18PFycSOnmdMJX8/z4/CvXOASMdMLKOnj0MW8ua54zj6XhWFrQfqDGI4hH7Nu3z+wSRCQfyqmItSmjItannIqY5Jlnshq2zRtDn5tyXW3foVJ8GXoRE5w+bWPis2WY/WXWOIRmzb2Y/pZ/rg1b0LH0bBqPIB4RFxdndgkikg/lVMTalFER61NORUywYQO8+KLrtrcXvPMqeOXe6og7k+S5ukRKuU1/u8YhnDqd+ziE89GxNIuatuIRfn5+ZpcgIvlQTkWsTRkVsT7lVMTD0tJgxAjIyHDdf/guaNrkvKv7aTSCSJHLOQ4hjbCyDh4b603TZvlnUMfSLJppa6LSNNM2PT0dr/P8tVNErEE5FbE2ZVTE+pRTEQ974QX4z39ctxvWgT9/Bl/f866enpGBl8PhoeJESp9Tp2y8Mi2ITZu9wZkOGDRr7uCRsX6EhhVsQmtpOJZqpq1Yytq1a80uQUTyoZyKWJsyKmJ9yqmIB23fDpMmuW7b7fDO1DwbtgBrN+3xQGEipdOmv724/9EQNm32+nccgo1Bg72Y9FxAgRu2oGPp2Up261pERERERERESpaMDBg5ElJSXPfvHQatW5lakkhp5XTCnLn+zPna3z0OoWw51ziEJpdrJMmlUNNWPCIiIsLsEkQkH8qpiLUpoyLWp5yKeMiuXfDPP67btSJhwhMFelpEeFgRFiVS+uQ+DsGLRx/3IyT04n7cr2NpFjVtxSM0SFrE+pRTEWtTRkWsTzkV8ZD69WHTahhzL9wxBAIDCvQ0Px+d9SdSWDZs9OKVaUHExtn+HYdgZ9AgB7fe7o/NdvGvq2NpFs20FY/Ys0ezg0SsTjkVsTZlVMT6lFMRD3FmQLANPn4VOnQo8NP2HDhWhEWJlA5OJ8ye489TzwYTGws4XeMQnn/Bh9sGXFrDFnQsPZvOtBURERERERGR4iP1FKTHg7fGHYh4UkyMaxzC31uyxiG0aOnFw49d/DgEOT9tUfGIJk2amF2CiORDORWxNmVUxPqUU5EiFBUFo0bB0QOQehIcgVzoKX1N6lcrouJESr4NG724/9EQ/t7iBc5UbHYbQ4Z68fSzAYXasNWxNIuatuIRhw4dMrsEEcmHcipibcqoiPUppyJFxDDg7rvho4+gaQv43zpw+F7wyxw6GlMExYmUbLmNQyhX3sELL/pc8vza3OhYmkXjEcQjTp8+bXYJIpIP5VTE2pRREetTTkWKyJdfwnffuW7bgYYXdybe6diEwqtJpBSIibHx8utBbN6aNQ6hZSsvHnq06MYh6FiaRU1b8QgfXaVTxPKUUxFrU0ZFrE85FSkCJ07AmDFZ96dOhnLlLuqlfHzUAhEpqPUbvJg6PYjYOBs4U7E7HAwe7OCWfoV/du3ZdCzNYjMMwzC7iNIqLi6OkJAQYmNjCQ4ONrucImUYBraiTLWIXDLlVMTalFER61NORYrAgAHwxReu2zd0hS9mXPRLKaMi+cvIgM+/9Gfut/4YTicY6ZQr72Ds4940alr0DdXSkNOC9gM101Y84q+//jK7BBHJh3IqYm3KqIj1KacihWzBgqyGbWgwvPbCJb3cXxt2FUJRIiVXTIyN8ZPK8NU3/hgZ6WBk0Kq1g+lv+XukYQs6lp5Nvw0QEREREREREWs5fRruuivr/osTIDzctHJESrp167159Y3AbOMQhgxxcPNtRTsOQc5PTVvxiHAdXEUsTzkVsTZlVMT6lFORQvTYYxAV5brd6SoYdPslv2R4xdBLfg2RkiZzHMJX3/iD4QQjjfIVXOMQGjbx/HxZHUuzqGkrHhEUFGR2CSKSD+VUxNqUURHrU05FCsnatfDhh67bQQHw5ssUxql+QQF+l/waIiXJyZM2Xn49iC3bvMGZDkDrNl489KgfZYLNmaiqY2kWzbQVj9i1S7ODRKxOORWxNmVUxPqUU5FC0qIFzPgQQkNg0liIjCyUl92172ihvI5ISbB2vTf3PxrClm1e/45DsDFipIMJkwJMa9iCjqVn05m2IiIiIiIiImItt3WHq+pCeC2zKxEpUTIy4LMv/Pl6vjXGIcj5qWkrHtGwYUOzSxCRfCinItamjIpYn3IqUkjS4iD1FITXAHvhnfHXsG7VQnstkeIoOtrOy68HsnW7l2XGIZxLx9Is1vg3IiXesWPHzC5BRPKhnIpYmzIqYn3KqcglSE6GX3+FjFRIiQa7D9gL9zyzY9GnC/X1RIoT1ziE4H8btmk4vKwxDuFcOpZmsc6/FSnRYmJizC5BRPKhnIpYmzIqYn3KqcglmDwZunSBwQPhxFHwCiz0t4g5FV/orylidenpMOszf55+rgxnzhjgTKNCRQdTXvKmz63+hXGNv0KlY2kWNW3FI7y8NIlDxOqUUxFrU0ZFrE85FblI69bBSy+5bn89H6ITi+RtvLzUApHSJTrazn8mBvP1fD/XOATDoE1bL6a96U/9RtacX6tjaRabYRiG2UWUVnFxcYSEhBAbG0twcLDZ5YiIiIiIiIh4VloatGkDGza47j8xBsaPM7UkkZJg9VpvXnsjkDPxtn/HITgYPtzODTdb7+za0qag/UD9mUk84q+//jK7BBHJh3IqYm3KqIj1KaciF+Gll7Iato3qwmMPFdlb/bVxZ5G9tohVpKfDjE/8mfxC1jiEipVc4xBuvMX6DVsdS7PonGPxCJ3QLWJ9yqmItSmjItannIpcoK1bXbNsAex2eGcq+PoW2dsZziJ7aRFLOHHCzkuvBbF9h8M1DgFoe4UXDz7iR1CZ4nHepo6lWdS0FY+oUKGC2SWISD6UUxFrU0ZFrE85FbkAGRkwciSkprrujxkBrVoW6VtWKK+xhFJyZR+HkI6Xt51hw4rfOAQdS7OoaSseERYWZnYJIpIP5VTE2pRREetTTkUuwBtvwP/+57pduzqMf7zI3zIsOLDI30PE09LT4ZPZ/ny7wB+MDDDSqVjJwePjvKnX0JoXG8uLjqVZise50VLs7dixw+wSRCQfyqmItSmjItannIoU0J498OSTWfffegkCAor8bXfsOVLk7yHiSSdO2Bk3IZhvF/i5xiEYBm2v8GLam/7FsmELOpaeTWfaioiIiIiIiIjneHtD+/bwyy9wxwC4+iqzKxIpdv5a4xqHEJ+QNQ5h+HA7vfsUr3EIcn5q2opH1K9f3+wSRCQfyqmItSmjItannIoUULVq8N/Z8OlHcEMfj71t/doRHnsvkaJyvnEI457wpm6D4nl27dl0LM2i8QjiETExMWaXICL5UE5FrE0ZFbE+5VSkgNITIfUk3N4Pgst47G1jTsd77L1EisLx4znHIbS70ovpb/mXiIYt6Fh6NjVtxSNOnDhhdgkikg/lVMTalFER61NORfJgGJCYCM4MSD7huu/w9WgJJ07GefT9RArTqtXePPBYMP/sdPw7DsHGnXd58cSEAAKDSk57T8fSLCXn36pYmt2ur5qI1SmnItamjIpYn3IqkocvvoCGDWHhN5B+Brw9d4ZtJrtdgz6l+ElPh49mBfDslDLExxvgTKNSuJ2XXvGh901+JW5+rY6lWWyGYRhmF1FaxcXFERISQmxsLMHBwWaXIyIiIiIiIlL4jh+HRo3g5EnX/eXzoVVrU0sSKQ6OH7cz5dUgduxyuM5SB65sb+P+h/xL1Nm1pU1B+4H6NywesWbNGrNLEJF8KKci1qaMilifcipyHvffn9WwvambaQ3bNX/vNuV9RS7GqtXe3P9YyL8N2zS8vG2MvtuLceMDS3TDVsfSLF5mFyClQ0ZGhtkliEg+lFMRa1NGRaxPORXJxX//C19+6bodFgJTXzCtlIx0p2nvLVJQ6ekw87MA/vu9HxgZYDgJr+zg8Sd8qFPP2+zyipyOpVnUtBWPKFeunNkliEg+lFMRa1NGRaxPORU5x+nTcPfdWfenTIDwSqaVUy7M83N0RS7EsWOucQg7d7suNoYN2re3M6YUjUPQsTSLmrbiERUrVjS7BBHJh3IqYm3KqIj1Kaci53jkEThyxHW7awcY0N/UciqW07VkxLpWrvJm2ttBJCTw7zgEB6PucNCjd8m72FhedCzNUjra9GK6bdu2mV2CiORDORWxNmVUxPqUU5Gz/PILfPyx63ZQIEx/CbM7T9t2HTb1/UVyk54OH8wI4PmXy5AQ7wRnOpUjHLzyqg89byhdDVvQsfRsOtNWRERERERERApPfDzccUfW/WfGQbVq5tUjYlFHj9p56bXs4xCuutrBfQ/4lZpxCHJ+atqKR9StW9fsEkQkH8qpiLUpoyLWp5yK/GvNGjhxwnX7qtYwapip5WSqWzPc7BJE3Fb8z5vp72Qfh3DHnQ669yp9Z9eeTcfSLGrbi0fExcWZXYKI5EM5FbE2ZVTE+pRTkX917AjrVsD1HeHNV8BujdZDXHyS2SWIkJYG738cwAuvZI5DSKNyhBdTX/MpdfNrc6NjaRZr7DmlxDt27JjZJYhIPpRTEWtTRkWsTzkV+VdGKkQEwZfvQ906ZlfjduxErNklSCl39KidsU8Gs+AHX9c4BAyu7uDF62/4UauOt9nlWYKOpVk0HkFERERERERECodhQMpJyEgGnzCzqxGxjD9X+jD9nUASEwAjDW8f1ziE63vq7FrJnc0wDMPsIkqruLg4QkJCiI2NJTg42OxyRERERERERC7OunUwaxY8/TjYToNXENh1nphIWhp8/EkA3//oB0YGGBlEVHHw+BM+Oru2lCpoP1DjEcQj1q1bZ3YJIpIP5VTE2pRREetTTqXUSkuDESNg+nRo3hb2HrZkw3bdlr1mlyClzJEjdh77TzDf/5g1DqHDNV68Nj1ADdvz0LE0i/X2olIipaWlmV2CiORDORWxNmVUxPqUUym1pkyBjRtdt4MCoKY1r/6elppudglSivyxwoc33s0+DuHO0Q669dA4hLzoWJpFTVvxiLAwzTISsTrlVMTalFER61NOpVTauhWeecZ12+GAd6aCj4+5NZ1HWGig2SVIKZCaCh/NCuCHRVnjEKpUdY1DqFlbZ9fmR8fSLGraikdERESYXYKI5EM5FbE2ZVTE+pRTKXUyMlxjEVJTXffHjICWLcytKQ8RFcuaXYKUcEeO2HlxahB79jlc4xBs0OEaL+57wB//AJ1eWxA6lmbRTFvxiC1btphdgojkQzkVsTZlVMT6lFMpdaZPh1WrXLfr1IAnx5paTn627DhodglSgv2xwocHxoawZ68DnGn4+Nq4b4wXj44LUMP2AuhYmkVn2oqIiIiIiIjIhdm9G5580nXbZoO3XoKAAHNrEjHB+cYhjPuPDzVqaRyCXDw1bcUjateubXYJIpIP5VTE2pRREetTTqXUMAy44w5ISnLdHzUArmpvbk0FULt6JbNLkBIm6oidKeeMQ+h4rRf3jNE4hIulY2kWNW3FIxITE80uQUTyoZyKWJsyKmJ9yqmUGvPmwdKlrtvVIuCZp8ytp4ASk1PNLkFKkN//9OGNdwNJSgSMNHx8Hdx1t4PO3fywqV970XQszaKZtuIRR44cMbsEEcmHcipibcqoiPUpp1Jq9OkDL70AAf4w/QUoE2R2RQVy5Ngps0uQEiA1Fd5+P4CXXgsiKdEJRhpVqjqY+poPXa5Xw/ZS6ViaRWfaioiIiIiIiEjB2YC7b4c+V0NETbOrEfGYw1F2prwaxN59rouNYbNx7XWucQh+/urWSuGyGYZhmF1EaRUXF0dISAixsbEEBwebXU6RysjIwOFwmF2GiORBORWxNmVUxPqUUyk1kk9C8hHwDgVb8fkBb0aGE4ej+NQr1vLbH65xCMlJaBxCESoNx9KC9gO1txKP2Lx5s9kliEg+lFMRa1NGRaxPOZUS7dgx+N//ID0JUqPBEVCsGrYAm3ccMLsEKYZSU+Gt9wJ4+fUgkpNc4xCqVtM4hKKiY2mW4rWHlWIrOTnZ7BJEJB/KqYi1KaMi1qecSok2ZgxceSU8OAbOnAGHn9kVXbDk5DSzS5Bi5nCUnUeeCOanX3xd4xAwuPY6L16bHkCNWt5ml1ci6ViaRU1b8YiQkBCzSxCRfCinItamjIpYn3IqJda338LcuWAY8MU8SC2el8cJCQ4wuwQpRpb/7sODY0PY9+/8Wh9fOw886MVDjwVofm0R0rE0S/Hc00qxExkZaXYJIpIP5VTE2pRREetTTqVEOnUK7rkn6/6UCVCponn1XILIiPJmlyDFQGoqvP9xAIt+9QMjA4wMqkU6GPcfHyJr6OzaoqZjaRadaSse8ffff5tdgojkQzkVsTZlVMT6lFMpkR5+GI4edd3udg3c3s/cei7B39s101byduiwaxzCol+zxiF06uzFq9MC1LD1EB1Ls+hMWxERERERERHJadEimDnTdbtMEEx/CV11SUqqZb/58Nb7gSQnAUYaPr4O7rnXQaeuxW9+s5QMatqKR9SoUcPsEkQkH8qpiLUpoyLWp5xKiXLmDNx5Z9b9Z8ZB1arm1VMIalQrnmMdpGilpMB7HwXyyxLff8chOP8dh+BLZA21zTxNx9Is+vaJR6Snp5tdgojkQzkVsTZlVMT6lFMpUZ54Ag78O07g6jYwapip5RQGZVTOdeiwnRenlmH/AbtrHILNRucuDkbf46+LjZlEOc2imbbiEYcOHTK7BBHJh3IqYm3KqIj1KadSYvz+O7z1lut2gD+89UqJGItw6EiM2SWIhSxd7sNDj4ewf7+rYevrZ+fBh7x44JEANWxNpGNpFp1pKyIiIiIiIiJZypaFVi1hzVqY8BDUrm12RSKFJrdxCJHVXeMQqlVXm0ysw2YYhmF2EaVVXFwcISEhxMbGEhwcbHY5RSotLQ1vb11pUcTKlFMRa1NGRaxPOZUSwzDgzCGY/QkMGgIOh9kVFYq0tHS8vdWUK80OHnKNQzhw0A7OdLDZ6NLFzuh7/PH109m1VlAajqUF7QdqPIJ4xPbt280uQUTyoZyKWJsyKmJ9yqmUGOlnwHkGBg8uMQ1bgO17oswuQUy0ZJlrHMKBA1njEB5+xIv7Hw5Qw9ZCdCzNoj8xiUckJiaaXYKI5EM5FbE2ZVTE+pRTKdbS0lxn2HrZIPkE2L3BXrJaBomJKWaXICZIToZ3Pwxk8bKscQjVazh4/AmNQ7AiHUuz6Exb8YigoCCzSxCRfCinItamjIpYn3IqxdqLL0KLFvDHr5CRBI4AsysqdEFBfmaXIB528JCdh8eFsHiZDzjTAIOu3RxMfT1ADVuL0rE0i2bamqg0zbRNTk7Gz08HSBErU05FrE0ZFbE+5VSKrS1boHlz19m2Pt6w9U+oXMXsqgpdckoafr4le1amZFm81Id3PgwkJRkw0vDzd3DPvQ6u7az9tJWVhmOpZtqKpWzcuNHsEkQkH8qpiLUpoyLWp5xKsZSRASNHuhq2APcNL5ENW4CNW/eZXYJ4QHIyvP5mIK+/FURKshOMdGrUdPDaNF81bIsBHUuz6FxwERERERERkdJq2jRYtcp1u15N+M9Yc+sRuQQHDjp4cWoQBw+5LjaGzUa36x3cebc/Pr662JgUL2raikdERkaaXYKI5EM5FbE2ZVTE+pRTKXZ27YInn3TdttngrZfB39/cmopQZJXyZpcgRWjxUh/e/iCQ1BTc4xDuG+PFNdf5ml2aXAAdS7OoaSsiIiIiIiJS2jidMGqU67fkAHcOgivbmVuTyEVIToZ3PghkyXJfMDLAcFKjpoNx//GlSjW1vaT40kxb8YgDBw6YXYKI5EM5FbE2ZVTE+pRTKVbefx+WL3fdjqwCk8abW48HHDgcbXYJUsj2H3Dw8LgQliz3cY1DwOD67g6mvh6ghm0xpWNpFn2DRUREREREREqTgwdh7Fmza994AcoEmVePyAUyDPh1iS/vfhRAaorhHocw5n4vOlyrcQhSMqhpKx5x+eWXm12CiORDORWxNmVUxPqUUyk2fv8dkpJctwffAp07mVuPh1zeqIbZJUghSE6Gt98PZOlvWeMQatby4vEnfHR2bQmgY2kWjUcQj9i9e7fZJYhIPpRTEWtTRkWsTzmVYmPAAPjzV+jaAV6YZHY1HrP7wFGzS5BLtG+/g4ceD2Hpb1njELr3cPDKa/5q2JYQOpZm0TdaPCI+Pt7sEkQkH8qpiLUpoyLWp5xKsZGeBA3C4esZ4PAzuxqPiY9PNrsEuUgah1B66FiaxXJn2h4+fJhBgwZRrlw5/P39adq0KWvWrHEvNwyDp556isqVK+Pv70/nzp3ZuXNntteIiYlh4MCBBAcHExoaysiRI3P8S9+0aRNXX301fn5+VKtWjZdeeilHLXPnzqVBgwb4+fnRtGlTfvjhh2zLC1KLuAQEBJhdgojkQzkVsTZlVMT6lFMpFgwnpESDM6NUNWwBAgLU3CuOkpPh1emBTH8nkNQUJxgZ1KzlxbQ3fNWwLYF0LM1iqabtqVOnaN++Pd7e3vz4449s3bqVqVOnEhYW5l7npZdeYvr06bz77rusWrWKwMBAunXrRnJy1l/MBg4cyJYtW/jll1/4/vvv+e2337jzzjvdy+Pi4ujatSvVq1dn7dq1vPzyyzz99NO8//777nVWrFjB7bffzsiRI1m/fj033XQTN910E5s3b76gWsSlQYMGZpcgIvlQTkWsTRkVsT7lVCxt/nyYPBnij0NaLHgHm12RxzWoFWF2CXKB9u138ODYEJb9njUOoUdPL155zZ+IqvrxeEmkY2kWm2EYhtlFZBo3bhx//vknv//+e67LDcMgIiKCRx55hEcffRSA2NhYKlWqxMyZM+nfvz/btm2jUaNGrF69mlatWgHw008/0aNHDw4dOkRERATvvPMOTz75JEePHsXHx8f93vPnz2f79u0A9OvXj4SEBL7//nv3+19xxRU0a9aMd999t0C1nCslJYWUlBT3/bi4OKpVq0ZsbCzBwSX7gLlq1Sratm1rdhkikgflVMTalFER61NOxbJiYqBRIzh2DBrXg4WfQ4XKZlflcavW76Rt87pmlyEFYBjw86++vD8jcxxCOv4BDu6/34urOurs2pKsNBxL4+LiCAkJybcfaKk/S3z33Xd069aNW2+9leXLl1OlShXuuece7rjjDgD27t3L0aNH6dy5s/s5ISEhtG3blpUrV9K/f39WrlxJaGiou2EL0LlzZ+x2O6tWraJPnz6sXLmSDh06uBu2AN26dWPKlCmcOnWKsLAwVq5cycMPP5ytvm7dujF//vwC13KuF154gUmTcg55X7NmDYGBgbRo0YJt27aRlJREmTJlqFmzJps2bQKgevXqOJ1ODh48CECzZs3YtWsX8fHxBAYGUq9ePdavXw9A1apVcTgc7N+/H4DLLruMffv2ERcXh5+fH40bN2bt2rUARERE4Ofnx549ewBo0qQJhw4d4vTp0/j4+NCsWTP++usvAMLDwwkKCmLXrl0ANGzYkGPHjhETE4OXlxctW7bkr7/+wjAMKlSoQFhYGDt27AAgLS2NPXv2cOLECex2O61bt2bNmjVkZGRQrlw5KlasyLZt2wCoW7cucXFxHDt2DIC2bduybt060tLSCAsLIyIigi1btgBQu3ZtEhMTOXLkCACtWrVi8+bNJCcnExISQmRkJH///TcANWrUID09nUOHDgHQokULtm/fTmJiIkFBQdSuXZuNGzcCEBkZCcCBAwcA19ULd+/eTXx8PAEBATRo0IB169a5t7eXlxf79u0DoGnTphw4cIDY2Fj8/Pxo0qSJe8RH5cqVCQgIcA/Wbty4MVFRUZw6dQpvb29atGjBqlWrAKhUqRLBwcHukRsNGzbk+PHjnDx5EofDQatWrVi9ejVOp5MKFSpQtmxZ/vnnHwDq1avHqVOnOHHiBDabjTZt2rB27VrS09MpW7YslSpVcm/vOnXqEB8fz9GjrqH8bdq0YcOGDaSmphIaGkrVqlXdZ5jXqlWL5ORkoqKiAGjZsiVbtmwhOTmZ4OBgatSoke07m5GR4d7ezZs3Z8eOHSQkJBAUFESdOnXYsGEDANWqVcNut2f7zu7du5czZ87g7+9Pw4YN3du7SpUq+Pj4sHfvXvf2PnjwIKdPn8bX15fLLruM1atXu7+zgYGB7u3dqFEjjh49SkxMTI7tXbFiRUJCQtzbu0GDBkRHRxMdHe3+zmZu7/Lly1O+fHn3H3nq1q1LbGwsx48fz/GdLVu2LOHh4WzdutX9nU1ISHBv79atW7Np0yZSUlIIDQ2lWrVq7u9szZo1SU1N5fDhw+7vbFHuI06dOsXGjRtN2UfUr1+fmJgY7SO0j9A+Io99RHx8PImJiabtI8z87wjtI7SPKC77iFOnTrFq1apS+d8R2kdYex9R59lnKffvZz4VWpbYZDvBp8+wc6/ru9SwThWOn4zj5KkzOLzstGpam9Ubd+F0GlQoF0zZ0CD+2e3Kbr1alTkVl8CJ6DhsdmhzeV3W/r2b9HQnZcOCqFQ+lG07XduhTo1w4hOTOXr8NABtmtVhw9Z9pKamExoSSNXwsmz+x/W9qxVZieTUVKKOngKg5WW12LLjEMnJqQSX8adG1Yps2ub63lWvWoEMp5NDUScBaN6kJjv2RJGQmEJQoB91aoSzYYtrm1WLKOfaRxw6wam4eJKSU9l78Dhn4pPw9/ehYZ2qrPvb9R2tEl4WHx8v9h5w5bFpg0gORkVzOi4RX19vLmsQyeqNru0bXjGUwAA/du9zbcNG9apy9PhpYk7H4+3toEWTWqzasBMMqFg+hJDgAHbucX2XGtSpQnRMHNExZ7A7bLS+rA6rN+3CmWFQvmwZypcNZvsuV3br1qpMbFwix6NjwQZtm9Vl3eY9pKVlUDY0iPCKoWzd4dretWuEk3DW9m59eW02bT9ASkoaocEBVIsoz9/bXd+7mpEVSU1N5/DRGNd3tmkttu06RFJSKmWC/KlZLfv2djqdHPx3ezdrXINd+44Sn5BMYIAv9WpFsH6za79aNaIcjn+3N8BlDauz79Bx4s4k4efnQ+N6VVm7ybW9I8LD8PPxYc8B13ezSf1qHDoaw9HjScz/b1V27QzjVGwCYFC3jo1HH4P4hN2sWqV9REn+74jY2FhWrVpVov874uwTOvNiqTNt/fxc83Qefvhhbr31VlavXs0DDzzAu+++y9ChQ1mxYgXt27cnKiqKypWz/ip42223YbPZ+PLLL3n++eeZNWuW+8uSqWLFikyaNIm7776brl27UrNmTd577z338q1bt9K4cWO2bt1Kw4YN8fHxYdasWdx+++3udd5++20mTZrEsWPHClTLuUrzmbaHDx+mSpUqZpchInlQTkWsTRkVsT7lVCzpp5+ge3fX7TJBsHYJlNLv6eGjJ6kSXs7sMiQPe/c5mPJqEIej7OBMB5uNHj0cjLzTDx9fm9nliQeUhmNpsTzT1ul00qpVK55//nnA1QnfvHmzu2lb3Pn6+uLrWzpP4/fystRXTURyoZyKWJsyKmJ9yqlYzpkzMHp01v3nnii1DVtQRq3MMGDRL65xCGmpBhhpGodQSimnWSx1IbLKlSvTqFGjbI81bNjQfUp4eHg4gPs09UzHjh1zLwsPD3f/tChTeno6MTEx2dbJ7TXOfo/zrXP28vxqkSyZp+qLiHUppyLWpoyKWJ9yKpYzbhz8+/+nueYKGFH8T4a6FPsOHs9/JfG4xEQbr7weyFvvB5KW6gQjg9p1HEx7w1cN21JIx9Islmratm/fPsdYgx07dlC9enXANZcpPDycxYsXu5fHxcWxatUq2rVrB0C7du04ffq0e44SwJIlS3A6ne5Bxu3ateO3334jLS3Nvc4vv/xC/fr1CQsLc69z9vtkrpP5PgWpRURERERERMQUv/0Gb7/tuh3gD2+9Ajb9vFysZc9eBw89Hsxvf/qAMw0w6NXbi5dfDaByFZ1xKaWbpWbarl69miuvvJJJkyZx22238ddff3HHHXfw/vvvM3DgQACmTJnCiy++yKxZs6hZsyYTJkxg06ZNbN261T0Tt3v37hw7dox3332XtLQ0hg8fTqtWrfj8888BiI2NpX79+nTt2pXHH3+czZs3M2LECF577TXuvPNOAFasWME111zDiy++SM+ePZkzZw7PP/8869ato0mTJgWuJS8FnWFREiQmJhIQEGB2GSKSB+VUxNqUURHrU07FMhIT4fLL4d8Lu/HikzDmHnNrsoDEpBQC/HXmphUYBvz0sy8fzMwch5BOQKBrHEL7a/TvqDQrDcfSgvYDLXWmbevWrfn222/54osvaNKkCc888wyvv/66u2ELMHbsWMaMGcOdd95J69atiY+P56effsrWJJ09ezYNGjSgU6dO9OjRg6uuuor333/fvTwkJISff/6ZvXv30rJlSx555BGeeuopd8MW4Morr+Tzzz/n/fff5/LLL+frr79m/vz57oZtQWsRl8wRFyJiXcqpiLUpoyLWp5yKZUyfntWwbX053DM67/VLiQNR0WaXILjGIbz8WhBvf5A1DqFOXQevT/dVw1Z0LD2Lpc60LW1K05m2q1atco+nEBFrUk5FrE0ZFbE+5VQsIzkZnh4Pb74NyxZAo4ZmV2QJq9bvpG3zumaXUart2evgxalBHDlqB2c62Gz07m1n+Ch/vH00vkNKx7G0oP1ADQgRj9DZxyLWp5yKWJsyKmJ9yqlYho8Dnrwb7roNKlY1uxrL8PPzNruEUssw4MdFvnw4K3McQhqBQa5xCFd20Nm1kkXH0iw609ZEpelM24yMDBwOh9lliEgelFMRa1NGRaxPORVLMAxIPg4pJ8A7TBcfO0tGhhOHw1JTIkuFxEQbb7wTyB8rfcDIAMNJ3Xp2xo7zJTxC5xJKdqXhWFosZ9pKybVmzRqzSxCRfCinItamjIpYn3Iqptq2DbZuhfR4SD0JXmXUsD3Hmk27zS6h1Nmz18GDY4P5Y6U3ONMAgxtudDDllQA1bCVXOpZmUUJEREREREREirP0dBgyBDZtgnFjYMxw8NYoADFP5jiED2YGkJ6WNQ7hgQe9aHeVxiGIFITOtBWPqFy5stkliEg+lFMRa1NGRaxPORXTvPYarFkDqanw5bdg9ze7IkuqXCnM7BJKhYQEG1OmBvHOh4GkpznByKBuPQfT3vBTw1bypWNpFp1pKx4REBBgdgkikg/lVMTalFER61NOxRQ7dsBTT7lu22zw1sugC/nkKsDPx+wSSrxdux1MeTWIo8fsrnEINhs33uRg2Eh/vLw1rkPyp2NpFp1pKx6xe7dmB4lYnXIqYm3KqIj1KaficU4njBoFycmu+3cNhnZXmFuThe3ef8zsEkosw4Dvf/TlsSeDOXrUBs40AoPsPDnem1F3BahhKwWmY2kWnWkrIiIiIiIiUhy9+y78/rvrdo2q8PR4c+uRUikhwcb0twNZscoHjAwwnNSr7+DxJ/yoGO4wuzyRYstmGIZhdhGlVVxcHCEhIcTGxhIcHGx2OUUqPj6eoKAgs8sQkTwopyLWpoyKWJ9yKh61fz80aQLx8a77Cz6D6641tyaLi09IJihQoyMK085dDl56LXMcQjrYbNx0k52hIzQOQS5OaTiWFrQfqPEI4hFRUVFmlyAi+VBORaxNGRWxPuVUPMYwYPTorIbt0FvVsC2AqOMxZpdQYhgGLPjBl7Hjs8YhBJWxM36CNyNHaxyCXDwdS7NoPIJ4xKlTp8wuQUTyoZyKWJsyKmJ9yql4zCefwKJFrtsRFeH5p00tp7g4dTrB7BJKhNzGIdRv4MXYcb4ahyCXTMfSLGraikd4e3ubXYKI5EM5FbE2ZVTE+pRT8Zg6daBeXdixE157DkJDza6oWPD2UQvkUu3c5WDKq0EcO24HZxrY7PS5xYshw/x0dq0UCh1Ls2imrYlK00xbERERERERKSSGE07uhvnzYcBAs6uRUiBzHMKMTwNITzPASCeojIOHHvaiTTtfs8sTKVY001YsZdWqVWaXICL5UE5FrE0ZFbE+5VQ8JuUUeKXA7bebXUmxsmr9TrNLKJbi4208/3IQH8wIJD3NCUYG9Rt4Mf1NPzVspdDpWJpFvw0QERERERERsbqEBPD3ByMVUk+Cwx9sOg9LitaOna5xCMdPaByCiKepaSseUalSJbNLEJF8KKci1qaMilifcipF6u67Yc8eeOM5qFUBvILMrqjYqVQhxOwSig3DgO8W+jHzM/9/xyGkUSbYNQ6h9RU6u1aKjo6lWdS0FY/QzF4R61NORaxNGRWxPuVUiswPP8Cnn7pud+8LW1aArtVzwYKD/M0uoViIj7fx+luBrFrtA0Y6GAYNGjoYO86PCpUcZpcnJZyOpVn0WwrxiJ07NTtIxOqUUxFrU0ZFrE85lSIRFwejR2fdn/AI+AeaV08xtnPvUbNLsLx/djh44LFgVq32do1DwMYtt3rxwksBatiKR+hYmkVn2oqIiIiIiIhY1eOPw6FDrtvXtoNhg82tR0okw4D/fu8ah5CRrnEIIlagpq14RMOGDc0uQUTyoZyKWJsyKmJ9yqkUumXL4N13XbcD/eHNV8Cmiz9drIZ1qphdgiWdOWNj2tvZxyE0bOQah1C+os6uFc/SsTSLxiOIRxw/ftzsEkQkH8qpiLUpoyLWp5xKoUpMhFGjsu5PfBRq1DCtnJLg+Mk4s0uwHNc4hJBs4xD63urF81MC1LAVU+hYmkVNW/GIkydPml2CiORDORWxNmVUxPqUUylUEybA7t2u222bw913mltPCXDy1BmzS7AMw4D5C/x4fEIwJ04AzjTKBNuZ+LQXQ0f64+WtM7rFHDqWZtF4BPEIh0N/oROxOuVUxNqUURHrU06l0KxaBa+/7rrt6wNvTwW7zrm6VA4vbUNwjUN4/a1A/lpz9jgEL8aO89XZtWI6HUuz2AzDMMwuorSKi4sjJCSE2NhYgoODzS5HRERERERErGDKFBg3znV74iMw9mFz65ESY/s/Xrz0WhAnom3gTAebnVtvtTNwiB8OL51dK+IJBe0H6s9M4hGrV682uwQRyYdyKmJtyqiI9SmnUmjGjoVF8+CmrvDw/WZXU2Ks3rjL7BJMYxjw7Xd+jHuqjHscQnCInacneTFkhL8atmIZOpZm0XgE8Qin02l2CSKSD+VUxNqUURHrU06l0KTHQ9sGcOX7YNf/bS8sTmfp/KHxmTM2XnszkNVrs8YhNG7ixWOP+1Kugn6KLtaiY2kW7f3FIypUqGB2CSKSD+VUxNqUURHrU06lUDjTIOUE4AV2b7OrKVEqlCt9Ywm3bXeNQ4g+aXN9t2x2buvnYMBgjUMQa9KxNIuatuIRZcuWNbsEEcmHcipibcqoiPUpp3JJ3njDdbGxYTdDeiJ4h5ldUYlTNjTI7BI8JnMcwqzZ/jgzDDDSCA5x8Mij3rRo7WN2eSLnpWNpFs20FY/4559/zC5BRPKhnIpYmzIqYn3KqVy0HTtcc2zvuw+uvwnwA5vOgixs/+yOMrsEj4iLszH5hSBmfBqAMyMDjAyaNPVi+pt+atiK5elYmkVn2oqIiIiIiIiYxemEkSMhOdl1//JG4BNgbk1SbJ07DsFmd41DuH2wPw6NrxUpVtS0FY+oV6+e2SWISD6UUxFrU0ZFrE85lYvyzjvwxx+u2zWqwsQnza2nBKtXq7LZJRQZw4B58/349IuscQghoa5xCM1b6exaKT50LM2i8QjiEadOnTK7BBHJh3IqYm3KqIj1Kadywfbvh3Hjsu6/OQUCdZZtUTkVl2B2CUUiLs7GpOfLMGt2znEIathKcaNjaRY1bcUjTpw4YXYJIpIP5VTE2pRREetTTuWCGAbceSfEx7vuD7sNru1oZkUl3onoOLNLKHRbt3lx/6MhrF3v5RqHYLPR/3YHz74YQNnymocgxY+OpVk0HkE8wqYh+iKWp5yKWJsyKmJ9yqlckFmz4OefXbcjKsJzT5taTmlgK0GnrZ1vHMKjj3nTrKXOrpXiS8fSLDbDMIyCrnzgwAEAIiMjs93PT+b6kl1cXBwhISHExsYSHBxsdjkiIiIiIiLiCUeOQKNGcPq06/5XH0LP7qaWJMVHbKyN194MYu16bzD+z959h0dVp20c/55pqSR0Qu+9d7CtiIqKHeuKuvaOoNhfu66rggVhLbvuuhasawdRxLIqCNK7dJLQQxqp0877xyEZIiUBkpyTzP25rrmcmQwzT8bcc5JnfvP8gmCa9OzlZvzdMVpdK1IDVLQfeFgrbdu0aYNhGBQWFuLz+UovlycUCh3Ow0gttGDBAvr37293GSJyCMqpiLMpoyLOp5xKhT38cKRhe+GZathWkwXL1tO/Z3u7yzgqK1Z6eOb5RDKzDGscgsvFJZe6uWR0HK5atJJYopeOpRGH1bT917/+hWEYeL3eMpdFyhMMBu0uQUTKoZyKOJsyKuJ8yqlU2LPPgumHz7+EZ5+0u5qoEQyG7S7hiJkmfPhxLG+/F48ZDoMZoG49axxC734ahyC1h46lEYfVtP3LX/5yyMsiB1O/fn27SxCRciinIs6mjIo4n3IqFZbgg4n3w4NjoGFDu6uJGvXrJdpdwhHJyTGYOCmRRUu8EA4CJr16uxl/dyz1GmgcgtQuOpZGVMlGZH6/n0AgQEJCQlXcvdRATZo0sbsEESmHciribMqoiPMpp1IhZhiKM6xZpA1T7K4mqjRpWNfuEg7b8hUenn2h7DiESy91c/FlGocgtZOOpRFHFfH33nuPcePGlbnu0UcfJTExkbp163LeeeeRl5d3VAVK7bBq1Sq7SxCRciinIs6mjIo4n3Iqh/Trr5CWBoEc6+SpY3dFUWfV2nS7S6gw04QP/hvL/Y8kkZkJhAPUrefiiSe9XHq5GrZSe+lYGnFUMZ84cSL5+fmll2fPns2jjz7KiBEjGDduHDNmzODJJzWfR0RERERERKJYTg5ccAF07w5TXgIjFgx9rF0OLCfH4KHH6/DWu/GYoSCYIXr19jBpciy9+mp+rUi0OKrxCOvXr+fKK68svTx16lRSUlL45JNP8Hg8hMNh/vvf//LUU08ddaFSs3Xo0MHuEkSkHMqpiLMpoyLOp5zKQd19N2zZYp2f9g1cf4299USpDm2cP47iQOMQ/vxnNxf9WatrJTroWBpxVJEvLi4mNja29PI333zD6aefjsdj9YK7detGenrN+fiBVB2NyRBxPuVUxNmUURHnU07lgL7/Hl57zTqfGA8vPQuGYW9NUSqvoMjuEg4qHIb3Pyo7DqFefWscwiWj1bCV6KFjacRRxb5t27Z8++23AMyfP59169Zx2mmnlX59x44dJCbWzN0ZpXJt377d7hJEpBzKqYizKaMizqecyn7y8+HaayOXH7kLWre2r54ot31ntt0lHFB2tsHDT9Th7fci4xD69PUwaUqcxiFI1NGxNOKoxiPccMMN3H777axcuZL09HRatGjBmWeeWfr1X375he7dux91kSIiIiIiIiI1zoMPwoYN1vmh/eCGaw99e4k6S5d5mPBiIlnZGocgImUZpmmaR3MH//jHP5g+fTp169blnnvuoUuXLgBkZmZy6qmncuONN3LttTowHUhubi7Jycnk5OSQlJRkdzlVyjRNDH0ESMTRlFMRZ1NGRZxPOZUyfv0VjjkGTBNiY2D2DOjcye6qopqTMhoOwwf/jWXqB/GY4TCYQerVd3PX3V569tHqWoleTsppValoP/Com7Zy5KKpabto0SL69u1rdxkicgjKqYizKaMizqecSqniYujbF1atsi4/eheMH2trSQKLVmykb/e2dpdBdrbBhBcTWbLMC+EgYNKnr5s7746lbj0tr5XoFg3H0or2A4/q1WDKlCmH/HooFOLPf/7z0TyE1BJ+v9/uEkSkHMqpiLMpoyLOp5xKqSeeiDRs+3SDsbfaW48A4PcH7S6Bpcs8jBmfzJJlnr3jEAwuv8LDY3+NV8NWBB1L93VUM23HjBlDXFwcV1999X5fKy4uZtSoUcycOfNoHkJqibp169pdgoiUQzkVcTZlVMT5lFMpNWgQNE2BXRnw8kTwHNWf3lJJ6iYn2PbY4TC8/1Ec734Yt3ccQoD6DaxxCD16axyCSAkdSyOO6sjx6KOPcv311+Pz+Rg9enTp9fn5+Zx11lnMmTOHjz766KiLlJqvRYsWdpcgIuVQTkWcTRkVcT7lVEqNPA3mToeff4VeveyuRvZqkVLflsfNyrLGISxdHhmH0LefhzvvjiW5rlbXiuxLx9KIo3p1+L//+z/uvfderrrqKj744AMAsrKyGD58OPPnz2f69OmcddZZlVKo1GzLly+3uwQRKYdyKuJsyqiI8ymnUqo4E+p44eyz7a5E9rH897Rqf8wlS61xCEuXlx2H8OiT8WrYihyAjqURR/0ZjSeeeIKioiIuv/xysrOzmTx5Mlu2bGHmzJkMHjy4MmoUERERERERcbbcXKhTB4L54N8NnjpQy3dAl4MLh+HdD+J4/78ahyAiR6ZSButMmDCBoqIibrrpJpo0acKPP/5Ijx49KuOupZZo166d3SWISDmUUxFnU0ZFnE85jWLhMJxxBtStC8/9HzSpBy6v3VXJH7Rr1aRaHicz02DipLLjEPr193DHXRqHIFIeHUsjDqtpO2bMmIN+zTAMEhIS6NOnD6+99lqZ61988cUjr1BqhaKiIrtLEJFyKKcizqaMijifchrFpkyBX36xzm/ZCD99bW89ckBF1bAr/eIlHia8mEhOrgFhPy63m8svdzPq4jgtvBapAB1LIw6raTt58uRybzNjxowyl9W0FYCtW7fSsmVLu8sQkUNQTkWcTRkVcT7lNEpt2gT33Re5/NSD4NJqSifauj2Llk0bVsl9H2gcQoOGbu6+x0u3nhqHIFJROpZGHFbTNhwOV1UdIiIiIiIiIjWLacJ110F+vnX56ovhhBPsrUmqXWamwbMvJLJ8ZWQcQv8B1jiEpGQ18EXkyBimaZp2FxGtcnNzSU5OJicnh6SkJLvLqVLBYBCPp1JGKItIFVFORZxNGRVxPuU0Cv3rX3DNNdb55inw2/eQXLv/tqvJgqEQHre7Uu9z0WIPEyeVjEMI7B2H4NI4BJEjFA3H0or2A/WWj1SLFStW2F2CiJRDORVxNmVUxPmU0yizdSvccUfk8ot/VcPW4VasSa+0+wqF4K2pcTz8ZBI5OUA4QMNGbv72tJcLLlHDVuRI6VgacVSta5fLhVGBV6JQKHQ0DyO1gAZJizifciribMqoiPMpp1HENOHmm7G6dcDFZ8PpI+ytScpVVFQ5G5EdaBzCgIFuxo2P0zgEkaOkY2nEUTVtH3roof2atqFQiE2bNvHpp5/SuXNnzjzzzKMqUGqH2j7+QaQ2UE5FnE0ZFXE+5TSKfPABfPaZdb5RfXjmCXvrkQpJqhN31PexcJGX515K2DsOwY/L7ebKK92cd6FW14pUBh1LI46qafvII48c9Gvbtm1jyJAhdOrU6WgeQmqJNm3a2F2CiJRDORVxNmVUxPmU0yjy44+R8xMfg4YN7KtFKqxNi8ZH/G9DIZj6fhwffBwHZhhMaxzC3fd46drDV4lVikQ3HUsjqmzdftOmTbnxxht5/PHHq+ohpAZZunSp3SWISDmUUxFnU0ZFnE85jSJTJsPU1+Cai2HUeXZXIxW0dNXmI/p3u3cbPPBIHathGw6CGWbgIDeTpsSpYStSyXQsjajS7dgSEhLYuHFjVT6EiIiIiIiISPUK5MDpQ+Hs0+2uRKrYwkVeJk5KIHePNQ7B7XFz5ZUuzr1A4xBEpGpVWdN2+fLlTJo0SeMRBIDWrVvbXYKIlEM5FXE2ZVTE+ZTTKBEqgqIMcMWBoU2napLWLRpV+LahELzzXhwfflJ2HMI993rp0l2ra0Wqio6lEUfVtG3btu1+G5EBZGdnk5OTQ3x8PJ9++unRPITUEqFQyO4SRKQcyqmIsymjIs6nnNZy990HfXrDmcdB2A++enZXJIcpFA5X6HYZGS6efSGBlas91jgEYNBgD2PvjKVOkhr1IlVJx9KIo2ra/ulPf9qvaWsYBvXq1aN9+/Zccskl1K9f/6gKlNohPT2d5s2b212GiByCciribMqoiPMpp7XYrFnwt79Z5y8+C16fYm89ckTSt+6meZND9ygWLPIy8cUE9uQZEA7g9rj5y19cnDNK4xBEqoOOpRFH1bR94403KqkMEREREREREQfKz4frrotcHtQfDLd99UiVCIXg7Xfj+OjTODBDYAZp1Ngah9C5m8YhiEj1M0zTNO0uIlrl5uaSnJxMTk4OSUlJdpdTpfx+Pz6fDnQiTqacijibMirifMppLTV2LLz4onX+mP7w9afg0kfkayJ/IIjPu//atYwMF888n8iq390Qtj6aPWiwS+MQRGwQDcfSivYDD2ul7WOPPXbYhRiGwYMPPnjY/05qlzVr1tCjRw+7yxCRQ1BORZxNGRVxPuW0Fpo9GyZNss7HxsCUiWrY1mBrNmylR+dWZa6bv9DLc5PKjkO46ioXZ5+vcQgidtCxNOKwmraPPPLIfteVzLT944JdwzAwTVNNWwEgPz/f7hJEpBzKqYizKaMizqec1jJFRXDNNVDyt+4DY6FTR1tLkqOTX1Bcej4YtMYh/PezyDiExk3c3H2PxiGI2EnH0ojDatqG/7DT4pYtWxg5ciQ9evRg7NixdO7cGYDVq1fzwgsvsHLlSqZNm1Z51UqNlZiYaHcJIlIO5VTE2ZRREedTTmuZJ56A1aut8/16wJib7a1HjtjWbS5mzoph6aq2rF4RR/++Ad6cGr93HEIQgMFDPIy9M5bEOlpJLWInHUsjjmqm7bnnnovX6+XDDz884NcvuOACQqEQn3zyyREXWJtF00zb4uJiYmJi7C5DRA5BORVxNmVUxPmU01pk8WIYMMDancrrgZ+nQ4/udlclR+Db73w89lQddu5yYWJSXOyioMCgfdsgDev78Xhd/OUvGocg4hTRcCytaD/wqN5C+u677zjppJMO+vXhw4cza9aso3kIqSUWL15sdwkiUg7lVMTZlFER51NOa5Hx462GLcCdN6lhW0Nt3ebisafqkJntol3bEKbpp6DAoKgI1qx1k1jHzdPPeDlnlBq2Ik6hY2nEUTVtY2NjmTNnzkG/Pnv2bGJjY4/mIURERERERESq11tvwTkjoVtHuHuc3dXIEZo5K4adu1ykNA7x+1oPGbt9GIZJbKyJy+3ixOGxdOqq+bUi4kyHNdP2jy677DImTZpE3bp1ue2222jfvj0A69evZ9KkSUydOpUxY8ZUSqFSs7Vs2dLuEkSkHMqpiLMpoyLOp5zWIg3rwH+egT1BqOUf063NduxyUVBosHK1l1AI3C4wDGjd2mBPnovcPXZXKCJ/pGNpxFE1bZ9++mkyMjKYPHkyU6ZMweWyFu6Gw2FM0+TSSy/l6aefrpRCpWYr+dkQEedSTkWcTRkVcT7ltJYIB6F4F+CG+nXtrkaOUF6ewYKFPjKzXMTHhTEME18MdO7kIi7eatg2bmx3lSLyRzqWRhxV09bn8/HWW29x1113MW3aNFJTUwFo3bo1p59+Or17966UIqXm27x5MykpKXaXISKHoJyKOJsyKuJ8ymkN98030L8/JIQhmA/eenZXJEdo2XIPz72USGYWxHjDFBUZtGhhULdeLnHx9UhNtRq2p55qd6Ui8kc6lkYcVdO2RK9evejVq1dl3JWIiIiIiIhI9dqwAc47DxIT4NkH4Pxz0M5UNU8wCO+8F8d/P4vDDIeJ9QXo1RMys2Mo9rvYujWGzEyrYfvww9C0qd0Vi4gcXKU0bTdu3MhXX33F5s2bAWjTpg2nnXYabdu2rYy7l1pATX0R51NORZxNGRVxPuW0hjJNuP56KCiwTv/7FS640O6q5DBt2eri2ecTWb/RbY24wKRXbzfj7vQRCLn45hvYssVL8+bWCls1bEWcScfSiKNu2t555528+OKLhMPhMte7XC7Gjh3LhAkTjvYhpBbYuHEj3bp1s7sMETkE5VTE2ZRREedTTmuo11+HWbOs881T4PGH7a1HDotpwtczY/jHG/H4iwEzgMfr5vLL3Zx3YVzpgukrr4SVK9cqoyIOp2NpxFFN9504cSLPP/88559/PnPmzCE7O5vs7GzmzJnDBRdcwPPPP8/zzz9fWbVKDbZnj7blFHE65VTE2ZRREedTTmugLVvgzjsjlyc9BclJ9tUjhyUnx+DJZxKZ8loC/uIwmEGat3Az4Tkf518Ut9+EC2VUxPmU04ijWmn7j3/8g7PPPpsPPvigzPWDBw/mvffeo6ioiFdffZVx48YdVZFS88XFxdldgoiUQzkVcTZlVMT5lNMaxjThppsgN9e6fMk5cJp2pqopFi7y8sKUBLKyDQgHwDA4Y6SHq6+LJSb2wPOIlVER51NOI46qabtp0yZuv/32g359xIgRzJgx42geQmqJrl272l2CiJRDORVxNmVUxPmU0xrmvffgiy+s840bwDOP21uPVIjfD/95J57Pp8WCGQYzQHJdN2Nu9zBoaMwh/60yKuJ8ymnEUY1HaNy4MUuWLDno15csWUKjRo2O5iGklli4cKHdJYhIOZRTEWdTRkWcTzmtQXbtgjFjIpefexwaNLCvHqmQTZvd3HFvMp9Pi7E2GzPD9B/g4aUpseU2bEEZFakJlNOIo1ppe+GFF/Liiy/Spk0bbrvtNhISEgDIz89n8uTJ/POf/2Ts2LGVUaeIiIiIiIhI5RgzBjIyrPPnnArnnWNvPXJIpglfTI/hjbfjCfhNMAN4fW6uvsbNyLNj95tdKyJSGxxV0/bxxx9n8eLF3H///Tz00EM0a9YMgK1btxIMBhk2bBiPPfZYpRQqNVvz5s3tLkFEyqGcijibMirifMppDWGacMop8NV0cBnw3N/srkgOITPT4IUpiSxa4gUzCKZJm7Ye7rrHS6s23sO6L2VUxPmU04ijatrGx8cza9YsPvvsM7766is2b94MwGmnncYZZ5zBWWedhaG3vATw+Xx2lyAi5VBORZxNGRVxPuW0hjAMuPLPcGwnWLcJUprYXZEcxNzfvLw4JYE9eSWbjbk49zwXV1wVh9d3+L0GZVTE+ZTTiCNu2hYUFDB69GhGjRrFZZddxjnn6OMkcnAbN26kcePGdpchIoegnIo4mzIq4nzKaQ1hhqF4N6TUh5bt7K5GDqCoCF7/TzwzZsaCGQIzSP0Gbsbd4aVP/yNv6CijIs6nnEYc8UZk8fHxfPvttxQUFFRmPSIiIiIiIiKVLyfH+m8gF4qzwFPH3nrkgNatdzP27mRmzIyxVtdiMvQYDy/9Pe6oGrYiIjXNETdtAY477jjmzJlTWbVILdazZ0+7SxCRciinIs6mjIo4n3LqYPn50Lcv/OUK2L4e3LFguO2uSvYRDsNHn8Qy/v4ktmyxxiHExLq4bYyH+x6MJyn5qNoXgDIqUhMopxFH9ao3efJkfvrpJ/7v//6P9PT0yqpJaqG0tDS7SxCRciinIs6mjIo4n3LqYA88ABs3wn/egtsfAE+83RXJPnbtcvHAI3X4zzvxhIIhMEN07OTmxZdiOPX0WCprqxxlVMT5lNOIo9qIrHfv3gSDQZ566imeeuopPB4PMTExZW5jGAY5JR9DkaiVnZ1tdwkiUg7lVMTZlFER51NOHeqXX2DSJOt8XCw8cr+99UgZP/3iY8prCeTnA2E/hsvNhRe5uXR0LB5v5W5sroyKOJ9yGnFUTdsLLrigsuqQWu6PzXwRcR7lVMTZlFER51NOHaioCK65BkzTuvzA7dCxg701CQAFBQavvh7Pdz/G7N1sLEyjxm7uuNNHj97eKnlMZVTE+ZTTCMM0S45eFVdUVMRnn33Gxo0badCgAWeeeSZNmzativpqtdzcXJKTk8nJySEpKcnucqpUOBzG5Tr6GUQiUnWUUxFnU0ZFnE85daD774ennrLO9+8J308Dt2bZ2m3Vag8TJyWwY6cLwkEwDE44wcXNt8WSkFh1GVJGRZwvGnJa0X7gYT8LO3fupEePHvz5z3/m/vvv58Ybb6RTp058++23R1Ww1G6//fab3SWISDmUUxFnU0ZFnE85dZiFC+GZZ6zzXg+8/JwatjYLhWDq+3Hc82ASO3ZYm43FJ7i4c7yXu+6Lr9KGLSijIjWBchpx2OMRHn/8cTZt2sS4ceM46aSTWLduHY8//jg33HAD69evr4oaRURERERERCouELDGIoRC1uXxN0H3bvbWFOW2bXMxcVIiv691W6trMenazcP4u2NonKJmuojIHx3221jffPMNV1xxBRMmTOCMM85gzJgxTJ48mU2bNvH7778fVTGPPPIIhmGUOXXp0qX060VFRdxyyy00aNCAxMRERo0axY4dO8rcR2pqKiNHjiQ+Pp7GjRtz1113EQwGy9zmhx9+oF+/fsTExNChQwfeeOON/WqZMmUKbdq0ITY2lsGDBzNv3rwyX69ILRKRkpJidwkiUg7lVMTZlFER51NOHeSZZ2DxYut8t45w1zhby4lmpgmzvvcx5q5kfl9jNWxdboPRl3t46tn4am3YKqMizqecRhx20zY1NZXjjjuuzHXHHXccpmlWStOye/fubNu2rfT0888/l35t3LhxfPHFF3z44Yf8+OOPbN26lfPPP7/066FQiJEjR+L3+5k9ezb/+c9/eOONN3jooYdKb7Nx40ZGjhzJsGHDWLx4MWPHjuXaa6/l66+/Lr3N+++/zx133MHDDz/MwoUL6d27NyNGjGDnzp0VrkXKSkhIsLsEESmHciribMqoiPMppw5hmjB7tnXe5YKXJ4I2trHFnj0GzzyXyAtTEikqDIMZoGkzF8886+Xiy+KqfVqFMirifMppxGGPRyguLiY2NrbMdSWX/7ii9YgK8ngO2FXPycnh9ddfZ+rUqZx00kkA/Pvf/6Zr1678+uuvDBkyhG+++YaVK1fy7bff0qRJE/r06cPjjz/OPffcwyOPPILP5+OVV16hbdu2TJw4EYCuXbvy888/8/zzzzNixAgAnnvuOa677jquuuoqAF555RWmTZvGv/71L+69994K1XKw5664uLj0cm5u7lE/XzXF+vXradiwod1liMghKKcizqaMijifcuoQhgGff2o1a7dvhwH97a4oKi1d5uG5lxLZnWnNrsUwOOVUD9ffFEdsnGFLTcqoiPMppxGH3bQF2LRpEwsXLiy9nJOTA8DatWupW7fufrfv169fhe977dq1NGvWjNjYWIYOHcpTTz1Fq1atWLBgAYFAgJNPPrn0tl26dKFVq1bMmTOHIUOGMGfOHHr27EmTJk1KbzNixAhuuukmVqxYQd++fZkzZ06Z+yi5zdixYwHw+/0sWLCA++67r/TrLpeLk08+mTlz5gBUqJYDeeqpp3j00Uf3u37+/PkkJCTQr18/Vq1aRWFhIXXq1KFt27YsXboUgNatWxMOh0lLSwOgT58+rFu3jry8PBISEujUqROLFi0CoEWLFrjdbjZv3gxAr1692LRpE7m5ucTGxtK9e3cWLFgAUPpcb9iwAYAePXqQnp5OdnY2Pp+PPn36lI6GSElJITExkXXr1gFWw3vHjh1kZmbi8Xjo378/8+bNwzRNGjVqRL169VizZg0AgUCADRs2sGvXLlwuFwMHDmT+/PmEQiEaNGhA48aNWbVqFQAdO3YkNze3dOX24MGDWbhwIYFAgHr16tGsWTNWrFgBQPv27SkoKGDbtm0ADBgwgOXLl1NUVERycjKtWrVi2bJlALRp04ZgMEh6ejpg/VyuXr2agoICEhMTad++PUuWLAGgVatWgLWyHKB3796sX7+evLw84uPj6dKlS2kGWrRogcfjYdOmTQD07NmT1NRUcnJyiI2NpUePHsyfPx+Apk2bEh8fXzr/uXv37mzdupWsrCy8Xi/9+vVj7ty5ADRp0oSkpCTWrl1b+nzv3LmT3bt343a7GTBgAL/99hvhcJhGjRpRv3790hElnTp1Iisri127dmEYBoMGDWLBggUEg0Hq169PkyZNSp/vDh06kJeXx/bt2wEYNGgQixcvxu/3U7duXVq0aMHy5csBaNeuHUVFRWzduhWA/v37s2LFCoqKikhKSqJNmzZlfmZDoVDp8923b1/WrFlDfn4+iYmJdOjQgcV7P7LWsmVLXC5XmZ/ZjRs3smfPHuLi4ujatWvp8928eXN8Ph8bN24sfb7T0tLIzs4mJiaGXr16lQ4uT0lJISEhofT57tatG9u3byczM3O/57tx48YkJyeXPt9dunQhIyODjIyM0p/Zkue7YcOGNGzYkNWrV5f+zObk5JSuxt/3Z7Z+/fqkpKSwcuXK0p/Z/Pz80ud74MCBLF26lOLiYurWrUvLli1Lf2bbtm2L3+9ny5YtpT+zVfkakZWVxZIlS2x5jejcuTOZmZl6jdBrhF4jDvEakZeXR0FBgW2vEXb+HqHXCL1G1JTXiKysLObOnRuVv0c47zViLqE+/WlQvz6N9xSwap31PHRsm0JuXiE7dll/ww7u25GFKzYS8AepVzeBZo3rs2KN9Ty0b92EgiI/23ZkATCgV3uWr0mlqChAclI8rZo1ZNlqK+dtWja2XiO2ZVrPd4+2rN6wlYKCYhITY2nfKoUlK62ct2puNSNSt2QA0LtbG9anbicvr4j4+Bi6tGvGwuXWz2iLpvWt14g06+ejZ5dWpG7NICe3gNhYLz06tWL+UutntGmTesTH+li/2Xr9696pJVt3ZpKVnY/X56Ff97bMXWS9JjRplExSYhxrN1o/S107NGfn7lx2Z+3B7XExoGd7fluyjnDYpFGDJOrXTeT39VZ2O7VrSlZuPrsycjFcMKh3RxYsW08wGKZ+vUQa1K3L81MC/PBjQ+Jjg4RCQVzuABdetJNrr+th62tEVlYWhYWFUfl7hF4j9HtETfk9Iicnh7lz59bq3yP2XdB5KIZpmmaFbrmXy+XCMPZ/V8w0zf2uL7kuVDL8vRxfffUVeXl5dO7cmW3btvHoo4+yZcsWli9fzhdffMFVV1213zc2aNAghg0bxtNPP83111/P5s2by4w6KCgoICEhgenTp3P66afTqVMnrrrqqjJN2enTpzNy5EgKCgrIysqiefPmzJ49m6FDh5be5u677+bHH39k7ty5TJ06tdxaDuRAK21btmxJTk4OSUlJFXqOaqo9e/ZQp04du8sQkUNQTkWcTRkVcT7l1CGC+ZCfCu44cPnsriaqpG9xMeGFRNZvdEM4BJj06u1m3J0xNGxs/2ZjyqiI80VDTnNzc0lOTi63H3jYK23//e9/H1Vhh3L66aeXnu/VqxeDBw+mdevWfPDBB8TFxVXZ41aXmJgYYqJ0ltL27dtrfehEajrlVMTZlFER51NObWSacPXVcOklcExnwFDDthqZJsz4JoZ//icefzFgBvB43VxxhZtzL4jjAOu+bKGMijifchpx2E3bK6+8sirqOKC6devSqVMn1q1bxymnnILf7yc7O7vMCIYdO3aUzsBNSUkpXTq/79dLvlby3z9umLZjxw6SkpKIi4vD7XbjdrsPeJt976O8WqSszMxMu0sQkXIopyLOpoyKOJ9yaqN//APeeMM63Xk9PPpQef9CKklOjsGklxOYN98HZgjMMC1buRl/t492Hbx2l1eGMirifMpphMvuAg4lLy+P9evX07RpU/r374/X62XWrFmlX//9999JTU0tHWMwdOhQli1bVjrrBWDmzJkkJSXRrVu30tvsex8ltym5D5/PR//+/cvcJhwOM2vWrNLbVKQWKcvrddbBWkT2p5yKOJsyKuJ8yqlN0tNh/PjI5eOOxTFLO2u5BYu83HpHMvPme63NxjAZeaaH5yfFO65hC8qoSE2gnEYc9kzbqjR+/HjOOussWrduzdatW3n44YdZvHgxK1eupFGjRtx0001Mnz6dN954g6SkJG677TYAZs+eDUAoFKJPnz40a9aMZ555hu3bt3P55Zdz7bXX8te//hWAjRs30qNHD2655RauvvpqvvvuO8aMGcO0adMYMWIEAO+//z5XXnklr776KoMGDeKFF17ggw8+YPXq1aWbnJVXS0VUdIaFiIiIiIiIHIBpwllnwbRp1uU/nwv/mGJrSdHA74c33o7ni+mxe1fXhkiu6+b2sR4GDonOkYAiIhVV0X6go1bapqenc+mll9K5c2cuuugiGjRowK+//kqjRo0AeP755znzzDMZNWoUJ5xwAikpKXz88cel/97tdvPll1/idrsZOnQoo0eP5oorruCxxx4rvU3btm2ZNm0aM2fOpHfv3kycOJF//vOfpQ1bgIsvvpgJEybw0EMP0adPHxYvXsyMGTNKG7YVqUXKKtmBUEScSzkVcTZlVMT5lFMbTJ0aadg2aQhPP25vPVFg02Y34+5J5ovpMRAOgmkyYKCbyS/HOb5hq4yKOJ9yGuGolbbRJppW2s6dO5fBgwfbXYaIHIJyKuJsyqiI8ymn1WznTujWDXbvti6/83c49xx7a6rFTBM+nxbLG2/HEQyYYAbxxbi5+ho3Z5wVWyMmUiijIs4XDTmtaD/wsDciEzkSjRs3trsEESmHciribMqoiPMpp9XsttsiDdtzR6hhW4UyMw2en5zI4qVeMK3VtW3bebjrHh8tW9ectoIyKuJ8ymlEzXl1lRotOTnZ7hJEpBzKqYizKaMizqecVqNPP4UPPrDO10uGiU/ZWk5tNmeul5deTmBPnmFtNma4OG+Um8uvjMXrqwHLa/ehjIo4n3Ia4aiZtlJ7rV271u4SRKQcyqmIsymjIs6nnFaTUAjuvDNy+ZmHIKXJwW8vR6SoCF56OYG/PluHPXtMCAeo38DN4094ufq6uBrXsAVlVKQmUE4jtNJWREREREREag63G2Z8BddcCfExcOnFdldU66xd52bCi4ls3ebau7rW4Jhj3dx6eyx1krT2S0SkOqhpK9WiS5cudpcgIuVQTkWcTRkVcT7ltBq1bgyfvAp+DzViB6waIhyG/34ayzvvxxEKmmAGiI1zc/0Nbk4eUTM2GzsUZVTE+ZTTCL1FJtUiIyPD7hJEpBzKqYizKaMizqecVpNQMRRngDcBkuvaXU2tsXOniwceqcObU+MJBUJghujU2c2LL8Vwymk1v2ELyqhITaCcRqhpK9VCoRNxPuVUxNmUURHnU06r2CefQH4+FO+2GreeOLsrqjX+97OPMXcls3ylB8J+DJfBxZd4eHpCPM1a1J4P6CqjIs6nnEbUnldfcTSXS+8PiDidciribMqoiPMpp1Xol19g1Cho0xomPQTDTra7olohP9/g1dfj+f5/MWBaq2sbN3Fz53gv3Xr67C6v0imjIs6nnEYYpmmadhcRrXJzc0lOTiYnJ4ekpCS7yxEREREREXGeoiLo0wd+/926/Nf74fZbbC2pNli5ysPESQns3OWCcBAMgxNPdHHjLbEkJKppIiJSVSraD9QrsVSL3377ze4SRKQcyqmIsymjIs6nnFaRRx+NNGwH9oZbb7S3nhouGIS3343j3oeS2LnTgHCA+AQX4+/ycuc98bW6YauMijifchqh8QhSLcLhsN0liEg5lFMRZ1NGRZxPOa0CCxbAs89a531e+PsEcLvtrakG27bNxYQXE1mzzm2trsWkW3cPd94VQ+OU2v+8KqMizqecRqhpK9WiYcOGdpcgIuVQTkWcTRkVcT7ltJL5/XD11RAKWZfvuhm6dbO3phrKNGHW9z5e/VcCRYWAGcTtcfHnP7u54JI4omWEpDIq4nzKaYSatlItFDoR51NORZxNGRVxPuW0kj39NCxdap3v0RnGj7W1nJpqzx6Dya8kMHuur3SzsWbN3Yy/y0vHLrVvs7FDUUZFnE85jYiS99PEbqtXr7a7BBEph3Iq4mzKqIjzKaeVaMUKePxx67zbDS9PBF90NRgrw9JlHm67M5nZc70QDgAmp47w8OLk+Khr2IIyKlITKKcRWmkrIiIiIiIizhEKwTXXQCBgXR5zNfTra29NNUwgAG9NjeOTL+LADIMZoE6Sm9vGeBh6XIzd5YmISAWoaSvVomPHjnaXICLlUE5FnE0ZFXE+5bQSjRoFS5ZAyxR44B67q6lR0tJdTHghkQ2bSjYbgz59PYy7M4b6DWv/ZmOHooyKOJ9yGqGmrVSLnJwc6tevb3cZInIIyqmIsymjIs6nnFYStxvG3gQn9YDCEMTF2V1RjWCa8NXXMbz+Zjz+YsAM4PG6ufJKF+eMisMw7K7QfsqoiPMppxGaaSvVYufOnXaXICLlUE5FnE0ZFXE+5bSShINQnAEd2kK/fnZXUyPk5Bg8/rdEXv5nAv7iMJhBWrby8NwLPs69QA3bEsqoiPMppxFaaSsiIiIiIiL2y86GunXBnw2BPPDVs7mgmmH+Qi8vTE4gJ9ewNhszXJx5loerro3FF6NurYhITWWYpmnaXUS0ys3NJTk5mZycHJKSkuwuR0RERERExB5padC7N1x1Bdz1F0hIBrc2zDoUvx/+9WY802bEghkCM0RyXTdjx3kYMFjPnYiIU1W0H6jxCFItFi5caHcJIlIO5VTE2ZRREedTTo+QacKNN0JWFjz3Ijw9RQ3bcmzY6Gbs3clMmxFjjZMwTQYO8jDllTg1bA9BGRVxPuU0QuMRpFoEAgG7SxCRciinIs6mjIo4n3J6hN55B6ZPt86nNILxY20tx8lMEz79IpY3p8YRDJhgBvDFuLnmWjennxmr2bXlUEZFnE85jVDTVqqFdv4TcT7lVMTZlFER51NOj8COHXD77ZHLzz8O9TTL9kB27zZ4fnIiS5Z5wbRW17Zr72H83T5attaf9hWhjIo4n3IaoVd2qRYpKSl2lyAi5VBORZxNGRVxPuX0CNx2G2RmWufPOx3OPsveehxq9q9eJr+SwJ48a7Mxw+XivFFuRl8Ri9en5bUVpYyKOJ9yGqGZtlItVq5caXcJIlIO5VTE2ZRREedTTg/TJ5/Ahx9a5+vXheeesrUcJyoqgkl/T+CpCXXYs8eEcIAGDV088aSXq66NU8P2MCmjIs6nnEZopa2IiIiIiIhUr6wsuPnmyOVnHoLGjeyrx4HWrHUz4cVEtm13QTgAhsGxx7q55fY46iRp/ZWISG2npq1Ui/bt29tdgoiUQzkVcTZlVMT5lNPDcMcdsH27dX7En+CSi+ytx0HCYfjok1jeeT+OcMjabCw2zs2NN7k56RRtNnY0lFER51NOI/T2nFSL/Px8u0sQkXIopyLOpoyKOJ9yWkEFBbB0qXW+TiK89CzqRFp27nRx30N1eOvdeMLBEJghOnfxMGlyDMNPVcP2aCmjIs6nnEaoaSvVYnvJu+gi4ljKqYizKaMizqecVlB8PPzyIzwyHp5+EJo3t7siR/jhfz5uG5/MytUeCPsxXAaXXOrhb8/G0bS5PiRbGZRREedTTiP0yi8iIiIiIiLVxzQhnAu3/wV89eyuxnb5+QYv/yOeH3+OAdNaXdu4iZvxd3np2sNnd3kiImITwzRN0+4iolVubi7Jycnk5OSQlJRkdzlVKhwO43JpYbeIkymnIs6mjIo4n3JaQf4cKEgHbxIYbrursdWKlR6eeymBnbtcEA6CYTBsmIsbbo4lIVE/S5VNGRVxvmjIaUX7gbX7WRDHWFoys0pEHEs5FXE2ZVTE+ZTTQygshFGjYN6vUJwBrpiobtgGg/DW1DjueziJnTsNCAdISHRx191e7rg7Xg3bKqKMijifchqhI4FUi+LiYrtLEJFyKKcizqaMijifcnoIDz8MH38MxxwH/3oLPPF2V2Sbrdtc3P1AEh98HIsZCoIZokdPDy9NieWEYTF2l1erKaMizqecRmimrVSLunXr2l2CiJRDORVxNmVUxPmU04P47TeYONE673bBscfbW49NTBO+/S6G1/4dT1EhYAZwe9yMHu3m/IviqOWfBnYEZVTE+ZTTCDVtpVq0bNnS7hJEpBzKqYizKaMizqecHoDfD9dcA+GwdfmeW6FbV3trssGePQYvvZLAnLm+vZuNhWnW3M34u3107Oy1u7yooYyKOJ9yGqH38qRaLFu2zO4SRKQcyqmIsymjIs6nnB7AU09ByfPSswvcMcbeemyweImHW+9IZs5cL4QDgMmI09y8ODleDdtqpoyKOJ9yGqGVtiIiIiIiIlL5li+HJ5+0zrvd8PIE8PnsrakaBQLWZmOffBEHZhjMAHWS3Iy53cOQYzW7VkREDk1NW6kWbdu2tbsEESmHciribMqoiPMpp/sIBuHqq63OJcDt10DfvvbWVI1S09xMeDGBjZvcEA4C0Lefh7F3xFC/odvm6qKXMirifMpphJq2Ui38fr/dJYhIOZRTEWdTRkWcTzndxwsvWBuQAXRqC/ffbWs51cU0YdqMGP79Vjz+YsAM4PG6+ctfXJx9fhyGYXeF0U0ZFXE+5TRCM22lWmzZssXuEkSkHMqpiLMpoyLOp5zulZMDjz1mnTcMmPIsxMXZW1M1yM42eOypRF59PQF/cRjMIK3buHn+RR/njFLD1gmUURHnU04jtNJWREREREREKk9yMnz3LVz9FzhmABwz1O6KqtxvC7y8OCWBnFzD2mzMcHHW2W7+ck0cvhh1a0VE5PAZpmmadhcRrXJzc0lOTiYnJ4ekpCS7y6lSgUAAr1c7o4o4mXIq4mzKqIjzKaf7KNoFuengqgPx8XZXU2WKi+Ffb8Yz/etYMENghqhbz83YcR76D9JmY06jjIo4XzTktKL9QI1HkGqxatUqu0sQkXIopyLOpoyKOJ9yulcwH4p3Q1zdWt2w3bDRzdi7k5n+dczezcZMBg32MPnlODVsHUoZFXE+5TRC4xGkSm3dCjNnwvz5dRkwAE45BZo1s7sqETmQwsJCu0sQkUNQRkWcL6pzaprw7rsw6nwIZFiX3bWzcWma8OkXsbw5NY5gwAQzgC/GzXXXuxlxRqxm1zpYVGdUpIZQTiPUtJUq8+231v4DO3eC39+EmTPh9dfh4Ydh+HC7qxORP6pTp47dJYjIISijIs4X1Tl96y248kp4pge89DD0G2J3RVUiI8PF85MTWLrcC2YQTJP2HdyMvzuGFq3057XTRXVGRWoI5TRCM21tVJtn2m7dCpdcApmZ4PGAzxciLs5NRgY0aADvvw9Nm9pdpYjsq7CwkLgo2NlZpKZSRkWcL2pzun07dOsGWVnW5fdfgzNH2ltTFfhljo/Jr8STl29AOIjhcjFqlIvLrojF49Xy2pogajMqUoNEQ04101ZsNXOmtcK2RQvYtg3WrQuxerXJrl2wZAncdJO16nbmTPj9d8jPt7tiEVm6dKndJYjIISijIs4XtTm99dZIw3bUGbWuYVtYCC9OSeBvExPJyzMhHKBhIxdP/tXLldfEqWFbg0RtRkVqEOU0Qp/fkCqxc6f13+Lifa40QxgYhEIGa343+TRoAgbgAsOgYUNo2RJatbJOJecTEmz4BkREREREpHz//a91AmhQDyb81d56Ktnva9xMnJTItu0uCAfAMDjueA+3jIklsY7WQImISNVR01aqROPG1n9jYqBLF8jJDhIKuCgocFFY6Mbn8UMwCBhYk/pdZOy0TosWGuzbzK1fP9LI3behm5ho3/cnUhu1bt3a7hJE5BCUURHni7qcZmbCLbdELj/7MDRuZF89lSgUgg8/juXdD+MIh6zNxmLj3Nx4k5uTTtFmYzVV1GVUpAZSTiPUtJUqccop1viDLVusJqvPE8TncZGaHkOf5kFemZSL32+QlmaQmmaQmuYiNc1NXn7Ju9WRZm5mhnVavDByXUkzd9+VuSXNXM2sFjky4XDY7hJE5BCUURHni7qcjhsHO3ZY508fBhddYG89lWTHDhcTJyWy6ncPhIOASecuHu68y0fT5voTuiaLuoyK1EDKaYSOOFIlmjWDhx+GRx+F9euhqNBNbIyXxo3DPHzfHrp1DQHQp3fk35gmZGcbpKW72bzZIC090szdk1ey+rakcWuQmeEmM8PFkkVlm7n16lnN29atyzZ11cwVObS0tDSaNWtmdxkichDKqIjzRVVOv/oK3nzTOp9UByY9TU1ffmqa8MP/fLz8zwQKC4GwH8Pl5tJL3Vx0aSxuT83+/iTKMipSQymnEWraSpUZPtzaRPabb2D+vG0M6JnIqadA06YHftfEMKBePZN69YL06hm53jQhJ8cgNc1NappBWhqkprnZnHrgZm7WbjdZu10sXVy2mZucvH8jt1UrOMRGfSIiIiIi8ke5uXDDDZHLT94HzZrbV08lyM83+Ptr8fzvlxgwQ2CGaJLiZvxdXrp099ldnoiIRCHDNE3T7iKiVW5uLsnJyeTk5JBUyzuHxZkbiPGEwFO5u4qVNHPT0g02b4a0dDepaW5ycvdv5mK4wXCx7+iFkmbuvhuflZySkyu1VBHHKy4uJiYmxu4yROQglFER54uanBYWwiOPwIQJcMIg+PKjGr3KdvkKD8+9lMiuDMMah2AYDB/u4vqb4ohPqLnfl+wvajIqUoNFQ04r2g9U09ZG0dS0XbFoDt3bN6z0pu3B5OQYexu4kZW5qWlusnNcgElJw/ZQzdykpLKzcvdt5tbg30lFDmrFihV0797d7jJE5CCUURHni6qc+nPglxnQpCW0aWN3NUckGISp78fx0adxmOEwmEESEt3ccquH40+s3Q2DaBVVGRWpoaIhpxXtB2o8glSLvIKian285GST5OQgPUpzHgBgz559xywYbE51kZbuIivbzR+bublZbpZnGyxfum+D10WdOgdemVu3rpq5UrPl5eXZXYKIHIIyKuJ8UZPTkB+Kd0H//uCJt7uaI7Jlq4uJLyaydr27dLOxHj093HlXDA0bu+0uT6pI1GRUpAZTTiPUtJVqkRDnjHeq69Qx6d4tSPduZa/fsyeyMjc1tWQTNDeZWfs3c/dku1iR42LFsrLN3MTEsk3ckqZuvXpq5krNkJBQPSvhReTIKKMizlfrc5qZaf1yW7wbQkXgq293RYfNNOGbb2P4xxvxFBcBZgC3x83o0W7OvygOl8vuCqUq1fqMitQCymmExiPYKJrGI/izNuBzV/5M26qWl1e2mZuatm8zd6/S0QquvefLNnMTEso2cks2Q6tfX81ccRa/34/Pp402RJxKGRVxvlqd099+g2HD4P674PrzILYuuGrWGqDcXIOXXkng13m+vZuNhWnewsX4u3106OS1uzypBrU6oyK1RDTkVOMRxFEWrdzM4J4t7C7jsCUmmnTtEqRrl7LX5+eXNHPZ28x1k5buImP3vs1caz5ufq6LVSus0x+bufuOWCg536CBmrlij0WLFjF48GC7yxCRg1BGRZyv1ubU74err4b8fHjgEUh0w7VX213VYVm02MMLUxLJzDIgHADD4PQz3Fx9XRyxcfrlO1rU2oyK1CLKaYSatiJHICHBpEvnIF06l1xjzczNzzdI3+LaZ2Wum9Q0Fxm7967GhTLN3NUrrdO+zdz4+P2bua1bq5krIiIiIjb5619h+XLrfK+ucOXl9tZzGPx+eHNqPJ99GQtmGMwAScluxtzuYfAxzhjhJiIiciBq2kq1aJFS8+ZdHYmEBJPOnUJ07lRyjdXMLSgwSEu3Nj1LTaW0mbsrY/9mbsEeF7+vsk6RZq5BXJyx3+ZnLVtCo0Zq5krlaNGi5q2GF4kmyqiI89XKnC5bBk8+aZ33eODlCeCtGaMENqe6mfBiAps2l2w2Bv36e7h9XAz1G2qzsWhUKzMqUssopxFq2kq1cLuje6J/fHxJMze09xqrmVtYCGnpbtLSXGxOxWrqprnZuWv/Zm5hnos1q63Tvs3c2FjjgCtz1cyVw+V2648XESdTRkWcr9blNBi0xiIErYYnY6+FPn1sLakiTBO+/CqGf78VT8BvghnA63Nz1dVuzjwnVr8jR7Fal1GRWkg5jVDTVqrF5i0ZpNTXuyV/FBcHnTqG6NQxVOb6oiKrmZua6iItHVLTrGbujp1uwKSkYQsGRflu1v7uYu3vB27m/nF1buPGaubKgW3evJmUlBS7yxCRg1BGRZyv1uX0+edh/nzrfOd2cN9d9tZTAVlZBi/+PZEFi7ylm421aevmzrt8tGlXM1YIS9WpdRkVqYWU0wg1bUUcKDYWOnYI0bHD/s3c9C0Haua6ME2oSDM3Jmb/Zm7LlpCSomauiIiIiOy1Zg089JB13jBgyrPWL6kONm++lxenJJC7p2SzMRfnnOvmiqvi8MXoF10REalZDNO0Wj1S/XJzc0lOTiYnJ4ekpCS7y6lShRnriPOZ4Emwu5Raqbg40sxNTYuMWdi+Y/9mLoYbDBdQtpnr8xm0aGGNVti3odukCbiie7pF1CgsLCQuLs7uMkTkIJRREeerNTkNh+HEE+Gnn6zLN10JE/5qa0mHUlwMr/8nnq++id27ujZEvfpuxt3hpe8An93liYPUmoyK1GLRkNOK9gO10laqxaYtGXRt28DuMmqtmBho3y5E+3ZlV+b6/WWbualp1mZo27a7Mc19Z+Ya+ENuNqxzsWHdgZu5fxyzkJKiZm5ts2nTJrp27Wp3GSJyEMqoiPPVmpxu3WqdANq0gEcesLeeQ1i/wc2zLySyZavL2mzMgMFDPIwZF0tSsn5ZlbJqTUZFajHlNEJNW6kWuXmFdpcQlXw+aNc2RLu2+zdzt2x1k5pqkJpmWOMWtrjYuu1QzVxj7wpdq5nr9Uaaufuuzk1JAc0Nr5lyc3PtLkFEDkEZFXG+WpPTFi1g4Rz4v3vh1JMg0XmflguH4ZPPY3n7vTiCAWuzsZhYN9de52bEGdpsTA6s1mRUpBZTTiPUtJVqERujjyU5ic8HbduEaNum7PV+P2zdFmnmpqW52JzmZtt2F+Fw2WZuIORm43oXG9eXbeZ6PFYzt2RWbsnK3KZN1cx1uliHz6kTiXbKqIjz1ZqchkPgKoDHxoMv2e5q9pOR4eK5lxJYtsILZhBMkw4d3Yy/O4bmLfUnrhxcrcmoSC2mnEZopq2NommmbTBnEx4joJm2NVQgYK3MTUuLrMxNTXezddv+zVwMlzU3l/2buc2b778yt2lT8Oh3a0cIBoN49D9DxLGUURHnqzU5LcqAou3grbv39znn+Hm2j8mvJpCfD4QDGC43F1zg4s+Xx+LxanmtHFqtyahILRYNOdVMW3GUBcs3MrhnC7vLkCPk9UKb1iHatC57fTBYsjJ378zcVBep6daYhVAI9t0ALRhysXmjm80bDX7+QzO3WbPIitySpq6audVvwYIFDB482O4yROQglFER56vROd22DW66CZ56DJrHgDveUQ3bwkJ49fUEZv0Qs3ezsTANG7m5c7yXHr31qT6pmBqdUZEooZxGqCUiIkfM44FWLUO0all2Zm4wCNu2u9i82U1aetlmbjAIf2zmpm5yk7qp7MpctzvSzN13dW7z5mrmioiIiFQq04RbboHPPoOvZ8B/XoAzz7a7qlKrf/cwcVIC23e4IBwAw+D4E9zcfFssiXWc01gWERGpTGp9SLVo1rie3SVINfJ4oGWLMC1bhMtcX9LMTUtzl1mZu2Xr/s3cUMhF2mY3aZvLNnNdrrIrc0uaus2bWyuC5cg1a9bM7hJE5BCUURHnq7E5/egj+OQT63xiAgw+xt569gqF4IP/xvHeR7GEQ9ZmY3Hxbm662c2Jw7XZmBy+GptRkSiinEaoaSvVIjZG3TQp28w9Zmjk+lDIauamplrN3LR0F6mpLtIP0MwNGy7SU92kpxrM/kMzt2nTss3cVq2gWTNr4zUpnwa+izibMirifDUyp7t3w623Ri5PeBgaNbSvnr22b3cxcVIiq9d4IBwETLp2c3PnXbE0aardbeXI1MiMikQZ5TRCTVupFhvSdtKormbayoG53dCieZgWzfdv5m7fYTVz09Jhc6qLtDSrmRsIlN0ALWy42JLmZkuawZzZkWauYVgrc0s2PitZmduihZq5f7RhwwYaNWpkdxkichDKqIjz1cicjh0LO3da50cOhwtG2VqOacL3P/p45fUECguBcACX28Wll7q58NI43OrXylGokRkViTLKaYSatiLiWG43NG8WpnmzMPv0cgmFYMdO194N0AzS0g1SU92kb3Xj95dt5pr7NHN/nVO2mZuSsv/KXDVzRUREJGpMnw5vv22dT64DL/4NO2cO5OUZ/P21BH6a7du72ViIlKZuxt/lpXM3/YImIiLRxTBN07S7iGiVm5tLcnIyOTk5JCUl2V1OlcrfuZaEWMCTYHcpUouFw7Bjh4vUtEgzd/PmAzdzMVxguImMXnCVaebuuzK3pJkbE2PjN1cN8vPzSUhQRkWcShkVcb4aldPcXOjeHdLTrctT/gZ/udy2cpYt9/DcS4lk7DascQiGwfDhbm64OZa4eA2vlcpRozIqEqWiIacV7Qdqpa1Ui/QdWXRurc3IpGq5XNC0aZimTcMMHhS5vqSZm5ZuNXNT0wzS0tykbXFRXFzSxI2szN22xc22LQbz5pZt5jZpYjVzW7eONHVbtIDaMnInPT2dzp07212GiByEMirifDUqp3ffHWnYnnQMXDnaljKCQXjnvTj++1kcZjgMZoDEOm5uucXDcSfW8nfMpdrVqIyKRCnlNEJNW6kW2bn5gJq2Yo99m7mDBkauN03YuTOyMjc11SAt3U1q+oGbudu3utm+1eC3eZFmLhg0bly2kVsyN7emNXOzs7PtLkFEDkEZFXG+GpPTNWvgtdes8wlx8NKztoxF2LLVxbPPJ7J+o7t0s7FevT2MuzOGho01vFYqX43JqEgUU04j1LSVauHzee0uQWQ/hgFNmoRp0iTMwAGR600Tdu1y7d34zNi7OtdN2hY3RUWwbzMXXOzc7mbn9pJm7t7RC3ubuSUN3H2buXFxdny35fNpmK+IoymjIs5XY3LaqRN8PR2uvw5uuRratKnWhzdN+HpmDP94Ix5/MWAG8HjdXH65m/MujLNzrK7UcjUmoyJRTDmN0ExbG0XTTFtzz2YM06+ZtlKjlTRz09JdpKaWNHNdpKZ7DtjMxeVi3xW5Jc3cRo3KNnFL/hsfb+M3B5imiaG/kkQcSxkVcb4ak1PThMLtkJUGyc32/s5SPXJyDF56JYG5v5VsNhameQsXd93jo31HLfSQqlVjMioSxaIhp5ppK44yb+kGBvdsYXcZIkfFMKBx4zCNG4fp3y9yvWnC7t1/XJnrIjXdTWGhK/KP9zZzd+2wTgvml23mNmwYaeCWjFto2RKqawb7vHnzGDx4cPU8mIgcNmVUxPlqTE6De8CfCckp1dqwXbjIywtTEsjKNiAcAMPgjJEerr4ulpjY2v0HujhDjcmoSBRTTiPUtBUROUqGAQ0bhmnY8MDN3NQ0N2lpsDnVsFbpprspKNi/mZux0zotXLDPal3DoEGDyMrcfVfn1vINNUVERKQyFRfDRx/BRaOgaBe4fOCqnj8H/X74zzvxfD4tFkxrs7Hkum7G3O5h0FBtNiYiInIgatpKtUhpVNfuEkSq3b7N3H59I9ebJmRmWpuebd5skJa+d2Vumpv8kmZu6agFF7t3WadFC8s2c+vXL9vILVmdm5h4ZPWmpKQc3TcsIlVKGRVxPkfn9Mkn4fHH4bW/w4v/B516V8vDbtrsZsKLiWxOde3dbAz6D/Bw+x2x1Ktffat8RcDhGRURQDndl5q2Ui0S4/UOukgJw4AGDUwaNAjSZ5+/l0wTsrKsTc9SU61m7ubUgzdzMzOs0+KFketKmrl/3PysVSuoU+fA9WzdCjNnwsaNDWnbFk45BZo1q+InQUQOW+KRviMjItXGsTldsgSeeso6P3seFFb9Q5omfDE9hjfejifgN8EM4PW5ufoaNyPPjtVmY2ILx2ZUREoppxFq2kq1WLd5Bw0001bkkAwD6tc3qV9//2ZudnakmZuatnfMQpqbPXklq28jm6BlZrjJzHCxZFHZZm7duvuPWdiwASZMgJ07oajIRWwsvP46PPwwDB9uy9MgIgexbt06GjRoYHcZInIIjsxpMAjXXGP9F2DsddC7alfZZmYavDAlkUVLvGAGwTRp09bD+Lt9tG6rP0HFPo7MqIiUoZxG6IgpVeORR8Dthgcf3P9rf3seQmF44M5qL0ukJjIMqFfPpF69IL17Ra43TWsH5tQ0t9XITYPUNDebUw/czM3OdJOd6WLpYuu6oiIXCxcZhELQsCHExYVo0wbS0+HRR6FbN2ja1J7vWURERCrJxImwYIF1vkt7uG98lT7c3N+8vDglwfpdJBwAw8U557m54i+x+GK0vFZERKSi1LSVquF2w0MPWecffJCu7fd+1vpvz8PjE+DBqv1lUSQaGAbUrWtSt26QXj1Lrg0AZZu5qalWMzct3U1ObqSZu2unl+IiL/EJJnv2GJhmHHv2mKSkGOzYAd98A1deadM3JyL76dq1q90liEg5HJfT33+3Pj4D4HLB35+F2NgqeaiiInj9P/HMmBkLZgjMIPUbuBl3h5c+/X1V8pgih8txGRWR/SinEWraStUoWWG7t3G766QhJH3+GTwzxWrY3jvOxuJEar/kZJOeyUF69ii5JtLMTUu3mrn/fAPS0j34PGECQQiHTAJ+SEszKCoy+Okng8suA4+OFCKOsGPHDpKSkuwuQ0QOwVE5DYfh2muhuNi6fNMVMHhwlTzUuvXWZmNbtrr2rq41GHqMh1tvjyUpWZuNiXM4KqMickDKaYT+FJeqs0/jtt0jLusXx47toEF9SNsCLZvbW59IFEpONklODtKjO+zK8LBydQzt24Uo9sO6DSEKC1yYYZNQyMX8+SY33uji0kvhxBOtBfQiYp/MzEy7SxCRcjgqp3//O/z8s3W+bUt4+IFKf4hwGD7+LJa334sjFLQ2G4uJdXP9DW5OOU2bjYnzOCqjInJAymmE3vaUqvXgg+DzYYTD1uW1G2Ds/dBlEAw4Cf7vSfhpDgQC9tYpEoVOGV5M40ZhUtPcxPigVYsiunUJYRgGMd4wjeoVsGNrES88H+KWW+Cnn6w5uiJiD4+WvYs4nmNyumkT3Htv5PKUZyAhvlIfYtcuFw88Uof/vBNPKBgCM0THTm5efCmGU09Xw1acyTEZFZGDUk4jDNPUn+B2yc3NJTk5mZycnNq79Pvxx60RCa69K20PJjkJTv4T3HY9DOxXffWJRLlZ3/t49K912JnhwsBqyjZuHOaaKwpYv8Fg0WI3YIDLAy4vbdq6GT0aBg1Cf4yJiIg4VXY23HEH/PvfcNXFMPm5Sr37n37xMeW1BPLzgXAAw+XmwgtdXDo6Fo9XvyCIiIgcSkX7gWra2qjWN21LGraPPca8ESMYNGOGtRHCScMgPx/m/bb/sr2P/w2nnhLpBvn91kBNlxaFi1SVbdtcfDMrhvlLMxnQqz6nDi+maVPrTZblKzy8/W4MK1a6rFwaXnB56NjJat727avmrUh1mTdvHoMGDbK7DBE5BEfltCgDvv4UBh1nLZCoBAUFBq/8M57v/xezd7OxMI0au7jjTh89ensr5TFEqpKjMioiBxQNOa1oP1CdMKka+zRsefBBTNOMXP7uexh5JuzcCW++CZdcBPXqQnwcHDcQAtngz4JgAbzzAbTvBzeMg4+/gJxcu78zkVqnadMwV44uZPSl6Vw5urC0YQvQo3uQpx7P57GHCunUIQThYggVsvb3Yh5+KMR998Hy5TYWLxJF9D67iPM5JqfBAvDvhpOGV1rDdtVqD2PGJ/H9/3zWZmOYnPAnNy/9PU4NW6kxHJNRETko5TRCgyKkaoRCpQ1bgEaNGlnXl2xOFgpBw4Zw+eXWKRiEtWuhQUcIFVmnYC7MmAk7d8HbH1gnjweGDoQRw+G04dClo5b5iVSSRg0P/EedYUDfPkH69A4yb76Xt6f62LQ5DEaAFct83Hevhz59XYweDZ07V3PRIlGk9FgqIo5la05NEzIzrcUQxbshHAJfzFHfbSgE730Yx/v/jcMMh8EMEJ/g5qabPZw4/OjvX6Q66Vgq4nzKaYTGI9io1o9H2EdWVhb16tU7vH9kmjD6z/Dp51BQcODbtGphNW8vHQWD+h99oSJRLCsnj3rJieXezjThlzk+3n7Xx5YtgOEClw8MD4MGu7jsMmjXrurrFYk2R3QsFZFqZWtOP/gArr8ennoELhkOvnrWMfoobNvmYuKkRH5f67aawJh07eZm/N0xNE5xV0rZItVJx1IR54uGnGo8gjjKmjVrDv8fGQa88y7s3g1ffw1jboMOf+gEpabDa/+BOXMrp1CRKLZmw7YK3c4w4Lhj/Ex5IY9xY/w0aRzeu0K+kHm/+rl9TJinn4a0tCouWCTKHNGxVESqlW05zciAW2+FnBy4eRz8suSoGramaW1WOuauZH5f44ZwEJfbYPTlHp56Nl4NW6mxdCwVcT7lNELjEcT5YmPh1FOt04uTrDEKX34J06fB/36yNis79TjwZwIucMfA/BVw83g49SRrJe4xg8CrWVsilcnthpNO9HPCcX6+/S6G9z+CjIwQGG5+/p+XX372cOIwF5deCk2b2l2tiIhILTZ2LOzaZZ0/82QYNuyI72rPHoO/v5bAz3N8ezcbC9G0mYc7x3vo3M1XOfWKiIhIuRy70vZvf/sbhmEwduzY0uuKioq45ZZbaNCgAYmJiYwaNYodO3aU+XepqamMHDmS+Ph4GjduzF133UUwGCxzmx9++IF+/foRExNDhw4deOONN/Z7/ClTptCmTRtiY2MZPHgw8+bNK/P1itQiEZ0rc9Blx44wbhzM/NZahTt9OvQeBgmtwFffus306bB6LUx6Fc64CFr1hMuugzffh+07K68WkVqkc/tmR/TvPB447dRiXp2cx/XXBKibHIJQEWawkO9nBbjxBpPJkyN/S4rIkanUY6mIVAlbcjptGrzzjnW+bhK88Lcj3vNh6TIPt92ZzM9zvKWbjZ1yqocXJ8epYSu1go6lIs6nnEY4smn722+/8eqrr9KrV68y148bN44vvviCDz/8kB9//JGtW7dy/vnnl349FAoxcuRI/H4/s2fP5j//+Q9vvPEGDz30UOltNm7cyMiRIxk2bBiLFy9m7NixXHvttXz99delt3n//fe54447ePjhh1m4cCG9e/dmxIgR7Ny5s8K1SFmZmZlVc8eJiXD66eCJAW8SxKdAQhvYXQSufX68c/fAp9PhpjugfV847nR4YgIs1rb3IiUys/OO6t/7fHDWyGL+8fc8/nJ5gDqJYQgVEg4U8vVXAa6/zuS116w9UkTk8FXZsVREKk215zQnB264IXL5qf87oo+3BIPw7zfj+L/Hkti9GwgHSKzj4r77vIy5I564eG38K7WDjqUizqecRjhuI7K8vDz69evH3//+d5544gn69OnDCy+8QE5ODo0aNWLq1KlccMEFAKxevZquXbsyZ84chgwZwldffcWZZ57J1q1badKkCQCvvPIK99xzD7t27cLn83HPPfcwbdo0li+PNOsuueQSsrOzmTFjBgCDBw9m4MCBTJ48GYBwOEzLli257bbbuPfeeytUy4EUFxdTXFxcejk3N5eWLVtGxUZkc+fOZfDgwdX7oLt3w4wZMP1LmPE1ZGbtf5vLL4JXnq/eukQcau6itQzu27HS7q+gwOCzL2L49AsvBQUmGB5wefHFejjzTINRo6CWv/SJVCpbjqUicliqPac33ACvvWadH34cfPbeYa+yTd/i4tnnE9mwKbLZWK/ebsbdGUPDxppdK7WLjqUizhcNOa3oRmSOm2l7yy23MHLkSE4++WSeeOKJ0usXLFhAIBDg5JNPLr2uS5cutGrVqrRROmfOHHr27FnasAUYMWIEN910EytWrKBv377MmTOnzH2U3KZkDIPf72fBggXcd999pV93uVycfPLJzJkzp8K1HMhTTz3Fo48+ut/18+fPJyEhgX79+rFq1SoKCwupU6cObdu2ZenSpQC0bt2acDhM2t6dffr06cO6devIy8sjISGBTp06sWjRIgBatGiB2+1m8+bNAPTq1YtNmzaRm5tLbGws3bt3Z8GCBQA0a9aM2NhYNmzYAECPHj1IT08nOzsbn89Hnz59SkdDpKSkkJiYyLp16wDo2rUrO3bsIDMzE4/HQ//+/Zk3bx6madKoUSPq1atXOkA6GAyyYcMGdu3ahcvlYuDAgcyfP59QKESDBg1o3Lgxq1atAqBjx47k5uaWjpsYPHgwCxcuJBAIUK9ePZo1a8aKFSsAaN++PQUFBWzbZm2gNGDAAJYvX05RURHJycm0Ou88lnXoALfcRsesLDxfz8D99Tck7K1rc4+ebF+4gsT4WNq3bsLyeb/T6f4H4dRhFA87gQ2J9cAw6N2tDetTt5OXV0R8fAxd2jVj4fKN1vPdtD4ej4dNadZK7J5dWpG6NYOc3AJiY7306NSK+UvXA9C0ST3iY32s32x9b907tWTrzkyysvPx+jz0696WuYvWAtCkUTJJiXGs3bjder47NGfn7lx2Z+3B7XExoGd7fluyjnDYpFGDJOrXTeT39VsB6NSuKVm5+ezKyMVwwaDeHVmwbD3BYJj69RJp0rAuq9amA9ChTQp5BUVs35kNwKA+HVi8chN+f5C6yQm0SKnP8t+tn7t2rZpQ5PezdbvVAO/fqx0r1qRTVOQnqU4cbVo0Zukq6+eudYtGhMJh0rfuBqBvj7as2bCV/IJiEhNi6dAmhcUrNgHQslkDXC4Xm9Otz8/36tqajWk72ZNXSFycj64dWrBwmfUz2jylPj6fh42pkec7bWsG2bkFxMR46dWlFb8tsZ7vlMZ1SYiPZf0m6zns1qkF23dmk5mdh9frpl+PdsxdvBZMaNwwmeSkeNbu3YyrS4fmZGTmkpG5B5fbYGCvDvy2dB3hkEnD+nVoWD+J1eu2WD+z7ZqSk1vAzowcMGBwn44sXL6BQCBE/bqJpDSuy8o11vPdvk0K+fs83wN7t2fp6lSKiwPUTYqnZbOGLFudCkDbVo3x+4Ns2W6909ivZztWrUunsNBPncQ42rYs+3yHw2HS9j7ffbq3Yd2m7eTlF5EQH0Onds1YVPIz26wB7j8835vSd5KVm8+SVZvp3qkFC5Zaz3ezlHrE+nxsSLV+Znt0bkn69kyyc/Lx+Tz06daGeYvXlT7fifGxrNv7fHft2IIBg7fSpEUhP/3UiGVLmrEjIx8Tg7ffiuHTT2Po1y+VP/0piz59OpKZmVn9rxGtWrFs2TIA2rRpQzAYJD3d+n/Vr18/Vq9eTUFBAYmJibRv354lS5YA0KpVK8AayQPQu3dv1q9fT15eHvHx8XTp0oWFCxdaz3eLFtZrxCbr571nz56kpqaSk5NDbGwsPXr0YP78+QA0bdqU+Ph41q+3foa7d+/O1q1bycrKwuv10q9fP+bOtTZebNKkCUlJSaxda71mdO3alZ07d7J7927cbjcDBgzgt99+IxwO06hRI+rXr8/vv/8OQKdOncjKymLXrl0YhsGgQYNYsGABwWCQ+vXr06RJk9Lnu0OHDuTl5bF9u/X/ddCgQSxevBi/30/dunVp0aJF6Ruh7dq1o6ioiK1brdei/v37s2LFCoqKikhKSqJNmzZljmuhUKj0+e7bty9r1qwhPz+fxMREOnTowOLFiwFo2bKl9Rqxz3Ft48aN7Nmzh7i4OLp27Vr6fDdv3hyfz8fGjRtLn++0tDSys7OJiYmhV69e/Pbbb9bPbEoKCQkJpc93t27d2L59O5mZmfs9340bNyY5Obn0+e7SpQsZGRlkZGSU/syWPN8NGzakYcOGrF69uvRnNicnp/QTO/v+zNavX5+UlBRWrlxZ+jObn59f+nwPHDiQpUuXUlxcTH5+PgUFBaU/s23btsXv97Nly5bSn9na+ntE586d9RqBXiNqwmtEVlYWc+fOrZbXiKQFC+i6t2Ebiotj09130bTIX+HfI9q0aMyr/97D51+m4HWHMc0AgWCQ08/I4Pax7Vi/fjXrN+o1Qq8Rtes1Iisri8LCwqj8PaJu3bq0bNlSv0foNcLxrxG5ubnMnTu3Vv8ese+CzkNx1Erb9957jyeffJLffvuN2NhYTjzxxNKVtlOnTuWqq67a7xsbNGgQw4YN4+mnn+b6669n8+bNZUYdFBQUkJCQwPTp0zn99NPp1KkTV111VZmm7PTp0xk5ciQFBQVkZWXRvHlzZs+ezdChQ0tvc/fdd/Pjjz8yd+7cCtVyING80tZxtm615t6OOhsSfBDMh2ABfPApXHd35HYtmsGIvZuZ/ek4SIi3rWSRmi472+CjT2KYPsNLIEDpytvEJDfnn29w1lnWvoMiIiJSjvx86NUL9jY6mPAI3HRdhf95To7BpJcTmDe/ZLOxMC1buRh/t492HbR5r4iISFWq6Epbx8y0TUtL4/bbb+edd94htpb+1R4TE0NSUlKZU7QoeWfHMZo1g2uvhXqNwVcX4ptDYhtYmVb2dulb4fW34cKroGUPOOcyePlfsGGTDUWLVK35y9ZX6f3XrWty7VVFvDYln9NHBHG7ghAqJC+niDffCHLttSaffQZ+f5WWIVJjOe5YKiL7qbacrl1rNW4BjukPN1xT4X+6YJGXW+9IZt78yGZjI8/08PykeDVspdbTsVTE+ZTTCMc0bRcsWMDOnTvp168fHo8Hj8fDjz/+yKRJk/B4PDRp0gS/3092dnaZf7djxw5SUlIAa+lxyRL2fb9e8rVD3SYpKYm4uDgaNmyI2+0+4G32vY/yapGyQqGQ3SWUz+WF5yZZvwS/8AKcejLExES+XlwM3/4A4x+Eq2+1q0qRKhMKhqvlcRo2DHPzDYW8Ojmf4ScFMUyreZuTWcQ//xHkuutMpk+3NkURkYgacSwViXLVltM+fWDJr3D5+TB5QtkNeA/C74fX/hXPI0/WITsbCAdIruvioYe93HhrHDGx2mxMaj8dS0WcTzmNcEzTdvjw4SxbtozFixeXngYMGMBll11Wet7r9TJr1qzSf/P777+TmppaOsZg6NChLFu2rHTWC8DMmTNJSkqiW7dupbfZ9z5KblNyHz6fj/79+5e5TTgcZtasWaW36d+/f7m1SFkNGjSwu4SK69ABbr8dvp5pbWb2+edw/bXQskXkNicfA/5Ma6xCOACmCTePhzemwrbt9tUuchQa1KtTrY/XpEmYsbcW8vJL+ZxwfAjCQQgWkrmriJf/HuKG602+/RZ0zBax1KhjqUiUqrachvwQH4LJf4POncq9+cZNbsbdk8wX02Os460ZZsBAN5NfjmPgkJhy/71IbaFjqYjzKacRjppp+0f7zrQFuOmmm5g+fTpvvPEGSUlJ3HbbbQDMnj0bsLrxffr0oVmzZjzzzDNs376dyy+/nGuvvZa//vWvAGzcuJEePXpwyy23cPXVV/Pdd98xZswYpk2bxogRIwB4//33ufLKK3n11VcZNGgQL7zwAh988AGrV68u3eSsvFoqoqIzLGqD3Nzcmv89miasWAFffgFnnAqd2kBwD4SLYflKOPb8yG1794jMwh3QF9zaeVecL3dPAUl17JvbvGmzm3fei+HXuXvz4vKCy0uz5m4uuwyOP/6wN8QWqVVqxbFUpJarlpyaJhTtgOIM8NUv96afT4vljbfjCAZMMIP4YtxcfY2bM86K1XFVoo6OpSLOFw05rXEzbSvi+eef58wzz2TUqFGccMIJpKSk8PHHH5d+3e128+WXX+J2uxk6dCijR4/miiuu4LHHHiu9Tdu2bZk2bRozZ86kd+/eTJw4kX/+85+lDVuAiy++mAkTJvDQQw/Rp08fFi9ezIwZM0obthWpRcoq2RmwRjMM6NED7r0PevWH2AaQ0BoS2sAvf/j+liyHZybBSedA295w9W3WJmeZWXZULlIhq9ZtsfXx27QO8cA9BTz3TAH9+4WsVezBQramFfHsMyFuuw3mzLH+ABWJRrXiWCpSy1VpThcvhgsvhLR1UJwJnkN/QiYz0+Chx+vwzzfiCQZCYIZo287DC5NiGHm2GrYSnXQsFXE+5TTC0Stta7toWmk7d+5cBg8ebHcZVScUgvnzrVW406fDwkUHvl39erBpiVbeiiPNXbSWwX072l1GqZWrPLw11cfyFW7rTRPDCy4PHTq6GT0a+vXTyluJLrX+WCpSC1RZTgMBGDwYFi2Cuknw6Rsw8OCPM2eul5deTmBPnmGNQzBcnHe+i8uvjMXr08FTopeOpSLOFw05rWg/UE1bG0VT0zYzM5P69Q/98a1aZds2+OormPYFzJwFe/ZY1583Av41EVyx4PaB4YYp/4RWLWDY8ZCYYG/dEtUys/dQv271zrUtj2nC0mUe3poaw+9rDDBc1tgEw0PXblbztlcvu6sUqR5RdywVqYGqLKdPPQX332+d79IBZn9TdsPcvYqK4B//TuCbWTFgWqtr6zfwMO4OD336+yq/LpEaRsdSEeeLhpyqaVsDRFPTdtOmTbRp08buMuzh98Mvv8C0L+HYwXD6iRDYA2E/5OdBu+Og2A8+Hxw3JDILt0M7uyuXKLMpfSdtWjS2u4wDMk2Yv9DL21N9bNjospbYunxgeOjV28Xll0OXLnZXKVK1ovpYKlJDVElOV6+GPn2guBhcLpj1MQwauN/N1q5zM+HFRLZuc+1dXWtwzDEGt94eR52kGjUVT6TK6Fgq4nzRkNOK9gM91ViTRLEdO3bU+tAdlM8Hw4ZZpxIxDSFUDN99ZjVswWrufvc/63TPI9C+DYwYDqedDMcNPuBqCpHKtGNXjmObtoYBA/sHGNAvwOxffbzzrpe09CIwXCxd7OOuJR4GDHQxejS0b293tSJVI6qPpSI1RKXnNBSCa66xGrYAN1+5X8M2HIaPPoll6gdxhIImmAFi49xcf4Obk0dodq3IvnQsFXE+5TRCTVsROxgu8MTBiLPhyy/hy89h+leQmha5zfpN8PfXrVNCPKyaCw1q90cERMpjGHDsUD9DB/v58Scf737gY9u2IjDczJ/nZf5vHo451sVll0GrVnZXKyIicpSmTIHZs63z7VrBQ/eX+fLOnS6eeymBFau81upaTDp1dnPnXTE0a6E/9URERGoyjUewUTSNR5AKME1YudIaozB9OvwyG4JB62tdOsCcz8EdA64Yq3P19XdQJxEG9QOPfimX6BQMwnc/xPDuB14yMrDmRLu8GC4PfzrRxaWXQrNmdlcpIiJyBDZuhB49oKDAuvzVu3DCCaVf/t/PPv7+jwTy84FwAMPl5qKLXFxyWSwer5bXioiIOJVm2tYA0dS0XbhwIf369bO7jJolJwe++cbazKxjOxh3A4TyIeQHTBhyDvy+HurVhZNPtGbhnjIMGmo1rhyZhSs20q97W7vLOCKBAHw9M4YP/usjK8vc27z14XJ7GH6ywSWXQGNnTn4QqTAdS0Wcr9Jyappw6qnw7bfW5WsugUkTAcjPN3j19Xi+/19ks7HGTdzcOd5Lt57abEzkUHQsFXG+aMipZtqKowQCAbtLqHmSk+HCC61TiXAIwkWwbrXVsAXIyoYPP7VOhgED+1obmZ06HPr0QIPMpKIC/qDdJRwxrxfOPKOYU4YXM31GDB9+bLBnTyHhsIeZX3v5/jsPI04zuOgiqOUbkUotpmOpiPNVWk5nzow0bJunwOMPA7BylYeJkxLYucsF4QAYBicO83DjLbEkJGqzMZHy6Fgq4nzKaYSO7FIt6tWrZ3cJtYPLDZ4EaNYR/v1vuOB8SN7nXRnThHkL4bFn4bjToEN/WL7KvnqlRqlXN8HuEo5aTAycd04xr7+yh9GXBkmID0GokGBxIdO+CHDddSb/+pe1kF2kptGxVMT5Ki2np5wC774FjRrApKcIJiTx9rtx3PtQEjt3GhAOEJ/gYvxdXu68J14NW5EK0rFUxPmU0wiNR7BRNI1HyMvLIzEx0e4yaqdAwNqgYtqXMG0arNynSRsbAxvnQmIyGF5r1e3K38Hthk7ttQpXysjLLyIxIdbuMipVXp7BJ5/H8PmXXoqKTDA84PISG+/h7LMNzjsP9NIkNYWOpSLOV2k5DYegYAvk7GJbUXMmvJjImnVu63pMunW3NhtrnOI++scSiSI6loo4XzTktKL9QL0lK9VixYoVdpdQe3m98Kc/wTPPwoqVsGkT/H0KjDzdOtWpD2E/BLLBnw1PPAP9/gQ9j4XxD8I330NRkc3fhDjBijVpdpdQ6RITTS7/cxH/fDmP884J4vOGIFREUV4hH7wX5NprTd5/HwoL7a5UpHw6loo4X6Xl1J+NGchl5sJWjLkrmTVr3RAO4vYYXH6Fh6eejVfDVuQI6Fgq4nzKaYRm2orUNq1bw003WyfTtFbThgMQKoLCHPj+Z+t2GzfDy/+yTnGxcOJx1izcEcOhZXN7vweRSpacbHL1lUWce1YxH/w3lq9nQjBYSH6uh7ff9PLZZ24uvNDgjDOsEQsiIiLVLiMDfvoJzjqNPbszmfyPZsyeF793s7EwzZpb4xA6dtFmYyIiItFA4xFsFE3jETIyMmjYsKHdZUh+Prz8Mkz7An6eDcGDbDzVrQs8/yQcN6R66xNbZWTm0rB+7X4tKrFzp4v3Poxh1vcewmHAZY1NqN/AzUUXGZx6qrWIXcRJdCwVcb6jyulll8HUqWQPG8mDdZ9nU1ELCAfBMDj1VBfX3RhHbJxGW4kcDR1LRZwvGnKq8QjiKAUFBXaXIAAJCTB+PHz/I+zeDR9+CFf9BVKalL3dytVQN876Q6HErt2wM6Nay5XqVVDkt7uEatO4cZgxtxTy90n5/OmEEIYZhGAhmbuKeOXlEDdcbzJz5sHf1xCxg46lIs53xDn94guYOhUA90+/kJ3thnCAOkku7rvfy23j4tWwFakEOpaKOJ9yGqGmrVSLbdu22V2C/FFSElxwAfzr37BlKyxYAI8+AoMHQZvW0LULhArAnwmBXHj1dWjXB/50Jvz1OVi4BGuJotQW23Zk2V1CtWveLMz4sQW89HwBxwwJWW9UBAvYtaOYSS+GuPlm+OEH/aiLM+hYKuJ8R5TT7GyC191YevEfXZ4i29eYPn09vDQllmOO19wekcqiY6mI8ymnEZppKyLgckG/ftbpoYetjcliYqwNzEJFEMyDr7+3ZuTOX2SdnpwIjRvBqcOsWbgnnQDJ0fHReql9WrcKcd/dBaxb7+ad92KYvwAIB9mW7mHiBC8ffOBm9GgYOtQaEy0iIlIZTBPSLrmLVju2ArCg4cn81Ho01/zFzTmj4nTMERERiWKaaWujaJppGwqFcLu1w22NZZrwwP3w5ZewbPmBb+PxwDEDYezNMOKk6q1PKkUoFMbt1gcwAFat9vD2uzEsXeayurSGF1we2rW3mrcDBqh5K9VPx1IR5zucnGZnwxdjZ3H5f04GoMCdyJMXzePaxzvQtr0Gq4tUBR1LRZwvGnKqmbbiKMuXH6TRJzWDYcBfn4KlyyA1FV55Bc46E+LjI7cJBuF/cyAnE8x9PkteXAyFhdVfsxy25WtS7S7BMbp2CfLko/k8+WghXTqFIFwMoUI2rCvmsUdD3HUXLFlivZ8hUl10LBVxvormdP58uPPGfE758LrS6xac/wgP/7uLGrYiVUjHUhHnU04j1LSValFUVGR3CVJZWraEG26Az7+wNjP7+mu47VZo3xbcbhh+PARz987CzYNpX0GLHnD+5fDaG7A5ze7vQA6iqChgdwmO06tnkGf+ms8jDxbTvm0IQn4IFfL7qmL+74EwDzwAq1bZXaVECx1LRZyvvJz6/dZ7348+CmfPvZ+Ugo0A7Ok9lOPfG4cvRh/jEKlKOpaKOJ9yGqGZtlItkpOT7S5BqkJsLJx6qnWa9BKkp0PzZhAqhnAR+PfAjFnWjNyvv7NOPABdO8GpJ1mzcIcOBK9WlDhBclJ8+TeKQoYB/fsG6NcnwK/zvLw91UdqWhiMAMuW+Lh7qYf+A1xcdhl07Gh3tVKb6Vgq4nyHyumGDTBhAqSlmXTZ/RNnbXoJADMmhjrvv27tMSAiVUrHUhHnU04jNNPWRtE007agoID4eDWEotI9d8Pbb8PWg+wAmVQHhp8Aoy+C006u3tqkjILCYuLjtEN1ecJh+Hm2j3fe87F1K2C4weUFw8PQY1z8+c/Qpo3dVUptpGOpiPMdKKemCZ9+Cm++CcFAGMJ+mgQ382TWbTSZPxP+9gTc84A9BYtEGR1LRZwvGnKqmbbiKMuWLbO7BLHL089A+hZYtAgefwyGDim7kiR3D3wyDebNLzsg1DSt7phUm2WrNdO2IlwuOOE4P39/MY8xtwRo1DAEoSIIFTLnFz9jbgvz7LOwZYvdlUpto2OpiPP9Mae7d8ODD8K//gVBfxBCRbRrlcfDkxJo8s1E+PhtuPMem6oViT46loo4n3IaofEIIlL1DAP69LFO//eg9RfMjBkw/UuY8TVkZsGpJ0Ag27q9KwbWbIbTL4ZTh8GIk+DkE6GuPiYhzuF2wynDiznxhGJmzvLx/kcxZGYWYYbd/O8HHz/9z8Pwkw0uvRQaN7a7WhERqW6zZ8PkybAn1wQzgBEu5rwz8xh9WRivkQ/uRDjnYnDpTzIRERHZn8Yj2CiaxiPs2LGDJk2a2F2GOFEoBPPmwcD+QACChRDcAy+8Ag8+E7md2w1DBsCI4dYs3G6drWawVJodGTk0aajG+JHy+2H6jBg+/NhHbq65d2yCD4/Xw6kjDC66CBo0sLtKqcl0LBVxrq1bYeZMWL9+D61a1WHbNuvXG8wQhP00qFvEHTdl06t9ESTFQygf4luCt47dpYtEFR1LRZwvGnJa0X6g3taVahEMBu0uQZzK7YahQ/de8IEnAcwG4PdCQgLk51tfCoXgl7nW6aG/Qsvm1grcs06Hk/9kW/m1iXJ6dHw+OPfsYk47tZjPv4zl488M8vMLCYY9TP/Sy8yZHs44w+DCC0Gz9eVIKKMizvTtt/DYY7BzJxQWxpGTA263SacOIRrWL+LYQfncclOQOq+8Ahf9BybeD+ddDJ5Eu0sXiTo6loo4n3IaoZm2Ui3S09PtLkFqEsOAx56wxijMnAljb4eOHcreJm0L/PMt+Neb9tRYC6Vvy7S7hFohNhYuuqCI11/J45KLgsTGWDNvA4WFfPZJgGuvNXnzTdizx+5KpabRsVTEebZutRq2u3dDXBzk5YXx+UwCfpN16+Dyi/O45+4QdbashadegO074PJxkJapTwyJ2EDHUhHnU04j1LQVEeeKiYGTT4bnX4A1a2HtWnjhBTj1ZGtZI8Apx4M/E/zZECqEgnw4ZgTc+yh8/5P1mXURGyQkmFx2idW8Pf/cAD5vCEKFFOUV8uH7Qa691uS996CgwO5KRUTkSOzZAy++CKtWWU3brVutfVQNQjRsECQ52aTQH4MRDsHNd0Z+Jxl7K3Tqam/xIiIi4niaaWujaJppGwgE8Hq9dpchtUl+Pnz3HQzqD/XrQLAAgnnwzbdwwY2R29VJhJNOsEYpnHoSNK3ds3GORiAQxOvV1Jyqkplp8NEnsXz1tYdgEGvjGcNLnWQ3o0YZjBxprdIVORgdS0Xst3MnzJ0Lv/4Ky5fD2rUmqanWG3WYJhCmedMQzZqarN/o4eorCrjL+wLc84h1Bx3awZJlEB9v43chEr10LBVxvmjIqWbaiqOsXr2anj172l2G1CYJCXDWWZHL3joQbggbs8HlgnDYun5PHnw23ToB9O5hbWQ24iSr4auPJpZavWErPTu3sruMWqt+fZPrrynkvLNdvP9RDDNnQTgUZE+2hzf+7eXTT91cdJHBaadBLf8dRY6QjqUi1c80YfNmq0k7Zw5s2ABgghkGM4TPY4LpweMKU79emLiEQpo0iiUcNjBNaMcGePTpyB2+9poatiI20rFUxPmU0wg1baVaFOjzv1IdXG4Yfw9ccz3MmAHTv4QZX0PG7shtliy3Th9/CYv/Z1+tDlRQUGx3CVGhUaMwt95UyKhzXbz7YQw//AhmMEj2bg+vverl44/dXHyxwckng0dHadmHjqUi1SMctkYe/Pqrddq+nb2raENWszYcADNM05QAw44NMfXDJIqKXbRqZZKzJ0Q4DKlpbho3CnHmtDFQUGjd8Q3XwrDhdn5rIlFPx1IR51NOI/TnoFSLxETtjivVqF49uPRS6xQKwfz58OUXMH06LFxk3eaU46xZuIYHXDHg8sEN46BjOxgxHHp2i7pVuImJ+mx+dWraNMwdYwq58HwX77wbyy9zgHCQjB1epkz28t//uvnzn+FPf7IWj4voWCpSdfx+WLzYatLOnQu5uexdTWutqMUMghmmY/tihgwMMnRomBYtrF8Vevfew6N/rcP6jW78/jgyvG4aNw7zat+XiZn8s/UALZvDMxPt/BZFBB1LRWoC5TRCM21tFE0zbYuKiojVsEZxgm3b4KuvoE8P6NHZmoMbLLA++9jrlMjtmqVYzdvThsOJx0Fign01V5Oi4gCxMfpcvl02bHTz9rsx/DbfDRjWzFuXlxYt3Vx2GRx7bNS9jyB/oGOpSOXas8d6X/fXX2HBAiguZp8mrdWodbvC9OxWzJBBQQYPMmnY6MD3tW2bi29mxbBlGzRvCqd120iTkSdC7h7rBtO+gDPOrK5vTUQOQsdSEeeLhpxWtB+opq2NoqlpO3fuXAYPHmx3GSIHFg7AW2/CX6498Nd9PjhuSGQWbod21VtfNZm7aC2D+3a0u4yo9/saq3m7eElJ89YLLg9t27kZPRoGDlTzNlrpWCpy9DIyrNm0JRuJhcPmPitqg2CGiI0J0b93MUMGhxjQ3ySxTsXvv/RYOvMHuPwGa7b+FX+G/7xTZd+TiFScjqUizhcNOdVGZCIiFeXywpXXwPHDYNo0axbu9z/uXXKD9ZnJ7/5nnR78K6SvgPg4e2uWWqtzpxCPP1zAsuUe3poaw6rVJpgBNq7z8vhjHjp1dnP55dC7t5q3IiLlMU1ITY3Mp123DvbdSIywNfYgOSnI4AFWo7Z3b+v92qNyyonw62fw15fh+UlH/42IiIhI1NFKWxtF00rbbdu20bRpU7vLEKm4ggL4/nv48nOY/hWkplnXDz8WPnoVDC+4Y6yG76RXoU4inDoMmjezt+6jsG1nFk0b17O7DNmHacKixV7eftfH2nUGGC7rZ87w0qOni9GjoXt3u6uU6qJjqUjFhMOwenWkUbttGwfdSGzIwABDB4fo3KVy5oeXHktDhVZTOKEVuGv3RzxFahIdS0WcLxpyqpW2IiJHIz4eRo60TqYJK1fCtC+hXWuIawqBPRAugqIsePoFyM61/l3PbtYIhdNOhkH9wO229duQms0woF/fAH37BJg338vbU31s2hwGI8DypT7uvcdD335W87ZTJ7urFRGxj98PS5ZYow/mzYOcHA64kViHdn6GDAwwZEiYVq0q4RMLT04EtwvuHRe5zgxbTdvnp4Lhg0ceOcoHERERkWikpq1Ui9TU1Fr/TonUYoZhLWfcd0mjrx6E/bDox0jDFmDZSus0YTLUrwvDT7Rm4Z58IjSsX82FH57ULRlaaetQhgGDBwYYNCDAz7N9vPOejy1bisBws2iBl0ULPQwe4uKyy6BtW7urlaqiY6lIWXl5ZTcSKyriDxuJhXAZoTIbiTVqXMlFuF3w+ATrfM/uuN/6CF56EP75ITwxER57rJIfUESOho6lIs6nnEaoaSsiciQMwxqPcPzJ1pKeL7+A6dNh/oLIbTKz4cNPrZNhwOL/1dpNzKR6GAYcf6yfY4b4+eF/Pqa+72PnzhAYbubO8TL3Vw/HHW81b1u0sLtaEZHKl5EBc+dajdplyyAU2n8jsRhfyUZiQQb0hzpVOYWsZIXt4xMgMYHGefnw/Q+Ql281bB98sAofXERERGozzbS1UTTNtC0qKiI2VvO8JArs2AFffQXTvoCZ30LO3lW4zZrA8m+tuXbuGDDcMONbKPbDSSdYM3FtVlQcIDbGa3cZchiCQfj2uxje+9DL7t1YP1cuL4bLw7CTXFx6KaSk2F2lVBYdSyUamSakp1tjD379FdauhQNtJJZUJ7KRWJ8+lbCRWEVs2QrTvoEvv4Hvf7KG6ZZ49FF46KFqKEJEDoeOpSLOFw05rWg/UE1bG0VT03bFihV01245Em0CAZg925qFmxgPd98KwT0QKrb+0BxxOcxbDF4vHDt47yzc4dCxfSUM2Tt8K9am0b1jy2p/XDl6fj989XUMH37sIyfH3Nu89eH2eDjlVIOLL4aGDe2uUo6WjqUSLUyz7EZiW7fyh43ErBW1TRoHGDrQz5AhJl27mpWykVi5VqyGL2dYjdqFSw58G58PiouroRgROVw6loo4XzTkVBuRiaPk5eXZXYJI9fN64U9/sk4lzAZW03bnVvht7x97gQD88LN1uu8xaNvaat6OGA7HD4FqepcxL6+oWh5HKp/PB+ecVcyIU4r5cnoM//3UIC+vkFDYw4zpXmZ96+H0MwwuuADqaWxxjaVjqdRmfj8sXWo1aefOhexsImMPiKyobd82spFY69Y2vMd55U2was3+1yfVgdw9hD0eXH4/PP64RiOIOJCOpSLOp5xGqGkr1SI+Pt7uEkScwXCBJw4atIBp0yKzcDdtjtxm42Z4+V/WKT4O/vsmnHBMlZcWHx9T5Y8hVSs2Fi44v5jTR/j57MsYPv3coLAwSKDIw+efevn6aw9nnWVw/vlQp47d1crh0rFUapv8/MhGYvPnH3wjsR5drfm0gweaNG5SHYUVwHf/g98WwWP3WdeFA9abrqedEGna9u4B55wNOzPhlVfgscdYce659Pz008hoBDVuRRxFx1IR51NOIzQewUbRNB4hEAjg9WpWpsgBlXwOdNo0axbuz7OtYaUALhes+xkaNgZXjNX0XbEasrJhyADwVN57b4FAEK9X7+XVJnv2GHz8WQyff+nF7zfB8IDLR1yCm3PPNTjnHEhIsLtKqSgdS6U22L3bWkk7Z87BNxLzeSMbiQ0cUMUbiZXYmQFffWuNPvjup70dZGDRN9C6Kbi94IqFdVvg+zlw3vnQpq21ovahh0o3HSvN6R+uFxFn0LFUxPmiIaeaaVsDRFPTdu7cuQwePNjuMkRqhtxc+OYbmD4NsjPh7VcgVAChvX9A3v4ovPkh1E2Gk/8Ep55knRo1OKqHnbtoLYP7dqyEb0CcJivL4KNPYpk+w2O9H2B4wOUlMcnNqFEGZ55ZbVM45CjoWCo1UclGYiXzadesgf02EiNMnYQgg/r7GTokSJ8+EFMdH/5Yt8GaTfvlDPh1/t65uX/wt4dg3B3WRqIu3/7zGB55BNzu0sZsmZw+/jiEQtZtRMQRdCwVcb5oyKlm2oqI1FRJSXDBBdapRDgE4SIIFMLM/1nXZefAR59bJ8OA/n2sWbinDbc+slktO7JITVCvnsl1Vxdy3tku3v8ohpmzIBQKkpfj4T//9vLpp24uvNDg9NOracd1EanVTBN+/z3SqN2yhQNuJNa4UZChg4oZMjhM165W77NahMNwwkhYtPTAX2/SGM4eCWefC6eMAN8hOsiHashqha2IiIgcBa20tVE0rbTdsmULzZs3t7sMkZovGISpU2Hal9Zq3OycA9+uSWN47gk4d2SF73rL9t00Tzm61bpSM2zf7uK9j2L47nuP1UdxWStvGzR0c/HFBqecUqmTN6SS6FgqThYIlN1ILCuLA24k1q6NnyGDAgwZHKZNm2rYSKy4GFavtd7MLBEOwkVXwVffRa7r0gnOPgvOPQ8GDz3iNz6VUxFnU0ZFnC8acqqVtuIoHv31L1I5PB644grrFAxaQwGnfWltZrZseeR2O3ZCg0Rr05SSj3Pu2g0Zu6FLR+vykxPB7YJ7x+29631y+rfnIRSGB+6s5m9QqkNKSpixtxZywXkupr4Xw0+/AOEgu3d6+PsUHx995ObPf4YTT6zGlW9SLh1LxWny82HBgshGYoWF7LeRmEGI7l2KGTIoyNAh1bSRWFY2fP0dTPsavvneasBunA9uE8yANSLm7NMhOx/OPRvOHQWdOlfKQyunIs6mjIo4n3IaoWdCqsWmTZto0qQ6fksXiSIeDxx/vHX629OQlmY1b6d9CUsWw9Ch1h+n/nxrA7N334f7noTWLa0RCjm58N7H1n3dO45NaTtp0jDZatg+PgEeHG/rtydVr0XzMHffWciFo9y8814Mc+cB4SA7t3l54XkvH37o5rLL4LjjqmE1nJRLx1JxgsxMayXtr79aK2uDwQNvJNa3VzFD924klpRcDYWlbYEvv7ZOP/8a2dCzxI8/w6mngLeONZ/2hjvhxso/zimnIs6mjIo4n3IaoaatiEht0bIl3HCDdQqHrZVF4YC1gVmoEL75wbrd5jR49Q3rvMdjNWjnLyLmL1fDjC/hib0N270rcKX2a9smxP/dW8CatW7efjeGRYuBcJAtqR6eedrLBx+4GT0aBg1S81YkGm3ZYn2w49dfrVm1ZTcSCwGhvRuJWfNp+/Qxq2dzQ78fJk6BL2bAkuUHvk2DenDG6dCyByS0rIaiRERERCqHZtraKJpm2hYUFBAfH293GSLRbfJk+ORj+Olna/jgwYw8FT74d/XVJY6zfIWHt9+NYcVKl9WlNbzg8tCxk9W87dtXzVs76Fgq1cU0Yc2ayEZi6elQtlFrraht1DDI0EF+hgwO0a2bDeNUTBO6D7XejNxX29Zw9plwzvlw/AnVOqRbORVxNmVUxPmiIUBOi20AAFvpSURBVKcV7QeqaWujaGrarl69mi5duthdhogA7NkD335rjVH46ivYuq3s1yc9AX/5c2QWbn4B/O8XOG4o1Em0p2apdqYJS5Z6eGtqDGvWGtaIDZcXDA/duru5/HLo0aP8+5HKo2OpVKVgsOxGYpmZHHAjsTatrI3Ehg4J07ZtNbyBk5cP3/5gjT3YtRs+e2fvp0iKwfTD/c/Cy29Cvz5wzllWo7ZXb9veWVJORZxNGRVxvmjIqTYiE0fJyTnIDvciUv3q1IHzzrNOpgm33AIvv4xpGBimCWs2WXMJAwXW7f83By64zlpCNbAvnHicdRrUD2JibP1WpOoYBvTpHaR3ryC/LfDy9lQfGzeFwQiwcrmP++710Kevi9GjoXPl7N8j5dCxVCpbQQEsXGiNPpg/37r8x/m0+24kNniwSUpKNRS2fSd8NdNq1H7/MxQXR762aRW0aGHNpfU1grv/D+57HFq2qobCyqecijibMirifMpphJq2Ui1iq2WwmYgctieegJdfhsceY+nZZ9P744/hscegUXO4b7y1kunHudZtQyH4db51+tsLEBcLxwyGYcdbTdze3a05ulKrGAYMGhBgYP8Av8zx8c57PtLTi8BwsXihj8WLPAwcZDVv27Wzu9raTcdSqQxZWZGNxJYsOfBGYl5PiL69/AwZFGTQQJPkutVQ2O/rrCbttK9h3kLrTcU/SqoDG3Ohc5vIp0Ha1KuG4ipOORVxNmVUxPmU0wiNR7BRNI1HCIVCuKt90JmIHNLjj8NDD1lN2gcfjOT0D9fz/ffw3w/h21nw+5qD39+xg+Gbj6uvfrFFOAw//uRj6vs+tm8HDHfp2IRjj3Nx2WXWnnhS+XQslSO1ZUtkPu3vv4Np7r+RWGJ8kIH9ihkyOES/flTPRmIlcnKhVU9rRsMfNWsKZ50B554PJ50MPl81Fnb4lFMRZ1NGRZwvGnKq8QjiKPPnz2fw4MF2lyEi+wqFIo1Z9snp3suEQtZ/hw2zTmD95T9rFnz7DXz3PWzZGrm/Xh0hkGutfnL5rBmoDzwBPbpaK3GbNqnGb06qissFw/7k5/hj/cz6Pob3PoSMjBAYbn75ycvsXzycOMzFpZdC06Z2V1u76FgqFWWasG6dNfbg118hLQ0OtJFYwwZlNxKr8v26iorgh58hIxNGX2RdFw5CghuOHQA//mpd170rnHUmnDcKBg6qUTsfKqcizqaMijifchqhpq2ISLR65JGDf62kcftHzZvDFVdYp5LtxWfOhFkz4awLwJsEoQII5kLaVnjh5ci/7dopMg/3+KGQXLs/YVDbeTww4pRihv2pmK9nxvDBfyE7O4QZdvP9LB8//uDh5FMMLrkEGjWyu1qR2i8YhOXLrUbt3LmwezeH3EhsyOAw7dpVQz80MwtmzLJGH3z7g7W5ZYP6cMGp4AqD4bHm0958M4w8x2rUduhYxUWJiIiIOJ/GI9gomsYjpKam0qqVMzaIEJEDq7SchkMQLoY3/g3X3Xrg27hc0K83DNvbxD1uSDUs8ZKqVFQE076K4b+f+tizx7QaMS4vHq+H0043uPBCqF/f7iprNh1L5Y8KC2HBAms17fz5kJ/PATcS69rZz5CBQYYMCVfPCvjNaVaT9ssZ8Mu8yCc39vX1h3DiyVbD1hVTo1bTHopyKuJsyqiI80VDTivaD1TT1kbR1LTNyMigYcOGdpchIodQ6TktKrKWfH07E779FuYvsAai/lFsDGxZWc0DFKWqFBQYfP5lDJ987qWgINK89cV6OPNMg1GjoJYf8qqMjqUCkJ0N8+ZZL6+LFx9sI7EwfXoWMXRwqPo2EgPYtgPOGw3LVh746w3rw8gz4Nxz4dTTIT6+mgqrPsqpiLMpoyLOFw051UxbcZT169fX+tCJ1HSVntPY2Mg83Cf/Cjk58OOP1jzcWd/BylXW7Yb0B1cB+Ius1VZuH9x8N2RlW6twhx0PndrXmlVYtV18vMklFxUx8vRiPvk8hs+/NCguDuIv8PDxRz6mT3dz7rkG554LCQl2V1uz6FgavbZts1bTzpkDq1cfeCOxhLggA/v5GTokSL++JrFxVfyaGQjAzl3QvFnkusb1YVdG2du1bwtnn2ltJHbs8VDLNxZRTkWcTRkVcT7lNEJNWxERqR7JyXD22dYJrC7ErFmQXAcSWkGwEIJ5UJwDn02DnD3wxQzrtk1T4MRjrQbusOOs3cTF0erUMbnisiLOObOYDz+OYfoMg0CgkKI8D+/9f3v3Hd9Uvf9x/JWkk5a2lFKG7L1BVouA7GGZIktFwas/uShccVwVUBDhiqgXcYLXhYOhoF5lU6DAZcqQIbI3Ipu2dLdJfn8cmlLastuctu/n43EekpNvkk+O+eQ0n3zz+c70ZN48G717W+jRQ5OsRa6WvpDYhg3GduwYZF1IzEHx4FTCmxoLidWte2WXmVwq2MZegsgomL8Ulq4wFppcNBvsyeBMAYsNunaA7XugZ3fo9QDUqasv3URERERugdojuFFhao8QFxeHv7+/u8MQkWswRZ46HXBgL4S3MBavyUn1KkYBd9j/QeWKeRae3Lrz5y18/4MPS5d5kJYGWD3A4klAkI2+fS1ERICXl7ujNDdT5KjkmvSFxDZsMBYSO3cOo3rrNGbSphdqy5e9vJBYMwdVq+VBPfSvU7BgqVGoXbUWUlIyrrNa4cBaKFEGvIqC1QfwLNQ9ypWnIuamHBUxv8KQp+ppmw8UpqLtvn37qF69urvDEJFrMFWeOhxGs8ZlkbB8GaxZBwkJWcdtWgq1amdULaJjwNsLfH3zNFy5cadPW5k9x5vlUR44nRjFW6snwcVt9O9voVOnQl3vuSZT5ajcEUlJsHWrUaj99decFxKrWT2F5s3SCAtzUKbMde/29p2/AF/MMBYT2/xb9mMCA+C+zjD+dahSQ7NpL1OeipibclTE/ApDnqqnrZjKxYvXmDEnIqZgqjy1WqFRI2N78SVITjaqGssijZYKv26CEsWhWnlIuWiMt3jC+9NgyicQ1hjatTJ64t5dX1VAEylZ0sEzwxLp09vKzO98+N8acKalceGsB1M/9uKHuVYGPGihXbsC3/ryppkqR+WWxcRkXkgsNRVjNu0VhVoPm4OG9ZMIb2YsJFYsOI+DTLPDuEnGTN8r3VUGenaDnvdDm3aaHp8N5amIuSlHRcxPeZpBn2IlT3h6ero7BBG5DlPnqbc3tG5tbOMnQGwsHDwIRSsbvRTtSUY/3JX/Mwq8q9cZG5MgoCi0am4UcNu0hFrVNSPMBO4q4+CfzybQt7eNmbO9Wb8RcKRx5pQn77/nydy5Nh56CFq1MmryYvIclWv66y+j5cH69bB795ULiTmMtgeXFxJr0iiF8GZpNG7kxLdILr9PJSTCitXGbNoypWDMi0YsjmQo5gFNG8Cv26BeHaM/bc/e0LiJ3j+vQ3kqYm7KURHzU55mUHsENypM7RFERHKdwwFP/R0WL4Gjx3IeVzIUxr4EgwbkXWxyXfsP2Jgx25stW22AxdU2oXwFGw8/DM2bq1Yk+YfTCYcOZSwkduQIZLeQWHAxYyGx5uFXLySWS86eh0XLYMESWL4KEpOM/XeVgp1LweoJNh/wKArbdkNoaahcJZeDEhERESlc1NM2HyhMRduNGzcSFhbm7jBE5BoKTJ6mV0vS++FGrYRz5zOPmT4FencHq7dRCbwYDSvXwL33QPG8/h2yXGn3Hg++menFzt9txv8biydYPahS1cYjjxgdMwpr8bbA5GgBlZYGf/xhFGnXr79iITHsmQq15e7KWEisWl5M/D942JhNu2AprN9kfMF1tSK+sGUdVKuZ8b4ot0R5KmJuylER8ysMeaqetiIiUjhZLFClirEN+btRoNi5EyKXGkXcteuhbTvAAanRgBMil8Fjzxq3bVA3o5VCizCjmCF5plbNNP41Lo0dOz34ZqY3e/c5wJnKwf2evDbWg1q1bQwcCPXruztSkcwLiW3aBHFxXLGQmP1yj1oHNasnE940jfBwB3fdlYcBbtwM7Xpmf12JEOgeAT16QacuWsBRRERExGRUtJU8UbJkSXeHICLXUWDz1GqFBg2M7YV/GtPhPDwyejfak2H1JmOs0wnbdhrblKnGIjthjaFNC2jbCho31KJmecBigQb106hfL43NWz35dqYXhw47wZLK7l1ejB7lQf0GVgYOhFq13B1t3imwOZrPxMQYBdoNG+C33yAlhauKtMZCYg3qJRPeLJVmTSG4eC4HlZICq9aBrw+0DDf2OdKgQTUICoDoWGNftSrQozv0uh+at9Bqf7lAeSpibspREfNTnmZQewQ3KkztES5cuEBwsH5yLGJmhTpPV6+Gn/8Ly5fD9h05j2vbCubPzrOwxOB0wvqNRvH2+AkLWKxg9QKLB02aGsXbKoWg7WahzlE3O306oz/trl1XLSR2uVDr62OnaaPkywuJQRG/XA4qOgaWRhn9aZesgEtx0LE1zPkPOFPA4mH0p/33p+DlA70egFq1czkoUZ6KmJtyVMT8CkOeqj2CmMr+/fsLfE8SkfyuUOfpvfcaG8DZs7BiBSyPNP578HDGuKZ1ICUGbF5G30cs8MzLxgzcNi2hQjl3RF/gWSxwT3gq4c1SWb3Gi5nfefHXX0lgsbH5V082b/LgnhZWHnoIKlRwd7S5p1DnaB5zOuHwYaM37fUWEgtrkkJ4mIN69Zzk+mLHJ/6EBZFGj9rV64xfDlxp5TqIT4WQu8Dma7xPjf1XLgclV1KeipibclTE/JSnGVS0zUdSU1Ox2+3uDuOWJSUluTsEcRNPT09s+gmm5BclSkD//sYGRrVm2TKjiNu9D3gFgT0B0mJh9374/FtjA6hc0Wil0KYltG4JIQX7G+K8ZrVCm3tTaHlPClGrvJn1PZw9aweLjXVrPFm/zoN7WxvF2zJl3B2t5Dd2e8ZCYhs2wJkzXLGQmAMcqeB0cFfpVJqHpRDezEH1Gnm0ZteWbfDMSPgth18CFAuE+zpDz14QXMWYWSsiIiIi+ZraI7jRjU6Hjo2N5dy5cyQnJ+dhdHeWw+HAarW6OwxxE4vFQmBgIKVKlcKiFalNKzY2tsC3arljnA6jF+6HH8CzL+U8rl5to6VCm5bQ/l71w73DUlNh6TIvvpvrzcWLTrDYwOqF1eZB+w4WBgyA0FB3R3nnKEfvvORkoy/thg3w669w6RLZLiRWo1rGQmJly+ZyUGlpkJAIAUUz9h09CrXvyTyufFno0Q163g+t25L703zlRihPRcxNOSpifoUhT2+0HqiirRvdyP+k2NhY/vzzT/z9/QkMDMTT0zNfFr2Sk5Px9vZ2dxjiBk6nk/j4eM6ePUvp0qUJCgpyd0iSgwMHDlC1alV3h5G/pKbC5s2wLNLYNvx6eVWiqxQLhKM7tehPLklOhoWLvZn7kxexsRnFWw9PDzp1ttC/PxSEtljK0TsjNtZYSGz9+msvJFa/jtGfNqyZM/cXEotPgOWrYN5iWLwMHhkAE142vhxyphiv6dZ9jX7OPbpDz95wd6M8muYrN0N5KmJuylER8ysMeaqetgXEuXPn8Pf3p2zZsvmyWJsuLS0NHx/9VK+w8vX1JTk5mTNnzhAYGJivX8sF2fnz5wv8yfGO8/SE5s2N7dUxkJAAa9ZA5BJYvgK2bTd+Xt2yGdhjwY7RY9LqBQ8NgeSUjHYK9Wobv/+Xm+btDff3TKZLp2TmLfDhx58txMcnkubwYOF8T5Yt86BrVwsPPACBge6O9tYpR2/dmTMZbQ9+/z37hcR8vO00uTuZ5mF2Gjdy4uef20Gdg0WRRqE2ag1c2UZq3kIY94zRl9arBFh9YO0Gcj8ouV3KUxFzU46KmJ/yNIOKtiaWmppKcnIyISEh+b7Ild/jl9sXEBBAbGwsdrsdD/1E3JTUd/gOKFIEOnUyNoDz5yEqCoKDwK882BMhLQ7iL0JkFCQlw9IVxtiQYGh9uYDbpiVUqqBZdDfJ1xf69UkioksyP/3izS/zLSQlpZGS4MFPP3iyaJEHPXpYuP9+8M+HtS/l6I1zOo121OmF2kOHILuFxIIC0whvmkx4mJ369fOgw8CfJ+H7n2H+Yti45XLP3Kv4+12eRRsKfsUy3gd06swXlKci5qYcFTE/5WkGtUdwo+tNh05KSuLw4cNUrFgRX19fN0QocuckJiZy5MgRKlWqpFnXUrg5nfD7Nuh0H5w6nfO48mWN4u1Lz0DF8nkWXkESE2Phh/96s2CRp/ET+MttE/yK2rj/fgs9ehiFXikY7HbYvdso0q5fn/NCYmVKZSwkVqNmHn83sng5PPBo1v2lSkKPrtCjF3ToZEwfFxEREZECST1t84EbLdoWhCJXfHw8fn5+7g5D3KggvZ4Lqk2bNtG0aVN3h1F4OJ1GhSkyEpZHwqrVEHsp67jda6HcFbNuz5wDXx8omg+nirrJhQsWvv/BhyWRHqSlAVYPsHhSNNBG374WIiLyR41MOZpVSkrmhcRiY8l2IbHqVZMJb5pKeLiTsmVzuVCblAQr18KCJdChDfSMMGb2OpIhIRaqtoL4RKhVA7p3g/t7Q7NwtUcpIJSnIuamHBUxv8KQp+ppK6ai7wZEzM/hcLg7hMLFYoHatY3tmWeMFeO3bDEWNFu+DNZtgPJ3QZkSkBpt3MbqBW9Pgf98A00aGjNx27aCZo3Ay8uNT8bcgoOd/P3/Eund08rsOd4sjwKHPY1L0R588bknP/1ko18/C50758HP42+DctRw6ZKxkNiGDbB1q7EQXUaR1ijU2qwO6tVJpnlYGs2aOgkpkctBXYw2ZtEuWAKRKyEu3th/5gzcFw4WD7D5QFBF+Ho61G0A1WvkclDiDspTEXNTjoqYn/I0g2baulFhmmmbnJyMd36YxiS5piC9nguqQ4cOUblyZXeHIekSE+HYMahW2VhB3p4MaZcgrDP8sS/z2CK+cE9YRj/cBnU0a+8aTv5lZdb3PqxabTN+PW/1AKsXISWsPPighXbtwIyttwtzjp45Axs3Ziwk5nDksJBYQ6M/bZPGebCQ2LETMH+Jsa3ZYPRnuFrxYDi2F7z9jUUI1ae6wCvMeSqSHyhHRcyvMOSpZtqKqRTGRtIrV66kbdu2zJkzhz59+rg7HCAjpqioKNq0aePucMRkgoOD3R2CXMnXF2pcnoln9QRPf0gLhLbtwQ7svaJwm5AIy1YaGxgLn735GjzcN09Dzi/KlHbw/DMJ9O1tY8Ysb9ZtABxpnDvtyQfvezJ3ro0HH4TWrc1V+y5MOep0wtGjGf1pc1pILDAg80JieTbh/KtZ8NQL2V9XvBh0jYCePaFzBBRRe6jCpDDlqUh+pBwVMT/laQYTfRSRgiwpKSnLvunTp2OxWFybj48PZcqUoXPnzrz//vtcupRNb8cbtG7dOl577TWio6NvI+pre/HFF7FYLPTv3/+27icvYhW5EXv37nV3CHI9Hh7w4cewZy+cOAHTp8MjD0OZ0pnHXYiG4CJgTzKKXAB/nYbZP8KpM3kdtWmVL2dn5IsJTHkngaZN7MZCVWmJ/HUiicn/tjNsGKxde3ktKxMo6DnqcMCuXfD55/DkkzB8OMz41smhg2ngSIG0BEhLoHSJOO7vdom3JsTy9RcJDHvaTpMmuVSwTU2FlWvg6PGMfU47NKuXeVylCjBiGEStMHLsq2+hd19QP/9Cp6DnqUh+pxwVMT/laQbNtBW3e/3116lUqRKpqamcOnWKlStXMmLECCZPnswvv/xC/fr1b/o+161bx7hx4xg8eDBBQUF3PGan08msWbOoWLEi8+bN49KlSxQtWvSW7iu3YxWRAuquu2DQIGNzOmHvXli2zFjUbN16uLct4IC0WKNwu3AB/ONV47a1qkObVtC2JbQMh8Ccf5JTGFSpbGfMqAT27PXg21nebN/hBGcax4948uZEDypXsTFwIDRpol+332kpKbBtW8ZCYjExZLuQWLUqyYQ3TSM83EG5crn8/+FSnDFrfd4SWLIcomPg5X/Ay0+DMwUsNqhRDXr3gIYNoWdvqFdfLw4RERERuaNUtC2kTp40Fiw/cwZCQ6FjRyhTJvce71o9TO+77z6aNGniujxy5EhWrFhBt27d6NGjB7t378bX1zf3grsFK1eu5MSJE6xYsYLOnTvz448/MmjQIHeHJXJbqlev7u4Q5FZZLFCzprENG2YUcS0WcNiNFesdybB6U8b43fuMbernxu//GzfIWNQsrDEU0r7TNWukMeG1NHbsNIq3u/c4wZnKoQOevD7Ogxo1jeJtgwbuqc8VlByNi8u8kFhSElkWErNaHNSrnUx4szTCw/JgIbG/TsOiSKNQu3KNUU2+0vwlMPo58CoBVh+wecMPP+dyUJIfFZQ8FSmolKMi5qc8zaD2CIXQsmUwYABMnGj8BHHiROPy8uW595j27BbnuIZ27drx6quvcvToUb799lvX/h07djB48GAqV66Mj48PpUqV4m9/+xvnz593jXnttdf45z//CUClSpVc7ReOHDkCwJdffkm7du0IDQ3F29ub2rVrM3Xq1JuKb8aMGdSuXZu2bdvSoUMHZsyYcUO3S05Oplu3bgQGBrraIuQU65EjR7BYLEyfPj3L/VgsFl577TXX5aNHj/LUU09Ro0YNfH19KV68OH379nU9Z5EbcfHiRXeHIHdKekXRagOPIuBVDJ59CUa+DM2aZm7U6nDApt/g7Q8goh888nf3xGwi9eulMelf8bz2ahJVK9svLwSXyN7dybz6ioNRo+CPP/I+rvyco+fOwfz58Mor8PDDMHmyk3Vr7SQlpII9EewJ+HgmcE+TWJ4bFsuML+OY8Hoq3brlcsF2USS07Q5VG8Hwl2DpiswF24Ci0O8BGDkaipQzcsnDFyz6E1qyl5/zVKQwUI6KmJ/yNINm2hYyJ0/C66/DhQtQpYrxud3hMBYoHzcOateG0qWvfz83KzU1FW9v75u6zSOPPMKoUaNYunQp//d//wdAZGQkhw4d4rHHHqNUqVLs2rWL//znP+zatYsNGzZgsVjo3bs3+/btY9asWbz77ruEhIQAUKKE8alv6tSp1KlThx49euDh4cG8efN46qmncDgcPP3009eNKzk5mR9++IHnn38egAcffJDHHnuMU6dOUapUqRxvl5iYSM+ePdm8eTPLli2jadOm+Pv75xjr2bNnb/hYbdq0iXXr1jFgwADKli3LkSNHmDp1Km3atOGPP/6gSJEiN3xfUnidPXu2wK/SWajdc4+xAURHw6pVsGwpLF8Bu/dkjGveAFKijZXubV5gd8Lj/4B7mhmzcatXKRQ/A7dYoPHdqTRqmMqGXz35dqYXx447wJLK7zu8eOlFDxo3sfLww1CtWt7ElJ9y1Ok0/rbYsMHYDhyAnBYSa9Y4mebhdho0yOWFxOx2IzCPK/78TUyCX7dmHlemNPToCj3vh3Yd8nB1MykI8lOeihRGylER81OeZlDRNp969lm4lS8fDhyAnTuhaNHLfeMuS/9w1bcvVK16c/dZrBi8++61x1hu4QN+2bJlCQwM5ODBg659Tz31lKtYmi48PJwHH3yQNWvW0KpVK+rXr0+jRo2YNWsWvXr1omLFipnGr1q1KlO7hWHDhtGlSxcmT558Q0Xb+fPnEx0dzYABAwDo1asXTz75JLNnz2bEiBHZ3iYuLo5u3bqxa9cuVqxYQcOGDQGuGevNFG27du1Knz59Mu3r3r07zZs354cffuCRRx654fuSwutW8lTyqaAgY2X7nj2NyydPGj+3WB4J3fqAd3FIizO2X7fC3J+NDaBMKaN426al0RP36kXQChiLBZqHpRLWNJU167yYMduLkyeTwGJjyyZPtmz2ILy5Uby96nSTC7GYO0cdDqO18vr1RqH2r7+4vIqb3SjWOtLAaadUyVSaN00hPNxBzZqZJ37fcYmJRruD+UthwVKYPAF63Xe5bUgKtGkE3l5QrQr06G70p23arFB8MSG5w+x5KlLYKUdFzE95mkFF23zq4kW4oiPADbtwwZhokpqa9Tq73bj+Vu73evxucfVkf39/Ll265Lp8ZbE1KSmJuLg4wsPDAdi6dSutWrW67n1eeR8xMTGkpqbSunVrlixZQkxMDIGBgde8/YwZM2jSpAlVL1e3ixYtSteuXZkxY0a2RduYmBg6derEoUOHWLlyJXXq1LlujDfryueUmppKbGwsVatWJSgoiK1bt6poKzekWbNm7g5B3KVMGXjkEWNL5yxhFLU2fZ957MlTMHOusQHUqJrRD7drp1yuwLmP1Qr3tkyhRfMUolZ5Met7L86csYPFxoZ1nmzc4EGre6089JCxRlxuMGOOpqTA9u1GkXbjxqsWEiNjRm2VSimEN00lPNxBhQq5XBM9fwEWLzeKtJFRkJCYcd3Pv0D31mDzAa9g8PeFI0egVMH+8kHyjhnzVEQyKEdFzE95mkFF23yqWLFbu93Fi/Dnn+DpmfkDk9MJNhsEB0Px4nc+lvj4+Fsq3MbFxREaGuq6fOHCBcaNG8fs2bM5c+ZMprExV04dvoa1a9cyduxY1q9fT0JCQpb7uFbRNjo6moULFzJs2DAOGL/1BKBFixb88MMP7Nu3L0vT7BEjRpCUlMRvv/2WKwVbMFovTJw4kS+//JI///wTp9Ppuu5Gj4vIli1baNy4sbvDELOwWI3C1suvQpfusCwSli+D/601Zi+m23vA2BYsNYq2V0pfEK0AsdmgQ7sU2tybwtJlXnw315sLF5JwOmysXunF/1Z70K69hQcfhJIl7+xjmyVH4+MzFhLbsiW7hcTsWC126tZKJjwsjfBmTkqEXvdub8+xE/DLIliwBNb+anwTfTVfHygSBP4VjfYf6a/NUmohJHeOWfJURLKnHBUxP+VpBhVt86nrtSPIycmTxqJjFy9C+fKZe9pWrgzffZc7PW2vLCLeqBMnThATE+Oa0QrQr18/1q1bxz//+U8aNmyIv78/DoeDLl264HA4rnufBw8epH379tSsWZPJkydTrlw5vLy8WLhwIe++++5172POnDkkJyfz73//m3//+99Zrp8xYwbjxo3LtK9nz57Mnj2bN998k6+//hrrDc5Cy+knAdkt6jZ8+HC+/PJLRowYQfPmzQkMDMRisTBgwIAbOi4iAGlpae4OQczIaoVGjYztxZcgOdmo1i2LNFoq/LrJKJC1DofUaGO8xROsXhDxoHG57eV2CnfXz9xPNB/z8ICILil0aJfCoiXezPnRQkxMIk6HjeWRXqyM8qBTZwv9+sHlduW3zZ05eu4c/Pqr0fpg506w250ZM2qdRtsDL087jRsk0zw8jSaNoWhAHgb4zXfwxuSs+0OKQ7f7jP60ne+DK36ZIpIbdC4VMTflqIj5KU8zFIxPTnLDypSBsWONRccOHjQmmTidEBpq7M+Ngi2Axy18SP/mm28A6Ny5M2CsILh8+XLGjRvHmDFjXOP279+f5bY5FTznzZtHcnIyv/zyC+XLl3ftj4qKuqGYZsyYQd26dRk7dmyW6z755BNmzpyZpWjbq1cvOnXqxODBgylatChTp069oViLXZ7CHB0dnWn/0aNHs4ydO3cugwYNylRITkpKynJbkWsJDg52dwiSH3h7Q+vWxjZ+Aly6BKtXQ0iwMYPRnmT0wr1wBtZuNL4ZXLUWmASBAdCqeUZP3JrV8v1MXC8v6Nk9mc4dk5m3wJsf/mshPj4Ru8ODRQs8WbbMg4gIC336GK2Eb0de5qjTCSdOZPSnNU61Vy0khoOifmmENUkmPMxOw4bGyyPXpKbC/9bD/CUw9G9GH1qnHezJ0Lk5vHF5XNXK0KMb9OoN97Q0pkeL5BGdS0XMTTkqYn7K0wwq2hZC7dtD7dqwdCmcOWMUbDt1yr2CLYCnp+dNjV+xYgXjx4+nUqVKPPzwwwDYLn/ounrW7pQpU7LcPr0Vw9VFy+zuIyYmhi+//PK6MR0/fpzVq1czbty4LIt+AaSkpPDwww+zceNGwsLCMl336KOPEhsby/DhwwkICGDSpEnXjTUgIICQkBBWr16dqVfuxx9/nOWxbTZbluPywQcfZDsrVyQnJe/0b7mlcChaFLp2zbjs6Q/O4rDnNJQrC0ePZVwXE2sU3OYvMS6XKgmtW8C4l6FcLjWCzSM+PtD3gWQiuqTw33ne/PcXC0lJdlITbfz8kyeLF3vQvbuF3r2NQ3YrcjtHnU7Ys8co0m7YYPw6J7uFxEJLpNG8WTLhYQ5q1crlmmjsJaMv7bwlsHSF8RoCKFUcRgwGi81o49G0DbwzCbpEQO06+f7LAMm/dC4VMTflqIj5KU8zqGhbSJUuDYMG5d3jJSYm4u/vn+11ixYtYs+ePaSlpXH69GlWrFhBZGQkFSpU4JdffsHHxwcwipj33nsvb731Fqmpqdx1110sXbqUw4cPZ7nP9P4no0ePZsCAAXh6etK9e3c6deqEl5cX3bt3Z8iQIcTFxfHpp58SGhrKX3/9dc3nMHPmTJxOJz169Mj2+oiICDw8PJgxY0aWoi3AsGHDiI2NZfTo0QQGBjJq1Khrxurn58cTTzzBm2++yRNPPEGTJk1YvXo1+/bty3Lf3bp145tvviEwMJDatWuzfv16li1bRvGbbVAshdru3buzfe2K3DSLBZqEweEjcOiQ0UphWSRErTQWiUp36jR8/xO89Urm/rcn/oQiRSD4Fhu4u5Gfn5OHByTRPSKZH3/2Zt4CSElJIzneg7nfe7FwoY3777fQo4fxFG9GbuRoairs2GHMqN24EaKjyXYhscoVU2jeLI8WEvvrlNEjed4SY5Z2dqunLl0No0aD1cco2los8PyLuRiUyI3RuVTE3JSjIuanPM2goq24XXqrAy8vL4KDg6lXrx5Tpkzhscceo+hV05FmzpzJ8OHD+eijj3A6nXTq1IlFixZRpkyZTOOaNm3K+PHjmTZtGosXL8bhcHD48GFq1KjB3LlzeeWVV3jhhRcoVaoUQ4cOpUSJEvztb3+7ZpwzZsygfPnyNGjQINvrg4KCaNmyJd999x2TJ2fTVw8YNWoUMTExrsLt008/nWOsfn5+jBkzhrNnzzJ37ly+//577rvvPhYtWpRpcTaA9957D5vNxowZM0hKSqJFixYsW7bM1VpCRMQtLBaoUsXYhvzdaJWwY0fGomar1xgtEooVNfrh4gSLF0x4B76dAw3qQttWRiuFe5pBkfzTjzQgwMngR5Lo0TWZuT/5sGiJhbS0RBJiPZjxjSe//GLjgQcsdO1qzNLNS/HxxgJi69fD5s3ZLyRmIfNCYqF5NeHh1Tdg8kfZXxcYABFdoGdPuK8beOVl01wRERERkbxlcd7KClFyR8TGxhIYGEhMTAwBAVk/eCQlJXH48GEqVarkmm2aX6Wlpd1SX1spOArS67mgOn/+vGZnS95KSYG//jJaIziSjd6kKZegzj1w/GTmsV5eEN44ox9u44b5alGzs2etfDfXm2UrPLDbAasHWD0JKmajXz8LnTsbT/FabidHz583ZtJu2GAsJJaWlv1CYo3qG4Xapk0gIPCWHurG2O2wfhM0bpCxOJjTDjO+gyH/zBhX9i7o2c1YSKxNO7jJdksieU3nUhFzU46KmF9hyNPr1QPT5Z9PO5Kv2e12FW1FTC4uLq7AnxzFZLy8oEIF499WD/DwA/ygTz9Yvhx27MwYm5ICq9cb2+tvQ1F/eH8S9OvljshvWokSDoYNTeSBXlZmzfFm5SpwpqURfd6D/3ziyY8/2ujf30KHDjnXom82R0+cMIq069eD0Vkn+4XEmjVOoXl4Wu4vJJaQCMtXGT2NFy+Dcxfg+y+gc0ujaG+xQpd2cHd96BoBvR6ARo3Vn1byFZ1LRcxNOSpifsrTDKqiSZ5ITU3FO1c/CYrI7Tp16hQV0gtoIu7i7Q2T3zX+ffasUbxdHgkrVsChIxnjLsVB6SCwJ4LV2yj4HTkGq9ZB25ZQvqw7or+u0qUdPPePRPr2tjJztjdr1gGONM6d9uSjDz354QcbDz4IbdqA1Zr5ttfLUafTKM6mF2r//BOyFGovLyQW3jSF8DA7tWvn8kJiZ8/DwkhYsARWrIbEpMzXz18I97UFnxCjP22AN2zdnosBieQunUtFzE05KmJ+ytMMKtqKiIiIOZUoAQMGGBvAkSMZ/XA3bYbwlkAqpMUahcmf/guvTDLGVq4IbVoYPXHvbQEhwe55DjkoV9bBSy8k0vewjRmzvfl1E+BI49SfHrw72ZM5c2w8/DC0aGF0kIiMhM2bS7NnD3TsCOmt3NMXEtuwwWh/cPEi2S4kVqlCCuHNUgkPc1CpUh5MXp0xB6bPhA2bjV7GV/MrAp06QI8+4JfbK5uJiIiIiOQ/puppO3XqVKZOncqRI0cAqFOnDmPGjOG+++4DjJ6Yzz//PLNnzyY5OZnOnTvz8ccfU7JkxuoYx44dY+jQoURFReHv78+gQYOYOHFipp/mr1y5kueee45du3ZRrlw5XnnlFQYPHpwplo8++oi3336bU6dO0aBBAz744AOaNWvmuv5GYrmewtTT1ul0YtEHskKtIL2eCyrlqeRLTofRC9eRDD0egCUrsh9Xv05GP9wWYeDvl7dxXsfefTa+neXNtu02wAJWT7B6YPOwcfQoJCYCOAELxYtDnz5GwXbz5svXZbOQWJ2ayYQ3SyM8zEnJUrkYvNOZtej6ygR4d2rmfaEloHsE9OgFnbrk/QpsInlA51IRc1OOiphfYcjTG+1pa83xGjcoW7Ysb775Jlu2bGHz5s20a9eOnj17smvXLgCeffZZ5s2bx5w5c1i1ahUnT56kd+/ertvb7Xa6du1KSkoK69at46uvvmL69OmMGTPGNebw4cN07dqVtm3bsm3bNkaMGMETTzzBkiVLXGO+++47nnvuOcaOHcvWrVtp0KABnTt35syZM64x14tFMks0Pm2KiIlt27bN3SGI3DyLFTx8wSsIXp8I416De1tmXbBqxy54/xPo/Qg8/YI7Ir2mGtXtjB+bwMTxidSuZQdHCknxSfxvtYMDB5wkJ4PVmoDDYSwkNmGCk8ildhLjU40WEfYEvGwJhDWK5ZmhsXz7RRwT/5VKz565VLBNToalUfDMy1CtidGawpEGafGQcgG6tDDGVa8KLzwLa1bDX6fgs+lG0VYFWymgdC4VMTflqIj5KU8zmGqmbXaCg4N5++236dOnDyVKlGDmzJn06dMHgD179lCrVi3Wr19PeHg4ixYtolu3bpw8edI143XatGm89NJLnD17Fi8vL1566SUWLFjA77//7nqMAQMGEB0dzeLFiwEICwujadOmfPjhhwA4HA7KlSvH8OHDefnll4mJibluLNlJTk4mOTnZdTk2NpZy5coVipm2cXFx+Pv7uzsMcaOC9HouqDZu3EhYWJi7wxC5M+LjYc0aWLYUli2H7TuMGaEAU8bCoL5GL1yrFySlwqCh0Kq5MRO3bq2sDWXzkNMJ27Z78PIYf9au96ZIEScWq4XUVDuenp44nU4SEqBq5RRqVUuiWeNkwsMc3H23M3drodExxkzmBUuMgu2luIzrJr4EQweDzQc8ioLFCw6fgJq1cjEgEfPRuVTE3JSjIuZXGPL0Rmfamranrd1uZ86cOcTHx9O8eXO2bNlCamoqHTp0cI2pWbMm5cuXdxVK169fT7169TK1KOjcuTNDhw5l165d3H333axfvz7TfaSPGTFiBAApKSls2bKFkSNHuq63Wq106NCB9evXA9xQLNmZOHEi48aNy7J/8+bN+Pn50ahRI3bv3k1iYiJFixalTJkyJCcnEx8fj81mw+l0kpKSAkCRIkVITk7Gbrdjs9nw9vYmISEBAC8vLywWi6tAfOVYq9WKr68v8fHx2Y719fUlNTWVtLS0LGM9PT2x2WwkJSVlGWuxWPDz8yM+Ph6n05llrNVqJTk5mdTU1CxjPTw88PT0dM3G9fHxwW63k5qaCoC/v3+OY729vXE4HK6xfn5+JCYm4nA4sNlseHl5ZRp79TFMSkpyjb36GKa/HrI7hj4+Pjkeb19fX1JSUrI93p6enq5jkdMxjIuLu+3jfeUxvNnjfeUxzO54X3kMrz7eVx7Dq8darVZSUlLYvn07/v7+VK1a1fUNWrly5bBarRw9ehSA+vXrc/jwYS5duoSvry+1atVi69atANx11114eXlx+PBhAOrVq8fx48eJjo7G29ub+vXrs2nTJgBKlSqFn58fBw8eBKB27dqcOnWKCxcu4OnpSaNGjdi4cSMAoaGhBAYGsn//fsDI6XPnznHu3DmsVitNmzZl06ZNOBwOQkJCCAkJYc+ePQBUq1aNmJgY12z8sLAwtm7dSmpqKsHBwZQqVYo//vgDgCpVqhAfH8+pU6cAaNq0KTt27CA5OZmgoCDKlSvHzp07AahUqRIpKSn8aawmlOU9olKlSuzYsQOAChUq4HA4OH78OAANGzbkwIEDxMXF4efnR/Xq1fntt98A41cNNpst0/E+cuQIcXFxbN++nTp16rBlyxYAypQpg4+PD4cOHQKgbt26nDhxgujoaLy8vGjYsCG//vqr63j7+/tz4MABAGrVqsXp06e5cOECHh4eNG7cmF9//RWn00mJEiUoVqwY+4wl7alRowYXLlzg7NmzruO9efNm7HY7xYsXJzQ0lN27d7uOd2xsLKdPn85yvIsVK0aZMmVcv9CoUqUKCQkJ/PXXXwA0adKE33//naSkJAIDAylfvrzreFesWJG0tDROnDjhOt579uwhISEBf39/qlSpwvbtxgJJ5cuXB4yWPAANGjTg4MGDxMXFUaRIEWrWrOl6zZYtWxYPDw9X65969epx7NgxYmJi8PHxoW7dumzevBmA0qVLU6RIEddrtk6dOpw8eZKLFy9mec2WLFmSgIAA12u2Vq1anDlzhvPnz2Oz2WjSpInrNVuiRAmCg4PZu3cvANWrV+fixYucPXsWi8VCs2bN2LJlC2lpaQQHB1OyZEnX8a5atSpxcXGu12yzZs3Ytm0bKSkpBAUFUbZsWdcXoZUrVyYpKYmTJ08C0LhxY3bt2kVSUhIBAQFUrFgx02vWbre7jvfdd9/Nvn37iI+Pv3PvEUFB1Bs3nuNPPEnc0aMEb99OxQP72VauLil/nKdUSBH8vK2c/XEptRZGGgtmAalBQVxq0ojgXl3YFlqW5DJlCA0JJDCgCPsPGa+lmlXv4tyFWM5duITVZqFp/aps2nEAh91JSHBRQoID2HPAyN1qlUsTE5vAmXMxYIGwhtXY+vshUlPtBAf5Uyo0iD/2GcehSsVSxCckkeKMplr1suzZV4G0tDQSk4yfiDkdaVisaXh7WwlrdomR/zzF6XMXALB5VGbHnhMkJqZQ1N+XSuVC2bHbOGYVypYw3iNOnjfeI+pU5MCRU8TFJ+FXxJvqlcvw2+/G+2rZMsWxWa0cPXEWr9NnqLP/D1L+u5Aim7Zgtdu5mtPbi5N7T3Fi9wXq1q3PiaN/ZrxHOJ16j9B7hHnfI7jzf0fExcWxcePGQvl3RGxsLD4+Pvo7Qu8Rpn6PiIuLIzExUZ810HuE3iPM+x6RmJjIxo0bC/TfEVdO6LwW08203blzJ82bNycpKQl/f39mzpxJREQEM2fO5LHHHsvyxJo1a0bbtm2ZNGkSTz75JEePHs3U6iAhIQE/Pz8WLlzIfffdR/Xq1XnssccyFWUXLlxI165dSUhI4OLFi9x1112sW7eO5s2bu8a8+OKLrFq1io0bN95QLNkpzDNt04vLUngVpNdzQRUfH4+fn7n6fIrkKqfT6IX72jiY8GbO4yqUM2bgtm0FfXrk2aJZX33ry8R3/KlS2U5srIWERAeBARZ8feHgIRsjX4hj0MBcbj90/yOwNJs+wcFBENEFevWGLhGg9w4RQOdSEbNTjoqYX2HI03zZ0xaMb0C2bdvGxo0bGTp0KIMGDXJ9a5TfeXt7ExAQkGkrLNTTVsT8rmwbI1IoWCzGz/lffwN+/x2mTIHuXSGgaOZxR4/DV7PgzXez3kdaWq6F17F9MqElHBw7biMgwIlvkQR8feHYcRuhoQ46tb+xb+ivKy0NVq+DUeON1c3AWNAsLQHua5UxrmJ5+MdTsGIZnD4L38yCB/qqYCtyBZ1LRcxNOSpifsrTDKZrj+Dl5UXVqlUBY6rzpk2beO+99+jfvz8pKSlER0cTFBTkGn/69GlKlTJW2ChVqpRr6vyV16dfl/7f9H1XjgkICMDX1xebzYbNZst2zJX3cb1YREREJJ+wWKBOHWN75hmjiLl5MyyLhOXLYN0GSEmB1uGQGm3cxuplbPfcB0X9MmbiNmsEl1vs3K4ypR2MHXWJcW8U5eBhG0lJPpzzNgq2Y0deonRpx63feVw8LF8F8xbDkuVw4fLzahcO9zYGiw1s3tCrL8TYodcDUL9Bns0yFhEREREp7ExXtL2aw+EgOTmZxo0b4+npyfLly3nggQcA2Lt3L8eOHXO1MWjevDn/+te/OHPmDKGhoQBERkYSEBBA7dq1XWMWLlyY6TEiIyNd9+Hl5UXjxo1Zvnw5vXr1csWwfPlyhg0bBnBDsUhm3t7e7g5BRK6jcuXK7g5BxBw8PCA83NheeRUSE2HtWigZAn4VwJ4MaZfgxDHYZfTjYsNmeHMKFPGFe8Iyirj1a9/Wombt26ZQu+ZFli735tDRVCpXSKFT++RbK9iePguLIo1CbdQayK6X1uKV0KUHWH2Moq2/FcaOv+X4RQobnUtFzE05KmJ+ytMMpmqPMHLkSFavXs2RI0fYuXMnI0eOZOXKlTz88MMEBgby+OOP89xzzxEVFcWWLVt47LHHaN68uWvhr06dOlG7dm0eeeQRtm/fzpIlS3jllVd4+umnXUXDv//97xw6dIgXX3yRPXv28PHHH/P999/z7LPPuuJ47rnn+PTTT/nqq6/YvXs3Q4cOJT4+nsceewzghmKRzEzWOtmlYsWKDB482HV55cqVWCwWVq5c6drXpk0b6tate9uPdeTIESwWC9OnT7/t+8otVx+Pm2GxWHjttdfuaDySt9IXshORq/j6QocOUK8hePqDT3GjeHvRCtWrZR6bkAjLVsIrE6BFZ6hYHwY+CX+duuWHL13awaCBiTzxt1MMGph4awXbR/8OVe6Gp/8Ji5dnLtgW9Ye+veHbr+Bfk8GrGHj4gsVUfyaK5As6l4qYm3JUxPyUpxlM9df4mTNnePTRR6lRowbt27dn06ZNLFmyhI4dOwLw7rvv0q1bNx544AHuvfdeSpUqxY8//ui6vc1mY/78+dhsNpo3b87AgQN59NFHef31111jKlWqxIIFC4iMjKRBgwb8+9//5rPPPqNz586uMf379+edd95hzJgxNGzYkG3btrF48WJKlizpGnO9WCSzlJSULPumT5+OxWJxbT4+PlSvXp1hw4ZlaU9RmKQXji0WC99++222Y1q0aIHFYrkjxWSRdOmrcIrIDbBYoHkL2LsPjh+H6dNh4ENQpnTmcecvwsJIKOoDziuKrQcPw6kzN/WQJ09dvP4ghwN2XrUWgNMBxYOMhdfSlS4FQx6HhfPh7Dn4/gd4+FEoVuymYhKRzHQuFTE35aiI+SlPM5iqPcLnn39+zet9fHz46KOP+Oijj3IcU6FChSztD67Wpk0bfvvtt2uOGTZsmKsdwq3GIjfm9ddfp1KlSiQlJbFmzRqmTp3KwoUL+f333ylSpEiexnLvvfeSmJiI1x3qR3ilChUqkJiYiKen5w2N9/HxYebMmQwcODDT/iNHjrBu3Tp8fHzueIwiInILypaFQYOMzemEvXshMhKWR8LKVdCwHvh6QVqsUUC1eMKYf8F/F0GtGpdbKbSEluEQeMUipf/6N9is8PKzWR/zzXfB7oDRz0NSEqxcA/OXGgXiM2dh30YIDQJHsjFjtmsHWPMr9OgBve6HpmG31bZBRERERERyl6mKtlJw+V1jZen77ruPJk2aAPDEE09QvHhxJk+ezM8//8yDDz6Y7W3i4+OveZ+3ymq15loxNH028Y2KiIjgl19+4dy5c4SEhLj2z5w5k5IlS1KtWjUuXryBWVciN6hx48buDkEk/7NYoGZNYxs+HOx2OHcO/EKMAqojGZJjYdV6Y/zuvcY29XOw2aBxA6OI26alUeAdP9kY9/KzNK5/ub/Xm+/C+HegZwQ8/H8QuRLiEzLHsWARPP4oeAUbrQ661YAej+bZYRAprHQuFTE35aiI+SlPM2iKRWHz2mswPocFRcaPN67PBYmJiTc8tl27dgAcPnwYgMGDB+Pv78/BgweJiIigaNGiPPzww4CxSNyUKVOoU6cOPj4+lCxZkiFDhmQpZjqdTiZMmEDZsmUpUqQIbdu2ZdeuXVkeO7uettlZunQpRYoU4cEHHyQtLQ0wFrRr2bIlQUFB+Pv7U6NGDUaNGuW6zc32tO3Zsyfe3t7MmTMn0/6ZM2fSr18/bDZbltukpaUxfvx4qlSpgre3NxUrVmTUqFEkX7XYzI0eD4Do6GhGjBhBuXLl8Pb2pmrVqkyaNAmH4zZWLRdTyuk1ICK3wWaDkiXBagOPIka/WGsIDBkCTZtknu1qt8OvW+Gt9yGiH7w7Dfr0MAq0b77Lrn0noM+jxmWLBX5eCP9dmLlg6+sD3e6DGo2Nvrs+xY3HtWY9Z4jInadzqYi5KUdFzE95mkEzbQsbmw3GjDH+/eqrGfvHjzf2X9H/9066mQLfwYMHAShevLhrX1paGp07d6Zly5a88847rrYJQ4YMYfr06Tz22GP84x//4PDhw3z44Yf89ttvrF271tWKYMyYMUyYMIGIiAgiIiLYunUrnTp1yrbX7vXMnz+fPn360L9/f7744gtsNhu7du2iW7du1K9fn9dffx1vb28OHDjA2rVrb/r+0xUpUoSePXsya9Yshg4dCsD27dvZtWsXn332GTt27MhymyeeeIKvvvqKPn368Pzzz7Nx40YmTpzI7t27+emnn1zjbvR4JCQk0Lp1a/7880+GDBlC+fLlWbduHSNHjuSvv/5iypQpt/z8xHzU8F0kj/j5wcQ3jX9HR8PKlbBsKSxfAXv2ZoxLSoJn/wY1KsP4d6j35nuQmmpcd2V/2pBg6BoBPXtC5wjI49ZCIpJB51IRc1OOipif8jSDiraFTXqh9srC7ZUF2ysLuXdQdrNC08XExHDu3DmSkpJYu3Ytr7/+Or6+vnTr1s01Jjk5mb59+zJx4kTXvjVr1vDZZ58xY8YMHnroIdf+tm3b0qVLF+bMmcNDDz3E2bNneeutt+jatSvz5s3DYrEAMHr0aN54442beh4//vgjAwYMYPDgwUybNg3r5RlSkZGRpKSksGjRokytDG7XQw89RPfu3Tl+/DjlypVjxowZVK5cmfDw8Cxjt2/fzldffcUTTzzBp59+CsBTTz1FaGgo77zzDlFRUbRt2/amjsfkyZM5ePAgv/32G9WqGSukDxkyhDJlyvD222/z/PPPU65cuTv2fMW9AgICrj9IRO6soCDo1cvYAE6ehOXLjX64O3dCwzCoVxfe/ghrSqrx5avdDpUrQs/u0LM3tGxl7BcRt9O5VMTclKMi5qc8zaD2CPnZ5MnG4ifX23r0yHy7V1+FGjWMQq3FYvy3aFH45JOst508OfNtL1269vU58Pb2zvG6Dh06UKJECcqVK8eAAQPw9/fnp59+4q677so0Ln22abo5c+YQGBhIx44dOXfunGtr3Lgx/v7+REVFAbBs2TJSUlIYPny4q0AJMGLEiBuKPd2sWbPo378/Q4YM4ZNPPnEVbAGCgoIA+Pnnn+9o24BOnToRHBzM7NmzcTqdzJ49O8c+v+kL8D333HOZ9j///PMALFiwALi54zFnzhxatWpFsWLFMh3jDh06YLfbWb169Z14mmISFStWdHcIIlKmDDzyCEz/Grb8BkVKwbszICUVp5eXUbB9+ik4cAgmvw+t26hgK2IiOpeKmJtyVMT8lKcZNNM2P4uNhT//vP647GZCFiuW+fKlS8aW3WNcyenM/JhXX5+DhIQE/P39s73uo48+onr16nh4eFCyZElq1KiRqSAK4OHhQdmyZTPt279/PzExMYSGhmZ7v2fOnAHg6NGjAK6ZoulKlChBsauPQw4OHz7MwIED6du3Lx988EGW6/v3789nn33GE088wcsvv0z79u3p3bs3ffr0yfJcboanpyd9+/Zl5syZNGvWjOPHj2eaVXylo0ePYrVaqVq1aqb9pUqVIigoyHUcbuZ47N+/nx07dlCiRIlsHzP9GEvBsGPHDsLCwtwdhohcafx4GDsWXn+dXzt1ImzpUuPL1pKlcu3XMSJy63QuFTE35aiI+SlPM6hom58FBMBVs1GzlV3B7aqFuiha1Li/7B7jShZL5se8A9PWmzVrRpMmTa45xtvbO0vx0+FwEBoayowZM7K9TU6FxltRunRpSpcuzcKFC9m8eXOWeH19fVm9ejVRUVEsWLCAxYsX891339GuXTuWLl16zfYQ1/PQQw8xbdo0XnvtNRo0aEDt2rWvOf7K2bO3y+Fw0LFjR1588cVsr69evfodeywREbnK1e2LNm7Mvs2RiIiIiIgUOCra5mfPPWdsN2v8eNi7N+NDYPqHwn/+8/of/ooWhRMnbvohr9Ue4VZVqVKFZcuW0aJFC3x9fXMcV6FCBcCYNVq5cmXX/rNnz3Lx6uJ1Dnx8fJg/fz7t2rWjS5curFq1ijp16mQaY7Vaad++Pe3bt2fy5Mm88cYbjB49mqioKDp06HALz9DQsmVLypcvz8qVK5k0aVKO4ypUqIDD4WD//v3UqlXLtf/06dNER0e7jsPNHI8qVaoQFxd3W/FL/pH+2hARk7DbM/Wbd+Vo+rnabndTYCKSE51LRcxNOSpifsrTDOppW9hkt+jYq68al8eMMa7PBc4rV7m+Q/r164fdbmd8NjGnpaURHR0NGD1zPT09+eCDDzLFMWXKlJt6vMDAQJYsWUJoaCgdO3bk4MGDrusuXLiQZXzDhg0BYxG122GxWHj//fcZO3YsjzzySI7jIiIigKzPa/LlvsNdu3YFbu549OvXj/Xr17NkyZIs10VHR5OWlnazT0dMzK4CkIi5vPZapi9TM+Xoq68a14uIqehcKmJuylER81OeZtBM28Lmqlk7Lrk8ayclJQUvL687ep+tW7dmyJAhTJw4kW3bttGpUyc8PT3Zv38/c+bM4b333qNPnz6UKFGCF154gYkTJ9KtWzciIiL47bffWLRoESEhITf1mCEhIURGRtKyZUs6dOjAmjVruOuuu3j99ddZvXo1Xbt2pUKFCpw5c4aPP/6YsmXL0rJly9t+rj179qRnz57XHNOgQQMGDRrEf/7zH6Kjo2ndujW//vorX331Fb169aJt27YAN3U8/vnPf/LLL7/QrVs3Bg8eTOPGjYmPj2fnzp3MnTuXI0eO3PQxFPM6ceJElgUARcQ8lKMi5qc8FTE35aiI+SlPM6hoW9hca1ZOPuyLN23aNBo3bswnn3zCqFGj8PDwoGLFigwcOJAWLVq4xk2YMAEfHx+mTZtGVFQUYWFhLF261DX79GbcddddLFu2jFatWtGxY0dWr15Njx49OHLkCF988QXnzp0jJCSE1q1bM27cOAIDA+/kU76mzz77jMqVKzN9+nR++uknSpUqxciRIxk7dmymcTd6PIoUKcKqVat44403mDNnDl9//TUBAQFUr149z5+biIiIiIiIiEhhYXHmxu/W5YbExsYSGBhITEwMAdks6JWUlMThw4epVKkSPj4+bojwznE4HFkWEpPCpSC9nguq3JgRLyJ3jnJUxPyUpyLmphwVMb/CkKfXqwemUxVN8sTt9nUVkdy3b98+d4cgItegHBUxP+WpiLkpR0XMT3maQUVbyRNqJC1ifvHx8e4OQUSuQTkqYn7KUxFzU46KmJ/yNIOKtpInbDabu0MQkevw9/d3dwgicg3KURHzU56KmJtyVMT8lKcZVLSVPOHt7e3uEETkOqpWreruEETkGpSjIuanPBUxN+WoiPkpTzOoaCt5IiEhwd0hiMh1bNu2zd0hiMg1KEdFzE95KmJuylER81OeZlDRVkRERERERERERMREVLTNB5xOp7tDuG1eXl7uDkHcrCC8jgu6cuXKuTsEEbkG5aiI+SlPRcxNOSpifsrTDCrampinpycWi6VArJxnsVjcHYK4WXqLDE9PTzdHIjmxWnVKEDEz5aiI+SlPRcxNOSpifsrTDB7uDkByZrPZCAwM5OzZsyQnJxMQEICHh0e+LIDGx8fj5+fn7jDEDZxOJwkJCZw5c4agoCBsNpu7Q5IcHD16lFKlSrk7DBHJgXJUxPyUpyLmphwVMT/laQYVbU2uVKlS+Pr6cubMGWJjY90dzi1LTk7G29vb3WGIGwUFBemNV0RERERERETkBlicajTpNrGxsQQGBhITE0NAQMA1xzqdTux2O2lpaXkU3Z2VlJSEj4+Pu8MQN/H09NQM23wgMTERX19fd4chIjlQjoqYn/JUxNyUoyLmVxjy9EbrgZppm09YLBY8PDzw8Mif/8sOHTpE7dq13R2GiFzD4cOHlaciJqYcFTE/5amIuSlHRcxPeZpB3X0lT1y6dMndIYjIdShPRcxNOSpifspTEXNTjoqYn/I0g4q2kicK+tR2kYJAeSpibspREfNTnoqYm3JUxPyUpxnU09aNbqanbX6XmpqKp6enu8MQkWtQnoqYm3JUxPyUpyLmphwVMb/CkKc3Wg/UTFvJE1u3bnV3CCJyHcpTEXNTjoqYn/JUxNyUoyLmpzzNkD9XtSog0ic5x8bGujmS3BcfH18onqdIfqY8FTE35aiI+SlPRcxNOSpifoUhT9Of3/WaH6ho60bpzZXLlSvn5khEREREREREREQkr1y6dInAwMAcr1dPWzdyOBycPHmSokWLYrFY3B1OromNjaVcuXIcP368wPfuFcmvlKci5qYcFTE/5amIuSlHRcyvsOSp0+nk0qVLlClTBqs15861mmnrRlarlbJly7o7jDwTEBBQoJNOpCBQnoqYm3JUxPyUpyLmphwVMb/CkKfXmmGbTguRiYiIiIiIiIiIiJiIirYiIiIiIiIiIiIiJqKireQ6b29vxo4di7e3t7tDEZEcKE9FzE05KmJ+ylMRc1OOipif8jQzLUQmIiIiIiIiIiIiYiKaaSsiIiIiIiIiIiJiIiraioiIiIiIiIiIiJiIirYiIiIiIiIiIiIiJqKirYiIiIiIiIiIiIiJqGgrIiIiIiIiIiIiYiIq2oqIiIiIiIiIiIiYiIq2IiIiIiIityk5OdndIYiIiEgBoqKt5LpLly6RkJDg7jBEJAfHjh1jz5497g5DRK7h0KFDrF692t1hiEgO9u7dy+jRo0lNTXV3KCKSg5SUFOLj490dhojcBKfT6e4Q3EpFW8lV+/bto2XLlnz33Xcq3IqY0G+//UaTJk34/fff3R2KiORgx44dtGzZkq+//pozZ864OxwRucqOHTto2LAhkydPZunSpe4OR0SysXv3bgYNGkTbtm158skn2bFjh7tDEpErHDhwgEmTJvHiiy8yffp0zp49C4DFYinUhVsVbSVXff311+zcuZPRo0fz448/kpSUlOn6wpx8Iu62fft2WrVqxcCBA+nTp4+7wxGRbBw+fJjOnTszcOBAPv30U0JDQ7OM0blUxH22b99OeHg4jz/+OP3792fWrFkkJCQoL0VMZNeuXbRs2RJfX1969uzJggUL+PzzzzONUc6KuM/vv/9OWFgYq1ev5vDhw/z973+nX79+/Pzzz0DhLtx6uDsAKdjatGkDQFpaGo8//jh2u51HH30Ui8UC4PqviOStPXv2cM899zBixAj+9a9/kZaWxtq1a7l48SLFixenVatW7g5RRIA1a9Zwzz338NZbb5GamsrkyZPZt28fZcqUoV27drRt29b1h6zOqSJ5a+vWrbRp04bnnnuOCRMm8N577zFmzBhOnjxJ1apVlZciJnDp0iVGjBjB448/zltvvQVAyZIl+d///kdcXBz+/v4AOpeKuElMTAxDhgxhyJAhvPHGG4DxWbVevXrExsYSHR3NoEGDCm1uqmgrue6nn35i165dREdHM3ToUIKCgli0aBG1atXimWeecXd4IoWK0+kkNTWVUaNG4efnR48ePQDo3bs3x44d49SpU1y4cIEnn3ySMWPGZDurT0Tyzm+//UZiYiIAnTp1IiUlhQoVKjBnzhyioqJ4+OGHGTp0aKH9Q1bEXS5evEirVq0YOnQoEyZMAOCpp57i22+/Zfz48UyfPl15KWICFouF2NhYqlev7tq3fft2tm7dSoMGDbj77rtp3769zqUibpKamkpSUhKdOnXC6XSSmJhItWrVuOeee4iNjeWbb76hcePG1K1b192huoWKtnJH2e12bDYbDocDq9VKWFgYISEhJCQkMG3aNPz8/HjggQcoWrQokZGR7g5XpNBxOBx4eXkxevRoRo8ezdixYzl69CgVK1bkyy+/pHjx4vz+++/cf//9BAQEuL7tFJG8k34uBahfvz5Hjx7lu+++w8PDg9mzZ1OyZElOnTrFyy+/zI8//ki/fv0oXry4m6MWKTzsdjvFihVjzZo13H333YDxpajVaqVTp078/PPPnDt3jhIlSmjmnoibpJ9L4+LiiI6OZt26dZQsWZLNmzfzxRdf8OabbxISEsLChQuZNWsW4eHhrnwWkdyXnqMxMTHs3r2bU6dOYbFYKFKkCMeOHSMpKYmXXnqJp59+mjlz5hTaoq162sods23bNnr16kVCQgJWq/HSKlq0KImJiaxbtw4wfp7i6+tLYmIiBw8edM0eEpHct23bNnr27ElcXByNGzdm0qRJxMXFUa5cOaZOncrdd99N+fLliYiIYPLkyXz66aecOHGi0PYPEnGHK8+lAHXr1mXhwoVMmjSJgIAASpYsCUCpUqUYOXIky5cvZ8uWLe4MWaRQuTJHry7w2Gw2nnnmGY4dO8a0adMAtQITcYf0PI2Pj6dUqVJ8/PHHrFmzhi+//JL//Oc/fPrppwwfPpwHH3yQ8ePHs2XLFp1LRfLQlTlapUoV/vGPfzBo0CBeeeUV3n//ferXr0/Dhg0ZMGAAr7zyCsuWLSM+Pr5Qfi5V0VbuiO3bt3PPPfdQp04dihQpAkBKSgpOp5Nq1aqRkpLCM888w4IFC9i1axd///vfefDBB5k3b56bIxcpHNJztG7duvj7++N0OmnQoAGffvopQ4YMoUyZMkDmRRhKly5NSEiIPnCK5JGrz6VOp5MmTZowZcoUdu7cycGDBzl06JBrfEhICM2bNyc4ONiNUYsUHuk5Wrt2bdffu4BrNm1aWhqhoaEMGTKExYsXc+zYMTdGK1I4XXku9fPzw+Fw0L59e9atW8f06dMpW7Ys5cuXB4xfoAUHB9OoUSMCAwPdHLlI4XDludTPzw+A4cOH8+qrrzJr1ixmzZrF888/zyeffALA+fPncTqd+Pn5FcrPpWqPILdtx44dtGjRgmHDhvHmm2+69qf/ARsWFka3bt0oWbIk8+bNo3z58kyZMgVPT0/q16/vxshFCofsctRisZCUlEStWrWoVauWa2z6iXD//v1Ur14dh8PhlphFCpuc8jQlJYUnn3ySxMREnn/+ecaNG8cTTzxB9erV+fDDDzl58qTrSxcRyT1X5uikSZNc+1NSUvDy8gLAw8P4aNWpUyc++eQTtm7d6ioOiUjuy+5carVaSU5OJiQkhNjYWC5evMgff/xBy5YtsdvtTJ48mSNHjhAWFubm6EUKvqvPpek1o9DQUF555RWef/55UlJSMn2JcvbsWWrXrk1qaioeHh6FrnBrcRbG+cVyx5w6dYq7776bBg0asHjxYux2Oy+88AL79+/nwIEDPPXUU3h7e7N3714effRRGjZsmKlXn4jkrmvl6MGDBxkyZAidO3d2FW4PHTrE9OnT+eCDD1izZg116tRx8zMQKfhyytN9+/Zx+PBhhgwZQseOHV3n1fR+mgkJCfz000/qwSeSy27kXNqlSxdq1qzpuk1ERARxcXGsXLkSi8VS6D5kiuS16+Xp//3f/9G/f3/mz5/P0KFDady4MX5+fhw4cIB58+bpXCqSy6719276uTQiIoIaNWoAxiSizz77jGnTprFu3bpC+7lUM23ltjVv3pzjx4/z888/M23aNFJTU2nYsCEVKlTgww8/pGPHjgwdOtTVOFoFW5G8lVOOVqxYkffff5/ff/+dMWPGEBcXx6hRo9i+fTtRUVGF9sQo4g7XytP33nuPHTt28Mknn7Bu3TpOnjxJSkoK1apVo3Tp0u4OXaRQuNFzafrM2ieffJJ69eq51nkQkdx3rTz94IMP+OOPPxgzZgw//fQTS5cupVKlStx///1UqVLF3aGLFAo55WilSpX44IMP2LVrF2PGjCEgIIBvvvmGqKgoVq1aVbg/lzpFbtPJkyedjz76qNPX19fZsWNH57lz51zXffPNN86goCDnwoUL3RihSOF2rRydMWOGMygoyLlo0SKn0+l0RkVFOQ8fPuymSEUKr2vl6bfffusMCAhwzp8/340RihRuN3Iu1d+7Iu51vXNpUFCQzqUibnQj59IFCxa4xp4+fdpdoZqG2iPIHXHy5Ek+/PBDOnToQLt27Vy9SQCqVavG/fffz1tvveXmKEUKL+WoiPkpT0XMTTkqYn7Xy9NevXrx9ttvuzlKkcJLOXpz1B5B7ogyZcrw8ssv4+PjAxiLpzidTi5cuECJEiVo2LChewMUKeSul6MNGjRwc4QionOpiLkpR0XM73p5qt61Iu6lHL05KtrKHRMQEJDpssVi4f333+fcuXO0aNHCTVGJSLpr5WjLli3dFJWIXEnnUhFzU46KmJ/yVMTclKM3TkVbyRWzZ88mKiqKOXPmsHz5cipUqODukETkCspREfNTnoqYm3JUxPyUpyLmphy9Ni1nKrmidu3a/Pnnn/zvf//T9HYRE1KOipif8lTE3JSjIuanPBUxN+XotWkhMsk1KSkpeHl5uTsMEcmBclTE/JSnIuamHBUxP+WpiLkpR3Omoq2IiIiIiIiIiIiIiag9goiIiIiIiIiIiIiJqGgrIiIiIiIiIiIiYiIq2oqIiIiIiIiIiIiYiIq2IiIiIiIiIiIiIiaioq2IiIiIiIiIiIiIiahoKyIiIiIiIiIiImIiKtqKiIiIiBQCR44cwWKxMH36dHeHIiIiIiLXoaKtiIiIiBRKFovlhraVK1e6O1QRERERKWQ83B2AiIiIiIg7fPPNN5kuf/3110RGRmbZX6tWrbwMS0RERERERVsRERERKZwGDhyY6fKGDRuIjIzMsl9EREREJK+pPYKIiIiISA6+/PJL2rVrR2hoKN7e3tSuXZupU6dmGVexYkW6devGmjVraNasGT4+PlSuXJmvv/46y9gdO3bQunVrfH19KVu2LBMmTODLL7/EYrFw5MgR1ziHw8Frr71GmTJlKFKkCG3btuWPP/6gYsWKDB482DXuwoULvPDCC9SrVw9/f38CAgK477772L59e24cEhERERHJA5ppKyIiIiKSg6lTp1KnTh169OiBh4cH8+bN46mnnsLhcPD0009nGnvgwAH69OnD448/zqBBg/jiiy8YPHgwjRs3pk6dOgD8+eeftG3bFovFwsiRI/Hz8+Ozzz7D29s7y2OPHDmSt956i+7du9O5c2e2b99O586dSUpKyjTu0KFD/Pe//6Vv375UqlSJ06dP88knn9C6dWv++OMPypQpk3sHSERERERyhYq2IiIiIiI5WLVqFb6+vq7Lw4YNo0uXLkyePDlL0Xbv3r2sXr2aVq1aAdCvXz/KlSvHl19+yTvvvAPApEmTuHjxIlu3bqVhw4YAPPbYY1SrVi3TfZ0+fZrJkyfTq1cvfvrpJ9f+cePG8dprr2UaW69ePfbt24fVmvEjukceeYSaNWvy+eef8+qrr972cRARERGRvKX2CCIiIiIiObiyYBsTE8O5c+do3bo1hw4dIiYmJtPY2rVruwq2ACVKlKBGjRocOnTItW/x4sU0b97cVbAFCA4O5uGHH850X8uXLyctLY2nnnoq0/7hw4dnidHb29tVsLXb7Zw/fx5/f39q1KjB1q1bb/5Ji4iIiIjbqWgrIiIiIpKDtWvX0qFDB/z8/AgKCqJEiRKMGjUKIEvRtnz58lluX6xYMS5evOi6fPToUapWrZpl3NX7jh49mu3+4OBgihUrlmmfw+Hg3XffpVq1anh7exMSEkKJEiXYsWNHlhhFREREJH9Q0VZEREREJBsHDx6kffv2nDt3jsmTJ7NgwQIiIyN59tlnAaNYeiWbzZbt/TidzlyN84033uC5557j3nvv5dtvv2XJkiVERkZSp06dLDGKiIiISP6gnrYiIiIiItmYN28eycnJ/PLLL5lm0UZFRd3yfVaoUIEDBw5k2X/1vgoVKrj2V6pUybX//PnzmWbuAsydO5e2bdvy+eefZ9ofHR1NSEjILccqIiIiIu6jmbYiIiIiItlInzl75UzZmJgYvvzyy1u+z86dO7N+/Xq2bdvm2nfhwgVmzJiRaVz79u3x8PBg6tSpmfZ/+OGH2cZ59WzeOXPm8Oeff95ynCIiIiLiXpppKyIiIiKSjU6dOuHl5UX37t0ZMmQIcXFxfPrpp4SGhvLXX3/d0n2++OKLfPvtt3Ts2JHhw4fj5+fHZ599Rvny5blw4QIWiwWAkiVL8swzz/Dvf/+bHj160KVLF7Zv386iRYsICQlxjQPo1q0br7/+Oo899hj33HMPO3fuZMaMGVSuXPmOHAcRERERyXuaaSsiIiIiko0aNWowd+5cLBYLL7zwAtOmTePJJ5/kmWeeueX7LFeuHFFRUdSqVYs33niDKVOmMGjQIP72t78B4OPj4xo7adIkXn31VTZt2sQLL7zAgQMHWLp0KU6nM9O4UaNG8fzzz7NkyRKeeeYZtm7dyoIFCyhXrtytP3kRERERcSuLM7dXRhARERERkWsaMWIEn3zyCXFxcTkuaAZGn9pixYoxYcIERo8enYcRioiIiEhe0kxbEREREZE8lJiYmOny+fPn+eabb2jZsmWmgu3V4wCmTJkCQJs2bXIzRBERERFxM/W0FRERERHJQ82bN6dNmzbUqlWL06dP8/nnnxMbG8urr76aadx3333H9OnTiYiIwN/fnzVr1jBr1iw6depEixYt3BS9iIiIiOQFFW1FRERERPJQREQEc+fO5T//+Q8Wi4VGjRrx+eefc++992YaV79+fTw8PHjrrbeIjY11LU42YcIEN0UuIiIiInlFPW1FRERERERERERETEQ9bUVERERERERERERMREVbERERERERERERERNR0VZERERERERERETERFS0FRERERERERERETERFW1FRERERERERERETERFWxERERERERERERETUdFWRERERERERERExERUtBURERERERERERExkf8Hh22NaHktW2cAAAAASUVORK5CYII=\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OCsYjzge9OVe",
        "outputId": "a48d9153-15a5-4ffd-ac08-8b2cceb261a7"
      },
      "source": [
        "from sklearn.metrics import mean_squared_error\n",
        "from math import sqrt\n",
        "rmse=sqrt(mean_squared_error(test['Produksi'],test['Predictions']))\n",
        "print(f\"RMSE Model LSTM: {rmse:.2f}\")"
      ],
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "RMSE Model LSTM: 83818.69\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def mean_absolute_percentage_error(y_true, y_pred):\n",
        "    y_true, y_pred = np.array(y_true), np.array(y_pred)\n",
        "    return np.mean(np.abs((y_true - y_pred) / y_true)) * 100\n",
        "\n",
        "# Gunakan nilai sebenarnya dari data test dan prediksi model:\n",
        "y_true = test['Produksi'].values\n",
        "y_pred = test['Predictions'].values\n",
        "\n",
        "mape = mean_absolute_percentage_error(y_true, y_pred)\n",
        "print(f\"MAPE Model LSTM: {mape:.2f}%\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0y8tGeJgLFR8",
        "outputId": "be6b6809-0aae-4e92-9830-f6eed282a4bc"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "MAPE Model LSTM: 12.68%\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# prompt: evaluas mae-nya juga\n",
        "\n",
        "# Evaluasi MAE (Mean Absolute Error)\n",
        "from sklearn.metrics import mean_absolute_error\n",
        "\n",
        "mae = mean_absolute_error(y_true, y_pred)\n",
        "print(f\"MAE Model LSTM: {mae:.2f}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YMHlVmMH-vyM",
        "outputId": "26eea9f6-01e9-47c3-ff3f-61c260dd5c8c"
      },
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "MAE Model LSTM: 63719.99\n"
          ]
        }
      ]
    }
  ]
}